aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/arch/riscv/include
diff options
context:
space:
mode:
Diffstat (limited to 'arch/riscv/include')
-rw-r--r--arch/riscv/include/asm/Kbuild9
-rw-r--r--arch/riscv/include/asm/acenv.h11
-rw-r--r--arch/riscv/include/asm/acpi.h99
-rw-r--r--arch/riscv/include/asm/alternative-macros.h158
-rw-r--r--arch/riscv/include/asm/alternative.h32
-rw-r--r--arch/riscv/include/asm/arch_hweight.h78
-rw-r--r--arch/riscv/include/asm/archrandom.h72
-rw-r--r--arch/riscv/include/asm/asm-extable.h21
-rw-r--r--arch/riscv/include/asm/asm-prototypes.h32
-rw-r--r--arch/riscv/include/asm/asm.h129
-rw-r--r--arch/riscv/include/asm/assembler.h82
-rw-r--r--arch/riscv/include/asm/atomic.h235
-rw-r--r--arch/riscv/include/asm/barrier.h65
-rw-r--r--arch/riscv/include/asm/bitops.h223
-rw-r--r--arch/riscv/include/asm/bugs.h22
-rw-r--r--arch/riscv/include/asm/cache.h18
-rw-r--r--arch/riscv/include/asm/cacheflush.h74
-rw-r--r--arch/riscv/include/asm/cfi.h40
-rw-r--r--arch/riscv/include/asm/checksum.h92
-rw-r--r--arch/riscv/include/asm/cmpxchg.h625
-rw-r--r--arch/riscv/include/asm/compat.h20
-rw-r--r--arch/riscv/include/asm/cpu.h8
-rw-r--r--arch/riscv/include/asm/cpu_ops.h15
-rw-r--r--arch/riscv/include/asm/cpu_ops_sbi.h2
-rw-r--r--arch/riscv/include/asm/cpufeature-macros.h66
-rw-r--r--arch/riscv/include/asm/cpufeature.h153
-rw-r--r--arch/riscv/include/asm/crash_reserve.h11
-rw-r--r--arch/riscv/include/asm/csr.h217
-rw-r--r--arch/riscv/include/asm/dma-noncoherent.h28
-rw-r--r--arch/riscv/include/asm/dmi.h24
-rw-r--r--arch/riscv/include/asm/efi.h25
-rw-r--r--arch/riscv/include/asm/elf.h47
-rw-r--r--arch/riscv/include/asm/entry-common.h43
-rw-r--r--arch/riscv/include/asm/errata_list.h76
-rw-r--r--arch/riscv/include/asm/exec.h8
-rw-r--r--arch/riscv/include/asm/extable.h4
-rw-r--r--arch/riscv/include/asm/fence.h11
-rw-r--r--arch/riscv/include/asm/fixmap.h8
-rw-r--r--arch/riscv/include/asm/fpu.h16
-rw-r--r--arch/riscv/include/asm/ftrace.h220
-rw-r--r--arch/riscv/include/asm/futex.h4
-rw-r--r--arch/riscv/include/asm/gpr-num.h8
-rw-r--r--arch/riscv/include/asm/hugetlb.h51
-rw-r--r--arch/riscv/include/asm/hwcap.h141
-rw-r--r--arch/riscv/include/asm/hwprobe.h44
-rw-r--r--arch/riscv/include/asm/image.h2
-rw-r--r--arch/riscv/include/asm/insn-def.h272
-rw-r--r--arch/riscv/include/asm/insn.h431
-rw-r--r--arch/riscv/include/asm/io.h29
-rw-r--r--arch/riscv/include/asm/irq.h64
-rw-r--r--arch/riscv/include/asm/irq_stack.h33
-rw-r--r--arch/riscv/include/asm/irq_work.h2
-rw-r--r--arch/riscv/include/asm/irqflags.h1
-rw-r--r--arch/riscv/include/asm/jump_label.h62
-rw-r--r--arch/riscv/include/asm/kasan.h4
-rw-r--r--arch/riscv/include/asm/kexec.h11
-rw-r--r--arch/riscv/include/asm/kfence.h41
-rw-r--r--arch/riscv/include/asm/kgdb.h9
-rw-r--r--arch/riscv/include/asm/kprobes.h13
-rw-r--r--arch/riscv/include/asm/kvm_aia.h171
-rw-r--r--arch/riscv/include/asm/kvm_host.h156
-rw-r--r--arch/riscv/include/asm/kvm_nacl.h245
-rw-r--r--arch/riscv/include/asm/kvm_vcpu_fp.h8
-rw-r--r--arch/riscv/include/asm/kvm_vcpu_insn.h48
-rw-r--r--arch/riscv/include/asm/kvm_vcpu_pmu.h132
-rw-r--r--arch/riscv/include/asm/kvm_vcpu_sbi.h73
-rw-r--r--arch/riscv/include/asm/kvm_vcpu_timer.h10
-rw-r--r--arch/riscv/include/asm/kvm_vcpu_vector.h78
-rw-r--r--arch/riscv/include/asm/membarrier.h50
-rw-r--r--arch/riscv/include/asm/mmio.h17
-rw-r--r--arch/riscv/include/asm/mmiowb.h2
-rw-r--r--arch/riscv/include/asm/mmu.h21
-rw-r--r--arch/riscv/include/asm/mmu_context.h13
-rw-r--r--arch/riscv/include/asm/mmzone.h13
-rw-r--r--arch/riscv/include/asm/module.h16
-rw-r--r--arch/riscv/include/asm/page.h114
-rw-r--r--arch/riscv/include/asm/paravirt.h28
-rw-r--r--arch/riscv/include/asm/paravirt_api_clock.h1
-rw-r--r--arch/riscv/include/asm/parse_asm.h219
-rw-r--r--arch/riscv/include/asm/pci.h32
-rw-r--r--arch/riscv/include/asm/perf_event.h10
-rw-r--r--arch/riscv/include/asm/pgalloc.h70
-rw-r--r--arch/riscv/include/asm/pgtable-32.h3
-rw-r--r--arch/riscv/include/asm/pgtable-64.h99
-rw-r--r--arch/riscv/include/asm/pgtable-bits.h8
-rw-r--r--arch/riscv/include/asm/pgtable.h509
-rw-r--r--arch/riscv/include/asm/processor.h156
-rw-r--r--arch/riscv/include/asm/ptdump.h22
-rw-r--r--arch/riscv/include/asm/ptrace.h28
-rw-r--r--arch/riscv/include/asm/runtime-const.h268
-rw-r--r--arch/riscv/include/asm/sbi.h353
-rw-r--r--arch/riscv/include/asm/scs.h54
-rw-r--r--arch/riscv/include/asm/sections.h1
-rw-r--r--arch/riscv/include/asm/semihost.h26
-rw-r--r--arch/riscv/include/asm/set_memory.h6
-rw-r--r--arch/riscv/include/asm/simd.h64
-rw-r--r--arch/riscv/include/asm/smp.h47
-rw-r--r--arch/riscv/include/asm/sparsemem.h2
-rw-r--r--arch/riscv/include/asm/spinlock.h50
-rw-r--r--arch/riscv/include/asm/stackprotector.h10
-rw-r--r--arch/riscv/include/asm/stacktrace.h10
-rw-r--r--arch/riscv/include/asm/string.h12
-rw-r--r--arch/riscv/include/asm/suspend.h31
-rw-r--r--arch/riscv/include/asm/switch_to.h59
-rw-r--r--arch/riscv/include/asm/sync_core.h29
-rw-r--r--arch/riscv/include/asm/syscall.h50
-rw-r--r--arch/riscv/include/asm/syscall_table.h7
-rw-r--r--arch/riscv/include/asm/syscall_wrapper.h108
-rw-r--r--arch/riscv/include/asm/text-patching.h (renamed from arch/riscv/include/asm/patch.h)6
-rw-r--r--arch/riscv/include/asm/thread_info.h69
-rw-r--r--arch/riscv/include/asm/timex.h2
-rw-r--r--arch/riscv/include/asm/tlb.h8
-rw-r--r--arch/riscv/include/asm/tlbbatch.h15
-rw-r--r--arch/riscv/include/asm/tlbflush.h60
-rw-r--r--arch/riscv/include/asm/topology.h26
-rw-r--r--arch/riscv/include/asm/trace.h54
-rw-r--r--arch/riscv/include/asm/uaccess.h263
-rw-r--r--arch/riscv/include/asm/unistd.h13
-rw-r--r--arch/riscv/include/asm/uprobes.h15
-rw-r--r--arch/riscv/include/asm/vdso.h8
-rw-r--r--arch/riscv/include/asm/vdso/arch_data.h17
-rw-r--r--arch/riscv/include/asm/vdso/getrandom.h30
-rw-r--r--arch/riscv/include/asm/vdso/gettimeofday.h22
-rw-r--r--arch/riscv/include/asm/vdso/processor.h7
-rw-r--r--arch/riscv/include/asm/vdso/vsyscall.h13
-rw-r--r--arch/riscv/include/asm/vector.h440
-rw-r--r--arch/riscv/include/asm/vendor_extensions.h104
-rw-r--r--arch/riscv/include/asm/vendor_extensions/andes.h19
-rw-r--r--arch/riscv/include/asm/vendor_extensions/sifive.h16
-rw-r--r--arch/riscv/include/asm/vendor_extensions/sifive_hwprobe.h19
-rw-r--r--arch/riscv/include/asm/vendor_extensions/thead.h47
-rw-r--r--arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h19
-rw-r--r--arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h37
-rw-r--r--arch/riscv/include/asm/vendorid_list.h2
-rw-r--r--arch/riscv/include/asm/vmalloc.h21
-rw-r--r--arch/riscv/include/asm/word-at-a-time.h30
-rw-r--r--arch/riscv/include/asm/xip_fixup.h32
-rw-r--r--arch/riscv/include/asm/xor.h68
-rw-r--r--arch/riscv/include/uapi/asm/Kbuild2
-rw-r--r--arch/riscv/include/uapi/asm/auxvec.h5
-rw-r--r--arch/riscv/include/uapi/asm/elf.h5
-rw-r--r--arch/riscv/include/uapi/asm/hwcap.h1
-rw-r--r--arch/riscv/include/uapi/asm/hwprobe.h114
-rw-r--r--arch/riscv/include/uapi/asm/kvm.h235
-rw-r--r--arch/riscv/include/uapi/asm/ptrace.h50
-rw-r--r--arch/riscv/include/uapi/asm/setup.h8
-rw-r--r--arch/riscv/include/uapi/asm/sigcontext.h22
-rw-r--r--arch/riscv/include/uapi/asm/ucontext.h12
-rw-r--r--arch/riscv/include/uapi/asm/unistd.h32
-rw-r--r--arch/riscv/include/uapi/asm/vendor/sifive.h6
-rw-r--r--arch/riscv/include/uapi/asm/vendor/thead.h3
151 files changed, 8154 insertions, 1703 deletions
diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild
index 504f8b7e72d4..bd5fc9403295 100644
--- a/arch/riscv/include/asm/Kbuild
+++ b/arch/riscv/include/asm/Kbuild
@@ -1,11 +1,18 @@
# SPDX-License-Identifier: GPL-2.0
+syscall-y += syscall_table_32.h
+syscall-y += syscall_table_64.h
+
generic-y += early_ioremap.h
generic-y += flat.h
+generic-y += fprobe.h
generic-y += kvm_para.h
+generic-y += mmzone.h
+generic-y += mcs_spinlock.h
generic-y += parport.h
-generic-y += spinlock.h
generic-y += spinlock_types.h
+generic-y += ticket_spinlock.h
generic-y += qrwlock.h
generic-y += qrwlock_types.h
+generic-y += qspinlock.h
generic-y += user.h
generic-y += vmlinux.lds.h
diff --git a/arch/riscv/include/asm/acenv.h b/arch/riscv/include/asm/acenv.h
new file mode 100644
index 000000000000..43ae2e32c779
--- /dev/null
+++ b/arch/riscv/include/asm/acenv.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * RISC-V specific ACPICA environments and implementation
+ */
+
+#ifndef _ASM_ACENV_H
+#define _ASM_ACENV_H
+
+/* This header is required unconditionally by the ACPI core */
+
+#endif /* _ASM_ACENV_H */
diff --git a/arch/riscv/include/asm/acpi.h b/arch/riscv/include/asm/acpi.h
new file mode 100644
index 000000000000..6e13695120bc
--- /dev/null
+++ b/arch/riscv/include/asm/acpi.h
@@ -0,0 +1,99 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2013-2014, Linaro Ltd.
+ * Author: Al Stone <al.stone@linaro.org>
+ * Author: Graeme Gregory <graeme.gregory@linaro.org>
+ * Author: Hanjun Guo <hanjun.guo@linaro.org>
+ *
+ * Copyright (C) 2021-2023, Ventana Micro Systems Inc.
+ * Author: Sunil V L <sunilvl@ventanamicro.com>
+ */
+
+#ifndef _ASM_ACPI_H
+#define _ASM_ACPI_H
+
+/* Basic configuration for ACPI */
+#ifdef CONFIG_ACPI
+
+typedef u64 phys_cpuid_t;
+#define PHYS_CPUID_INVALID INVALID_HARTID
+
+/* ACPI table mapping after acpi_permanent_mmap is set */
+void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size);
+#define acpi_os_ioremap acpi_os_ioremap
+
+#define acpi_strict 1 /* No out-of-spec workarounds on RISC-V */
+extern int acpi_disabled;
+extern int acpi_noirq;
+extern int acpi_pci_disabled;
+
+static inline void disable_acpi(void)
+{
+ acpi_disabled = 1;
+ acpi_pci_disabled = 1;
+ acpi_noirq = 1;
+}
+
+static inline void enable_acpi(void)
+{
+ acpi_disabled = 0;
+ acpi_pci_disabled = 0;
+ acpi_noirq = 0;
+}
+
+/*
+ * The ACPI processor driver for ACPI core code needs this macro
+ * to find out whether this cpu was already mapped (mapping from CPU hardware
+ * ID to CPU logical ID) or not.
+ */
+#define cpu_physical_id(cpu) cpuid_to_hartid_map(cpu)
+
+/*
+ * Since MADT must provide at least one RINTC structure, the
+ * CPU will be always available in MADT on RISC-V.
+ */
+static inline bool acpi_has_cpu_in_madt(void)
+{
+ return true;
+}
+
+static inline void arch_fix_phys_package_id(int num, u32 slot) { }
+
+void acpi_init_rintc_map(void);
+struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu);
+static inline u32 get_acpi_id_for_cpu(int cpu)
+{
+ return acpi_cpu_get_madt_rintc(cpu)->uid;
+}
+
+int acpi_get_riscv_isa(struct acpi_table_header *table,
+ unsigned int cpu, const char **isa);
+
+void acpi_get_cbo_block_size(struct acpi_table_header *table, u32 *cbom_size,
+ u32 *cboz_size, u32 *cbop_size);
+#else
+static inline void acpi_init_rintc_map(void) { }
+static inline struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu)
+{
+ return NULL;
+}
+
+static inline int acpi_get_riscv_isa(struct acpi_table_header *table,
+ unsigned int cpu, const char **isa)
+{
+ return -EINVAL;
+}
+
+static inline void acpi_get_cbo_block_size(struct acpi_table_header *table,
+ u32 *cbom_size, u32 *cboz_size,
+ u32 *cbop_size) { }
+
+#endif /* CONFIG_ACPI */
+
+#ifdef CONFIG_ACPI_NUMA
+void acpi_map_cpus_to_nodes(void);
+#else
+static inline void acpi_map_cpus_to_nodes(void) { }
+#endif /* CONFIG_ACPI_NUMA */
+
+#endif /*_ASM_ACPI_H*/
diff --git a/arch/riscv/include/asm/alternative-macros.h b/arch/riscv/include/asm/alternative-macros.h
index ec2f3f1b836f..231d777d936c 100644
--- a/arch/riscv/include/asm/alternative-macros.h
+++ b/arch/riscv/include/asm/alternative-macros.h
@@ -6,18 +6,18 @@
#ifdef __ASSEMBLY__
-.macro ALT_ENTRY oldptr newptr vendor_id errata_id new_len
- RISCV_PTR \oldptr
- RISCV_PTR \newptr
- REG_ASM \vendor_id
- REG_ASM \new_len
- .word \errata_id
+.macro ALT_ENTRY oldptr newptr vendor_id patch_id new_len
+ .4byte \oldptr - .
+ .4byte \newptr - .
+ .2byte \vendor_id
+ .2byte \new_len
+ .4byte \patch_id
.endm
-.macro ALT_NEW_CONTENT vendor_id, errata_id, enable = 1, new_c : vararg
+.macro ALT_NEW_CONTENT vendor_id, patch_id, enable = 1, new_c
.if \enable
.pushsection .alternative, "a"
- ALT_ENTRY 886b, 888f, \vendor_id, \errata_id, 889f - 888f
+ ALT_ENTRY 886b, 888f, \vendor_id, \patch_id, 889f - 888f
.popsection
.subsection 1
888 :
@@ -33,7 +33,7 @@
.endif
.endm
-.macro __ALTERNATIVE_CFG old_c, new_c, vendor_id, errata_id, enable
+.macro ALTERNATIVE_CFG old_c, new_c, vendor_id, patch_id, enable
886 :
.option push
.option norvc
@@ -41,50 +41,34 @@
\old_c
.option pop
887 :
- ALT_NEW_CONTENT \vendor_id, \errata_id, \enable, \new_c
+ ALT_NEW_CONTENT \vendor_id, \patch_id, \enable, "\new_c"
.endm
-#define _ALTERNATIVE_CFG(old_c, new_c, vendor_id, errata_id, CONFIG_k) \
- __ALTERNATIVE_CFG old_c, new_c, vendor_id, errata_id, IS_ENABLED(CONFIG_k)
-
-.macro __ALTERNATIVE_CFG_2 old_c, new_c_1, vendor_id_1, errata_id_1, enable_1, \
- new_c_2, vendor_id_2, errata_id_2, enable_2
-886 :
- .option push
- .option norvc
- .option norelax
- \old_c
- .option pop
-887 :
- ALT_NEW_CONTENT \vendor_id_1, \errata_id_1, \enable_1, \new_c_1
- ALT_NEW_CONTENT \vendor_id_2, \errata_id_2, \enable_2, \new_c_2
+.macro ALTERNATIVE_CFG_2 old_c, new_c_1, vendor_id_1, patch_id_1, enable_1, \
+ new_c_2, vendor_id_2, patch_id_2, enable_2
+ ALTERNATIVE_CFG "\old_c", "\new_c_1", \vendor_id_1, \patch_id_1, \enable_1
+ ALT_NEW_CONTENT \vendor_id_2, \patch_id_2, \enable_2, "\new_c_2"
.endm
-#define _ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, errata_id_1, \
- CONFIG_k_1, \
- new_c_2, vendor_id_2, errata_id_2, \
- CONFIG_k_2) \
- __ALTERNATIVE_CFG_2 old_c, new_c_1, vendor_id_1, errata_id_1, \
- IS_ENABLED(CONFIG_k_1), \
- new_c_2, vendor_id_2, errata_id_2, \
- IS_ENABLED(CONFIG_k_2)
+#define __ALTERNATIVE_CFG(...) ALTERNATIVE_CFG __VA_ARGS__
+#define __ALTERNATIVE_CFG_2(...) ALTERNATIVE_CFG_2 __VA_ARGS__
#else /* !__ASSEMBLY__ */
#include <asm/asm.h>
#include <linux/stringify.h>
-#define ALT_ENTRY(oldptr, newptr, vendor_id, errata_id, newlen) \
- RISCV_PTR " " oldptr "\n" \
- RISCV_PTR " " newptr "\n" \
- REG_ASM " " vendor_id "\n" \
- REG_ASM " " newlen "\n" \
- ".word " errata_id "\n"
+#define ALT_ENTRY(oldptr, newptr, vendor_id, patch_id, newlen) \
+ ".4byte ((" oldptr ") - .) \n" \
+ ".4byte ((" newptr ") - .) \n" \
+ ".2byte " vendor_id "\n" \
+ ".2byte " newlen "\n" \
+ ".4byte " patch_id "\n"
-#define ALT_NEW_CONTENT(vendor_id, errata_id, enable, new_c) \
+#define ALT_NEW_CONTENT(vendor_id, patch_id, enable, new_c) \
".if " __stringify(enable) " == 1\n" \
".pushsection .alternative, \"a\"\n" \
- ALT_ENTRY("886b", "888f", __stringify(vendor_id), __stringify(errata_id), "889f - 888f") \
+ ALT_ENTRY("886b", "888f", __stringify(vendor_id), __stringify(patch_id), "889f - 888f") \
".popsection\n" \
".subsection 1\n" \
"888 :\n" \
@@ -99,7 +83,7 @@
".previous\n" \
".endif\n"
-#define __ALTERNATIVE_CFG(old_c, new_c, vendor_id, errata_id, enable) \
+#define __ALTERNATIVE_CFG(old_c, new_c, vendor_id, patch_id, enable) \
"886 :\n" \
".option push\n" \
".option norvc\n" \
@@ -107,84 +91,60 @@
old_c "\n" \
".option pop\n" \
"887 :\n" \
- ALT_NEW_CONTENT(vendor_id, errata_id, enable, new_c)
+ ALT_NEW_CONTENT(vendor_id, patch_id, enable, new_c)
-#define _ALTERNATIVE_CFG(old_c, new_c, vendor_id, errata_id, CONFIG_k) \
- __ALTERNATIVE_CFG(old_c, new_c, vendor_id, errata_id, IS_ENABLED(CONFIG_k))
-
-#define __ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, errata_id_1, \
- enable_1, \
- new_c_2, vendor_id_2, errata_id_2, \
- enable_2) \
- "886 :\n" \
- ".option push\n" \
- ".option norvc\n" \
- ".option norelax\n" \
- old_c "\n" \
- ".option pop\n" \
- "887 :\n" \
- ALT_NEW_CONTENT(vendor_id_1, errata_id_1, enable_1, new_c_1) \
- ALT_NEW_CONTENT(vendor_id_2, errata_id_2, enable_2, new_c_2)
-
-#define _ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, errata_id_1, \
- CONFIG_k_1, \
- new_c_2, vendor_id_2, errata_id_2, \
- CONFIG_k_2) \
- __ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, errata_id_1, \
- IS_ENABLED(CONFIG_k_1), \
- new_c_2, vendor_id_2, errata_id_2, \
- IS_ENABLED(CONFIG_k_2))
+#define __ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, patch_id_1, enable_1, \
+ new_c_2, vendor_id_2, patch_id_2, enable_2) \
+ __ALTERNATIVE_CFG(old_c, new_c_1, vendor_id_1, patch_id_1, enable_1) \
+ ALT_NEW_CONTENT(vendor_id_2, patch_id_2, enable_2, new_c_2)
#endif /* __ASSEMBLY__ */
+#define _ALTERNATIVE_CFG(old_c, new_c, vendor_id, patch_id, CONFIG_k) \
+ __ALTERNATIVE_CFG(old_c, new_c, vendor_id, patch_id, IS_ENABLED(CONFIG_k))
+
+#define _ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, patch_id_1, CONFIG_k_1, \
+ new_c_2, vendor_id_2, patch_id_2, CONFIG_k_2) \
+ __ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, patch_id_1, IS_ENABLED(CONFIG_k_1), \
+ new_c_2, vendor_id_2, patch_id_2, IS_ENABLED(CONFIG_k_2))
+
#else /* CONFIG_RISCV_ALTERNATIVE */
#ifdef __ASSEMBLY__
-.macro __ALTERNATIVE_CFG old_c
+.macro ALTERNATIVE_CFG old_c
\old_c
.endm
-#define _ALTERNATIVE_CFG(old_c, new_c, vendor_id, errata_id, CONFIG_k) \
- __ALTERNATIVE_CFG old_c
-
-#define _ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, errata_id_1, \
- CONFIG_k_1, \
- new_c_2, vendor_id_2, errata_id_2, \
- CONFIG_k_2) \
- __ALTERNATIVE_CFG old_c
+#define __ALTERNATIVE_CFG(old_c, ...) ALTERNATIVE_CFG old_c
+#define __ALTERNATIVE_CFG_2(old_c, ...) ALTERNATIVE_CFG old_c
#else /* !__ASSEMBLY__ */
-#define __ALTERNATIVE_CFG(old_c) \
- old_c "\n"
+#define __ALTERNATIVE_CFG(old_c, ...) old_c "\n"
+#define __ALTERNATIVE_CFG_2(old_c, ...) old_c "\n"
-#define _ALTERNATIVE_CFG(old_c, new_c, vendor_id, errata_id, CONFIG_k) \
- __ALTERNATIVE_CFG(old_c)
+#endif /* __ASSEMBLY__ */
-#define _ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, errata_id_1, \
- CONFIG_k_1, \
- new_c_2, vendor_id_2, errata_id_2, \
- CONFIG_k_2) \
- __ALTERNATIVE_CFG(old_c)
+#define _ALTERNATIVE_CFG(old_c, ...) __ALTERNATIVE_CFG(old_c)
+#define _ALTERNATIVE_CFG_2(old_c, ...) __ALTERNATIVE_CFG_2(old_c)
-#endif /* __ASSEMBLY__ */
#endif /* CONFIG_RISCV_ALTERNATIVE */
/*
* Usage:
- * ALTERNATIVE(old_content, new_content, vendor_id, errata_id, CONFIG_k)
+ * ALTERNATIVE(old_content, new_content, vendor_id, patch_id, CONFIG_k)
* in the assembly code. Otherwise,
- * asm(ALTERNATIVE(old_content, new_content, vendor_id, errata_id, CONFIG_k));
+ * asm(ALTERNATIVE(old_content, new_content, vendor_id, patch_id, CONFIG_k));
*
* old_content: The old content which is probably replaced with new content.
* new_content: The new content.
* vendor_id: The CPU vendor ID.
- * errata_id: The errata ID.
- * CONFIG_k: The Kconfig of this errata. When Kconfig is disabled, the old
- * content will alwyas be executed.
+ * patch_id: The patch ID (erratum ID or cpufeature ID).
+ * CONFIG_k: The Kconfig of this patch ID. When Kconfig is disabled, the old
+ * content will always be executed.
*/
-#define ALTERNATIVE(old_content, new_content, vendor_id, errata_id, CONFIG_k) \
- _ALTERNATIVE_CFG(old_content, new_content, vendor_id, errata_id, CONFIG_k)
+#define ALTERNATIVE(old_content, new_content, vendor_id, patch_id, CONFIG_k) \
+ _ALTERNATIVE_CFG(old_content, new_content, vendor_id, patch_id, CONFIG_k)
/*
* A vendor wants to replace an old_content, but another vendor has used
@@ -193,13 +153,9 @@
* on the following sample code and then replace ALTERNATIVE() with
* ALTERNATIVE_2() to append its customized content.
*/
-#define ALTERNATIVE_2(old_content, new_content_1, vendor_id_1, \
- errata_id_1, CONFIG_k_1, \
- new_content_2, vendor_id_2, \
- errata_id_2, CONFIG_k_2) \
- _ALTERNATIVE_CFG_2(old_content, new_content_1, vendor_id_1, \
- errata_id_1, CONFIG_k_1, \
- new_content_2, vendor_id_2, \
- errata_id_2, CONFIG_k_2)
+#define ALTERNATIVE_2(old_content, new_content_1, vendor_id_1, patch_id_1, CONFIG_k_1, \
+ new_content_2, vendor_id_2, patch_id_2, CONFIG_k_2) \
+ _ALTERNATIVE_CFG_2(old_content, new_content_1, vendor_id_1, patch_id_1, CONFIG_k_1, \
+ new_content_2, vendor_id_2, patch_id_2, CONFIG_k_2)
#endif
diff --git a/arch/riscv/include/asm/alternative.h b/arch/riscv/include/asm/alternative.h
index 6511dd73e812..3c2b59b25017 100644
--- a/arch/riscv/include/asm/alternative.h
+++ b/arch/riscv/include/asm/alternative.h
@@ -6,8 +6,6 @@
#ifndef __ASM_ALTERNATIVE_H
#define __ASM_ALTERNATIVE_H
-#define ERRATA_STRING_LENGTH_MAX 32
-
#include <asm/alternative-macros.h>
#ifndef __ASSEMBLY__
@@ -15,31 +13,41 @@
#ifdef CONFIG_RISCV_ALTERNATIVE
#include <linux/init.h>
+#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/stddef.h>
#include <asm/hwcap.h>
+#define PATCH_ID_CPUFEATURE_ID(p) lower_16_bits(p)
+#define PATCH_ID_CPUFEATURE_VALUE(p) upper_16_bits(p)
+
#define RISCV_ALTERNATIVES_BOOT 0 /* alternatives applied during regular boot */
#define RISCV_ALTERNATIVES_MODULE 1 /* alternatives applied during module-init */
#define RISCV_ALTERNATIVES_EARLY_BOOT 2 /* alternatives applied before mmu start */
+/* add the relative offset to the address of the offset to get the absolute address */
+#define __ALT_PTR(a, f) ((void *)&(a)->f + (a)->f)
+#define ALT_OLD_PTR(a) __ALT_PTR(a, old_offset)
+#define ALT_ALT_PTR(a) __ALT_PTR(a, alt_offset)
+
void __init apply_boot_alternatives(void);
void __init apply_early_boot_alternatives(void);
void apply_module_alternatives(void *start, size_t length);
+void riscv_alternative_fix_offsets(void *alt_ptr, unsigned int len,
+ int patch_offset);
+
struct alt_entry {
- void *old_ptr; /* address of original instruciton or data */
- void *alt_ptr; /* address of replacement instruction or data */
- unsigned long vendor_id; /* cpu vendor id */
- unsigned long alt_len; /* The replacement size */
- unsigned int errata_id; /* The errata id */
-} __packed;
-
-struct errata_checkfunc_id {
- unsigned long vendor_id;
- bool (*func)(struct alt_entry *alt);
+ s32 old_offset; /* offset relative to original instruction or data */
+ s32 alt_offset; /* offset relative to replacement instruction or data */
+ u16 vendor_id; /* CPU vendor ID */
+ u16 alt_len; /* The replacement size */
+ u32 patch_id; /* The patch ID (erratum ID or cpufeature ID) */
};
+void andes_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
+ unsigned long archid, unsigned long impid,
+ unsigned int stage);
void sifive_errata_patch_func(struct alt_entry *begin, struct alt_entry *end,
unsigned long archid, unsigned long impid,
unsigned int stage);
diff --git a/arch/riscv/include/asm/arch_hweight.h b/arch/riscv/include/asm/arch_hweight.h
new file mode 100644
index 000000000000..0e7cdbbec8ef
--- /dev/null
+++ b/arch/riscv/include/asm/arch_hweight.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Based on arch/x86/include/asm/arch_hweight.h
+ */
+
+#ifndef _ASM_RISCV_HWEIGHT_H
+#define _ASM_RISCV_HWEIGHT_H
+
+#include <asm/alternative-macros.h>
+#include <asm/hwcap.h>
+
+#if (BITS_PER_LONG == 64)
+#define CPOPW "cpopw "
+#elif (BITS_PER_LONG == 32)
+#define CPOPW "cpop "
+#else
+#error "Unexpected BITS_PER_LONG"
+#endif
+
+static __always_inline unsigned int __arch_hweight32(unsigned int w)
+{
+#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB)
+ asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+ RISCV_ISA_EXT_ZBB, 1)
+ : : : : legacy);
+
+ asm (".option push\n"
+ ".option arch,+zbb\n"
+ CPOPW "%0, %1\n"
+ ".option pop\n"
+ : "=r" (w) : "r" (w) :);
+
+ return w;
+
+legacy:
+#endif
+ return __sw_hweight32(w);
+}
+
+static inline unsigned int __arch_hweight16(unsigned int w)
+{
+ return __arch_hweight32(w & 0xffff);
+}
+
+static inline unsigned int __arch_hweight8(unsigned int w)
+{
+ return __arch_hweight32(w & 0xff);
+}
+
+#if BITS_PER_LONG == 64
+static __always_inline unsigned long __arch_hweight64(__u64 w)
+{
+#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB)
+ asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+ RISCV_ISA_EXT_ZBB, 1)
+ : : : : legacy);
+
+ asm (".option push\n"
+ ".option arch,+zbb\n"
+ "cpop %0, %1\n"
+ ".option pop\n"
+ : "=r" (w) : "r" (w) :);
+
+ return w;
+
+legacy:
+#endif
+ return __sw_hweight64(w);
+}
+#else /* BITS_PER_LONG == 64 */
+static inline unsigned long __arch_hweight64(__u64 w)
+{
+ return __arch_hweight32((u32)w) +
+ __arch_hweight32((u32)(w >> 32));
+}
+#endif /* !(BITS_PER_LONG == 64) */
+
+#endif /* _ASM_RISCV_HWEIGHT_H */
diff --git a/arch/riscv/include/asm/archrandom.h b/arch/riscv/include/asm/archrandom.h
new file mode 100644
index 000000000000..5345360adfb9
--- /dev/null
+++ b/arch/riscv/include/asm/archrandom.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Kernel interface for the RISCV arch_random_* functions
+ *
+ * Copyright (c) 2023 Rivos Inc.
+ *
+ */
+
+#ifndef ASM_RISCV_ARCHRANDOM_H
+#define ASM_RISCV_ARCHRANDOM_H
+
+#include <asm/csr.h>
+#include <asm/processor.h>
+
+#define SEED_RETRY_LOOPS 100
+
+static inline bool __must_check csr_seed_long(unsigned long *v)
+{
+ unsigned int retry = SEED_RETRY_LOOPS, valid_seeds = 0;
+ const int needed_seeds = sizeof(long) / sizeof(u16);
+ u16 *entropy = (u16 *)v;
+
+ do {
+ /*
+ * The SEED CSR must be accessed with a read-write instruction.
+ */
+ unsigned long csr_seed = csr_swap(CSR_SEED, 0);
+ unsigned long opst = csr_seed & SEED_OPST_MASK;
+
+ switch (opst) {
+ case SEED_OPST_ES16:
+ entropy[valid_seeds++] = csr_seed & SEED_ENTROPY_MASK;
+ if (valid_seeds == needed_seeds)
+ return true;
+ break;
+
+ case SEED_OPST_DEAD:
+ pr_err_once("archrandom: Unrecoverable error\n");
+ return false;
+
+ case SEED_OPST_BIST:
+ case SEED_OPST_WAIT:
+ default:
+ cpu_relax();
+ continue;
+ }
+ } while (--retry);
+
+ return false;
+}
+
+static inline size_t __must_check arch_get_random_longs(unsigned long *v, size_t max_longs)
+{
+ return 0;
+}
+
+static inline size_t __must_check arch_get_random_seed_longs(unsigned long *v, size_t max_longs)
+{
+ if (!max_longs)
+ return 0;
+
+ /*
+ * If Zkr is supported and csr_seed_long succeeds, we return one long
+ * worth of entropy.
+ */
+ if (riscv_has_extension_likely(RISCV_ISA_EXT_ZKR) && csr_seed_long(v))
+ return 1;
+
+ return 0;
+}
+
+#endif /* ASM_RISCV_ARCHRANDOM_H */
diff --git a/arch/riscv/include/asm/asm-extable.h b/arch/riscv/include/asm/asm-extable.h
index 14be0673f5b5..0c8bfd54fc4e 100644
--- a/arch/riscv/include/asm/asm-extable.h
+++ b/arch/riscv/include/asm/asm-extable.h
@@ -6,6 +6,9 @@
#define EX_TYPE_FIXUP 1
#define EX_TYPE_BPF 2
#define EX_TYPE_UACCESS_ERR_ZERO 3
+#define EX_TYPE_LOAD_UNALIGNED_ZEROPAD 4
+
+#ifdef CONFIG_MMU
#ifdef __ASSEMBLY__
@@ -45,6 +48,11 @@
#define EX_DATA_REG_ZERO_SHIFT 5
#define EX_DATA_REG_ZERO GENMASK(9, 5)
+#define EX_DATA_REG_DATA_SHIFT 0
+#define EX_DATA_REG_DATA GENMASK(4, 0)
+#define EX_DATA_REG_ADDR_SHIFT 5
+#define EX_DATA_REG_ADDR GENMASK(9, 5)
+
#define EX_DATA_REG(reg, gpr) \
"((.L__gpr_num_" #gpr ") << " __stringify(EX_DATA_REG_##reg##_SHIFT) ")"
@@ -60,6 +68,19 @@
#define _ASM_EXTABLE_UACCESS_ERR(insn, fixup, err) \
_ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, zero)
+#define _ASM_EXTABLE_LOAD_UNALIGNED_ZEROPAD(insn, fixup, data, addr) \
+ __DEFINE_ASM_GPR_NUMS \
+ __ASM_EXTABLE_RAW(#insn, #fixup, \
+ __stringify(EX_TYPE_LOAD_UNALIGNED_ZEROPAD), \
+ "(" \
+ EX_DATA_REG(DATA, data) " | " \
+ EX_DATA_REG(ADDR, addr) \
+ ")")
+
#endif /* __ASSEMBLY__ */
+#else /* CONFIG_MMU */
+ #define _ASM_EXTABLE_UACCESS_ERR(insn, fixup, err)
+#endif /* CONFIG_MMU */
+
#endif /* __ASM_ASM_EXTABLE_H */
diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h
index ef386fcf3939..a9988bf21ec8 100644
--- a/arch/riscv/include/asm/asm-prototypes.h
+++ b/arch/riscv/include/asm/asm-prototypes.h
@@ -9,6 +9,33 @@ long long __lshrti3(long long a, int b);
long long __ashrti3(long long a, int b);
long long __ashlti3(long long a, int b);
+#ifdef CONFIG_RISCV_ISA_V
+
+#ifdef CONFIG_MMU
+asmlinkage int enter_vector_usercopy(void *dst, void *src, size_t n, bool enable_sum);
+#endif /* CONFIG_MMU */
+
+void xor_regs_2_(unsigned long bytes, unsigned long *__restrict p1,
+ const unsigned long *__restrict p2);
+void xor_regs_3_(unsigned long bytes, unsigned long *__restrict p1,
+ const unsigned long *__restrict p2,
+ const unsigned long *__restrict p3);
+void xor_regs_4_(unsigned long bytes, unsigned long *__restrict p1,
+ const unsigned long *__restrict p2,
+ const unsigned long *__restrict p3,
+ const unsigned long *__restrict p4);
+void xor_regs_5_(unsigned long bytes, unsigned long *__restrict p1,
+ const unsigned long *__restrict p2,
+ const unsigned long *__restrict p3,
+ const unsigned long *__restrict p4,
+ const unsigned long *__restrict p5);
+
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+asmlinkage void riscv_v_context_nesting_start(struct pt_regs *regs);
+asmlinkage void riscv_v_context_nesting_end(struct pt_regs *regs);
+#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */
+
+#endif /* CONFIG_RISCV_ISA_V */
#define DECLARE_DO_ERROR_INFO(name) asmlinkage void name(struct pt_regs *regs)
@@ -25,7 +52,10 @@ DECLARE_DO_ERROR_INFO(do_trap_ecall_s);
DECLARE_DO_ERROR_INFO(do_trap_ecall_m);
DECLARE_DO_ERROR_INFO(do_trap_break);
-asmlinkage unsigned long get_overflow_stack(void);
+asmlinkage void ret_from_fork_kernel(void *fn_arg, int (*fn)(void *), struct pt_regs *regs);
+asmlinkage void ret_from_fork_user(struct pt_regs *regs);
asmlinkage void handle_bad_stack(struct pt_regs *regs);
+asmlinkage void do_page_fault(struct pt_regs *regs);
+asmlinkage void do_irq(struct pt_regs *regs);
#endif /* _ASM_RISCV_PROTOTYPES_H */
diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h
index 618d7c5af1a2..a8a2af6dfe9d 100644
--- a/arch/riscv/include/asm/asm.h
+++ b/arch/riscv/include/asm/asm.h
@@ -23,9 +23,11 @@
#define REG_L __REG_SEL(ld, lw)
#define REG_S __REG_SEL(sd, sw)
#define REG_SC __REG_SEL(sc.d, sc.w)
+#define REG_AMOSWAP_AQ __REG_SEL(amoswap.d.aq, amoswap.w.aq)
#define REG_ASM __REG_SEL(.dword, .word)
#define SZREG __REG_SEL(8, 4)
#define LGREG __REG_SEL(3, 2)
+#define SRLI __REG_SEL(srliw, srli)
#if __SIZEOF_POINTER__ == 8
#ifdef __ASSEMBLY__
@@ -67,4 +69,131 @@
#error "Unexpected __SIZEOF_SHORT__"
#endif
+#ifdef __ASSEMBLY__
+#include <asm/asm-offsets.h>
+
+/* Common assembly source macros */
+
+/*
+ * NOP sequence
+ */
+.macro nops, num
+ .rept \num
+ nop
+ .endr
+.endm
+
+#ifdef CONFIG_SMP
+#ifdef CONFIG_32BIT
+#define PER_CPU_OFFSET_SHIFT 2
+#else
+#define PER_CPU_OFFSET_SHIFT 3
+#endif
+
+.macro asm_per_cpu dst sym tmp
+ REG_L \tmp, TASK_TI_CPU_NUM(tp)
+ slli \tmp, \tmp, PER_CPU_OFFSET_SHIFT
+ la \dst, __per_cpu_offset
+ add \dst, \dst, \tmp
+ REG_L \tmp, 0(\dst)
+ la \dst, \sym
+ add \dst, \dst, \tmp
+.endm
+#else /* CONFIG_SMP */
+.macro asm_per_cpu dst sym tmp
+ la \dst, \sym
+.endm
+#endif /* CONFIG_SMP */
+
+.macro load_per_cpu dst ptr tmp
+ asm_per_cpu \dst \ptr \tmp
+ REG_L \dst, 0(\dst)
+.endm
+
+#ifdef CONFIG_SHADOW_CALL_STACK
+/* gp is used as the shadow call stack pointer instead */
+.macro load_global_pointer
+.endm
+#else
+/* load __global_pointer to gp */
+.macro load_global_pointer
+.option push
+.option norelax
+ la gp, __global_pointer$
+.option pop
+.endm
+#endif /* CONFIG_SHADOW_CALL_STACK */
+
+ /* save all GPs except x1 ~ x5 */
+ .macro save_from_x6_to_x31
+ REG_S x6, PT_T1(sp)
+ REG_S x7, PT_T2(sp)
+ REG_S x8, PT_S0(sp)
+ REG_S x9, PT_S1(sp)
+ REG_S x10, PT_A0(sp)
+ REG_S x11, PT_A1(sp)
+ REG_S x12, PT_A2(sp)
+ REG_S x13, PT_A3(sp)
+ REG_S x14, PT_A4(sp)
+ REG_S x15, PT_A5(sp)
+ REG_S x16, PT_A6(sp)
+ REG_S x17, PT_A7(sp)
+ REG_S x18, PT_S2(sp)
+ REG_S x19, PT_S3(sp)
+ REG_S x20, PT_S4(sp)
+ REG_S x21, PT_S5(sp)
+ REG_S x22, PT_S6(sp)
+ REG_S x23, PT_S7(sp)
+ REG_S x24, PT_S8(sp)
+ REG_S x25, PT_S9(sp)
+ REG_S x26, PT_S10(sp)
+ REG_S x27, PT_S11(sp)
+ REG_S x28, PT_T3(sp)
+ REG_S x29, PT_T4(sp)
+ REG_S x30, PT_T5(sp)
+ REG_S x31, PT_T6(sp)
+ .endm
+
+ /* restore all GPs except x1 ~ x5 */
+ .macro restore_from_x6_to_x31
+ REG_L x6, PT_T1(sp)
+ REG_L x7, PT_T2(sp)
+ REG_L x8, PT_S0(sp)
+ REG_L x9, PT_S1(sp)
+ REG_L x10, PT_A0(sp)
+ REG_L x11, PT_A1(sp)
+ REG_L x12, PT_A2(sp)
+ REG_L x13, PT_A3(sp)
+ REG_L x14, PT_A4(sp)
+ REG_L x15, PT_A5(sp)
+ REG_L x16, PT_A6(sp)
+ REG_L x17, PT_A7(sp)
+ REG_L x18, PT_S2(sp)
+ REG_L x19, PT_S3(sp)
+ REG_L x20, PT_S4(sp)
+ REG_L x21, PT_S5(sp)
+ REG_L x22, PT_S6(sp)
+ REG_L x23, PT_S7(sp)
+ REG_L x24, PT_S8(sp)
+ REG_L x25, PT_S9(sp)
+ REG_L x26, PT_S10(sp)
+ REG_L x27, PT_S11(sp)
+ REG_L x28, PT_T3(sp)
+ REG_L x29, PT_T4(sp)
+ REG_L x30, PT_T5(sp)
+ REG_L x31, PT_T6(sp)
+ .endm
+
+/* Annotate a function as being unsuitable for kprobes. */
+#ifdef CONFIG_KPROBES
+#define ASM_NOKPROBE(name) \
+ .pushsection "_kprobe_blacklist", "aw"; \
+ RISCV_PTR name; \
+ .popsection
+#else
+#define ASM_NOKPROBE(name)
+#endif
+
+#endif /* __ASSEMBLY__ */
+
#endif /* _ASM_RISCV_ASM_H */
diff --git a/arch/riscv/include/asm/assembler.h b/arch/riscv/include/asm/assembler.h
new file mode 100644
index 000000000000..44b1457d3e95
--- /dev/null
+++ b/arch/riscv/include/asm/assembler.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 StarFive Technology Co., Ltd.
+ *
+ * Author: Jee Heng Sia <jeeheng.sia@starfivetech.com>
+ */
+
+#ifndef __ASSEMBLY__
+#error "Only include this from assembly code"
+#endif
+
+#ifndef __ASM_ASSEMBLER_H
+#define __ASM_ASSEMBLER_H
+
+#include <asm/asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/csr.h>
+
+/*
+ * suspend_restore_csrs - restore CSRs
+ */
+ .macro suspend_restore_csrs
+ REG_L t0, (SUSPEND_CONTEXT_REGS + PT_EPC)(a0)
+ csrw CSR_EPC, t0
+ REG_L t0, (SUSPEND_CONTEXT_REGS + PT_STATUS)(a0)
+ csrw CSR_STATUS, t0
+ REG_L t0, (SUSPEND_CONTEXT_REGS + PT_BADADDR)(a0)
+ csrw CSR_TVAL, t0
+ REG_L t0, (SUSPEND_CONTEXT_REGS + PT_CAUSE)(a0)
+ csrw CSR_CAUSE, t0
+ .endm
+
+/*
+ * suspend_restore_regs - Restore registers (except A0 and T0-T6)
+ */
+ .macro suspend_restore_regs
+ REG_L ra, (SUSPEND_CONTEXT_REGS + PT_RA)(a0)
+ REG_L sp, (SUSPEND_CONTEXT_REGS + PT_SP)(a0)
+ REG_L gp, (SUSPEND_CONTEXT_REGS + PT_GP)(a0)
+ REG_L tp, (SUSPEND_CONTEXT_REGS + PT_TP)(a0)
+ REG_L s0, (SUSPEND_CONTEXT_REGS + PT_S0)(a0)
+ REG_L s1, (SUSPEND_CONTEXT_REGS + PT_S1)(a0)
+ REG_L a1, (SUSPEND_CONTEXT_REGS + PT_A1)(a0)
+ REG_L a2, (SUSPEND_CONTEXT_REGS + PT_A2)(a0)
+ REG_L a3, (SUSPEND_CONTEXT_REGS + PT_A3)(a0)
+ REG_L a4, (SUSPEND_CONTEXT_REGS + PT_A4)(a0)
+ REG_L a5, (SUSPEND_CONTEXT_REGS + PT_A5)(a0)
+ REG_L a6, (SUSPEND_CONTEXT_REGS + PT_A6)(a0)
+ REG_L a7, (SUSPEND_CONTEXT_REGS + PT_A7)(a0)
+ REG_L s2, (SUSPEND_CONTEXT_REGS + PT_S2)(a0)
+ REG_L s3, (SUSPEND_CONTEXT_REGS + PT_S3)(a0)
+ REG_L s4, (SUSPEND_CONTEXT_REGS + PT_S4)(a0)
+ REG_L s5, (SUSPEND_CONTEXT_REGS + PT_S5)(a0)
+ REG_L s6, (SUSPEND_CONTEXT_REGS + PT_S6)(a0)
+ REG_L s7, (SUSPEND_CONTEXT_REGS + PT_S7)(a0)
+ REG_L s8, (SUSPEND_CONTEXT_REGS + PT_S8)(a0)
+ REG_L s9, (SUSPEND_CONTEXT_REGS + PT_S9)(a0)
+ REG_L s10, (SUSPEND_CONTEXT_REGS + PT_S10)(a0)
+ REG_L s11, (SUSPEND_CONTEXT_REGS + PT_S11)(a0)
+ .endm
+
+/*
+ * copy_page - copy 1 page (4KB) of data from source to destination
+ * @a0 - destination
+ * @a1 - source
+ */
+ .macro copy_page a0, a1
+ lui a2, 0x1
+ add a2, a2, a0
+1 :
+ REG_L t0, 0(a1)
+ REG_L t1, SZREG(a1)
+
+ REG_S t0, 0(a0)
+ REG_S t1, SZREG(a0)
+
+ addi a0, a0, 2 * SZREG
+ addi a1, a1, 2 * SZREG
+ bne a2, a0, 1b
+ .endm
+
+#endif /* __ASM_ASSEMBLER_H */
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index 0dfe9d857a76..5b96c2f61adb 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -17,7 +17,6 @@
#endif
#include <asm/cmpxchg.h>
-#include <asm/barrier.h>
#define __atomic_acquire_fence() \
__asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory")
@@ -196,22 +195,28 @@ ATOMIC_OPS(xor, xor, i)
#undef ATOMIC_FETCH_OP
#undef ATOMIC_OP_RETURN
+#define _arch_atomic_fetch_add_unless(_prev, _rc, counter, _a, _u, sfx) \
+({ \
+ __asm__ __volatile__ ( \
+ "0: lr." sfx " %[p], %[c]\n" \
+ " beq %[p], %[u], 1f\n" \
+ " add %[rc], %[p], %[a]\n" \
+ " sc." sfx ".rl %[rc], %[rc], %[c]\n" \
+ " bnez %[rc], 0b\n" \
+ " fence rw, rw\n" \
+ "1:\n" \
+ : [p]"=&r" (_prev), [rc]"=&r" (_rc), [c]"+A" (counter) \
+ : [a]"r" (_a), [u]"r" (_u) \
+ : "memory"); \
+})
+
/* This is required to provide a full barrier on success. */
static __always_inline int arch_atomic_fetch_add_unless(atomic_t *v, int a, int u)
{
int prev, rc;
- __asm__ __volatile__ (
- "0: lr.w %[p], %[c]\n"
- " beq %[p], %[u], 1f\n"
- " add %[rc], %[p], %[a]\n"
- " sc.w.rl %[rc], %[rc], %[c]\n"
- " bnez %[rc], 0b\n"
- " fence rw, rw\n"
- "1:\n"
- : [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
- : [a]"r" (a), [u]"r" (u)
- : "memory");
+ _arch_atomic_fetch_add_unless(prev, rc, v->counter, a, u, "w");
+
return prev;
}
#define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless
@@ -222,149 +227,86 @@ static __always_inline s64 arch_atomic64_fetch_add_unless(atomic64_t *v, s64 a,
s64 prev;
long rc;
- __asm__ __volatile__ (
- "0: lr.d %[p], %[c]\n"
- " beq %[p], %[u], 1f\n"
- " add %[rc], %[p], %[a]\n"
- " sc.d.rl %[rc], %[rc], %[c]\n"
- " bnez %[rc], 0b\n"
- " fence rw, rw\n"
- "1:\n"
- : [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
- : [a]"r" (a), [u]"r" (u)
- : "memory");
+ _arch_atomic_fetch_add_unless(prev, rc, v->counter, a, u, "d");
+
return prev;
}
#define arch_atomic64_fetch_add_unless arch_atomic64_fetch_add_unless
#endif
-/*
- * atomic_{cmp,}xchg is required to have exactly the same ordering semantics as
- * {cmp,}xchg and the operations that return, so they need a full barrier.
- */
-#define ATOMIC_OP(c_t, prefix, size) \
-static __always_inline \
-c_t arch_atomic##prefix##_xchg_relaxed(atomic##prefix##_t *v, c_t n) \
-{ \
- return __xchg_relaxed(&(v->counter), n, size); \
-} \
-static __always_inline \
-c_t arch_atomic##prefix##_xchg_acquire(atomic##prefix##_t *v, c_t n) \
-{ \
- return __xchg_acquire(&(v->counter), n, size); \
-} \
-static __always_inline \
-c_t arch_atomic##prefix##_xchg_release(atomic##prefix##_t *v, c_t n) \
-{ \
- return __xchg_release(&(v->counter), n, size); \
-} \
-static __always_inline \
-c_t arch_atomic##prefix##_xchg(atomic##prefix##_t *v, c_t n) \
-{ \
- return __xchg(&(v->counter), n, size); \
-} \
-static __always_inline \
-c_t arch_atomic##prefix##_cmpxchg_relaxed(atomic##prefix##_t *v, \
- c_t o, c_t n) \
-{ \
- return __cmpxchg_relaxed(&(v->counter), o, n, size); \
-} \
-static __always_inline \
-c_t arch_atomic##prefix##_cmpxchg_acquire(atomic##prefix##_t *v, \
- c_t o, c_t n) \
-{ \
- return __cmpxchg_acquire(&(v->counter), o, n, size); \
-} \
-static __always_inline \
-c_t arch_atomic##prefix##_cmpxchg_release(atomic##prefix##_t *v, \
- c_t o, c_t n) \
-{ \
- return __cmpxchg_release(&(v->counter), o, n, size); \
-} \
-static __always_inline \
-c_t arch_atomic##prefix##_cmpxchg(atomic##prefix##_t *v, c_t o, c_t n) \
-{ \
- return __cmpxchg(&(v->counter), o, n, size); \
-}
-
-#ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS() \
- ATOMIC_OP(int, , 4)
-#else
-#define ATOMIC_OPS() \
- ATOMIC_OP(int, , 4) \
- ATOMIC_OP(s64, 64, 8)
-#endif
-
-ATOMIC_OPS()
-
-#define arch_atomic_xchg_relaxed arch_atomic_xchg_relaxed
-#define arch_atomic_xchg_acquire arch_atomic_xchg_acquire
-#define arch_atomic_xchg_release arch_atomic_xchg_release
-#define arch_atomic_xchg arch_atomic_xchg
-#define arch_atomic_cmpxchg_relaxed arch_atomic_cmpxchg_relaxed
-#define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg_acquire
-#define arch_atomic_cmpxchg_release arch_atomic_cmpxchg_release
-#define arch_atomic_cmpxchg arch_atomic_cmpxchg
-
-#undef ATOMIC_OPS
-#undef ATOMIC_OP
+#define _arch_atomic_inc_unless_negative(_prev, _rc, counter, sfx) \
+({ \
+ __asm__ __volatile__ ( \
+ "0: lr." sfx " %[p], %[c]\n" \
+ " bltz %[p], 1f\n" \
+ " addi %[rc], %[p], 1\n" \
+ " sc." sfx ".rl %[rc], %[rc], %[c]\n" \
+ " bnez %[rc], 0b\n" \
+ " fence rw, rw\n" \
+ "1:\n" \
+ : [p]"=&r" (_prev), [rc]"=&r" (_rc), [c]"+A" (counter) \
+ : \
+ : "memory"); \
+})
static __always_inline bool arch_atomic_inc_unless_negative(atomic_t *v)
{
int prev, rc;
- __asm__ __volatile__ (
- "0: lr.w %[p], %[c]\n"
- " bltz %[p], 1f\n"
- " addi %[rc], %[p], 1\n"
- " sc.w.rl %[rc], %[rc], %[c]\n"
- " bnez %[rc], 0b\n"
- " fence rw, rw\n"
- "1:\n"
- : [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
- :
- : "memory");
+ _arch_atomic_inc_unless_negative(prev, rc, v->counter, "w");
+
return !(prev < 0);
}
#define arch_atomic_inc_unless_negative arch_atomic_inc_unless_negative
+#define _arch_atomic_dec_unless_positive(_prev, _rc, counter, sfx) \
+({ \
+ __asm__ __volatile__ ( \
+ "0: lr." sfx " %[p], %[c]\n" \
+ " bgtz %[p], 1f\n" \
+ " addi %[rc], %[p], -1\n" \
+ " sc." sfx ".rl %[rc], %[rc], %[c]\n" \
+ " bnez %[rc], 0b\n" \
+ " fence rw, rw\n" \
+ "1:\n" \
+ : [p]"=&r" (_prev), [rc]"=&r" (_rc), [c]"+A" (counter) \
+ : \
+ : "memory"); \
+})
+
static __always_inline bool arch_atomic_dec_unless_positive(atomic_t *v)
{
int prev, rc;
- __asm__ __volatile__ (
- "0: lr.w %[p], %[c]\n"
- " bgtz %[p], 1f\n"
- " addi %[rc], %[p], -1\n"
- " sc.w.rl %[rc], %[rc], %[c]\n"
- " bnez %[rc], 0b\n"
- " fence rw, rw\n"
- "1:\n"
- : [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
- :
- : "memory");
+ _arch_atomic_dec_unless_positive(prev, rc, v->counter, "w");
+
return !(prev > 0);
}
#define arch_atomic_dec_unless_positive arch_atomic_dec_unless_positive
+#define _arch_atomic_dec_if_positive(_prev, _rc, counter, sfx) \
+({ \
+ __asm__ __volatile__ ( \
+ "0: lr." sfx " %[p], %[c]\n" \
+ " addi %[rc], %[p], -1\n" \
+ " bltz %[rc], 1f\n" \
+ " sc." sfx ".rl %[rc], %[rc], %[c]\n" \
+ " bnez %[rc], 0b\n" \
+ " fence rw, rw\n" \
+ "1:\n" \
+ : [p]"=&r" (_prev), [rc]"=&r" (_rc), [c]"+A" (counter) \
+ : \
+ : "memory"); \
+})
+
static __always_inline int arch_atomic_dec_if_positive(atomic_t *v)
{
int prev, rc;
- __asm__ __volatile__ (
- "0: lr.w %[p], %[c]\n"
- " addi %[rc], %[p], -1\n"
- " bltz %[rc], 1f\n"
- " sc.w.rl %[rc], %[rc], %[c]\n"
- " bnez %[rc], 0b\n"
- " fence rw, rw\n"
- "1:\n"
- : [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
- :
- : "memory");
+ _arch_atomic_dec_if_positive(prev, rc, v->counter, "w");
+
return prev - 1;
}
@@ -376,17 +318,8 @@ static __always_inline bool arch_atomic64_inc_unless_negative(atomic64_t *v)
s64 prev;
long rc;
- __asm__ __volatile__ (
- "0: lr.d %[p], %[c]\n"
- " bltz %[p], 1f\n"
- " addi %[rc], %[p], 1\n"
- " sc.d.rl %[rc], %[rc], %[c]\n"
- " bnez %[rc], 0b\n"
- " fence rw, rw\n"
- "1:\n"
- : [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
- :
- : "memory");
+ _arch_atomic_inc_unless_negative(prev, rc, v->counter, "d");
+
return !(prev < 0);
}
@@ -397,17 +330,8 @@ static __always_inline bool arch_atomic64_dec_unless_positive(atomic64_t *v)
s64 prev;
long rc;
- __asm__ __volatile__ (
- "0: lr.d %[p], %[c]\n"
- " bgtz %[p], 1f\n"
- " addi %[rc], %[p], -1\n"
- " sc.d.rl %[rc], %[rc], %[c]\n"
- " bnez %[rc], 0b\n"
- " fence rw, rw\n"
- "1:\n"
- : [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
- :
- : "memory");
+ _arch_atomic_dec_unless_positive(prev, rc, v->counter, "d");
+
return !(prev > 0);
}
@@ -418,17 +342,8 @@ static __always_inline s64 arch_atomic64_dec_if_positive(atomic64_t *v)
s64 prev;
long rc;
- __asm__ __volatile__ (
- "0: lr.d %[p], %[c]\n"
- " addi %[rc], %[p], -1\n"
- " bltz %[rc], 1f\n"
- " sc.d.rl %[rc], %[rc], %[c]\n"
- " bnez %[rc], 0b\n"
- " fence rw, rw\n"
- "1:\n"
- : [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
- :
- : "memory");
+ _arch_atomic_dec_if_positive(prev, rc, v->counter, "d");
+
return prev - 1;
}
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
index d0e24aaa2aa0..b8c5726d86ac 100644
--- a/arch/riscv/include/asm/barrier.h
+++ b/arch/riscv/include/asm/barrier.h
@@ -11,36 +11,18 @@
#define _ASM_RISCV_BARRIER_H
#ifndef __ASSEMBLY__
-
-#define nop() __asm__ __volatile__ ("nop")
-
-#define RISCV_FENCE(p, s) \
- __asm__ __volatile__ ("fence " #p "," #s : : : "memory")
+#include <asm/cmpxchg.h>
+#include <asm/fence.h>
/* These barriers need to enforce ordering on both devices or memory. */
-#define mb() RISCV_FENCE(iorw,iorw)
-#define rmb() RISCV_FENCE(ir,ir)
-#define wmb() RISCV_FENCE(ow,ow)
+#define __mb() RISCV_FENCE(iorw, iorw)
+#define __rmb() RISCV_FENCE(ir, ir)
+#define __wmb() RISCV_FENCE(ow, ow)
/* These barriers do not need to enforce ordering on devices, just memory. */
-#define __smp_mb() RISCV_FENCE(rw,rw)
-#define __smp_rmb() RISCV_FENCE(r,r)
-#define __smp_wmb() RISCV_FENCE(w,w)
-
-#define __smp_store_release(p, v) \
-do { \
- compiletime_assert_atomic_type(*p); \
- RISCV_FENCE(rw,w); \
- WRITE_ONCE(*p, v); \
-} while (0)
-
-#define __smp_load_acquire(p) \
-({ \
- typeof(*p) ___p1 = READ_ONCE(*p); \
- compiletime_assert_atomic_type(*p); \
- RISCV_FENCE(r,rw); \
- ___p1; \
-})
+#define __smp_mb() RISCV_FENCE(rw, rw)
+#define __smp_rmb() RISCV_FENCE(r, r)
+#define __smp_wmb() RISCV_FENCE(w, w)
/*
* This is a very specific barrier: it's currently only used in two places in
@@ -67,7 +49,36 @@ do { \
* instances the scheduler pairs this with an mb(), so nothing is necessary on
* the new hart.
*/
-#define smp_mb__after_spinlock() RISCV_FENCE(iorw,iorw)
+#define smp_mb__after_spinlock() RISCV_FENCE(iorw, iorw)
+
+#define __smp_store_release(p, v) \
+do { \
+ compiletime_assert_atomic_type(*p); \
+ RISCV_FENCE(rw, w); \
+ WRITE_ONCE(*p, v); \
+} while (0)
+
+#define __smp_load_acquire(p) \
+({ \
+ typeof(*p) ___p1 = READ_ONCE(*p); \
+ compiletime_assert_atomic_type(*p); \
+ RISCV_FENCE(r, rw); \
+ ___p1; \
+})
+
+#ifdef CONFIG_RISCV_ISA_ZAWRS
+#define smp_cond_load_relaxed(ptr, cond_expr) ({ \
+ typeof(ptr) __PTR = (ptr); \
+ __unqual_scalar_typeof(*ptr) VAL; \
+ for (;;) { \
+ VAL = READ_ONCE(*__PTR); \
+ if (cond_expr) \
+ break; \
+ __cmpwait_relaxed(ptr, VAL); \
+ } \
+ (typeof(*ptr))VAL; \
+})
+#endif
#include <asm-generic/barrier.h>
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
index 3540b690944b..d59310f74c2b 100644
--- a/arch/riscv/include/asm/bitops.h
+++ b/arch/riscv/include/asm/bitops.h
@@ -15,15 +15,175 @@
#include <asm/barrier.h>
#include <asm/bitsperlong.h>
+#if !(defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB)) || defined(NO_ALTERNATIVE)
#include <asm-generic/bitops/__ffs.h>
-#include <asm-generic/bitops/ffz.h>
+#include <asm-generic/bitops/__fls.h>
+#include <asm-generic/bitops/ffs.h>
#include <asm-generic/bitops/fls.h>
+
+#else
+#define __HAVE_ARCH___FFS
+#define __HAVE_ARCH___FLS
+#define __HAVE_ARCH_FFS
+#define __HAVE_ARCH_FLS
+
+#include <asm-generic/bitops/__ffs.h>
#include <asm-generic/bitops/__fls.h>
+#include <asm-generic/bitops/ffs.h>
+#include <asm-generic/bitops/fls.h>
+
+#include <asm/alternative-macros.h>
+#include <asm/hwcap.h>
+
+#if (BITS_PER_LONG == 64)
+#define CTZW "ctzw "
+#define CLZW "clzw "
+#elif (BITS_PER_LONG == 32)
+#define CTZW "ctz "
+#define CLZW "clz "
+#else
+#error "Unexpected BITS_PER_LONG"
+#endif
+
+static __always_inline unsigned long variable__ffs(unsigned long word)
+{
+ asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+ RISCV_ISA_EXT_ZBB, 1)
+ : : : : legacy);
+
+ asm volatile (".option push\n"
+ ".option arch,+zbb\n"
+ "ctz %0, %1\n"
+ ".option pop\n"
+ : "=r" (word) : "r" (word) :);
+
+ return word;
+
+legacy:
+ return generic___ffs(word);
+}
+
+/**
+ * __ffs - find first set bit in a long word
+ * @word: The word to search
+ *
+ * Undefined if no set bit exists, so code should check against 0 first.
+ */
+#define __ffs(word) \
+ (__builtin_constant_p(word) ? \
+ (unsigned long)__builtin_ctzl(word) : \
+ variable__ffs(word))
+
+static __always_inline unsigned long variable__fls(unsigned long word)
+{
+ asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+ RISCV_ISA_EXT_ZBB, 1)
+ : : : : legacy);
+
+ asm volatile (".option push\n"
+ ".option arch,+zbb\n"
+ "clz %0, %1\n"
+ ".option pop\n"
+ : "=r" (word) : "r" (word) :);
+
+ return BITS_PER_LONG - 1 - word;
+
+legacy:
+ return generic___fls(word);
+}
+
+/**
+ * __fls - find last set bit in a long word
+ * @word: the word to search
+ *
+ * Undefined if no set bit exists, so code should check against 0 first.
+ */
+#define __fls(word) \
+ (__builtin_constant_p(word) ? \
+ (unsigned long)(BITS_PER_LONG - 1 - __builtin_clzl(word)) : \
+ variable__fls(word))
+
+static __always_inline int variable_ffs(int x)
+{
+ asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+ RISCV_ISA_EXT_ZBB, 1)
+ : : : : legacy);
+
+ if (!x)
+ return 0;
+
+ asm volatile (".option push\n"
+ ".option arch,+zbb\n"
+ CTZW "%0, %1\n"
+ ".option pop\n"
+ : "=r" (x) : "r" (x) :);
+
+ return x + 1;
+
+legacy:
+ return generic_ffs(x);
+}
+
+/**
+ * ffs - find first set bit in a word
+ * @x: the word to search
+ *
+ * This is defined the same way as the libc and compiler builtin ffs routines.
+ *
+ * ffs(value) returns 0 if value is 0 or the position of the first set bit if
+ * value is nonzero. The first (least significant) bit is at position 1.
+ */
+#define ffs(x) (__builtin_constant_p(x) ? __builtin_ffs(x) : variable_ffs(x))
+
+static __always_inline int variable_fls(unsigned int x)
+{
+ asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+ RISCV_ISA_EXT_ZBB, 1)
+ : : : : legacy);
+
+ if (!x)
+ return 0;
+
+ asm volatile (".option push\n"
+ ".option arch,+zbb\n"
+ CLZW "%0, %1\n"
+ ".option pop\n"
+ : "=r" (x) : "r" (x) :);
+
+ return 32 - x;
+
+legacy:
+ return generic_fls(x);
+}
+
+/**
+ * fls - find last set bit in a word
+ * @x: the word to search
+ *
+ * This is defined in a similar way as ffs, but returns the position of the most
+ * significant set bit.
+ *
+ * fls(value) returns 0 if value is 0 or the position of the last set bit if
+ * value is nonzero. The last (most significant) bit is at position 32.
+ */
+#define fls(x) \
+({ \
+ typeof(x) x_ = (x); \
+ __builtin_constant_p(x_) ? \
+ ((x_ != 0) ? (32 - __builtin_clz(x_)) : 0) \
+ : \
+ variable_fls(x_); \
+})
+
+#endif /* !(defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB)) || defined(NO_ALTERNATIVE) */
+
+#include <asm-generic/bitops/ffz.h>
#include <asm-generic/bitops/fls64.h>
#include <asm-generic/bitops/sched.h>
-#include <asm-generic/bitops/ffs.h>
-#include <asm-generic/bitops/hweight.h>
+#include <asm/arch_hweight.h>
+
+#include <asm-generic/bitops/const_hweight.h>
#if (BITS_PER_LONG == 64)
#define __AMO(op) "amo" #op ".d"
@@ -62,44 +222,44 @@
#define __NOT(x) (~(x))
/**
- * test_and_set_bit - Set a bit and return its old value
+ * arch_test_and_set_bit - Set a bit and return its old value
* @nr: Bit to set
* @addr: Address to count from
*
- * This operation may be reordered on other architectures than x86.
+ * This is an atomic fully-ordered operation (implied full memory barrier).
*/
-static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
+static __always_inline int arch_test_and_set_bit(int nr, volatile unsigned long *addr)
{
return __test_and_op_bit(or, __NOP, nr, addr);
}
/**
- * test_and_clear_bit - Clear a bit and return its old value
+ * arch_test_and_clear_bit - Clear a bit and return its old value
* @nr: Bit to clear
* @addr: Address to count from
*
- * This operation can be reordered on other architectures other than x86.
+ * This is an atomic fully-ordered operation (implied full memory barrier).
*/
-static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
+static __always_inline int arch_test_and_clear_bit(int nr, volatile unsigned long *addr)
{
return __test_and_op_bit(and, __NOT, nr, addr);
}
/**
- * test_and_change_bit - Change a bit and return its old value
+ * arch_test_and_change_bit - Change a bit and return its old value
* @nr: Bit to change
* @addr: Address to count from
*
* This operation is atomic and cannot be reordered.
* It also implies a memory barrier.
*/
-static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
+static __always_inline int arch_test_and_change_bit(int nr, volatile unsigned long *addr)
{
return __test_and_op_bit(xor, __NOP, nr, addr);
}
/**
- * set_bit - Atomically set a bit in memory
+ * arch_set_bit - Atomically set a bit in memory
* @nr: the bit to set
* @addr: the address to start counting from
*
@@ -110,13 +270,13 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
* Note that @nr may be almost arbitrarily large; this function is not
* restricted to acting on a single-word quantity.
*/
-static inline void set_bit(int nr, volatile unsigned long *addr)
+static __always_inline void arch_set_bit(int nr, volatile unsigned long *addr)
{
__op_bit(or, __NOP, nr, addr);
}
/**
- * clear_bit - Clears a bit in memory
+ * arch_clear_bit - Clears a bit in memory
* @nr: Bit to clear
* @addr: Address to start counting from
*
@@ -124,13 +284,13 @@ static inline void set_bit(int nr, volatile unsigned long *addr)
* on non x86 architectures, so if you are writing portable code,
* make sure not to rely on its reordering guarantees.
*/
-static inline void clear_bit(int nr, volatile unsigned long *addr)
+static __always_inline void arch_clear_bit(int nr, volatile unsigned long *addr)
{
__op_bit(and, __NOT, nr, addr);
}
/**
- * change_bit - Toggle a bit in memory
+ * arch_change_bit - Toggle a bit in memory
* @nr: Bit to change
* @addr: Address to start counting from
*
@@ -138,40 +298,40 @@ static inline void clear_bit(int nr, volatile unsigned long *addr)
* Note that @nr may be almost arbitrarily large; this function is not
* restricted to acting on a single-word quantity.
*/
-static inline void change_bit(int nr, volatile unsigned long *addr)
+static __always_inline void arch_change_bit(int nr, volatile unsigned long *addr)
{
__op_bit(xor, __NOP, nr, addr);
}
/**
- * test_and_set_bit_lock - Set a bit and return its old value, for lock
+ * arch_test_and_set_bit_lock - Set a bit and return its old value, for lock
* @nr: Bit to set
* @addr: Address to count from
*
* This operation is atomic and provides acquire barrier semantics.
* It can be used to implement bit locks.
*/
-static inline int test_and_set_bit_lock(
+static __always_inline int arch_test_and_set_bit_lock(
unsigned long nr, volatile unsigned long *addr)
{
return __test_and_op_bit_ord(or, __NOP, nr, addr, .aq);
}
/**
- * clear_bit_unlock - Clear a bit in memory, for unlock
+ * arch_clear_bit_unlock - Clear a bit in memory, for unlock
* @nr: the bit to set
* @addr: the address to start counting from
*
* This operation is atomic and provides release barrier semantics.
*/
-static inline void clear_bit_unlock(
+static __always_inline void arch_clear_bit_unlock(
unsigned long nr, volatile unsigned long *addr)
{
__op_bit_ord(and, __NOT, nr, addr, .rl);
}
/**
- * __clear_bit_unlock - Clear a bit in memory, for unlock
+ * arch___clear_bit_unlock - Clear a bit in memory, for unlock
* @nr: the bit to set
* @addr: the address to start counting from
*
@@ -185,10 +345,22 @@ static inline void clear_bit_unlock(
* non-atomic property here: it's a lot more instructions and we still have to
* provide release semantics anyway.
*/
-static inline void __clear_bit_unlock(
+static __always_inline void arch___clear_bit_unlock(
unsigned long nr, volatile unsigned long *addr)
{
- clear_bit_unlock(nr, addr);
+ arch_clear_bit_unlock(nr, addr);
+}
+
+static __always_inline bool arch_xor_unlock_is_negative_byte(unsigned long mask,
+ volatile unsigned long *addr)
+{
+ unsigned long res;
+ __asm__ __volatile__ (
+ __AMO(xor) ".rl %0, %2, %1"
+ : "=r" (res), "+A" (*addr)
+ : "r" (__NOP(mask))
+ : "memory");
+ return (res & BIT(7)) != 0;
}
#undef __test_and_op_bit
@@ -197,6 +369,9 @@ static inline void __clear_bit_unlock(
#undef __NOT
#undef __AMO
+#include <asm-generic/bitops/instrumented-atomic.h>
+#include <asm-generic/bitops/instrumented-lock.h>
+
#include <asm-generic/bitops/non-atomic.h>
#include <asm-generic/bitops/le.h>
#include <asm-generic/bitops/ext2-atomic.h>
diff --git a/arch/riscv/include/asm/bugs.h b/arch/riscv/include/asm/bugs.h
new file mode 100644
index 000000000000..17ca0a947730
--- /dev/null
+++ b/arch/riscv/include/asm/bugs.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Interface for managing mitigations for riscv vulnerabilities.
+ *
+ * Copyright (C) 2024 Rivos Inc.
+ */
+
+#ifndef __ASM_BUGS_H
+#define __ASM_BUGS_H
+
+/* Watch out, ordering is important here. */
+enum mitigation_state {
+ UNAFFECTED,
+ MITIGATED,
+ VULNERABLE,
+};
+
+void ghostwrite_set_vulnerable(void);
+bool ghostwrite_enable_mitigation(void);
+enum mitigation_state ghostwrite_get_state(void);
+
+#endif /* __ASM_BUGS_H */
diff --git a/arch/riscv/include/asm/cache.h b/arch/riscv/include/asm/cache.h
index 9b58b104559e..570e9d8acad1 100644
--- a/arch/riscv/include/asm/cache.h
+++ b/arch/riscv/include/asm/cache.h
@@ -11,6 +11,11 @@
#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT)
+#ifdef CONFIG_RISCV_DMA_NONCOHERENT
+#define ARCH_DMA_MINALIGN L1_CACHE_BYTES
+#define ARCH_KMALLOC_MINALIGN (8)
+#endif
+
/*
* RISC-V requires the stack pointer to be 16-byte aligned, so ensure that
* the flat loader aligns it accordingly.
@@ -19,4 +24,17 @@
#define ARCH_SLAB_MINALIGN 16
#endif
+#ifndef __ASSEMBLY__
+
+extern int dma_cache_alignment;
+#ifdef CONFIG_RISCV_DMA_NONCOHERENT
+#define dma_get_cache_alignment dma_get_cache_alignment
+static inline int dma_get_cache_alignment(void)
+{
+ return dma_cache_alignment;
+}
+#endif
+
+#endif /* __ASSEMBLY__ */
+
#endif /* _ASM_RISCV_CACHE_H */
diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
index 23ff70350992..6086b38d5427 100644
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -13,22 +13,53 @@ static inline void local_flush_icache_all(void)
asm volatile ("fence.i" ::: "memory");
}
+static inline void local_flush_icache_range(unsigned long start,
+ unsigned long end)
+{
+ local_flush_icache_all();
+}
+
#define PG_dcache_clean PG_arch_1
-static inline void flush_dcache_page(struct page *page)
+static inline void flush_dcache_folio(struct folio *folio)
{
- if (test_bit(PG_dcache_clean, &page->flags))
- clear_bit(PG_dcache_clean, &page->flags);
+ if (test_bit(PG_dcache_clean, &folio->flags))
+ clear_bit(PG_dcache_clean, &folio->flags);
}
+#define flush_dcache_folio flush_dcache_folio
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
-/*
- * RISC-V doesn't have an instruction to flush parts of the instruction cache,
- * so instead we just flush the whole thing.
- */
-#define flush_icache_range(start, end) flush_icache_all()
-#define flush_icache_user_page(vma, pg, addr, len) \
- flush_icache_mm(vma->vm_mm, 0)
+static inline void flush_dcache_page(struct page *page)
+{
+ flush_dcache_folio(page_folio(page));
+}
+
+#define flush_icache_user_page(vma, pg, addr, len) \
+do { \
+ if (vma->vm_flags & VM_EXEC) \
+ flush_icache_mm(vma->vm_mm, 0); \
+} while (0)
+
+#ifdef CONFIG_64BIT
+extern u64 new_vmalloc[NR_CPUS / sizeof(u64) + 1];
+extern char _end[];
+#define flush_cache_vmap flush_cache_vmap
+static inline void flush_cache_vmap(unsigned long start, unsigned long end)
+{
+ if (is_vmalloc_or_module_addr((void *)start)) {
+ int i;
+
+ /*
+ * We don't care if concurrently a cpu resets this value since
+ * the only place this can happen is in handle_exception() where
+ * an sfence.vma is emitted.
+ */
+ for (i = 0; i < ARRAY_SIZE(new_vmalloc); ++i)
+ new_vmalloc[i] = -1ULL;
+ }
+}
+#define flush_cache_vmap_early(start, end) local_flush_tlb_kernel_range(start, end)
+#endif
#ifndef CONFIG_SMP
@@ -43,6 +74,29 @@ void flush_icache_mm(struct mm_struct *mm, bool local);
#endif /* CONFIG_SMP */
/*
+ * RISC-V doesn't have an instruction to flush parts of the instruction cache,
+ * so instead we just flush the whole thing.
+ */
+#define flush_icache_range flush_icache_range
+static inline void flush_icache_range(unsigned long start, unsigned long end)
+{
+ flush_icache_all();
+}
+
+extern unsigned int riscv_cbom_block_size;
+extern unsigned int riscv_cboz_block_size;
+extern unsigned int riscv_cbop_block_size;
+void riscv_init_cbo_blocksizes(void);
+
+#ifdef CONFIG_RISCV_DMA_NONCOHERENT
+void riscv_noncoherent_supported(void);
+void __init riscv_set_dma_cache_alignment(void);
+#else
+static inline void riscv_noncoherent_supported(void) {}
+static inline void riscv_set_dma_cache_alignment(void) {}
+#endif
+
+/*
* Bits in sys_riscv_flush_icache()'s flags argument.
*/
#define SYS_RISCV_FLUSH_ICACHE_LOCAL 1UL
diff --git a/arch/riscv/include/asm/cfi.h b/arch/riscv/include/asm/cfi.h
new file mode 100644
index 000000000000..fb9696d7a3f2
--- /dev/null
+++ b/arch/riscv/include/asm/cfi.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_CFI_H
+#define _ASM_RISCV_CFI_H
+
+/*
+ * Clang Control Flow Integrity (CFI) support.
+ *
+ * Copyright (C) 2023 Google LLC
+ */
+#include <linux/bug.h>
+
+struct pt_regs;
+
+#ifdef CONFIG_CFI_CLANG
+enum bug_trap_type handle_cfi_failure(struct pt_regs *regs);
+#define __bpfcall
+static inline int cfi_get_offset(void)
+{
+ return 4;
+}
+
+#define cfi_get_offset cfi_get_offset
+extern u32 cfi_bpf_hash;
+extern u32 cfi_bpf_subprog_hash;
+extern u32 cfi_get_func_hash(void *func);
+#else
+static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
+{
+ return BUG_TRAP_TYPE_NONE;
+}
+
+#define cfi_bpf_hash 0U
+#define cfi_bpf_subprog_hash 0U
+static inline u32 cfi_get_func_hash(void *func)
+{
+ return 0;
+}
+#endif /* CONFIG_CFI_CLANG */
+
+#endif /* _ASM_RISCV_CFI_H */
diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h
new file mode 100644
index 000000000000..da378856f1d5
--- /dev/null
+++ b/arch/riscv/include/asm/checksum.h
@@ -0,0 +1,92 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Checksum routines
+ *
+ * Copyright (C) 2023 Rivos Inc.
+ */
+#ifndef __ASM_RISCV_CHECKSUM_H
+#define __ASM_RISCV_CHECKSUM_H
+
+#include <linux/in6.h>
+#include <linux/uaccess.h>
+
+#define ip_fast_csum ip_fast_csum
+
+extern unsigned int do_csum(const unsigned char *buff, int len);
+#define do_csum do_csum
+
+/* Default version is sufficient for 32 bit */
+#ifndef CONFIG_32BIT
+#define _HAVE_ARCH_IPV6_CSUM
+__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+ const struct in6_addr *daddr,
+ __u32 len, __u8 proto, __wsum sum);
+#endif
+
+/* Define riscv versions of functions before importing asm-generic/checksum.h */
+#include <asm-generic/checksum.h>
+
+/**
+ * Quickly compute an IP checksum with the assumption that IPv4 headers will
+ * always be in multiples of 32-bits, and have an ihl of at least 5.
+ *
+ * @ihl: the number of 32 bit segments and must be greater than or equal to 5.
+ * @iph: assumed to be word aligned given that NET_IP_ALIGN is set to 2 on
+ * riscv, defining IP headers to be aligned.
+ */
+static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+{
+ unsigned long csum = 0;
+ int pos = 0;
+
+ do {
+ csum += ((const unsigned int *)iph)[pos];
+ if (IS_ENABLED(CONFIG_32BIT))
+ csum += csum < ((const unsigned int *)iph)[pos];
+ } while (++pos < ihl);
+
+ /*
+ * ZBB only saves three instructions on 32-bit and five on 64-bit so not
+ * worth checking if supported without Alternatives.
+ */
+ if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) {
+ unsigned long fold_temp;
+
+ asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+ RISCV_ISA_EXT_ZBB, 1)
+ :
+ :
+ :
+ : no_zbb);
+
+ if (IS_ENABLED(CONFIG_32BIT)) {
+ asm(".option push \n\
+ .option arch,+zbb \n\
+ not %[fold_temp], %[csum] \n\
+ rori %[csum], %[csum], 16 \n\
+ sub %[csum], %[fold_temp], %[csum] \n\
+ .option pop"
+ : [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp));
+ } else {
+ asm(".option push \n\
+ .option arch,+zbb \n\
+ rori %[fold_temp], %[csum], 32 \n\
+ add %[csum], %[fold_temp], %[csum] \n\
+ srli %[csum], %[csum], 32 \n\
+ not %[fold_temp], %[csum] \n\
+ roriw %[csum], %[csum], 16 \n\
+ subw %[csum], %[fold_temp], %[csum] \n\
+ .option pop"
+ : [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp));
+ }
+ return (__force __sum16)(csum >> 16);
+ }
+no_zbb:
+#ifndef CONFIG_32BIT
+ csum += ror64(csum, 32);
+ csum >>= 32;
+#endif
+ return csum_fold((__force __wsum)csum);
+}
+
+#endif /* __ASM_RISCV_CHECKSUM_H */
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 12debce235e5..0b749e710216 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -8,143 +8,106 @@
#include <linux/bug.h>
-#include <asm/barrier.h>
+#include <asm/alternative-macros.h>
#include <asm/fence.h>
+#include <asm/hwcap.h>
+#include <asm/insn-def.h>
+#include <asm/cpufeature-macros.h>
+#include <asm/processor.h>
-#define __xchg_relaxed(ptr, new, size) \
-({ \
- __typeof__(ptr) __ptr = (ptr); \
- __typeof__(new) __new = (new); \
- __typeof__(*(ptr)) __ret; \
- switch (size) { \
- case 4: \
- __asm__ __volatile__ ( \
- " amoswap.w %0, %2, %1\n" \
- : "=r" (__ret), "+A" (*__ptr) \
- : "r" (__new) \
- : "memory"); \
- break; \
- case 8: \
- __asm__ __volatile__ ( \
- " amoswap.d %0, %2, %1\n" \
- : "=r" (__ret), "+A" (*__ptr) \
- : "r" (__new) \
- : "memory"); \
- break; \
- default: \
- BUILD_BUG(); \
- } \
- __ret; \
+#define __arch_xchg_masked(sc_sfx, swap_sfx, prepend, sc_append, \
+ swap_append, r, p, n) \
+({ \
+ if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) && \
+ riscv_has_extension_unlikely(RISCV_ISA_EXT_ZABHA)) { \
+ __asm__ __volatile__ ( \
+ prepend \
+ " amoswap" swap_sfx " %0, %z2, %1\n" \
+ swap_append \
+ : "=&r" (r), "+A" (*(p)) \
+ : "rJ" (n) \
+ : "memory"); \
+ } else { \
+ u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3); \
+ ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE; \
+ ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0) \
+ << __s; \
+ ulong __newx = (ulong)(n) << __s; \
+ ulong __retx; \
+ ulong __rc; \
+ \
+ __asm__ __volatile__ ( \
+ prepend \
+ PREFETCHW_ASM(%5) \
+ "0: lr.w %0, %2\n" \
+ " and %1, %0, %z4\n" \
+ " or %1, %1, %z3\n" \
+ " sc.w" sc_sfx " %1, %1, %2\n" \
+ " bnez %1, 0b\n" \
+ sc_append \
+ : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b)) \
+ : "rJ" (__newx), "rJ" (~__mask), "rJ" (__ptr32b) \
+ : "memory"); \
+ \
+ r = (__typeof__(*(p)))((__retx & __mask) >> __s); \
+ } \
})
-#define arch_xchg_relaxed(ptr, x) \
+#define __arch_xchg(sfx, prepend, append, r, p, n) \
({ \
- __typeof__(*(ptr)) _x_ = (x); \
- (__typeof__(*(ptr))) __xchg_relaxed((ptr), \
- _x_, sizeof(*(ptr))); \
+ __asm__ __volatile__ ( \
+ prepend \
+ " amoswap" sfx " %0, %2, %1\n" \
+ append \
+ : "=r" (r), "+A" (*(p)) \
+ : "r" (n) \
+ : "memory"); \
})
-#define __xchg_acquire(ptr, new, size) \
+#define _arch_xchg(ptr, new, sc_sfx, swap_sfx, prepend, \
+ sc_append, swap_append) \
({ \
__typeof__(ptr) __ptr = (ptr); \
- __typeof__(new) __new = (new); \
- __typeof__(*(ptr)) __ret; \
- switch (size) { \
- case 4: \
- __asm__ __volatile__ ( \
- " amoswap.w %0, %2, %1\n" \
- RISCV_ACQUIRE_BARRIER \
- : "=r" (__ret), "+A" (*__ptr) \
- : "r" (__new) \
- : "memory"); \
+ __typeof__(*(__ptr)) __new = (new); \
+ __typeof__(*(__ptr)) __ret; \
+ \
+ switch (sizeof(*__ptr)) { \
+ case 1: \
+ __arch_xchg_masked(sc_sfx, ".b" swap_sfx, \
+ prepend, sc_append, swap_append, \
+ __ret, __ptr, __new); \
break; \
- case 8: \
- __asm__ __volatile__ ( \
- " amoswap.d %0, %2, %1\n" \
- RISCV_ACQUIRE_BARRIER \
- : "=r" (__ret), "+A" (*__ptr) \
- : "r" (__new) \
- : "memory"); \
+ case 2: \
+ __arch_xchg_masked(sc_sfx, ".h" swap_sfx, \
+ prepend, sc_append, swap_append, \
+ __ret, __ptr, __new); \
break; \
- default: \
- BUILD_BUG(); \
- } \
- __ret; \
-})
-
-#define arch_xchg_acquire(ptr, x) \
-({ \
- __typeof__(*(ptr)) _x_ = (x); \
- (__typeof__(*(ptr))) __xchg_acquire((ptr), \
- _x_, sizeof(*(ptr))); \
-})
-
-#define __xchg_release(ptr, new, size) \
-({ \
- __typeof__(ptr) __ptr = (ptr); \
- __typeof__(new) __new = (new); \
- __typeof__(*(ptr)) __ret; \
- switch (size) { \
case 4: \
- __asm__ __volatile__ ( \
- RISCV_RELEASE_BARRIER \
- " amoswap.w %0, %2, %1\n" \
- : "=r" (__ret), "+A" (*__ptr) \
- : "r" (__new) \
- : "memory"); \
+ __arch_xchg(".w" swap_sfx, prepend, swap_append, \
+ __ret, __ptr, __new); \
break; \
case 8: \
- __asm__ __volatile__ ( \
- RISCV_RELEASE_BARRIER \
- " amoswap.d %0, %2, %1\n" \
- : "=r" (__ret), "+A" (*__ptr) \
- : "r" (__new) \
- : "memory"); \
+ __arch_xchg(".d" swap_sfx, prepend, swap_append, \
+ __ret, __ptr, __new); \
break; \
default: \
BUILD_BUG(); \
} \
- __ret; \
+ (__typeof__(*(__ptr)))__ret; \
})
-#define arch_xchg_release(ptr, x) \
-({ \
- __typeof__(*(ptr)) _x_ = (x); \
- (__typeof__(*(ptr))) __xchg_release((ptr), \
- _x_, sizeof(*(ptr))); \
-})
+#define arch_xchg_relaxed(ptr, x) \
+ _arch_xchg(ptr, x, "", "", "", "", "")
-#define __xchg(ptr, new, size) \
-({ \
- __typeof__(ptr) __ptr = (ptr); \
- __typeof__(new) __new = (new); \
- __typeof__(*(ptr)) __ret; \
- switch (size) { \
- case 4: \
- __asm__ __volatile__ ( \
- " amoswap.w.aqrl %0, %2, %1\n" \
- : "=r" (__ret), "+A" (*__ptr) \
- : "r" (__new) \
- : "memory"); \
- break; \
- case 8: \
- __asm__ __volatile__ ( \
- " amoswap.d.aqrl %0, %2, %1\n" \
- : "=r" (__ret), "+A" (*__ptr) \
- : "r" (__new) \
- : "memory"); \
- break; \
- default: \
- BUILD_BUG(); \
- } \
- __ret; \
-})
+#define arch_xchg_acquire(ptr, x) \
+ _arch_xchg(ptr, x, "", "", "", \
+ RISCV_ACQUIRE_BARRIER, RISCV_ACQUIRE_BARRIER)
+
+#define arch_xchg_release(ptr, x) \
+ _arch_xchg(ptr, x, "", "", RISCV_RELEASE_BARRIER, "", "")
#define arch_xchg(ptr, x) \
-({ \
- __typeof__(*(ptr)) _x_ = (x); \
- (__typeof__(*(ptr))) __xchg((ptr), _x_, sizeof(*(ptr))); \
-})
+ _arch_xchg(ptr, x, ".rl", ".aqrl", "", RISCV_FULL_BARRIER, "")
#define xchg32(ptr, x) \
({ \
@@ -163,190 +126,164 @@
* store NEW in MEM. Return the initial value in MEM. Success is
* indicated by comparing RETURN with OLD.
*/
-#define __cmpxchg_relaxed(ptr, old, new, size) \
-({ \
- __typeof__(ptr) __ptr = (ptr); \
- __typeof__(*(ptr)) __old = (old); \
- __typeof__(*(ptr)) __new = (new); \
- __typeof__(*(ptr)) __ret; \
- register unsigned int __rc; \
- switch (size) { \
- case 4: \
- __asm__ __volatile__ ( \
- "0: lr.w %0, %2\n" \
- " bne %0, %z3, 1f\n" \
- " sc.w %1, %z4, %2\n" \
- " bnez %1, 0b\n" \
- "1:\n" \
- : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
- : "rJ" ((long)__old), "rJ" (__new) \
- : "memory"); \
- break; \
- case 8: \
- __asm__ __volatile__ ( \
- "0: lr.d %0, %2\n" \
- " bne %0, %z3, 1f\n" \
- " sc.d %1, %z4, %2\n" \
- " bnez %1, 0b\n" \
- "1:\n" \
- : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
- : "rJ" (__old), "rJ" (__new) \
- : "memory"); \
- break; \
- default: \
- BUILD_BUG(); \
- } \
- __ret; \
-})
-
-#define arch_cmpxchg_relaxed(ptr, o, n) \
-({ \
- __typeof__(*(ptr)) _o_ = (o); \
- __typeof__(*(ptr)) _n_ = (n); \
- (__typeof__(*(ptr))) __cmpxchg_relaxed((ptr), \
- _o_, _n_, sizeof(*(ptr))); \
+#define __arch_cmpxchg_masked(sc_sfx, cas_sfx, \
+ sc_prepend, sc_append, \
+ cas_prepend, cas_append, \
+ r, p, o, n) \
+({ \
+ if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) && \
+ IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) && \
+ riscv_has_extension_unlikely(RISCV_ISA_EXT_ZABHA) && \
+ riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS)) { \
+ r = o; \
+ \
+ __asm__ __volatile__ ( \
+ cas_prepend \
+ " amocas" cas_sfx " %0, %z2, %1\n" \
+ cas_append \
+ : "+&r" (r), "+A" (*(p)) \
+ : "rJ" (n) \
+ : "memory"); \
+ } else { \
+ u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3); \
+ ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE; \
+ ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0) \
+ << __s; \
+ ulong __newx = (ulong)(n) << __s; \
+ ulong __oldx = (ulong)(o) << __s; \
+ ulong __retx; \
+ ulong __rc; \
+ \
+ __asm__ __volatile__ ( \
+ sc_prepend \
+ "0: lr.w %0, %2\n" \
+ " and %1, %0, %z5\n" \
+ " bne %1, %z3, 1f\n" \
+ " and %1, %0, %z6\n" \
+ " or %1, %1, %z4\n" \
+ " sc.w" sc_sfx " %1, %1, %2\n" \
+ " bnez %1, 0b\n" \
+ sc_append \
+ "1:\n" \
+ : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b)) \
+ : "rJ" ((long)__oldx), "rJ" (__newx), \
+ "rJ" (__mask), "rJ" (~__mask) \
+ : "memory"); \
+ \
+ r = (__typeof__(*(p)))((__retx & __mask) >> __s); \
+ } \
})
-#define __cmpxchg_acquire(ptr, old, new, size) \
+#define __arch_cmpxchg(lr_sfx, sc_sfx, cas_sfx, \
+ sc_prepend, sc_append, \
+ cas_prepend, cas_append, \
+ r, p, co, o, n) \
({ \
- __typeof__(ptr) __ptr = (ptr); \
- __typeof__(*(ptr)) __old = (old); \
- __typeof__(*(ptr)) __new = (new); \
- __typeof__(*(ptr)) __ret; \
- register unsigned int __rc; \
- switch (size) { \
- case 4: \
+ if (IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) && \
+ riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS)) { \
+ r = o; \
+ \
__asm__ __volatile__ ( \
- "0: lr.w %0, %2\n" \
- " bne %0, %z3, 1f\n" \
- " sc.w %1, %z4, %2\n" \
- " bnez %1, 0b\n" \
- RISCV_ACQUIRE_BARRIER \
- "1:\n" \
- : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
- : "rJ" ((long)__old), "rJ" (__new) \
+ cas_prepend \
+ " amocas" cas_sfx " %0, %z2, %1\n" \
+ cas_append \
+ : "+&r" (r), "+A" (*(p)) \
+ : "rJ" (n) \
: "memory"); \
- break; \
- case 8: \
+ } else { \
+ register unsigned int __rc; \
+ \
__asm__ __volatile__ ( \
- "0: lr.d %0, %2\n" \
- " bne %0, %z3, 1f\n" \
- " sc.d %1, %z4, %2\n" \
+ sc_prepend \
+ "0: lr" lr_sfx " %0, %2\n" \
+ " bne %0, %z3, 1f\n" \
+ " sc" sc_sfx " %1, %z4, %2\n" \
" bnez %1, 0b\n" \
- RISCV_ACQUIRE_BARRIER \
+ sc_append \
"1:\n" \
- : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
- : "rJ" (__old), "rJ" (__new) \
+ : "=&r" (r), "=&r" (__rc), "+A" (*(p)) \
+ : "rJ" (co o), "rJ" (n) \
: "memory"); \
- break; \
- default: \
- BUILD_BUG(); \
} \
- __ret; \
})
-#define arch_cmpxchg_acquire(ptr, o, n) \
-({ \
- __typeof__(*(ptr)) _o_ = (o); \
- __typeof__(*(ptr)) _n_ = (n); \
- (__typeof__(*(ptr))) __cmpxchg_acquire((ptr), \
- _o_, _n_, sizeof(*(ptr))); \
-})
-
-#define __cmpxchg_release(ptr, old, new, size) \
+#define _arch_cmpxchg(ptr, old, new, sc_sfx, cas_sfx, \
+ sc_prepend, sc_append, \
+ cas_prepend, cas_append) \
({ \
__typeof__(ptr) __ptr = (ptr); \
- __typeof__(*(ptr)) __old = (old); \
- __typeof__(*(ptr)) __new = (new); \
- __typeof__(*(ptr)) __ret; \
- register unsigned int __rc; \
- switch (size) { \
- case 4: \
- __asm__ __volatile__ ( \
- RISCV_RELEASE_BARRIER \
- "0: lr.w %0, %2\n" \
- " bne %0, %z3, 1f\n" \
- " sc.w %1, %z4, %2\n" \
- " bnez %1, 0b\n" \
- "1:\n" \
- : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
- : "rJ" ((long)__old), "rJ" (__new) \
- : "memory"); \
+ __typeof__(*(__ptr)) __old = (old); \
+ __typeof__(*(__ptr)) __new = (new); \
+ __typeof__(*(__ptr)) __ret; \
+ \
+ switch (sizeof(*__ptr)) { \
+ case 1: \
+ __arch_cmpxchg_masked(sc_sfx, ".b" cas_sfx, \
+ sc_prepend, sc_append, \
+ cas_prepend, cas_append, \
+ __ret, __ptr, __old, __new); \
break; \
- case 8: \
- __asm__ __volatile__ ( \
- RISCV_RELEASE_BARRIER \
- "0: lr.d %0, %2\n" \
- " bne %0, %z3, 1f\n" \
- " sc.d %1, %z4, %2\n" \
- " bnez %1, 0b\n" \
- "1:\n" \
- : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
- : "rJ" (__old), "rJ" (__new) \
- : "memory"); \
+ case 2: \
+ __arch_cmpxchg_masked(sc_sfx, ".h" cas_sfx, \
+ sc_prepend, sc_append, \
+ cas_prepend, cas_append, \
+ __ret, __ptr, __old, __new); \
break; \
- default: \
- BUILD_BUG(); \
- } \
- __ret; \
-})
-
-#define arch_cmpxchg_release(ptr, o, n) \
-({ \
- __typeof__(*(ptr)) _o_ = (o); \
- __typeof__(*(ptr)) _n_ = (n); \
- (__typeof__(*(ptr))) __cmpxchg_release((ptr), \
- _o_, _n_, sizeof(*(ptr))); \
-})
-
-#define __cmpxchg(ptr, old, new, size) \
-({ \
- __typeof__(ptr) __ptr = (ptr); \
- __typeof__(*(ptr)) __old = (old); \
- __typeof__(*(ptr)) __new = (new); \
- __typeof__(*(ptr)) __ret; \
- register unsigned int __rc; \
- switch (size) { \
case 4: \
- __asm__ __volatile__ ( \
- "0: lr.w %0, %2\n" \
- " bne %0, %z3, 1f\n" \
- " sc.w.rl %1, %z4, %2\n" \
- " bnez %1, 0b\n" \
- " fence rw, rw\n" \
- "1:\n" \
- : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
- : "rJ" ((long)__old), "rJ" (__new) \
- : "memory"); \
+ __arch_cmpxchg(".w", ".w" sc_sfx, ".w" cas_sfx, \
+ sc_prepend, sc_append, \
+ cas_prepend, cas_append, \
+ __ret, __ptr, (long)(int)(long), __old, __new); \
break; \
case 8: \
- __asm__ __volatile__ ( \
- "0: lr.d %0, %2\n" \
- " bne %0, %z3, 1f\n" \
- " sc.d.rl %1, %z4, %2\n" \
- " bnez %1, 0b\n" \
- " fence rw, rw\n" \
- "1:\n" \
- : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \
- : "rJ" (__old), "rJ" (__new) \
- : "memory"); \
+ __arch_cmpxchg(".d", ".d" sc_sfx, ".d" cas_sfx, \
+ sc_prepend, sc_append, \
+ cas_prepend, cas_append, \
+ __ret, __ptr, /**/, __old, __new); \
break; \
default: \
BUILD_BUG(); \
} \
- __ret; \
+ (__typeof__(*(__ptr)))__ret; \
})
+/*
+ * These macros are here to improve the readability of the arch_cmpxchg_XXX()
+ * macros.
+ */
+#define SC_SFX(x) x
+#define CAS_SFX(x) x
+#define SC_PREPEND(x) x
+#define SC_APPEND(x) x
+#define CAS_PREPEND(x) x
+#define CAS_APPEND(x) x
+
+#define arch_cmpxchg_relaxed(ptr, o, n) \
+ _arch_cmpxchg((ptr), (o), (n), \
+ SC_SFX(""), CAS_SFX(""), \
+ SC_PREPEND(""), SC_APPEND(""), \
+ CAS_PREPEND(""), CAS_APPEND(""))
+
+#define arch_cmpxchg_acquire(ptr, o, n) \
+ _arch_cmpxchg((ptr), (o), (n), \
+ SC_SFX(""), CAS_SFX(""), \
+ SC_PREPEND(""), SC_APPEND(RISCV_ACQUIRE_BARRIER), \
+ CAS_PREPEND(""), CAS_APPEND(RISCV_ACQUIRE_BARRIER))
+
+#define arch_cmpxchg_release(ptr, o, n) \
+ _arch_cmpxchg((ptr), (o), (n), \
+ SC_SFX(""), CAS_SFX(""), \
+ SC_PREPEND(RISCV_RELEASE_BARRIER), SC_APPEND(""), \
+ CAS_PREPEND(RISCV_RELEASE_BARRIER), CAS_APPEND(""))
+
#define arch_cmpxchg(ptr, o, n) \
-({ \
- __typeof__(*(ptr)) _o_ = (o); \
- __typeof__(*(ptr)) _n_ = (n); \
- (__typeof__(*(ptr))) __cmpxchg((ptr), \
- _o_, _n_, sizeof(*(ptr))); \
-})
+ _arch_cmpxchg((ptr), (o), (n), \
+ SC_SFX(".rl"), CAS_SFX(".aqrl"), \
+ SC_PREPEND(""), SC_APPEND(RISCV_FULL_BARRIER), \
+ CAS_PREPEND(""), CAS_APPEND(""))
#define arch_cmpxchg_local(ptr, o, n) \
- (__cmpxchg_relaxed((ptr), (o), (n), sizeof(*(ptr))))
+ arch_cmpxchg_relaxed((ptr), (o), (n))
#define arch_cmpxchg64(ptr, o, n) \
({ \
@@ -360,4 +297,152 @@
arch_cmpxchg_relaxed((ptr), (o), (n)); \
})
+#define arch_cmpxchg64_relaxed(ptr, o, n) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
+ arch_cmpxchg_relaxed((ptr), (o), (n)); \
+})
+
+#define arch_cmpxchg64_acquire(ptr, o, n) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
+ arch_cmpxchg_acquire((ptr), (o), (n)); \
+})
+
+#define arch_cmpxchg64_release(ptr, o, n) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
+ arch_cmpxchg_release((ptr), (o), (n)); \
+})
+
+#if defined(CONFIG_64BIT) && defined(CONFIG_RISCV_ISA_ZACAS)
+
+#define system_has_cmpxchg128() riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS)
+
+union __u128_halves {
+ u128 full;
+ struct {
+ u64 low, high;
+ };
+};
+
+#define __arch_cmpxchg128(p, o, n, cas_sfx) \
+({ \
+ __typeof__(*(p)) __o = (o); \
+ union __u128_halves __hn = { .full = (n) }; \
+ union __u128_halves __ho = { .full = (__o) }; \
+ register unsigned long t1 asm ("t1") = __hn.low; \
+ register unsigned long t2 asm ("t2") = __hn.high; \
+ register unsigned long t3 asm ("t3") = __ho.low; \
+ register unsigned long t4 asm ("t4") = __ho.high; \
+ \
+ __asm__ __volatile__ ( \
+ " amocas.q" cas_sfx " %0, %z3, %2" \
+ : "+&r" (t3), "+&r" (t4), "+A" (*(p)) \
+ : "rJ" (t1), "rJ" (t2) \
+ : "memory"); \
+ \
+ ((u128)t4 << 64) | t3; \
+})
+
+#define arch_cmpxchg128(ptr, o, n) \
+ __arch_cmpxchg128((ptr), (o), (n), ".aqrl")
+
+#define arch_cmpxchg128_local(ptr, o, n) \
+ __arch_cmpxchg128((ptr), (o), (n), "")
+
+#endif /* CONFIG_64BIT && CONFIG_RISCV_ISA_ZACAS */
+
+#ifdef CONFIG_RISCV_ISA_ZAWRS
+/*
+ * Despite wrs.nto being "WRS-with-no-timeout", in the absence of changes to
+ * @val we expect it to still terminate within a "reasonable" amount of time
+ * for an implementation-specific other reason, a pending, locally-enabled
+ * interrupt, or because it has been configured to raise an illegal
+ * instruction exception.
+ */
+static __always_inline void __cmpwait(volatile void *ptr,
+ unsigned long val,
+ int size)
+{
+ unsigned long tmp;
+
+ u32 *__ptr32b;
+ ulong __s, __val, __mask;
+
+ asm goto(ALTERNATIVE("j %l[no_zawrs]", "nop",
+ 0, RISCV_ISA_EXT_ZAWRS, 1)
+ : : : : no_zawrs);
+
+ switch (size) {
+ case 1:
+ __ptr32b = (u32 *)((ulong)(ptr) & ~0x3);
+ __s = ((ulong)(ptr) & 0x3) * BITS_PER_BYTE;
+ __val = val << __s;
+ __mask = 0xff << __s;
+
+ asm volatile(
+ " lr.w %0, %1\n"
+ " and %0, %0, %3\n"
+ " xor %0, %0, %2\n"
+ " bnez %0, 1f\n"
+ ZAWRS_WRS_NTO "\n"
+ "1:"
+ : "=&r" (tmp), "+A" (*(__ptr32b))
+ : "r" (__val), "r" (__mask)
+ : "memory");
+ break;
+ case 2:
+ __ptr32b = (u32 *)((ulong)(ptr) & ~0x3);
+ __s = ((ulong)(ptr) & 0x2) * BITS_PER_BYTE;
+ __val = val << __s;
+ __mask = 0xffff << __s;
+
+ asm volatile(
+ " lr.w %0, %1\n"
+ " and %0, %0, %3\n"
+ " xor %0, %0, %2\n"
+ " bnez %0, 1f\n"
+ ZAWRS_WRS_NTO "\n"
+ "1:"
+ : "=&r" (tmp), "+A" (*(__ptr32b))
+ : "r" (__val), "r" (__mask)
+ : "memory");
+ break;
+ case 4:
+ asm volatile(
+ " lr.w %0, %1\n"
+ " xor %0, %0, %2\n"
+ " bnez %0, 1f\n"
+ ZAWRS_WRS_NTO "\n"
+ "1:"
+ : "=&r" (tmp), "+A" (*(u32 *)ptr)
+ : "r" (val));
+ break;
+#if __riscv_xlen == 64
+ case 8:
+ asm volatile(
+ " lr.d %0, %1\n"
+ " xor %0, %0, %2\n"
+ " bnez %0, 1f\n"
+ ZAWRS_WRS_NTO "\n"
+ "1:"
+ : "=&r" (tmp), "+A" (*(u64 *)ptr)
+ : "r" (val));
+ break;
+#endif
+ default:
+ BUILD_BUG();
+ }
+
+ return;
+
+no_zawrs:
+ asm volatile(RISCV_PAUSE : : : "memory");
+}
+
+#define __cmpwait_relaxed(ptr, val) \
+ __cmpwait((ptr), (unsigned long)(val), sizeof(*(ptr)))
+#endif
+
#endif /* _ASM_RISCV_CMPXCHG_H */
diff --git a/arch/riscv/include/asm/compat.h b/arch/riscv/include/asm/compat.h
index 2ac955b51148..6081327e55f5 100644
--- a/arch/riscv/include/asm/compat.h
+++ b/arch/riscv/include/asm/compat.h
@@ -9,14 +9,32 @@
*/
#include <linux/types.h>
#include <linux/sched.h>
-#include <linux/sched/task_stack.h>
#include <asm-generic/compat.h>
static inline int is_compat_task(void)
{
+ if (!IS_ENABLED(CONFIG_COMPAT))
+ return 0;
+
return test_thread_flag(TIF_32BIT);
}
+static inline int is_compat_thread(struct thread_info *thread)
+{
+ if (!IS_ENABLED(CONFIG_COMPAT))
+ return 0;
+
+ return test_ti_thread_flag(thread, TIF_32BIT);
+}
+
+static inline void set_compat_task(bool is_compat)
+{
+ if (is_compat)
+ set_thread_flag(TIF_32BIT);
+ else
+ clear_thread_flag(TIF_32BIT);
+}
+
struct compat_user_regs_struct {
compat_ulong_t pc;
compat_ulong_t ra;
diff --git a/arch/riscv/include/asm/cpu.h b/arch/riscv/include/asm/cpu.h
new file mode 100644
index 000000000000..28d45a6678ce
--- /dev/null
+++ b/arch/riscv/include/asm/cpu.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef _ASM_CPU_H
+#define _ASM_CPU_H
+
+/* This header is required unconditionally by the ACPI core */
+
+#endif /* _ASM_CPU_H */
diff --git a/arch/riscv/include/asm/cpu_ops.h b/arch/riscv/include/asm/cpu_ops.h
index 134590f1b843..176b570ef982 100644
--- a/arch/riscv/include/asm/cpu_ops.h
+++ b/arch/riscv/include/asm/cpu_ops.h
@@ -13,32 +13,23 @@
/**
* struct cpu_operations - Callback operations for hotplugging CPUs.
*
- * @name: Name of the boot protocol.
- * @cpu_prepare: Early one-time preparation step for a cpu. If there
- * is a mechanism for doing so, tests whether it is
- * possible to boot the given HART.
* @cpu_start: Boots a cpu into the kernel.
- * @cpu_disable: Prepares a cpu to die. May fail for some
- * mechanism-specific reason, which will cause the hot
- * unplug to be aborted. Called from the cpu to be killed.
* @cpu_stop: Makes a cpu leave the kernel. Must not fail. Called from
* the cpu being stopped.
* @cpu_is_stopped: Ensures a cpu has left the kernel. Called from another
* cpu.
*/
struct cpu_operations {
- const char *name;
- int (*cpu_prepare)(unsigned int cpu);
int (*cpu_start)(unsigned int cpu,
struct task_struct *tidle);
#ifdef CONFIG_HOTPLUG_CPU
- int (*cpu_disable)(unsigned int cpu);
void (*cpu_stop)(void);
int (*cpu_is_stopped)(unsigned int cpu);
#endif
};
-extern const struct cpu_operations *cpu_ops[NR_CPUS];
-void __init cpu_set_ops(int cpu);
+extern const struct cpu_operations cpu_ops_spinwait;
+extern const struct cpu_operations *cpu_ops;
+void __init cpu_set_ops(void);
#endif /* ifndef __ASM_CPU_OPS_H */
diff --git a/arch/riscv/include/asm/cpu_ops_sbi.h b/arch/riscv/include/asm/cpu_ops_sbi.h
index 56e4b76d09ff..d6e4665b3195 100644
--- a/arch/riscv/include/asm/cpu_ops_sbi.h
+++ b/arch/riscv/include/asm/cpu_ops_sbi.h
@@ -10,6 +10,8 @@
#include <linux/sched.h>
#include <linux/threads.h>
+extern const struct cpu_operations cpu_ops_sbi;
+
/**
* struct sbi_hart_boot_data - Hart specific boot used during booting and
* cpu hotplug.
diff --git a/arch/riscv/include/asm/cpufeature-macros.h b/arch/riscv/include/asm/cpufeature-macros.h
new file mode 100644
index 000000000000..a8103edbf51f
--- /dev/null
+++ b/arch/riscv/include/asm/cpufeature-macros.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2022-2024 Rivos, Inc
+ */
+
+#ifndef _ASM_CPUFEATURE_MACROS_H
+#define _ASM_CPUFEATURE_MACROS_H
+
+#include <asm/hwcap.h>
+#include <asm/alternative-macros.h>
+
+#define STANDARD_EXT 0
+
+bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, unsigned int bit);
+#define riscv_isa_extension_available(isa_bitmap, ext) \
+ __riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext)
+
+static __always_inline bool __riscv_has_extension_likely(const unsigned long vendor,
+ const unsigned long ext)
+{
+ asm goto(ALTERNATIVE("j %l[l_no]", "nop", %[vendor], %[ext], 1)
+ :
+ : [vendor] "i" (vendor), [ext] "i" (ext)
+ :
+ : l_no);
+
+ return true;
+l_no:
+ return false;
+}
+
+static __always_inline bool __riscv_has_extension_unlikely(const unsigned long vendor,
+ const unsigned long ext)
+{
+ asm goto(ALTERNATIVE("nop", "j %l[l_yes]", %[vendor], %[ext], 1)
+ :
+ : [vendor] "i" (vendor), [ext] "i" (ext)
+ :
+ : l_yes);
+
+ return false;
+l_yes:
+ return true;
+}
+
+static __always_inline bool riscv_has_extension_unlikely(const unsigned long ext)
+{
+ compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX");
+
+ if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE))
+ return __riscv_has_extension_unlikely(STANDARD_EXT, ext);
+
+ return __riscv_isa_extension_available(NULL, ext);
+}
+
+static __always_inline bool riscv_has_extension_likely(const unsigned long ext)
+{
+ compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX");
+
+ if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE))
+ return __riscv_has_extension_likely(STANDARD_EXT, ext);
+
+ return __riscv_isa_extension_available(NULL, ext);
+}
+
+#endif /* _ASM_CPUFEATURE_MACROS_H */
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
new file mode 100644
index 000000000000..fbd0e4306c93
--- /dev/null
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -0,0 +1,153 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2022-2024 Rivos, Inc
+ */
+
+#ifndef _ASM_CPUFEATURE_H
+#define _ASM_CPUFEATURE_H
+
+#include <linux/bitmap.h>
+#include <linux/jump_label.h>
+#include <linux/workqueue.h>
+#include <linux/kconfig.h>
+#include <linux/percpu-defs.h>
+#include <linux/threads.h>
+#include <asm/hwcap.h>
+#include <asm/cpufeature-macros.h>
+
+/*
+ * These are probed via a device_initcall(), via either the SBI or directly
+ * from the corresponding CSRs.
+ */
+struct riscv_cpuinfo {
+ unsigned long mvendorid;
+ unsigned long marchid;
+ unsigned long mimpid;
+};
+
+struct riscv_isainfo {
+ DECLARE_BITMAP(isa, RISCV_ISA_EXT_MAX);
+};
+
+DECLARE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo);
+
+/* Per-cpu ISA extensions. */
+extern struct riscv_isainfo hart_isa[NR_CPUS];
+
+extern u32 thead_vlenb_of;
+
+void __init riscv_user_isa_enable(void);
+
+#define _RISCV_ISA_EXT_DATA(_name, _id, _subset_exts, _subset_exts_size, _validate) { \
+ .name = #_name, \
+ .property = #_name, \
+ .id = _id, \
+ .subset_ext_ids = _subset_exts, \
+ .subset_ext_size = _subset_exts_size, \
+ .validate = _validate \
+}
+
+#define __RISCV_ISA_EXT_DATA(_name, _id) _RISCV_ISA_EXT_DATA(_name, _id, NULL, 0, NULL)
+
+#define __RISCV_ISA_EXT_DATA_VALIDATE(_name, _id, _validate) \
+ _RISCV_ISA_EXT_DATA(_name, _id, NULL, 0, _validate)
+
+/* Used to declare pure "lasso" extension (Zk for instance) */
+#define __RISCV_ISA_EXT_BUNDLE(_name, _bundled_exts) \
+ _RISCV_ISA_EXT_DATA(_name, RISCV_ISA_EXT_INVALID, _bundled_exts, \
+ ARRAY_SIZE(_bundled_exts), NULL)
+#define __RISCV_ISA_EXT_BUNDLE_VALIDATE(_name, _bundled_exts, _validate) \
+ _RISCV_ISA_EXT_DATA(_name, RISCV_ISA_EXT_INVALID, _bundled_exts, \
+ ARRAY_SIZE(_bundled_exts), _validate)
+
+/* Used to declare extensions that are a superset of other extensions (Zvbb for instance) */
+#define __RISCV_ISA_EXT_SUPERSET(_name, _id, _sub_exts) \
+ _RISCV_ISA_EXT_DATA(_name, _id, _sub_exts, ARRAY_SIZE(_sub_exts), NULL)
+#define __RISCV_ISA_EXT_SUPERSET_VALIDATE(_name, _id, _sub_exts, _validate) \
+ _RISCV_ISA_EXT_DATA(_name, _id, _sub_exts, ARRAY_SIZE(_sub_exts), _validate)
+
+bool __init check_unaligned_access_emulated_all_cpus(void);
+void unaligned_access_init(void);
+int cpu_online_unaligned_access_init(unsigned int cpu);
+#if defined(CONFIG_RISCV_SCALAR_MISALIGNED)
+void unaligned_emulation_finish(void);
+bool unaligned_ctl_available(void);
+#else
+static inline bool unaligned_ctl_available(void)
+{
+ return false;
+}
+#endif
+
+#if defined(CONFIG_RISCV_MISALIGNED)
+DECLARE_PER_CPU(long, misaligned_access_speed);
+bool misaligned_traps_can_delegate(void);
+#else
+static inline bool misaligned_traps_can_delegate(void)
+{
+ return false;
+}
+#endif
+
+bool __init check_vector_unaligned_access_emulated_all_cpus(void);
+#if defined(CONFIG_RISCV_VECTOR_MISALIGNED)
+void check_vector_unaligned_access_emulated(struct work_struct *work __always_unused);
+DECLARE_PER_CPU(long, vector_misaligned_access);
+#endif
+
+#if defined(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS)
+DECLARE_STATIC_KEY_FALSE(fast_unaligned_access_speed_key);
+
+static __always_inline bool has_fast_unaligned_accesses(void)
+{
+ return static_branch_likely(&fast_unaligned_access_speed_key);
+}
+#else
+static __always_inline bool has_fast_unaligned_accesses(void)
+{
+ if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
+ return true;
+ else
+ return false;
+}
+#endif
+
+unsigned long riscv_get_elf_hwcap(void);
+
+struct riscv_isa_ext_data {
+ const unsigned int id;
+ const char *name;
+ const char *property;
+ const unsigned int *subset_ext_ids;
+ const unsigned int subset_ext_size;
+ int (*validate)(const struct riscv_isa_ext_data *data, const unsigned long *isa_bitmap);
+};
+
+extern const struct riscv_isa_ext_data riscv_isa_ext[];
+extern const size_t riscv_isa_ext_count;
+extern bool riscv_isa_fallback;
+
+unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap);
+static __always_inline bool riscv_cpu_has_extension_likely(int cpu, const unsigned long ext)
+{
+ compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX");
+
+ if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) &&
+ __riscv_has_extension_likely(STANDARD_EXT, ext))
+ return true;
+
+ return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
+}
+
+static __always_inline bool riscv_cpu_has_extension_unlikely(int cpu, const unsigned long ext)
+{
+ compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX");
+
+ if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) &&
+ __riscv_has_extension_unlikely(STANDARD_EXT, ext))
+ return true;
+
+ return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
+}
+
+#endif
diff --git a/arch/riscv/include/asm/crash_reserve.h b/arch/riscv/include/asm/crash_reserve.h
new file mode 100644
index 000000000000..013962e63587
--- /dev/null
+++ b/arch/riscv/include/asm/crash_reserve.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _RISCV_CRASH_RESERVE_H
+#define _RISCV_CRASH_RESERVE_H
+
+#define CRASH_ALIGN PMD_SIZE
+
+#define CRASH_ADDR_LOW_MAX dma32_phys_limit
+#define CRASH_ADDR_HIGH_MAX memblock_end_of_DRAM()
+
+extern phys_addr_t memblock_end_of_DRAM(void);
+#endif
diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
index 6d85655e7edf..6fed42e37705 100644
--- a/arch/riscv/include/asm/csr.h
+++ b/arch/riscv/include/asm/csr.h
@@ -7,7 +7,7 @@
#define _ASM_RISCV_CSR_H
#include <asm/asm.h>
-#include <linux/const.h>
+#include <linux/bits.h>
/* Status register flags */
#define SR_SIE _AC(0x00000002, UL) /* Supervisor Interrupt Enable */
@@ -24,29 +24,43 @@
#define SR_FS_CLEAN _AC(0x00004000, UL)
#define SR_FS_DIRTY _AC(0x00006000, UL)
+#define SR_VS _AC(0x00000600, UL) /* Vector Status */
+#define SR_VS_OFF _AC(0x00000000, UL)
+#define SR_VS_INITIAL _AC(0x00000200, UL)
+#define SR_VS_CLEAN _AC(0x00000400, UL)
+#define SR_VS_DIRTY _AC(0x00000600, UL)
+
+#define SR_VS_THEAD _AC(0x01800000, UL) /* xtheadvector Status */
+#define SR_VS_OFF_THEAD _AC(0x00000000, UL)
+#define SR_VS_INITIAL_THEAD _AC(0x00800000, UL)
+#define SR_VS_CLEAN_THEAD _AC(0x01000000, UL)
+#define SR_VS_DIRTY_THEAD _AC(0x01800000, UL)
+
#define SR_XS _AC(0x00018000, UL) /* Extension Status */
#define SR_XS_OFF _AC(0x00000000, UL)
#define SR_XS_INITIAL _AC(0x00008000, UL)
#define SR_XS_CLEAN _AC(0x00010000, UL)
#define SR_XS_DIRTY _AC(0x00018000, UL)
+#define SR_FS_VS (SR_FS | SR_VS) /* Vector and Floating-Point Unit */
+
#ifndef CONFIG_64BIT
-#define SR_SD _AC(0x80000000, UL) /* FS/XS dirty */
+#define SR_SD _AC(0x80000000, UL) /* FS/VS/XS dirty */
#else
-#define SR_SD _AC(0x8000000000000000, UL) /* FS/XS dirty */
+#define SR_SD _AC(0x8000000000000000, UL) /* FS/VS/XS dirty */
#endif
#ifdef CONFIG_64BIT
#define SR_UXL _AC(0x300000000, UL) /* XLEN mask for U-mode */
#define SR_UXL_32 _AC(0x100000000, UL) /* XLEN = 32 for U-mode */
#define SR_UXL_64 _AC(0x200000000, UL) /* XLEN = 64 for U-mode */
-#define SR_UXL_SHIFT 32
#endif
/* SATP flags */
#ifndef CONFIG_64BIT
#define SATP_PPN _AC(0x003FFFFF, UL)
#define SATP_MODE_32 _AC(0x80000000, UL)
+#define SATP_MODE_SHIFT 31
#define SATP_ASID_BITS 9
#define SATP_ASID_SHIFT 22
#define SATP_ASID_MASK _AC(0x1FF, UL)
@@ -55,6 +69,7 @@
#define SATP_MODE_39 _AC(0x8000000000000000, UL)
#define SATP_MODE_48 _AC(0x9000000000000000, UL)
#define SATP_MODE_57 _AC(0xa000000000000000, UL)
+#define SATP_MODE_SHIFT 60
#define SATP_ASID_BITS 16
#define SATP_ASID_SHIFT 44
#define SATP_ASID_MASK _AC(0xFFFF, UL)
@@ -73,14 +88,19 @@
#define IRQ_S_EXT 9
#define IRQ_VS_EXT 10
#define IRQ_M_EXT 11
+#define IRQ_S_GEXT 12
#define IRQ_PMU_OVF 13
+#define IRQ_LOCAL_MAX (IRQ_PMU_OVF + 1)
+#define IRQ_LOCAL_MASK GENMASK((IRQ_LOCAL_MAX - 1), 0)
/* Exception causes */
#define EXC_INST_MISALIGNED 0
#define EXC_INST_ACCESS 1
#define EXC_INST_ILLEGAL 2
#define EXC_BREAKPOINT 3
+#define EXC_LOAD_MISALIGNED 4
#define EXC_LOAD_ACCESS 5
+#define EXC_STORE_MISALIGNED 6
#define EXC_STORE_ACCESS 7
#define EXC_SYSCALL 8
#define EXC_HYPERVISOR_SYSCALL 9
@@ -105,6 +125,10 @@
/* HSTATUS flags */
#ifdef CONFIG_64BIT
+#define HSTATUS_HUPMM _AC(0x3000000000000, UL)
+#define HSTATUS_HUPMM_PMLEN_0 _AC(0x0000000000000, UL)
+#define HSTATUS_HUPMM_PMLEN_7 _AC(0x2000000000000, UL)
+#define HSTATUS_HUPMM_PMLEN_16 _AC(0x3000000000000, UL)
#define HSTATUS_VSXL _AC(0x300000000, UL)
#define HSTATUS_VSXL_SHIFT 32
#endif
@@ -128,25 +152,25 @@
#define HGATP32_MODE_SHIFT 31
#define HGATP32_VMID_SHIFT 22
-#define HGATP32_VMID_MASK _AC(0x1FC00000, UL)
-#define HGATP32_PPN _AC(0x003FFFFF, UL)
+#define HGATP32_VMID GENMASK(28, 22)
+#define HGATP32_PPN GENMASK(21, 0)
#define HGATP64_MODE_SHIFT 60
#define HGATP64_VMID_SHIFT 44
-#define HGATP64_VMID_MASK _AC(0x03FFF00000000000, UL)
-#define HGATP64_PPN _AC(0x00000FFFFFFFFFFF, UL)
+#define HGATP64_VMID GENMASK(57, 44)
+#define HGATP64_PPN GENMASK(43, 0)
#define HGATP_PAGE_SHIFT 12
#ifdef CONFIG_64BIT
#define HGATP_PPN HGATP64_PPN
#define HGATP_VMID_SHIFT HGATP64_VMID_SHIFT
-#define HGATP_VMID_MASK HGATP64_VMID_MASK
+#define HGATP_VMID HGATP64_VMID
#define HGATP_MODE_SHIFT HGATP64_MODE_SHIFT
#else
#define HGATP_PPN HGATP32_PPN
#define HGATP_VMID_SHIFT HGATP32_VMID_SHIFT
-#define HGATP_VMID_MASK HGATP32_VMID_MASK
+#define HGATP_VMID HGATP32_VMID
#define HGATP_MODE_SHIFT HGATP32_MODE_SHIFT
#endif
@@ -154,7 +178,64 @@
#define VSIP_TO_HVIP_SHIFT (IRQ_VS_SOFT - IRQ_S_SOFT)
#define VSIP_VALID_MASK ((_AC(1, UL) << IRQ_S_SOFT) | \
(_AC(1, UL) << IRQ_S_TIMER) | \
- (_AC(1, UL) << IRQ_S_EXT))
+ (_AC(1, UL) << IRQ_S_EXT) | \
+ (_AC(1, UL) << IRQ_PMU_OVF))
+
+/* AIA CSR bits */
+#define TOPI_IID_SHIFT 16
+#define TOPI_IID_MASK GENMASK(11, 0)
+#define TOPI_IPRIO_MASK GENMASK(7, 0)
+#define TOPI_IPRIO_BITS 8
+
+#define TOPEI_ID_SHIFT 16
+#define TOPEI_ID_MASK GENMASK(10, 0)
+#define TOPEI_PRIO_MASK GENMASK(10, 0)
+
+#define ISELECT_IPRIO0 0x30
+#define ISELECT_IPRIO15 0x3f
+#define ISELECT_MASK GENMASK(8, 0)
+
+#define HVICTL_VTI BIT(30)
+#define HVICTL_IID GENMASK(27, 16)
+#define HVICTL_IID_SHIFT 16
+#define HVICTL_DPR BIT(9)
+#define HVICTL_IPRIOM BIT(8)
+#define HVICTL_IPRIO GENMASK(7, 0)
+
+/* xENVCFG flags */
+#define ENVCFG_STCE (_AC(1, ULL) << 63)
+#define ENVCFG_PBMTE (_AC(1, ULL) << 62)
+#define ENVCFG_ADUE (_AC(1, ULL) << 61)
+#define ENVCFG_PMM (_AC(0x3, ULL) << 32)
+#define ENVCFG_PMM_PMLEN_0 (_AC(0x0, ULL) << 32)
+#define ENVCFG_PMM_PMLEN_7 (_AC(0x2, ULL) << 32)
+#define ENVCFG_PMM_PMLEN_16 (_AC(0x3, ULL) << 32)
+#define ENVCFG_CBZE (_AC(1, UL) << 7)
+#define ENVCFG_CBCFE (_AC(1, UL) << 6)
+#define ENVCFG_CBIE_SHIFT 4
+#define ENVCFG_CBIE (_AC(0x3, UL) << ENVCFG_CBIE_SHIFT)
+#define ENVCFG_CBIE_ILL _AC(0x0, UL)
+#define ENVCFG_CBIE_FLUSH _AC(0x1, UL)
+#define ENVCFG_CBIE_INV _AC(0x3, UL)
+#define ENVCFG_FIOM _AC(0x1, UL)
+
+/* Smstateen bits */
+#define SMSTATEEN0_AIA_IMSIC_SHIFT 58
+#define SMSTATEEN0_AIA_IMSIC (_ULL(1) << SMSTATEEN0_AIA_IMSIC_SHIFT)
+#define SMSTATEEN0_AIA_SHIFT 59
+#define SMSTATEEN0_AIA (_ULL(1) << SMSTATEEN0_AIA_SHIFT)
+#define SMSTATEEN0_AIA_ISEL_SHIFT 60
+#define SMSTATEEN0_AIA_ISEL (_ULL(1) << SMSTATEEN0_AIA_ISEL_SHIFT)
+#define SMSTATEEN0_HSENVCFG_SHIFT 62
+#define SMSTATEEN0_HSENVCFG (_ULL(1) << SMSTATEEN0_HSENVCFG_SHIFT)
+#define SMSTATEEN0_SSTATEEN0_SHIFT 63
+#define SMSTATEEN0_SSTATEEN0 (_ULL(1) << SMSTATEEN0_SSTATEEN0_SHIFT)
+
+/* mseccfg bits */
+#define MSECCFG_PMM ENVCFG_PMM
+#define MSECCFG_PMM_PMLEN_0 ENVCFG_PMM_PMLEN_0
+#define MSECCFG_PMM_PMLEN_7 ENVCFG_PMM_PMLEN_7
+#define MSECCFG_PMM_PMLEN_16 ENVCFG_PMM_PMLEN_16
/* symbolic CSR names: */
#define CSR_CYCLE 0xc00
@@ -222,12 +303,14 @@
#define CSR_HPMCOUNTER30H 0xc9e
#define CSR_HPMCOUNTER31H 0xc9f
-#define CSR_SSCOUNTOVF 0xda0
+#define CSR_SCOUNTOVF 0xda0
#define CSR_SSTATUS 0x100
#define CSR_SIE 0x104
#define CSR_STVEC 0x105
#define CSR_SCOUNTEREN 0x106
+#define CSR_SENVCFG 0x10a
+#define CSR_SSTATEEN0 0x10c
#define CSR_SSCRATCH 0x140
#define CSR_SEPC 0x141
#define CSR_SCAUSE 0x142
@@ -235,6 +318,30 @@
#define CSR_SIP 0x144
#define CSR_SATP 0x180
+#define CSR_STIMECMP 0x14D
+#define CSR_STIMECMPH 0x15D
+
+/* xtheadvector symbolic CSR names */
+#define CSR_VXSAT 0x9
+#define CSR_VXRM 0xa
+
+/* xtheadvector CSR masks */
+#define CSR_VXRM_MASK 3
+#define CSR_VXRM_SHIFT 1
+#define CSR_VXSAT_MASK 1
+
+/* Supervisor-Level Window to Indirectly Accessed Registers (AIA) */
+#define CSR_SISELECT 0x150
+#define CSR_SIREG 0x151
+
+/* Supervisor-Level Interrupts (AIA) */
+#define CSR_STOPEI 0x15c
+#define CSR_STOPI 0xdb0
+
+/* Supervisor-Level High-Half CSRs (AIA) */
+#define CSR_SIEH 0x114
+#define CSR_SIPH 0x154
+
#define CSR_VSSTATUS 0x200
#define CSR_VSIE 0x204
#define CSR_VSTVEC 0x205
@@ -244,6 +351,8 @@
#define CSR_VSTVAL 0x243
#define CSR_VSIP 0x244
#define CSR_VSATP 0x280
+#define CSR_VSTIMECMP 0x24D
+#define CSR_VSTIMECMPH 0x25D
#define CSR_HSTATUS 0x600
#define CSR_HEDELEG 0x602
@@ -252,7 +361,9 @@
#define CSR_HTIMEDELTA 0x605
#define CSR_HCOUNTEREN 0x606
#define CSR_HGEIE 0x607
+#define CSR_HENVCFG 0x60a
#define CSR_HTIMEDELTAH 0x615
+#define CSR_HENVCFGH 0x61a
#define CSR_HTVAL 0x643
#define CSR_HIP 0x644
#define CSR_HVIP 0x645
@@ -260,10 +371,40 @@
#define CSR_HGATP 0x680
#define CSR_HGEIP 0xe12
+/* Virtual Interrupts and Interrupt Priorities (H-extension with AIA) */
+#define CSR_HVIEN 0x608
+#define CSR_HVICTL 0x609
+#define CSR_HVIPRIO1 0x646
+#define CSR_HVIPRIO2 0x647
+
+/* VS-Level Window to Indirectly Accessed Registers (H-extension with AIA) */
+#define CSR_VSISELECT 0x250
+#define CSR_VSIREG 0x251
+
+/* VS-Level Interrupts (H-extension with AIA) */
+#define CSR_VSTOPEI 0x25c
+#define CSR_VSTOPI 0xeb0
+
+/* Hypervisor and VS-Level High-Half CSRs (H-extension with AIA) */
+#define CSR_HIDELEGH 0x613
+#define CSR_HVIENH 0x618
+#define CSR_HVIPH 0x655
+#define CSR_HVIPRIO1H 0x656
+#define CSR_HVIPRIO2H 0x657
+#define CSR_VSIEH 0x214
+#define CSR_VSIPH 0x254
+
+/* Hypervisor stateen CSRs */
+#define CSR_HSTATEEN0 0x60c
+#define CSR_HSTATEEN0H 0x61c
+
#define CSR_MSTATUS 0x300
#define CSR_MISA 0x301
+#define CSR_MIDELEG 0x303
#define CSR_MIE 0x304
#define CSR_MTVEC 0x305
+#define CSR_MENVCFG 0x30a
+#define CSR_MENVCFGH 0x31a
#define CSR_MSCRATCH 0x340
#define CSR_MEPC 0x341
#define CSR_MCAUSE 0x342
@@ -271,21 +412,65 @@
#define CSR_MIP 0x344
#define CSR_PMPCFG0 0x3a0
#define CSR_PMPADDR0 0x3b0
+#define CSR_MSECCFG 0x747
+#define CSR_MSECCFGH 0x757
#define CSR_MVENDORID 0xf11
#define CSR_MARCHID 0xf12
#define CSR_MIMPID 0xf13
#define CSR_MHARTID 0xf14
+/* Machine-Level Window to Indirectly Accessed Registers (AIA) */
+#define CSR_MISELECT 0x350
+#define CSR_MIREG 0x351
+
+/* Machine-Level Interrupts (AIA) */
+#define CSR_MTOPEI 0x35c
+#define CSR_MTOPI 0xfb0
+
+/* Virtual Interrupts for Supervisor Level (AIA) */
+#define CSR_MVIEN 0x308
+#define CSR_MVIP 0x309
+
+/* Machine-Level High-Half CSRs (AIA) */
+#define CSR_MIDELEGH 0x313
+#define CSR_MIEH 0x314
+#define CSR_MVIENH 0x318
+#define CSR_MVIPH 0x319
+#define CSR_MIPH 0x354
+
+#define CSR_VSTART 0x8
+#define CSR_VCSR 0xf
+#define CSR_VL 0xc20
+#define CSR_VTYPE 0xc21
+#define CSR_VLENB 0xc22
+
+/* Scalar Crypto Extension - Entropy */
+#define CSR_SEED 0x015
+#define SEED_OPST_MASK _AC(0xC0000000, UL)
+#define SEED_OPST_BIST _AC(0x00000000, UL)
+#define SEED_OPST_WAIT _AC(0x40000000, UL)
+#define SEED_OPST_ES16 _AC(0x80000000, UL)
+#define SEED_OPST_DEAD _AC(0xC0000000, UL)
+#define SEED_ENTROPY_MASK _AC(0xFFFF, UL)
+
#ifdef CONFIG_RISCV_M_MODE
# define CSR_STATUS CSR_MSTATUS
# define CSR_IE CSR_MIE
# define CSR_TVEC CSR_MTVEC
+# define CSR_ENVCFG CSR_MENVCFG
# define CSR_SCRATCH CSR_MSCRATCH
# define CSR_EPC CSR_MEPC
# define CSR_CAUSE CSR_MCAUSE
# define CSR_TVAL CSR_MTVAL
# define CSR_IP CSR_MIP
+# define CSR_IEH CSR_MIEH
+# define CSR_ISELECT CSR_MISELECT
+# define CSR_IREG CSR_MIREG
+# define CSR_IPH CSR_MIPH
+# define CSR_TOPEI CSR_MTOPEI
+# define CSR_TOPI CSR_MTOPI
+
# define SR_IE SR_MIE
# define SR_PIE SR_MPIE
# define SR_PP SR_MPP
@@ -297,12 +482,20 @@
# define CSR_STATUS CSR_SSTATUS
# define CSR_IE CSR_SIE
# define CSR_TVEC CSR_STVEC
+# define CSR_ENVCFG CSR_SENVCFG
# define CSR_SCRATCH CSR_SSCRATCH
# define CSR_EPC CSR_SEPC
# define CSR_CAUSE CSR_SCAUSE
# define CSR_TVAL CSR_STVAL
# define CSR_IP CSR_SIP
+# define CSR_IEH CSR_SIEH
+# define CSR_ISELECT CSR_SISELECT
+# define CSR_IREG CSR_SIREG
+# define CSR_IPH CSR_SIPH
+# define CSR_TOPEI CSR_STOPEI
+# define CSR_TOPI CSR_STOPI
+
# define SR_IE SR_SIE
# define SR_PIE SR_SPIE
# define SR_PP SR_SPP
diff --git a/arch/riscv/include/asm/dma-noncoherent.h b/arch/riscv/include/asm/dma-noncoherent.h
new file mode 100644
index 000000000000..312cfa0858fb
--- /dev/null
+++ b/arch/riscv/include/asm/dma-noncoherent.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 Renesas Electronics Corp.
+ */
+
+#ifndef __ASM_DMA_NONCOHERENT_H
+#define __ASM_DMA_NONCOHERENT_H
+
+#include <linux/dma-direct.h>
+
+/*
+ * struct riscv_nonstd_cache_ops - Structure for non-standard CMO function pointers
+ *
+ * @wback: Function pointer for cache writeback
+ * @inv: Function pointer for invalidating cache
+ * @wback_inv: Function pointer for flushing the cache (writeback + invalidating)
+ */
+struct riscv_nonstd_cache_ops {
+ void (*wback)(phys_addr_t paddr, size_t size);
+ void (*inv)(phys_addr_t paddr, size_t size);
+ void (*wback_inv)(phys_addr_t paddr, size_t size);
+};
+
+extern struct riscv_nonstd_cache_ops noncoherent_cache_ops;
+
+void riscv_noncoherent_register_cache_ops(const struct riscv_nonstd_cache_ops *ops);
+
+#endif /* __ASM_DMA_NONCOHERENT_H */
diff --git a/arch/riscv/include/asm/dmi.h b/arch/riscv/include/asm/dmi.h
new file mode 100644
index 000000000000..ca7cce557ef7
--- /dev/null
+++ b/arch/riscv/include/asm/dmi.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2024 Intel Corporation
+ *
+ * based on arch/arm64/include/asm/dmi.h
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#ifndef __ASM_DMI_H
+#define __ASM_DMI_H
+
+#include <linux/io.h>
+#include <linux/slab.h>
+
+#define dmi_early_remap(x, l) memremap(x, l, MEMREMAP_WB)
+#define dmi_early_unmap(x, l) memunmap(x)
+#define dmi_remap(x, l) memremap(x, l, MEMREMAP_WB)
+#define dmi_unmap(x) memunmap(x)
+#define dmi_alloc(l) kzalloc(l, GFP_KERNEL)
+
+#endif
diff --git a/arch/riscv/include/asm/efi.h b/arch/riscv/include/asm/efi.h
index f74879a8f1ea..46a355913b27 100644
--- a/arch/riscv/include/asm/efi.h
+++ b/arch/riscv/include/asm/efi.h
@@ -10,6 +10,7 @@
#include <asm/mmu_context.h>
#include <asm/ptrace.h>
#include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
#ifdef CONFIG_EFI
extern void efi_init(void);
@@ -18,10 +19,7 @@ extern void efi_init(void);
#endif
int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md);
-int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md);
-
-#define arch_efi_call_virt_setup() efi_virtmap_load()
-#define arch_efi_call_virt_teardown() efi_virtmap_unload()
+int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md, bool);
#define ARCH_EFI_IRQ_FLAGS_MASK (SR_IE | SR_SPIE)
@@ -31,13 +29,22 @@ static inline unsigned long efi_get_max_initrd_addr(unsigned long image_addr)
return ULONG_MAX;
}
-#define alloc_screen_info(x...) (&screen_info)
-
-static inline void free_screen_info(struct screen_info *si)
+static inline unsigned long efi_get_kimg_min_align(void)
{
+ /*
+ * RISC-V requires the kernel image to placed 2 MB aligned base for 64
+ * bit and 4MB for 32 bit.
+ */
+ return IS_ENABLED(CONFIG_64BIT) ? SZ_2M : SZ_4M;
}
-void efi_virtmap_load(void);
-void efi_virtmap_unload(void);
+#define EFI_KIMG_PREFERRED_ADDRESS efi_get_kimg_min_align()
+
+void arch_efi_call_virt_setup(void);
+void arch_efi_call_virt_teardown(void);
+
+unsigned long stext_offset(void);
+
+void efi_icache_sync(unsigned long start, unsigned long end);
#endif /* _ASM_EFI_H */
diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h
index 14fc7342490b..c7aea7886d22 100644
--- a/arch/riscv/include/asm/elf.h
+++ b/arch/riscv/include/asm/elf.h
@@ -14,6 +14,7 @@
#include <asm/auxvec.h>
#include <asm/byteorder.h>
#include <asm/cacheinfo.h>
+#include <asm/cpufeature.h>
/*
* These are used to set parameters in the core dumps.
@@ -40,6 +41,7 @@ extern bool compat_elf_check_arch(Elf32_Ehdr *hdr);
#define compat_elf_check_arch compat_elf_check_arch
#define CORE_DUMP_USE_REGSET
+#define ELF_FDPIC_CORE_EFLAGS 0
#define ELF_EXEC_PAGESIZE (PAGE_SIZE)
/*
@@ -48,25 +50,29 @@ extern bool compat_elf_check_arch(Elf32_Ehdr *hdr);
* the loader. We need to make sure that it is out of the way of the program
* that it will "exec", and that there is sufficient room for the brk.
*/
-#define ELF_ET_DYN_BASE ((TASK_SIZE / 3) * 2)
+#define ELF_ET_DYN_BASE ((DEFAULT_MAP_WINDOW / 3) * 2)
#ifdef CONFIG_64BIT
-#ifdef CONFIG_COMPAT
-#define STACK_RND_MASK (test_thread_flag(TIF_32BIT) ? \
+#define STACK_RND_MASK (is_compat_task() ? \
0x7ff >> (PAGE_SHIFT - 12) : \
0x3ffff >> (PAGE_SHIFT - 12))
-#else
-#define STACK_RND_MASK (0x3ffff >> (PAGE_SHIFT - 12))
-#endif
#endif
+
/*
- * This yields a mask that user programs can use to figure out what
- * instruction set this CPU supports. This could be done in user space,
- * but it's not easy, and we've already done it here.
+ * Provides information on the availiable set of ISA extensions to userspace,
+ * via a bitmap that coorespends to each single-letter ISA extension. This is
+ * essentially defunct, but will remain for compatibility with userspace.
*/
-#define ELF_HWCAP (elf_hwcap)
+#define ELF_HWCAP riscv_get_elf_hwcap()
extern unsigned long elf_hwcap;
+#define ELF_FDPIC_PLAT_INIT(_r, _exec_map_addr, _interp_map_addr, dynamic_addr) \
+ do { \
+ (_r)->a1 = _exec_map_addr; \
+ (_r)->a2 = _interp_map_addr; \
+ (_r)->a3 = dynamic_addr; \
+ } while (0)
+
/*
* This yields a string that ld.so will use to load implementation
* specific libraries for optimization. This is more specific in
@@ -76,7 +82,6 @@ extern unsigned long elf_hwcap;
#define COMPAT_ELF_PLATFORM (NULL)
-#ifdef CONFIG_MMU
#define ARCH_DLINFO \
do { \
/* \
@@ -99,7 +104,22 @@ do { \
get_cache_size(2, CACHE_TYPE_UNIFIED)); \
NEW_AUX_ENT(AT_L2_CACHEGEOMETRY, \
get_cache_geometry(2, CACHE_TYPE_UNIFIED)); \
+ NEW_AUX_ENT(AT_L3_CACHESIZE, \
+ get_cache_size(3, CACHE_TYPE_UNIFIED)); \
+ NEW_AUX_ENT(AT_L3_CACHEGEOMETRY, \
+ get_cache_geometry(3, CACHE_TYPE_UNIFIED)); \
+ /* \
+ * Should always be nonzero unless there's a kernel bug. \
+ * If we haven't determined a sensible value to give to \
+ * userspace, omit the entry: \
+ */ \
+ if (likely(signal_minsigstksz)) \
+ NEW_AUX_ENT(AT_MINSIGSTKSZ, signal_minsigstksz); \
+ else \
+ NEW_AUX_ENT(AT_IGNORE, 0); \
} while (0)
+
+#ifdef CONFIG_MMU
#define ARCH_HAS_SETUP_ADDITIONAL_PAGES
struct linux_binprm;
extern int arch_setup_additional_pages(struct linux_binprm *bprm,
@@ -115,10 +135,7 @@ do { \
#ifdef CONFIG_COMPAT
#define SET_PERSONALITY(ex) \
-do { if ((ex).e_ident[EI_CLASS] == ELFCLASS32) \
- set_thread_flag(TIF_32BIT); \
- else \
- clear_thread_flag(TIF_32BIT); \
+do { set_compat_task((ex).e_ident[EI_CLASS] == ELFCLASS32); \
if (personality(current->personality) != PER_LINUX32) \
set_personality(PER_LINUX | \
(current->personality & (~PER_MASK))); \
diff --git a/arch/riscv/include/asm/entry-common.h b/arch/riscv/include/asm/entry-common.h
new file mode 100644
index 000000000000..b28ccc6cdeea
--- /dev/null
+++ b/arch/riscv/include/asm/entry-common.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_RISCV_ENTRY_COMMON_H
+#define _ASM_RISCV_ENTRY_COMMON_H
+
+#include <asm/stacktrace.h>
+#include <asm/thread_info.h>
+#include <asm/vector.h>
+
+static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
+ unsigned long ti_work)
+{
+ if (ti_work & _TIF_RISCV_V_DEFER_RESTORE) {
+ clear_thread_flag(TIF_RISCV_V_DEFER_RESTORE);
+ /*
+ * We are already called with irq disabled, so go without
+ * keeping track of riscv_v_flags.
+ */
+ riscv_v_vstate_restore(&current->thread.vstate, regs);
+ }
+}
+
+#define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare
+
+void handle_page_fault(struct pt_regs *regs);
+void handle_break(struct pt_regs *regs);
+
+#ifdef CONFIG_RISCV_MISALIGNED
+int handle_misaligned_load(struct pt_regs *regs);
+int handle_misaligned_store(struct pt_regs *regs);
+#else
+static inline int handle_misaligned_load(struct pt_regs *regs)
+{
+ return -1;
+}
+
+static inline int handle_misaligned_store(struct pt_regs *regs)
+{
+ return -1;
+}
+#endif
+
+#endif /* _ASM_RISCV_ENTRY_COMMON_H */
diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
index 416ead0f9a65..6e426ed7919a 100644
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -6,8 +6,16 @@
#define ASM_ERRATA_LIST_H
#include <asm/alternative.h>
+#include <asm/csr.h>
+#include <asm/insn-def.h>
+#include <asm/hwcap.h>
#include <asm/vendorid_list.h>
+#ifdef CONFIG_ERRATA_ANDES
+#define ERRATA_ANDES_NO_IOCP 0
+#define ERRATA_ANDES_NUMBER 1
+#endif
+
#ifdef CONFIG_ERRATA_SIFIVE
#define ERRATA_SIFIVE_CIP_453 0
#define ERRATA_SIFIVE_CIP_1200 1
@@ -15,13 +23,12 @@
#endif
#ifdef CONFIG_ERRATA_THEAD
-#define ERRATA_THEAD_PBMT 0
-#define ERRATA_THEAD_NUMBER 1
+#define ERRATA_THEAD_MAE 0
+#define ERRATA_THEAD_PMU 1
+#define ERRATA_THEAD_GHOSTWRITE 2
+#define ERRATA_THEAD_NUMBER 3
#endif
-#define CPUFEATURE_SVPBMT 0
-#define CPUFEATURE_NUMBER 1
-
#ifdef __ASSEMBLY__
#define ALT_INSN_FAULT(x) \
@@ -37,30 +44,40 @@ ALTERNATIVE(__stringify(RISCV_PTR do_page_fault), \
CONFIG_ERRATA_SIFIVE_CIP_453)
#else /* !__ASSEMBLY__ */
-#define ALT_FLUSH_TLB_PAGE(x) \
+#define ALT_SFENCE_VMA_ASID(asid) \
+asm(ALTERNATIVE("sfence.vma x0, %0", "sfence.vma", SIFIVE_VENDOR_ID, \
+ ERRATA_SIFIVE_CIP_1200, CONFIG_ERRATA_SIFIVE_CIP_1200) \
+ : : "r" (asid) : "memory")
+
+#define ALT_SFENCE_VMA_ADDR(addr) \
asm(ALTERNATIVE("sfence.vma %0", "sfence.vma", SIFIVE_VENDOR_ID, \
ERRATA_SIFIVE_CIP_1200, CONFIG_ERRATA_SIFIVE_CIP_1200) \
: : "r" (addr) : "memory")
+#define ALT_SFENCE_VMA_ADDR_ASID(addr, asid) \
+asm(ALTERNATIVE("sfence.vma %0, %1", "sfence.vma", SIFIVE_VENDOR_ID, \
+ ERRATA_SIFIVE_CIP_1200, CONFIG_ERRATA_SIFIVE_CIP_1200) \
+ : : "r" (addr), "r" (asid) : "memory")
+
/*
* _val is marked as "will be overwritten", so need to set it to 0
* in the default case.
*/
#define ALT_SVPBMT_SHIFT 61
-#define ALT_THEAD_PBMT_SHIFT 59
+#define ALT_THEAD_MAE_SHIFT 59
#define ALT_SVPBMT(_val, prot) \
asm(ALTERNATIVE_2("li %0, 0\t\nnop", \
"li %0, %1\t\nslli %0,%0,%3", 0, \
- CPUFEATURE_SVPBMT, CONFIG_RISCV_ISA_SVPBMT, \
+ RISCV_ISA_EXT_SVPBMT, CONFIG_RISCV_ISA_SVPBMT, \
"li %0, %2\t\nslli %0,%0,%4", THEAD_VENDOR_ID, \
- ERRATA_THEAD_PBMT, CONFIG_ERRATA_THEAD_PBMT) \
+ ERRATA_THEAD_MAE, CONFIG_ERRATA_THEAD_MAE) \
: "=r"(_val) \
: "I"(prot##_SVPBMT >> ALT_SVPBMT_SHIFT), \
- "I"(prot##_THEAD >> ALT_THEAD_PBMT_SHIFT), \
+ "I"(prot##_THEAD >> ALT_THEAD_MAE_SHIFT), \
"I"(ALT_SVPBMT_SHIFT), \
- "I"(ALT_THEAD_PBMT_SHIFT))
+ "I"(ALT_THEAD_MAE_SHIFT))
-#ifdef CONFIG_ERRATA_THEAD_PBMT
+#ifdef CONFIG_ERRATA_THEAD_MAE
/*
* IO/NOCACHE memory types are handled together with svpbmt,
* so on T-Head chips, check if no other memory type is set,
@@ -68,13 +85,7 @@ asm(ALTERNATIVE_2("li %0, 0\t\nnop", \
*/
#define ALT_THEAD_PMA(_val) \
asm volatile(ALTERNATIVE( \
- "nop\n\t" \
- "nop\n\t" \
- "nop\n\t" \
- "nop\n\t" \
- "nop\n\t" \
- "nop\n\t" \
- "nop", \
+ __nops(7), \
"li t3, %1\n\t" \
"slli t3, t3, %3\n\t" \
"and t3, %0, t3\n\t" \
@@ -83,16 +94,35 @@ asm volatile(ALTERNATIVE( \
"slli t3, t3, %3\n\t" \
"or %0, %0, t3\n\t" \
"2:", THEAD_VENDOR_ID, \
- ERRATA_THEAD_PBMT, CONFIG_ERRATA_THEAD_PBMT) \
+ ERRATA_THEAD_MAE, CONFIG_ERRATA_THEAD_MAE) \
: "+r"(_val) \
- : "I"(_PAGE_MTMASK_THEAD >> ALT_THEAD_PBMT_SHIFT), \
- "I"(_PAGE_PMA_THEAD >> ALT_THEAD_PBMT_SHIFT), \
- "I"(ALT_THEAD_PBMT_SHIFT) \
+ : "I"(_PAGE_MTMASK_THEAD >> ALT_THEAD_MAE_SHIFT), \
+ "I"(_PAGE_PMA_THEAD >> ALT_THEAD_MAE_SHIFT), \
+ "I"(ALT_THEAD_MAE_SHIFT) \
: "t3")
#else
#define ALT_THEAD_PMA(_val)
#endif
+#define ALT_CMO_OP(_op, _start, _size, _cachesize) \
+asm volatile(ALTERNATIVE( \
+ __nops(5), \
+ "mv a0, %1\n\t" \
+ "j 2f\n\t" \
+ "3:\n\t" \
+ CBO_##_op(a0) \
+ "add a0, a0, %0\n\t" \
+ "2:\n\t" \
+ "bltu a0, %2, 3b\n\t", \
+ 0, RISCV_ISA_EXT_ZICBOM, CONFIG_RISCV_ISA_ZICBOM) \
+ : : "r"(_cachesize), \
+ "r"((unsigned long)(_start) & ~((_cachesize) - 1UL)), \
+ "r"((unsigned long)(_start) + (_size)) \
+ : "a0")
+
+#define THEAD_C9XX_RV_IRQ_PMU 17
+#define THEAD_C9XX_CSR_SCOUNTEROF 0x5c5
+
#endif /* __ASSEMBLY__ */
#endif
diff --git a/arch/riscv/include/asm/exec.h b/arch/riscv/include/asm/exec.h
new file mode 100644
index 000000000000..07d9942682e0
--- /dev/null
+++ b/arch/riscv/include/asm/exec.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_EXEC_H
+#define __ASM_EXEC_H
+
+extern unsigned long arch_align_stack(unsigned long sp);
+
+#endif /* __ASM_EXEC_H */
diff --git a/arch/riscv/include/asm/extable.h b/arch/riscv/include/asm/extable.h
index 512012d193dc..3eb5c1f7bf34 100644
--- a/arch/riscv/include/asm/extable.h
+++ b/arch/riscv/include/asm/extable.h
@@ -32,7 +32,11 @@ do { \
(b)->data = (tmp).data; \
} while (0)
+#ifdef CONFIG_MMU
bool fixup_exception(struct pt_regs *regs);
+#else
+static inline bool fixup_exception(struct pt_regs *regs) { return false; }
+#endif
#if defined(CONFIG_BPF_JIT) && defined(CONFIG_ARCH_RV64I)
bool ex_handler_bpf(const struct exception_table_entry *ex, struct pt_regs *regs);
diff --git a/arch/riscv/include/asm/fence.h b/arch/riscv/include/asm/fence.h
index 2b443a3a487f..182db7930edc 100644
--- a/arch/riscv/include/asm/fence.h
+++ b/arch/riscv/include/asm/fence.h
@@ -1,12 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
#ifndef _ASM_RISCV_FENCE_H
#define _ASM_RISCV_FENCE_H
+#define RISCV_FENCE_ASM(p, s) "\tfence " #p "," #s "\n"
+#define RISCV_FENCE(p, s) \
+ ({ __asm__ __volatile__ (RISCV_FENCE_ASM(p, s) : : : "memory"); })
+
#ifdef CONFIG_SMP
-#define RISCV_ACQUIRE_BARRIER "\tfence r , rw\n"
-#define RISCV_RELEASE_BARRIER "\tfence rw, w\n"
+#define RISCV_ACQUIRE_BARRIER RISCV_FENCE_ASM(r, rw)
+#define RISCV_RELEASE_BARRIER RISCV_FENCE_ASM(rw, w)
+#define RISCV_FULL_BARRIER RISCV_FENCE_ASM(rw, rw)
#else
#define RISCV_ACQUIRE_BARRIER
#define RISCV_RELEASE_BARRIER
+#define RISCV_FULL_BARRIER
#endif
#endif /* _ASM_RISCV_FENCE_H */
diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h
index 5c3e7b97fcc6..0a55099bb734 100644
--- a/arch/riscv/include/asm/fixmap.h
+++ b/arch/riscv/include/asm/fixmap.h
@@ -22,6 +22,14 @@
*/
enum fixed_addresses {
FIX_HOLE,
+ /*
+ * The fdt fixmap mapping must be PMD aligned and will be mapped
+ * using PMD entries in fixmap_pmd in 64-bit and a PGD entry in 32-bit.
+ */
+ FIX_FDT_END,
+ FIX_FDT = FIX_FDT_END + FIX_FDT_SIZE / PAGE_SIZE - 1,
+
+ /* Below fixmaps will be mapped using fixmap_pte */
FIX_PTE,
FIX_PMD,
FIX_PUD,
diff --git a/arch/riscv/include/asm/fpu.h b/arch/riscv/include/asm/fpu.h
new file mode 100644
index 000000000000..91c04c244e12
--- /dev/null
+++ b/arch/riscv/include/asm/fpu.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 SiFive
+ */
+
+#ifndef _ASM_RISCV_FPU_H
+#define _ASM_RISCV_FPU_H
+
+#include <asm/switch_to.h>
+
+#define kernel_fpu_available() has_fpu()
+
+void kernel_fpu_begin(void);
+void kernel_fpu_end(void);
+
+#endif /* ! _ASM_RISCV_FPU_H */
diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h
index 04dad3380041..22ebea3c2b26 100644
--- a/arch/riscv/include/asm/ftrace.h
+++ b/arch/riscv/include/asm/ftrace.h
@@ -11,24 +11,38 @@
#if defined(CONFIG_FUNCTION_GRAPH_TRACER) && defined(CONFIG_FRAME_POINTER)
#define HAVE_FUNCTION_GRAPH_FP_TEST
#endif
-#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
+
+#define ARCH_SUPPORTS_FTRACE_OPS 1
+#ifndef __ASSEMBLY__
+
+extern void *return_address(unsigned int level);
+
+#define ftrace_return_address(n) return_address(n)
+
+void _mcount(void);
+unsigned long ftrace_call_adjust(unsigned long addr);
+unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip);
+#define ftrace_get_symaddr(fentry_ip) arch_ftrace_get_symaddr(fentry_ip)
/*
- * Clang prior to 13 had "mcount" instead of "_mcount":
- * https://reviews.llvm.org/D98881
+ * Let's do like x86/arm64 and ignore the compat syscalls.
*/
-#if defined(CONFIG_CC_IS_GCC) || CONFIG_CLANG_VERSION >= 130000
-#define MCOUNT_NAME _mcount
-#else
-#define MCOUNT_NAME mcount
-#endif
+#define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS
+static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs)
+{
+ return is_compat_task();
+}
-#define ARCH_SUPPORTS_FTRACE_OPS 1
-#ifndef __ASSEMBLY__
-void MCOUNT_NAME(void);
-static inline unsigned long ftrace_call_adjust(unsigned long addr)
+#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME
+static inline bool arch_syscall_match_sym_name(const char *sym,
+ const char *name)
{
- return addr;
+ /*
+ * Since all syscall functions have __riscv_ prefix, we must skip it.
+ * However, as we described above, we decided to ignore compat
+ * syscalls, so we don't care about __riscv_compat_ prefix here.
+ */
+ return !strcmp(sym + 8, name);
}
struct dyn_arch_ftrace {
@@ -42,47 +56,187 @@ struct dyn_arch_ftrace {
* 2) jalr: setting low-12 offset to ra, jump to ra, and set ra to
* return address (original pc + 4)
*
+ * The first 2 instructions for each tracable function is compiled to 2 nop
+ * instructions. Then, the kernel initializes the first instruction to auipc at
+ * boot time (<ftrace disable>). The second instruction is patched to jalr to
+ * start the trace.
+ *
+ *<Image>:
+ * 0: nop
+ * 4: nop
+ *
+ *<ftrace enable>:
+ * 0: auipc t0, 0x?
+ * 4: jalr t0, ?(t0)
+ *
+ *<ftrace disable>:
+ * 0: auipc t0, 0x?
+ * 4: nop
+ *
* Dynamic ftrace generates probes to call sites, so we must deal with
* both auipc and jalr at the same time.
*/
-#define MCOUNT_ADDR ((unsigned long)MCOUNT_NAME)
+#define MCOUNT_ADDR ((unsigned long)_mcount)
#define JALR_SIGN_MASK (0x00000800)
#define JALR_OFFSET_MASK (0x00000fff)
#define AUIPC_OFFSET_MASK (0xfffff000)
#define AUIPC_PAD (0x00001000)
#define JALR_SHIFT 20
-#define JALR_BASIC (0x000080e7)
-#define AUIPC_BASIC (0x00000097)
-#define NOP4 (0x00000013)
-
-#define make_call(caller, callee, call) \
-do { \
- call[0] = to_auipc_insn((unsigned int)((unsigned long)callee - \
- (unsigned long)caller)); \
- call[1] = to_jalr_insn((unsigned int)((unsigned long)callee - \
- (unsigned long)caller)); \
-} while (0)
+#define JALR_T0 (0x000282e7)
+#define AUIPC_T0 (0x00000297)
+#define JALR_RANGE (JALR_SIGN_MASK - 1)
-#define to_jalr_insn(offset) \
- (((offset & JALR_OFFSET_MASK) << JALR_SHIFT) | JALR_BASIC)
+#define to_jalr_t0(offset) \
+ (((offset & JALR_OFFSET_MASK) << JALR_SHIFT) | JALR_T0)
-#define to_auipc_insn(offset) \
+#define to_auipc_t0(offset) \
((offset & JALR_SIGN_MASK) ? \
- (((offset & AUIPC_OFFSET_MASK) + AUIPC_PAD) | AUIPC_BASIC) : \
- ((offset & AUIPC_OFFSET_MASK) | AUIPC_BASIC))
+ (((offset & AUIPC_OFFSET_MASK) + AUIPC_PAD) | AUIPC_T0) : \
+ ((offset & AUIPC_OFFSET_MASK) | AUIPC_T0))
+
+#define make_call_t0(caller, callee, call) \
+do { \
+ unsigned int offset = \
+ (unsigned long) (callee) - (unsigned long) (caller); \
+ call[0] = to_auipc_t0(offset); \
+ call[1] = to_jalr_t0(offset); \
+} while (0)
/*
- * Let auipc+jalr be the basic *mcount unit*, so we make it 8 bytes here.
+ * Only the jalr insn in the auipc+jalr is patched, so we make it 4
+ * bytes here.
*/
-#define MCOUNT_INSN_SIZE 8
+#define MCOUNT_INSN_SIZE 4
+#define MCOUNT_AUIPC_SIZE 4
+#define MCOUNT_JALR_SIZE 4
+#define MCOUNT_NOP4_SIZE 4
#ifndef __ASSEMBLY__
struct dyn_ftrace;
int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
#define ftrace_init_nop ftrace_init_nop
-#endif
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
+#define arch_ftrace_get_regs(regs) NULL
+#define HAVE_ARCH_FTRACE_REGS
+struct ftrace_ops;
+struct ftrace_regs;
+#define arch_ftrace_regs(fregs) ((struct __arch_ftrace_regs *)(fregs))
+
+struct __arch_ftrace_regs {
+ unsigned long epc;
+ unsigned long ra;
+ unsigned long sp;
+ unsigned long s0;
+ unsigned long t1;
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+ unsigned long direct_tramp;
+#endif
+ union {
+ unsigned long args[8];
+ struct {
+ unsigned long a0;
+ unsigned long a1;
+ unsigned long a2;
+ unsigned long a3;
+ unsigned long a4;
+ unsigned long a5;
+ unsigned long a6;
+ unsigned long a7;
+#ifdef CONFIG_CC_IS_CLANG
+ unsigned long t2;
+ unsigned long t3;
+ unsigned long t4;
+ unsigned long t5;
+ unsigned long t6;
#endif
+ };
+ };
+};
+
+static __always_inline unsigned long ftrace_regs_get_instruction_pointer(const struct ftrace_regs
+ *fregs)
+{
+ return arch_ftrace_regs(fregs)->epc;
+}
+
+static __always_inline void ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs,
+ unsigned long pc)
+{
+ arch_ftrace_regs(fregs)->epc = pc;
+}
+
+static __always_inline unsigned long ftrace_regs_get_stack_pointer(const struct ftrace_regs *fregs)
+{
+ return arch_ftrace_regs(fregs)->sp;
+}
+
+static __always_inline unsigned long ftrace_regs_get_frame_pointer(const struct ftrace_regs *fregs)
+{
+ return arch_ftrace_regs(fregs)->s0;
+}
+
+static __always_inline unsigned long ftrace_regs_get_argument(struct ftrace_regs *fregs,
+ unsigned int n)
+{
+ if (n < 8)
+ return arch_ftrace_regs(fregs)->args[n];
+ return 0;
+}
+
+static __always_inline unsigned long ftrace_regs_get_return_value(const struct ftrace_regs *fregs)
+{
+ return arch_ftrace_regs(fregs)->a0;
+}
+
+static __always_inline unsigned long ftrace_regs_get_return_address(const struct ftrace_regs *fregs)
+{
+ return arch_ftrace_regs(fregs)->ra;
+}
+
+static __always_inline void ftrace_regs_set_return_value(struct ftrace_regs *fregs,
+ unsigned long ret)
+{
+ arch_ftrace_regs(fregs)->a0 = ret;
+}
+
+static __always_inline void ftrace_override_function_with_return(struct ftrace_regs *fregs)
+{
+ arch_ftrace_regs(fregs)->epc = arch_ftrace_regs(fregs)->ra;
+}
+
+static __always_inline struct pt_regs *
+ftrace_partial_regs(const struct ftrace_regs *fregs, struct pt_regs *regs)
+{
+ struct __arch_ftrace_regs *afregs = arch_ftrace_regs(fregs);
+
+ memcpy(&regs->a_regs, afregs->args, sizeof(afregs->args));
+ regs->epc = afregs->epc;
+ regs->ra = afregs->ra;
+ regs->sp = afregs->sp;
+ regs->s0 = afregs->s0;
+ regs->t1 = afregs->t1;
+ return regs;
+}
+
+int ftrace_regs_query_register_offset(const char *name);
+
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct ftrace_regs *fregs);
+#define ftrace_graph_func ftrace_graph_func
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, unsigned long addr)
+{
+ arch_ftrace_regs(fregs)->t1 = addr;
+}
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
+
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* CONFIG_DYNAMIC_FTRACE */
#endif /* _ASM_RISCV_FTRACE_H */
diff --git a/arch/riscv/include/asm/futex.h b/arch/riscv/include/asm/futex.h
index fc8130f995c1..90c86b115e00 100644
--- a/arch/riscv/include/asm/futex.h
+++ b/arch/riscv/include/asm/futex.h
@@ -85,7 +85,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
__enable_user_access();
__asm__ __volatile__ (
- "1: lr.w.aqrl %[v],%[u] \n"
+ "1: lr.w %[v],%[u] \n"
" bne %[v],%z[ov],3f \n"
"2: sc.w.aqrl %[t],%z[nv],%[u] \n"
" bnez %[t],1b \n"
@@ -93,7 +93,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
_ASM_EXTABLE_UACCESS_ERR(1b, 3b, %[r]) \
_ASM_EXTABLE_UACCESS_ERR(2b, 3b, %[r]) \
: [r] "+r" (ret), [v] "=&r" (val), [u] "+m" (*uaddr), [t] "=&r" (tmp)
- : [ov] "Jr" (oldval), [nv] "Jr" (newval)
+ : [ov] "Jr" ((long)(int)oldval), [nv] "Jr" (newval)
: "memory");
__disable_user_access();
diff --git a/arch/riscv/include/asm/gpr-num.h b/arch/riscv/include/asm/gpr-num.h
index dfee2829fc7c..efeb5edf8a3a 100644
--- a/arch/riscv/include/asm/gpr-num.h
+++ b/arch/riscv/include/asm/gpr-num.h
@@ -3,6 +3,11 @@
#define __ASM_GPR_NUM_H
#ifdef __ASSEMBLY__
+
+ .irp num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
+ .equ .L__gpr_num_x\num, \num
+ .endr
+
.equ .L__gpr_num_zero, 0
.equ .L__gpr_num_ra, 1
.equ .L__gpr_num_sp, 2
@@ -39,6 +44,9 @@
#else /* __ASSEMBLY__ */
#define __DEFINE_ASM_GPR_NUMS \
+" .irp num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31\n" \
+" .equ .L__gpr_num_x\\num, \\num\n" \
+" .endr\n" \
" .equ .L__gpr_num_zero, 0\n" \
" .equ .L__gpr_num_ra, 1\n" \
" .equ .L__gpr_num_sp, 2\n" \
diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h
index a5c2ca1d1cd8..446126497768 100644
--- a/arch/riscv/include/asm/hugetlb.h
+++ b/arch/riscv/include/asm/hugetlb.h
@@ -2,7 +2,56 @@
#ifndef _ASM_RISCV_HUGETLB_H
#define _ASM_RISCV_HUGETLB_H
-#include <asm-generic/hugetlb.h>
+#include <asm/cacheflush.h>
#include <asm/page.h>
+static inline void arch_clear_hugetlb_flags(struct folio *folio)
+{
+ clear_bit(PG_dcache_clean, &folio->flags);
+}
+#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags
+
+#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
+bool arch_hugetlb_migration_supported(struct hstate *h);
+#define arch_hugetlb_migration_supported arch_hugetlb_migration_supported
+#endif
+
+#ifdef CONFIG_RISCV_ISA_SVNAPOT
+#define __HAVE_ARCH_HUGE_PTE_CLEAR
+void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, unsigned long sz);
+
+#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
+void set_huge_pte_at(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep, pte_t pte,
+ unsigned long sz);
+
+#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep,
+ unsigned long sz);
+
+#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
+pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep);
+
+#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
+void huge_ptep_set_wrprotect(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep);
+
+#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
+int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep,
+ pte_t pte, int dirty);
+
+#define __HAVE_ARCH_HUGE_PTEP_GET
+pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+
+pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags);
+#define arch_make_huge_pte arch_make_huge_pte
+
+#endif /*CONFIG_RISCV_ISA_SVNAPOT*/
+
+#include <asm-generic/hugetlb.h>
+
#endif /* _ASM_RISCV_HUGETLB_H */
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 4e2486881840..affd63e11b0a 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -8,22 +8,8 @@
#ifndef _ASM_RISCV_HWCAP_H
#define _ASM_RISCV_HWCAP_H
-#include <linux/bits.h>
#include <uapi/asm/hwcap.h>
-#ifndef __ASSEMBLY__
-/*
- * This yields a mask that user programs can use to figure out what
- * instruction set this cpu supports.
- */
-#define ELF_HWCAP (elf_hwcap)
-
-enum {
- CAP_HWCAP = 1,
-};
-
-extern unsigned long elf_hwcap;
-
#define RISCV_ISA_EXT_a ('a' - 'a')
#define RISCV_ISA_EXT_c ('c' - 'a')
#define RISCV_ISA_EXT_d ('d' - 'a')
@@ -31,46 +17,107 @@ extern unsigned long elf_hwcap;
#define RISCV_ISA_EXT_h ('h' - 'a')
#define RISCV_ISA_EXT_i ('i' - 'a')
#define RISCV_ISA_EXT_m ('m' - 'a')
-#define RISCV_ISA_EXT_s ('s' - 'a')
-#define RISCV_ISA_EXT_u ('u' - 'a')
+#define RISCV_ISA_EXT_q ('q' - 'a')
+#define RISCV_ISA_EXT_v ('v' - 'a')
/*
- * Increse this to higher value as kernel support more ISA extensions.
- */
-#define RISCV_ISA_EXT_MAX 64
-#define RISCV_ISA_EXT_NAME_LEN_MAX 32
-
-/* The base ID for multi-letter ISA extensions */
-#define RISCV_ISA_EXT_BASE 26
-
-/*
- * This enum represent the logical ID for each multi-letter RISC-V ISA extension.
- * The logical ID should start from RISCV_ISA_EXT_BASE and must not exceed
- * RISCV_ISA_EXT_MAX. 0-25 range is reserved for single letter
- * extensions while all the multi-letter extensions should define the next
- * available logical extension id.
+ * These macros represent the logical IDs of each multi-letter RISC-V ISA
+ * extension and are used in the ISA bitmap. The logical IDs start from
+ * RISCV_ISA_EXT_BASE, which allows the 0-25 range to be reserved for single
+ * letter extensions. The maximum, RISCV_ISA_EXT_MAX, is defined in order
+ * to allocate the bitmap and may be increased when necessary.
+ *
+ * New extensions should just be added to the bottom, rather than added
+ * alphabetically, in order to avoid unnecessary shuffling.
*/
-enum riscv_isa_ext_id {
- RISCV_ISA_EXT_SSCOFPMF = RISCV_ISA_EXT_BASE,
- RISCV_ISA_EXT_SVPBMT,
- RISCV_ISA_EXT_ID_MAX = RISCV_ISA_EXT_MAX,
-};
-
-struct riscv_isa_ext_data {
- /* Name of the extension displayed to userspace via /proc/cpuinfo */
- char uprop[RISCV_ISA_EXT_NAME_LEN_MAX];
- /* The logical ISA extension ID */
- unsigned int isa_ext_id;
-};
+#define RISCV_ISA_EXT_BASE 26
-unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap);
+#define RISCV_ISA_EXT_SSCOFPMF 26
+#define RISCV_ISA_EXT_SSTC 27
+#define RISCV_ISA_EXT_SVINVAL 28
+#define RISCV_ISA_EXT_SVPBMT 29
+#define RISCV_ISA_EXT_ZBB 30
+#define RISCV_ISA_EXT_ZICBOM 31
+#define RISCV_ISA_EXT_ZIHINTPAUSE 32
+#define RISCV_ISA_EXT_SVNAPOT 33
+#define RISCV_ISA_EXT_ZICBOZ 34
+#define RISCV_ISA_EXT_SMAIA 35
+#define RISCV_ISA_EXT_SSAIA 36
+#define RISCV_ISA_EXT_ZBA 37
+#define RISCV_ISA_EXT_ZBS 38
+#define RISCV_ISA_EXT_ZICNTR 39
+#define RISCV_ISA_EXT_ZICSR 40
+#define RISCV_ISA_EXT_ZIFENCEI 41
+#define RISCV_ISA_EXT_ZIHPM 42
+#define RISCV_ISA_EXT_SMSTATEEN 43
+#define RISCV_ISA_EXT_ZICOND 44
+#define RISCV_ISA_EXT_ZBC 45
+#define RISCV_ISA_EXT_ZBKB 46
+#define RISCV_ISA_EXT_ZBKC 47
+#define RISCV_ISA_EXT_ZBKX 48
+#define RISCV_ISA_EXT_ZKND 49
+#define RISCV_ISA_EXT_ZKNE 50
+#define RISCV_ISA_EXT_ZKNH 51
+#define RISCV_ISA_EXT_ZKR 52
+#define RISCV_ISA_EXT_ZKSED 53
+#define RISCV_ISA_EXT_ZKSH 54
+#define RISCV_ISA_EXT_ZKT 55
+#define RISCV_ISA_EXT_ZVBB 56
+#define RISCV_ISA_EXT_ZVBC 57
+#define RISCV_ISA_EXT_ZVKB 58
+#define RISCV_ISA_EXT_ZVKG 59
+#define RISCV_ISA_EXT_ZVKNED 60
+#define RISCV_ISA_EXT_ZVKNHA 61
+#define RISCV_ISA_EXT_ZVKNHB 62
+#define RISCV_ISA_EXT_ZVKSED 63
+#define RISCV_ISA_EXT_ZVKSH 64
+#define RISCV_ISA_EXT_ZVKT 65
+#define RISCV_ISA_EXT_ZFH 66
+#define RISCV_ISA_EXT_ZFHMIN 67
+#define RISCV_ISA_EXT_ZIHINTNTL 68
+#define RISCV_ISA_EXT_ZVFH 69
+#define RISCV_ISA_EXT_ZVFHMIN 70
+#define RISCV_ISA_EXT_ZFA 71
+#define RISCV_ISA_EXT_ZTSO 72
+#define RISCV_ISA_EXT_ZACAS 73
+#define RISCV_ISA_EXT_ZVE32X 74
+#define RISCV_ISA_EXT_ZVE32F 75
+#define RISCV_ISA_EXT_ZVE64X 76
+#define RISCV_ISA_EXT_ZVE64F 77
+#define RISCV_ISA_EXT_ZVE64D 78
+#define RISCV_ISA_EXT_ZIMOP 79
+#define RISCV_ISA_EXT_ZCA 80
+#define RISCV_ISA_EXT_ZCB 81
+#define RISCV_ISA_EXT_ZCD 82
+#define RISCV_ISA_EXT_ZCF 83
+#define RISCV_ISA_EXT_ZCMOP 84
+#define RISCV_ISA_EXT_ZAWRS 85
+#define RISCV_ISA_EXT_SVVPTC 86
+#define RISCV_ISA_EXT_SMMPM 87
+#define RISCV_ISA_EXT_SMNPM 88
+#define RISCV_ISA_EXT_SSNPM 89
+#define RISCV_ISA_EXT_ZABHA 90
+#define RISCV_ISA_EXT_ZICCRSE 91
+#define RISCV_ISA_EXT_SVADE 92
+#define RISCV_ISA_EXT_SVADU 93
+#define RISCV_ISA_EXT_ZFBFMIN 94
+#define RISCV_ISA_EXT_ZVFBFMIN 95
+#define RISCV_ISA_EXT_ZVFBFWMA 96
+#define RISCV_ISA_EXT_ZAAMO 97
+#define RISCV_ISA_EXT_ZALRSC 98
+#define RISCV_ISA_EXT_ZICBOP 99
-#define riscv_isa_extension_mask(ext) BIT_MASK(RISCV_ISA_EXT_##ext)
+#define RISCV_ISA_EXT_XLINUXENVCFG 127
-bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit);
-#define riscv_isa_extension_available(isa_bitmap, ext) \
- __riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext)
+#define RISCV_ISA_EXT_MAX 128
+#define RISCV_ISA_EXT_INVALID U32_MAX
+#ifdef CONFIG_RISCV_M_MODE
+#define RISCV_ISA_EXT_SxAIA RISCV_ISA_EXT_SMAIA
+#define RISCV_ISA_EXT_SUPM RISCV_ISA_EXT_SMNPM
+#else
+#define RISCV_ISA_EXT_SxAIA RISCV_ISA_EXT_SSAIA
+#define RISCV_ISA_EXT_SUPM RISCV_ISA_EXT_SSNPM
#endif
#endif /* _ASM_RISCV_HWCAP_H */
diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h
new file mode 100644
index 000000000000..7fe0a379474a
--- /dev/null
+++ b/arch/riscv/include/asm/hwprobe.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright 2023-2024 Rivos, Inc
+ */
+
+#ifndef _ASM_HWPROBE_H
+#define _ASM_HWPROBE_H
+
+#include <uapi/asm/hwprobe.h>
+
+#define RISCV_HWPROBE_MAX_KEY 13
+
+static inline bool riscv_hwprobe_key_is_valid(__s64 key)
+{
+ return key >= 0 && key <= RISCV_HWPROBE_MAX_KEY;
+}
+
+static inline bool hwprobe_key_is_bitmask(__s64 key)
+{
+ switch (key) {
+ case RISCV_HWPROBE_KEY_BASE_BEHAVIOR:
+ case RISCV_HWPROBE_KEY_IMA_EXT_0:
+ case RISCV_HWPROBE_KEY_CPUPERF_0:
+ case RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0:
+ case RISCV_HWPROBE_KEY_VENDOR_EXT_SIFIVE_0:
+ return true;
+ }
+
+ return false;
+}
+
+static inline bool riscv_hwprobe_pair_cmp(struct riscv_hwprobe *pair,
+ struct riscv_hwprobe *other_pair)
+{
+ if (pair->key != other_pair->key)
+ return false;
+
+ if (hwprobe_key_is_bitmask(pair->key))
+ return (pair->value & other_pair->value) == other_pair->value;
+
+ return pair->value == other_pair->value;
+}
+
+#endif
diff --git a/arch/riscv/include/asm/image.h b/arch/riscv/include/asm/image.h
index e0b319af3681..8927a6ea1127 100644
--- a/arch/riscv/include/asm/image.h
+++ b/arch/riscv/include/asm/image.h
@@ -30,6 +30,8 @@
RISCV_HEADER_VERSION_MINOR)
#ifndef __ASSEMBLY__
+#define riscv_image_flag_field(flags, field)\
+ (((flags) >> field##_SHIFT) & field##_MASK)
/**
* struct riscv_image_header - riscv kernel image header
* @code0: Executable code
diff --git a/arch/riscv/include/asm/insn-def.h b/arch/riscv/include/asm/insn-def.h
new file mode 100644
index 000000000000..d5adbaec1d01
--- /dev/null
+++ b/arch/riscv/include/asm/insn-def.h
@@ -0,0 +1,272 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_INSN_DEF_H
+#define __ASM_INSN_DEF_H
+
+#include <asm/asm.h>
+
+#define INSN_R_FUNC7_SHIFT 25
+#define INSN_R_RS2_SHIFT 20
+#define INSN_R_RS1_SHIFT 15
+#define INSN_R_FUNC3_SHIFT 12
+#define INSN_R_RD_SHIFT 7
+#define INSN_R_OPCODE_SHIFT 0
+
+#define INSN_I_SIMM12_SHIFT 20
+#define INSN_I_RS1_SHIFT 15
+#define INSN_I_FUNC3_SHIFT 12
+#define INSN_I_RD_SHIFT 7
+#define INSN_I_OPCODE_SHIFT 0
+
+#define INSN_S_SIMM7_SHIFT 25
+#define INSN_S_RS2_SHIFT 20
+#define INSN_S_RS1_SHIFT 15
+#define INSN_S_FUNC3_SHIFT 12
+#define INSN_S_SIMM5_SHIFT 7
+#define INSN_S_OPCODE_SHIFT 0
+
+#ifdef __ASSEMBLY__
+
+#ifdef CONFIG_AS_HAS_INSN
+
+ .macro insn_r, opcode, func3, func7, rd, rs1, rs2
+ .insn r \opcode, \func3, \func7, \rd, \rs1, \rs2
+ .endm
+
+ .macro insn_i, opcode, func3, rd, rs1, simm12
+ .insn i \opcode, \func3, \rd, \rs1, \simm12
+ .endm
+
+ .macro insn_s, opcode, func3, rs2, simm12, rs1
+ .insn s \opcode, \func3, \rs2, \simm12(\rs1)
+ .endm
+
+#else
+
+#include <asm/gpr-num.h>
+
+ .macro insn_r, opcode, func3, func7, rd, rs1, rs2
+ .4byte ((\opcode << INSN_R_OPCODE_SHIFT) | \
+ (\func3 << INSN_R_FUNC3_SHIFT) | \
+ (\func7 << INSN_R_FUNC7_SHIFT) | \
+ (.L__gpr_num_\rd << INSN_R_RD_SHIFT) | \
+ (.L__gpr_num_\rs1 << INSN_R_RS1_SHIFT) | \
+ (.L__gpr_num_\rs2 << INSN_R_RS2_SHIFT))
+ .endm
+
+ .macro insn_i, opcode, func3, rd, rs1, simm12
+ .4byte ((\opcode << INSN_I_OPCODE_SHIFT) | \
+ (\func3 << INSN_I_FUNC3_SHIFT) | \
+ (.L__gpr_num_\rd << INSN_I_RD_SHIFT) | \
+ (.L__gpr_num_\rs1 << INSN_I_RS1_SHIFT) | \
+ (\simm12 << INSN_I_SIMM12_SHIFT))
+ .endm
+
+ .macro insn_s, opcode, func3, rs2, simm12, rs1
+ .4byte ((\opcode << INSN_S_OPCODE_SHIFT) | \
+ (\func3 << INSN_S_FUNC3_SHIFT) | \
+ (.L__gpr_num_\rs2 << INSN_S_RS2_SHIFT) | \
+ (.L__gpr_num_\rs1 << INSN_S_RS1_SHIFT) | \
+ ((\simm12 & 0x1f) << INSN_S_SIMM5_SHIFT) | \
+ (((\simm12 >> 5) & 0x7f) << INSN_S_SIMM7_SHIFT))
+ .endm
+
+#endif
+
+#define __INSN_R(...) insn_r __VA_ARGS__
+#define __INSN_I(...) insn_i __VA_ARGS__
+#define __INSN_S(...) insn_s __VA_ARGS__
+
+#else /* ! __ASSEMBLY__ */
+
+#ifdef CONFIG_AS_HAS_INSN
+
+#define __INSN_R(opcode, func3, func7, rd, rs1, rs2) \
+ ".insn r " opcode ", " func3 ", " func7 ", " rd ", " rs1 ", " rs2 "\n"
+
+#define __INSN_I(opcode, func3, rd, rs1, simm12) \
+ ".insn i " opcode ", " func3 ", " rd ", " rs1 ", " simm12 "\n"
+
+#define __INSN_S(opcode, func3, rs2, simm12, rs1) \
+ ".insn s " opcode ", " func3 ", " rs2 ", " simm12 "(" rs1 ")\n"
+
+#else
+
+#include <linux/stringify.h>
+#include <asm/gpr-num.h>
+
+#define DEFINE_INSN_R \
+ __DEFINE_ASM_GPR_NUMS \
+" .macro insn_r, opcode, func3, func7, rd, rs1, rs2\n" \
+" .4byte ((\\opcode << " __stringify(INSN_R_OPCODE_SHIFT) ") |" \
+" (\\func3 << " __stringify(INSN_R_FUNC3_SHIFT) ") |" \
+" (\\func7 << " __stringify(INSN_R_FUNC7_SHIFT) ") |" \
+" (.L__gpr_num_\\rd << " __stringify(INSN_R_RD_SHIFT) ") |" \
+" (.L__gpr_num_\\rs1 << " __stringify(INSN_R_RS1_SHIFT) ") |" \
+" (.L__gpr_num_\\rs2 << " __stringify(INSN_R_RS2_SHIFT) "))\n" \
+" .endm\n"
+
+#define DEFINE_INSN_I \
+ __DEFINE_ASM_GPR_NUMS \
+" .macro insn_i, opcode, func3, rd, rs1, simm12\n" \
+" .4byte ((\\opcode << " __stringify(INSN_I_OPCODE_SHIFT) ") |" \
+" (\\func3 << " __stringify(INSN_I_FUNC3_SHIFT) ") |" \
+" (.L__gpr_num_\\rd << " __stringify(INSN_I_RD_SHIFT) ") |" \
+" (.L__gpr_num_\\rs1 << " __stringify(INSN_I_RS1_SHIFT) ") |" \
+" (\\simm12 << " __stringify(INSN_I_SIMM12_SHIFT) "))\n" \
+" .endm\n"
+
+#define DEFINE_INSN_S \
+ __DEFINE_ASM_GPR_NUMS \
+" .macro insn_s, opcode, func3, rs2, simm12, rs1\n" \
+" .4byte ((\\opcode << " __stringify(INSN_S_OPCODE_SHIFT) ") |" \
+" (\\func3 << " __stringify(INSN_S_FUNC3_SHIFT) ") |" \
+" (.L__gpr_num_\\rs2 << " __stringify(INSN_S_RS2_SHIFT) ") |" \
+" (.L__gpr_num_\\rs1 << " __stringify(INSN_S_RS1_SHIFT) ") |" \
+" ((\\simm12 & 0x1f) << " __stringify(INSN_S_SIMM5_SHIFT) ") |" \
+" (((\\simm12 >> 5) & 0x7f) << " __stringify(INSN_S_SIMM7_SHIFT) "))\n" \
+" .endm\n"
+
+#define UNDEFINE_INSN_R \
+" .purgem insn_r\n"
+
+#define UNDEFINE_INSN_I \
+" .purgem insn_i\n"
+
+#define UNDEFINE_INSN_S \
+" .purgem insn_s\n"
+
+#define __INSN_R(opcode, func3, func7, rd, rs1, rs2) \
+ DEFINE_INSN_R \
+ "insn_r " opcode ", " func3 ", " func7 ", " rd ", " rs1 ", " rs2 "\n" \
+ UNDEFINE_INSN_R
+
+#define __INSN_I(opcode, func3, rd, rs1, simm12) \
+ DEFINE_INSN_I \
+ "insn_i " opcode ", " func3 ", " rd ", " rs1 ", " simm12 "\n" \
+ UNDEFINE_INSN_I
+
+#define __INSN_S(opcode, func3, rs2, simm12, rs1) \
+ DEFINE_INSN_S \
+ "insn_s " opcode ", " func3 ", " rs2 ", " simm12 ", " rs1 "\n" \
+ UNDEFINE_INSN_S
+
+#endif
+
+#endif /* ! __ASSEMBLY__ */
+
+#define INSN_R(opcode, func3, func7, rd, rs1, rs2) \
+ __INSN_R(RV_##opcode, RV_##func3, RV_##func7, \
+ RV_##rd, RV_##rs1, RV_##rs2)
+
+#define INSN_I(opcode, func3, rd, rs1, simm12) \
+ __INSN_I(RV_##opcode, RV_##func3, RV_##rd, \
+ RV_##rs1, RV_##simm12)
+
+#define INSN_S(opcode, func3, rs2, simm12, rs1) \
+ __INSN_S(RV_##opcode, RV_##func3, RV_##rs2, \
+ RV_##simm12, RV_##rs1)
+
+#define RV_OPCODE(v) __ASM_STR(v)
+#define RV_FUNC3(v) __ASM_STR(v)
+#define RV_FUNC7(v) __ASM_STR(v)
+#define RV_SIMM12(v) __ASM_STR(v)
+#define RV_RD(v) __ASM_STR(v)
+#define RV_RS1(v) __ASM_STR(v)
+#define RV_RS2(v) __ASM_STR(v)
+#define __RV_REG(v) __ASM_STR(x ## v)
+#define RV___RD(v) __RV_REG(v)
+#define RV___RS1(v) __RV_REG(v)
+#define RV___RS2(v) __RV_REG(v)
+
+#define RV_OPCODE_MISC_MEM RV_OPCODE(15)
+#define RV_OPCODE_OP_IMM RV_OPCODE(19)
+#define RV_OPCODE_SYSTEM RV_OPCODE(115)
+
+#define HFENCE_VVMA(vaddr, asid) \
+ INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(17), \
+ __RD(0), RS1(vaddr), RS2(asid))
+
+#define HFENCE_GVMA(gaddr, vmid) \
+ INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(49), \
+ __RD(0), RS1(gaddr), RS2(vmid))
+
+#define HLVX_HU(dest, addr) \
+ INSN_R(OPCODE_SYSTEM, FUNC3(4), FUNC7(50), \
+ RD(dest), RS1(addr), __RS2(3))
+
+#define HLV_W(dest, addr) \
+ INSN_R(OPCODE_SYSTEM, FUNC3(4), FUNC7(52), \
+ RD(dest), RS1(addr), __RS2(0))
+
+#ifdef CONFIG_64BIT
+#define HLV_D(dest, addr) \
+ INSN_R(OPCODE_SYSTEM, FUNC3(4), FUNC7(54), \
+ RD(dest), RS1(addr), __RS2(0))
+#else
+#define HLV_D(dest, addr) \
+ __ASM_STR(.error "hlv.d requires 64-bit support")
+#endif
+
+#define SINVAL_VMA(vaddr, asid) \
+ INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(11), \
+ __RD(0), RS1(vaddr), RS2(asid))
+
+#define SFENCE_W_INVAL() \
+ INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(12), \
+ __RD(0), __RS1(0), __RS2(0))
+
+#define SFENCE_INVAL_IR() \
+ INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(12), \
+ __RD(0), __RS1(0), __RS2(1))
+
+#define HINVAL_VVMA(vaddr, asid) \
+ INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(19), \
+ __RD(0), RS1(vaddr), RS2(asid))
+
+#define HINVAL_GVMA(gaddr, vmid) \
+ INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(51), \
+ __RD(0), RS1(gaddr), RS2(vmid))
+
+#define CBO_INVAL(base) \
+ INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0), \
+ RS1(base), SIMM12(0))
+
+#define CBO_CLEAN(base) \
+ INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0), \
+ RS1(base), SIMM12(1))
+
+#define CBO_FLUSH(base) \
+ INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0), \
+ RS1(base), SIMM12(2))
+
+#define CBO_ZERO(base) \
+ INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0), \
+ RS1(base), SIMM12(4))
+
+#define PREFETCH_I(base, offset) \
+ INSN_S(OPCODE_OP_IMM, FUNC3(6), __RS2(0), \
+ SIMM12((offset) & 0xfe0), RS1(base))
+
+#define PREFETCH_R(base, offset) \
+ INSN_S(OPCODE_OP_IMM, FUNC3(6), __RS2(1), \
+ SIMM12((offset) & 0xfe0), RS1(base))
+
+#define PREFETCH_W(base, offset) \
+ INSN_S(OPCODE_OP_IMM, FUNC3(6), __RS2(3), \
+ SIMM12((offset) & 0xfe0), RS1(base))
+
+#define RISCV_PAUSE ".4byte 0x100000f"
+#define ZAWRS_WRS_NTO ".4byte 0x00d00073"
+#define ZAWRS_WRS_STO ".4byte 0x01d00073"
+#define RISCV_NOP4 ".4byte 0x00000013"
+
+#define RISCV_INSN_NOP4 _AC(0x00000013, U)
+
+#ifndef __ASSEMBLY__
+#define nop() __asm__ __volatile__ ("nop")
+#define __nops(n) ".rept " #n "\nnop\n.endr\n"
+#define nops(n) __asm__ __volatile__ (__nops(n))
+#endif
+
+#endif /* __ASM_INSN_DEF_H */
diff --git a/arch/riscv/include/asm/insn.h b/arch/riscv/include/asm/insn.h
new file mode 100644
index 000000000000..09fde95a5e8f
--- /dev/null
+++ b/arch/riscv/include/asm/insn.h
@@ -0,0 +1,431 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 SiFive
+ */
+
+#ifndef _ASM_RISCV_INSN_H
+#define _ASM_RISCV_INSN_H
+
+#include <linux/bits.h>
+
+#define RV_INSN_FUNCT3_MASK GENMASK(14, 12)
+#define RV_INSN_FUNCT3_OPOFF 12
+#define RV_INSN_OPCODE_MASK GENMASK(6, 0)
+#define RV_INSN_OPCODE_OPOFF 0
+#define RV_INSN_FUNCT12_OPOFF 20
+
+#define RV_ENCODE_FUNCT3(f_) (RVG_FUNCT3_##f_ << RV_INSN_FUNCT3_OPOFF)
+#define RV_ENCODE_FUNCT12(f_) (RVG_FUNCT12_##f_ << RV_INSN_FUNCT12_OPOFF)
+
+/* The bit field of immediate value in I-type instruction */
+#define RV_I_IMM_SIGN_OPOFF 31
+#define RV_I_IMM_11_0_OPOFF 20
+#define RV_I_IMM_SIGN_OFF 12
+#define RV_I_IMM_11_0_OFF 0
+#define RV_I_IMM_11_0_MASK GENMASK(11, 0)
+
+/* The bit field of immediate value in J-type instruction */
+#define RV_J_IMM_SIGN_OPOFF 31
+#define RV_J_IMM_10_1_OPOFF 21
+#define RV_J_IMM_11_OPOFF 20
+#define RV_J_IMM_19_12_OPOFF 12
+#define RV_J_IMM_SIGN_OFF 20
+#define RV_J_IMM_10_1_OFF 1
+#define RV_J_IMM_11_OFF 11
+#define RV_J_IMM_19_12_OFF 12
+#define RV_J_IMM_10_1_MASK GENMASK(9, 0)
+#define RV_J_IMM_11_MASK GENMASK(0, 0)
+#define RV_J_IMM_19_12_MASK GENMASK(7, 0)
+
+/*
+ * U-type IMMs contain the upper 20bits [31:20] of an immediate with
+ * the rest filled in by zeros, so no shifting required. Similarly,
+ * bit31 contains the signed state, so no sign extension necessary.
+ */
+#define RV_U_IMM_SIGN_OPOFF 31
+#define RV_U_IMM_31_12_OPOFF 0
+#define RV_U_IMM_31_12_MASK GENMASK(31, 12)
+
+/* The bit field of immediate value in B-type instruction */
+#define RV_B_IMM_SIGN_OPOFF 31
+#define RV_B_IMM_10_5_OPOFF 25
+#define RV_B_IMM_4_1_OPOFF 8
+#define RV_B_IMM_11_OPOFF 7
+#define RV_B_IMM_SIGN_OFF 12
+#define RV_B_IMM_10_5_OFF 5
+#define RV_B_IMM_4_1_OFF 1
+#define RV_B_IMM_11_OFF 11
+#define RV_B_IMM_10_5_MASK GENMASK(5, 0)
+#define RV_B_IMM_4_1_MASK GENMASK(3, 0)
+#define RV_B_IMM_11_MASK GENMASK(0, 0)
+
+/* The register offset in RVG instruction */
+#define RVG_RS1_OPOFF 15
+#define RVG_RS2_OPOFF 20
+#define RVG_RD_OPOFF 7
+#define RVG_RS1_MASK GENMASK(4, 0)
+#define RVG_RD_MASK GENMASK(4, 0)
+
+/* The bit field of immediate value in RVC J instruction */
+#define RVC_J_IMM_SIGN_OPOFF 12
+#define RVC_J_IMM_4_OPOFF 11
+#define RVC_J_IMM_9_8_OPOFF 9
+#define RVC_J_IMM_10_OPOFF 8
+#define RVC_J_IMM_6_OPOFF 7
+#define RVC_J_IMM_7_OPOFF 6
+#define RVC_J_IMM_3_1_OPOFF 3
+#define RVC_J_IMM_5_OPOFF 2
+#define RVC_J_IMM_SIGN_OFF 11
+#define RVC_J_IMM_4_OFF 4
+#define RVC_J_IMM_9_8_OFF 8
+#define RVC_J_IMM_10_OFF 10
+#define RVC_J_IMM_6_OFF 6
+#define RVC_J_IMM_7_OFF 7
+#define RVC_J_IMM_3_1_OFF 1
+#define RVC_J_IMM_5_OFF 5
+#define RVC_J_IMM_4_MASK GENMASK(0, 0)
+#define RVC_J_IMM_9_8_MASK GENMASK(1, 0)
+#define RVC_J_IMM_10_MASK GENMASK(0, 0)
+#define RVC_J_IMM_6_MASK GENMASK(0, 0)
+#define RVC_J_IMM_7_MASK GENMASK(0, 0)
+#define RVC_J_IMM_3_1_MASK GENMASK(2, 0)
+#define RVC_J_IMM_5_MASK GENMASK(0, 0)
+
+/* The bit field of immediate value in RVC B instruction */
+#define RVC_B_IMM_SIGN_OPOFF 12
+#define RVC_B_IMM_4_3_OPOFF 10
+#define RVC_B_IMM_7_6_OPOFF 5
+#define RVC_B_IMM_2_1_OPOFF 3
+#define RVC_B_IMM_5_OPOFF 2
+#define RVC_B_IMM_SIGN_OFF 8
+#define RVC_B_IMM_4_3_OFF 3
+#define RVC_B_IMM_7_6_OFF 6
+#define RVC_B_IMM_2_1_OFF 1
+#define RVC_B_IMM_5_OFF 5
+#define RVC_B_IMM_4_3_MASK GENMASK(1, 0)
+#define RVC_B_IMM_7_6_MASK GENMASK(1, 0)
+#define RVC_B_IMM_2_1_MASK GENMASK(1, 0)
+#define RVC_B_IMM_5_MASK GENMASK(0, 0)
+
+#define RVC_INSN_FUNCT4_MASK GENMASK(15, 12)
+#define RVC_INSN_FUNCT4_OPOFF 12
+#define RVC_INSN_FUNCT3_MASK GENMASK(15, 13)
+#define RVC_INSN_FUNCT3_OPOFF 13
+#define RVC_INSN_J_RS1_MASK GENMASK(11, 7)
+#define RVC_INSN_J_RS2_MASK GENMASK(6, 2)
+#define RVC_INSN_OPCODE_MASK GENMASK(1, 0)
+#define RVC_ENCODE_FUNCT3(f_) (RVC_FUNCT3_##f_ << RVC_INSN_FUNCT3_OPOFF)
+#define RVC_ENCODE_FUNCT4(f_) (RVC_FUNCT4_##f_ << RVC_INSN_FUNCT4_OPOFF)
+
+/* The register offset in RVC op=C0 instruction */
+#define RVC_C0_RS1_OPOFF 7
+#define RVC_C0_RS2_OPOFF 2
+#define RVC_C0_RD_OPOFF 2
+
+/* The register offset in RVC op=C1 instruction */
+#define RVC_C1_RS1_OPOFF 7
+#define RVC_C1_RS2_OPOFF 2
+#define RVC_C1_RD_OPOFF 7
+
+/* The register offset in RVC op=C2 instruction */
+#define RVC_C2_RS1_OPOFF 7
+#define RVC_C2_RS2_OPOFF 2
+#define RVC_C2_RD_OPOFF 7
+#define RVC_C2_RS1_MASK GENMASK(4, 0)
+
+/* parts of opcode for RVG*/
+#define RVG_OPCODE_FENCE 0x0f
+#define RVG_OPCODE_AUIPC 0x17
+#define RVG_OPCODE_BRANCH 0x63
+#define RVG_OPCODE_JALR 0x67
+#define RVG_OPCODE_JAL 0x6f
+#define RVG_OPCODE_SYSTEM 0x73
+#define RVG_SYSTEM_CSR_OFF 20
+#define RVG_SYSTEM_CSR_MASK GENMASK(12, 0)
+
+/* parts of opcode for RVF, RVD and RVQ */
+#define RVFDQ_FL_FS_WIDTH_OFF 12
+#define RVFDQ_FL_FS_WIDTH_MASK GENMASK(2, 0)
+#define RVFDQ_FL_FS_WIDTH_W 2
+#define RVFDQ_FL_FS_WIDTH_D 3
+#define RVFDQ_LS_FS_WIDTH_Q 4
+#define RVFDQ_OPCODE_FL 0x07
+#define RVFDQ_OPCODE_FS 0x27
+
+/* parts of opcode for RVV */
+#define RVV_OPCODE_VECTOR 0x57
+#define RVV_VL_VS_WIDTH_8 0
+#define RVV_VL_VS_WIDTH_16 5
+#define RVV_VL_VS_WIDTH_32 6
+#define RVV_VL_VS_WIDTH_64 7
+#define RVV_OPCODE_VL RVFDQ_OPCODE_FL
+#define RVV_OPCODE_VS RVFDQ_OPCODE_FS
+
+/* parts of opcode for RVC*/
+#define RVC_OPCODE_C0 0x0
+#define RVC_OPCODE_C1 0x1
+#define RVC_OPCODE_C2 0x2
+
+/* parts of funct3 code for I, M, A extension*/
+#define RVG_FUNCT3_JALR 0x0
+#define RVG_FUNCT3_BEQ 0x0
+#define RVG_FUNCT3_BNE 0x1
+#define RVG_FUNCT3_BLT 0x4
+#define RVG_FUNCT3_BGE 0x5
+#define RVG_FUNCT3_BLTU 0x6
+#define RVG_FUNCT3_BGEU 0x7
+
+/* parts of funct3 code for C extension*/
+#define RVC_FUNCT3_C_BEQZ 0x6
+#define RVC_FUNCT3_C_BNEZ 0x7
+#define RVC_FUNCT3_C_J 0x5
+#define RVC_FUNCT3_C_JAL 0x1
+#define RVC_FUNCT4_C_JR 0x8
+#define RVC_FUNCT4_C_JALR 0x9
+#define RVC_FUNCT4_C_EBREAK 0x9
+
+#define RVG_FUNCT12_EBREAK 0x1
+#define RVG_FUNCT12_SRET 0x102
+
+#define RVG_MATCH_AUIPC (RVG_OPCODE_AUIPC)
+#define RVG_MATCH_JALR (RV_ENCODE_FUNCT3(JALR) | RVG_OPCODE_JALR)
+#define RVG_MATCH_JAL (RVG_OPCODE_JAL)
+#define RVG_MATCH_FENCE (RVG_OPCODE_FENCE)
+#define RVG_MATCH_BEQ (RV_ENCODE_FUNCT3(BEQ) | RVG_OPCODE_BRANCH)
+#define RVG_MATCH_BNE (RV_ENCODE_FUNCT3(BNE) | RVG_OPCODE_BRANCH)
+#define RVG_MATCH_BLT (RV_ENCODE_FUNCT3(BLT) | RVG_OPCODE_BRANCH)
+#define RVG_MATCH_BGE (RV_ENCODE_FUNCT3(BGE) | RVG_OPCODE_BRANCH)
+#define RVG_MATCH_BLTU (RV_ENCODE_FUNCT3(BLTU) | RVG_OPCODE_BRANCH)
+#define RVG_MATCH_BGEU (RV_ENCODE_FUNCT3(BGEU) | RVG_OPCODE_BRANCH)
+#define RVG_MATCH_EBREAK (RV_ENCODE_FUNCT12(EBREAK) | RVG_OPCODE_SYSTEM)
+#define RVG_MATCH_SRET (RV_ENCODE_FUNCT12(SRET) | RVG_OPCODE_SYSTEM)
+#define RVC_MATCH_C_BEQZ (RVC_ENCODE_FUNCT3(C_BEQZ) | RVC_OPCODE_C1)
+#define RVC_MATCH_C_BNEZ (RVC_ENCODE_FUNCT3(C_BNEZ) | RVC_OPCODE_C1)
+#define RVC_MATCH_C_J (RVC_ENCODE_FUNCT3(C_J) | RVC_OPCODE_C1)
+#define RVC_MATCH_C_JAL (RVC_ENCODE_FUNCT3(C_JAL) | RVC_OPCODE_C1)
+#define RVC_MATCH_C_JR (RVC_ENCODE_FUNCT4(C_JR) | RVC_OPCODE_C2)
+#define RVC_MATCH_C_JALR (RVC_ENCODE_FUNCT4(C_JALR) | RVC_OPCODE_C2)
+#define RVC_MATCH_C_EBREAK (RVC_ENCODE_FUNCT4(C_EBREAK) | RVC_OPCODE_C2)
+
+#define RVG_MASK_AUIPC (RV_INSN_OPCODE_MASK)
+#define RVG_MASK_JALR (RV_INSN_FUNCT3_MASK | RV_INSN_OPCODE_MASK)
+#define RVG_MASK_JAL (RV_INSN_OPCODE_MASK)
+#define RVG_MASK_FENCE (RV_INSN_OPCODE_MASK)
+#define RVC_MASK_C_JALR (RVC_INSN_FUNCT4_MASK | RVC_INSN_J_RS2_MASK | RVC_INSN_OPCODE_MASK)
+#define RVC_MASK_C_JR (RVC_INSN_FUNCT4_MASK | RVC_INSN_J_RS2_MASK | RVC_INSN_OPCODE_MASK)
+#define RVC_MASK_C_JAL (RVC_INSN_FUNCT3_MASK | RVC_INSN_OPCODE_MASK)
+#define RVC_MASK_C_J (RVC_INSN_FUNCT3_MASK | RVC_INSN_OPCODE_MASK)
+#define RVG_MASK_BEQ (RV_INSN_FUNCT3_MASK | RV_INSN_OPCODE_MASK)
+#define RVG_MASK_BNE (RV_INSN_FUNCT3_MASK | RV_INSN_OPCODE_MASK)
+#define RVG_MASK_BLT (RV_INSN_FUNCT3_MASK | RV_INSN_OPCODE_MASK)
+#define RVG_MASK_BGE (RV_INSN_FUNCT3_MASK | RV_INSN_OPCODE_MASK)
+#define RVG_MASK_BLTU (RV_INSN_FUNCT3_MASK | RV_INSN_OPCODE_MASK)
+#define RVG_MASK_BGEU (RV_INSN_FUNCT3_MASK | RV_INSN_OPCODE_MASK)
+#define RVC_MASK_C_BEQZ (RVC_INSN_FUNCT3_MASK | RVC_INSN_OPCODE_MASK)
+#define RVC_MASK_C_BNEZ (RVC_INSN_FUNCT3_MASK | RVC_INSN_OPCODE_MASK)
+#define RVC_MASK_C_EBREAK 0xffff
+#define RVG_MASK_EBREAK 0xffffffff
+#define RVG_MASK_SRET 0xffffffff
+
+#define __INSN_LENGTH_MASK _UL(0x3)
+#define __INSN_LENGTH_GE_32 _UL(0x3)
+#define __INSN_OPCODE_MASK _UL(0x7F)
+#define __INSN_BRANCH_OPCODE _UL(RVG_OPCODE_BRANCH)
+
+#define __RISCV_INSN_FUNCS(name, mask, val) \
+static __always_inline bool riscv_insn_is_##name(u32 code) \
+{ \
+ BUILD_BUG_ON(~(mask) & (val)); \
+ return (code & (mask)) == (val); \
+} \
+
+#if __riscv_xlen == 32
+/* C.JAL is an RV32C-only instruction */
+__RISCV_INSN_FUNCS(c_jal, RVC_MASK_C_JAL, RVC_MATCH_C_JAL)
+#else
+#define riscv_insn_is_c_jal(opcode) 0
+#endif
+__RISCV_INSN_FUNCS(auipc, RVG_MASK_AUIPC, RVG_MATCH_AUIPC)
+__RISCV_INSN_FUNCS(jalr, RVG_MASK_JALR, RVG_MATCH_JALR)
+__RISCV_INSN_FUNCS(jal, RVG_MASK_JAL, RVG_MATCH_JAL)
+__RISCV_INSN_FUNCS(c_j, RVC_MASK_C_J, RVC_MATCH_C_J)
+__RISCV_INSN_FUNCS(beq, RVG_MASK_BEQ, RVG_MATCH_BEQ)
+__RISCV_INSN_FUNCS(bne, RVG_MASK_BNE, RVG_MATCH_BNE)
+__RISCV_INSN_FUNCS(blt, RVG_MASK_BLT, RVG_MATCH_BLT)
+__RISCV_INSN_FUNCS(bge, RVG_MASK_BGE, RVG_MATCH_BGE)
+__RISCV_INSN_FUNCS(bltu, RVG_MASK_BLTU, RVG_MATCH_BLTU)
+__RISCV_INSN_FUNCS(bgeu, RVG_MASK_BGEU, RVG_MATCH_BGEU)
+__RISCV_INSN_FUNCS(c_beqz, RVC_MASK_C_BEQZ, RVC_MATCH_C_BEQZ)
+__RISCV_INSN_FUNCS(c_bnez, RVC_MASK_C_BNEZ, RVC_MATCH_C_BNEZ)
+__RISCV_INSN_FUNCS(c_ebreak, RVC_MASK_C_EBREAK, RVC_MATCH_C_EBREAK)
+__RISCV_INSN_FUNCS(ebreak, RVG_MASK_EBREAK, RVG_MATCH_EBREAK)
+__RISCV_INSN_FUNCS(sret, RVG_MASK_SRET, RVG_MATCH_SRET)
+__RISCV_INSN_FUNCS(fence, RVG_MASK_FENCE, RVG_MATCH_FENCE);
+
+/* special case to catch _any_ system instruction */
+static __always_inline bool riscv_insn_is_system(u32 code)
+{
+ return (code & RV_INSN_OPCODE_MASK) == RVG_OPCODE_SYSTEM;
+}
+
+/* special case to catch _any_ branch instruction */
+static __always_inline bool riscv_insn_is_branch(u32 code)
+{
+ return (code & RV_INSN_OPCODE_MASK) == RVG_OPCODE_BRANCH;
+}
+
+static __always_inline bool riscv_insn_is_c_jr(u32 code)
+{
+ return (code & RVC_MASK_C_JR) == RVC_MATCH_C_JR &&
+ (code & RVC_INSN_J_RS1_MASK) != 0;
+}
+
+static __always_inline bool riscv_insn_is_c_jalr(u32 code)
+{
+ return (code & RVC_MASK_C_JALR) == RVC_MATCH_C_JALR &&
+ (code & RVC_INSN_J_RS1_MASK) != 0;
+}
+
+#define RV_IMM_SIGN(x) (-(((x) >> 31) & 1))
+#define RVC_IMM_SIGN(x) (-(((x) >> 12) & 1))
+#define RV_X(X, s, mask) (((X) >> (s)) & (mask))
+#define RVC_X(X, s, mask) RV_X(X, s, mask)
+
+#define RV_EXTRACT_RS1_REG(x) \
+ ({typeof(x) x_ = (x); \
+ (RV_X(x_, RVG_RS1_OPOFF, RVG_RS1_MASK)); })
+
+#define RV_EXTRACT_RD_REG(x) \
+ ({typeof(x) x_ = (x); \
+ (RV_X(x_, RVG_RD_OPOFF, RVG_RD_MASK)); })
+
+#define RV_EXTRACT_UTYPE_IMM(x) \
+ ({typeof(x) x_ = (x); \
+ (RV_X(x_, RV_U_IMM_31_12_OPOFF, RV_U_IMM_31_12_MASK)); })
+
+#define RV_EXTRACT_JTYPE_IMM(x) \
+ ({typeof(x) x_ = (x); \
+ (RV_X(x_, RV_J_IMM_10_1_OPOFF, RV_J_IMM_10_1_MASK) << RV_J_IMM_10_1_OFF) | \
+ (RV_X(x_, RV_J_IMM_11_OPOFF, RV_J_IMM_11_MASK) << RV_J_IMM_11_OFF) | \
+ (RV_X(x_, RV_J_IMM_19_12_OPOFF, RV_J_IMM_19_12_MASK) << RV_J_IMM_19_12_OFF) | \
+ (RV_IMM_SIGN(x_) << RV_J_IMM_SIGN_OFF); })
+
+#define RV_EXTRACT_ITYPE_IMM(x) \
+ ({typeof(x) x_ = (x); \
+ (RV_X(x_, RV_I_IMM_11_0_OPOFF, RV_I_IMM_11_0_MASK)) | \
+ (RV_IMM_SIGN(x_) << RV_I_IMM_SIGN_OFF); })
+
+#define RV_EXTRACT_BTYPE_IMM(x) \
+ ({typeof(x) x_ = (x); \
+ (RV_X(x_, RV_B_IMM_4_1_OPOFF, RV_B_IMM_4_1_MASK) << RV_B_IMM_4_1_OFF) | \
+ (RV_X(x_, RV_B_IMM_10_5_OPOFF, RV_B_IMM_10_5_MASK) << RV_B_IMM_10_5_OFF) | \
+ (RV_X(x_, RV_B_IMM_11_OPOFF, RV_B_IMM_11_MASK) << RV_B_IMM_11_OFF) | \
+ (RV_IMM_SIGN(x_) << RV_B_IMM_SIGN_OFF); })
+
+#define RVC_EXTRACT_C2_RS1_REG(x) \
+ ({typeof(x) x_ = (x); \
+ (RV_X(x_, RVC_C2_RS1_OPOFF, RVC_C2_RS1_MASK)); })
+
+#define RVC_EXTRACT_JTYPE_IMM(x) \
+ ({typeof(x) x_ = (x); \
+ (RVC_X(x_, RVC_J_IMM_3_1_OPOFF, RVC_J_IMM_3_1_MASK) << RVC_J_IMM_3_1_OFF) | \
+ (RVC_X(x_, RVC_J_IMM_4_OPOFF, RVC_J_IMM_4_MASK) << RVC_J_IMM_4_OFF) | \
+ (RVC_X(x_, RVC_J_IMM_5_OPOFF, RVC_J_IMM_5_MASK) << RVC_J_IMM_5_OFF) | \
+ (RVC_X(x_, RVC_J_IMM_6_OPOFF, RVC_J_IMM_6_MASK) << RVC_J_IMM_6_OFF) | \
+ (RVC_X(x_, RVC_J_IMM_7_OPOFF, RVC_J_IMM_7_MASK) << RVC_J_IMM_7_OFF) | \
+ (RVC_X(x_, RVC_J_IMM_9_8_OPOFF, RVC_J_IMM_9_8_MASK) << RVC_J_IMM_9_8_OFF) | \
+ (RVC_X(x_, RVC_J_IMM_10_OPOFF, RVC_J_IMM_10_MASK) << RVC_J_IMM_10_OFF) | \
+ (RVC_IMM_SIGN(x_) << RVC_J_IMM_SIGN_OFF); })
+
+#define RVC_EXTRACT_BTYPE_IMM(x) \
+ ({typeof(x) x_ = (x); \
+ (RVC_X(x_, RVC_B_IMM_2_1_OPOFF, RVC_B_IMM_2_1_MASK) << RVC_B_IMM_2_1_OFF) | \
+ (RVC_X(x_, RVC_B_IMM_4_3_OPOFF, RVC_B_IMM_4_3_MASK) << RVC_B_IMM_4_3_OFF) | \
+ (RVC_X(x_, RVC_B_IMM_5_OPOFF, RVC_B_IMM_5_MASK) << RVC_B_IMM_5_OFF) | \
+ (RVC_X(x_, RVC_B_IMM_7_6_OPOFF, RVC_B_IMM_7_6_MASK) << RVC_B_IMM_7_6_OFF) | \
+ (RVC_IMM_SIGN(x_) << RVC_B_IMM_SIGN_OFF); })
+
+#define RVG_EXTRACT_SYSTEM_CSR(x) \
+ ({typeof(x) x_ = (x); RV_X(x_, RVG_SYSTEM_CSR_OFF, RVG_SYSTEM_CSR_MASK); })
+
+#define RVFDQ_EXTRACT_FL_FS_WIDTH(x) \
+ ({typeof(x) x_ = (x); RV_X(x_, RVFDQ_FL_FS_WIDTH_OFF, \
+ RVFDQ_FL_FS_WIDTH_MASK); })
+
+#define RVV_EXRACT_VL_VS_WIDTH(x) RVFDQ_EXTRACT_FL_FS_WIDTH(x)
+
+/*
+ * Get the immediate from a J-type instruction.
+ *
+ * @insn: instruction to process
+ * Return: immediate
+ */
+static inline s32 riscv_insn_extract_jtype_imm(u32 insn)
+{
+ return RV_EXTRACT_JTYPE_IMM(insn);
+}
+
+/*
+ * Update a J-type instruction with an immediate value.
+ *
+ * @insn: pointer to the jtype instruction
+ * @imm: the immediate to insert into the instruction
+ */
+static inline void riscv_insn_insert_jtype_imm(u32 *insn, s32 imm)
+{
+ /* drop the old IMMs, all jal IMM bits sit at 31:12 */
+ *insn &= ~GENMASK(31, 12);
+ *insn |= (RV_X(imm, RV_J_IMM_10_1_OFF, RV_J_IMM_10_1_MASK) << RV_J_IMM_10_1_OPOFF) |
+ (RV_X(imm, RV_J_IMM_11_OFF, RV_J_IMM_11_MASK) << RV_J_IMM_11_OPOFF) |
+ (RV_X(imm, RV_J_IMM_19_12_OFF, RV_J_IMM_19_12_MASK) << RV_J_IMM_19_12_OPOFF) |
+ (RV_X(imm, RV_J_IMM_SIGN_OFF, 1) << RV_J_IMM_SIGN_OPOFF);
+}
+
+/*
+ * Put together one immediate from a U-type and I-type instruction pair.
+ *
+ * The U-type contains an upper immediate, meaning bits[31:12] with [11:0]
+ * being zero, while the I-type contains a 12bit immediate.
+ * Combined these can encode larger 32bit values and are used for example
+ * in auipc + jalr pairs to allow larger jumps.
+ *
+ * @utype_insn: instruction containing the upper immediate
+ * @itype_insn: instruction
+ * Return: combined immediate
+ */
+static inline s32 riscv_insn_extract_utype_itype_imm(u32 utype_insn, u32 itype_insn)
+{
+ s32 imm;
+
+ imm = RV_EXTRACT_UTYPE_IMM(utype_insn);
+ imm += RV_EXTRACT_ITYPE_IMM(itype_insn);
+
+ return imm;
+}
+
+/*
+ * Update a set of two instructions (U-type + I-type) with an immediate value.
+ *
+ * Used for example in auipc+jalrs pairs the U-type instructions contains
+ * a 20bit upper immediate representing bits[31:12], while the I-type
+ * instruction contains a 12bit immediate representing bits[11:0].
+ *
+ * This also takes into account that both separate immediates are
+ * considered as signed values, so if the I-type immediate becomes
+ * negative (BIT(11) set) the U-type part gets adjusted.
+ *
+ * @utype_insn: pointer to the utype instruction of the pair
+ * @itype_insn: pointer to the itype instruction of the pair
+ * @imm: the immediate to insert into the two instructions
+ */
+static inline void riscv_insn_insert_utype_itype_imm(u32 *utype_insn, u32 *itype_insn, s32 imm)
+{
+ /* drop possible old IMM values */
+ *utype_insn &= ~(RV_U_IMM_31_12_MASK);
+ *itype_insn &= ~(RV_I_IMM_11_0_MASK << RV_I_IMM_11_0_OPOFF);
+
+ /* add the adapted IMMs */
+ *utype_insn |= (imm & RV_U_IMM_31_12_MASK) + ((imm & BIT(11)) << 1);
+ *itype_insn |= ((imm & RV_I_IMM_11_0_MASK) << RV_I_IMM_11_0_OPOFF);
+}
+#endif /* _ASM_RISCV_INSN_H */
diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h
index 69605a474270..a0e51840b9db 100644
--- a/arch/riscv/include/asm/io.h
+++ b/arch/riscv/include/asm/io.h
@@ -47,10 +47,10 @@
* sufficient to ensure this works sanely on controllers that support I/O
* writes.
*/
-#define __io_pbr() __asm__ __volatile__ ("fence io,i" : : : "memory");
-#define __io_par(v) __asm__ __volatile__ ("fence i,ior" : : : "memory");
-#define __io_pbw() __asm__ __volatile__ ("fence iow,o" : : : "memory");
-#define __io_paw() __asm__ __volatile__ ("fence o,io" : : : "memory");
+#define __io_pbr() RISCV_FENCE(io, i)
+#define __io_par(v) RISCV_FENCE(i, ior)
+#define __io_pbw() RISCV_FENCE(iow, o)
+#define __io_paw() RISCV_FENCE(o, io)
/*
* Accesses from a single hart to a single I/O address must be ordered. This
@@ -101,9 +101,9 @@ __io_reads_ins(reads, u32, l, __io_br(), __io_ar(addr))
__io_reads_ins(ins, u8, b, __io_pbr(), __io_par(addr))
__io_reads_ins(ins, u16, w, __io_pbr(), __io_par(addr))
__io_reads_ins(ins, u32, l, __io_pbr(), __io_par(addr))
-#define insb(addr, buffer, count) __insb((void __iomem *)(long)addr, buffer, count)
-#define insw(addr, buffer, count) __insw((void __iomem *)(long)addr, buffer, count)
-#define insl(addr, buffer, count) __insl((void __iomem *)(long)addr, buffer, count)
+#define insb(addr, buffer, count) __insb(PCI_IOBASE + (addr), buffer, count)
+#define insw(addr, buffer, count) __insw(PCI_IOBASE + (addr), buffer, count)
+#define insl(addr, buffer, count) __insl(PCI_IOBASE + (addr), buffer, count)
__io_writes_outs(writes, u8, b, __io_bw(), __io_aw())
__io_writes_outs(writes, u16, w, __io_bw(), __io_aw())
@@ -115,24 +115,29 @@ __io_writes_outs(writes, u32, l, __io_bw(), __io_aw())
__io_writes_outs(outs, u8, b, __io_pbw(), __io_paw())
__io_writes_outs(outs, u16, w, __io_pbw(), __io_paw())
__io_writes_outs(outs, u32, l, __io_pbw(), __io_paw())
-#define outsb(addr, buffer, count) __outsb((void __iomem *)(long)addr, buffer, count)
-#define outsw(addr, buffer, count) __outsw((void __iomem *)(long)addr, buffer, count)
-#define outsl(addr, buffer, count) __outsl((void __iomem *)(long)addr, buffer, count)
+#define outsb(addr, buffer, count) __outsb(PCI_IOBASE + (addr), buffer, count)
+#define outsw(addr, buffer, count) __outsw(PCI_IOBASE + (addr), buffer, count)
+#define outsl(addr, buffer, count) __outsl(PCI_IOBASE + (addr), buffer, count)
#ifdef CONFIG_64BIT
__io_reads_ins(reads, u64, q, __io_br(), __io_ar(addr))
#define readsq(addr, buffer, count) __readsq(addr, buffer, count)
__io_reads_ins(ins, u64, q, __io_pbr(), __io_par(addr))
-#define insq(addr, buffer, count) __insq((void __iomem *)addr, buffer, count)
+#define insq(addr, buffer, count) __insq(PCI_IOBASE + (addr), buffer, count)
__io_writes_outs(writes, u64, q, __io_bw(), __io_aw())
#define writesq(addr, buffer, count) __writesq(addr, buffer, count)
__io_writes_outs(outs, u64, q, __io_pbr(), __io_paw())
-#define outsq(addr, buffer, count) __outsq((void __iomem *)addr, buffer, count)
+#define outsq(addr, buffer, count) __outsq(PCI_IOBASE + (addr), buffer, count)
#endif
#include <asm-generic/io.h>
+#ifdef CONFIG_MMU
+#define arch_memremap_wb(addr, size, flags) \
+ ((__force void *)ioremap_prot((addr), (size), __pgprot(_PAGE_KERNEL)))
+#endif
+
#endif /* _ASM_RISCV_IO_H */
diff --git a/arch/riscv/include/asm/irq.h b/arch/riscv/include/asm/irq.h
index e4c435509983..7b038f3b7cb0 100644
--- a/arch/riscv/include/asm/irq.h
+++ b/arch/riscv/include/asm/irq.h
@@ -12,6 +12,68 @@
#include <asm-generic/irq.h>
-extern void __init init_IRQ(void);
+#define INVALID_CONTEXT UINT_MAX
+
+#ifdef CONFIG_SMP
+void arch_trigger_cpumask_backtrace(const cpumask_t *mask, int exclude_cpu);
+#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace
+#endif
+
+void riscv_set_intc_hwnode_fn(struct fwnode_handle *(*fn)(void));
+
+struct fwnode_handle *riscv_get_intc_hwnode(void);
+
+#ifdef CONFIG_ACPI
+
+enum riscv_irqchip_type {
+ ACPI_RISCV_IRQCHIP_INTC = 0x00,
+ ACPI_RISCV_IRQCHIP_IMSIC = 0x01,
+ ACPI_RISCV_IRQCHIP_PLIC = 0x02,
+ ACPI_RISCV_IRQCHIP_APLIC = 0x03,
+};
+
+int riscv_acpi_get_gsi_info(struct fwnode_handle *fwnode, u32 *gsi_base,
+ u32 *id, u32 *nr_irqs, u32 *nr_idcs);
+struct fwnode_handle *riscv_acpi_get_gsi_domain_id(u32 gsi);
+unsigned long acpi_rintc_index_to_hartid(u32 index);
+unsigned long acpi_rintc_ext_parent_to_hartid(unsigned int plic_id, unsigned int ctxt_idx);
+unsigned int acpi_rintc_get_plic_nr_contexts(unsigned int plic_id);
+unsigned int acpi_rintc_get_plic_context(unsigned int plic_id, unsigned int ctxt_idx);
+int __init acpi_rintc_get_imsic_mmio_info(u32 index, struct resource *res);
+
+#else
+static inline int riscv_acpi_get_gsi_info(struct fwnode_handle *fwnode, u32 *gsi_base,
+ u32 *id, u32 *nr_irqs, u32 *nr_idcs)
+{
+ return 0;
+}
+
+static inline unsigned long acpi_rintc_index_to_hartid(u32 index)
+{
+ return INVALID_HARTID;
+}
+
+static inline unsigned long acpi_rintc_ext_parent_to_hartid(unsigned int plic_id,
+ unsigned int ctxt_idx)
+{
+ return INVALID_HARTID;
+}
+
+static inline unsigned int acpi_rintc_get_plic_nr_contexts(unsigned int plic_id)
+{
+ return INVALID_CONTEXT;
+}
+
+static inline unsigned int acpi_rintc_get_plic_context(unsigned int plic_id, unsigned int ctxt_idx)
+{
+ return INVALID_CONTEXT;
+}
+
+static inline int __init acpi_rintc_get_imsic_mmio_info(u32 index, struct resource *res)
+{
+ return 0;
+}
+
+#endif /* CONFIG_ACPI */
#endif /* _ASM_RISCV_IRQ_H */
diff --git a/arch/riscv/include/asm/irq_stack.h b/arch/riscv/include/asm/irq_stack.h
new file mode 100644
index 000000000000..6441ded3b0cf
--- /dev/null
+++ b/arch/riscv/include/asm/irq_stack.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_RISCV_IRQ_STACK_H
+#define _ASM_RISCV_IRQ_STACK_H
+
+#include <linux/bug.h>
+#include <linux/gfp.h>
+#include <linux/kconfig.h>
+#include <linux/vmalloc.h>
+#include <linux/pgtable.h>
+#include <asm/thread_info.h>
+
+DECLARE_PER_CPU(ulong *, irq_stack_ptr);
+
+asmlinkage void call_on_irq_stack(struct pt_regs *regs,
+ void (*func)(struct pt_regs *));
+
+#ifdef CONFIG_VMAP_STACK
+/*
+ * To ensure that VMAP'd stack overflow detection works correctly, all VMAP'd
+ * stacks need to have the same alignment.
+ */
+static inline unsigned long *arch_alloc_vmap_stack(size_t stack_size, int node)
+{
+ void *p;
+
+ p = __vmalloc_node(stack_size, THREAD_ALIGN, THREADINFO_GFP, node,
+ __builtin_return_address(0));
+ return kasan_reset_tag(p);
+}
+#endif /* CONFIG_VMAP_STACK */
+
+#endif /* _ASM_RISCV_IRQ_STACK_H */
diff --git a/arch/riscv/include/asm/irq_work.h b/arch/riscv/include/asm/irq_work.h
index b53891964ae0..b27a4d64fc6a 100644
--- a/arch/riscv/include/asm/irq_work.h
+++ b/arch/riscv/include/asm/irq_work.h
@@ -6,5 +6,5 @@ static inline bool arch_irq_work_has_interrupt(void)
{
return IS_ENABLED(CONFIG_SMP);
}
-extern void arch_irq_work_raise(void);
+
#endif /* _ASM_RISCV_IRQ_WORK_H */
diff --git a/arch/riscv/include/asm/irqflags.h b/arch/riscv/include/asm/irqflags.h
index 08d4d6a5b7e9..6fd8cbfcfcc7 100644
--- a/arch/riscv/include/asm/irqflags.h
+++ b/arch/riscv/include/asm/irqflags.h
@@ -7,7 +7,6 @@
#ifndef _ASM_RISCV_IRQFLAGS_H
#define _ASM_RISCV_IRQFLAGS_H
-#include <asm/processor.h>
#include <asm/csr.h>
/* read interrupt enabled status */
diff --git a/arch/riscv/include/asm/jump_label.h b/arch/riscv/include/asm/jump_label.h
index 38af2ec7b9bf..87a71cc6d146 100644
--- a/arch/riscv/include/asm/jump_label.h
+++ b/arch/riscv/include/asm/jump_label.h
@@ -12,22 +12,32 @@
#include <linux/types.h>
#include <asm/asm.h>
+#define HAVE_JUMP_LABEL_BATCH
+
#define JUMP_LABEL_NOP_SIZE 4
-static __always_inline bool arch_static_branch(struct static_key *key,
- bool branch)
+#define JUMP_TABLE_ENTRY(key, label) \
+ ".pushsection __jump_table, \"aw\" \n\t" \
+ ".align " RISCV_LGPTR " \n\t" \
+ ".long 1b - ., " label " - . \n\t" \
+ "" RISCV_PTR " " key " - . \n\t" \
+ ".popsection \n\t"
+
+/* This macro is also expanded on the Rust side. */
+#define ARCH_STATIC_BRANCH_ASM(key, label) \
+ " .align 2 \n\t" \
+ " .option push \n\t" \
+ " .option norelax \n\t" \
+ " .option norvc \n\t" \
+ "1: nop \n\t" \
+ " .option pop \n\t" \
+ JUMP_TABLE_ENTRY(key, label)
+
+static __always_inline bool arch_static_branch(struct static_key * const key,
+ const bool branch)
{
- asm_volatile_goto(
- " .option push \n\t"
- " .option norelax \n\t"
- " .option norvc \n\t"
- "1: nop \n\t"
- " .option pop \n\t"
- " .pushsection __jump_table, \"aw\" \n\t"
- " .align " RISCV_LGPTR " \n\t"
- " .long 1b - ., %l[label] - . \n\t"
- " " RISCV_PTR " %0 - . \n\t"
- " .popsection \n\t"
+ asm goto(
+ ARCH_STATIC_BRANCH_ASM("%0", "%l[label]")
: : "i"(&((char *)key)[branch]) : : label);
return false;
@@ -35,20 +45,20 @@ label:
return true;
}
-static __always_inline bool arch_static_branch_jump(struct static_key *key,
- bool branch)
+#define ARCH_STATIC_BRANCH_JUMP_ASM(key, label) \
+ " .align 2 \n\t" \
+ " .option push \n\t" \
+ " .option norelax \n\t" \
+ " .option norvc \n\t" \
+ "1: j " label " \n\t" \
+ " .option pop \n\t" \
+ JUMP_TABLE_ENTRY(key, label)
+
+static __always_inline bool arch_static_branch_jump(struct static_key * const key,
+ const bool branch)
{
- asm_volatile_goto(
- " .option push \n\t"
- " .option norelax \n\t"
- " .option norvc \n\t"
- "1: jal zero, %l[label] \n\t"
- " .option pop \n\t"
- " .pushsection __jump_table, \"aw\" \n\t"
- " .align " RISCV_LGPTR " \n\t"
- " .long 1b - ., %l[label] - . \n\t"
- " " RISCV_PTR " %0 - . \n\t"
- " .popsection \n\t"
+ asm goto(
+ ARCH_STATIC_BRANCH_JUMP_ASM("%0", "%l[label]")
: : "i"(&((char *)key)[branch]) : : label);
return false;
diff --git a/arch/riscv/include/asm/kasan.h b/arch/riscv/include/asm/kasan.h
index 0b85e363e778..e6a0071bdb56 100644
--- a/arch/riscv/include/asm/kasan.h
+++ b/arch/riscv/include/asm/kasan.h
@@ -6,8 +6,6 @@
#ifndef __ASSEMBLY__
-#ifdef CONFIG_KASAN
-
/*
* The following comment was copied from arm64:
* KASAN_SHADOW_START: beginning of the kernel virtual addresses.
@@ -34,6 +32,8 @@
*/
#define KASAN_SHADOW_START ((KASAN_SHADOW_END - KASAN_SHADOW_SIZE) & PGDIR_MASK)
#define KASAN_SHADOW_END MODULES_LOWEST_VADDR
+
+#ifdef CONFIG_KASAN
#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
void kasan_init(void);
diff --git a/arch/riscv/include/asm/kexec.h b/arch/riscv/include/asm/kexec.h
index eee260e8ab30..b9ee8346cc8c 100644
--- a/arch/riscv/include/asm/kexec.h
+++ b/arch/riscv/include/asm/kexec.h
@@ -39,6 +39,7 @@ crash_setup_regs(struct pt_regs *newregs,
#define ARCH_HAS_KIMAGE_ARCH
struct kimage_arch {
+ void *fdt; /* For CONFIG_KEXEC_FILE */
unsigned long fdt_addr;
};
@@ -55,6 +56,7 @@ extern riscv_kexec_method riscv_kexec_norelocate;
#ifdef CONFIG_KEXEC_FILE
extern const struct kexec_file_ops elf_kexec_ops;
+extern const struct kexec_file_ops image_kexec_ops;
struct purgatory_info;
int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
@@ -62,6 +64,15 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
const Elf_Shdr *relsec,
const Elf_Shdr *symtab);
#define arch_kexec_apply_relocations_add arch_kexec_apply_relocations_add
+
+struct kimage;
+int arch_kimage_file_post_load_cleanup(struct kimage *image);
+#define arch_kimage_file_post_load_cleanup arch_kimage_file_post_load_cleanup
+
+int load_extra_segments(struct kimage *image, unsigned long kernel_start,
+ unsigned long kernel_len, char *initrd,
+ unsigned long initrd_len, char *cmdline,
+ unsigned long cmdline_len);
#endif
#endif
diff --git a/arch/riscv/include/asm/kfence.h b/arch/riscv/include/asm/kfence.h
index d887a54042aa..d08bf7fb3aee 100644
--- a/arch/riscv/include/asm/kfence.h
+++ b/arch/riscv/include/asm/kfence.h
@@ -8,41 +8,8 @@
#include <asm-generic/pgalloc.h>
#include <asm/pgtable.h>
-static inline int split_pmd_page(unsigned long addr)
-{
- int i;
- unsigned long pfn = PFN_DOWN(__pa((addr & PMD_MASK)));
- pmd_t *pmd = pmd_off_k(addr);
- pte_t *pte = pte_alloc_one_kernel(&init_mm);
-
- if (!pte)
- return -ENOMEM;
-
- for (i = 0; i < PTRS_PER_PTE; i++)
- set_pte(pte + i, pfn_pte(pfn + i, PAGE_KERNEL));
- set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(pte)), PAGE_TABLE));
-
- flush_tlb_kernel_range(addr, addr + PMD_SIZE);
- return 0;
-}
-
static inline bool arch_kfence_init_pool(void)
{
- int ret;
- unsigned long addr;
- pmd_t *pmd;
-
- for (addr = (unsigned long)__kfence_pool; is_kfence_address((void *)addr);
- addr += PAGE_SIZE) {
- pmd = pmd_off_k(addr);
-
- if (pmd_leaf(*pmd)) {
- ret = split_pmd_page(addr);
- if (ret)
- return false;
- }
- }
-
return true;
}
@@ -51,11 +18,13 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect)
pte_t *pte = virt_to_kpte(addr);
if (protect)
- set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT));
+ set_pte(pte, __pte(pte_val(ptep_get(pte)) & ~_PAGE_PRESENT));
else
- set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT));
+ set_pte(pte, __pte(pte_val(ptep_get(pte)) | _PAGE_PRESENT));
- flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+ preempt_disable();
+ local_flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+ preempt_enable();
return true;
}
diff --git a/arch/riscv/include/asm/kgdb.h b/arch/riscv/include/asm/kgdb.h
index 46677daf708b..cc11c4544cff 100644
--- a/arch/riscv/include/asm/kgdb.h
+++ b/arch/riscv/include/asm/kgdb.h
@@ -19,16 +19,9 @@
#ifndef __ASSEMBLY__
+void arch_kgdb_breakpoint(void);
extern unsigned long kgdb_compiled_break;
-static inline void arch_kgdb_breakpoint(void)
-{
- asm(".global kgdb_compiled_break\n"
- ".option norvc\n"
- "kgdb_compiled_break: ebreak\n"
- ".option rvc\n");
-}
-
#endif /* !__ASSEMBLY__ */
#define DBG_REG_ZERO "zero"
diff --git a/arch/riscv/include/asm/kprobes.h b/arch/riscv/include/asm/kprobes.h
index 217ef89f22b9..78ea44f76718 100644
--- a/arch/riscv/include/asm/kprobes.h
+++ b/arch/riscv/include/asm/kprobes.h
@@ -40,8 +40,15 @@ void arch_remove_kprobe(struct kprobe *p);
int kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr);
bool kprobe_breakpoint_handler(struct pt_regs *regs);
bool kprobe_single_step_handler(struct pt_regs *regs);
-void __kretprobe_trampoline(void);
-void __kprobes *trampoline_probe_handler(struct pt_regs *regs);
-
+#else
+static inline bool kprobe_breakpoint_handler(struct pt_regs *regs)
+{
+ return false;
+}
+
+static inline bool kprobe_single_step_handler(struct pt_regs *regs)
+{
+ return false;
+}
#endif /* CONFIG_KPROBES */
#endif /* _ASM_RISCV_KPROBES_H */
diff --git a/arch/riscv/include/asm/kvm_aia.h b/arch/riscv/include/asm/kvm_aia.h
new file mode 100644
index 000000000000..3b643b9efc07
--- /dev/null
+++ b/arch/riscv/include/asm/kvm_aia.h
@@ -0,0 +1,171 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2021 Western Digital Corporation or its affiliates.
+ * Copyright (C) 2022 Ventana Micro Systems Inc.
+ *
+ * Authors:
+ * Anup Patel <apatel@ventanamicro.com>
+ */
+
+#ifndef __KVM_RISCV_AIA_H
+#define __KVM_RISCV_AIA_H
+
+#include <linux/jump_label.h>
+#include <linux/kvm_types.h>
+#include <asm/csr.h>
+
+struct kvm_aia {
+ /* In-kernel irqchip created */
+ bool in_kernel;
+
+ /* In-kernel irqchip initialized */
+ bool initialized;
+
+ /* Virtualization mode (Emulation, HW Accelerated, or Auto) */
+ u32 mode;
+
+ /* Number of MSIs */
+ u32 nr_ids;
+
+ /* Number of wired IRQs */
+ u32 nr_sources;
+
+ /* Number of group bits in IMSIC address */
+ u32 nr_group_bits;
+
+ /* Position of group bits in IMSIC address */
+ u32 nr_group_shift;
+
+ /* Number of hart bits in IMSIC address */
+ u32 nr_hart_bits;
+
+ /* Number of guest bits in IMSIC address */
+ u32 nr_guest_bits;
+
+ /* Guest physical address of APLIC */
+ gpa_t aplic_addr;
+
+ /* Internal state of APLIC */
+ void *aplic_state;
+};
+
+struct kvm_vcpu_aia_csr {
+ unsigned long vsiselect;
+ unsigned long hviprio1;
+ unsigned long hviprio2;
+ unsigned long vsieh;
+ unsigned long hviph;
+ unsigned long hviprio1h;
+ unsigned long hviprio2h;
+};
+
+struct kvm_vcpu_aia {
+ /* CPU AIA CSR context of Guest VCPU */
+ struct kvm_vcpu_aia_csr guest_csr;
+
+ /* Guest physical address of IMSIC for this VCPU */
+ gpa_t imsic_addr;
+
+ /* HART index of IMSIC extacted from guest physical address */
+ u32 hart_index;
+
+ /* Internal state of IMSIC for this VCPU */
+ void *imsic_state;
+};
+
+#define KVM_RISCV_AIA_UNDEF_ADDR (-1)
+
+#define kvm_riscv_aia_initialized(k) ((k)->arch.aia.initialized)
+
+#define irqchip_in_kernel(k) ((k)->arch.aia.in_kernel)
+
+extern unsigned int kvm_riscv_aia_nr_hgei;
+extern unsigned int kvm_riscv_aia_max_ids;
+DECLARE_STATIC_KEY_FALSE(kvm_riscv_aia_available);
+#define kvm_riscv_aia_available() \
+ static_branch_unlikely(&kvm_riscv_aia_available)
+
+extern struct kvm_device_ops kvm_riscv_aia_device_ops;
+
+void kvm_riscv_vcpu_aia_imsic_release(struct kvm_vcpu *vcpu);
+int kvm_riscv_vcpu_aia_imsic_update(struct kvm_vcpu *vcpu);
+
+#define KVM_RISCV_AIA_IMSIC_TOPEI (ISELECT_MASK + 1)
+int kvm_riscv_vcpu_aia_imsic_rmw(struct kvm_vcpu *vcpu, unsigned long isel,
+ unsigned long *val, unsigned long new_val,
+ unsigned long wr_mask);
+int kvm_riscv_aia_imsic_rw_attr(struct kvm *kvm, unsigned long type,
+ bool write, unsigned long *val);
+int kvm_riscv_aia_imsic_has_attr(struct kvm *kvm, unsigned long type);
+void kvm_riscv_vcpu_aia_imsic_reset(struct kvm_vcpu *vcpu);
+int kvm_riscv_vcpu_aia_imsic_inject(struct kvm_vcpu *vcpu,
+ u32 guest_index, u32 offset, u32 iid);
+int kvm_riscv_vcpu_aia_imsic_init(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_aia_imsic_cleanup(struct kvm_vcpu *vcpu);
+
+int kvm_riscv_aia_aplic_set_attr(struct kvm *kvm, unsigned long type, u32 v);
+int kvm_riscv_aia_aplic_get_attr(struct kvm *kvm, unsigned long type, u32 *v);
+int kvm_riscv_aia_aplic_has_attr(struct kvm *kvm, unsigned long type);
+int kvm_riscv_aia_aplic_inject(struct kvm *kvm, u32 source, bool level);
+int kvm_riscv_aia_aplic_init(struct kvm *kvm);
+void kvm_riscv_aia_aplic_cleanup(struct kvm *kvm);
+
+#ifdef CONFIG_32BIT
+void kvm_riscv_vcpu_aia_flush_interrupts(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu);
+#else
+static inline void kvm_riscv_vcpu_aia_flush_interrupts(struct kvm_vcpu *vcpu)
+{
+}
+static inline void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu)
+{
+}
+#endif
+bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask);
+
+void kvm_riscv_vcpu_aia_update_hvip(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_aia_load(struct kvm_vcpu *vcpu, int cpu);
+void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu);
+int kvm_riscv_vcpu_aia_get_csr(struct kvm_vcpu *vcpu,
+ unsigned long reg_num,
+ unsigned long *out_val);
+int kvm_riscv_vcpu_aia_set_csr(struct kvm_vcpu *vcpu,
+ unsigned long reg_num,
+ unsigned long val);
+
+int kvm_riscv_vcpu_aia_rmw_topei(struct kvm_vcpu *vcpu,
+ unsigned int csr_num,
+ unsigned long *val,
+ unsigned long new_val,
+ unsigned long wr_mask);
+int kvm_riscv_vcpu_aia_rmw_ireg(struct kvm_vcpu *vcpu, unsigned int csr_num,
+ unsigned long *val, unsigned long new_val,
+ unsigned long wr_mask);
+#define KVM_RISCV_VCPU_AIA_CSR_FUNCS \
+{ .base = CSR_SIREG, .count = 1, .func = kvm_riscv_vcpu_aia_rmw_ireg }, \
+{ .base = CSR_STOPEI, .count = 1, .func = kvm_riscv_vcpu_aia_rmw_topei },
+
+int kvm_riscv_vcpu_aia_update(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_aia_reset(struct kvm_vcpu *vcpu);
+int kvm_riscv_vcpu_aia_init(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_aia_deinit(struct kvm_vcpu *vcpu);
+
+int kvm_riscv_aia_inject_msi_by_id(struct kvm *kvm, u32 hart_index,
+ u32 guest_index, u32 iid);
+int kvm_riscv_aia_inject_msi(struct kvm *kvm, struct kvm_msi *msi);
+int kvm_riscv_aia_inject_irq(struct kvm *kvm, unsigned int irq, bool level);
+
+void kvm_riscv_aia_init_vm(struct kvm *kvm);
+void kvm_riscv_aia_destroy_vm(struct kvm *kvm);
+
+int kvm_riscv_aia_alloc_hgei(int cpu, struct kvm_vcpu *owner,
+ void __iomem **hgei_va, phys_addr_t *hgei_pa);
+void kvm_riscv_aia_free_hgei(int cpu, int hgei);
+void kvm_riscv_aia_wakeon_hgei(struct kvm_vcpu *owner, bool enable);
+
+void kvm_riscv_aia_enable(void);
+void kvm_riscv_aia_disable(void);
+int kvm_riscv_aia_init(void);
+void kvm_riscv_aia_exit(void);
+
+#endif
diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 319c8aeb42af..85cfebc32e4c 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -13,9 +13,14 @@
#include <linux/kvm.h>
#include <linux/kvm_types.h>
#include <linux/spinlock.h>
-#include <asm/csr.h>
+#include <asm/hwcap.h>
+#include <asm/kvm_aia.h>
+#include <asm/ptrace.h>
#include <asm/kvm_vcpu_fp.h>
+#include <asm/kvm_vcpu_insn.h>
+#include <asm/kvm_vcpu_sbi.h>
#include <asm/kvm_vcpu_timer.h>
+#include <asm/kvm_vcpu_pmu.h>
#define KVM_MAX_VCPUS 1024
@@ -23,6 +28,8 @@
#define KVM_VCPU_MAX_FEATURES 0
+#define KVM_IRQCHIP_NUM_PINS 1024
+
#define KVM_REQ_SLEEP \
KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(1)
@@ -34,6 +41,18 @@
KVM_ARCH_REQ_FLAGS(4, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_HFENCE \
KVM_ARCH_REQ_FLAGS(5, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_STEAL_UPDATE KVM_ARCH_REQ(6)
+
+#define KVM_HEDELEG_DEFAULT (BIT(EXC_INST_MISALIGNED) | \
+ BIT(EXC_BREAKPOINT) | \
+ BIT(EXC_SYSCALL) | \
+ BIT(EXC_INST_PAGE_FAULT) | \
+ BIT(EXC_LOAD_PAGE_FAULT) | \
+ BIT(EXC_STORE_PAGE_FAULT))
+
+#define KVM_HIDELEG_DEFAULT (BIT(IRQ_VS_SOFT) | \
+ BIT(IRQ_VS_TIMER) | \
+ BIT(IRQ_VS_EXT))
enum kvm_riscv_hfence_type {
KVM_RISCV_HFENCE_UNKNOWN = 0,
@@ -61,9 +80,18 @@ struct kvm_vcpu_stat {
struct kvm_vcpu_stat_generic generic;
u64 ecall_exit_stat;
u64 wfi_exit_stat;
+ u64 wrs_exit_stat;
u64 mmio_exit_user;
u64 mmio_exit_kernel;
+ u64 csr_exit_user;
+ u64 csr_exit_kernel;
+ u64 signal_exits;
u64 exits;
+ u64 instr_illegal_exits;
+ u64 load_misaligned_exits;
+ u64 store_misaligned_exits;
+ u64 load_access_exits;
+ u64 store_access_exits;
};
struct kvm_arch_memory_slot {
@@ -88,18 +116,12 @@ struct kvm_arch {
/* Guest Timer */
struct kvm_guest_timer timer;
-};
-struct kvm_mmio_decode {
- unsigned long insn;
- int insn_len;
- int len;
- int shift;
- int return_handled;
-};
+ /* AIA Guest/VM context */
+ struct kvm_aia aia;
-struct kvm_sbi_context {
- int return_handled;
+ /* KVM_CAP_RISCV_MP_STATE_RESET */
+ bool mp_state_reset;
};
struct kvm_cpu_trap {
@@ -147,6 +169,7 @@ struct kvm_cpu_context {
unsigned long sstatus;
unsigned long hstatus;
union __riscv_fp_state fp;
+ struct __riscv_v_ext_state vector;
};
struct kvm_vcpu_csr {
@@ -160,6 +183,23 @@ struct kvm_vcpu_csr {
unsigned long hvip;
unsigned long vsatp;
unsigned long scounteren;
+ unsigned long senvcfg;
+};
+
+struct kvm_vcpu_config {
+ u64 henvcfg;
+ u64 hstateen0;
+ unsigned long hedeleg;
+};
+
+struct kvm_vcpu_smstateen_csr {
+ unsigned long sstateen0;
+};
+
+struct kvm_vcpu_reset_state {
+ spinlock_t lock;
+ unsigned long pc;
+ unsigned long a1;
};
struct kvm_vcpu_arch {
@@ -170,12 +210,19 @@ struct kvm_vcpu_arch {
int last_exit_cpu;
/* ISA feature bits (similar to MISA) */
- unsigned long isa;
+ DECLARE_BITMAP(isa, RISCV_ISA_EXT_MAX);
+
+ /* Vendor, Arch, and Implementation details */
+ unsigned long mvendorid;
+ unsigned long marchid;
+ unsigned long mimpid;
/* SSCRATCH, STVEC, and SCOUNTEREN of Host */
unsigned long host_sscratch;
unsigned long host_stvec;
unsigned long host_scounteren;
+ unsigned long host_senvcfg;
+ unsigned long host_sstateen0;
/* CPU context of Host */
struct kvm_cpu_context host_context;
@@ -186,11 +233,11 @@ struct kvm_vcpu_arch {
/* CPU CSR context of Guest VCPU */
struct kvm_vcpu_csr guest_csr;
- /* CPU context upon Guest VCPU reset */
- struct kvm_cpu_context guest_reset_context;
+ /* CPU Smstateen CSR context of Guest VCPU */
+ struct kvm_vcpu_smstateen_csr smstateen_csr;
- /* CPU CSR context upon Guest VCPU reset */
- struct kvm_vcpu_csr guest_reset_csr;
+ /* CPU reset state of Guest VCPU */
+ struct kvm_vcpu_reset_state reset_state;
/*
* VCPU interrupts
@@ -201,8 +248,9 @@ struct kvm_vcpu_arch {
* in irqs_pending. Our approach is modeled around multiple producer
* and single consumer problem where the consumer is the VCPU itself.
*/
- unsigned long irqs_pending;
- unsigned long irqs_pending_mask;
+#define KVM_RISCV_VCPU_NR_IRQS 64
+ DECLARE_BITMAP(irqs_pending, KVM_RISCV_VCPU_NR_IRQS);
+ DECLARE_BITMAP(irqs_pending_mask, KVM_RISCV_VCPU_NR_IRQS);
/* VCPU Timer */
struct kvm_vcpu_timer timer;
@@ -216,24 +264,47 @@ struct kvm_vcpu_arch {
/* MMIO instruction details */
struct kvm_mmio_decode mmio_decode;
+ /* CSR instruction details */
+ struct kvm_csr_decode csr_decode;
+
/* SBI context */
- struct kvm_sbi_context sbi_context;
+ struct kvm_vcpu_sbi_context sbi_context;
+
+ /* AIA VCPU context */
+ struct kvm_vcpu_aia aia_context;
/* Cache pages needed to program page tables with spinlock held */
struct kvm_mmu_memory_cache mmu_page_cache;
- /* VCPU power-off state */
- bool power_off;
+ /* VCPU power state */
+ struct kvm_mp_state mp_state;
+ spinlock_t mp_state_lock;
/* Don't run the VCPU (blocked) */
bool pause;
-};
-static inline void kvm_arch_hardware_unsetup(void) {}
-static inline void kvm_arch_sync_events(struct kvm *kvm) {}
-static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
+ /* Performance monitoring context */
+ struct kvm_pmu pmu_context;
+
+ /* 'static' configurations which are set only once */
+ struct kvm_vcpu_config cfg;
-#define KVM_ARCH_WANT_MMU_NOTIFIER
+ /* SBI steal-time accounting */
+ struct {
+ gpa_t shmem;
+ u64 last_steal;
+ } sta;
+};
+
+/*
+ * Returns true if a Performance Monitoring Interrupt (PMI), a.k.a. perf event,
+ * arrived in guest context. For riscv, any event that arrives while a vCPU is
+ * loaded is considered to be "in guest".
+ */
+static inline bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu)
+{
+ return IS_ENABLED(CONFIG_GUEST_PERF_EVENTS) && !!vcpu;
+}
#define KVM_RISCV_GSTAGE_TLB_MIN_ORDER 12
@@ -285,46 +356,63 @@ void kvm_riscv_hfence_vvma_gva(struct kvm *kvm,
void kvm_riscv_hfence_vvma_all(struct kvm *kvm,
unsigned long hbase, unsigned long hmask);
+int kvm_riscv_gstage_ioremap(struct kvm *kvm, gpa_t gpa,
+ phys_addr_t hpa, unsigned long size,
+ bool writable, bool in_atomic);
+void kvm_riscv_gstage_iounmap(struct kvm *kvm, gpa_t gpa,
+ unsigned long size);
int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,
struct kvm_memory_slot *memslot,
gpa_t gpa, unsigned long hva, bool is_write);
int kvm_riscv_gstage_alloc_pgd(struct kvm *kvm);
void kvm_riscv_gstage_free_pgd(struct kvm *kvm);
void kvm_riscv_gstage_update_hgatp(struct kvm_vcpu *vcpu);
-void kvm_riscv_gstage_mode_detect(void);
-unsigned long kvm_riscv_gstage_mode(void);
+void __init kvm_riscv_gstage_mode_detect(void);
+unsigned long __init kvm_riscv_gstage_mode(void);
int kvm_riscv_gstage_gpa_bits(void);
-void kvm_riscv_gstage_vmid_detect(void);
+void __init kvm_riscv_gstage_vmid_detect(void);
unsigned long kvm_riscv_gstage_vmid_bits(void);
int kvm_riscv_gstage_vmid_init(struct kvm *kvm);
bool kvm_riscv_gstage_vmid_ver_changed(struct kvm_vmid *vmid);
void kvm_riscv_gstage_vmid_update(struct kvm_vcpu *vcpu);
+int kvm_riscv_setup_default_irq_routing(struct kvm *kvm, u32 lines);
+
void __kvm_riscv_unpriv_trap(void);
-void kvm_riscv_vcpu_wfi(struct kvm_vcpu *vcpu);
unsigned long kvm_riscv_vcpu_unpriv_read(struct kvm_vcpu *vcpu,
bool read_insn,
unsigned long guest_addr,
struct kvm_cpu_trap *trap);
void kvm_riscv_vcpu_trap_redirect(struct kvm_vcpu *vcpu,
struct kvm_cpu_trap *trap);
-int kvm_riscv_vcpu_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
struct kvm_cpu_trap *trap);
void __kvm_riscv_switch_to(struct kvm_vcpu_arch *vcpu_arch);
+void kvm_riscv_vcpu_setup_isa(struct kvm_vcpu *vcpu);
+unsigned long kvm_riscv_vcpu_num_regs(struct kvm_vcpu *vcpu);
+int kvm_riscv_vcpu_copy_reg_indices(struct kvm_vcpu *vcpu,
+ u64 __user *uindices);
+int kvm_riscv_vcpu_get_reg(struct kvm_vcpu *vcpu,
+ const struct kvm_one_reg *reg);
+int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu,
+ const struct kvm_one_reg *reg);
+
int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq);
int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq);
void kvm_riscv_vcpu_flush_interrupts(struct kvm_vcpu *vcpu);
void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu);
-bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, unsigned long mask);
+bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, u64 mask);
+void __kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu);
void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu);
+void __kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu);
void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu);
+bool kvm_riscv_vcpu_stopped(struct kvm_vcpu *vcpu);
-int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
-int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run);
+void kvm_riscv_vcpu_sbi_sta_reset(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_record_steal_time(struct kvm_vcpu *vcpu);
#endif /* __RISCV_KVM_HOST_H__ */
diff --git a/arch/riscv/include/asm/kvm_nacl.h b/arch/riscv/include/asm/kvm_nacl.h
new file mode 100644
index 000000000000..4124d5e06a0f
--- /dev/null
+++ b/arch/riscv/include/asm/kvm_nacl.h
@@ -0,0 +1,245 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2024 Ventana Micro Systems Inc.
+ */
+
+#ifndef __KVM_NACL_H
+#define __KVM_NACL_H
+
+#include <linux/jump_label.h>
+#include <linux/percpu.h>
+#include <asm/byteorder.h>
+#include <asm/csr.h>
+#include <asm/sbi.h>
+
+struct kvm_vcpu_arch;
+
+DECLARE_STATIC_KEY_FALSE(kvm_riscv_nacl_available);
+#define kvm_riscv_nacl_available() \
+ static_branch_unlikely(&kvm_riscv_nacl_available)
+
+DECLARE_STATIC_KEY_FALSE(kvm_riscv_nacl_sync_csr_available);
+#define kvm_riscv_nacl_sync_csr_available() \
+ static_branch_unlikely(&kvm_riscv_nacl_sync_csr_available)
+
+DECLARE_STATIC_KEY_FALSE(kvm_riscv_nacl_sync_hfence_available);
+#define kvm_riscv_nacl_sync_hfence_available() \
+ static_branch_unlikely(&kvm_riscv_nacl_sync_hfence_available)
+
+DECLARE_STATIC_KEY_FALSE(kvm_riscv_nacl_sync_sret_available);
+#define kvm_riscv_nacl_sync_sret_available() \
+ static_branch_unlikely(&kvm_riscv_nacl_sync_sret_available)
+
+DECLARE_STATIC_KEY_FALSE(kvm_riscv_nacl_autoswap_csr_available);
+#define kvm_riscv_nacl_autoswap_csr_available() \
+ static_branch_unlikely(&kvm_riscv_nacl_autoswap_csr_available)
+
+struct kvm_riscv_nacl {
+ void *shmem;
+ phys_addr_t shmem_phys;
+};
+DECLARE_PER_CPU(struct kvm_riscv_nacl, kvm_riscv_nacl);
+
+void __kvm_riscv_nacl_hfence(void *shmem,
+ unsigned long control,
+ unsigned long page_num,
+ unsigned long page_count);
+
+void __kvm_riscv_nacl_switch_to(struct kvm_vcpu_arch *vcpu_arch,
+ unsigned long sbi_ext_id,
+ unsigned long sbi_func_id);
+
+int kvm_riscv_nacl_enable(void);
+
+void kvm_riscv_nacl_disable(void);
+
+void kvm_riscv_nacl_exit(void);
+
+int kvm_riscv_nacl_init(void);
+
+#ifdef CONFIG_32BIT
+#define lelong_to_cpu(__x) le32_to_cpu(__x)
+#define cpu_to_lelong(__x) cpu_to_le32(__x)
+#else
+#define lelong_to_cpu(__x) le64_to_cpu(__x)
+#define cpu_to_lelong(__x) cpu_to_le64(__x)
+#endif
+
+#define nacl_shmem() \
+ this_cpu_ptr(&kvm_riscv_nacl)->shmem
+
+#define nacl_scratch_read_long(__shmem, __offset) \
+({ \
+ unsigned long *__p = (__shmem) + \
+ SBI_NACL_SHMEM_SCRATCH_OFFSET + \
+ (__offset); \
+ lelong_to_cpu(*__p); \
+})
+
+#define nacl_scratch_write_long(__shmem, __offset, __val) \
+do { \
+ unsigned long *__p = (__shmem) + \
+ SBI_NACL_SHMEM_SCRATCH_OFFSET + \
+ (__offset); \
+ *__p = cpu_to_lelong(__val); \
+} while (0)
+
+#define nacl_scratch_write_longs(__shmem, __offset, __array, __count) \
+do { \
+ unsigned int __i; \
+ unsigned long *__p = (__shmem) + \
+ SBI_NACL_SHMEM_SCRATCH_OFFSET + \
+ (__offset); \
+ for (__i = 0; __i < (__count); __i++) \
+ __p[__i] = cpu_to_lelong((__array)[__i]); \
+} while (0)
+
+#define nacl_sync_hfence(__e) \
+ sbi_ecall(SBI_EXT_NACL, SBI_EXT_NACL_SYNC_HFENCE, \
+ (__e), 0, 0, 0, 0, 0)
+
+#define nacl_hfence_mkconfig(__type, __order, __vmid, __asid) \
+({ \
+ unsigned long __c = SBI_NACL_SHMEM_HFENCE_CONFIG_PEND; \
+ __c |= ((__type) & SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_MASK) \
+ << SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_SHIFT; \
+ __c |= (((__order) - SBI_NACL_SHMEM_HFENCE_ORDER_BASE) & \
+ SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_MASK) \
+ << SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_SHIFT; \
+ __c |= ((__vmid) & SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_MASK) \
+ << SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_SHIFT; \
+ __c |= ((__asid) & SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_MASK); \
+ __c; \
+})
+
+#define nacl_hfence_mkpnum(__order, __addr) \
+ ((__addr) >> (__order))
+
+#define nacl_hfence_mkpcount(__order, __size) \
+ ((__size) >> (__order))
+
+#define nacl_hfence_gvma(__shmem, __gpa, __gpsz, __order) \
+__kvm_riscv_nacl_hfence(__shmem, \
+ nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_GVMA, \
+ __order, 0, 0), \
+ nacl_hfence_mkpnum(__order, __gpa), \
+ nacl_hfence_mkpcount(__order, __gpsz))
+
+#define nacl_hfence_gvma_all(__shmem) \
+__kvm_riscv_nacl_hfence(__shmem, \
+ nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_ALL, \
+ 0, 0, 0), 0, 0)
+
+#define nacl_hfence_gvma_vmid(__shmem, __vmid, __gpa, __gpsz, __order) \
+__kvm_riscv_nacl_hfence(__shmem, \
+ nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_VMID, \
+ __order, __vmid, 0), \
+ nacl_hfence_mkpnum(__order, __gpa), \
+ nacl_hfence_mkpcount(__order, __gpsz))
+
+#define nacl_hfence_gvma_vmid_all(__shmem, __vmid) \
+__kvm_riscv_nacl_hfence(__shmem, \
+ nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_VMID_ALL, \
+ 0, __vmid, 0), 0, 0)
+
+#define nacl_hfence_vvma(__shmem, __vmid, __gva, __gvsz, __order) \
+__kvm_riscv_nacl_hfence(__shmem, \
+ nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_VVMA, \
+ __order, __vmid, 0), \
+ nacl_hfence_mkpnum(__order, __gva), \
+ nacl_hfence_mkpcount(__order, __gvsz))
+
+#define nacl_hfence_vvma_all(__shmem, __vmid) \
+__kvm_riscv_nacl_hfence(__shmem, \
+ nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ALL, \
+ 0, __vmid, 0), 0, 0)
+
+#define nacl_hfence_vvma_asid(__shmem, __vmid, __asid, __gva, __gvsz, __order)\
+__kvm_riscv_nacl_hfence(__shmem, \
+ nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ASID, \
+ __order, __vmid, __asid), \
+ nacl_hfence_mkpnum(__order, __gva), \
+ nacl_hfence_mkpcount(__order, __gvsz))
+
+#define nacl_hfence_vvma_asid_all(__shmem, __vmid, __asid) \
+__kvm_riscv_nacl_hfence(__shmem, \
+ nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ASID_ALL, \
+ 0, __vmid, __asid), 0, 0)
+
+#define nacl_csr_read(__shmem, __csr) \
+({ \
+ unsigned long *__a = (__shmem) + SBI_NACL_SHMEM_CSR_OFFSET; \
+ lelong_to_cpu(__a[SBI_NACL_SHMEM_CSR_INDEX(__csr)]); \
+})
+
+#define nacl_csr_write(__shmem, __csr, __val) \
+do { \
+ void *__s = (__shmem); \
+ unsigned int __i = SBI_NACL_SHMEM_CSR_INDEX(__csr); \
+ unsigned long *__a = (__s) + SBI_NACL_SHMEM_CSR_OFFSET; \
+ u8 *__b = (__s) + SBI_NACL_SHMEM_DBITMAP_OFFSET; \
+ __a[__i] = cpu_to_lelong(__val); \
+ __b[__i >> 3] |= 1U << (__i & 0x7); \
+} while (0)
+
+#define nacl_csr_swap(__shmem, __csr, __val) \
+({ \
+ void *__s = (__shmem); \
+ unsigned int __i = SBI_NACL_SHMEM_CSR_INDEX(__csr); \
+ unsigned long *__a = (__s) + SBI_NACL_SHMEM_CSR_OFFSET; \
+ u8 *__b = (__s) + SBI_NACL_SHMEM_DBITMAP_OFFSET; \
+ unsigned long __r = lelong_to_cpu(__a[__i]); \
+ __a[__i] = cpu_to_lelong(__val); \
+ __b[__i >> 3] |= 1U << (__i & 0x7); \
+ __r; \
+})
+
+#define nacl_sync_csr(__csr) \
+ sbi_ecall(SBI_EXT_NACL, SBI_EXT_NACL_SYNC_CSR, \
+ (__csr), 0, 0, 0, 0, 0)
+
+/*
+ * Each ncsr_xyz() macro defined below has it's own static-branch so every
+ * use of ncsr_xyz() macro emits a patchable direct jump. This means multiple
+ * back-to-back ncsr_xyz() macro usage will emit multiple patchable direct
+ * jumps which is sub-optimal.
+ *
+ * Based on the above, it is recommended to avoid multiple back-to-back
+ * ncsr_xyz() macro usage.
+ */
+
+#define ncsr_read(__csr) \
+({ \
+ unsigned long __r; \
+ if (kvm_riscv_nacl_available()) \
+ __r = nacl_csr_read(nacl_shmem(), __csr); \
+ else \
+ __r = csr_read(__csr); \
+ __r; \
+})
+
+#define ncsr_write(__csr, __val) \
+do { \
+ if (kvm_riscv_nacl_sync_csr_available()) \
+ nacl_csr_write(nacl_shmem(), __csr, __val); \
+ else \
+ csr_write(__csr, __val); \
+} while (0)
+
+#define ncsr_swap(__csr, __val) \
+({ \
+ unsigned long __r; \
+ if (kvm_riscv_nacl_sync_csr_available()) \
+ __r = nacl_csr_swap(nacl_shmem(), __csr, __val); \
+ else \
+ __r = csr_swap(__csr, __val); \
+ __r; \
+})
+
+#define nsync_csr(__csr) \
+do { \
+ if (kvm_riscv_nacl_sync_csr_available()) \
+ nacl_sync_csr(__csr); \
+} while (0)
+
+#endif
diff --git a/arch/riscv/include/asm/kvm_vcpu_fp.h b/arch/riscv/include/asm/kvm_vcpu_fp.h
index 4da9b8e0f050..b5540147409f 100644
--- a/arch/riscv/include/asm/kvm_vcpu_fp.h
+++ b/arch/riscv/include/asm/kvm_vcpu_fp.h
@@ -22,9 +22,9 @@ void __kvm_riscv_fp_d_restore(struct kvm_cpu_context *context);
void kvm_riscv_vcpu_fp_reset(struct kvm_vcpu *vcpu);
void kvm_riscv_vcpu_guest_fp_save(struct kvm_cpu_context *cntx,
- unsigned long isa);
+ const unsigned long *isa);
void kvm_riscv_vcpu_guest_fp_restore(struct kvm_cpu_context *cntx,
- unsigned long isa);
+ const unsigned long *isa);
void kvm_riscv_vcpu_host_fp_save(struct kvm_cpu_context *cntx);
void kvm_riscv_vcpu_host_fp_restore(struct kvm_cpu_context *cntx);
#else
@@ -32,12 +32,12 @@ static inline void kvm_riscv_vcpu_fp_reset(struct kvm_vcpu *vcpu)
{
}
static inline void kvm_riscv_vcpu_guest_fp_save(struct kvm_cpu_context *cntx,
- unsigned long isa)
+ const unsigned long *isa)
{
}
static inline void kvm_riscv_vcpu_guest_fp_restore(
struct kvm_cpu_context *cntx,
- unsigned long isa)
+ const unsigned long *isa)
{
}
static inline void kvm_riscv_vcpu_host_fp_save(struct kvm_cpu_context *cntx)
diff --git a/arch/riscv/include/asm/kvm_vcpu_insn.h b/arch/riscv/include/asm/kvm_vcpu_insn.h
new file mode 100644
index 000000000000..350011c83581
--- /dev/null
+++ b/arch/riscv/include/asm/kvm_vcpu_insn.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2022 Ventana Micro Systems Inc.
+ */
+
+#ifndef __KVM_VCPU_RISCV_INSN_H
+#define __KVM_VCPU_RISCV_INSN_H
+
+struct kvm_vcpu;
+struct kvm_run;
+struct kvm_cpu_trap;
+
+struct kvm_mmio_decode {
+ unsigned long insn;
+ int insn_len;
+ int len;
+ int shift;
+ int return_handled;
+};
+
+struct kvm_csr_decode {
+ unsigned long insn;
+ int return_handled;
+};
+
+/* Return values used by function emulating a particular instruction */
+enum kvm_insn_return {
+ KVM_INSN_EXIT_TO_USER_SPACE = 0,
+ KVM_INSN_CONTINUE_NEXT_SEPC,
+ KVM_INSN_CONTINUE_SAME_SEPC,
+ KVM_INSN_ILLEGAL_TRAP,
+ KVM_INSN_VIRTUAL_TRAP
+};
+
+void kvm_riscv_vcpu_wfi(struct kvm_vcpu *vcpu);
+int kvm_riscv_vcpu_csr_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_riscv_vcpu_virtual_insn(struct kvm_vcpu *vcpu, struct kvm_run *run,
+ struct kvm_cpu_trap *trap);
+
+int kvm_riscv_vcpu_mmio_load(struct kvm_vcpu *vcpu, struct kvm_run *run,
+ unsigned long fault_addr,
+ unsigned long htinst);
+int kvm_riscv_vcpu_mmio_store(struct kvm_vcpu *vcpu, struct kvm_run *run,
+ unsigned long fault_addr,
+ unsigned long htinst);
+int kvm_riscv_vcpu_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
+
+#endif
diff --git a/arch/riscv/include/asm/kvm_vcpu_pmu.h b/arch/riscv/include/asm/kvm_vcpu_pmu.h
new file mode 100644
index 000000000000..1d85b6617508
--- /dev/null
+++ b/arch/riscv/include/asm/kvm_vcpu_pmu.h
@@ -0,0 +1,132 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2023 Rivos Inc
+ *
+ * Authors:
+ * Atish Patra <atishp@rivosinc.com>
+ */
+
+#ifndef __KVM_VCPU_RISCV_PMU_H
+#define __KVM_VCPU_RISCV_PMU_H
+
+#include <linux/perf/riscv_pmu.h>
+#include <asm/kvm_vcpu_insn.h>
+#include <asm/sbi.h>
+
+#ifdef CONFIG_RISCV_PMU_SBI
+#define RISCV_KVM_MAX_FW_CTRS 32
+#define RISCV_KVM_MAX_HW_CTRS 32
+#define RISCV_KVM_MAX_COUNTERS (RISCV_KVM_MAX_HW_CTRS + RISCV_KVM_MAX_FW_CTRS)
+static_assert(RISCV_KVM_MAX_COUNTERS <= 64);
+
+struct kvm_fw_event {
+ /* Current value of the event */
+ u64 value;
+
+ /* Event monitoring status */
+ bool started;
+};
+
+/* Per virtual pmu counter data */
+struct kvm_pmc {
+ u8 idx;
+ struct perf_event *perf_event;
+ u64 counter_val;
+ union sbi_pmu_ctr_info cinfo;
+ /* Event monitoring status */
+ bool started;
+ /* Monitoring event ID */
+ unsigned long event_idx;
+ struct kvm_vcpu *vcpu;
+};
+
+/* PMU data structure per vcpu */
+struct kvm_pmu {
+ struct kvm_pmc pmc[RISCV_KVM_MAX_COUNTERS];
+ struct kvm_fw_event fw_event[RISCV_KVM_MAX_FW_CTRS];
+ /* Number of the virtual firmware counters available */
+ int num_fw_ctrs;
+ /* Number of the virtual hardware counters available */
+ int num_hw_ctrs;
+ /* A flag to indicate that pmu initialization is done */
+ bool init_done;
+ /* Bit map of all the virtual counter used */
+ DECLARE_BITMAP(pmc_in_use, RISCV_KVM_MAX_COUNTERS);
+ /* Bit map of all the virtual counter overflown */
+ DECLARE_BITMAP(pmc_overflown, RISCV_KVM_MAX_COUNTERS);
+ /* The address of the counter snapshot area (guest physical address) */
+ gpa_t snapshot_addr;
+ /* The actual data of the snapshot */
+ struct riscv_pmu_snapshot_data *sdata;
+};
+
+#define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu_context)
+#define pmu_to_vcpu(pmu) (container_of((pmu), struct kvm_vcpu, arch.pmu_context))
+
+#if defined(CONFIG_32BIT)
+#define KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS \
+{.base = CSR_CYCLEH, .count = 32, .func = kvm_riscv_vcpu_pmu_read_hpm }, \
+{.base = CSR_CYCLE, .count = 32, .func = kvm_riscv_vcpu_pmu_read_hpm },
+#else
+#define KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS \
+{.base = CSR_CYCLE, .count = 32, .func = kvm_riscv_vcpu_pmu_read_hpm },
+#endif
+
+int kvm_riscv_vcpu_pmu_incr_fw(struct kvm_vcpu *vcpu, unsigned long fid);
+int kvm_riscv_vcpu_pmu_read_hpm(struct kvm_vcpu *vcpu, unsigned int csr_num,
+ unsigned long *val, unsigned long new_val,
+ unsigned long wr_mask);
+
+int kvm_riscv_vcpu_pmu_num_ctrs(struct kvm_vcpu *vcpu, struct kvm_vcpu_sbi_return *retdata);
+int kvm_riscv_vcpu_pmu_ctr_info(struct kvm_vcpu *vcpu, unsigned long cidx,
+ struct kvm_vcpu_sbi_return *retdata);
+int kvm_riscv_vcpu_pmu_ctr_start(struct kvm_vcpu *vcpu, unsigned long ctr_base,
+ unsigned long ctr_mask, unsigned long flags, u64 ival,
+ struct kvm_vcpu_sbi_return *retdata);
+int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base,
+ unsigned long ctr_mask, unsigned long flags,
+ struct kvm_vcpu_sbi_return *retdata);
+int kvm_riscv_vcpu_pmu_ctr_cfg_match(struct kvm_vcpu *vcpu, unsigned long ctr_base,
+ unsigned long ctr_mask, unsigned long flags,
+ unsigned long eidx, u64 evtdata,
+ struct kvm_vcpu_sbi_return *retdata);
+int kvm_riscv_vcpu_pmu_fw_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx,
+ struct kvm_vcpu_sbi_return *retdata);
+int kvm_riscv_vcpu_pmu_fw_ctr_read_hi(struct kvm_vcpu *vcpu, unsigned long cidx,
+ struct kvm_vcpu_sbi_return *retdata);
+void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu);
+int kvm_riscv_vcpu_pmu_snapshot_set_shmem(struct kvm_vcpu *vcpu, unsigned long saddr_low,
+ unsigned long saddr_high, unsigned long flags,
+ struct kvm_vcpu_sbi_return *retdata);
+void kvm_riscv_vcpu_pmu_deinit(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_pmu_reset(struct kvm_vcpu *vcpu);
+
+#else
+struct kvm_pmu {
+};
+
+static inline int kvm_riscv_vcpu_pmu_read_legacy(struct kvm_vcpu *vcpu, unsigned int csr_num,
+ unsigned long *val, unsigned long new_val,
+ unsigned long wr_mask)
+{
+ if (csr_num == CSR_CYCLE || csr_num == CSR_INSTRET) {
+ *val = 0;
+ return KVM_INSN_CONTINUE_NEXT_SEPC;
+ } else {
+ return KVM_INSN_ILLEGAL_TRAP;
+ }
+}
+
+#define KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS \
+{.base = CSR_CYCLE, .count = 3, .func = kvm_riscv_vcpu_pmu_read_legacy },
+
+static inline void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu) {}
+static inline int kvm_riscv_vcpu_pmu_incr_fw(struct kvm_vcpu *vcpu, unsigned long fid)
+{
+ return 0;
+}
+
+static inline void kvm_riscv_vcpu_pmu_deinit(struct kvm_vcpu *vcpu) {}
+static inline void kvm_riscv_vcpu_pmu_reset(struct kvm_vcpu *vcpu) {}
+#endif /* CONFIG_RISCV_PMU_SBI */
+#endif /* !__KVM_VCPU_RISCV_PMU_H */
diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h
index 83d6d4d2b1df..439ab2b3534f 100644
--- a/arch/riscv/include/asm/kvm_vcpu_sbi.h
+++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h
@@ -11,26 +11,89 @@
#define KVM_SBI_IMPID 3
-#define KVM_SBI_VERSION_MAJOR 0
-#define KVM_SBI_VERSION_MINOR 3
+#define KVM_SBI_VERSION_MAJOR 2
+#define KVM_SBI_VERSION_MINOR 0
+
+enum kvm_riscv_sbi_ext_status {
+ KVM_RISCV_SBI_EXT_STATUS_UNINITIALIZED,
+ KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE,
+ KVM_RISCV_SBI_EXT_STATUS_ENABLED,
+ KVM_RISCV_SBI_EXT_STATUS_DISABLED,
+};
+
+struct kvm_vcpu_sbi_context {
+ int return_handled;
+ enum kvm_riscv_sbi_ext_status ext_status[KVM_RISCV_SBI_EXT_MAX];
+};
+
+struct kvm_vcpu_sbi_return {
+ unsigned long out_val;
+ unsigned long err_val;
+ struct kvm_cpu_trap *utrap;
+ bool uexit;
+};
struct kvm_vcpu_sbi_extension {
unsigned long extid_start;
unsigned long extid_end;
+
+ bool default_disabled;
+
/**
* SBI extension handler. It can be defined for a given extension or group of
* extension. But it should always return linux error codes rather than SBI
* specific error codes.
*/
int (*handler)(struct kvm_vcpu *vcpu, struct kvm_run *run,
- unsigned long *out_val, struct kvm_cpu_trap *utrap,
- bool *exit);
+ struct kvm_vcpu_sbi_return *retdata);
+
+ /* Extension specific probe function */
+ unsigned long (*probe)(struct kvm_vcpu *vcpu);
};
void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run);
void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu,
struct kvm_run *run,
u32 type, u64 flags);
-const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext(unsigned long extid);
+void kvm_riscv_vcpu_sbi_request_reset(struct kvm_vcpu *vcpu,
+ unsigned long pc, unsigned long a1);
+void kvm_riscv_vcpu_sbi_load_reset_state(struct kvm_vcpu *vcpu);
+int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_riscv_vcpu_set_reg_sbi_ext(struct kvm_vcpu *vcpu,
+ const struct kvm_one_reg *reg);
+int kvm_riscv_vcpu_get_reg_sbi_ext(struct kvm_vcpu *vcpu,
+ const struct kvm_one_reg *reg);
+int kvm_riscv_vcpu_set_reg_sbi(struct kvm_vcpu *vcpu,
+ const struct kvm_one_reg *reg);
+int kvm_riscv_vcpu_get_reg_sbi(struct kvm_vcpu *vcpu,
+ const struct kvm_one_reg *reg);
+const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext(
+ struct kvm_vcpu *vcpu, unsigned long extid);
+bool riscv_vcpu_supports_sbi_ext(struct kvm_vcpu *vcpu, int idx);
+int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run);
+void kvm_riscv_vcpu_sbi_init(struct kvm_vcpu *vcpu);
+
+int kvm_riscv_vcpu_get_reg_sbi_sta(struct kvm_vcpu *vcpu, unsigned long reg_num,
+ unsigned long *reg_val);
+int kvm_riscv_vcpu_set_reg_sbi_sta(struct kvm_vcpu *vcpu, unsigned long reg_num,
+ unsigned long reg_val);
+
+#ifdef CONFIG_RISCV_SBI_V01
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01;
+#endif
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_base;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_time;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_ipi;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_srst;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_hsm;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_dbcn;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_susp;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_sta;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_experimental;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_vendor;
+#ifdef CONFIG_RISCV_PMU_SBI
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_pmu;
+#endif
#endif /* __RISCV_KVM_VCPU_SBI_H__ */
diff --git a/arch/riscv/include/asm/kvm_vcpu_timer.h b/arch/riscv/include/asm/kvm_vcpu_timer.h
index 375281eb49e0..82f7260301da 100644
--- a/arch/riscv/include/asm/kvm_vcpu_timer.h
+++ b/arch/riscv/include/asm/kvm_vcpu_timer.h
@@ -28,6 +28,11 @@ struct kvm_vcpu_timer {
u64 next_cycles;
/* Underlying hrtimer instance */
struct hrtimer hrt;
+
+ /* Flag to check if sstc is enabled or not */
+ bool sstc_enabled;
+ /* A function pointer to switch between stimecmp or hrtimer at runtime */
+ int (*timer_next_event)(struct kvm_vcpu *vcpu, u64 ncycles);
};
int kvm_riscv_vcpu_timer_next_event(struct kvm_vcpu *vcpu, u64 ncycles);
@@ -39,6 +44,9 @@ int kvm_riscv_vcpu_timer_init(struct kvm_vcpu *vcpu);
int kvm_riscv_vcpu_timer_deinit(struct kvm_vcpu *vcpu);
int kvm_riscv_vcpu_timer_reset(struct kvm_vcpu *vcpu);
void kvm_riscv_vcpu_timer_restore(struct kvm_vcpu *vcpu);
-int kvm_riscv_guest_timer_init(struct kvm *kvm);
+void kvm_riscv_guest_timer_init(struct kvm *kvm);
+void kvm_riscv_vcpu_timer_sync(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu);
+bool kvm_riscv_vcpu_timer_pending(struct kvm_vcpu *vcpu);
#endif
diff --git a/arch/riscv/include/asm/kvm_vcpu_vector.h b/arch/riscv/include/asm/kvm_vcpu_vector.h
new file mode 100644
index 000000000000..57a798a4cb0d
--- /dev/null
+++ b/arch/riscv/include/asm/kvm_vcpu_vector.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2022 SiFive
+ *
+ * Authors:
+ * Vincent Chen <vincent.chen@sifive.com>
+ * Greentime Hu <greentime.hu@sifive.com>
+ */
+
+#ifndef __KVM_VCPU_RISCV_VECTOR_H
+#define __KVM_VCPU_RISCV_VECTOR_H
+
+#include <linux/types.h>
+
+#ifdef CONFIG_RISCV_ISA_V
+#include <asm/vector.h>
+#include <asm/kvm_host.h>
+
+static __always_inline void __kvm_riscv_vector_save(struct kvm_cpu_context *context)
+{
+ __riscv_v_vstate_save(&context->vector, context->vector.datap);
+}
+
+static __always_inline void __kvm_riscv_vector_restore(struct kvm_cpu_context *context)
+{
+ __riscv_v_vstate_restore(&context->vector, context->vector.datap);
+}
+
+void kvm_riscv_vcpu_vector_reset(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_guest_vector_save(struct kvm_cpu_context *cntx,
+ unsigned long *isa);
+void kvm_riscv_vcpu_guest_vector_restore(struct kvm_cpu_context *cntx,
+ unsigned long *isa);
+void kvm_riscv_vcpu_host_vector_save(struct kvm_cpu_context *cntx);
+void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cntx);
+int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu);
+#else
+
+struct kvm_cpu_context;
+
+static inline void kvm_riscv_vcpu_vector_reset(struct kvm_vcpu *vcpu)
+{
+}
+
+static inline void kvm_riscv_vcpu_guest_vector_save(struct kvm_cpu_context *cntx,
+ unsigned long *isa)
+{
+}
+
+static inline void kvm_riscv_vcpu_guest_vector_restore(struct kvm_cpu_context *cntx,
+ unsigned long *isa)
+{
+}
+
+static inline void kvm_riscv_vcpu_host_vector_save(struct kvm_cpu_context *cntx)
+{
+}
+
+static inline void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cntx)
+{
+}
+
+static inline int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu)
+{
+ return 0;
+}
+
+static inline void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu)
+{
+}
+#endif
+
+int kvm_riscv_vcpu_get_reg_vector(struct kvm_vcpu *vcpu,
+ const struct kvm_one_reg *reg);
+int kvm_riscv_vcpu_set_reg_vector(struct kvm_vcpu *vcpu,
+ const struct kvm_one_reg *reg);
+#endif
diff --git a/arch/riscv/include/asm/membarrier.h b/arch/riscv/include/asm/membarrier.h
new file mode 100644
index 000000000000..47b240d0d596
--- /dev/null
+++ b/arch/riscv/include/asm/membarrier.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _ASM_RISCV_MEMBARRIER_H
+#define _ASM_RISCV_MEMBARRIER_H
+
+static inline void membarrier_arch_switch_mm(struct mm_struct *prev,
+ struct mm_struct *next,
+ struct task_struct *tsk)
+{
+ /*
+ * Only need the full barrier when switching between processes.
+ * Barrier when switching from kernel to userspace is not
+ * required here, given that it is implied by mmdrop(). Barrier
+ * when switching from userspace to kernel is not needed after
+ * store to rq->curr.
+ */
+ if (IS_ENABLED(CONFIG_SMP) &&
+ likely(!(atomic_read(&next->membarrier_state) &
+ (MEMBARRIER_STATE_PRIVATE_EXPEDITED |
+ MEMBARRIER_STATE_GLOBAL_EXPEDITED)) || !prev))
+ return;
+
+ /*
+ * The membarrier system call requires a full memory barrier
+ * after storing to rq->curr, before going back to user-space.
+ *
+ * This barrier is also needed for the SYNC_CORE command when
+ * switching between processes; in particular, on a transition
+ * from a thread belonging to another mm to a thread belonging
+ * to the mm for which a membarrier SYNC_CORE is done on CPU0:
+ *
+ * - [CPU0] sets all bits in the mm icache_stale_mask (in
+ * prepare_sync_core_cmd());
+ *
+ * - [CPU1] stores to rq->curr (by the scheduler);
+ *
+ * - [CPU0] loads rq->curr within membarrier and observes
+ * cpu_rq(1)->curr->mm != mm, so the IPI is skipped on
+ * CPU1; this means membarrier relies on switch_mm() to
+ * issue the sync-core;
+ *
+ * - [CPU1] switch_mm() loads icache_stale_mask; if the bit
+ * is zero, switch_mm() may incorrectly skip the sync-core.
+ *
+ * Matches a full barrier in the proximity of the membarrier
+ * system call entry.
+ */
+ smp_mb();
+}
+
+#endif /* _ASM_RISCV_MEMBARRIER_H */
diff --git a/arch/riscv/include/asm/mmio.h b/arch/riscv/include/asm/mmio.h
index aff6c33ab0c0..06cadfd7a237 100644
--- a/arch/riscv/include/asm/mmio.h
+++ b/arch/riscv/include/asm/mmio.h
@@ -12,6 +12,7 @@
#define _ASM_RISCV_MMIO_H
#include <linux/types.h>
+#include <asm/fence.h>
#include <asm/mmiowb.h>
/* Generic IO read/write. These perform native-endian accesses. */
@@ -101,9 +102,9 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
* Relaxed I/O memory access primitives. These follow the Device memory
* ordering rules but do not guarantee any ordering relative to Normal memory
* accesses. These are defined to order the indicated access (either a read or
- * write) with all other I/O memory accesses. Since the platform specification
- * defines that all I/O regions are strongly ordered on channel 2, no explicit
- * fences are required to enforce this ordering.
+ * write) with all other I/O memory accesses to the same peripheral. Since the
+ * platform specification defines that all I/O regions are strongly ordered on
+ * channel 0, no explicit fences are required to enforce this ordering.
*/
/* FIXME: These are now the same as asm-generic */
#define __io_rbr() do {} while (0)
@@ -125,14 +126,14 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
#endif
/*
- * I/O memory access primitives. Reads are ordered relative to any
- * following Normal memory access. Writes are ordered relative to any prior
- * Normal memory access. The memory barriers here are necessary as RISC-V
+ * I/O memory access primitives. Reads are ordered relative to any following
+ * Normal memory read and delay() loop. Writes are ordered relative to any
+ * prior Normal memory write. The memory barriers here are necessary as RISC-V
* doesn't define any ordering between the memory space and the I/O space.
*/
#define __io_br() do {} while (0)
-#define __io_ar(v) __asm__ __volatile__ ("fence i,r" : : : "memory")
-#define __io_bw() __asm__ __volatile__ ("fence w,o" : : : "memory")
+#define __io_ar(v) RISCV_FENCE(i, ir)
+#define __io_bw() RISCV_FENCE(w, o)
#define __io_aw() mmiowb_set_pending()
#define readb(c) ({ u8 __v; __io_br(); __v = readb_cpu(c); __io_ar(__v); __v; })
diff --git a/arch/riscv/include/asm/mmiowb.h b/arch/riscv/include/asm/mmiowb.h
index 0b2333e71fdc..52ce4a399d9b 100644
--- a/arch/riscv/include/asm/mmiowb.h
+++ b/arch/riscv/include/asm/mmiowb.h
@@ -7,7 +7,7 @@
* "o,w" is sufficient to ensure that all writes to the device have completed
* before the write to the spinlock is allowed to commit.
*/
-#define mmiowb() __asm__ __volatile__ ("fence o,w" : : : "memory");
+#define mmiowb() RISCV_FENCE(o, w)
#include <linux/smp.h>
#include <asm-generic/mmiowb.h>
diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
index cedcf8ea3c76..1cc90465d75b 100644
--- a/arch/riscv/include/asm/mmu.h
+++ b/arch/riscv/include/asm/mmu.h
@@ -16,15 +16,30 @@ typedef struct {
atomic_long_t id;
#endif
void *vdso;
- void *vdso_info;
#ifdef CONFIG_SMP
/* A local icache flush is needed before user execution can resume. */
cpumask_t icache_stale_mask;
+ /* Force local icache flush on all migrations. */
+ bool force_icache_flush;
+#endif
+#ifdef CONFIG_BINFMT_ELF_FDPIC
+ unsigned long exec_fdpic_loadmap;
+ unsigned long interp_fdpic_loadmap;
+#endif
+ unsigned long flags;
+#ifdef CONFIG_RISCV_ISA_SUPM
+ u8 pmlen;
#endif
} mm_context_t;
-void __init create_pgd_mapping(pgd_t *pgdp, uintptr_t va, phys_addr_t pa,
- phys_addr_t sz, pgprot_t prot);
+/* Lock the pointer masking mode because this mm is multithreaded */
+#define MM_CONTEXT_LOCK_PMLEN 0
+
+#define cntx2asid(cntx) ((cntx) & SATP_ASID_MASK)
+#define cntx2version(cntx) ((cntx) & ~SATP_ASID_MASK)
+
+void __meminit create_pgd_mapping(pgd_t *pgdp, uintptr_t va, phys_addr_t pa, phys_addr_t sz,
+ pgprot_t prot);
#endif /* __ASSEMBLY__ */
#endif /* _ASM_RISCV_MMU_H */
diff --git a/arch/riscv/include/asm/mmu_context.h b/arch/riscv/include/asm/mmu_context.h
index 7030837adc1a..8c4bc49a3a0f 100644
--- a/arch/riscv/include/asm/mmu_context.h
+++ b/arch/riscv/include/asm/mmu_context.h
@@ -20,6 +20,9 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
static inline void activate_mm(struct mm_struct *prev,
struct mm_struct *next)
{
+#ifdef CONFIG_RISCV_ISA_SUPM
+ next->context.pmlen = 0;
+#endif
switch_mm(prev, next, NULL);
}
@@ -30,11 +33,21 @@ static inline int init_new_context(struct task_struct *tsk,
#ifdef CONFIG_MMU
atomic_long_set(&mm->context.id, 0);
#endif
+ if (IS_ENABLED(CONFIG_RISCV_ISA_SUPM))
+ clear_bit(MM_CONTEXT_LOCK_PMLEN, &mm->context.flags);
return 0;
}
DECLARE_STATIC_KEY_FALSE(use_asid_allocator);
+#ifdef CONFIG_RISCV_ISA_SUPM
+#define mm_untag_mask mm_untag_mask
+static inline unsigned long mm_untag_mask(struct mm_struct *mm)
+{
+ return -1UL >> mm->context.pmlen;
+}
+#endif
+
#include <asm-generic/mmu_context.h>
#endif /* _ASM_RISCV_MMU_CONTEXT_H */
diff --git a/arch/riscv/include/asm/mmzone.h b/arch/riscv/include/asm/mmzone.h
deleted file mode 100644
index fa17e01d9ab2..000000000000
--- a/arch/riscv/include/asm/mmzone.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ASM_MMZONE_H
-#define __ASM_MMZONE_H
-
-#ifdef CONFIG_NUMA
-
-#include <asm/numa.h>
-
-extern struct pglist_data *node_data[];
-#define NODE_DATA(nid) (node_data[(nid)])
-
-#endif /* CONFIG_NUMA */
-#endif /* __ASM_MMZONE_H */
diff --git a/arch/riscv/include/asm/module.h b/arch/riscv/include/asm/module.h
index 76aa96a9fc08..0f3baaa6a9a8 100644
--- a/arch/riscv/include/asm/module.h
+++ b/arch/riscv/include/asm/module.h
@@ -5,6 +5,7 @@
#define _ASM_RISCV_MODULE_H
#include <asm-generic/module.h>
+#include <linux/elf.h>
struct module;
unsigned long module_emit_got_entry(struct module *mod, unsigned long val);
@@ -111,4 +112,19 @@ static inline struct plt_entry *get_plt_entry(unsigned long val,
#endif /* CONFIG_MODULE_SECTIONS */
+static inline const Elf_Shdr *find_section(const Elf_Ehdr *hdr,
+ const Elf_Shdr *sechdrs,
+ const char *name)
+{
+ const Elf_Shdr *s, *se;
+ const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+
+ for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) {
+ if (strcmp(name, secstrs + s->sh_name) == 0)
+ return s;
+ }
+
+ return NULL;
+}
+
#endif /* _ASM_RISCV_MODULE_H */
diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h
index 1526e410e802..572a141ddecd 100644
--- a/arch/riscv/include/asm/page.h
+++ b/arch/riscv/include/asm/page.h
@@ -12,15 +12,8 @@
#include <linux/pfn.h>
#include <linux/const.h>
-#define PAGE_SHIFT (12)
-#define PAGE_SIZE (_AC(1, UL) << PAGE_SHIFT)
-#define PAGE_MASK (~(PAGE_SIZE - 1))
+#include <vdso/page.h>
-#ifdef CONFIG_64BIT
-#define HUGE_MAX_HSTATE 2
-#else
-#define HUGE_MAX_HSTATE 1
-#endif
#define HPAGE_SHIFT PMD_SHIFT
#define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT)
#define HPAGE_MASK (~(HPAGE_SIZE - 1))
@@ -31,28 +24,33 @@
* When not using MMU this corresponds to the first free page in
* physical memory (aligned on a page boundary).
*/
-#ifdef CONFIG_64BIT
#ifdef CONFIG_MMU
-#define PAGE_OFFSET kernel_map.page_offset
-#else
-#define PAGE_OFFSET _AC(CONFIG_PAGE_OFFSET, UL)
-#endif
-/*
- * By default, CONFIG_PAGE_OFFSET value corresponds to SV48 address space so
- * define the PAGE_OFFSET value for SV39.
- */
+#ifdef CONFIG_64BIT
+#define PAGE_OFFSET_L5 _AC(0xff60000000000000, UL)
#define PAGE_OFFSET_L4 _AC(0xffffaf8000000000, UL)
-#define PAGE_OFFSET_L3 _AC(0xffffffd800000000, UL)
+#define PAGE_OFFSET_L3 _AC(0xffffffd600000000, UL)
+#ifdef CONFIG_XIP_KERNEL
+#define PAGE_OFFSET PAGE_OFFSET_L3
#else
-#define PAGE_OFFSET _AC(CONFIG_PAGE_OFFSET, UL)
+#define PAGE_OFFSET kernel_map.page_offset
+#endif /* CONFIG_XIP_KERNEL */
+#else
+#define PAGE_OFFSET _AC(0xc0000000, UL)
#endif /* CONFIG_64BIT */
+#else
+#define PAGE_OFFSET ((unsigned long)phys_ram_base)
+#endif /* CONFIG_MMU */
#ifndef __ASSEMBLY__
+#ifdef CONFIG_RISCV_ISA_ZICBOZ
+void clear_page(void *page);
+#else
#define clear_page(pgaddr) memset((pgaddr), 0, PAGE_SIZE)
+#endif
#define copy_page(to, from) memcpy((to), (from), PAGE_SIZE)
-#define clear_user_page(pgaddr, vaddr, page) memset((pgaddr), 0, PAGE_SIZE)
+#define clear_user_page(pgaddr, vaddr, page) clear_page(pgaddr)
#define copy_user_page(vto, vfrom, vaddr, topg) \
memcpy((vto), (vfrom), PAGE_SIZE)
@@ -90,31 +88,38 @@ typedef struct page *pgtable_t;
#define PTE_FMT "%08lx"
#endif
-#ifdef CONFIG_MMU
-extern unsigned long riscv_pfn_base;
-#define ARCH_PFN_OFFSET (riscv_pfn_base)
-#else
-#define ARCH_PFN_OFFSET (PAGE_OFFSET >> PAGE_SHIFT)
-#endif /* CONFIG_MMU */
+#if defined(CONFIG_64BIT) && defined(CONFIG_MMU)
+/*
+ * We override this value as its generic definition uses __pa too early in
+ * the boot process (before kernel_map.va_pa_offset is set).
+ */
+#define MIN_MEMBLOCK_ADDR 0
+#endif
+
+#define ARCH_PFN_OFFSET (PFN_DOWN((unsigned long)phys_ram_base))
struct kernel_mapping {
- unsigned long page_offset;
unsigned long virt_addr;
+ unsigned long virt_offset;
uintptr_t phys_addr;
uintptr_t size;
/* Offset between linear mapping virtual address and kernel load address */
unsigned long va_pa_offset;
/* Offset between kernel mapping virtual address and kernel load address */
- unsigned long va_kernel_pa_offset;
- unsigned long va_kernel_xip_pa_offset;
#ifdef CONFIG_XIP_KERNEL
+ unsigned long va_kernel_xip_text_pa_offset;
+ unsigned long va_kernel_xip_data_pa_offset;
uintptr_t xiprom;
uintptr_t xiprom_sz;
+#else
+ unsigned long page_offset;
+ unsigned long va_kernel_pa_offset;
#endif
};
extern struct kernel_mapping kernel_map;
extern phys_addr_t phys_ram_base;
+extern unsigned long vmemmap_start_pfn;
#define is_kernel_mapping(x) \
((x) >= kernel_map.virt_addr && (x) < (kernel_map.virt_addr + kernel_map.size))
@@ -122,22 +127,41 @@ extern phys_addr_t phys_ram_base;
#define is_linear_mapping(x) \
((x) >= PAGE_OFFSET && (!IS_ENABLED(CONFIG_64BIT) || (x) < PAGE_OFFSET + KERN_VIRT_SIZE))
+#ifndef CONFIG_DEBUG_VIRTUAL
#define linear_mapping_pa_to_va(x) ((void *)((unsigned long)(x) + kernel_map.va_pa_offset))
-#define kernel_mapping_pa_to_va(y) ({ \
- unsigned long _y = y; \
- (IS_ENABLED(CONFIG_XIP_KERNEL) && _y < phys_ram_base) ? \
- (void *)((unsigned long)(_y) + kernel_map.va_kernel_xip_pa_offset) : \
- (void *)((unsigned long)(_y) + kernel_map.va_kernel_pa_offset + XIP_OFFSET); \
+#else
+void *linear_mapping_pa_to_va(unsigned long x);
+#endif
+
+#ifdef CONFIG_XIP_KERNEL
+#define kernel_mapping_pa_to_va(y) ({ \
+ unsigned long _y = (unsigned long)(y); \
+ (_y < phys_ram_base) ? \
+ (void *)(_y + kernel_map.va_kernel_xip_text_pa_offset) : \
+ (void *)(_y + kernel_map.va_kernel_xip_data_pa_offset); \
})
+#else
+#define kernel_mapping_pa_to_va(y) ((void *)((unsigned long)(y) + kernel_map.va_kernel_pa_offset))
+#endif
+
#define __pa_to_va_nodebug(x) linear_mapping_pa_to_va(x)
+#ifndef CONFIG_DEBUG_VIRTUAL
#define linear_mapping_va_to_pa(x) ((unsigned long)(x) - kernel_map.va_pa_offset)
+#else
+phys_addr_t linear_mapping_va_to_pa(unsigned long x);
+#endif
+
+#ifdef CONFIG_XIP_KERNEL
#define kernel_mapping_va_to_pa(y) ({ \
- unsigned long _y = y; \
- (IS_ENABLED(CONFIG_XIP_KERNEL) && _y < kernel_map.virt_addr + XIP_OFFSET) ? \
- ((unsigned long)(_y) - kernel_map.va_kernel_xip_pa_offset) : \
- ((unsigned long)(_y) - kernel_map.va_kernel_pa_offset - XIP_OFFSET); \
+ unsigned long _y = (unsigned long)(y); \
+ (_y < kernel_map.virt_addr + kernel_map.xiprom_sz) ? \
+ (_y - kernel_map.va_kernel_xip_text_pa_offset) : \
+ (_y - kernel_map.va_kernel_xip_data_pa_offset); \
})
+#else
+#define kernel_mapping_va_to_pa(y) ((unsigned long)(y) - kernel_map.va_kernel_pa_offset)
+#endif
#define __va_to_pa_nodebug(x) ({ \
unsigned long _x = x; \
@@ -166,16 +190,14 @@ extern phys_addr_t __phys_addr_symbol(unsigned long x);
#define virt_to_page(vaddr) (pfn_to_page(virt_to_pfn(vaddr)))
#define page_to_virt(page) (pfn_to_virt(page_to_pfn(page)))
-#define page_to_phys(page) (pfn_to_phys(page_to_pfn(page)))
-#define page_to_bus(page) (page_to_phys(page))
-#define phys_to_page(paddr) (pfn_to_page(phys_to_pfn(paddr)))
-
#define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x))
-#ifdef CONFIG_FLATMEM
-#define pfn_valid(pfn) \
- (((pfn) >= ARCH_PFN_OFFSET) && (((pfn) - ARCH_PFN_OFFSET) < max_mapnr))
-#endif
+unsigned long kaslr_offset(void);
+
+static __always_inline void *pfn_to_kaddr(unsigned long pfn)
+{
+ return __va(pfn << PAGE_SHIFT);
+}
#endif /* __ASSEMBLY__ */
diff --git a/arch/riscv/include/asm/paravirt.h b/arch/riscv/include/asm/paravirt.h
new file mode 100644
index 000000000000..c0abde70fc2c
--- /dev/null
+++ b/arch/riscv/include/asm/paravirt.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_PARAVIRT_H
+#define _ASM_RISCV_PARAVIRT_H
+
+#ifdef CONFIG_PARAVIRT
+#include <linux/static_call_types.h>
+
+struct static_key;
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
+
+u64 dummy_steal_clock(int cpu);
+
+DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
+
+static inline u64 paravirt_steal_clock(int cpu)
+{
+ return static_call(pv_steal_clock)(cpu);
+}
+
+int __init pv_time_init(void);
+
+#else
+
+#define pv_time_init() do {} while (0)
+
+#endif /* CONFIG_PARAVIRT */
+#endif /* _ASM_RISCV_PARAVIRT_H */
diff --git a/arch/riscv/include/asm/paravirt_api_clock.h b/arch/riscv/include/asm/paravirt_api_clock.h
new file mode 100644
index 000000000000..65ac7cee0dad
--- /dev/null
+++ b/arch/riscv/include/asm/paravirt_api_clock.h
@@ -0,0 +1 @@
+#include <asm/paravirt.h>
diff --git a/arch/riscv/include/asm/parse_asm.h b/arch/riscv/include/asm/parse_asm.h
deleted file mode 100644
index f36368de839f..000000000000
--- a/arch/riscv/include/asm/parse_asm.h
+++ /dev/null
@@ -1,219 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2020 SiFive
- */
-
-#include <linux/bits.h>
-
-/* The bit field of immediate value in I-type instruction */
-#define I_IMM_SIGN_OPOFF 31
-#define I_IMM_11_0_OPOFF 20
-#define I_IMM_SIGN_OFF 12
-#define I_IMM_11_0_OFF 0
-#define I_IMM_11_0_MASK GENMASK(11, 0)
-
-/* The bit field of immediate value in J-type instruction */
-#define J_IMM_SIGN_OPOFF 31
-#define J_IMM_10_1_OPOFF 21
-#define J_IMM_11_OPOFF 20
-#define J_IMM_19_12_OPOFF 12
-#define J_IMM_SIGN_OFF 20
-#define J_IMM_10_1_OFF 1
-#define J_IMM_11_OFF 11
-#define J_IMM_19_12_OFF 12
-#define J_IMM_10_1_MASK GENMASK(9, 0)
-#define J_IMM_11_MASK GENMASK(0, 0)
-#define J_IMM_19_12_MASK GENMASK(7, 0)
-
-/* The bit field of immediate value in B-type instruction */
-#define B_IMM_SIGN_OPOFF 31
-#define B_IMM_10_5_OPOFF 25
-#define B_IMM_4_1_OPOFF 8
-#define B_IMM_11_OPOFF 7
-#define B_IMM_SIGN_OFF 12
-#define B_IMM_10_5_OFF 5
-#define B_IMM_4_1_OFF 1
-#define B_IMM_11_OFF 11
-#define B_IMM_10_5_MASK GENMASK(5, 0)
-#define B_IMM_4_1_MASK GENMASK(3, 0)
-#define B_IMM_11_MASK GENMASK(0, 0)
-
-/* The register offset in RVG instruction */
-#define RVG_RS1_OPOFF 15
-#define RVG_RS2_OPOFF 20
-#define RVG_RD_OPOFF 7
-
-/* The bit field of immediate value in RVC J instruction */
-#define RVC_J_IMM_SIGN_OPOFF 12
-#define RVC_J_IMM_4_OPOFF 11
-#define RVC_J_IMM_9_8_OPOFF 9
-#define RVC_J_IMM_10_OPOFF 8
-#define RVC_J_IMM_6_OPOFF 7
-#define RVC_J_IMM_7_OPOFF 6
-#define RVC_J_IMM_3_1_OPOFF 3
-#define RVC_J_IMM_5_OPOFF 2
-#define RVC_J_IMM_SIGN_OFF 11
-#define RVC_J_IMM_4_OFF 4
-#define RVC_J_IMM_9_8_OFF 8
-#define RVC_J_IMM_10_OFF 10
-#define RVC_J_IMM_6_OFF 6
-#define RVC_J_IMM_7_OFF 7
-#define RVC_J_IMM_3_1_OFF 1
-#define RVC_J_IMM_5_OFF 5
-#define RVC_J_IMM_4_MASK GENMASK(0, 0)
-#define RVC_J_IMM_9_8_MASK GENMASK(1, 0)
-#define RVC_J_IMM_10_MASK GENMASK(0, 0)
-#define RVC_J_IMM_6_MASK GENMASK(0, 0)
-#define RVC_J_IMM_7_MASK GENMASK(0, 0)
-#define RVC_J_IMM_3_1_MASK GENMASK(2, 0)
-#define RVC_J_IMM_5_MASK GENMASK(0, 0)
-
-/* The bit field of immediate value in RVC B instruction */
-#define RVC_B_IMM_SIGN_OPOFF 12
-#define RVC_B_IMM_4_3_OPOFF 10
-#define RVC_B_IMM_7_6_OPOFF 5
-#define RVC_B_IMM_2_1_OPOFF 3
-#define RVC_B_IMM_5_OPOFF 2
-#define RVC_B_IMM_SIGN_OFF 8
-#define RVC_B_IMM_4_3_OFF 3
-#define RVC_B_IMM_7_6_OFF 6
-#define RVC_B_IMM_2_1_OFF 1
-#define RVC_B_IMM_5_OFF 5
-#define RVC_B_IMM_4_3_MASK GENMASK(1, 0)
-#define RVC_B_IMM_7_6_MASK GENMASK(1, 0)
-#define RVC_B_IMM_2_1_MASK GENMASK(1, 0)
-#define RVC_B_IMM_5_MASK GENMASK(0, 0)
-
-/* The register offset in RVC op=C0 instruction */
-#define RVC_C0_RS1_OPOFF 7
-#define RVC_C0_RS2_OPOFF 2
-#define RVC_C0_RD_OPOFF 2
-
-/* The register offset in RVC op=C1 instruction */
-#define RVC_C1_RS1_OPOFF 7
-#define RVC_C1_RS2_OPOFF 2
-#define RVC_C1_RD_OPOFF 7
-
-/* The register offset in RVC op=C2 instruction */
-#define RVC_C2_RS1_OPOFF 7
-#define RVC_C2_RS2_OPOFF 2
-#define RVC_C2_RD_OPOFF 7
-
-/* parts of opcode for RVG*/
-#define OPCODE_BRANCH 0x63
-#define OPCODE_JALR 0x67
-#define OPCODE_JAL 0x6f
-#define OPCODE_SYSTEM 0x73
-
-/* parts of opcode for RVC*/
-#define OPCODE_C_0 0x0
-#define OPCODE_C_1 0x1
-#define OPCODE_C_2 0x2
-
-/* parts of funct3 code for I, M, A extension*/
-#define FUNCT3_JALR 0x0
-#define FUNCT3_BEQ 0x0
-#define FUNCT3_BNE 0x1000
-#define FUNCT3_BLT 0x4000
-#define FUNCT3_BGE 0x5000
-#define FUNCT3_BLTU 0x6000
-#define FUNCT3_BGEU 0x7000
-
-/* parts of funct3 code for C extension*/
-#define FUNCT3_C_BEQZ 0xc000
-#define FUNCT3_C_BNEZ 0xe000
-#define FUNCT3_C_J 0xa000
-#define FUNCT3_C_JAL 0x2000
-#define FUNCT4_C_JR 0x8000
-#define FUNCT4_C_JALR 0xf000
-
-#define FUNCT12_SRET 0x10200000
-
-#define MATCH_JALR (FUNCT3_JALR | OPCODE_JALR)
-#define MATCH_JAL (OPCODE_JAL)
-#define MATCH_BEQ (FUNCT3_BEQ | OPCODE_BRANCH)
-#define MATCH_BNE (FUNCT3_BNE | OPCODE_BRANCH)
-#define MATCH_BLT (FUNCT3_BLT | OPCODE_BRANCH)
-#define MATCH_BGE (FUNCT3_BGE | OPCODE_BRANCH)
-#define MATCH_BLTU (FUNCT3_BLTU | OPCODE_BRANCH)
-#define MATCH_BGEU (FUNCT3_BGEU | OPCODE_BRANCH)
-#define MATCH_SRET (FUNCT12_SRET | OPCODE_SYSTEM)
-#define MATCH_C_BEQZ (FUNCT3_C_BEQZ | OPCODE_C_1)
-#define MATCH_C_BNEZ (FUNCT3_C_BNEZ | OPCODE_C_1)
-#define MATCH_C_J (FUNCT3_C_J | OPCODE_C_1)
-#define MATCH_C_JAL (FUNCT3_C_JAL | OPCODE_C_1)
-#define MATCH_C_JR (FUNCT4_C_JR | OPCODE_C_2)
-#define MATCH_C_JALR (FUNCT4_C_JALR | OPCODE_C_2)
-
-#define MASK_JALR 0x707f
-#define MASK_JAL 0x7f
-#define MASK_C_JALR 0xf07f
-#define MASK_C_JR 0xf07f
-#define MASK_C_JAL 0xe003
-#define MASK_C_J 0xe003
-#define MASK_BEQ 0x707f
-#define MASK_BNE 0x707f
-#define MASK_BLT 0x707f
-#define MASK_BGE 0x707f
-#define MASK_BLTU 0x707f
-#define MASK_BGEU 0x707f
-#define MASK_C_BEQZ 0xe003
-#define MASK_C_BNEZ 0xe003
-#define MASK_SRET 0xffffffff
-
-#define __INSN_LENGTH_MASK _UL(0x3)
-#define __INSN_LENGTH_GE_32 _UL(0x3)
-#define __INSN_OPCODE_MASK _UL(0x7F)
-#define __INSN_BRANCH_OPCODE _UL(OPCODE_BRANCH)
-
-/* Define a series of is_XXX_insn functions to check if the value INSN
- * is an instance of instruction XXX.
- */
-#define DECLARE_INSN(INSN_NAME, INSN_MATCH, INSN_MASK) \
-static inline bool is_ ## INSN_NAME ## _insn(long insn) \
-{ \
- return (insn & (INSN_MASK)) == (INSN_MATCH); \
-}
-
-#define RV_IMM_SIGN(x) (-(((x) >> 31) & 1))
-#define RVC_IMM_SIGN(x) (-(((x) >> 12) & 1))
-#define RV_X(X, s, mask) (((X) >> (s)) & (mask))
-#define RVC_X(X, s, mask) RV_X(X, s, mask)
-
-#define EXTRACT_JTYPE_IMM(x) \
- ({typeof(x) x_ = (x); \
- (RV_X(x_, J_IMM_10_1_OPOFF, J_IMM_10_1_MASK) << J_IMM_10_1_OFF) | \
- (RV_X(x_, J_IMM_11_OPOFF, J_IMM_11_MASK) << J_IMM_11_OFF) | \
- (RV_X(x_, J_IMM_19_12_OPOFF, J_IMM_19_12_MASK) << J_IMM_19_12_OFF) | \
- (RV_IMM_SIGN(x_) << J_IMM_SIGN_OFF); })
-
-#define EXTRACT_ITYPE_IMM(x) \
- ({typeof(x) x_ = (x); \
- (RV_X(x_, I_IMM_11_0_OPOFF, I_IMM_11_0_MASK)) | \
- (RV_IMM_SIGN(x_) << I_IMM_SIGN_OFF); })
-
-#define EXTRACT_BTYPE_IMM(x) \
- ({typeof(x) x_ = (x); \
- (RV_X(x_, B_IMM_4_1_OPOFF, B_IMM_4_1_MASK) << B_IMM_4_1_OFF) | \
- (RV_X(x_, B_IMM_10_5_OPOFF, B_IMM_10_5_MASK) << B_IMM_10_5_OFF) | \
- (RV_X(x_, B_IMM_11_OPOFF, B_IMM_11_MASK) << B_IMM_11_OFF) | \
- (RV_IMM_SIGN(x_) << B_IMM_SIGN_OFF); })
-
-#define EXTRACT_RVC_J_IMM(x) \
- ({typeof(x) x_ = (x); \
- (RVC_X(x_, RVC_J_IMM_3_1_OPOFF, RVC_J_IMM_3_1_MASK) << RVC_J_IMM_3_1_OFF) | \
- (RVC_X(x_, RVC_J_IMM_4_OPOFF, RVC_J_IMM_4_MASK) << RVC_J_IMM_4_OFF) | \
- (RVC_X(x_, RVC_J_IMM_5_OPOFF, RVC_J_IMM_5_MASK) << RVC_J_IMM_5_OFF) | \
- (RVC_X(x_, RVC_J_IMM_6_OPOFF, RVC_J_IMM_6_MASK) << RVC_J_IMM_6_OFF) | \
- (RVC_X(x_, RVC_J_IMM_7_OPOFF, RVC_J_IMM_7_MASK) << RVC_J_IMM_7_OFF) | \
- (RVC_X(x_, RVC_J_IMM_9_8_OPOFF, RVC_J_IMM_9_8_MASK) << RVC_J_IMM_9_8_OFF) | \
- (RVC_X(x_, RVC_J_IMM_10_OPOFF, RVC_J_IMM_10_MASK) << RVC_J_IMM_10_OFF) | \
- (RVC_IMM_SIGN(x_) << RVC_J_IMM_SIGN_OFF); })
-
-#define EXTRACT_RVC_B_IMM(x) \
- ({typeof(x) x_ = (x); \
- (RVC_X(x_, RVC_B_IMM_2_1_OPOFF, RVC_B_IMM_2_1_MASK) << RVC_B_IMM_2_1_OFF) | \
- (RVC_X(x_, RVC_B_IMM_4_3_OPOFF, RVC_B_IMM_4_3_MASK) << RVC_B_IMM_4_3_OFF) | \
- (RVC_X(x_, RVC_B_IMM_5_OPOFF, RVC_B_IMM_5_MASK) << RVC_B_IMM_5_OFF) | \
- (RVC_X(x_, RVC_B_IMM_7_6_OPOFF, RVC_B_IMM_7_6_MASK) << RVC_B_IMM_7_6_OFF) | \
- (RVC_IMM_SIGN(x_) << RVC_B_IMM_SIGN_OFF); })
diff --git a/arch/riscv/include/asm/pci.h b/arch/riscv/include/asm/pci.h
index 7fd52a30e605..cc2a184cfc2e 100644
--- a/arch/riscv/include/asm/pci.h
+++ b/arch/riscv/include/asm/pci.h
@@ -12,31 +12,10 @@
#include <asm/io.h>
-#define PCIBIOS_MIN_IO 0
-#define PCIBIOS_MIN_MEM 0
-
-/* RISC-V shim does not initialize PCI bus */
-#define pcibios_assign_all_busses() 1
-
-#define ARCH_GENERIC_PCI_MMAP_RESOURCE 1
-
-extern int isa_dma_bridge_buggy;
-
-#ifdef CONFIG_PCI
-static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
-{
- /* no legacy IRQ on risc-v */
- return -ENODEV;
-}
-
-static inline int pci_proc_domain(struct pci_bus *bus)
-{
- /* always show the domain in /proc */
- return 1;
-}
-
-#ifdef CONFIG_NUMA
+#define PCIBIOS_MIN_IO 4
+#define PCIBIOS_MIN_MEM 16
+#if defined(CONFIG_PCI) && defined(CONFIG_NUMA)
static inline int pcibus_to_node(struct pci_bus *bus)
{
return dev_to_node(&bus->dev);
@@ -46,8 +25,9 @@ static inline int pcibus_to_node(struct pci_bus *bus)
cpu_all_mask : \
cpumask_of_node(pcibus_to_node(bus)))
#endif
-#endif /* CONFIG_NUMA */
+#endif /* defined(CONFIG_PCI) && defined(CONFIG_NUMA) */
-#endif /* CONFIG_PCI */
+/* Generic PCI */
+#include <asm-generic/pci.h>
#endif /* _ASM_RISCV_PCI_H */
diff --git a/arch/riscv/include/asm/perf_event.h b/arch/riscv/include/asm/perf_event.h
index d42c901f9a97..bcc928fd3785 100644
--- a/arch/riscv/include/asm/perf_event.h
+++ b/arch/riscv/include/asm/perf_event.h
@@ -8,6 +8,16 @@
#ifndef _ASM_RISCV_PERF_EVENT_H
#define _ASM_RISCV_PERF_EVENT_H
+#ifdef CONFIG_PERF_EVENTS
#include <linux/perf_event.h>
#define perf_arch_bpf_user_pt_regs(regs) (struct user_regs_struct *)regs
+
+#define perf_arch_fetch_caller_regs(regs, __ip) { \
+ (regs)->epc = (__ip); \
+ (regs)->s0 = (unsigned long) __builtin_frame_address(0); \
+ (regs)->sp = current_stack_pointer; \
+ (regs)->status = SR_PP; \
+}
+#endif
+
#endif /* _ASM_RISCV_PERF_EVENT_H */
diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h
index 947f23d7b6af..770ce18a7328 100644
--- a/arch/riscv/include/asm/pgalloc.h
+++ b/arch/riscv/include/asm/pgalloc.h
@@ -8,10 +8,10 @@
#define _ASM_RISCV_PGALLOC_H
#include <linux/mm.h>
+#include <asm/sbi.h>
#include <asm/tlb.h>
#ifdef CONFIG_MMU
-#define __HAVE_ARCH_PUD_ALLOC_ONE
#define __HAVE_ARCH_PUD_FREE
#include <asm-generic/pgalloc.h>
@@ -79,15 +79,6 @@ static inline void pgd_populate_safe(struct mm_struct *mm, pgd_t *pgd,
}
}
-#define pud_alloc_one pud_alloc_one
-static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
-{
- if (pgtable_l4_enabled)
- return __pud_alloc_one(mm, addr);
-
- return NULL;
-}
-
#define pud_free pud_free
static inline void pud_free(struct mm_struct *mm, pud_t *pud)
{
@@ -95,64 +86,55 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud)
__pud_free(mm, pud);
}
-#define __pud_free_tlb(tlb, pud, addr) pud_free((tlb)->mm, pud)
-
-#define p4d_alloc_one p4d_alloc_one
-static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr)
+static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
+ unsigned long addr)
{
- if (pgtable_l5_enabled) {
- gfp_t gfp = GFP_PGTABLE_USER;
-
- if (mm == &init_mm)
- gfp = GFP_PGTABLE_KERNEL;
- return (p4d_t *)get_zeroed_page(gfp);
- }
-
- return NULL;
+ if (pgtable_l4_enabled)
+ tlb_remove_ptdesc(tlb, virt_to_ptdesc(pud));
}
-static inline void __p4d_free(struct mm_struct *mm, p4d_t *p4d)
+static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
+ unsigned long addr)
{
- BUG_ON((unsigned long)p4d & (PAGE_SIZE-1));
- free_page((unsigned long)p4d);
+ if (pgtable_l5_enabled)
+ tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d));
}
+#endif /* __PAGETABLE_PMD_FOLDED */
-#define p4d_free p4d_free
-static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
+static inline void sync_kernel_mappings(pgd_t *pgd)
{
- if (pgtable_l5_enabled)
- __p4d_free(mm, p4d);
+ memcpy(pgd + USER_PTRS_PER_PGD,
+ init_mm.pgd + USER_PTRS_PER_PGD,
+ (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
}
-#define __p4d_free_tlb(tlb, p4d, addr) p4d_free((tlb)->mm, p4d)
-#endif /* __PAGETABLE_PMD_FOLDED */
-
static inline pgd_t *pgd_alloc(struct mm_struct *mm)
{
pgd_t *pgd;
- pgd = (pgd_t *)__get_free_page(GFP_KERNEL);
+ pgd = __pgd_alloc(mm, 0);
if (likely(pgd != NULL)) {
- memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
/* Copy kernel mappings */
- memcpy(pgd + USER_PTRS_PER_PGD,
- init_mm.pgd + USER_PTRS_PER_PGD,
- (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
+ sync_kernel_mappings(pgd);
}
return pgd;
}
#ifndef __PAGETABLE_PMD_FOLDED
-#define __pmd_free_tlb(tlb, pmd, addr) pmd_free((tlb)->mm, pmd)
+static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
+ unsigned long addr)
+{
+ tlb_remove_ptdesc(tlb, virt_to_ptdesc(pmd));
+}
#endif /* __PAGETABLE_PMD_FOLDED */
-#define __pte_free_tlb(tlb, pte, buf) \
-do { \
- pgtable_pte_page_dtor(pte); \
- tlb_remove_page((tlb), pte); \
-} while (0)
+static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
+ unsigned long addr)
+{
+ tlb_remove_ptdesc(tlb, page_ptdesc(pte));
+}
#endif /* CONFIG_MMU */
#endif /* _ASM_RISCV_PGALLOC_H */
diff --git a/arch/riscv/include/asm/pgtable-32.h b/arch/riscv/include/asm/pgtable-32.h
index 59ba1fbaf784..00f3369570a8 100644
--- a/arch/riscv/include/asm/pgtable-32.h
+++ b/arch/riscv/include/asm/pgtable-32.h
@@ -33,4 +33,7 @@
_PAGE_WRITE | _PAGE_EXEC | \
_PAGE_USER | _PAGE_GLOBAL))
+static const __maybe_unused int pgtable_l4_enabled;
+static const __maybe_unused int pgtable_l5_enabled;
+
#endif /* _ASM_RISCV_PGTABLE_32_H */
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
index dc42375c2357..7de05db7d3bd 100644
--- a/arch/riscv/include/asm/pgtable-64.h
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -16,8 +16,6 @@ extern bool pgtable_l5_enabled;
#define PGDIR_SHIFT_L3 30
#define PGDIR_SHIFT_L4 39
#define PGDIR_SHIFT_L5 48
-#define PGDIR_SIZE_L3 (_AC(1, UL) << PGDIR_SHIFT_L3)
-
#define PGDIR_SHIFT (pgtable_l5_enabled ? PGDIR_SHIFT_L5 : \
(pgtable_l4_enabled ? PGDIR_SHIFT_L4 : PGDIR_SHIFT_L3))
/* Size of region mapped by a page global directory */
@@ -25,7 +23,11 @@ extern bool pgtable_l5_enabled;
#define PGDIR_MASK (~(PGDIR_SIZE - 1))
/* p4d is folded into pgd in case of 4-level page table */
-#define P4D_SHIFT 39
+#define P4D_SHIFT_L3 30
+#define P4D_SHIFT_L4 39
+#define P4D_SHIFT_L5 39
+#define P4D_SHIFT (pgtable_l5_enabled ? P4D_SHIFT_L5 : \
+ (pgtable_l4_enabled ? P4D_SHIFT_L4 : P4D_SHIFT_L3))
#define P4D_SIZE (_AC(1, UL) << P4D_SHIFT)
#define P4D_MASK (~(P4D_SIZE - 1))
@@ -75,6 +77,40 @@ typedef struct {
#define _PAGE_PFN_MASK GENMASK(53, 10)
/*
+ * [63] Svnapot definitions:
+ * 0 Svnapot disabled
+ * 1 Svnapot enabled
+ */
+#define _PAGE_NAPOT_SHIFT 63
+#define _PAGE_NAPOT BIT(_PAGE_NAPOT_SHIFT)
+/*
+ * Only 64KB (order 4) napot ptes supported.
+ */
+#define NAPOT_CONT_ORDER_BASE 4
+enum napot_cont_order {
+ NAPOT_CONT64KB_ORDER = NAPOT_CONT_ORDER_BASE,
+ NAPOT_ORDER_MAX,
+};
+
+#define for_each_napot_order(order) \
+ for (order = NAPOT_CONT_ORDER_BASE; order < NAPOT_ORDER_MAX; order++)
+#define for_each_napot_order_rev(order) \
+ for (order = NAPOT_ORDER_MAX - 1; \
+ order >= NAPOT_CONT_ORDER_BASE; order--)
+#define napot_cont_order(val) (__builtin_ctzl((val.pte >> _PAGE_PFN_SHIFT) << 1))
+
+#define napot_cont_shift(order) ((order) + PAGE_SHIFT)
+#define napot_cont_size(order) BIT(napot_cont_shift(order))
+#define napot_cont_mask(order) (~(napot_cont_size(order) - 1UL))
+#define napot_pte_num(order) BIT(order)
+
+#ifdef CONFIG_RISCV_ISA_SVNAPOT
+#define HUGE_MAX_HSTATE (2 + (NAPOT_ORDER_MAX - NAPOT_CONT_ORDER_BASE))
+#else
+#define HUGE_MAX_HSTATE 2
+#endif
+
+/*
* [62:61] Svpbmt Memory Type definitions:
*
* 00 - PMA Normal Cacheable, No change to implied PMA memory type
@@ -88,14 +124,18 @@ typedef struct {
/*
* [63:59] T-Head Memory Type definitions:
- *
- * 00000 - NC Weakly-ordered, Non-cacheable, Non-bufferable, Non-shareable, Non-trustable
+ * bit[63] SO - Strong Order
+ * bit[62] C - Cacheable
+ * bit[61] B - Bufferable
+ * bit[60] SH - Shareable
+ * bit[59] Sec - Trustable
+ * 00110 - NC Weakly-ordered, Non-cacheable, Bufferable, Shareable, Non-trustable
* 01110 - PMA Weakly-ordered, Cacheable, Bufferable, Shareable, Non-trustable
- * 10000 - IO Strongly-ordered, Non-cacheable, Non-bufferable, Non-shareable, Non-trustable
+ * 10010 - IO Strongly-ordered, Non-cacheable, Non-bufferable, Shareable, Non-trustable
*/
#define _PAGE_PMA_THEAD ((1UL << 62) | (1UL << 61) | (1UL << 60))
-#define _PAGE_NOCACHE_THEAD 0UL
-#define _PAGE_IO_THEAD (1UL << 63)
+#define _PAGE_NOCACHE_THEAD ((1UL << 61) | (1UL << 60))
+#define _PAGE_IO_THEAD ((1UL << 63) | (1UL << 60))
#define _PAGE_MTMASK_THEAD (_PAGE_PMA_THEAD | _PAGE_IO_THEAD | (1UL << 59))
static inline u64 riscv_page_mtmask(void)
@@ -144,11 +184,11 @@ static inline int pud_none(pud_t pud)
static inline int pud_bad(pud_t pud)
{
- return !pud_present(pud);
+ return !pud_present(pud) || (pud_val(pud) & _PAGE_LEAF);
}
#define pud_leaf pud_leaf
-static inline int pud_leaf(pud_t pud)
+static inline bool pud_leaf(pud_t pud)
{
return pud_present(pud) && (pud_val(pud) & _PAGE_LEAF);
}
@@ -160,7 +200,7 @@ static inline int pud_user(pud_t pud)
static inline void set_pud(pud_t *pudp, pud_t pud)
{
- *pudp = pud;
+ WRITE_ONCE(*pudp, pud);
}
static inline void pud_clear(pud_t *pudp)
@@ -222,8 +262,6 @@ static inline unsigned long _pmd_pfn(pmd_t pmd)
return __page_val_to_pfn(pmd_val(pmd));
}
-#define mk_pmd(page, prot) pfn_pmd(page_to_pfn(page), prot)
-
#define pmd_ERROR(e) \
pr_err("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e))
@@ -236,7 +274,7 @@ static inline unsigned long _pmd_pfn(pmd_t pmd)
static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
{
if (pgtable_l4_enabled)
- *p4dp = p4d;
+ WRITE_ONCE(*p4dp, p4d);
else
set_pud((pud_t *)p4dp, (pud_t){ p4d_val(p4d) });
}
@@ -298,18 +336,12 @@ static inline struct page *p4d_page(p4d_t p4d)
#define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
#define pud_offset pud_offset
-static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
-{
- if (pgtable_l4_enabled)
- return p4d_pgtable(*p4d) + pud_index(address);
-
- return (pud_t *)p4d;
-}
+pud_t *pud_offset(p4d_t *p4d, unsigned long address);
static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
{
if (pgtable_l5_enabled)
- *pgdp = pgd;
+ WRITE_ONCE(*pgdp, pgd);
else
set_p4d((p4d_t *)pgdp, (p4d_t){ pgd_val(pgd) });
}
@@ -362,12 +394,27 @@ static inline struct page *pgd_page(pgd_t pgd)
#define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1))
#define p4d_offset p4d_offset
-static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+p4d_t *p4d_offset(pgd_t *pgd, unsigned long address);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline int pte_devmap(pte_t pte);
+static inline pte_t pmd_pte(pmd_t pmd);
+static inline pte_t pud_pte(pud_t pud);
+
+static inline int pmd_devmap(pmd_t pmd)
{
- if (pgtable_l5_enabled)
- return pgd_pgtable(*pgd) + p4d_index(address);
+ return pte_devmap(pmd_pte(pmd));
+}
- return (p4d_t *)pgd;
+static inline int pud_devmap(pud_t pud)
+{
+ return pte_devmap(pud_pte(pud));
+}
+
+static inline int pgd_devmap(pgd_t pgd)
+{
+ return 0;
}
+#endif
#endif /* _ASM_RISCV_PGTABLE_64_H */
diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h
index b9e13a8fe2b7..a8f5205cea54 100644
--- a/arch/riscv/include/asm/pgtable-bits.h
+++ b/arch/riscv/include/asm/pgtable-bits.h
@@ -16,9 +16,10 @@
#define _PAGE_GLOBAL (1 << 5) /* Global */
#define _PAGE_ACCESSED (1 << 6) /* Set by hardware on any access */
#define _PAGE_DIRTY (1 << 7) /* Set by hardware on any write */
-#define _PAGE_SOFT (1 << 8) /* Reserved for software */
+#define _PAGE_SOFT (3 << 8) /* Reserved for software */
-#define _PAGE_SPECIAL _PAGE_SOFT
+#define _PAGE_SPECIAL (1 << 8) /* RSW: 0x1 */
+#define _PAGE_DEVMAP (1 << 9) /* RSW, devmap */
#define _PAGE_TABLE _PAGE_PRESENT
/*
@@ -27,6 +28,9 @@
*/
#define _PAGE_PROT_NONE _PAGE_GLOBAL
+/* Used for swap PTEs only. */
+#define _PAGE_SWP_EXCLUSIVE _PAGE_ACCESSED
+
#define _PAGE_PFN_SHIFT 10
/*
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 5dbd6610729b..438ce7df24c3 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -12,7 +12,11 @@
#include <asm/pgtable-bits.h>
#ifndef CONFIG_MMU
-#define KERNEL_LINK_ADDR PAGE_OFFSET
+#ifdef CONFIG_RELOCATABLE
+#define KERNEL_LINK_ADDR UL(0)
+#else
+#define KERNEL_LINK_ADDR _AC(CONFIG_PHYS_RAM_BASE, UL)
+#endif
#define KERN_VIRT_SIZE (UL(-1))
#else
@@ -31,7 +35,7 @@
#define PTRS_PER_PTE (PAGE_SIZE / sizeof(pte_t))
/*
- * Half of the kernel address space (half of the entries of the page global
+ * Half of the kernel address space (1/4 of the entries of the page global
* directory) is for the direct mapping.
*/
#define KERN_VIRT_SIZE ((PTRS_PER_PGD / 2 * PGDIR_SIZE) / 2)
@@ -55,6 +59,9 @@
#define MODULES_LOWEST_VADDR (KERNEL_LINK_ADDR - SZ_2G)
#define MODULES_VADDR (PFN_ALIGN((unsigned long)&_end) - SZ_2G)
#define MODULES_END (PFN_ALIGN((unsigned long)&_start))
+#else
+#define MODULES_VADDR VMALLOC_START
+#define MODULES_END VMALLOC_END
#endif
/*
@@ -62,11 +69,16 @@
* struct pages to map half the virtual address space. Then
* position vmemmap directly below the VMALLOC region.
*/
+#define VA_BITS_SV32 32
#ifdef CONFIG_64BIT
+#define VA_BITS_SV39 39
+#define VA_BITS_SV48 48
+#define VA_BITS_SV57 57
+
#define VA_BITS (pgtable_l5_enabled ? \
- 57 : (pgtable_l4_enabled ? 48 : 39))
+ VA_BITS_SV57 : (pgtable_l4_enabled ? VA_BITS_SV48 : VA_BITS_SV39))
#else
-#define VA_BITS 32
+#define VA_BITS VA_BITS_SV32
#endif
#define VMEMMAP_SHIFT \
@@ -79,7 +91,7 @@
* Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel
* is configured with CONFIG_SPARSEMEM_VMEMMAP enabled.
*/
-#define vmemmap ((struct page *)VMEMMAP_START)
+#define vmemmap ((struct page *)VMEMMAP_START - vmemmap_start_pfn)
#define PCI_IO_SIZE SZ_16M
#define PCI_IO_END VMEMMAP_START
@@ -87,31 +99,39 @@
#define FIXADDR_TOP PCI_IO_START
#ifdef CONFIG_64BIT
-#define FIXADDR_SIZE PMD_SIZE
+#define MAX_FDT_SIZE PMD_SIZE
+#define FIX_FDT_SIZE (MAX_FDT_SIZE + SZ_2M)
+#define FIXADDR_SIZE (PMD_SIZE + FIX_FDT_SIZE)
#else
-#define FIXADDR_SIZE PGDIR_SIZE
+#define MAX_FDT_SIZE PGDIR_SIZE
+#define FIX_FDT_SIZE MAX_FDT_SIZE
+#define FIXADDR_SIZE (PGDIR_SIZE + FIX_FDT_SIZE)
#endif
#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE)
#endif
-#ifdef CONFIG_XIP_KERNEL
-#define XIP_OFFSET SZ_32M
-#define XIP_OFFSET_MASK (SZ_32M - 1)
-#else
-#define XIP_OFFSET 0
-#endif
-
#ifndef __ASSEMBLY__
#include <asm/page.h>
#include <asm/tlbflush.h>
#include <linux/mm_types.h>
+#include <asm/compat.h>
+#include <asm/cpufeature.h>
#define __page_val_to_pfn(_val) (((_val) & _PAGE_PFN_MASK) >> _PAGE_PFN_SHIFT)
#ifdef CONFIG_64BIT
#include <asm/pgtable-64.h>
+
+#define VA_USER_SV39 (UL(1) << (VA_BITS_SV39 - 1))
+#define VA_USER_SV48 (UL(1) << (VA_BITS_SV48 - 1))
+#define VA_USER_SV57 (UL(1) << (VA_BITS_SV57 - 1))
+
+#define MMAP_VA_BITS_64 ((VA_BITS >= VA_BITS_SV48) ? VA_BITS_SV48 : VA_BITS)
+#define MMAP_MIN_VA_BITS_64 (VA_BITS_SV39)
+#define MMAP_VA_BITS (is_compat_task() ? VA_BITS_SV32 : MMAP_VA_BITS_64)
+#define MMAP_MIN_VA_BITS (is_compat_task() ? VA_BITS_SV32 : MMAP_MIN_VA_BITS_64)
#else
#include <asm/pgtable-32.h>
#endif /* CONFIG_64BIT */
@@ -120,11 +140,14 @@
#ifdef CONFIG_XIP_KERNEL
#define XIP_FIXUP(addr) ({ \
+ extern char _sdata[], _start[], _end[]; \
+ uintptr_t __rom_start_data = CONFIG_XIP_PHYS_ADDR \
+ + (uintptr_t)&_sdata - (uintptr_t)&_start; \
+ uintptr_t __rom_end_data = CONFIG_XIP_PHYS_ADDR \
+ + (uintptr_t)&_end - (uintptr_t)&_start; \
uintptr_t __a = (uintptr_t)(addr); \
- (__a >= CONFIG_XIP_PHYS_ADDR && \
- __a < CONFIG_XIP_PHYS_ADDR + XIP_OFFSET * 2) ? \
- __a - CONFIG_XIP_PHYS_ADDR + CONFIG_PHYS_RAM_BASE - XIP_OFFSET :\
- __a; \
+ (__a >= __rom_start_data && __a < __rom_end_data) ? \
+ __a - __rom_start_data + CONFIG_PHYS_RAM_BASE : __a; \
})
#else
#define XIP_FIXUP(addr) (addr)
@@ -143,7 +166,7 @@ struct pt_alloc_ops {
#endif
};
-extern struct pt_alloc_ops pt_ops __initdata;
+extern struct pt_alloc_ops pt_ops __meminitdata;
#ifdef CONFIG_MMU
/* Number of PGD entries that a user-mode program can use */
@@ -161,8 +184,7 @@ extern struct pt_alloc_ops pt_ops __initdata;
_PAGE_EXEC | _PAGE_WRITE)
#define PAGE_COPY PAGE_READ
-#define PAGE_COPY_EXEC PAGE_EXEC
-#define PAGE_COPY_READ_EXEC PAGE_READ_EXEC
+#define PAGE_COPY_EXEC PAGE_READ_EXEC
#define PAGE_SHARED PAGE_WRITE
#define PAGE_SHARED_EXEC PAGE_WRITE_EXEC
@@ -185,26 +207,8 @@ extern struct pt_alloc_ops pt_ops __initdata;
#define PAGE_KERNEL_IO __pgprot(_PAGE_IOREMAP)
extern pgd_t swapper_pg_dir[];
-
-/* MAP_PRIVATE permissions: xwr (copy-on-write) */
-#define __P000 PAGE_NONE
-#define __P001 PAGE_READ
-#define __P010 PAGE_COPY
-#define __P011 PAGE_COPY
-#define __P100 PAGE_EXEC
-#define __P101 PAGE_READ_EXEC
-#define __P110 PAGE_COPY_EXEC
-#define __P111 PAGE_COPY_READ_EXEC
-
-/* MAP_SHARED permissions: xwr */
-#define __S000 PAGE_NONE
-#define __S001 PAGE_READ
-#define __S010 PAGE_SHARED
-#define __S011 PAGE_SHARED
-#define __S100 PAGE_EXEC
-#define __S101 PAGE_READ_EXEC
-#define __S110 PAGE_SHARED_EXEC
-#define __S111 PAGE_SHARED_EXEC
+extern pgd_t trampoline_pg_dir[];
+extern pgd_t early_pg_dir[];
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static inline int pmd_present(pmd_t pmd)
@@ -235,14 +239,14 @@ static inline int pmd_bad(pmd_t pmd)
}
#define pmd_leaf pmd_leaf
-static inline int pmd_leaf(pmd_t pmd)
+static inline bool pmd_leaf(pmd_t pmd)
{
return pmd_present(pmd) && (pmd_val(pmd) & _PAGE_LEAF);
}
static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
{
- *pmdp = pmd;
+ WRITE_ONCE(*pmdp, pmd);
}
static inline void pmd_clear(pmd_t *pmdp)
@@ -284,10 +288,47 @@ static inline pte_t pud_pte(pud_t pud)
return __pte(pud_val(pud));
}
+#ifdef CONFIG_RISCV_ISA_SVNAPOT
+
+static __always_inline bool has_svnapot(void)
+{
+ return riscv_has_extension_likely(RISCV_ISA_EXT_SVNAPOT);
+}
+
+static inline unsigned long pte_napot(pte_t pte)
+{
+ return pte_val(pte) & _PAGE_NAPOT;
+}
+
+static inline pte_t pte_mknapot(pte_t pte, unsigned int order)
+{
+ int pos = order - 1 + _PAGE_PFN_SHIFT;
+ unsigned long napot_bit = BIT(pos);
+ unsigned long napot_mask = ~GENMASK(pos, _PAGE_PFN_SHIFT);
+
+ return __pte((pte_val(pte) & napot_mask) | napot_bit | _PAGE_NAPOT);
+}
+
+#else
+
+static __always_inline bool has_svnapot(void) { return false; }
+
+static inline unsigned long pte_napot(pte_t pte)
+{
+ return 0;
+}
+
+#endif /* CONFIG_RISCV_ISA_SVNAPOT */
+
/* Yields the page frame number (PFN) of a page table entry */
static inline unsigned long pte_pfn(pte_t pte)
{
- return __page_val_to_pfn(pte_val(pte));
+ unsigned long res = __page_val_to_pfn(pte_val(pte));
+
+ if (has_svnapot() && pte_napot(pte))
+ res = res & (res - 1UL);
+
+ return res;
}
#define pte_page(x) pfn_to_page(pte_pfn(x))
@@ -302,13 +343,32 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot)
return __pte((pfn << _PAGE_PFN_SHIFT) | prot_val);
}
-#define mk_pte(page, prot) pfn_pte(page_to_pfn(page), prot)
+#define pte_pgprot pte_pgprot
+static inline pgprot_t pte_pgprot(pte_t pte)
+{
+ unsigned long pfn = pte_pfn(pte);
+
+ return __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte));
+}
static inline int pte_present(pte_t pte)
{
return (pte_val(pte) & (_PAGE_PRESENT | _PAGE_PROT_NONE));
}
+#define pte_accessible pte_accessible
+static inline unsigned long pte_accessible(struct mm_struct *mm, pte_t a)
+{
+ if (pte_val(a) & _PAGE_PRESENT)
+ return true;
+
+ if ((pte_val(a) & _PAGE_PROT_NONE) &&
+ atomic_read(&mm->tlb_flush_pending))
+ return true;
+
+ return false;
+}
+
static inline int pte_none(pte_t pte)
{
return (pte_val(pte) == 0);
@@ -349,6 +409,13 @@ static inline int pte_special(pte_t pte)
return pte_val(pte) & _PAGE_SPECIAL;
}
+#ifdef CONFIG_ARCH_HAS_PTE_DEVMAP
+static inline int pte_devmap(pte_t pte)
+{
+ return pte_val(pte) & _PAGE_DEVMAP;
+}
+#endif
+
/* static inline pte_t pte_rdprotect(pte_t pte) */
static inline pte_t pte_wrprotect(pte_t pte)
@@ -358,7 +425,7 @@ static inline pte_t pte_wrprotect(pte_t pte)
/* static inline pte_t pte_mkread(pte_t pte) */
-static inline pte_t pte_mkwrite(pte_t pte)
+static inline pte_t pte_mkwrite_novma(pte_t pte)
{
return __pte(pte_val(pte) | _PAGE_WRITE);
}
@@ -390,11 +457,22 @@ static inline pte_t pte_mkspecial(pte_t pte)
return __pte(pte_val(pte) | _PAGE_SPECIAL);
}
+static inline pte_t pte_mkdevmap(pte_t pte)
+{
+ return __pte(pte_val(pte) | _PAGE_DEVMAP);
+}
+
static inline pte_t pte_mkhuge(pte_t pte)
{
return pte;
}
+#ifdef CONFIG_RISCV_ISA_SVNAPOT
+#define pte_leaf_size(pte) (pte_napot(pte) ? \
+ napot_cont_size(napot_cont_order(pte)) :\
+ PAGE_SIZE)
+#endif
+
#ifdef CONFIG_NUMA_BALANCING
/*
* See the comment in include/asm-generic/pgtable.h
@@ -425,9 +503,13 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
/* Commit new configuration to MMU hardware */
-static inline void update_mmu_cache(struct vm_area_struct *vma,
- unsigned long address, pte_t *ptep)
+static inline void update_mmu_cache_range(struct vm_fault *vmf,
+ struct vm_area_struct *vma, unsigned long address,
+ pte_t *ptep, unsigned int nr)
{
+ asm goto(ALTERNATIVE("nop", "j %l[svvptc]", 0, RISCV_ISA_EXT_SVVPTC, 1)
+ : : : : svvptc);
+
/*
* The kernel assumes that TLBs don't cache invalid entries, but
* in RISC-V, SFENCE.VMA specifies an ordering constraint, not a
@@ -435,8 +517,21 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
* Relying on flush_tlb_fix_spurious_fault would suffice, but
* the extra traps reduce performance. So, eagerly SFENCE.VMA.
*/
- local_flush_tlb_page(address);
+ while (nr--)
+ local_flush_tlb_page(address + nr * PAGE_SIZE);
+
+svvptc:;
+ /*
+ * Svvptc guarantees that the new valid pte will be visible within
+ * a bounded timeframe, so when the uarch does not cache invalid
+ * entries, we don't have to do anything.
+ */
}
+#define update_mmu_cache(vma, addr, ptep) \
+ update_mmu_cache_range(NULL, vma, addr, ptep, 1)
+
+#define update_mmu_tlb_range(vma, addr, ptep, nr) \
+ update_mmu_cache_range(NULL, vma, addr, ptep, nr)
static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp)
@@ -459,46 +554,48 @@ static inline int pte_same(pte_t pte_a, pte_t pte_b)
*/
static inline void set_pte(pte_t *ptep, pte_t pteval)
{
- *ptep = pteval;
+ WRITE_ONCE(*ptep, pteval);
}
-void flush_icache_pte(pte_t pte);
+void flush_icache_pte(struct mm_struct *mm, pte_t pte);
-static inline void __set_pte_at(struct mm_struct *mm,
- unsigned long addr, pte_t *ptep, pte_t pteval)
+static inline void __set_pte_at(struct mm_struct *mm, pte_t *ptep, pte_t pteval)
{
if (pte_present(pteval) && pte_exec(pteval))
- flush_icache_pte(pteval);
+ flush_icache_pte(mm, pteval);
set_pte(ptep, pteval);
}
-static inline void set_pte_at(struct mm_struct *mm,
- unsigned long addr, pte_t *ptep, pte_t pteval)
+#define PFN_PTE_SHIFT _PAGE_PFN_SHIFT
+
+static inline void set_ptes(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pteval, unsigned int nr)
{
- page_table_check_pte_set(mm, addr, ptep, pteval);
- __set_pte_at(mm, addr, ptep, pteval);
+ page_table_check_ptes_set(mm, ptep, pteval, nr);
+
+ for (;;) {
+ __set_pte_at(mm, ptep, pteval);
+ if (--nr == 0)
+ break;
+ ptep++;
+ pte_val(pteval) += 1 << _PAGE_PFN_SHIFT;
+ }
}
+#define set_ptes set_ptes
static inline void pte_clear(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
- __set_pte_at(mm, addr, ptep, __pte(0));
+ __set_pte_at(mm, ptep, __pte(0));
}
-#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
-static inline int ptep_set_access_flags(struct vm_area_struct *vma,
- unsigned long address, pte_t *ptep,
- pte_t entry, int dirty)
-{
- if (!pte_same(*ptep, entry))
- set_pte_at(vma->vm_mm, address, ptep, entry);
- /*
- * update_mmu_cache will unconditionally execute, handling both
- * the case that the PTE changed and the spurious fault case.
- */
- return true;
-}
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS /* defined in mm/pgtable.c */
+extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
+ pte_t *ptep, pte_t entry, int dirty);
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG /* defined in mm/pgtable.c */
+extern int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address,
+ pte_t *ptep);
#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
@@ -506,21 +603,11 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
{
pte_t pte = __pte(atomic_long_xchg((atomic_long_t *)ptep, 0));
- page_table_check_pte_clear(mm, address, pte);
+ page_table_check_pte_clear(mm, pte);
return pte;
}
-#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
-static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
- unsigned long address,
- pte_t *ptep)
-{
- if (!pte_young(*ptep))
- return 0;
- return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep));
-}
-
#define __HAVE_ARCH_PTEP_SET_WRPROTECT
static inline void ptep_set_wrprotect(struct mm_struct *mm,
unsigned long address, pte_t *ptep)
@@ -550,6 +637,12 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
return ptep_test_and_clear_young(vma, address, ptep);
}
+#define pgprot_nx pgprot_nx
+static inline pgprot_t pgprot_nx(pgprot_t _prot)
+{
+ return __pgprot(pgprot_val(_prot) & ~_PAGE_EXEC);
+}
+
#define pgprot_noncached pgprot_noncached
static inline pgprot_t pgprot_noncached(pgprot_t _prot)
{
@@ -573,6 +666,17 @@ static inline pgprot_t pgprot_writecombine(pgprot_t _prot)
}
/*
+ * Both Svade and Svadu control the hardware behavior when the PTE A/D bits need to be set. By
+ * default the M-mode firmware enables the hardware updating scheme when only Svadu is present in
+ * DT.
+ */
+#define arch_has_hw_pte_young arch_has_hw_pte_young
+static inline bool arch_has_hw_pte_young(void)
+{
+ return riscv_has_extension_unlikely(RISCV_ISA_EXT_SVADU);
+}
+
+/*
* THP functions
*/
static inline pmd_t pte_pmd(pte_t pte)
@@ -580,6 +684,11 @@ static inline pmd_t pte_pmd(pte_t pte)
return __pmd(pte_val(pte));
}
+static inline pud_t pte_pud(pte_t pte)
+{
+ return __pud(pte_val(pte));
+}
+
static inline pmd_t pmd_mkhuge(pmd_t pmd)
{
return pmd;
@@ -599,11 +708,24 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
#define __pud_to_phys(pud) (__page_val_to_pfn(pud_val(pud)) << PAGE_SHIFT)
+#define pud_pfn pud_pfn
static inline unsigned long pud_pfn(pud_t pud)
{
return ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT);
}
+#define pmd_pgprot pmd_pgprot
+static inline pgprot_t pmd_pgprot(pmd_t pmd)
+{
+ return pte_pgprot(pmd_pte(pmd));
+}
+
+#define pud_pgprot pud_pgprot
+static inline pgprot_t pud_pgprot(pud_t pud)
+{
+ return pte_pgprot(pud_pte(pud));
+}
+
static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
{
return pte_pmd(pte_modify(pmd_pte(pmd), newprot));
@@ -615,11 +737,19 @@ static inline int pmd_write(pmd_t pmd)
return pte_write(pmd_pte(pmd));
}
+#define pud_write pud_write
+static inline int pud_write(pud_t pud)
+{
+ return pte_write(pud_pte(pud));
+}
+
+#define pmd_dirty pmd_dirty
static inline int pmd_dirty(pmd_t pmd)
{
return pte_dirty(pmd_pte(pmd));
}
+#define pmd_young pmd_young
static inline int pmd_young(pmd_t pmd)
{
return pte_young(pmd_pte(pmd));
@@ -640,9 +770,9 @@ static inline pmd_t pmd_mkyoung(pmd_t pmd)
return pte_pmd(pte_mkyoung(pmd_pte(pmd)));
}
-static inline pmd_t pmd_mkwrite(pmd_t pmd)
+static inline pmd_t pmd_mkwrite_novma(pmd_t pmd)
{
- return pte_pmd(pte_mkwrite(pmd_pte(pmd)));
+ return pte_pmd(pte_mkwrite_novma(pmd_pte(pmd)));
}
static inline pmd_t pmd_wrprotect(pmd_t pmd)
@@ -660,18 +790,47 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd)
return pte_pmd(pte_mkdirty(pmd_pte(pmd)));
}
+static inline pmd_t pmd_mkdevmap(pmd_t pmd)
+{
+ return pte_pmd(pte_mkdevmap(pmd_pte(pmd)));
+}
+
+#ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP
+static inline bool pmd_special(pmd_t pmd)
+{
+ return pte_special(pmd_pte(pmd));
+}
+
+static inline pmd_t pmd_mkspecial(pmd_t pmd)
+{
+ return pte_pmd(pte_mkspecial(pmd_pte(pmd)));
+}
+#endif
+
+#ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP
+static inline bool pud_special(pud_t pud)
+{
+ return pte_special(pud_pte(pud));
+}
+
+static inline pud_t pud_mkspecial(pud_t pud)
+{
+ return pte_pud(pte_mkspecial(pud_pte(pud)));
+}
+#endif
+
static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp, pmd_t pmd)
{
- page_table_check_pmd_set(mm, addr, pmdp, pmd);
- return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd));
+ page_table_check_pmd_set(mm, pmdp, pmd);
+ return __set_pte_at(mm, (pte_t *)pmdp, pmd_pte(pmd));
}
static inline void set_pud_at(struct mm_struct *mm, unsigned long addr,
pud_t *pudp, pud_t pud)
{
- page_table_check_pud_set(mm, addr, pudp, pud);
- return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud));
+ page_table_check_pud_set(mm, pudp, pud);
+ return __set_pte_at(mm, (pte_t *)pudp, pud_pte(pud));
}
#ifdef CONFIG_PAGE_TABLE_CHECK
@@ -718,7 +877,7 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
{
pmd_t pmd = __pmd(atomic_long_xchg((atomic_long_t *)pmdp, 0));
- page_table_check_pmd_clear(mm, address, pmd);
+ page_table_check_pmd_clear(mm, pmd);
return pmd;
}
@@ -734,22 +893,125 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp, pmd_t pmd)
{
- page_table_check_pmd_set(vma->vm_mm, address, pmdp, pmd);
+ page_table_check_pmd_set(vma->vm_mm, pmdp, pmd);
return __pmd(atomic_long_xchg((atomic_long_t *)pmdp, pmd_val(pmd)));
}
+
+#define pmdp_collapse_flush pmdp_collapse_flush
+extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
+ unsigned long address, pmd_t *pmdp);
+
+static inline pud_t pud_wrprotect(pud_t pud)
+{
+ return pte_pud(pte_wrprotect(pud_pte(pud)));
+}
+
+static inline int pud_trans_huge(pud_t pud)
+{
+ return pud_leaf(pud);
+}
+
+static inline int pud_dirty(pud_t pud)
+{
+ return pte_dirty(pud_pte(pud));
+}
+
+static inline pud_t pud_mkyoung(pud_t pud)
+{
+ return pte_pud(pte_mkyoung(pud_pte(pud)));
+}
+
+static inline pud_t pud_mkold(pud_t pud)
+{
+ return pte_pud(pte_mkold(pud_pte(pud)));
+}
+
+static inline pud_t pud_mkdirty(pud_t pud)
+{
+ return pte_pud(pte_mkdirty(pud_pte(pud)));
+}
+
+static inline pud_t pud_mkclean(pud_t pud)
+{
+ return pte_pud(pte_mkclean(pud_pte(pud)));
+}
+
+static inline pud_t pud_mkwrite(pud_t pud)
+{
+ return pte_pud(pte_mkwrite_novma(pud_pte(pud)));
+}
+
+static inline pud_t pud_mkhuge(pud_t pud)
+{
+ return pud;
+}
+
+static inline pud_t pud_mkdevmap(pud_t pud)
+{
+ return pte_pud(pte_mkdevmap(pud_pte(pud)));
+}
+
+static inline int pudp_set_access_flags(struct vm_area_struct *vma,
+ unsigned long address, pud_t *pudp,
+ pud_t entry, int dirty)
+{
+ return ptep_set_access_flags(vma, address, (pte_t *)pudp, pud_pte(entry), dirty);
+}
+
+static inline int pudp_test_and_clear_young(struct vm_area_struct *vma,
+ unsigned long address, pud_t *pudp)
+{
+ return ptep_test_and_clear_young(vma, address, (pte_t *)pudp);
+}
+
+static inline int pud_young(pud_t pud)
+{
+ return pte_young(pud_pte(pud));
+}
+
+static inline void update_mmu_cache_pud(struct vm_area_struct *vma,
+ unsigned long address, pud_t *pudp)
+{
+ pte_t *ptep = (pte_t *)pudp;
+
+ update_mmu_cache(vma, address, ptep);
+}
+
+static inline pud_t pudp_establish(struct vm_area_struct *vma,
+ unsigned long address, pud_t *pudp, pud_t pud)
+{
+ page_table_check_pud_set(vma->vm_mm, pudp, pud);
+ return __pud(atomic_long_xchg((atomic_long_t *)pudp, pud_val(pud)));
+}
+
+static inline pud_t pud_mkinvalid(pud_t pud)
+{
+ return __pud(pud_val(pud) & ~(_PAGE_PRESENT | _PAGE_PROT_NONE));
+}
+
+extern pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address,
+ pud_t *pudp);
+
+static inline pud_t pud_modify(pud_t pud, pgprot_t newprot)
+{
+ return pte_pud(pte_modify(pud_pte(pud), newprot));
+}
+
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
/*
- * Encode and decode a swap entry
+ * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that
+ * are !pte_none() && !pte_present().
*
* Format of swap PTE:
* bit 0: _PAGE_PRESENT (zero)
* bit 1 to 3: _PAGE_LEAF (zero)
* bit 5: _PAGE_PROT_NONE (zero)
- * bits 6 to 10: swap type
- * bits 10 to XLEN-1: swap offset
+ * bit 6: exclusive marker
+ * bits 7 to 11: swap type
+ * bits 12 to XLEN-1: swap offset
*/
-#define __SWP_TYPE_SHIFT 6
+#define __SWP_TYPE_SHIFT 7
#define __SWP_TYPE_BITS 5
#define __SWP_TYPE_MASK ((1UL << __SWP_TYPE_BITS) - 1)
#define __SWP_OFFSET_SHIFT (__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
@@ -760,11 +1022,27 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
#define __swp_type(x) (((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK)
#define __swp_offset(x) ((x).val >> __SWP_OFFSET_SHIFT)
#define __swp_entry(type, offset) ((swp_entry_t) \
- { ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) })
+ { (((type) & __SWP_TYPE_MASK) << __SWP_TYPE_SHIFT) | \
+ ((offset) << __SWP_OFFSET_SHIFT) })
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
+static inline bool pte_swp_exclusive(pte_t pte)
+{
+ return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
+}
+
+static inline pte_t pte_swp_mkexclusive(pte_t pte)
+{
+ return __pte(pte_val(pte) | _PAGE_SWP_EXCLUSIVE);
+}
+
+static inline pte_t pte_swp_clear_exclusive(pte_t pte)
+{
+ return __pte(pte_val(pte) & ~_PAGE_SWP_EXCLUSIVE);
+}
+
#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
#define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val(pmd) })
#define __swp_entry_to_pmd(swp) __pmd((swp).val)
@@ -784,22 +1062,24 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
* Task size is 0x4000000000 for RV64 or 0x9fc00000 for RV32.
* Note that PGDIR_SIZE must evenly divide TASK_SIZE.
* Task size is:
- * - 0x9fc00000 (~2.5GB) for RV32.
- * - 0x4000000000 ( 256GB) for RV64 using SV39 mmu
- * - 0x800000000000 ( 128TB) for RV64 using SV48 mmu
+ * - 0x9fc00000 (~2.5GB) for RV32.
+ * - 0x4000000000 ( 256GB) for RV64 using SV39 mmu
+ * - 0x800000000000 ( 128TB) for RV64 using SV48 mmu
+ * - 0x100000000000000 ( 64PB) for RV64 using SV57 mmu
*
* Note that PGDIR_SIZE must evenly divide TASK_SIZE since "RISC-V
* Instruction Set Manual Volume II: Privileged Architecture" states that
* "load and store effective addresses, which are 64bits, must have bits
* 63–48 all equal to bit 47, or else a page-fault exception will occur."
+ * Similarly for SV57, bits 63–57 must be equal to bit 56.
*/
#ifdef CONFIG_64BIT
#define TASK_SIZE_64 (PGDIR_SIZE * PTRS_PER_PGD / 2)
-#define TASK_SIZE_MIN (PGDIR_SIZE_L3 * PTRS_PER_PGD / 2)
+#define TASK_SIZE_MAX LONG_MAX
#ifdef CONFIG_COMPAT
#define TASK_SIZE_32 (_AC(0x80000000, UL) - PAGE_SIZE)
-#define TASK_SIZE (test_thread_flag(TIF_32BIT) ? \
+#define TASK_SIZE (is_compat_task() ? \
TASK_SIZE_32 : TASK_SIZE_64)
#else
#define TASK_SIZE TASK_SIZE_64
@@ -807,7 +1087,6 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
#else
#define TASK_SIZE FIXADDR_START
-#define TASK_SIZE_MIN TASK_SIZE
#endif
#else /* CONFIG_MMU */
@@ -815,14 +1094,12 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
#define PAGE_SHARED __pgprot(0)
#define PAGE_KERNEL __pgprot(0)
#define swapper_pg_dir NULL
-#define TASK_SIZE 0xffffffffUL
-#define VMALLOC_START 0
+#define TASK_SIZE _AC(-1, UL)
+#define VMALLOC_START _AC(0, UL)
#define VMALLOC_END TASK_SIZE
#endif /* !CONFIG_MMU */
-#define kern_addr_valid(addr) (1) /* FIXME */
-
extern char _start[];
extern void *_dtb_early_va;
extern uintptr_t _dtb_early_pa;
@@ -834,7 +1111,6 @@ extern uintptr_t _dtb_early_pa;
#define dtb_early_pa _dtb_early_pa
#endif /* CONFIG_XIP_KERNEL */
extern u64 satp_mode;
-extern bool pgtable_l4_enabled;
void paging_init(void);
void misc_mem_init(void);
@@ -846,6 +1122,25 @@ void misc_mem_init(void);
extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+/*
+ * Use set_p*_safe(), and elide TLB flushing, when confident that *no*
+ * TLB flush will be required as a result of the "set". For example, use
+ * in scenarios where it is known ahead of time that the routine is
+ * setting non-present entries, or re-setting an existing entry to the
+ * same value. Otherwise, use the typical "set" helpers and flush the
+ * TLB.
+ */
+#define set_p4d_safe(p4dp, p4d) \
+({ \
+ WARN_ON_ONCE(p4d_present(*p4dp) && !p4d_same(*p4dp, p4d)); \
+ set_p4d(p4dp, p4d); \
+})
+
+#define set_pgd_safe(pgdp, pgd) \
+({ \
+ WARN_ON_ONCE(pgd_present(*pgdp) && !pgd_same(*pgdp, pgd)); \
+ set_pgd(pgdp, pgd); \
+})
#endif /* !__ASSEMBLY__ */
#endif /* _ASM_RISCV_PGTABLE_H */
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index 21c8072dce17..24d3af4d3807 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -7,30 +7,100 @@
#define _ASM_RISCV_PROCESSOR_H
#include <linux/const.h>
+#include <linux/cache.h>
+#include <linux/prctl.h>
#include <vdso/processor.h>
#include <asm/ptrace.h>
+#include <asm/insn-def.h>
+#include <asm/alternative-macros.h>
+#include <asm/hwcap.h>
-/*
- * This decides where the kernel will search for a free chunk of vm
- * space during mmap's.
- */
-#define TASK_UNMAPPED_BASE PAGE_ALIGN(TASK_SIZE / 3)
+#define arch_get_mmap_end(addr, len, flags) \
+({ \
+ STACK_TOP_MAX; \
+})
+
+#define arch_get_mmap_base(addr, base) \
+({ \
+ base; \
+})
-#define STACK_TOP TASK_SIZE
#ifdef CONFIG_64BIT
+#define DEFAULT_MAP_WINDOW (UL(1) << (MMAP_VA_BITS - 1))
#define STACK_TOP_MAX TASK_SIZE_64
#else
+#define DEFAULT_MAP_WINDOW TASK_SIZE
#define STACK_TOP_MAX TASK_SIZE
#endif
#define STACK_ALIGN 16
+#define STACK_TOP DEFAULT_MAP_WINDOW
+
+#ifdef CONFIG_MMU
+#define user_max_virt_addr() arch_get_mmap_end(ULONG_MAX, 0, 0)
+#else
+#define user_max_virt_addr() 0
+#endif /* CONFIG_MMU */
+
+/*
+ * This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+ */
+#ifdef CONFIG_64BIT
+#define TASK_UNMAPPED_BASE PAGE_ALIGN((UL(1) << MMAP_MIN_VA_BITS) / 3)
+#else
+#define TASK_UNMAPPED_BASE PAGE_ALIGN(TASK_SIZE / 3)
+#endif
+
#ifndef __ASSEMBLY__
struct task_struct;
struct pt_regs;
+/*
+ * We use a flag to track in-kernel Vector context. Currently the flag has the
+ * following meaning:
+ *
+ * - bit 0: indicates whether the in-kernel Vector context is active. The
+ * activation of this state disables the preemption. On a non-RT kernel, it
+ * also disable bh.
+ * - bits 8: is used for tracking preemptible kernel-mode Vector, when
+ * RISCV_ISA_V_PREEMPTIVE is enabled. Calling kernel_vector_begin() does not
+ * disable the preemption if the thread's kernel_vstate.datap is allocated.
+ * Instead, the kernel set this bit field. Then the trap entry/exit code
+ * knows if we are entering/exiting the context that owns preempt_v.
+ * - 0: the task is not using preempt_v
+ * - 1: the task is actively using preempt_v. But whether does the task own
+ * the preempt_v context is decided by bits in RISCV_V_CTX_DEPTH_MASK.
+ * - bit 16-23 are RISCV_V_CTX_DEPTH_MASK, used by context tracking routine
+ * when preempt_v starts:
+ * - 0: the task is actively using, and own preempt_v context.
+ * - non-zero: the task was using preempt_v, but then took a trap within.
+ * Thus, the task does not own preempt_v. Any use of Vector will have to
+ * save preempt_v, if dirty, and fallback to non-preemptible kernel-mode
+ * Vector.
+ * - bit 29: The thread voluntarily calls schedule() while holding an active
+ * preempt_v. All preempt_v context should be dropped in such case because
+ * V-regs are caller-saved. Only sstatus.VS=ON is persisted across a
+ * schedule() call.
+ * - bit 30: The in-kernel preempt_v context is saved, and requries to be
+ * restored when returning to the context that owns the preempt_v.
+ * - bit 31: The in-kernel preempt_v context is dirty, as signaled by the
+ * trap entry code. Any context switches out-of current task need to save
+ * it to the task's in-kernel V context. Also, any traps nesting on-top-of
+ * preempt_v requesting to use V needs a save.
+ */
+#define RISCV_V_CTX_DEPTH_MASK 0x00ff0000
+
+#define RISCV_V_CTX_UNIT_DEPTH 0x00010000
+#define RISCV_KERNEL_MODE_V 0x00000001
+#define RISCV_PREEMPT_V 0x00000100
+#define RISCV_PREEMPT_V_DIRTY 0x80000000
+#define RISCV_PREEMPT_V_NEED_RESTORE 0x40000000
+#define RISCV_PREEMPT_V_IN_SCHEDULE 0x20000000
+
/* CPU-specific state of a task */
struct thread_struct {
/* Callee-saved registers */
@@ -39,6 +109,19 @@ struct thread_struct {
unsigned long s[12]; /* s[0]: frame pointer */
struct __riscv_d_ext_state fstate;
unsigned long bad_cause;
+ unsigned long envcfg;
+ unsigned long sum;
+ u32 riscv_v_flags;
+ u32 vstate_ctrl;
+ struct __riscv_v_ext_state vstate;
+ unsigned long align_ctl;
+ struct __riscv_v_ext_state kernel_vstate;
+#ifdef CONFIG_SMP
+ /* Flush the icache on migration */
+ bool force_icache_flush;
+ /* A forced icache flush is not needed if migrating to the previous cpu. */
+ unsigned int prev_cpu;
+#endif
};
/* Whitelist the fstate from the task_struct for hardened usercopy */
@@ -51,6 +134,7 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset,
#define INIT_THREAD { \
.sp = sizeof(init_stack) + (long)&init_stack, \
+ .align_ctl = PR_UNALIGN_NOPRINT, \
}
#define task_pt_regs(tsk) \
@@ -60,16 +144,32 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset,
#define KSTK_EIP(tsk) (task_pt_regs(tsk)->epc)
#define KSTK_ESP(tsk) (task_pt_regs(tsk)->sp)
+#define PREFETCH_ASM(x) \
+ ALTERNATIVE(__nops(1), PREFETCH_R(x, 0), 0, \
+ RISCV_ISA_EXT_ZICBOP, CONFIG_RISCV_ISA_ZICBOP)
-/* Do necessary setup to start up a newly executed thread. */
-extern void start_thread(struct pt_regs *regs,
- unsigned long pc, unsigned long sp);
+#define PREFETCHW_ASM(x) \
+ ALTERNATIVE(__nops(1), PREFETCH_W(x, 0), 0, \
+ RISCV_ISA_EXT_ZICBOP, CONFIG_RISCV_ISA_ZICBOP)
-/* Free all resources held by a thread. */
-static inline void release_thread(struct task_struct *dead_task)
+#ifdef CONFIG_RISCV_ISA_ZICBOP
+#define ARCH_HAS_PREFETCH
+static inline void prefetch(const void *x)
{
+ __asm__ __volatile__(PREFETCH_ASM(%0) : : "r" (x) : "memory");
}
+#define ARCH_HAS_PREFETCHW
+static inline void prefetchw(const void *x)
+{
+ __asm__ __volatile__(PREFETCHW_ASM(%0) : : "r" (x) : "memory");
+}
+#endif /* CONFIG_RISCV_ISA_ZICBOP */
+
+/* Do necessary setup to start up a newly executed thread. */
+extern void start_thread(struct pt_regs *regs,
+ unsigned long pc, unsigned long sp);
+
extern unsigned long __get_wchan(struct task_struct *p);
@@ -78,13 +178,43 @@ static inline void wait_for_interrupt(void)
__asm__ __volatile__ ("wfi");
}
+extern phys_addr_t dma32_phys_limit;
+
struct device_node;
-int riscv_of_processor_hartid(struct device_node *node);
-int riscv_of_parent_hartid(struct device_node *node);
+int riscv_of_processor_hartid(struct device_node *node, unsigned long *hartid);
+int riscv_early_of_processor_hartid(struct device_node *node, unsigned long *hartid);
+int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid);
extern void riscv_fill_hwcap(void);
extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
+extern unsigned long signal_minsigstksz __ro_after_init;
+
+#ifdef CONFIG_RISCV_ISA_V
+/* Userspace interface for PR_RISCV_V_{SET,GET}_VS prctl()s: */
+#define RISCV_V_SET_CONTROL(arg) riscv_v_vstate_ctrl_set_current(arg)
+#define RISCV_V_GET_CONTROL() riscv_v_vstate_ctrl_get_current()
+extern long riscv_v_vstate_ctrl_set_current(unsigned long arg);
+extern long riscv_v_vstate_ctrl_get_current(void);
+#endif /* CONFIG_RISCV_ISA_V */
+
+extern int get_unalign_ctl(struct task_struct *tsk, unsigned long addr);
+extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val);
+
+#define GET_UNALIGN_CTL(tsk, addr) get_unalign_ctl((tsk), (addr))
+#define SET_UNALIGN_CTL(tsk, val) set_unalign_ctl((tsk), (val))
+
+#define RISCV_SET_ICACHE_FLUSH_CTX(arg1, arg2) riscv_set_icache_flush_ctx(arg1, arg2)
+extern int riscv_set_icache_flush_ctx(unsigned long ctx, unsigned long per_thread);
+
+#ifdef CONFIG_RISCV_ISA_SUPM
+/* PR_{SET,GET}_TAGGED_ADDR_CTRL prctl */
+long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg);
+long get_tagged_addr_ctrl(struct task_struct *task);
+#define SET_TAGGED_ADDR_CTRL(arg) set_tagged_addr_ctrl(current, arg)
+#define GET_TAGGED_ADDR_CTRL() get_tagged_addr_ctrl(current)
+#endif
+
#endif /* __ASSEMBLY__ */
#endif /* _ASM_RISCV_PROCESSOR_H */
diff --git a/arch/riscv/include/asm/ptdump.h b/arch/riscv/include/asm/ptdump.h
deleted file mode 100644
index 3c9ea6dd5af7..000000000000
--- a/arch/riscv/include/asm/ptdump.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2019 SiFive
- */
-
-#ifndef _ASM_RISCV_PTDUMP_H
-#define _ASM_RISCV_PTDUMP_H
-
-void ptdump_check_wx(void);
-
-#ifdef CONFIG_DEBUG_WX
-static inline void debug_checkwx(void)
-{
- ptdump_check_wx();
-}
-#else
-static inline void debug_checkwx(void)
-{
-}
-#endif
-
-#endif /* _ASM_RISCV_PTDUMP_H */
diff --git a/arch/riscv/include/asm/ptrace.h b/arch/riscv/include/asm/ptrace.h
index 6ecd461129d2..a7dc0e330757 100644
--- a/arch/riscv/include/asm/ptrace.h
+++ b/arch/riscv/include/asm/ptrace.h
@@ -23,14 +23,16 @@ struct pt_regs {
unsigned long t2;
unsigned long s0;
unsigned long s1;
- unsigned long a0;
- unsigned long a1;
- unsigned long a2;
- unsigned long a3;
- unsigned long a4;
- unsigned long a5;
- unsigned long a6;
- unsigned long a7;
+ struct_group(a_regs,
+ unsigned long a0;
+ unsigned long a1;
+ unsigned long a2;
+ unsigned long a3;
+ unsigned long a4;
+ unsigned long a5;
+ unsigned long a6;
+ unsigned long a7;
+ );
unsigned long s2;
unsigned long s3;
unsigned long s4;
@@ -53,6 +55,9 @@ struct pt_regs {
unsigned long orig_a0;
};
+#define PTRACE_SYSEMU 0x1f
+#define PTRACE_SYSEMU_SINGLESTEP 0x20
+
#ifdef CONFIG_64BIT
#define REG_FMT "%016lx"
#else
@@ -121,8 +126,6 @@ extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
unsigned long frame_pointer);
-int do_syscall_trace_enter(struct pt_regs *regs);
-void do_syscall_trace_exit(struct pt_regs *regs);
/**
* regs_get_register() - get register value from its offset
@@ -172,6 +175,11 @@ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs,
return 0;
}
+static __always_inline bool regs_irqs_disabled(struct pt_regs *regs)
+{
+ return !(regs->status & SR_PIE);
+}
+
#endif /* __ASSEMBLY__ */
#endif /* _ASM_RISCV_PTRACE_H */
diff --git a/arch/riscv/include/asm/runtime-const.h b/arch/riscv/include/asm/runtime-const.h
new file mode 100644
index 000000000000..451fd76b8811
--- /dev/null
+++ b/arch/riscv/include/asm/runtime-const.h
@@ -0,0 +1,268 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_RUNTIME_CONST_H
+#define _ASM_RISCV_RUNTIME_CONST_H
+
+#include <asm/asm.h>
+#include <asm/alternative.h>
+#include <asm/cacheflush.h>
+#include <asm/insn-def.h>
+#include <linux/memory.h>
+#include <asm/text-patching.h>
+
+#include <linux/uaccess.h>
+
+#ifdef CONFIG_32BIT
+#define runtime_const_ptr(sym) \
+({ \
+ typeof(sym) __ret; \
+ asm_inline(".option push\n\t" \
+ ".option norvc\n\t" \
+ "1:\t" \
+ "lui %[__ret],0x89abd\n\t" \
+ "addi %[__ret],%[__ret],-0x211\n\t" \
+ ".option pop\n\t" \
+ ".pushsection runtime_ptr_" #sym ",\"a\"\n\t" \
+ ".long 1b - .\n\t" \
+ ".popsection" \
+ : [__ret] "=r" (__ret)); \
+ __ret; \
+})
+#else
+/*
+ * Loading 64-bit constants into a register from immediates is a non-trivial
+ * task on riscv64. To get it somewhat performant, load 32 bits into two
+ * different registers and then combine the results.
+ *
+ * If the processor supports the Zbkb extension, we can combine the final
+ * "slli,slli,srli,add" into the single "pack" instruction. If the processor
+ * doesn't support Zbkb but does support the Zbb extension, we can
+ * combine the final "slli,srli,add" into one instruction "add.uw".
+ */
+#define RISCV_RUNTIME_CONST_64_PREAMBLE \
+ ".option push\n\t" \
+ ".option norvc\n\t" \
+ "1:\t" \
+ "lui %[__ret],0x89abd\n\t" \
+ "lui %[__tmp],0x1234\n\t" \
+ "addiw %[__ret],%[__ret],-0x211\n\t" \
+ "addiw %[__tmp],%[__tmp],0x567\n\t" \
+
+#define RISCV_RUNTIME_CONST_64_BASE \
+ "slli %[__tmp],%[__tmp],32\n\t" \
+ "slli %[__ret],%[__ret],32\n\t" \
+ "srli %[__ret],%[__ret],32\n\t" \
+ "add %[__ret],%[__ret],%[__tmp]\n\t" \
+
+#define RISCV_RUNTIME_CONST_64_ZBA \
+ ".option push\n\t" \
+ ".option arch,+zba\n\t" \
+ ".option norvc\n\t" \
+ "slli %[__tmp],%[__tmp],32\n\t" \
+ "add.uw %[__ret],%[__ret],%[__tmp]\n\t" \
+ "nop\n\t" \
+ "nop\n\t" \
+ ".option pop\n\t" \
+
+#define RISCV_RUNTIME_CONST_64_ZBKB \
+ ".option push\n\t" \
+ ".option arch,+zbkb\n\t" \
+ ".option norvc\n\t" \
+ "pack %[__ret],%[__ret],%[__tmp]\n\t" \
+ "nop\n\t" \
+ "nop\n\t" \
+ "nop\n\t" \
+ ".option pop\n\t" \
+
+#define RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \
+ ".option pop\n\t" \
+ ".pushsection runtime_ptr_" #sym ",\"a\"\n\t" \
+ ".long 1b - .\n\t" \
+ ".popsection" \
+
+#if defined(CONFIG_RISCV_ISA_ZBA) && defined(CONFIG_TOOLCHAIN_HAS_ZBA) \
+ && defined(CONFIG_RISCV_ISA_ZBKB)
+#define runtime_const_ptr(sym) \
+({ \
+ typeof(sym) __ret, __tmp; \
+ asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE \
+ ALTERNATIVE_2( \
+ RISCV_RUNTIME_CONST_64_BASE, \
+ RISCV_RUNTIME_CONST_64_ZBA, \
+ 0, RISCV_ISA_EXT_ZBA, 1, \
+ RISCV_RUNTIME_CONST_64_ZBKB, \
+ 0, RISCV_ISA_EXT_ZBKB, 1 \
+ ) \
+ RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \
+ : [__ret] "=r" (__ret), [__tmp] "=r" (__tmp)); \
+ __ret; \
+})
+#elif defined(CONFIG_RISCV_ISA_ZBA) && defined(CONFIG_TOOLCHAIN_HAS_ZBA)
+#define runtime_const_ptr(sym) \
+({ \
+ typeof(sym) __ret, __tmp; \
+ asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE \
+ ALTERNATIVE( \
+ RISCV_RUNTIME_CONST_64_BASE, \
+ RISCV_RUNTIME_CONST_64_ZBA, \
+ 0, RISCV_ISA_EXT_ZBA, 1 \
+ ) \
+ RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \
+ : [__ret] "=r" (__ret), [__tmp] "=r" (__tmp)); \
+ __ret; \
+})
+#elif defined(CONFIG_RISCV_ISA_ZBKB)
+#define runtime_const_ptr(sym) \
+({ \
+ typeof(sym) __ret, __tmp; \
+ asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE \
+ ALTERNATIVE( \
+ RISCV_RUNTIME_CONST_64_BASE, \
+ RISCV_RUNTIME_CONST_64_ZBKB, \
+ 0, RISCV_ISA_EXT_ZBKB, 1 \
+ ) \
+ RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \
+ : [__ret] "=r" (__ret), [__tmp] "=r" (__tmp)); \
+ __ret; \
+})
+#else
+#define runtime_const_ptr(sym) \
+({ \
+ typeof(sym) __ret, __tmp; \
+ asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE \
+ RISCV_RUNTIME_CONST_64_BASE \
+ RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \
+ : [__ret] "=r" (__ret), [__tmp] "=r" (__tmp)); \
+ __ret; \
+})
+#endif
+#endif
+
+#define runtime_const_shift_right_32(val, sym) \
+({ \
+ u32 __ret; \
+ asm_inline(".option push\n\t" \
+ ".option norvc\n\t" \
+ "1:\t" \
+ SRLI " %[__ret],%[__val],12\n\t" \
+ ".option pop\n\t" \
+ ".pushsection runtime_shift_" #sym ",\"a\"\n\t" \
+ ".long 1b - .\n\t" \
+ ".popsection" \
+ : [__ret] "=r" (__ret) \
+ : [__val] "r" (val)); \
+ __ret; \
+})
+
+#define runtime_const_init(type, sym) do { \
+ extern s32 __start_runtime_##type##_##sym[]; \
+ extern s32 __stop_runtime_##type##_##sym[]; \
+ \
+ runtime_const_fixup(__runtime_fixup_##type, \
+ (unsigned long)(sym), \
+ __start_runtime_##type##_##sym, \
+ __stop_runtime_##type##_##sym); \
+} while (0)
+
+static inline void __runtime_fixup_caches(void *where, unsigned int insns)
+{
+ /* On riscv there are currently only cache-wide flushes so va is ignored. */
+ __always_unused uintptr_t va = (uintptr_t)where;
+
+ flush_icache_range(va, va + 4 * insns);
+}
+
+/*
+ * The 32-bit immediate is stored in a lui+addi pairing.
+ * lui holds the upper 20 bits of the immediate in the first 20 bits of the instruction.
+ * addi holds the lower 12 bits of the immediate in the first 12 bits of the instruction.
+ */
+static inline void __runtime_fixup_32(__le16 *lui_parcel, __le16 *addi_parcel, unsigned int val)
+{
+ unsigned int lower_immediate, upper_immediate;
+ u32 lui_insn, addi_insn, addi_insn_mask;
+ __le32 lui_res, addi_res;
+
+ /* Mask out upper 12 bit of addi */
+ addi_insn_mask = 0x000fffff;
+
+ lui_insn = (u32)le16_to_cpu(lui_parcel[0]) | (u32)le16_to_cpu(lui_parcel[1]) << 16;
+ addi_insn = (u32)le16_to_cpu(addi_parcel[0]) | (u32)le16_to_cpu(addi_parcel[1]) << 16;
+
+ lower_immediate = sign_extend32(val, 11);
+ upper_immediate = (val - lower_immediate);
+
+ if (upper_immediate & 0xfffff000) {
+ /* replace upper 20 bits of lui with upper immediate */
+ lui_insn &= 0x00000fff;
+ lui_insn |= upper_immediate & 0xfffff000;
+ } else {
+ /* replace lui with nop if immediate is small enough to fit in addi */
+ lui_insn = RISCV_INSN_NOP4;
+ /*
+ * lui is being skipped, so do a load instead of an add. A load
+ * is performed by adding with the x0 register. Setting rs to
+ * zero with the following mask will accomplish this goal.
+ */
+ addi_insn_mask &= 0x07fff;
+ }
+
+ if (lower_immediate & 0x00000fff) {
+ /* replace upper 12 bits of addi with lower 12 bits of val */
+ addi_insn &= addi_insn_mask;
+ addi_insn |= (lower_immediate & 0x00000fff) << 20;
+ } else {
+ /* replace addi with nop if lower_immediate is empty */
+ addi_insn = RISCV_INSN_NOP4;
+ }
+
+ addi_res = cpu_to_le32(addi_insn);
+ lui_res = cpu_to_le32(lui_insn);
+ mutex_lock(&text_mutex);
+ patch_insn_write(addi_parcel, &addi_res, sizeof(addi_res));
+ patch_insn_write(lui_parcel, &lui_res, sizeof(lui_res));
+ mutex_unlock(&text_mutex);
+}
+
+static inline void __runtime_fixup_ptr(void *where, unsigned long val)
+{
+#ifdef CONFIG_32BIT
+ __runtime_fixup_32(where, where + 4, val);
+ __runtime_fixup_caches(where, 2);
+#else
+ __runtime_fixup_32(where, where + 8, val);
+ __runtime_fixup_32(where + 4, where + 12, val >> 32);
+ __runtime_fixup_caches(where, 4);
+#endif
+}
+
+/*
+ * Replace the least significant 5 bits of the srli/srliw immediate that is
+ * located at bits 20-24
+ */
+static inline void __runtime_fixup_shift(void *where, unsigned long val)
+{
+ __le16 *parcel = where;
+ __le32 res;
+ u32 insn;
+
+ insn = (u32)le16_to_cpu(parcel[0]) | (u32)le16_to_cpu(parcel[1]) << 16;
+
+ insn &= 0xfe0fffff;
+ insn |= (val & 0b11111) << 20;
+
+ res = cpu_to_le32(insn);
+ mutex_lock(&text_mutex);
+ patch_text_nosync(where, &res, sizeof(insn));
+ mutex_unlock(&text_mutex);
+}
+
+static inline void runtime_const_fixup(void (*fn)(void *, unsigned long),
+ unsigned long val, s32 *start, s32 *end)
+{
+ while (start < end) {
+ fn(*start + (void *)start, val);
+ start++;
+ }
+}
+
+#endif /* _ASM_RISCV_RUNTIME_CONST_H */
diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
index 9e3c2cf1edaf..341e74238aa0 100644
--- a/arch/riscv/include/asm/sbi.h
+++ b/arch/riscv/include/asm/sbi.h
@@ -9,6 +9,7 @@
#include <linux/types.h>
#include <linux/cpumask.h>
+#include <linux/jump_label.h>
#ifdef CONFIG_RISCV_SBI
enum sbi_ext_id {
@@ -29,7 +30,12 @@ enum sbi_ext_id {
SBI_EXT_RFENCE = 0x52464E43,
SBI_EXT_HSM = 0x48534D,
SBI_EXT_SRST = 0x53525354,
+ SBI_EXT_SUSP = 0x53555350,
SBI_EXT_PMU = 0x504D55,
+ SBI_EXT_DBCN = 0x4442434E,
+ SBI_EXT_STA = 0x535441,
+ SBI_EXT_NACL = 0x4E41434C,
+ SBI_EXT_FWFT = 0x46574654,
/* Experimentals extensions must lie within this range */
SBI_EXT_EXPERIMENTAL_START = 0x08000000,
@@ -113,6 +119,14 @@ enum sbi_srst_reset_reason {
SBI_SRST_RESET_REASON_SYS_FAILURE,
};
+enum sbi_ext_susp_fid {
+ SBI_EXT_SUSP_SYSTEM_SUSPEND = 0,
+};
+
+enum sbi_ext_susp_sleep_type {
+ SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM = 0,
+};
+
enum sbi_ext_pmu_fid {
SBI_EXT_PMU_NUM_COUNTERS = 0,
SBI_EXT_PMU_COUNTER_GET_INFO,
@@ -120,10 +134,35 @@ enum sbi_ext_pmu_fid {
SBI_EXT_PMU_COUNTER_START,
SBI_EXT_PMU_COUNTER_STOP,
SBI_EXT_PMU_COUNTER_FW_READ,
+ SBI_EXT_PMU_COUNTER_FW_READ_HI,
+ SBI_EXT_PMU_SNAPSHOT_SET_SHMEM,
};
-#define RISCV_PMU_RAW_EVENT_MASK GENMASK_ULL(55, 0)
+union sbi_pmu_ctr_info {
+ unsigned long value;
+ struct {
+ unsigned long csr:12;
+ unsigned long width:6;
+#if __riscv_xlen == 32
+ unsigned long reserved:13;
+#else
+ unsigned long reserved:45;
+#endif
+ unsigned long type:1;
+ };
+};
+
+/* Data structure to contain the pmu snapshot data */
+struct riscv_pmu_snapshot_data {
+ u64 ctr_overflow_mask;
+ u64 ctr_values[64];
+ u64 reserved[447];
+};
+
+#define RISCV_PMU_RAW_EVENT_MASK GENMASK_ULL(47, 0)
+#define RISCV_PMU_PLAT_FW_EVENT_MASK GENMASK_ULL(61, 0)
#define RISCV_PMU_RAW_EVENT_IDX 0x20000
+#define RISCV_PLAT_FW_EVENT 0xFFFF
/** General pmu event codes specified in SBI PMU extension */
enum sbi_pmu_hw_generic_events_t {
@@ -155,9 +194,9 @@ enum sbi_pmu_fw_generic_events_t {
SBI_PMU_FW_ILLEGAL_INSN = 4,
SBI_PMU_FW_SET_TIMER = 5,
SBI_PMU_FW_IPI_SENT = 6,
- SBI_PMU_FW_IPI_RECVD = 7,
+ SBI_PMU_FW_IPI_RCVD = 7,
SBI_PMU_FW_FENCE_I_SENT = 8,
- SBI_PMU_FW_FENCE_I_RECVD = 9,
+ SBI_PMU_FW_FENCE_I_RCVD = 9,
SBI_PMU_FW_SFENCE_VMA_SENT = 10,
SBI_PMU_FW_SFENCE_VMA_RCVD = 11,
SBI_PMU_FW_SFENCE_VMA_ASID_SENT = 12,
@@ -189,22 +228,209 @@ enum sbi_pmu_ctr_type {
SBI_PMU_CTR_TYPE_FW,
};
+/* Helper macros to decode event idx */
+#define SBI_PMU_EVENT_IDX_OFFSET 20
+#define SBI_PMU_EVENT_IDX_MASK 0xFFFFF
+#define SBI_PMU_EVENT_IDX_CODE_MASK 0xFFFF
+#define SBI_PMU_EVENT_IDX_TYPE_MASK 0xF0000
+#define SBI_PMU_EVENT_RAW_IDX 0x20000
+#define SBI_PMU_FIXED_CTR_MASK 0x07
+
+#define SBI_PMU_EVENT_CACHE_ID_CODE_MASK 0xFFF8
+#define SBI_PMU_EVENT_CACHE_OP_ID_CODE_MASK 0x06
+#define SBI_PMU_EVENT_CACHE_RESULT_ID_CODE_MASK 0x01
+
+#define SBI_PMU_EVENT_CACHE_ID_SHIFT 3
+#define SBI_PMU_EVENT_CACHE_OP_SHIFT 1
+
+#define SBI_PMU_EVENT_IDX_INVALID 0xFFFFFFFF
+
/* Flags defined for config matching function */
-#define SBI_PMU_CFG_FLAG_SKIP_MATCH (1 << 0)
-#define SBI_PMU_CFG_FLAG_CLEAR_VALUE (1 << 1)
-#define SBI_PMU_CFG_FLAG_AUTO_START (1 << 2)
-#define SBI_PMU_CFG_FLAG_SET_VUINH (1 << 3)
-#define SBI_PMU_CFG_FLAG_SET_VSNH (1 << 4)
-#define SBI_PMU_CFG_FLAG_SET_UINH (1 << 5)
-#define SBI_PMU_CFG_FLAG_SET_SINH (1 << 6)
-#define SBI_PMU_CFG_FLAG_SET_MINH (1 << 7)
+#define SBI_PMU_CFG_FLAG_SKIP_MATCH BIT(0)
+#define SBI_PMU_CFG_FLAG_CLEAR_VALUE BIT(1)
+#define SBI_PMU_CFG_FLAG_AUTO_START BIT(2)
+#define SBI_PMU_CFG_FLAG_SET_VUINH BIT(3)
+#define SBI_PMU_CFG_FLAG_SET_VSINH BIT(4)
+#define SBI_PMU_CFG_FLAG_SET_UINH BIT(5)
+#define SBI_PMU_CFG_FLAG_SET_SINH BIT(6)
+#define SBI_PMU_CFG_FLAG_SET_MINH BIT(7)
/* Flags defined for counter start function */
-#define SBI_PMU_START_FLAG_SET_INIT_VALUE (1 << 0)
+#define SBI_PMU_START_FLAG_SET_INIT_VALUE BIT(0)
+#define SBI_PMU_START_FLAG_INIT_SNAPSHOT BIT(1)
/* Flags defined for counter stop function */
-#define SBI_PMU_STOP_FLAG_RESET (1 << 0)
+#define SBI_PMU_STOP_FLAG_RESET BIT(0)
+#define SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT BIT(1)
+
+enum sbi_ext_dbcn_fid {
+ SBI_EXT_DBCN_CONSOLE_WRITE = 0,
+ SBI_EXT_DBCN_CONSOLE_READ = 1,
+ SBI_EXT_DBCN_CONSOLE_WRITE_BYTE = 2,
+};
+
+/* SBI STA (steal-time accounting) extension */
+enum sbi_ext_sta_fid {
+ SBI_EXT_STA_STEAL_TIME_SET_SHMEM = 0,
+};
+
+struct sbi_sta_struct {
+ __le32 sequence;
+ __le32 flags;
+ __le64 steal;
+ u8 preempted;
+ u8 pad[47];
+} __packed;
+
+#define SBI_SHMEM_DISABLE -1
+
+enum sbi_ext_nacl_fid {
+ SBI_EXT_NACL_PROBE_FEATURE = 0x0,
+ SBI_EXT_NACL_SET_SHMEM = 0x1,
+ SBI_EXT_NACL_SYNC_CSR = 0x2,
+ SBI_EXT_NACL_SYNC_HFENCE = 0x3,
+ SBI_EXT_NACL_SYNC_SRET = 0x4,
+};
+
+enum sbi_ext_nacl_feature {
+ SBI_NACL_FEAT_SYNC_CSR = 0x0,
+ SBI_NACL_FEAT_SYNC_HFENCE = 0x1,
+ SBI_NACL_FEAT_SYNC_SRET = 0x2,
+ SBI_NACL_FEAT_AUTOSWAP_CSR = 0x3,
+};
+#define SBI_NACL_SHMEM_ADDR_SHIFT 12
+#define SBI_NACL_SHMEM_SCRATCH_OFFSET 0x0000
+#define SBI_NACL_SHMEM_SCRATCH_SIZE 0x1000
+#define SBI_NACL_SHMEM_SRET_OFFSET 0x0000
+#define SBI_NACL_SHMEM_SRET_SIZE 0x0200
+#define SBI_NACL_SHMEM_AUTOSWAP_OFFSET (SBI_NACL_SHMEM_SRET_OFFSET + \
+ SBI_NACL_SHMEM_SRET_SIZE)
+#define SBI_NACL_SHMEM_AUTOSWAP_SIZE 0x0080
+#define SBI_NACL_SHMEM_UNUSED_OFFSET (SBI_NACL_SHMEM_AUTOSWAP_OFFSET + \
+ SBI_NACL_SHMEM_AUTOSWAP_SIZE)
+#define SBI_NACL_SHMEM_UNUSED_SIZE 0x0580
+#define SBI_NACL_SHMEM_HFENCE_OFFSET (SBI_NACL_SHMEM_UNUSED_OFFSET + \
+ SBI_NACL_SHMEM_UNUSED_SIZE)
+#define SBI_NACL_SHMEM_HFENCE_SIZE 0x0780
+#define SBI_NACL_SHMEM_DBITMAP_OFFSET (SBI_NACL_SHMEM_HFENCE_OFFSET + \
+ SBI_NACL_SHMEM_HFENCE_SIZE)
+#define SBI_NACL_SHMEM_DBITMAP_SIZE 0x0080
+#define SBI_NACL_SHMEM_CSR_OFFSET (SBI_NACL_SHMEM_DBITMAP_OFFSET + \
+ SBI_NACL_SHMEM_DBITMAP_SIZE)
+#define SBI_NACL_SHMEM_CSR_SIZE ((__riscv_xlen / 8) * 1024)
+#define SBI_NACL_SHMEM_SIZE (SBI_NACL_SHMEM_CSR_OFFSET + \
+ SBI_NACL_SHMEM_CSR_SIZE)
+
+#define SBI_NACL_SHMEM_CSR_INDEX(__csr_num) \
+ ((((__csr_num) & 0xc00) >> 2) | ((__csr_num) & 0xff))
+
+#define SBI_NACL_SHMEM_HFENCE_ENTRY_SZ ((__riscv_xlen / 8) * 4)
+#define SBI_NACL_SHMEM_HFENCE_ENTRY_MAX \
+ (SBI_NACL_SHMEM_HFENCE_SIZE / \
+ SBI_NACL_SHMEM_HFENCE_ENTRY_SZ)
+#define SBI_NACL_SHMEM_HFENCE_ENTRY(__num) \
+ (SBI_NACL_SHMEM_HFENCE_OFFSET + \
+ (__num) * SBI_NACL_SHMEM_HFENCE_ENTRY_SZ)
+#define SBI_NACL_SHMEM_HFENCE_ENTRY_CONFIG(__num) \
+ SBI_NACL_SHMEM_HFENCE_ENTRY(__num)
+#define SBI_NACL_SHMEM_HFENCE_ENTRY_PNUM(__num)\
+ (SBI_NACL_SHMEM_HFENCE_ENTRY(__num) + (__riscv_xlen / 8))
+#define SBI_NACL_SHMEM_HFENCE_ENTRY_PCOUNT(__num)\
+ (SBI_NACL_SHMEM_HFENCE_ENTRY(__num) + \
+ ((__riscv_xlen / 8) * 3))
+
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_BITS 1
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_SHIFT \
+ (__riscv_xlen - SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_BITS)
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_MASK \
+ ((1UL << SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_BITS) - 1)
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_PEND \
+ (SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_MASK << \
+ SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_SHIFT)
+
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD1_BITS 3
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD1_SHIFT \
+ (SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_SHIFT - \
+ SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD1_BITS)
+
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_BITS 4
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_SHIFT \
+ (SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD1_SHIFT - \
+ SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_BITS)
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_MASK \
+ ((1UL << SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_BITS) - 1)
+
+#define SBI_NACL_SHMEM_HFENCE_TYPE_GVMA 0x0
+#define SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_ALL 0x1
+#define SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_VMID 0x2
+#define SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_VMID_ALL 0x3
+#define SBI_NACL_SHMEM_HFENCE_TYPE_VVMA 0x4
+#define SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ALL 0x5
+#define SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ASID 0x6
+#define SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ASID_ALL 0x7
+
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD2_BITS 1
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD2_SHIFT \
+ (SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_SHIFT - \
+ SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD2_BITS)
+
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_BITS 7
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_SHIFT \
+ (SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD2_SHIFT - \
+ SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_BITS)
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_MASK \
+ ((1UL << SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_BITS) - 1)
+#define SBI_NACL_SHMEM_HFENCE_ORDER_BASE 12
+
+#if __riscv_xlen == 32
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_BITS 9
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_BITS 7
+#else
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_BITS 16
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_BITS 14
+#endif
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_SHIFT \
+ SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_BITS
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_MASK \
+ ((1UL << SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_BITS) - 1)
+#define SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_MASK \
+ ((1UL << SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_BITS) - 1)
+
+#define SBI_NACL_SHMEM_AUTOSWAP_FLAG_HSTATUS BIT(0)
+#define SBI_NACL_SHMEM_AUTOSWAP_HSTATUS ((__riscv_xlen / 8) * 1)
+
+#define SBI_NACL_SHMEM_SRET_X(__i) ((__riscv_xlen / 8) * (__i))
+#define SBI_NACL_SHMEM_SRET_X_LAST 31
+
+/* SBI function IDs for FW feature extension */
+#define SBI_EXT_FWFT_SET 0x0
+#define SBI_EXT_FWFT_GET 0x1
+
+enum sbi_fwft_feature_t {
+ SBI_FWFT_MISALIGNED_EXC_DELEG = 0x0,
+ SBI_FWFT_LANDING_PAD = 0x1,
+ SBI_FWFT_SHADOW_STACK = 0x2,
+ SBI_FWFT_DOUBLE_TRAP = 0x3,
+ SBI_FWFT_PTE_AD_HW_UPDATING = 0x4,
+ SBI_FWFT_POINTER_MASKING_PMLEN = 0x5,
+ SBI_FWFT_LOCAL_RESERVED_START = 0x6,
+ SBI_FWFT_LOCAL_RESERVED_END = 0x3fffffff,
+ SBI_FWFT_LOCAL_PLATFORM_START = 0x40000000,
+ SBI_FWFT_LOCAL_PLATFORM_END = 0x7fffffff,
+
+ SBI_FWFT_GLOBAL_RESERVED_START = 0x80000000,
+ SBI_FWFT_GLOBAL_RESERVED_END = 0xbfffffff,
+ SBI_FWFT_GLOBAL_PLATFORM_START = 0xc0000000,
+ SBI_FWFT_GLOBAL_PLATFORM_END = 0xffffffff,
+};
+
+#define SBI_FWFT_PLATFORM_FEATURE_BIT BIT(30)
+#define SBI_FWFT_GLOBAL_FEATURE_BIT BIT(31)
+
+#define SBI_FWFT_SET_FLAG_LOCK BIT(0)
+
+/* SBI spec version fields */
#define SBI_SPEC_VERSION_DEFAULT 0x1
#define SBI_SPEC_VERSION_MAJOR_SHIFT 24
#define SBI_SPEC_VERSION_MAJOR_MASK 0x7f
@@ -220,6 +446,12 @@ enum sbi_pmu_ctr_type {
#define SBI_ERR_ALREADY_AVAILABLE -6
#define SBI_ERR_ALREADY_STARTED -7
#define SBI_ERR_ALREADY_STOPPED -8
+#define SBI_ERR_NO_SHMEM -9
+#define SBI_ERR_INVALID_STATE -10
+#define SBI_ERR_BAD_RANGE -11
+#define SBI_ERR_TIMEOUT -12
+#define SBI_ERR_IO -13
+#define SBI_ERR_DENIED_LOCKED -14
extern unsigned long sbi_spec_version;
struct sbiret {
@@ -228,24 +460,28 @@ struct sbiret {
};
void sbi_init(void);
-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);
+long __sbi_base_ecall(int fid);
+struct sbiret __sbi_ecall(unsigned long arg0, unsigned long arg1,
+ unsigned long arg2, unsigned long arg3,
+ unsigned long arg4, unsigned long arg5,
+ int fid, int ext);
+#define sbi_ecall(e, f, a0, a1, a2, a3, a4, a5) \
+ __sbi_ecall(a0, a1, a2, a3, a4, a5, f, e)
+#ifdef CONFIG_RISCV_SBI_V01
void sbi_console_putchar(int ch);
int sbi_console_getchar(void);
+#else
+static inline void sbi_console_putchar(int ch) { }
+static inline int sbi_console_getchar(void) { return -ENOENT; }
+#endif
long sbi_get_mvendorid(void);
long sbi_get_marchid(void);
long sbi_get_mimpid(void);
void sbi_set_timer(uint64_t stime_value);
void sbi_shutdown(void);
-void sbi_clear_ipi(void);
-int sbi_send_ipi(const struct cpumask *cpu_mask);
+void sbi_send_ipi(unsigned int cpu);
int sbi_remote_fence_i(const struct cpumask *cpu_mask);
-int sbi_remote_sfence_vma(const struct cpumask *cpu_mask,
- unsigned long start,
- unsigned long size);
int sbi_remote_sfence_vma_asid(const struct cpumask *cpu_mask,
unsigned long start,
@@ -265,7 +501,24 @@ int sbi_remote_hfence_vvma_asid(const struct cpumask *cpu_mask,
unsigned long start,
unsigned long size,
unsigned long asid);
-int sbi_probe_extension(int ext);
+long sbi_probe_extension(int ext);
+
+int sbi_fwft_set(u32 feature, unsigned long value, unsigned long flags);
+int sbi_fwft_set_cpumask(const cpumask_t *mask, u32 feature,
+ unsigned long value, unsigned long flags);
+/**
+ * sbi_fwft_set_online_cpus() - Set a feature on all online cpus
+ * @feature: The feature to be set
+ * @value: The feature value to be set
+ * @flags: FWFT feature set flags
+ *
+ * Return: 0 on success, appropriate linux error code otherwise.
+ */
+static inline int sbi_fwft_set_online_cpus(u32 feature, unsigned long value,
+ unsigned long flags)
+{
+ return sbi_fwft_set_cpumask(cpu_online_mask, feature, value, flags);
+}
/* Check if current SBI specification version is 0.1 or not */
static inline int sbi_spec_is_0_1(void)
@@ -290,13 +543,61 @@ static inline unsigned long sbi_minor_version(void)
static inline unsigned long sbi_mk_version(unsigned long major,
unsigned long minor)
{
- return ((major & SBI_SPEC_VERSION_MAJOR_MASK) <<
- SBI_SPEC_VERSION_MAJOR_SHIFT) | minor;
+ return ((major & SBI_SPEC_VERSION_MAJOR_MASK) << SBI_SPEC_VERSION_MAJOR_SHIFT)
+ | (minor & SBI_SPEC_VERSION_MINOR_MASK);
+}
+
+static inline int sbi_err_map_linux_errno(int err)
+{
+ switch (err) {
+ case SBI_SUCCESS:
+ return 0;
+ case SBI_ERR_DENIED:
+ case SBI_ERR_DENIED_LOCKED:
+ return -EPERM;
+ case SBI_ERR_INVALID_PARAM:
+ case SBI_ERR_INVALID_STATE:
+ return -EINVAL;
+ case SBI_ERR_BAD_RANGE:
+ return -ERANGE;
+ case SBI_ERR_INVALID_ADDRESS:
+ return -EFAULT;
+ case SBI_ERR_NO_SHMEM:
+ return -ENOMEM;
+ case SBI_ERR_TIMEOUT:
+ return -ETIMEDOUT;
+ case SBI_ERR_IO:
+ return -EIO;
+ case SBI_ERR_NOT_SUPPORTED:
+ case SBI_ERR_FAILURE:
+ default:
+ return -ENOTSUPP;
+ };
}
-int sbi_err_map_linux_errno(int err);
+extern bool sbi_debug_console_available;
+int sbi_debug_console_write(const char *bytes, unsigned int num_bytes);
+int sbi_debug_console_read(char *bytes, unsigned int num_bytes);
+
#else /* CONFIG_RISCV_SBI */
static inline int sbi_remote_fence_i(const struct cpumask *cpu_mask) { return -1; }
static inline void sbi_init(void) {}
#endif /* CONFIG_RISCV_SBI */
+
+unsigned long riscv_get_mvendorid(void);
+unsigned long riscv_get_marchid(void);
+unsigned long riscv_cached_mvendorid(unsigned int cpu_id);
+unsigned long riscv_cached_marchid(unsigned int cpu_id);
+unsigned long riscv_cached_mimpid(unsigned int cpu_id);
+
+#if IS_ENABLED(CONFIG_SMP) && IS_ENABLED(CONFIG_RISCV_SBI)
+DECLARE_STATIC_KEY_FALSE(riscv_sbi_for_rfence);
+#define riscv_use_sbi_for_rfence() \
+ static_branch_unlikely(&riscv_sbi_for_rfence)
+void sbi_ipi_init(void);
+#else
+static inline bool riscv_use_sbi_for_rfence(void) { return false; }
+static inline void sbi_ipi_init(void) { }
+#endif
+
#endif /* _ASM_RISCV_SBI_H */
diff --git a/arch/riscv/include/asm/scs.h b/arch/riscv/include/asm/scs.h
new file mode 100644
index 000000000000..0e45db78b24b
--- /dev/null
+++ b/arch/riscv/include/asm/scs.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_SCS_H
+#define _ASM_SCS_H
+
+#ifdef __ASSEMBLY__
+#include <asm/asm-offsets.h>
+
+#ifdef CONFIG_SHADOW_CALL_STACK
+
+/* Load init_shadow_call_stack to gp. */
+.macro scs_load_init_stack
+ la gp, init_shadow_call_stack
+ XIP_FIXUP_OFFSET gp
+.endm
+
+/* Load the per-CPU IRQ shadow call stack to gp. */
+.macro scs_load_irq_stack tmp
+ load_per_cpu gp, irq_shadow_call_stack_ptr, \tmp
+.endm
+
+/* Load task_scs_sp(current) to gp. */
+.macro scs_load_current
+ REG_L gp, TASK_TI_SCS_SP(tp)
+.endm
+
+/* Load task_scs_sp(current) to gp, but only if tp has changed. */
+.macro scs_load_current_if_task_changed prev
+ beq \prev, tp, _skip_scs
+ scs_load_current
+_skip_scs:
+.endm
+
+/* Save gp to task_scs_sp(current). */
+.macro scs_save_current
+ REG_S gp, TASK_TI_SCS_SP(tp)
+.endm
+
+#else /* CONFIG_SHADOW_CALL_STACK */
+
+.macro scs_load_init_stack
+.endm
+.macro scs_load_irq_stack tmp
+.endm
+.macro scs_load_current
+.endm
+.macro scs_load_current_if_task_changed prev
+.endm
+.macro scs_save_current
+.endm
+
+#endif /* CONFIG_SHADOW_CALL_STACK */
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_SCS_H */
diff --git a/arch/riscv/include/asm/sections.h b/arch/riscv/include/asm/sections.h
index 32336e8a17cb..a393d5035c54 100644
--- a/arch/riscv/include/asm/sections.h
+++ b/arch/riscv/include/asm/sections.h
@@ -13,6 +13,7 @@ extern char _start_kernel[];
extern char __init_data_begin[], __init_data_end[];
extern char __init_text_begin[], __init_text_end[];
extern char __alt_start[], __alt_end[];
+extern char __exittext_begin[], __exittext_end[];
static inline bool is_va_kernel_text(uintptr_t va)
{
diff --git a/arch/riscv/include/asm/semihost.h b/arch/riscv/include/asm/semihost.h
new file mode 100644
index 000000000000..557a34938193
--- /dev/null
+++ b/arch/riscv/include/asm/semihost.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2022 tinylab.org
+ * Author: Bin Meng <bmeng@tinylab.org>
+ */
+
+#ifndef _RISCV_SEMIHOST_H_
+#define _RISCV_SEMIHOST_H_
+
+struct uart_port;
+
+static inline void smh_putc(struct uart_port *port, unsigned char c)
+{
+ asm volatile("addi a1, %0, 0\n"
+ "addi a0, zero, 3\n"
+ ".balign 16\n"
+ ".option push\n"
+ ".option norvc\n"
+ "slli zero, zero, 0x1f\n"
+ "ebreak\n"
+ "srai zero, zero, 0x7\n"
+ ".option pop\n"
+ : : "r" (&c) : "a0", "a1", "memory");
+}
+
+#endif /* _RISCV_SEMIHOST_H_ */
diff --git a/arch/riscv/include/asm/set_memory.h b/arch/riscv/include/asm/set_memory.h
index a2c14d4b3993..ea263d3683ef 100644
--- a/arch/riscv/include/asm/set_memory.h
+++ b/arch/riscv/include/asm/set_memory.h
@@ -42,11 +42,12 @@ static inline int set_kernel_memory(char *startp, char *endp,
int set_direct_map_invalid_noflush(struct page *page);
int set_direct_map_default_noflush(struct page *page);
+int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid);
bool kernel_page_present(struct page *page);
#endif /* __ASSEMBLY__ */
-#ifdef CONFIG_STRICT_KERNEL_RWX
+#if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_XIP_KERNEL)
#ifdef CONFIG_64BIT
#define SECTION_ALIGN (1 << 21)
#else
@@ -56,4 +57,7 @@ bool kernel_page_present(struct page *page);
#define SECTION_ALIGN L1_CACHE_BYTES
#endif /* CONFIG_STRICT_KERNEL_RWX */
+#define PECOFF_SECTION_ALIGNMENT 0x1000
+#define PECOFF_FILE_ALIGNMENT 0x200
+
#endif /* _ASM_RISCV_SET_MEMORY_H */
diff --git a/arch/riscv/include/asm/simd.h b/arch/riscv/include/asm/simd.h
new file mode 100644
index 000000000000..adb50f3ec205
--- /dev/null
+++ b/arch/riscv/include/asm/simd.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2023 SiFive
+ */
+
+#ifndef __ASM_SIMD_H
+#define __ASM_SIMD_H
+
+#include <linux/compiler.h>
+#include <linux/irqflags.h>
+#include <linux/percpu.h>
+#include <linux/preempt.h>
+#include <linux/types.h>
+#include <linux/thread_info.h>
+
+#include <asm/vector.h>
+
+#ifdef CONFIG_RISCV_ISA_V
+/*
+ * may_use_simd - whether it is allowable at this time to issue vector
+ * instructions or access the vector register file
+ *
+ * Callers must not assume that the result remains true beyond the next
+ * preempt_enable() or return from softirq context.
+ */
+static __must_check inline bool may_use_simd(void)
+{
+ /*
+ * RISCV_KERNEL_MODE_V is only set while preemption is disabled,
+ * and is clear whenever preemption is enabled.
+ */
+ if (in_hardirq() || in_nmi())
+ return false;
+
+ /*
+ * Nesting is achieved in preempt_v by spreading the control for
+ * preemptible and non-preemptible kernel-mode Vector into two fields.
+ * Always try to match with preempt_v if kernel V-context exists. Then,
+ * fallback to check non preempt_v if nesting happens, or if the config
+ * is not set.
+ */
+ if (IS_ENABLED(CONFIG_RISCV_ISA_V_PREEMPTIVE) && current->thread.kernel_vstate.datap) {
+ if (!riscv_preempt_v_started(current))
+ return true;
+ }
+ /*
+ * Non-preemptible kernel-mode Vector temporarily disables bh. So we
+ * must not return true on irq_disabled(). Otherwise we would fail the
+ * lockdep check calling local_bh_enable()
+ */
+ return !irqs_disabled() && !(riscv_v_flags() & RISCV_KERNEL_MODE_V);
+}
+
+#else /* ! CONFIG_RISCV_ISA_V */
+
+static __must_check inline bool may_use_simd(void)
+{
+ return false;
+}
+
+#endif /* ! CONFIG_RISCV_ISA_V */
+
+#endif
diff --git a/arch/riscv/include/asm/smp.h b/arch/riscv/include/asm/smp.h
index 23170c933d73..7ac80e9f2288 100644
--- a/arch/riscv/include/asm/smp.h
+++ b/arch/riscv/include/asm/smp.h
@@ -15,12 +15,10 @@
struct seq_file;
extern unsigned long boot_cpu_hartid;
-struct riscv_ipi_ops {
- void (*ipi_inject)(const struct cpumask *target);
- void (*ipi_clear)(void);
-};
-
#ifdef CONFIG_SMP
+
+#include <linux/jump_label.h>
+
/*
* Mapping between linux logical cpu index and hartid.
*/
@@ -33,22 +31,28 @@ void show_ipi_stats(struct seq_file *p, int prec);
/* SMP initialization hook for setup_arch */
void __init setup_smp(void);
-/* Called from C code, this handles an IPI. */
-void handle_IPI(struct pt_regs *regs);
-
/* Hook for the generic smp_call_function_many() routine. */
void arch_send_call_function_ipi_mask(struct cpumask *mask);
/* Hook for the generic smp_call_function_single() routine. */
void arch_send_call_function_single_ipi(int cpu);
-int riscv_hartid_to_cpuid(int hartid);
+int riscv_hartid_to_cpuid(unsigned long hartid);
+
+/* Enable IPI for CPU hotplug */
+void riscv_ipi_enable(void);
+
+/* Disable IPI for CPU hotplug */
+void riscv_ipi_disable(void);
+
+/* Check if IPI interrupt numbers are available */
+bool riscv_ipi_have_virq_range(void);
-/* Set custom IPI operations */
-void riscv_set_ipi_ops(const struct riscv_ipi_ops *ops);
+/* Set the IPI interrupt numbers for arch (called by irqchip drivers) */
+void riscv_ipi_set_virq_range(int virq, int nr);
-/* Clear IPI for current CPU */
-void riscv_clear_ipi(void);
+/* Check other CPUs stop or not */
+bool smp_crash_stop_failed(void);
/* Secondary hart entry */
asmlinkage void smp_callin(void);
@@ -61,7 +65,7 @@ asmlinkage void smp_callin(void);
#if defined CONFIG_HOTPLUG_CPU
int __cpu_disable(void);
-void __cpu_die(unsigned int cpu);
+static inline void __cpu_die(unsigned int cpu) { }
#endif /* CONFIG_HOTPLUG_CPU */
#else
@@ -70,7 +74,7 @@ static inline void show_ipi_stats(struct seq_file *p, int prec)
{
}
-static inline int riscv_hartid_to_cpuid(int hartid)
+static inline int riscv_hartid_to_cpuid(unsigned long hartid)
{
if (hartid == boot_cpu_hartid)
return 0;
@@ -82,11 +86,20 @@ static inline unsigned long cpuid_to_hartid_map(int cpu)
return boot_cpu_hartid;
}
-static inline void riscv_set_ipi_ops(const struct riscv_ipi_ops *ops)
+static inline void riscv_ipi_enable(void)
{
}
-static inline void riscv_clear_ipi(void)
+static inline void riscv_ipi_disable(void)
+{
+}
+
+static inline bool riscv_ipi_have_virq_range(void)
+{
+ return false;
+}
+
+static inline void riscv_ipi_set_virq_range(int virq, int nr)
{
}
diff --git a/arch/riscv/include/asm/sparsemem.h b/arch/riscv/include/asm/sparsemem.h
index 63acaecc3374..2f901a410586 100644
--- a/arch/riscv/include/asm/sparsemem.h
+++ b/arch/riscv/include/asm/sparsemem.h
@@ -7,7 +7,7 @@
#ifdef CONFIG_64BIT
#define MAX_PHYSMEM_BITS 56
#else
-#define MAX_PHYSMEM_BITS 34
+#define MAX_PHYSMEM_BITS 32
#endif /* CONFIG_64BIT */
#define SECTION_SIZE_BITS 27
#endif /* CONFIG_SPARSEMEM */
diff --git a/arch/riscv/include/asm/spinlock.h b/arch/riscv/include/asm/spinlock.h
new file mode 100644
index 000000000000..52f11bfd0079
--- /dev/null
+++ b/arch/riscv/include/asm/spinlock.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_RISCV_SPINLOCK_H
+#define __ASM_RISCV_SPINLOCK_H
+
+#ifdef CONFIG_QUEUED_SPINLOCKS
+#define _Q_PENDING_LOOPS (1 << 9)
+#endif
+
+#ifdef CONFIG_RISCV_COMBO_SPINLOCKS
+
+#define __no_arch_spinlock_redefine
+#include <asm/ticket_spinlock.h>
+#include <asm/qspinlock.h>
+#include <asm/jump_label.h>
+
+/*
+ * TODO: Use an alternative instead of a static key when we are able to parse
+ * the extensions string earlier in the boot process.
+ */
+DECLARE_STATIC_KEY_TRUE(qspinlock_key);
+
+#define SPINLOCK_BASE_DECLARE(op, type, type_lock) \
+static __always_inline type arch_spin_##op(type_lock lock) \
+{ \
+ if (static_branch_unlikely(&qspinlock_key)) \
+ return queued_spin_##op(lock); \
+ return ticket_spin_##op(lock); \
+}
+
+SPINLOCK_BASE_DECLARE(lock, void, arch_spinlock_t *)
+SPINLOCK_BASE_DECLARE(unlock, void, arch_spinlock_t *)
+SPINLOCK_BASE_DECLARE(is_locked, int, arch_spinlock_t *)
+SPINLOCK_BASE_DECLARE(is_contended, int, arch_spinlock_t *)
+SPINLOCK_BASE_DECLARE(trylock, bool, arch_spinlock_t *)
+SPINLOCK_BASE_DECLARE(value_unlocked, int, arch_spinlock_t)
+
+#elif defined(CONFIG_RISCV_QUEUED_SPINLOCKS)
+
+#include <asm/qspinlock.h>
+
+#else
+
+#include <asm/ticket_spinlock.h>
+
+#endif
+
+#include <asm/qrwlock.h>
+
+#endif /* __ASM_RISCV_SPINLOCK_H */
diff --git a/arch/riscv/include/asm/stackprotector.h b/arch/riscv/include/asm/stackprotector.h
index 09093af46565..43895b90fe3f 100644
--- a/arch/riscv/include/asm/stackprotector.h
+++ b/arch/riscv/include/asm/stackprotector.h
@@ -3,9 +3,6 @@
#ifndef _ASM_RISCV_STACKPROTECTOR_H
#define _ASM_RISCV_STACKPROTECTOR_H
-#include <linux/random.h>
-#include <linux/version.h>
-
extern unsigned long __stack_chk_guard;
/*
@@ -16,12 +13,7 @@ extern unsigned long __stack_chk_guard;
*/
static __always_inline void boot_init_stack_canary(void)
{
- unsigned long canary;
-
- /* Try to get a semi random initial value. */
- get_random_bytes(&canary, sizeof(canary));
- canary ^= LINUX_VERSION_CODE;
- canary &= CANARY_MASK;
+ unsigned long canary = get_random_canary();
current->stack_canary = canary;
if (!IS_ENABLED(CONFIG_STACKPROTECTOR_PER_TASK))
diff --git a/arch/riscv/include/asm/stacktrace.h b/arch/riscv/include/asm/stacktrace.h
index 3450c1912afd..b1495a7e06ce 100644
--- a/arch/riscv/include/asm/stacktrace.h
+++ b/arch/riscv/include/asm/stacktrace.h
@@ -16,4 +16,14 @@ extern void notrace walk_stackframe(struct task_struct *task, struct pt_regs *re
extern void dump_backtrace(struct pt_regs *regs, struct task_struct *task,
const char *loglvl);
+static inline bool on_thread_stack(void)
+{
+ return !(((unsigned long)(current->stack) ^ current_stack_pointer) & ~(THREAD_SIZE - 1));
+}
+
+
+#ifdef CONFIG_VMAP_STACK
+DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack);
+#endif /* CONFIG_VMAP_STACK */
+
#endif /* _ASM_RISCV_STACKTRACE_H */
diff --git a/arch/riscv/include/asm/string.h b/arch/riscv/include/asm/string.h
index 909049366555..5ba77f60bf0b 100644
--- a/arch/riscv/include/asm/string.h
+++ b/arch/riscv/include/asm/string.h
@@ -18,6 +18,18 @@ extern asmlinkage void *__memcpy(void *, const void *, size_t);
#define __HAVE_ARCH_MEMMOVE
extern asmlinkage void *memmove(void *, const void *, size_t);
extern asmlinkage void *__memmove(void *, const void *, size_t);
+
+#if !(defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS))
+#define __HAVE_ARCH_STRCMP
+extern asmlinkage int strcmp(const char *cs, const char *ct);
+
+#define __HAVE_ARCH_STRLEN
+extern asmlinkage __kernel_size_t strlen(const char *);
+
+#define __HAVE_ARCH_STRNCMP
+extern asmlinkage int strncmp(const char *cs, const char *ct, size_t count);
+#endif
+
/* For those files which don't want to check by kasan. */
#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
#define memcpy(dst, src, len) __memcpy(dst, src, len)
diff --git a/arch/riscv/include/asm/suspend.h b/arch/riscv/include/asm/suspend.h
index 8be391c2aecb..dc5782b5fbad 100644
--- a/arch/riscv/include/asm/suspend.h
+++ b/arch/riscv/include/asm/suspend.h
@@ -13,14 +13,23 @@ struct suspend_context {
/* Saved and restored by low-level functions */
struct pt_regs regs;
/* Saved and restored by high-level functions */
- unsigned long scratch;
+ unsigned long envcfg;
unsigned long tvec;
unsigned long ie;
#ifdef CONFIG_MMU
unsigned long satp;
+ unsigned long stimecmp;
+#if __riscv_xlen < 64
+ unsigned long stimecmph;
+#endif
#endif
};
+/*
+ * Used by hibernation core and cleared during resume sequence
+ */
+extern int in_suspend;
+
/* Low-level CPU suspend entry function */
int __cpu_suspend_enter(struct suspend_context *context);
@@ -33,4 +42,24 @@ int cpu_suspend(unsigned long arg,
/* Low-level CPU resume entry function */
int __cpu_resume_enter(unsigned long hartid, unsigned long context);
+/* Used to save and restore the CSRs */
+void suspend_save_csrs(struct suspend_context *context);
+void suspend_restore_csrs(struct suspend_context *context);
+
+/* Low-level API to support hibernation */
+int swsusp_arch_suspend(void);
+int swsusp_arch_resume(void);
+int arch_hibernation_header_save(void *addr, unsigned int max_size);
+int arch_hibernation_header_restore(void *addr);
+int __hibernate_cpu_resume(void);
+
+/* Used to resume on the CPU we hibernated on */
+int hibernate_resume_nonboot_cpu_disable(void);
+
+asmlinkage void hibernate_restore_image(unsigned long resume_satp, unsigned long satp_temp,
+ unsigned long cpu_resume);
+asmlinkage int hibernate_core_restore_code(void);
+bool riscv_sbi_hsm_is_supported(void);
+bool riscv_sbi_suspend_state_is_valid(u32 state);
+int riscv_sbi_hart_suspend(u32 state);
#endif
diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index 0a3f4f95c555..0e71eb82f920 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -8,6 +8,9 @@
#include <linux/jump_label.h>
#include <linux/sched/task_stack.h>
+#include <linux/mm_types.h>
+#include <asm/vector.h>
+#include <asm/cpufeature.h>
#include <asm/processor.h>
#include <asm/ptrace.h>
#include <asm/csr.h>
@@ -45,38 +48,80 @@ static inline void fstate_restore(struct task_struct *task,
}
}
-static inline void __switch_to_aux(struct task_struct *prev,
+static inline void __switch_to_fpu(struct task_struct *prev,
struct task_struct *next)
{
struct pt_regs *regs;
regs = task_pt_regs(prev);
- if (unlikely(regs->status & SR_SD))
- fstate_save(prev, regs);
+ fstate_save(prev, regs);
fstate_restore(next, task_pt_regs(next));
}
-extern struct static_key_false cpu_hwcap_fpu;
static __always_inline bool has_fpu(void)
{
- return static_branch_likely(&cpu_hwcap_fpu);
+ return riscv_has_extension_likely(RISCV_ISA_EXT_f) ||
+ riscv_has_extension_likely(RISCV_ISA_EXT_d);
}
#else
static __always_inline bool has_fpu(void) { return false; }
#define fstate_save(task, regs) do { } while (0)
#define fstate_restore(task, regs) do { } while (0)
-#define __switch_to_aux(__prev, __next) do { } while (0)
+#define __switch_to_fpu(__prev, __next) do { } while (0)
#endif
+static inline void envcfg_update_bits(struct task_struct *task,
+ unsigned long mask, unsigned long val)
+{
+ unsigned long envcfg;
+
+ envcfg = (task->thread.envcfg & ~mask) | val;
+ task->thread.envcfg = envcfg;
+ if (task == current)
+ csr_write(CSR_ENVCFG, envcfg);
+}
+
+static inline void __switch_to_envcfg(struct task_struct *next)
+{
+ asm volatile (ALTERNATIVE("nop", "csrw " __stringify(CSR_ENVCFG) ", %0",
+ 0, RISCV_ISA_EXT_XLINUXENVCFG, 1)
+ :: "r" (next->thread.envcfg) : "memory");
+}
+
extern struct task_struct *__switch_to(struct task_struct *,
struct task_struct *);
+static inline bool switch_to_should_flush_icache(struct task_struct *task)
+{
+#ifdef CONFIG_SMP
+ bool stale_mm = task->mm && task->mm->context.force_icache_flush;
+ bool stale_thread = task->thread.force_icache_flush;
+ bool thread_migrated = smp_processor_id() != task->thread.prev_cpu;
+
+ return thread_migrated && (stale_mm || stale_thread);
+#else
+ return false;
+#endif
+}
+
+#ifdef CONFIG_SMP
+#define __set_prev_cpu(thread) ((thread).prev_cpu = smp_processor_id())
+#else
+#define __set_prev_cpu(thread)
+#endif
+
#define switch_to(prev, next, last) \
do { \
struct task_struct *__prev = (prev); \
struct task_struct *__next = (next); \
+ __set_prev_cpu(__prev->thread); \
if (has_fpu()) \
- __switch_to_aux(__prev, __next); \
+ __switch_to_fpu(__prev, __next); \
+ if (has_vector() || has_xtheadvector()) \
+ __switch_to_vector(__prev, __next); \
+ if (switch_to_should_flush_icache(__next)) \
+ local_flush_icache_all(); \
+ __switch_to_envcfg(__next); \
((last) = __switch_to(__prev, __next)); \
} while (0)
diff --git a/arch/riscv/include/asm/sync_core.h b/arch/riscv/include/asm/sync_core.h
new file mode 100644
index 000000000000..9153016da8f1
--- /dev/null
+++ b/arch/riscv/include/asm/sync_core.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_SYNC_CORE_H
+#define _ASM_RISCV_SYNC_CORE_H
+
+/*
+ * RISC-V implements return to user-space through an xRET instruction,
+ * which is not core serializing.
+ */
+static inline void sync_core_before_usermode(void)
+{
+ asm volatile ("fence.i" ::: "memory");
+}
+
+#ifdef CONFIG_SMP
+/*
+ * Ensure the next switch_mm() on every CPU issues a core serializing
+ * instruction for the given @mm.
+ */
+static inline void prepare_sync_core_cmd(struct mm_struct *mm)
+{
+ cpumask_setall(&mm->context.icache_stale_mask);
+}
+#else
+static inline void prepare_sync_core_cmd(struct mm_struct *mm)
+{
+}
+#endif /* CONFIG_SMP */
+
+#endif /* _ASM_RISCV_SYNC_CORE_H */
diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h
index 384a63b86420..34313387f977 100644
--- a/arch/riscv/include/asm/syscall.h
+++ b/arch/riscv/include/asm/syscall.h
@@ -10,6 +10,7 @@
#ifndef _ASM_RISCV_SYSCALL_H
#define _ASM_RISCV_SYSCALL_H
+#include <asm/hwprobe.h>
#include <uapi/linux/audit.h>
#include <linux/sched.h>
#include <linux/err.h>
@@ -29,6 +30,13 @@ static inline int syscall_get_nr(struct task_struct *task,
return regs->a7;
}
+static inline void syscall_set_nr(struct task_struct *task,
+ struct pt_regs *regs,
+ int nr)
+{
+ regs->a7 = nr;
+}
+
static inline void syscall_rollback(struct task_struct *task,
struct pt_regs *regs)
{
@@ -61,8 +69,23 @@ static inline void syscall_get_arguments(struct task_struct *task,
unsigned long *args)
{
args[0] = regs->orig_a0;
- args++;
- memcpy(args, &regs->a1, 5 * sizeof(args[0]));
+ args[1] = regs->a1;
+ args[2] = regs->a2;
+ args[3] = regs->a3;
+ args[4] = regs->a4;
+ args[5] = regs->a5;
+}
+
+static inline void syscall_set_arguments(struct task_struct *task,
+ struct pt_regs *regs,
+ const unsigned long *args)
+{
+ regs->orig_a0 = args[0];
+ regs->a1 = args[1];
+ regs->a2 = args[2];
+ regs->a3 = args[3];
+ regs->a4 = args[4];
+ regs->a5 = args[5];
}
static inline int syscall_get_arch(struct task_struct *task)
@@ -74,5 +97,28 @@ static inline int syscall_get_arch(struct task_struct *task)
#endif
}
+typedef long (*syscall_t)(const struct pt_regs *);
+static inline void syscall_handler(struct pt_regs *regs, ulong syscall)
+{
+ syscall_t fn;
+
+#ifdef CONFIG_COMPAT
+ if ((regs->status & SR_UXL) == SR_UXL_32)
+ fn = compat_sys_call_table[syscall];
+ else
+#endif
+ fn = sys_call_table[syscall];
+
+ regs->a0 = fn(regs);
+}
+
+static inline bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs)
+{
+ return false;
+}
+
asmlinkage long sys_riscv_flush_icache(uintptr_t, uintptr_t, uintptr_t);
+
+asmlinkage long sys_riscv_hwprobe(struct riscv_hwprobe *, size_t, size_t,
+ unsigned long *, unsigned int);
#endif /* _ASM_RISCV_SYSCALL_H */
diff --git a/arch/riscv/include/asm/syscall_table.h b/arch/riscv/include/asm/syscall_table.h
new file mode 100644
index 000000000000..0c2d61782813
--- /dev/null
+++ b/arch/riscv/include/asm/syscall_table.h
@@ -0,0 +1,7 @@
+#include <asm/bitsperlong.h>
+
+#if __BITS_PER_LONG == 64
+#include <asm/syscall_table_64.h>
+#else
+#include <asm/syscall_table_32.h>
+#endif
diff --git a/arch/riscv/include/asm/syscall_wrapper.h b/arch/riscv/include/asm/syscall_wrapper.h
new file mode 100644
index 000000000000..ac80216549ff
--- /dev/null
+++ b/arch/riscv/include/asm/syscall_wrapper.h
@@ -0,0 +1,108 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * syscall_wrapper.h - riscv specific wrappers to syscall definitions
+ *
+ * Based on arch/arm64/include/syscall_wrapper.h
+ */
+
+#ifndef __ASM_SYSCALL_WRAPPER_H
+#define __ASM_SYSCALL_WRAPPER_H
+
+#include <asm/ptrace.h>
+
+asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *);
+
+#ifdef CONFIG_64BIT
+
+#define __SYSCALL_SE_DEFINEx(x, prefix, name, ...) \
+ static long __se_##prefix##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \
+ static long __se_##prefix##name(__MAP(x,__SC_LONG,__VA_ARGS__))
+
+#define SC_RISCV_REGS_TO_ARGS(x, ...) \
+ __MAP(x,__SC_ARGS \
+ ,,regs->orig_a0,,regs->a1,,regs->a2 \
+ ,,regs->a3,,regs->a4,,regs->a5,,regs->a6)
+
+#else
+/*
+ * Use type aliasing to ensure registers a0-a6 are correctly passed to the syscall
+ * implementation when >word-size arguments are used.
+ */
+#define __SYSCALL_SE_DEFINEx(x, prefix, name, ...) \
+ __diag_push(); \
+ __diag_ignore(GCC, 8, "-Wattribute-alias", \
+ "Type aliasing is used to sanitize syscall arguments"); \
+ static long __se_##prefix##name(ulong, ulong, ulong, ulong, ulong, ulong, \
+ ulong) \
+ __attribute__((alias(__stringify(___se_##prefix##name)))); \
+ __diag_pop(); \
+ static long noinline ___se_##prefix##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \
+ __used; \
+ static long ___se_##prefix##name(__MAP(x,__SC_LONG,__VA_ARGS__))
+
+#define SC_RISCV_REGS_TO_ARGS(x, ...) \
+ regs->orig_a0,regs->a1,regs->a2,regs->a3,regs->a4,regs->a5,regs->a6
+
+#endif /* CONFIG_64BIT */
+
+#ifdef CONFIG_COMPAT
+
+#define COMPAT_SYSCALL_DEFINEx(x, name, ...) \
+ asmlinkage long __riscv_compat_sys##name(const struct pt_regs *regs); \
+ ALLOW_ERROR_INJECTION(__riscv_compat_sys##name, ERRNO); \
+ static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \
+ __SYSCALL_SE_DEFINEx(x, compat_sys, name, __VA_ARGS__) \
+ { \
+ return __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__)); \
+ } \
+ asmlinkage long __riscv_compat_sys##name(const struct pt_regs *regs) \
+ { \
+ return __se_compat_sys##name(SC_RISCV_REGS_TO_ARGS(x,__VA_ARGS__)); \
+ } \
+ static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
+
+#define COMPAT_SYSCALL_DEFINE0(sname) \
+ asmlinkage long __riscv_compat_sys_##sname(const struct pt_regs *__unused); \
+ ALLOW_ERROR_INJECTION(__riscv_compat_sys_##sname, ERRNO); \
+ asmlinkage long __riscv_compat_sys_##sname(const struct pt_regs *__unused)
+
+#define COND_SYSCALL_COMPAT(name) \
+ asmlinkage long __weak __riscv_compat_sys_##name(const struct pt_regs *regs); \
+ asmlinkage long __weak __riscv_compat_sys_##name(const struct pt_regs *regs) \
+ { \
+ return sys_ni_syscall(); \
+ }
+
+#endif /* CONFIG_COMPAT */
+
+#define __SYSCALL_DEFINEx(x, name, ...) \
+ asmlinkage long __riscv_sys##name(const struct pt_regs *regs); \
+ ALLOW_ERROR_INJECTION(__riscv_sys##name, ERRNO); \
+ static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \
+ __SYSCALL_SE_DEFINEx(x, sys, name, __VA_ARGS__) \
+ { \
+ long ret = __do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \
+ __MAP(x,__SC_TEST,__VA_ARGS__); \
+ __PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \
+ return ret; \
+ } \
+ asmlinkage long __riscv_sys##name(const struct pt_regs *regs) \
+ { \
+ return __se_sys##name(SC_RISCV_REGS_TO_ARGS(x,__VA_ARGS__)); \
+ } \
+ static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
+
+#define SYSCALL_DEFINE0(sname) \
+ SYSCALL_METADATA(_##sname, 0); \
+ asmlinkage long __riscv_sys_##sname(const struct pt_regs *__unused); \
+ ALLOW_ERROR_INJECTION(__riscv_sys_##sname, ERRNO); \
+ asmlinkage long __riscv_sys_##sname(const struct pt_regs *__unused)
+
+#define COND_SYSCALL(name) \
+ asmlinkage long __weak __riscv_sys_##name(const struct pt_regs *regs); \
+ asmlinkage long __weak __riscv_sys_##name(const struct pt_regs *regs) \
+ { \
+ return sys_ni_syscall(); \
+ }
+
+#endif /* __ASM_SYSCALL_WRAPPER_H */
diff --git a/arch/riscv/include/asm/patch.h b/arch/riscv/include/asm/text-patching.h
index 9a7d7346001e..7228e266b9a1 100644
--- a/arch/riscv/include/asm/patch.h
+++ b/arch/riscv/include/asm/text-patching.h
@@ -6,7 +6,11 @@
#ifndef _ASM_RISCV_PATCH_H
#define _ASM_RISCV_PATCH_H
+int patch_insn_write(void *addr, const void *insn, size_t len);
int patch_text_nosync(void *addr, const void *insns, size_t len);
-int patch_text(void *addr, u32 insn);
+int patch_text_set_nosync(void *addr, u8 c, size_t len);
+int patch_text(void *addr, u32 *insns, size_t len);
+
+extern int riscv_patch_in_stop_machine;
#endif /* _ASM_RISCV_PATCH_H */
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index 78933ac04995..f5916a70879a 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -10,19 +10,15 @@
#include <asm/page.h>
#include <linux/const.h>
-
-#ifdef CONFIG_KASAN
-#define KASAN_STACK_ORDER 1
-#else
-#define KASAN_STACK_ORDER 0
-#endif
+#include <linux/sizes.h>
/* thread information allocation */
-#ifdef CONFIG_64BIT
-#define THREAD_SIZE_ORDER (2 + KASAN_STACK_ORDER)
+#ifdef CONFIG_KASAN
+#define KASAN_STACK_ORDER 1
#else
-#define THREAD_SIZE_ORDER (1 + KASAN_STACK_ORDER)
+#define KASAN_STACK_ORDER 0
#endif
+#define THREAD_SIZE_ORDER (CONFIG_THREAD_SIZE_ORDER + KASAN_STACK_ORDER)
#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER)
/*
@@ -38,7 +34,8 @@
#define THREAD_SHIFT (PAGE_SHIFT + THREAD_SIZE_ORDER)
#define OVERFLOW_STACK_SIZE SZ_4K
-#define SHADOW_OVERFLOW_STACK_SIZE (1024)
+
+#define IRQ_STACK_SIZE THREAD_SIZE
#ifndef __ASSEMBLY__
@@ -64,8 +61,28 @@ struct thread_info {
long kernel_sp; /* Kernel stack pointer */
long user_sp; /* User stack pointer */
int cpu;
+ unsigned long syscall_work; /* SYSCALL_WORK_ flags */
+#ifdef CONFIG_SHADOW_CALL_STACK
+ void *scs_base;
+ void *scs_sp;
+#endif
+#ifdef CONFIG_64BIT
+ /*
+ * Used in handle_exception() to save a0, a1 and a2 before knowing if we
+ * can access the kernel stack.
+ */
+ unsigned long a0, a1, a2;
+#endif
};
+#ifdef CONFIG_SHADOW_CALL_STACK
+#define INIT_SCS \
+ .scs_base = init_shadow_call_stack, \
+ .scs_sp = init_shadow_call_stack,
+#else
+#define INIT_SCS
+#endif
+
/*
* macros/functions for gaining access to the thread information structure
*
@@ -75,8 +92,12 @@ struct thread_info {
{ \
.flags = 0, \
.preempt_count = INIT_PREEMPT_COUNT, \
+ INIT_SCS \
}
+void arch_release_task_struct(struct task_struct *tsk);
+int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
+
#endif /* !__ASSEMBLY__ */
/*
@@ -86,35 +107,23 @@ struct thread_info {
* - pending work-to-be-done flags are in lowest half-word
* - other flags in upper half-word(s)
*/
-#define TIF_SYSCALL_TRACE 0 /* syscall trace active */
-#define TIF_NOTIFY_RESUME 1 /* callback before returning to user */
-#define TIF_SIGPENDING 2 /* signal pending */
-#define TIF_NEED_RESCHED 3 /* rescheduling necessary */
+#define TIF_NEED_RESCHED 0 /* rescheduling necessary */
+#define TIF_NEED_RESCHED_LAZY 1 /* Lazy rescheduling needed */
+#define TIF_NOTIFY_RESUME 2 /* callback before returning to user */
+#define TIF_SIGPENDING 3 /* signal pending */
#define TIF_RESTORE_SIGMASK 4 /* restore signal mask in do_signal() */
#define TIF_MEMDIE 5 /* is terminating due to OOM killer */
-#define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */
-#define TIF_SYSCALL_AUDIT 7 /* syscall auditing */
-#define TIF_SECCOMP 8 /* syscall secure computing */
#define TIF_NOTIFY_SIGNAL 9 /* signal notifications exist */
#define TIF_UPROBE 10 /* uprobe breakpoint or singlestep */
#define TIF_32BIT 11 /* compat-mode 32bit process */
+#define TIF_RISCV_V_DEFER_RESTORE 12 /* restore Vector before returing to user */
-#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
+#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
+#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY)
#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
#define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
-#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
-#define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT)
-#define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT)
-#define _TIF_SECCOMP (1 << TIF_SECCOMP)
#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL)
#define _TIF_UPROBE (1 << TIF_UPROBE)
-
-#define _TIF_WORK_MASK \
- (_TIF_NOTIFY_RESUME | _TIF_SIGPENDING | _TIF_NEED_RESCHED | \
- _TIF_NOTIFY_SIGNAL | _TIF_UPROBE)
-
-#define _TIF_SYSCALL_WORK \
- (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT | \
- _TIF_SECCOMP)
+#define _TIF_RISCV_V_DEFER_RESTORE (1 << TIF_RISCV_V_DEFER_RESTORE)
#endif /* _ASM_RISCV_THREAD_INFO_H */
diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h
index d6a7428f6248..a06697846e69 100644
--- a/arch/riscv/include/asm/timex.h
+++ b/arch/riscv/include/asm/timex.h
@@ -88,6 +88,4 @@ static inline int read_current_timer(unsigned long *timer_val)
return 0;
}
-extern void time_init(void);
-
#endif /* _ASM_RISCV_TIMEX_H */
diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
index 120bcf2ed8a8..50b63b5c15bd 100644
--- a/arch/riscv/include/asm/tlb.h
+++ b/arch/riscv/include/asm/tlb.h
@@ -15,7 +15,13 @@ static void tlb_flush(struct mmu_gather *tlb);
static inline void tlb_flush(struct mmu_gather *tlb)
{
- flush_tlb_mm(tlb->mm);
+#ifdef CONFIG_MMU
+ if (tlb->fullmm || tlb->need_flush_all || tlb->freed_tables)
+ flush_tlb_mm(tlb->mm);
+ else
+ flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end,
+ tlb_get_unmap_size(tlb));
+#endif
}
#endif /* _ASM_RISCV_TLB_H */
diff --git a/arch/riscv/include/asm/tlbbatch.h b/arch/riscv/include/asm/tlbbatch.h
new file mode 100644
index 000000000000..46014f70b9da
--- /dev/null
+++ b/arch/riscv/include/asm/tlbbatch.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 Rivos Inc.
+ */
+
+#ifndef _ASM_RISCV_TLBBATCH_H
+#define _ASM_RISCV_TLBBATCH_H
+
+#include <linux/cpumask.h>
+
+struct arch_tlbflush_unmap_batch {
+ struct cpumask cpumask;
+};
+
+#endif /* _ASM_RISCV_TLBBATCH_H */
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index 801019381dea..1a20dd746a49 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -11,52 +11,64 @@
#include <asm/smp.h>
#include <asm/errata_list.h>
+#define FLUSH_TLB_MAX_SIZE ((unsigned long)-1)
+#define FLUSH_TLB_NO_ASID ((unsigned long)-1)
+
#ifdef CONFIG_MMU
static inline void local_flush_tlb_all(void)
{
__asm__ __volatile__ ("sfence.vma" : : : "memory");
}
+static inline void local_flush_tlb_all_asid(unsigned long asid)
+{
+ if (asid != FLUSH_TLB_NO_ASID)
+ ALT_SFENCE_VMA_ASID(asid);
+ else
+ local_flush_tlb_all();
+}
+
/* Flush one page from local TLB */
static inline void local_flush_tlb_page(unsigned long addr)
{
- ALT_FLUSH_TLB_PAGE(__asm__ __volatile__ ("sfence.vma %0" : : "r" (addr) : "memory"));
+ ALT_SFENCE_VMA_ADDR(addr);
+}
+
+static inline void local_flush_tlb_page_asid(unsigned long addr,
+ unsigned long asid)
+{
+ if (asid != FLUSH_TLB_NO_ASID)
+ ALT_SFENCE_VMA_ADDR_ASID(addr, asid);
+ else
+ local_flush_tlb_page(addr);
}
-#else /* CONFIG_MMU */
-#define local_flush_tlb_all() do { } while (0)
-#define local_flush_tlb_page(addr) do { } while (0)
-#endif /* CONFIG_MMU */
-#if defined(CONFIG_SMP) && defined(CONFIG_MMU)
void flush_tlb_all(void);
void flush_tlb_mm(struct mm_struct *mm);
+void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
+ unsigned long end, unsigned int page_size);
void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr);
void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end);
+void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+void local_flush_tlb_kernel_range(unsigned long start, unsigned long end);
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end);
+void flush_pud_tlb_range(struct vm_area_struct *vma, unsigned long start,
+ unsigned long end);
#endif
-#else /* CONFIG_SMP && CONFIG_MMU */
-#define flush_tlb_all() local_flush_tlb_all()
-#define flush_tlb_page(vma, addr) local_flush_tlb_page(addr)
+bool arch_tlbbatch_should_defer(struct mm_struct *mm);
+void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
+ struct mm_struct *mm, unsigned long start, unsigned long end);
+void arch_flush_tlb_batched_pending(struct mm_struct *mm);
+void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
-static inline void flush_tlb_range(struct vm_area_struct *vma,
- unsigned long start, unsigned long end)
-{
- local_flush_tlb_all();
-}
-
-#define flush_tlb_mm(mm) flush_tlb_all()
-#endif /* !CONFIG_SMP || !CONFIG_MMU */
-
-/* Flush a range of kernel pages */
-static inline void flush_tlb_kernel_range(unsigned long start,
- unsigned long end)
-{
- flush_tlb_all();
-}
+extern unsigned long tlb_flush_all_threshold;
+#else /* CONFIG_MMU */
+#define local_flush_tlb_all() do { } while (0)
+#endif /* CONFIG_MMU */
#endif /* _ASM_RISCV_TLBFLUSH_H */
diff --git a/arch/riscv/include/asm/topology.h b/arch/riscv/include/asm/topology.h
new file mode 100644
index 000000000000..fe1a8bf6902d
--- /dev/null
+++ b/arch/riscv/include/asm/topology.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_TOPOLOGY_H
+#define _ASM_RISCV_TOPOLOGY_H
+
+#include <linux/arch_topology.h>
+
+#ifdef CONFIG_NUMA
+#include <asm/numa.h>
+#endif
+
+/* Replace task scheduler's default frequency-invariant accounting */
+#define arch_scale_freq_tick topology_scale_freq_tick
+#define arch_set_freq_scale topology_set_freq_scale
+#define arch_scale_freq_capacity topology_get_freq_scale
+#define arch_scale_freq_invariant topology_scale_freq_invariant
+#define arch_scale_freq_ref topology_get_freq_ref
+
+/* Replace task scheduler's default cpu-invariant accounting */
+#define arch_scale_cpu_capacity topology_get_cpu_scale
+
+/* Enable topology flag updates */
+#define arch_update_cpu_topology topology_update_cpu_topology
+
+#include <asm-generic/topology.h>
+
+#endif /* _ASM_RISCV_TOPOLOGY_H */
diff --git a/arch/riscv/include/asm/trace.h b/arch/riscv/include/asm/trace.h
new file mode 100644
index 000000000000..6151cee5450c
--- /dev/null
+++ b/arch/riscv/include/asm/trace.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM riscv
+
+#if !defined(_TRACE_RISCV_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_RISCV_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT_CONDITION(sbi_call,
+ TP_PROTO(int ext, int fid),
+ TP_ARGS(ext, fid),
+ TP_CONDITION(ext != SBI_EXT_HSM),
+
+ TP_STRUCT__entry(
+ __field(int, ext)
+ __field(int, fid)
+ ),
+
+ TP_fast_assign(
+ __entry->ext = ext;
+ __entry->fid = fid;
+ ),
+
+ TP_printk("ext=0x%x fid=%d", __entry->ext, __entry->fid)
+);
+
+TRACE_EVENT_CONDITION(sbi_return,
+ TP_PROTO(int ext, long error, long value),
+ TP_ARGS(ext, error, value),
+ TP_CONDITION(ext != SBI_EXT_HSM),
+
+ TP_STRUCT__entry(
+ __field(long, error)
+ __field(long, value)
+ ),
+
+ TP_fast_assign(
+ __entry->error = error;
+ __entry->value = value;
+ ),
+
+ TP_printk("error=%ld value=0x%lx", __entry->error, __entry->value)
+);
+
+#endif /* _TRACE_RISCV_H */
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+
+#define TRACE_INCLUDE_PATH asm
+#define TRACE_INCLUDE_FILE trace
+
+#include <trace/define_trace.h>
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index 855450bed9f5..d472da4450e6 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -9,8 +9,41 @@
#define _ASM_RISCV_UACCESS_H
#include <asm/asm-extable.h>
+#include <asm/cpufeature.h>
#include <asm/pgtable.h> /* for TASK_SIZE */
+#ifdef CONFIG_RISCV_ISA_SUPM
+static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, unsigned long addr)
+{
+ if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM)) {
+ u8 pmlen = mm->context.pmlen;
+
+ /* Virtual addresses are sign-extended; physical addresses are zero-extended. */
+ if (IS_ENABLED(CONFIG_MMU))
+ return (long)(addr << pmlen) >> pmlen;
+ else
+ return (addr << pmlen) >> pmlen;
+ }
+
+ return addr;
+}
+
+#define untagged_addr(addr) ({ \
+ unsigned long __addr = (__force unsigned long)(addr); \
+ (__force __typeof__(addr))__untagged_addr_remote(current->mm, __addr); \
+})
+
+#define untagged_addr_remote(mm, addr) ({ \
+ unsigned long __addr = (__force unsigned long)(addr); \
+ mmap_assert_locked(mm); \
+ (__force __typeof__(addr))__untagged_addr_remote(mm, __addr); \
+})
+
+#define access_ok(addr, size) likely(__access_ok(untagged_addr(addr), size))
+#else
+#define untagged_addr(addr) (addr)
+#endif
+
/*
* User space memory access functions
*/
@@ -29,6 +62,19 @@
__asm__ __volatile__ ("csrc sstatus, %0" : : "r" (SR_SUM) : "memory")
/*
+ * This is the smallest unsigned integer type that can fit a value
+ * (up to 'long long')
+ */
+#define __inttype(x) __typeof__( \
+ __typefits(x, char, \
+ __typefits(x, short, \
+ __typefits(x, int, \
+ __typefits(x, long, 0ULL)))))
+
+#define __typefits(x, type, not) \
+ __builtin_choose_expr(sizeof(x) <= sizeof(type), (unsigned type)0, not)
+
+/*
* The exception table consists of pairs of addresses: the first is the
* address of an instruction that is allowed to fault, and the second is
* the address at which the program should continue. No registers are
@@ -50,27 +96,58 @@
* call.
*/
-#define __get_user_asm(insn, x, ptr, err) \
+#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
+#define __get_user_asm(insn, x, ptr, label) \
+ asm_goto_output( \
+ "1:\n" \
+ " " insn " %0, %1\n" \
+ _ASM_EXTABLE_UACCESS_ERR(1b, %l2, %0) \
+ : "=&r" (x) \
+ : "m" (*(ptr)) : : label)
+#else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
+#define __get_user_asm(insn, x, ptr, label) \
do { \
- __typeof__(x) __x; \
+ long __gua_err = 0; \
__asm__ __volatile__ ( \
"1:\n" \
" " insn " %1, %2\n" \
"2:\n" \
_ASM_EXTABLE_UACCESS_ERR_ZERO(1b, 2b, %0, %1) \
- : "+r" (err), "=&r" (__x) \
+ : "+r" (__gua_err), "=&r" (x) \
: "m" (*(ptr))); \
- (x) = __x; \
+ if (__gua_err) \
+ goto label; \
} while (0)
+#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
#ifdef CONFIG_64BIT
-#define __get_user_8(x, ptr, err) \
- __get_user_asm("ld", x, ptr, err)
+#define __get_user_8(x, ptr, label) \
+ __get_user_asm("ld", x, ptr, label)
#else /* !CONFIG_64BIT */
-#define __get_user_8(x, ptr, err) \
+
+#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
+#define __get_user_8(x, ptr, label) \
+ u32 __user *__ptr = (u32 __user *)(ptr); \
+ u32 __lo, __hi; \
+ asm_goto_output( \
+ "1:\n" \
+ " lw %0, %2\n" \
+ "2:\n" \
+ " lw %1, %3\n" \
+ _ASM_EXTABLE_UACCESS_ERR(1b, %l4, %0) \
+ _ASM_EXTABLE_UACCESS_ERR(2b, %l4, %0) \
+ : "=&r" (__lo), "=r" (__hi) \
+ : "m" (__ptr[__LSW]), "m" (__ptr[__MSW]) \
+ : : label); \
+ (x) = (__typeof__(x))((__typeof__((x) - (x)))( \
+ (((u64)__hi << 32) | __lo))); \
+
+#else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
+#define __get_user_8(x, ptr, label) \
do { \
u32 __user *__ptr = (u32 __user *)(ptr); \
u32 __lo, __hi; \
+ long __gu8_err = 0; \
__asm__ __volatile__ ( \
"1:\n" \
" lw %1, %3\n" \
@@ -79,35 +156,62 @@ do { \
"3:\n" \
_ASM_EXTABLE_UACCESS_ERR_ZERO(1b, 3b, %0, %1) \
_ASM_EXTABLE_UACCESS_ERR_ZERO(2b, 3b, %0, %1) \
- : "+r" (err), "=&r" (__lo), "=r" (__hi) \
+ : "+r" (__gu8_err), "=&r" (__lo), "=r" (__hi) \
: "m" (__ptr[__LSW]), "m" (__ptr[__MSW])); \
- if (err) \
+ if (__gu8_err) { \
__hi = 0; \
- (x) = (__typeof__(x))((__typeof__((x)-(x)))( \
+ goto label; \
+ } \
+ (x) = (__typeof__(x))((__typeof__((x) - (x)))( \
(((u64)__hi << 32) | __lo))); \
} while (0)
+#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
+
#endif /* CONFIG_64BIT */
-#define __get_user_nocheck(x, __gu_ptr, __gu_err) \
+unsigned long __must_check __asm_copy_to_user_sum_enabled(void __user *to,
+ const void *from, unsigned long n);
+unsigned long __must_check __asm_copy_from_user_sum_enabled(void *to,
+ const void __user *from, unsigned long n);
+
+#define __get_user_nocheck(x, __gu_ptr, label) \
do { \
+ if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && \
+ !IS_ALIGNED((uintptr_t)__gu_ptr, sizeof(*__gu_ptr))) { \
+ if (__asm_copy_from_user_sum_enabled(&(x), __gu_ptr, sizeof(*__gu_ptr))) \
+ goto label; \
+ break; \
+ } \
switch (sizeof(*__gu_ptr)) { \
case 1: \
- __get_user_asm("lb", (x), __gu_ptr, __gu_err); \
+ __get_user_asm("lb", (x), __gu_ptr, label); \
break; \
case 2: \
- __get_user_asm("lh", (x), __gu_ptr, __gu_err); \
+ __get_user_asm("lh", (x), __gu_ptr, label); \
break; \
case 4: \
- __get_user_asm("lw", (x), __gu_ptr, __gu_err); \
+ __get_user_asm("lw", (x), __gu_ptr, label); \
break; \
case 8: \
- __get_user_8((x), __gu_ptr, __gu_err); \
+ __get_user_8((x), __gu_ptr, label); \
break; \
default: \
BUILD_BUG(); \
} \
} while (0)
+#define __get_user_error(x, ptr, err) \
+do { \
+ __label__ __gu_failed; \
+ \
+ __get_user_nocheck(x, ptr, __gu_failed); \
+ err = 0; \
+ break; \
+__gu_failed: \
+ x = 0; \
+ err = -EFAULT; \
+} while (0)
+
/**
* __get_user: - Get a simple variable from user space, with less checking.
* @x: Variable to store result.
@@ -130,15 +234,18 @@ do { \
*/
#define __get_user(x, ptr) \
({ \
- const __typeof__(*(ptr)) __user *__gu_ptr = (ptr); \
+ const __typeof__(*(ptr)) __user *__gu_ptr = untagged_addr(ptr); \
long __gu_err = 0; \
+ __typeof__(x) __gu_val; \
\
__chk_user_ptr(__gu_ptr); \
\
__enable_user_access(); \
- __get_user_nocheck(x, __gu_ptr, __gu_err); \
+ __get_user_error(__gu_val, __gu_ptr, __gu_err); \
__disable_user_access(); \
\
+ (x) = __gu_val; \
+ \
__gu_err; \
})
@@ -165,64 +272,76 @@ do { \
might_fault(); \
access_ok(__p, sizeof(*__p)) ? \
__get_user((x), __p) : \
- ((x) = 0, -EFAULT); \
+ ((x) = (__force __typeof__(x))0, -EFAULT); \
})
-#define __put_user_asm(insn, x, ptr, err) \
+#define __put_user_asm(insn, x, ptr, label) \
do { \
__typeof__(*(ptr)) __x = x; \
- __asm__ __volatile__ ( \
+ asm goto( \
"1:\n" \
- " " insn " %z2, %1\n" \
- "2:\n" \
- _ASM_EXTABLE_UACCESS_ERR(1b, 2b, %0) \
- : "+r" (err), "=m" (*(ptr)) \
- : "rJ" (__x)); \
+ " " insn " %z0, %1\n" \
+ _ASM_EXTABLE(1b, %l2) \
+ : : "rJ" (__x), "m"(*(ptr)) : : label); \
} while (0)
#ifdef CONFIG_64BIT
-#define __put_user_8(x, ptr, err) \
- __put_user_asm("sd", x, ptr, err)
+#define __put_user_8(x, ptr, label) \
+ __put_user_asm("sd", x, ptr, label)
#else /* !CONFIG_64BIT */
-#define __put_user_8(x, ptr, err) \
+#define __put_user_8(x, ptr, label) \
do { \
u32 __user *__ptr = (u32 __user *)(ptr); \
u64 __x = (__typeof__((x)-(x)))(x); \
- __asm__ __volatile__ ( \
+ asm goto( \
"1:\n" \
- " sw %z3, %1\n" \
+ " sw %z0, %2\n" \
"2:\n" \
- " sw %z4, %2\n" \
- "3:\n" \
- _ASM_EXTABLE_UACCESS_ERR(1b, 3b, %0) \
- _ASM_EXTABLE_UACCESS_ERR(2b, 3b, %0) \
- : "+r" (err), \
- "=m" (__ptr[__LSW]), \
- "=m" (__ptr[__MSW]) \
- : "rJ" (__x), "rJ" (__x >> 32)); \
+ " sw %z1, %3\n" \
+ _ASM_EXTABLE(1b, %l4) \
+ _ASM_EXTABLE(2b, %l4) \
+ : : "rJ" (__x), "rJ" (__x >> 32), \
+ "m" (__ptr[__LSW]), \
+ "m" (__ptr[__MSW]) : : label); \
} while (0)
#endif /* CONFIG_64BIT */
-#define __put_user_nocheck(x, __gu_ptr, __pu_err) \
+#define __put_user_nocheck(x, __gu_ptr, label) \
do { \
+ if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && \
+ !IS_ALIGNED((uintptr_t)__gu_ptr, sizeof(*__gu_ptr))) { \
+ __inttype(x) val = (__inttype(x))x; \
+ if (__asm_copy_to_user_sum_enabled(__gu_ptr, &(val), sizeof(*__gu_ptr))) \
+ goto label; \
+ break; \
+ } \
switch (sizeof(*__gu_ptr)) { \
case 1: \
- __put_user_asm("sb", (x), __gu_ptr, __pu_err); \
+ __put_user_asm("sb", (x), __gu_ptr, label); \
break; \
case 2: \
- __put_user_asm("sh", (x), __gu_ptr, __pu_err); \
+ __put_user_asm("sh", (x), __gu_ptr, label); \
break; \
case 4: \
- __put_user_asm("sw", (x), __gu_ptr, __pu_err); \
+ __put_user_asm("sw", (x), __gu_ptr, label); \
break; \
case 8: \
- __put_user_8((x), __gu_ptr, __pu_err); \
+ __put_user_8((x), __gu_ptr, label); \
break; \
default: \
BUILD_BUG(); \
} \
} while (0)
+#define __put_user_error(x, ptr, err) \
+do { \
+ __label__ err_label; \
+ __put_user_nocheck(x, ptr, err_label); \
+ break; \
+err_label: \
+ (err) = -EFAULT; \
+} while (0)
+
/**
* __put_user: - Write a simple value into user space, with less checking.
* @x: Value to copy to user space.
@@ -246,14 +365,14 @@ do { \
*/
#define __put_user(x, ptr) \
({ \
- __typeof__(*(ptr)) __user *__gu_ptr = (ptr); \
+ __typeof__(*(ptr)) __user *__gu_ptr = untagged_addr(ptr); \
__typeof__(*__gu_ptr) __val = (x); \
long __pu_err = 0; \
\
__chk_user_ptr(__gu_ptr); \
\
__enable_user_access(); \
- __put_user_nocheck(__val, __gu_ptr, __pu_err); \
+ __put_user_error(__val, __gu_ptr, __pu_err); \
__disable_user_access(); \
\
__pu_err; \
@@ -293,13 +412,13 @@ unsigned long __must_check __asm_copy_from_user(void *to,
static inline unsigned long
raw_copy_from_user(void *to, const void __user *from, unsigned long n)
{
- return __asm_copy_from_user(to, from, n);
+ return __asm_copy_from_user(to, untagged_addr(from), n);
}
static inline unsigned long
raw_copy_to_user(void __user *to, const void *from, unsigned long n)
{
- return __asm_copy_to_user(to, from, n);
+ return __asm_copy_to_user(untagged_addr(to), from, n);
}
extern long strncpy_from_user(char *dest, const char __user *src, long count);
@@ -314,27 +433,49 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n)
{
might_fault();
return access_ok(to, n) ?
- __clear_user(to, n) : n;
+ __clear_user(untagged_addr(to), n) : n;
}
#define __get_kernel_nofault(dst, src, type, err_label) \
-do { \
- long __kr_err; \
- \
- __get_user_nocheck(*((type *)(dst)), (type *)(src), __kr_err); \
- if (unlikely(__kr_err)) \
- goto err_label; \
-} while (0)
+ __get_user_nocheck(*((type *)(dst)), (type *)(src), err_label)
#define __put_kernel_nofault(dst, src, type, err_label) \
-do { \
- long __kr_err; \
- \
- __put_user_nocheck(*((type *)(src)), (type *)(dst), __kr_err); \
- if (unlikely(__kr_err)) \
- goto err_label; \
+ __put_user_nocheck(*((type *)(src)), (type *)(dst), err_label)
+
+static __must_check __always_inline bool user_access_begin(const void __user *ptr, size_t len)
+{
+ if (unlikely(!access_ok(ptr, len)))
+ return 0;
+ __enable_user_access();
+ return 1;
+}
+#define user_access_begin user_access_begin
+#define user_access_end __disable_user_access
+
+static inline unsigned long user_access_save(void) { return 0UL; }
+static inline void user_access_restore(unsigned long enabled) { }
+
+/*
+ * We want the unsafe accessors to always be inlined and use
+ * the error labels - thus the macro games.
+ */
+#define unsafe_put_user(x, ptr, label) \
+ __put_user_nocheck(x, (ptr), label)
+
+#define unsafe_get_user(x, ptr, label) do { \
+ __inttype(*(ptr)) __gu_val; \
+ __get_user_nocheck(__gu_val, (ptr), label); \
+ (x) = (__force __typeof__(*(ptr)))__gu_val; \
} while (0)
+#define unsafe_copy_to_user(_dst, _src, _len, label) \
+ if (__asm_copy_to_user_sum_enabled(_dst, _src, _len)) \
+ goto label;
+
+#define unsafe_copy_from_user(_dst, _src, _len, label) \
+ if (__asm_copy_from_user_sum_enabled(_dst, _src, _len)) \
+ goto label;
+
#else /* CONFIG_MMU */
#include <asm-generic/uaccess.h>
#endif /* CONFIG_MMU */
diff --git a/arch/riscv/include/asm/unistd.h b/arch/riscv/include/asm/unistd.h
index 221630bdbd07..e6d904fa67c5 100644
--- a/arch/riscv/include/asm/unistd.h
+++ b/arch/riscv/include/asm/unistd.h
@@ -3,11 +3,6 @@
* Copyright (C) 2012 Regents of the University of California
*/
-/*
- * There is explicitly no include guard here because this file is expected to
- * be included multiple times.
- */
-
#define __ARCH_WANT_SYS_CLONE
#ifdef CONFIG_COMPAT
@@ -21,6 +16,14 @@
#define __ARCH_WANT_COMPAT_FADVISE64_64
#endif
+#if defined(__LP64__) && !defined(__SYSCALL_COMPAT)
+#define __ARCH_WANT_NEW_STAT
+#define __ARCH_WANT_SET_GET_RLIMIT
+#endif /* __LP64__ */
+
+#define __ARCH_WANT_MEMFD_SECRET
+
+
#include <uapi/asm/unistd.h>
#define NR_syscalls (__NR_syscalls)
diff --git a/arch/riscv/include/asm/uprobes.h b/arch/riscv/include/asm/uprobes.h
index f2183e00fdd2..5008f76cdc27 100644
--- a/arch/riscv/include/asm/uprobes.h
+++ b/arch/riscv/include/asm/uprobes.h
@@ -4,7 +4,7 @@
#define _ASM_RISCV_UPROBES_H
#include <asm/probes.h>
-#include <asm/patch.h>
+#include <asm/text-patching.h>
#include <asm/bug.h>
#define MAX_UINSN_BYTES 8
@@ -34,7 +34,18 @@ struct arch_uprobe {
bool simulate;
};
+#ifdef CONFIG_UPROBES
bool uprobe_breakpoint_handler(struct pt_regs *regs);
bool uprobe_single_step_handler(struct pt_regs *regs);
-
+#else
+static inline bool uprobe_breakpoint_handler(struct pt_regs *regs)
+{
+ return false;
+}
+
+static inline bool uprobe_single_step_handler(struct pt_regs *regs)
+{
+ return false;
+}
+#endif /* CONFIG_UPROBES */
#endif /* _ASM_RISCV_UPROBES_H */
diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h
index af981426fe0f..c130d8100232 100644
--- a/arch/riscv/include/asm/vdso.h
+++ b/arch/riscv/include/asm/vdso.h
@@ -10,11 +10,11 @@
/*
* All systems with an MMU have a VDSO, but systems without an MMU don't
- * support shared libraries and therefor don't have one.
+ * support shared libraries and therefore don't have one.
*/
#ifdef CONFIG_MMU
-#define __VVAR_PAGES 2
+#define __VDSO_PAGES 4
#ifndef __ASSEMBLY__
#include <generated/vdso-offsets.h>
@@ -28,8 +28,12 @@
#define COMPAT_VDSO_SYMBOL(base, name) \
(void __user *)((unsigned long)(base) + compat__vdso_##name##_offset)
+extern char compat_vdso_start[], compat_vdso_end[];
+
#endif /* CONFIG_COMPAT */
+extern char vdso_start[], vdso_end[];
+
#endif /* !__ASSEMBLY__ */
#endif /* CONFIG_MMU */
diff --git a/arch/riscv/include/asm/vdso/arch_data.h b/arch/riscv/include/asm/vdso/arch_data.h
new file mode 100644
index 000000000000..da57a3786f7a
--- /dev/null
+++ b/arch/riscv/include/asm/vdso/arch_data.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __RISCV_ASM_VDSO_ARCH_DATA_H
+#define __RISCV_ASM_VDSO_ARCH_DATA_H
+
+#include <linux/types.h>
+#include <vdso/datapage.h>
+#include <asm/hwprobe.h>
+
+struct vdso_arch_data {
+ /* Stash static answers to the hwprobe queries when all CPUs are selected. */
+ __u64 all_cpu_hwprobe_values[RISCV_HWPROBE_MAX_KEY + 1];
+
+ /* Boolean indicating all CPUs have the same static hwprobe values. */
+ __u8 homogeneous_cpus;
+};
+
+#endif /* __RISCV_ASM_VDSO_ARCH_DATA_H */
diff --git a/arch/riscv/include/asm/vdso/getrandom.h b/arch/riscv/include/asm/vdso/getrandom.h
new file mode 100644
index 000000000000..8dc92441702a
--- /dev/null
+++ b/arch/riscv/include/asm/vdso/getrandom.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2025 Xi Ruoyao <xry111@xry111.site>. All Rights Reserved.
+ */
+#ifndef __ASM_VDSO_GETRANDOM_H
+#define __ASM_VDSO_GETRANDOM_H
+
+#ifndef __ASSEMBLY__
+
+#include <asm/unistd.h>
+
+static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, unsigned int _flags)
+{
+ register long ret asm("a0");
+ register long nr asm("a7") = __NR_getrandom;
+ register void *buffer asm("a0") = _buffer;
+ register size_t len asm("a1") = _len;
+ register unsigned int flags asm("a2") = _flags;
+
+ asm volatile ("ecall\n"
+ : "+r" (ret)
+ : "r" (nr), "r" (buffer), "r" (len), "r" (flags)
+ : "memory");
+
+ return ret;
+}
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_GETRANDOM_H */
diff --git a/arch/riscv/include/asm/vdso/gettimeofday.h b/arch/riscv/include/asm/vdso/gettimeofday.h
index 77d9c2f721c4..29164f84f93c 100644
--- a/arch/riscv/include/asm/vdso/gettimeofday.h
+++ b/arch/riscv/include/asm/vdso/gettimeofday.h
@@ -9,6 +9,12 @@
#include <asm/csr.h>
#include <uapi/linux/time.h>
+/*
+ * 32-bit land is lacking generic time vsyscalls as well as the legacy 32-bit
+ * time syscalls like gettimeofday. Skip these definitions since on 32-bit.
+ */
+#ifdef CONFIG_GENERIC_TIME_VSYSCALL
+
#define VDSO_HAS_CLOCK_GETRES 1
static __always_inline
@@ -60,8 +66,10 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
return ret;
}
+#endif /* CONFIG_GENERIC_TIME_VSYSCALL */
+
static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
- const struct vdso_data *vd)
+ const struct vdso_time_data *vd)
{
/*
* The purpose of csr_read(CSR_TIME) is to trap the system into
@@ -71,18 +79,6 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
return csr_read(CSR_TIME);
}
-static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
-{
- return _vdso_data;
-}
-
-#ifdef CONFIG_TIME_NS
-static __always_inline
-const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
-{
- return _timens_data;
-}
-#endif
#endif /* !__ASSEMBLY__ */
#endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/riscv/include/asm/vdso/processor.h b/arch/riscv/include/asm/vdso/processor.h
index 134388cbaaa1..8f383f05a290 100644
--- a/arch/riscv/include/asm/vdso/processor.h
+++ b/arch/riscv/include/asm/vdso/processor.h
@@ -5,6 +5,7 @@
#ifndef __ASSEMBLY__
#include <asm/barrier.h>
+#include <asm/insn-def.h>
static inline void cpu_relax(void)
{
@@ -13,6 +14,12 @@ static inline void cpu_relax(void)
/* In lieu of a halt instruction, induce a long-latency stall. */
__asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy));
#endif
+
+ /*
+ * Reduce instruction retirement.
+ * This assumes the PC changes.
+ */
+ __asm__ __volatile__ (RISCV_PAUSE);
barrier();
}
diff --git a/arch/riscv/include/asm/vdso/vsyscall.h b/arch/riscv/include/asm/vdso/vsyscall.h
index 82fd5d83bd60..1140b54b4bc8 100644
--- a/arch/riscv/include/asm/vdso/vsyscall.h
+++ b/arch/riscv/include/asm/vdso/vsyscall.h
@@ -4,21 +4,8 @@
#ifndef __ASSEMBLY__
-#include <linux/timekeeper_internal.h>
#include <vdso/datapage.h>
-extern struct vdso_data *vdso_data;
-
-/*
- * Update the vDSO data page to keep in sync with kernel timekeeping.
- */
-static __always_inline struct vdso_data *__riscv_get_k_vdso_data(void)
-{
- return vdso_data;
-}
-
-#define __arch_get_k_vdso_data __riscv_get_k_vdso_data
-
/* The asm-generic header needs to be included after the definitions above */
#include <asm-generic/vdso/vsyscall.h>
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
new file mode 100644
index 000000000000..45c9b426fcc5
--- /dev/null
+++ b/arch/riscv/include/asm/vector.h
@@ -0,0 +1,440 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2020 SiFive
+ */
+
+#ifndef __ASM_RISCV_VECTOR_H
+#define __ASM_RISCV_VECTOR_H
+
+#include <linux/types.h>
+#include <uapi/asm-generic/errno.h>
+
+#ifdef CONFIG_RISCV_ISA_V
+
+#include <linux/stringify.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <asm/ptrace.h>
+#include <asm/cpufeature.h>
+#include <asm/csr.h>
+#include <asm/asm.h>
+#include <asm/vendorid_list.h>
+#include <asm/vendor_extensions.h>
+#include <asm/vendor_extensions/thead.h>
+
+#define __riscv_v_vstate_or(_val, TYPE) ({ \
+ typeof(_val) _res = _val; \
+ if (has_xtheadvector()) \
+ _res = (_res & ~SR_VS_THEAD) | SR_VS_##TYPE##_THEAD; \
+ else \
+ _res = (_res & ~SR_VS) | SR_VS_##TYPE; \
+ _res; \
+})
+
+#define __riscv_v_vstate_check(_val, TYPE) ({ \
+ bool _res; \
+ if (has_xtheadvector()) \
+ _res = ((_val) & SR_VS_THEAD) == SR_VS_##TYPE##_THEAD; \
+ else \
+ _res = ((_val) & SR_VS) == SR_VS_##TYPE; \
+ _res; \
+})
+
+extern unsigned long riscv_v_vsize;
+int riscv_v_setup_vsize(void);
+bool insn_is_vector(u32 insn_buf);
+bool riscv_v_first_use_handler(struct pt_regs *regs);
+void kernel_vector_begin(void);
+void kernel_vector_end(void);
+void get_cpu_vector_context(void);
+void put_cpu_vector_context(void);
+void riscv_v_thread_free(struct task_struct *tsk);
+void __init riscv_v_setup_ctx_cache(void);
+void riscv_v_thread_alloc(struct task_struct *tsk);
+
+static inline u32 riscv_v_flags(void)
+{
+ return READ_ONCE(current->thread.riscv_v_flags);
+}
+
+static __always_inline bool has_vector(void)
+{
+ return riscv_has_extension_unlikely(RISCV_ISA_EXT_ZVE32X);
+}
+
+static __always_inline bool has_xtheadvector_no_alternatives(void)
+{
+ if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR))
+ return riscv_isa_vendor_extension_available(THEAD_VENDOR_ID, XTHEADVECTOR);
+ else
+ return false;
+}
+
+static __always_inline bool has_xtheadvector(void)
+{
+ if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR))
+ return riscv_has_vendor_extension_unlikely(THEAD_VENDOR_ID,
+ RISCV_ISA_VENDOR_EXT_XTHEADVECTOR);
+ else
+ return false;
+}
+
+static inline void __riscv_v_vstate_clean(struct pt_regs *regs)
+{
+ regs->status = __riscv_v_vstate_or(regs->status, CLEAN);
+}
+
+static inline void __riscv_v_vstate_dirty(struct pt_regs *regs)
+{
+ regs->status = __riscv_v_vstate_or(regs->status, DIRTY);
+}
+
+static inline void riscv_v_vstate_off(struct pt_regs *regs)
+{
+ regs->status = __riscv_v_vstate_or(regs->status, OFF);
+}
+
+static inline void riscv_v_vstate_on(struct pt_regs *regs)
+{
+ regs->status = __riscv_v_vstate_or(regs->status, INITIAL);
+}
+
+static inline bool riscv_v_vstate_query(struct pt_regs *regs)
+{
+ return !__riscv_v_vstate_check(regs->status, OFF);
+}
+
+static __always_inline void riscv_v_enable(void)
+{
+ if (has_xtheadvector())
+ csr_set(CSR_SSTATUS, SR_VS_THEAD);
+ else
+ csr_set(CSR_SSTATUS, SR_VS);
+}
+
+static __always_inline void riscv_v_disable(void)
+{
+ if (has_xtheadvector())
+ csr_clear(CSR_SSTATUS, SR_VS_THEAD);
+ else
+ csr_clear(CSR_SSTATUS, SR_VS);
+}
+
+static __always_inline bool riscv_v_is_on(void)
+{
+ return !!(csr_read(CSR_SSTATUS) & SR_VS);
+}
+
+static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest)
+{
+ asm volatile (
+ "csrr %0, " __stringify(CSR_VSTART) "\n\t"
+ "csrr %1, " __stringify(CSR_VTYPE) "\n\t"
+ "csrr %2, " __stringify(CSR_VL) "\n\t"
+ : "=r" (dest->vstart), "=r" (dest->vtype), "=r" (dest->vl),
+ "=r" (dest->vcsr) : :);
+
+ if (has_xtheadvector()) {
+ unsigned long status;
+
+ /*
+ * CSR_VCSR is defined as
+ * [2:1] - vxrm[1:0]
+ * [0] - vxsat
+ * The earlier vector spec implemented by T-Head uses separate
+ * registers for the same bit-elements, so just combine those
+ * into the existing output field.
+ *
+ * Additionally T-Head cores need FS to be enabled when accessing
+ * the VXRM and VXSAT CSRs, otherwise ending in illegal instructions.
+ * Though the cores do not implement the VXRM and VXSAT fields in the
+ * FCSR CSR that vector-0.7.1 specifies.
+ */
+ status = csr_read_set(CSR_STATUS, SR_FS_DIRTY);
+ dest->vcsr = csr_read(CSR_VXSAT) | csr_read(CSR_VXRM) << CSR_VXRM_SHIFT;
+
+ dest->vlenb = riscv_v_vsize / 32;
+
+ if ((status & SR_FS) != SR_FS_DIRTY)
+ csr_write(CSR_STATUS, status);
+ } else {
+ dest->vcsr = csr_read(CSR_VCSR);
+ dest->vlenb = csr_read(CSR_VLENB);
+ }
+}
+
+static __always_inline void __vstate_csr_restore(struct __riscv_v_ext_state *src)
+{
+ asm volatile (
+ ".option push\n\t"
+ ".option arch, +zve32x\n\t"
+ "vsetvl x0, %2, %1\n\t"
+ ".option pop\n\t"
+ "csrw " __stringify(CSR_VSTART) ", %0\n\t"
+ : : "r" (src->vstart), "r" (src->vtype), "r" (src->vl));
+
+ if (has_xtheadvector()) {
+ unsigned long status = csr_read(CSR_SSTATUS);
+
+ /*
+ * Similar to __vstate_csr_save above, restore values for the
+ * separate VXRM and VXSAT CSRs from the vcsr variable.
+ */
+ status = csr_read_set(CSR_STATUS, SR_FS_DIRTY);
+
+ csr_write(CSR_VXRM, (src->vcsr >> CSR_VXRM_SHIFT) & CSR_VXRM_MASK);
+ csr_write(CSR_VXSAT, src->vcsr & CSR_VXSAT_MASK);
+
+ if ((status & SR_FS) != SR_FS_DIRTY)
+ csr_write(CSR_STATUS, status);
+ } else {
+ csr_write(CSR_VCSR, src->vcsr);
+ }
+}
+
+static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to,
+ void *datap)
+{
+ unsigned long vl;
+
+ riscv_v_enable();
+ __vstate_csr_save(save_to);
+ if (has_xtheadvector()) {
+ asm volatile (
+ "mv t0, %0\n\t"
+ THEAD_VSETVLI_T4X0E8M8D1
+ THEAD_VSB_V_V0T0
+ "add t0, t0, t4\n\t"
+ THEAD_VSB_V_V0T0
+ "add t0, t0, t4\n\t"
+ THEAD_VSB_V_V0T0
+ "add t0, t0, t4\n\t"
+ THEAD_VSB_V_V0T0
+ : : "r" (datap) : "memory", "t0", "t4");
+ } else {
+ asm volatile (
+ ".option push\n\t"
+ ".option arch, +zve32x\n\t"
+ "vsetvli %0, x0, e8, m8, ta, ma\n\t"
+ "vse8.v v0, (%1)\n\t"
+ "add %1, %1, %0\n\t"
+ "vse8.v v8, (%1)\n\t"
+ "add %1, %1, %0\n\t"
+ "vse8.v v16, (%1)\n\t"
+ "add %1, %1, %0\n\t"
+ "vse8.v v24, (%1)\n\t"
+ ".option pop\n\t"
+ : "=&r" (vl) : "r" (datap) : "memory");
+ }
+ riscv_v_disable();
+}
+
+static inline void __riscv_v_vstate_restore(struct __riscv_v_ext_state *restore_from,
+ void *datap)
+{
+ unsigned long vl;
+
+ riscv_v_enable();
+ if (has_xtheadvector()) {
+ asm volatile (
+ "mv t0, %0\n\t"
+ THEAD_VSETVLI_T4X0E8M8D1
+ THEAD_VLB_V_V0T0
+ "add t0, t0, t4\n\t"
+ THEAD_VLB_V_V0T0
+ "add t0, t0, t4\n\t"
+ THEAD_VLB_V_V0T0
+ "add t0, t0, t4\n\t"
+ THEAD_VLB_V_V0T0
+ : : "r" (datap) : "memory", "t0", "t4");
+ } else {
+ asm volatile (
+ ".option push\n\t"
+ ".option arch, +zve32x\n\t"
+ "vsetvli %0, x0, e8, m8, ta, ma\n\t"
+ "vle8.v v0, (%1)\n\t"
+ "add %1, %1, %0\n\t"
+ "vle8.v v8, (%1)\n\t"
+ "add %1, %1, %0\n\t"
+ "vle8.v v16, (%1)\n\t"
+ "add %1, %1, %0\n\t"
+ "vle8.v v24, (%1)\n\t"
+ ".option pop\n\t"
+ : "=&r" (vl) : "r" (datap) : "memory");
+ }
+ __vstate_csr_restore(restore_from);
+ riscv_v_disable();
+}
+
+static inline void __riscv_v_vstate_discard(void)
+{
+ unsigned long vl, vtype_inval = 1UL << (BITS_PER_LONG - 1);
+
+ riscv_v_enable();
+ if (has_xtheadvector())
+ asm volatile (THEAD_VSETVLI_T4X0E8M8D1 : : : "t4");
+ else
+ asm volatile (
+ ".option push\n\t"
+ ".option arch, +zve32x\n\t"
+ "vsetvli %0, x0, e8, m8, ta, ma\n\t"
+ ".option pop\n\t": "=&r" (vl));
+
+ asm volatile (
+ ".option push\n\t"
+ ".option arch, +zve32x\n\t"
+ "vmv.v.i v0, -1\n\t"
+ "vmv.v.i v8, -1\n\t"
+ "vmv.v.i v16, -1\n\t"
+ "vmv.v.i v24, -1\n\t"
+ "vsetvl %0, x0, %1\n\t"
+ ".option pop\n\t"
+ : "=&r" (vl) : "r" (vtype_inval));
+
+ riscv_v_disable();
+}
+
+static inline void riscv_v_vstate_discard(struct pt_regs *regs)
+{
+ if (riscv_v_vstate_query(regs)) {
+ __riscv_v_vstate_discard();
+ __riscv_v_vstate_dirty(regs);
+ }
+}
+
+static inline void riscv_v_vstate_save(struct __riscv_v_ext_state *vstate,
+ struct pt_regs *regs)
+{
+ if (__riscv_v_vstate_check(regs->status, DIRTY)) {
+ __riscv_v_vstate_save(vstate, vstate->datap);
+ __riscv_v_vstate_clean(regs);
+ }
+}
+
+static inline void riscv_v_vstate_restore(struct __riscv_v_ext_state *vstate,
+ struct pt_regs *regs)
+{
+ if (riscv_v_vstate_query(regs)) {
+ __riscv_v_vstate_restore(vstate, vstate->datap);
+ __riscv_v_vstate_clean(regs);
+ }
+}
+
+static inline void riscv_v_vstate_set_restore(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ if (riscv_v_vstate_query(regs)) {
+ set_tsk_thread_flag(task, TIF_RISCV_V_DEFER_RESTORE);
+ riscv_v_vstate_on(regs);
+ }
+}
+
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+static inline bool riscv_preempt_v_dirty(struct task_struct *task)
+{
+ return !!(task->thread.riscv_v_flags & RISCV_PREEMPT_V_DIRTY);
+}
+
+static inline bool riscv_preempt_v_restore(struct task_struct *task)
+{
+ return !!(task->thread.riscv_v_flags & RISCV_PREEMPT_V_NEED_RESTORE);
+}
+
+static inline void riscv_preempt_v_clear_dirty(struct task_struct *task)
+{
+ barrier();
+ task->thread.riscv_v_flags &= ~RISCV_PREEMPT_V_DIRTY;
+}
+
+static inline void riscv_preempt_v_set_restore(struct task_struct *task)
+{
+ barrier();
+ task->thread.riscv_v_flags |= RISCV_PREEMPT_V_NEED_RESTORE;
+}
+
+static inline bool riscv_preempt_v_started(struct task_struct *task)
+{
+ return !!(task->thread.riscv_v_flags & RISCV_PREEMPT_V);
+}
+
+#else /* !CONFIG_RISCV_ISA_V_PREEMPTIVE */
+static inline bool riscv_preempt_v_dirty(struct task_struct *task) { return false; }
+static inline bool riscv_preempt_v_restore(struct task_struct *task) { return false; }
+static inline bool riscv_preempt_v_started(struct task_struct *task) { return false; }
+#define riscv_preempt_v_clear_dirty(tsk) do {} while (0)
+#define riscv_preempt_v_set_restore(tsk) do {} while (0)
+#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */
+
+static inline void __switch_to_vector(struct task_struct *prev,
+ struct task_struct *next)
+{
+ struct pt_regs *regs;
+
+ if (riscv_preempt_v_started(prev)) {
+ if (riscv_v_is_on()) {
+ WARN_ON(prev->thread.riscv_v_flags & RISCV_V_CTX_DEPTH_MASK);
+ riscv_v_disable();
+ prev->thread.riscv_v_flags |= RISCV_PREEMPT_V_IN_SCHEDULE;
+ }
+ if (riscv_preempt_v_dirty(prev)) {
+ __riscv_v_vstate_save(&prev->thread.kernel_vstate,
+ prev->thread.kernel_vstate.datap);
+ riscv_preempt_v_clear_dirty(prev);
+ }
+ } else {
+ regs = task_pt_regs(prev);
+ riscv_v_vstate_save(&prev->thread.vstate, regs);
+ }
+
+ if (riscv_preempt_v_started(next)) {
+ if (next->thread.riscv_v_flags & RISCV_PREEMPT_V_IN_SCHEDULE) {
+ next->thread.riscv_v_flags &= ~RISCV_PREEMPT_V_IN_SCHEDULE;
+ riscv_v_enable();
+ } else {
+ riscv_preempt_v_set_restore(next);
+ }
+ } else {
+ riscv_v_vstate_set_restore(next, task_pt_regs(next));
+ }
+}
+
+void riscv_v_vstate_ctrl_init(struct task_struct *tsk);
+bool riscv_v_vstate_ctrl_user_allowed(void);
+
+#else /* ! CONFIG_RISCV_ISA_V */
+
+struct pt_regs;
+
+static inline int riscv_v_setup_vsize(void) { return -EOPNOTSUPP; }
+static __always_inline bool has_vector(void) { return false; }
+static __always_inline bool insn_is_vector(u32 insn_buf) { return false; }
+static __always_inline bool has_xtheadvector_no_alternatives(void) { return false; }
+static __always_inline bool has_xtheadvector(void) { return false; }
+static inline bool riscv_v_first_use_handler(struct pt_regs *regs) { return false; }
+static inline bool riscv_v_vstate_query(struct pt_regs *regs) { return false; }
+static inline bool riscv_v_vstate_ctrl_user_allowed(void) { return false; }
+#define riscv_v_vsize (0)
+#define riscv_v_vstate_discard(regs) do {} while (0)
+#define riscv_v_vstate_save(vstate, regs) do {} while (0)
+#define riscv_v_vstate_restore(vstate, regs) do {} while (0)
+#define __switch_to_vector(__prev, __next) do {} while (0)
+#define riscv_v_vstate_off(regs) do {} while (0)
+#define riscv_v_vstate_on(regs) do {} while (0)
+#define riscv_v_thread_free(tsk) do {} while (0)
+#define riscv_v_setup_ctx_cache() do {} while (0)
+#define riscv_v_thread_alloc(tsk) do {} while (0)
+
+#endif /* CONFIG_RISCV_ISA_V */
+
+/*
+ * Return the implementation's vlen value.
+ *
+ * riscv_v_vsize contains the value of "32 vector registers with vlenb length"
+ * so rebuild the vlen value in bits from it.
+ */
+static inline int riscv_vector_vlen(void)
+{
+ return riscv_v_vsize / 32 * 8;
+}
+
+#endif /* ! __ASM_RISCV_VECTOR_H */
diff --git a/arch/riscv/include/asm/vendor_extensions.h b/arch/riscv/include/asm/vendor_extensions.h
new file mode 100644
index 000000000000..7437304a71b9
--- /dev/null
+++ b/arch/riscv/include/asm/vendor_extensions.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2024 Rivos, Inc
+ */
+
+#ifndef _ASM_VENDOR_EXTENSIONS_H
+#define _ASM_VENDOR_EXTENSIONS_H
+
+#include <asm/cpufeature.h>
+
+#include <linux/array_size.h>
+#include <linux/types.h>
+
+/*
+ * The extension keys of each vendor must be strictly less than this value.
+ */
+#define RISCV_ISA_VENDOR_EXT_MAX 32
+
+struct riscv_isavendorinfo {
+ DECLARE_BITMAP(isa, RISCV_ISA_VENDOR_EXT_MAX);
+};
+
+struct riscv_isa_vendor_ext_data_list {
+ bool is_initialized;
+ const size_t ext_data_count;
+ const struct riscv_isa_ext_data *ext_data;
+ struct riscv_isavendorinfo per_hart_isa_bitmap[NR_CPUS];
+ struct riscv_isavendorinfo all_harts_isa_bitmap;
+};
+
+extern struct riscv_isa_vendor_ext_data_list *riscv_isa_vendor_ext_list[];
+
+extern const size_t riscv_isa_vendor_ext_list_size;
+
+/*
+ * The alternatives need some way of distinguishing between vendor extensions
+ * and errata. Incrementing all of the vendor extension keys so they are at
+ * least 0x8000 accomplishes that.
+ */
+#define RISCV_VENDOR_EXT_ALTERNATIVES_BASE 0x8000
+
+#define VENDOR_EXT_ALL_CPUS -1
+
+bool __riscv_isa_vendor_extension_available(int cpu, unsigned long vendor, unsigned int bit);
+#define riscv_cpu_isa_vendor_extension_available(cpu, vendor, ext) \
+ __riscv_isa_vendor_extension_available(cpu, vendor, RISCV_ISA_VENDOR_EXT_##ext)
+#define riscv_isa_vendor_extension_available(vendor, ext) \
+ __riscv_isa_vendor_extension_available(VENDOR_EXT_ALL_CPUS, vendor, \
+ RISCV_ISA_VENDOR_EXT_##ext)
+
+static __always_inline bool riscv_has_vendor_extension_likely(const unsigned long vendor,
+ const unsigned long ext)
+{
+ if (!IS_ENABLED(CONFIG_RISCV_ISA_VENDOR_EXT))
+ return false;
+
+ if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE))
+ return __riscv_has_extension_likely(vendor,
+ ext + RISCV_VENDOR_EXT_ALTERNATIVES_BASE);
+
+ return __riscv_isa_vendor_extension_available(VENDOR_EXT_ALL_CPUS, vendor, ext);
+}
+
+static __always_inline bool riscv_has_vendor_extension_unlikely(const unsigned long vendor,
+ const unsigned long ext)
+{
+ if (!IS_ENABLED(CONFIG_RISCV_ISA_VENDOR_EXT))
+ return false;
+
+ if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE))
+ return __riscv_has_extension_unlikely(vendor,
+ ext + RISCV_VENDOR_EXT_ALTERNATIVES_BASE);
+
+ return __riscv_isa_vendor_extension_available(VENDOR_EXT_ALL_CPUS, vendor, ext);
+}
+
+static __always_inline bool riscv_cpu_has_vendor_extension_likely(const unsigned long vendor,
+ int cpu, const unsigned long ext)
+{
+ if (!IS_ENABLED(CONFIG_RISCV_ISA_VENDOR_EXT))
+ return false;
+
+ if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) &&
+ __riscv_has_extension_likely(vendor, ext + RISCV_VENDOR_EXT_ALTERNATIVES_BASE))
+ return true;
+
+ return __riscv_isa_vendor_extension_available(cpu, vendor, ext);
+}
+
+static __always_inline bool riscv_cpu_has_vendor_extension_unlikely(const unsigned long vendor,
+ int cpu,
+ const unsigned long ext)
+{
+ if (!IS_ENABLED(CONFIG_RISCV_ISA_VENDOR_EXT))
+ return false;
+
+ if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) &&
+ __riscv_has_extension_unlikely(vendor, ext + RISCV_VENDOR_EXT_ALTERNATIVES_BASE))
+ return true;
+
+ return __riscv_isa_vendor_extension_available(cpu, vendor, ext);
+}
+
+#endif /* _ASM_VENDOR_EXTENSIONS_H */
diff --git a/arch/riscv/include/asm/vendor_extensions/andes.h b/arch/riscv/include/asm/vendor_extensions/andes.h
new file mode 100644
index 000000000000..7bb2fc43438f
--- /dev/null
+++ b/arch/riscv/include/asm/vendor_extensions/andes.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_ANDES_H
+#define _ASM_RISCV_VENDOR_EXTENSIONS_ANDES_H
+
+#include <asm/vendor_extensions.h>
+
+#include <linux/types.h>
+
+#define RISCV_ISA_VENDOR_EXT_XANDESPMU 0
+
+/*
+ * Extension keys should be strictly less than max.
+ * It is safe to increment this when necessary.
+ */
+#define RISCV_ISA_VENDOR_EXT_MAX_ANDES 32
+
+extern struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_andes;
+
+#endif
diff --git a/arch/riscv/include/asm/vendor_extensions/sifive.h b/arch/riscv/include/asm/vendor_extensions/sifive.h
new file mode 100644
index 000000000000..ac00e500361c
--- /dev/null
+++ b/arch/riscv/include/asm/vendor_extensions/sifive.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_SIFIVE_H
+#define _ASM_RISCV_VENDOR_EXTENSIONS_SIFIVE_H
+
+#include <asm/vendor_extensions.h>
+
+#include <linux/types.h>
+
+#define RISCV_ISA_VENDOR_EXT_XSFVQMACCDOD 0
+#define RISCV_ISA_VENDOR_EXT_XSFVQMACCQOQ 1
+#define RISCV_ISA_VENDOR_EXT_XSFVFNRCLIPXFQF 2
+#define RISCV_ISA_VENDOR_EXT_XSFVFWMACCQQQ 3
+
+extern struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_sifive;
+
+#endif
diff --git a/arch/riscv/include/asm/vendor_extensions/sifive_hwprobe.h b/arch/riscv/include/asm/vendor_extensions/sifive_hwprobe.h
new file mode 100644
index 000000000000..90a61abd033c
--- /dev/null
+++ b/arch/riscv/include/asm/vendor_extensions/sifive_hwprobe.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_SIFIVE_HWPROBE_H
+#define _ASM_RISCV_VENDOR_EXTENSIONS_SIFIVE_HWPROBE_H
+
+#include <linux/cpumask.h>
+
+#include <uapi/asm/hwprobe.h>
+
+#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_SIFIVE
+void hwprobe_isa_vendor_ext_sifive_0(struct riscv_hwprobe *pair, const struct cpumask *cpus);
+#else
+static inline void hwprobe_isa_vendor_ext_sifive_0(struct riscv_hwprobe *pair,
+ const struct cpumask *cpus)
+{
+ pair->value = 0;
+}
+#endif
+
+#endif
diff --git a/arch/riscv/include/asm/vendor_extensions/thead.h b/arch/riscv/include/asm/vendor_extensions/thead.h
new file mode 100644
index 000000000000..e85c75b3b340
--- /dev/null
+++ b/arch/riscv/include/asm/vendor_extensions/thead.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_H
+#define _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_H
+
+#include <asm/vendor_extensions.h>
+
+#include <linux/types.h>
+
+/*
+ * Extension keys must be strictly less than RISCV_ISA_VENDOR_EXT_MAX.
+ */
+#define RISCV_ISA_VENDOR_EXT_XTHEADVECTOR 0
+
+extern struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_thead;
+
+#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD
+void disable_xtheadvector(void);
+#else
+static inline void disable_xtheadvector(void) { }
+#endif
+
+/* Extension specific helpers */
+
+/*
+ * Vector 0.7.1 as used for example on T-Head Xuantie cores, uses an older
+ * encoding for vsetvli (ta, ma vs. d1), so provide an instruction for
+ * vsetvli t4, x0, e8, m8, d1
+ */
+#define THEAD_VSETVLI_T4X0E8M8D1 ".long 0x00307ed7\n\t"
+
+/*
+ * While in theory, the vector-0.7.1 vsb.v and vlb.v result in the same
+ * encoding as the standard vse8.v and vle8.v, compilers seem to optimize
+ * the call resulting in a different encoding and then using a value for
+ * the "mop" field that is not part of vector-0.7.1
+ * So encode specific variants for vstate_save and _restore.
+ */
+#define THEAD_VSB_V_V0T0 ".long 0x02028027\n\t"
+#define THEAD_VSB_V_V8T0 ".long 0x02028427\n\t"
+#define THEAD_VSB_V_V16T0 ".long 0x02028827\n\t"
+#define THEAD_VSB_V_V24T0 ".long 0x02028c27\n\t"
+#define THEAD_VLB_V_V0T0 ".long 0x012028007\n\t"
+#define THEAD_VLB_V_V8T0 ".long 0x012028407\n\t"
+#define THEAD_VLB_V_V16T0 ".long 0x012028807\n\t"
+#define THEAD_VLB_V_V24T0 ".long 0x012028c07\n\t"
+
+#endif
diff --git a/arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h b/arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h
new file mode 100644
index 000000000000..65a9c5612466
--- /dev/null
+++ b/arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_HWPROBE_H
+#define _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_HWPROBE_H
+
+#include <linux/cpumask.h>
+
+#include <uapi/asm/hwprobe.h>
+
+#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD
+void hwprobe_isa_vendor_ext_thead_0(struct riscv_hwprobe *pair, const struct cpumask *cpus);
+#else
+static inline void hwprobe_isa_vendor_ext_thead_0(struct riscv_hwprobe *pair,
+ const struct cpumask *cpus)
+{
+ pair->value = 0;
+}
+#endif
+
+#endif
diff --git a/arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h b/arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h
new file mode 100644
index 000000000000..6b9293e984a9
--- /dev/null
+++ b/arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2024 Rivos, Inc
+ */
+
+#ifndef _ASM_RISCV_SYS_HWPROBE_H
+#define _ASM_RISCV_SYS_HWPROBE_H
+
+#include <asm/cpufeature.h>
+
+#define VENDOR_EXT_KEY(ext) \
+ do { \
+ if (__riscv_isa_extension_available(isainfo->isa, RISCV_ISA_VENDOR_EXT_##ext)) \
+ pair->value |= RISCV_HWPROBE_VENDOR_EXT_##ext; \
+ else \
+ missing |= RISCV_HWPROBE_VENDOR_EXT_##ext; \
+ } while (false)
+
+/*
+ * Loop through and record extensions that 1) anyone has, and 2) anyone
+ * doesn't have.
+ *
+ * _extension_checks is an arbitrary C block to set the values of pair->value
+ * and missing. It should be filled with VENDOR_EXT_KEY expressions.
+ */
+#define VENDOR_EXTENSION_SUPPORTED(pair, cpus, per_hart_vendor_bitmap, _extension_checks) \
+ do { \
+ int cpu; \
+ u64 missing = 0; \
+ for_each_cpu(cpu, (cpus)) { \
+ struct riscv_isavendorinfo *isainfo = &(per_hart_vendor_bitmap)[cpu]; \
+ _extension_checks \
+ } \
+ (pair)->value &= ~missing; \
+ } while (false) \
+
+#endif /* _ASM_RISCV_SYS_HWPROBE_H */
diff --git a/arch/riscv/include/asm/vendorid_list.h b/arch/riscv/include/asm/vendorid_list.h
index cb89af3f0704..a5150cdf34d8 100644
--- a/arch/riscv/include/asm/vendorid_list.h
+++ b/arch/riscv/include/asm/vendorid_list.h
@@ -5,6 +5,8 @@
#ifndef ASM_VENDOR_LIST_H
#define ASM_VENDOR_LIST_H
+#define ANDES_VENDOR_ID 0x31e
+#define MICROCHIP_VENDOR_ID 0x029
#define SIFIVE_VENDOR_ID 0x489
#define THEAD_VENDOR_ID 0x5b7
diff --git a/arch/riscv/include/asm/vmalloc.h b/arch/riscv/include/asm/vmalloc.h
index ff9abc00d139..fefe94dc98e2 100644
--- a/arch/riscv/include/asm/vmalloc.h
+++ b/arch/riscv/include/asm/vmalloc.h
@@ -1,4 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
#ifndef _ASM_RISCV_VMALLOC_H
#define _ASM_RISCV_VMALLOC_H
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+
+extern bool pgtable_l4_enabled, pgtable_l5_enabled;
+
+#define IOREMAP_MAX_ORDER (PUD_SHIFT)
+
+#define arch_vmap_pud_supported arch_vmap_pud_supported
+static inline bool arch_vmap_pud_supported(pgprot_t prot)
+{
+ return pgtable_l4_enabled || pgtable_l5_enabled;
+}
+
+#define arch_vmap_pmd_supported arch_vmap_pmd_supported
+static inline bool arch_vmap_pmd_supported(pgprot_t prot)
+{
+ return true;
+}
+
+#endif
+
#endif /* _ASM_RISCV_VMALLOC_H */
diff --git a/arch/riscv/include/asm/word-at-a-time.h b/arch/riscv/include/asm/word-at-a-time.h
index 7c086ac6ecd4..3802cda71ab7 100644
--- a/arch/riscv/include/asm/word-at-a-time.h
+++ b/arch/riscv/include/asm/word-at-a-time.h
@@ -9,7 +9,9 @@
#define _ASM_RISCV_WORD_AT_A_TIME_H
-#include <linux/kernel.h>
+#include <asm/asm-extable.h>
+#include <linux/bitops.h>
+#include <linux/wordpart.h>
struct word_at_a_time {
const unsigned long one_bits, high_bits;
@@ -45,4 +47,30 @@ static inline unsigned long find_zero(unsigned long mask)
/* The mask we created is directly usable as a bytemask */
#define zero_bytemask(mask) (mask)
+#ifdef CONFIG_DCACHE_WORD_ACCESS
+
+/*
+ * Load an unaligned word from kernel space.
+ *
+ * In the (very unlikely) case of the word being a page-crosser
+ * and the next page not being mapped, take the exception and
+ * return zeroes in the non-existing part.
+ */
+static inline unsigned long load_unaligned_zeropad(const void *addr)
+{
+ unsigned long ret;
+
+ /* Load word from unaligned pointer addr */
+ asm(
+ "1: " REG_L " %0, %2\n"
+ "2:\n"
+ _ASM_EXTABLE_LOAD_UNALIGNED_ZEROPAD(1b, 2b, %0, %1)
+ : "=&r" (ret)
+ : "r" (addr), "m" (*(unsigned long *)addr));
+
+ return ret;
+}
+
+#endif /* CONFIG_DCACHE_WORD_ACCESS */
+
#endif /* _ASM_RISCV_WORD_AT_A_TIME_H */
diff --git a/arch/riscv/include/asm/xip_fixup.h b/arch/riscv/include/asm/xip_fixup.h
index d4ffc3c37649..f3d56299bc22 100644
--- a/arch/riscv/include/asm/xip_fixup.h
+++ b/arch/riscv/include/asm/xip_fixup.h
@@ -9,18 +9,36 @@
#ifdef CONFIG_XIP_KERNEL
.macro XIP_FIXUP_OFFSET reg
- REG_L t0, _xip_fixup
+ /* Fix-up address in Flash into address in RAM early during boot before
+ * MMU is up. Because generated code "thinks" data is in Flash, but it
+ * is actually in RAM (actually data is also in Flash, but Flash is
+ * read-only, thus we need to use the data residing in RAM).
+ *
+ * The start of data in Flash is _sdata and the start of data in RAM is
+ * CONFIG_PHYS_RAM_BASE. So this fix-up essentially does this:
+ * reg += CONFIG_PHYS_RAM_BASE - _start
+ */
+ li t0, CONFIG_PHYS_RAM_BASE
add \reg, \reg, t0
+ la t0, _sdata
+ sub \reg, \reg, t0
.endm
.macro XIP_FIXUP_FLASH_OFFSET reg
- la t1, __data_loc
- REG_L t1, _xip_phys_offset
- sub \reg, \reg, t1
+ /* In linker script, at the transition from read-only section to
+ * writable section, the VMA is increased while LMA remains the same.
+ * (See in linker script how _sdata, __data_loc and LOAD_OFFSET is
+ * changed)
+ *
+ * Consequently, early during boot before MMU is up, the generated code
+ * reads the "writable" section at wrong addresses, because VMA is used
+ * by compiler to generate code, but the data is located in Flash using
+ * LMA.
+ */
+ la t0, _sdata
+ sub \reg, \reg, t0
+ la t0, __data_loc
add \reg, \reg, t0
.endm
-
-_xip_fixup: .dword CONFIG_PHYS_RAM_BASE - CONFIG_XIP_PHYS_ADDR - XIP_OFFSET
-_xip_phys_offset: .dword CONFIG_XIP_PHYS_ADDR + XIP_OFFSET
#else
.macro XIP_FIXUP_OFFSET reg
.endm
diff --git a/arch/riscv/include/asm/xor.h b/arch/riscv/include/asm/xor.h
new file mode 100644
index 000000000000..96011861e46b
--- /dev/null
+++ b/arch/riscv/include/asm/xor.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2021 SiFive
+ */
+
+#include <linux/hardirq.h>
+#include <asm-generic/xor.h>
+#ifdef CONFIG_RISCV_ISA_V
+#include <asm/vector.h>
+#include <asm/switch_to.h>
+#include <asm/asm-prototypes.h>
+
+static void xor_vector_2(unsigned long bytes, unsigned long *__restrict p1,
+ const unsigned long *__restrict p2)
+{
+ kernel_vector_begin();
+ xor_regs_2_(bytes, p1, p2);
+ kernel_vector_end();
+}
+
+static void xor_vector_3(unsigned long bytes, unsigned long *__restrict p1,
+ const unsigned long *__restrict p2,
+ const unsigned long *__restrict p3)
+{
+ kernel_vector_begin();
+ xor_regs_3_(bytes, p1, p2, p3);
+ kernel_vector_end();
+}
+
+static void xor_vector_4(unsigned long bytes, unsigned long *__restrict p1,
+ const unsigned long *__restrict p2,
+ const unsigned long *__restrict p3,
+ const unsigned long *__restrict p4)
+{
+ kernel_vector_begin();
+ xor_regs_4_(bytes, p1, p2, p3, p4);
+ kernel_vector_end();
+}
+
+static void xor_vector_5(unsigned long bytes, unsigned long *__restrict p1,
+ const unsigned long *__restrict p2,
+ const unsigned long *__restrict p3,
+ const unsigned long *__restrict p4,
+ const unsigned long *__restrict p5)
+{
+ kernel_vector_begin();
+ xor_regs_5_(bytes, p1, p2, p3, p4, p5);
+ kernel_vector_end();
+}
+
+static struct xor_block_template xor_block_rvv = {
+ .name = "rvv",
+ .do_2 = xor_vector_2,
+ .do_3 = xor_vector_3,
+ .do_4 = xor_vector_4,
+ .do_5 = xor_vector_5
+};
+
+#undef XOR_TRY_TEMPLATES
+#define XOR_TRY_TEMPLATES \
+ do { \
+ xor_speed(&xor_block_8regs); \
+ xor_speed(&xor_block_32regs); \
+ if (has_vector()) { \
+ xor_speed(&xor_block_rvv);\
+ } \
+ } while (0)
+#endif
diff --git a/arch/riscv/include/uapi/asm/Kbuild b/arch/riscv/include/uapi/asm/Kbuild
index f66554cd5c45..89ac01faa5ae 100644
--- a/arch/riscv/include/uapi/asm/Kbuild
+++ b/arch/riscv/include/uapi/asm/Kbuild
@@ -1 +1,3 @@
# SPDX-License-Identifier: GPL-2.0
+syscall-y += unistd_32.h
+syscall-y += unistd_64.h
diff --git a/arch/riscv/include/uapi/asm/auxvec.h b/arch/riscv/include/uapi/asm/auxvec.h
index 32c73ba1d531..95050ebe9ad0 100644
--- a/arch/riscv/include/uapi/asm/auxvec.h
+++ b/arch/riscv/include/uapi/asm/auxvec.h
@@ -30,8 +30,11 @@
#define AT_L1D_CACHEGEOMETRY 43
#define AT_L2_CACHESIZE 44
#define AT_L2_CACHEGEOMETRY 45
+#define AT_L3_CACHESIZE 46
+#define AT_L3_CACHEGEOMETRY 47
/* entries in ARCH_DLINFO */
-#define AT_VECTOR_SIZE_ARCH 7
+#define AT_VECTOR_SIZE_ARCH 10
+#define AT_MINSIGSTKSZ 51
#endif /* _UAPI_ASM_RISCV_AUXVEC_H */
diff --git a/arch/riscv/include/uapi/asm/elf.h b/arch/riscv/include/uapi/asm/elf.h
index d696d6610231..11a71b8533d5 100644
--- a/arch/riscv/include/uapi/asm/elf.h
+++ b/arch/riscv/include/uapi/asm/elf.h
@@ -49,6 +49,7 @@ typedef union __riscv_fp_state elf_fpregset_t;
#define R_RISCV_TLS_DTPREL64 9
#define R_RISCV_TLS_TPREL32 10
#define R_RISCV_TLS_TPREL64 11
+#define R_RISCV_IRELATIVE 58
/* Relocation types not used by the dynamic linker */
#define R_RISCV_BRANCH 16
@@ -81,7 +82,6 @@ typedef union __riscv_fp_state elf_fpregset_t;
#define R_RISCV_ALIGN 43
#define R_RISCV_RVC_BRANCH 44
#define R_RISCV_RVC_JUMP 45
-#define R_RISCV_LUI 46
#define R_RISCV_GPREL_I 47
#define R_RISCV_GPREL_S 48
#define R_RISCV_TPREL_I 49
@@ -93,6 +93,9 @@ typedef union __riscv_fp_state elf_fpregset_t;
#define R_RISCV_SET16 55
#define R_RISCV_SET32 56
#define R_RISCV_32_PCREL 57
+#define R_RISCV_PLT32 59
+#define R_RISCV_SET_ULEB128 60
+#define R_RISCV_SUB_ULEB128 61
#endif /* _UAPI_ASM_RISCV_ELF_H */
diff --git a/arch/riscv/include/uapi/asm/hwcap.h b/arch/riscv/include/uapi/asm/hwcap.h
index 46dc3f5ee99f..c52bb7bbbabe 100644
--- a/arch/riscv/include/uapi/asm/hwcap.h
+++ b/arch/riscv/include/uapi/asm/hwcap.h
@@ -21,5 +21,6 @@
#define COMPAT_HWCAP_ISA_F (1 << ('F' - 'A'))
#define COMPAT_HWCAP_ISA_D (1 << ('D' - 'A'))
#define COMPAT_HWCAP_ISA_C (1 << ('C' - 'A'))
+#define COMPAT_HWCAP_ISA_V (1 << ('V' - 'A'))
#endif /* _UAPI_ASM_RISCV_HWCAP_H */
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
new file mode 100644
index 000000000000..aaf6ad970499
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright 2023-2024 Rivos, Inc
+ */
+
+#ifndef _UAPI_ASM_HWPROBE_H
+#define _UAPI_ASM_HWPROBE_H
+
+#include <linux/types.h>
+
+/*
+ * Interface for probing hardware capabilities from userspace, see
+ * Documentation/arch/riscv/hwprobe.rst for more information.
+ */
+struct riscv_hwprobe {
+ __s64 key;
+ __u64 value;
+};
+
+#define RISCV_HWPROBE_KEY_MVENDORID 0
+#define RISCV_HWPROBE_KEY_MARCHID 1
+#define RISCV_HWPROBE_KEY_MIMPID 2
+#define RISCV_HWPROBE_KEY_BASE_BEHAVIOR 3
+#define RISCV_HWPROBE_BASE_BEHAVIOR_IMA (1 << 0)
+#define RISCV_HWPROBE_KEY_IMA_EXT_0 4
+#define RISCV_HWPROBE_IMA_FD (1 << 0)
+#define RISCV_HWPROBE_IMA_C (1 << 1)
+#define RISCV_HWPROBE_IMA_V (1 << 2)
+#define RISCV_HWPROBE_EXT_ZBA (1 << 3)
+#define RISCV_HWPROBE_EXT_ZBB (1 << 4)
+#define RISCV_HWPROBE_EXT_ZBS (1 << 5)
+#define RISCV_HWPROBE_EXT_ZICBOZ (1 << 6)
+#define RISCV_HWPROBE_EXT_ZBC (1 << 7)
+#define RISCV_HWPROBE_EXT_ZBKB (1 << 8)
+#define RISCV_HWPROBE_EXT_ZBKC (1 << 9)
+#define RISCV_HWPROBE_EXT_ZBKX (1 << 10)
+#define RISCV_HWPROBE_EXT_ZKND (1 << 11)
+#define RISCV_HWPROBE_EXT_ZKNE (1 << 12)
+#define RISCV_HWPROBE_EXT_ZKNH (1 << 13)
+#define RISCV_HWPROBE_EXT_ZKSED (1 << 14)
+#define RISCV_HWPROBE_EXT_ZKSH (1 << 15)
+#define RISCV_HWPROBE_EXT_ZKT (1 << 16)
+#define RISCV_HWPROBE_EXT_ZVBB (1 << 17)
+#define RISCV_HWPROBE_EXT_ZVBC (1 << 18)
+#define RISCV_HWPROBE_EXT_ZVKB (1 << 19)
+#define RISCV_HWPROBE_EXT_ZVKG (1 << 20)
+#define RISCV_HWPROBE_EXT_ZVKNED (1 << 21)
+#define RISCV_HWPROBE_EXT_ZVKNHA (1 << 22)
+#define RISCV_HWPROBE_EXT_ZVKNHB (1 << 23)
+#define RISCV_HWPROBE_EXT_ZVKSED (1 << 24)
+#define RISCV_HWPROBE_EXT_ZVKSH (1 << 25)
+#define RISCV_HWPROBE_EXT_ZVKT (1 << 26)
+#define RISCV_HWPROBE_EXT_ZFH (1 << 27)
+#define RISCV_HWPROBE_EXT_ZFHMIN (1 << 28)
+#define RISCV_HWPROBE_EXT_ZIHINTNTL (1 << 29)
+#define RISCV_HWPROBE_EXT_ZVFH (1 << 30)
+#define RISCV_HWPROBE_EXT_ZVFHMIN (1ULL << 31)
+#define RISCV_HWPROBE_EXT_ZFA (1ULL << 32)
+#define RISCV_HWPROBE_EXT_ZTSO (1ULL << 33)
+#define RISCV_HWPROBE_EXT_ZACAS (1ULL << 34)
+#define RISCV_HWPROBE_EXT_ZICOND (1ULL << 35)
+#define RISCV_HWPROBE_EXT_ZIHINTPAUSE (1ULL << 36)
+#define RISCV_HWPROBE_EXT_ZVE32X (1ULL << 37)
+#define RISCV_HWPROBE_EXT_ZVE32F (1ULL << 38)
+#define RISCV_HWPROBE_EXT_ZVE64X (1ULL << 39)
+#define RISCV_HWPROBE_EXT_ZVE64F (1ULL << 40)
+#define RISCV_HWPROBE_EXT_ZVE64D (1ULL << 41)
+#define RISCV_HWPROBE_EXT_ZIMOP (1ULL << 42)
+#define RISCV_HWPROBE_EXT_ZCA (1ULL << 43)
+#define RISCV_HWPROBE_EXT_ZCB (1ULL << 44)
+#define RISCV_HWPROBE_EXT_ZCD (1ULL << 45)
+#define RISCV_HWPROBE_EXT_ZCF (1ULL << 46)
+#define RISCV_HWPROBE_EXT_ZCMOP (1ULL << 47)
+#define RISCV_HWPROBE_EXT_ZAWRS (1ULL << 48)
+#define RISCV_HWPROBE_EXT_SUPM (1ULL << 49)
+#define RISCV_HWPROBE_EXT_ZICNTR (1ULL << 50)
+#define RISCV_HWPROBE_EXT_ZIHPM (1ULL << 51)
+#define RISCV_HWPROBE_EXT_ZFBFMIN (1ULL << 52)
+#define RISCV_HWPROBE_EXT_ZVFBFMIN (1ULL << 53)
+#define RISCV_HWPROBE_EXT_ZVFBFWMA (1ULL << 54)
+#define RISCV_HWPROBE_EXT_ZICBOM (1ULL << 55)
+#define RISCV_HWPROBE_EXT_ZAAMO (1ULL << 56)
+#define RISCV_HWPROBE_EXT_ZALRSC (1ULL << 57)
+#define RISCV_HWPROBE_EXT_ZABHA (1ULL << 58)
+#define RISCV_HWPROBE_KEY_CPUPERF_0 5
+#define RISCV_HWPROBE_MISALIGNED_UNKNOWN (0 << 0)
+#define RISCV_HWPROBE_MISALIGNED_EMULATED (1 << 0)
+#define RISCV_HWPROBE_MISALIGNED_SLOW (2 << 0)
+#define RISCV_HWPROBE_MISALIGNED_FAST (3 << 0)
+#define RISCV_HWPROBE_MISALIGNED_UNSUPPORTED (4 << 0)
+#define RISCV_HWPROBE_MISALIGNED_MASK (7 << 0)
+#define RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE 6
+#define RISCV_HWPROBE_KEY_HIGHEST_VIRT_ADDRESS 7
+#define RISCV_HWPROBE_KEY_TIME_CSR_FREQ 8
+#define RISCV_HWPROBE_KEY_MISALIGNED_SCALAR_PERF 9
+#define RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN 0
+#define RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED 1
+#define RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW 2
+#define RISCV_HWPROBE_MISALIGNED_SCALAR_FAST 3
+#define RISCV_HWPROBE_MISALIGNED_SCALAR_UNSUPPORTED 4
+#define RISCV_HWPROBE_KEY_MISALIGNED_VECTOR_PERF 10
+#define RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN 0
+#define RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW 2
+#define RISCV_HWPROBE_MISALIGNED_VECTOR_FAST 3
+#define RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED 4
+#define RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0 11
+#define RISCV_HWPROBE_KEY_ZICBOM_BLOCK_SIZE 12
+#define RISCV_HWPROBE_KEY_VENDOR_EXT_SIFIVE_0 13
+/* Increase RISCV_HWPROBE_MAX_KEY when adding items. */
+
+/* Flags */
+#define RISCV_HWPROBE_WHICH_CPUS (1 << 0)
+
+#endif
diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index 6119368ba6d5..5f59fd226cc5 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -12,9 +12,10 @@
#ifndef __ASSEMBLY__
#include <linux/types.h>
+#include <asm/bitsperlong.h>
#include <asm/ptrace.h>
-#define __KVM_HAVE_READONLY_MEM
+#define __KVM_HAVE_IRQ_LINE
#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
@@ -48,6 +49,12 @@ struct kvm_sregs {
/* CONFIG registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
struct kvm_riscv_config {
unsigned long isa;
+ unsigned long zicbom_block_size;
+ unsigned long mvendorid;
+ unsigned long marchid;
+ unsigned long mimpid;
+ unsigned long zicboz_block_size;
+ unsigned long satp_mode;
};
/* CORE registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
@@ -60,7 +67,7 @@ struct kvm_riscv_core {
#define KVM_RISCV_MODE_S 1
#define KVM_RISCV_MODE_U 0
-/* CSR registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
+/* General CSR registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
struct kvm_riscv_csr {
unsigned long sstatus;
unsigned long sie;
@@ -72,6 +79,23 @@ struct kvm_riscv_csr {
unsigned long sip;
unsigned long satp;
unsigned long scounteren;
+ unsigned long senvcfg;
+};
+
+/* AIA CSR registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
+struct kvm_riscv_aia_csr {
+ unsigned long siselect;
+ unsigned long iprio1;
+ unsigned long iprio2;
+ unsigned long sieh;
+ unsigned long siph;
+ unsigned long iprio1h;
+ unsigned long iprio2h;
+};
+
+/* Smstateen CSR for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
+struct kvm_riscv_smstateen_csr {
+ unsigned long sstateen0;
};
/* TIMER registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
@@ -96,19 +120,108 @@ enum KVM_RISCV_ISA_EXT_ID {
KVM_RISCV_ISA_EXT_H,
KVM_RISCV_ISA_EXT_I,
KVM_RISCV_ISA_EXT_M,
+ KVM_RISCV_ISA_EXT_SVPBMT,
+ KVM_RISCV_ISA_EXT_SSTC,
+ KVM_RISCV_ISA_EXT_SVINVAL,
+ KVM_RISCV_ISA_EXT_ZIHINTPAUSE,
+ KVM_RISCV_ISA_EXT_ZICBOM,
+ KVM_RISCV_ISA_EXT_ZICBOZ,
+ KVM_RISCV_ISA_EXT_ZBB,
+ KVM_RISCV_ISA_EXT_SSAIA,
+ KVM_RISCV_ISA_EXT_V,
+ KVM_RISCV_ISA_EXT_SVNAPOT,
+ KVM_RISCV_ISA_EXT_ZBA,
+ KVM_RISCV_ISA_EXT_ZBS,
+ KVM_RISCV_ISA_EXT_ZICNTR,
+ KVM_RISCV_ISA_EXT_ZICSR,
+ KVM_RISCV_ISA_EXT_ZIFENCEI,
+ KVM_RISCV_ISA_EXT_ZIHPM,
+ KVM_RISCV_ISA_EXT_SMSTATEEN,
+ KVM_RISCV_ISA_EXT_ZICOND,
+ KVM_RISCV_ISA_EXT_ZBC,
+ KVM_RISCV_ISA_EXT_ZBKB,
+ KVM_RISCV_ISA_EXT_ZBKC,
+ KVM_RISCV_ISA_EXT_ZBKX,
+ KVM_RISCV_ISA_EXT_ZKND,
+ KVM_RISCV_ISA_EXT_ZKNE,
+ KVM_RISCV_ISA_EXT_ZKNH,
+ KVM_RISCV_ISA_EXT_ZKR,
+ KVM_RISCV_ISA_EXT_ZKSED,
+ KVM_RISCV_ISA_EXT_ZKSH,
+ KVM_RISCV_ISA_EXT_ZKT,
+ KVM_RISCV_ISA_EXT_ZVBB,
+ KVM_RISCV_ISA_EXT_ZVBC,
+ KVM_RISCV_ISA_EXT_ZVKB,
+ KVM_RISCV_ISA_EXT_ZVKG,
+ KVM_RISCV_ISA_EXT_ZVKNED,
+ KVM_RISCV_ISA_EXT_ZVKNHA,
+ KVM_RISCV_ISA_EXT_ZVKNHB,
+ KVM_RISCV_ISA_EXT_ZVKSED,
+ KVM_RISCV_ISA_EXT_ZVKSH,
+ KVM_RISCV_ISA_EXT_ZVKT,
+ KVM_RISCV_ISA_EXT_ZFH,
+ KVM_RISCV_ISA_EXT_ZFHMIN,
+ KVM_RISCV_ISA_EXT_ZIHINTNTL,
+ KVM_RISCV_ISA_EXT_ZVFH,
+ KVM_RISCV_ISA_EXT_ZVFHMIN,
+ KVM_RISCV_ISA_EXT_ZFA,
+ KVM_RISCV_ISA_EXT_ZTSO,
+ KVM_RISCV_ISA_EXT_ZACAS,
+ KVM_RISCV_ISA_EXT_SSCOFPMF,
+ KVM_RISCV_ISA_EXT_ZIMOP,
+ KVM_RISCV_ISA_EXT_ZCA,
+ KVM_RISCV_ISA_EXT_ZCB,
+ KVM_RISCV_ISA_EXT_ZCD,
+ KVM_RISCV_ISA_EXT_ZCF,
+ KVM_RISCV_ISA_EXT_ZCMOP,
+ KVM_RISCV_ISA_EXT_ZAWRS,
+ KVM_RISCV_ISA_EXT_SMNPM,
+ KVM_RISCV_ISA_EXT_SSNPM,
+ KVM_RISCV_ISA_EXT_SVADE,
+ KVM_RISCV_ISA_EXT_SVADU,
+ KVM_RISCV_ISA_EXT_SVVPTC,
+ KVM_RISCV_ISA_EXT_ZABHA,
+ KVM_RISCV_ISA_EXT_ZICCRSE,
+ KVM_RISCV_ISA_EXT_ZAAMO,
+ KVM_RISCV_ISA_EXT_ZALRSC,
KVM_RISCV_ISA_EXT_MAX,
};
+/*
+ * SBI extension IDs specific to KVM. This is not the same as the SBI
+ * extension IDs defined by the RISC-V SBI specification.
+ */
+enum KVM_RISCV_SBI_EXT_ID {
+ KVM_RISCV_SBI_EXT_V01 = 0,
+ KVM_RISCV_SBI_EXT_TIME,
+ KVM_RISCV_SBI_EXT_IPI,
+ KVM_RISCV_SBI_EXT_RFENCE,
+ KVM_RISCV_SBI_EXT_SRST,
+ KVM_RISCV_SBI_EXT_HSM,
+ KVM_RISCV_SBI_EXT_PMU,
+ KVM_RISCV_SBI_EXT_EXPERIMENTAL,
+ KVM_RISCV_SBI_EXT_VENDOR,
+ KVM_RISCV_SBI_EXT_DBCN,
+ KVM_RISCV_SBI_EXT_STA,
+ KVM_RISCV_SBI_EXT_SUSP,
+ KVM_RISCV_SBI_EXT_MAX,
+};
+
+/* SBI STA extension registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
+struct kvm_riscv_sbi_sta {
+ unsigned long shmem_lo;
+ unsigned long shmem_hi;
+};
+
/* Possible states for kvm_riscv_timer */
#define KVM_RISCV_TIMER_STATE_OFF 0
#define KVM_RISCV_TIMER_STATE_ON 1
-#define KVM_REG_SIZE(id) \
- (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
-
/* If you need to interpret the index values, here is the key: */
#define KVM_REG_RISCV_TYPE_MASK 0x00000000FF000000
#define KVM_REG_RISCV_TYPE_SHIFT 24
+#define KVM_REG_RISCV_SUBTYPE_MASK 0x0000000000FF0000
+#define KVM_REG_RISCV_SUBTYPE_SHIFT 16
/* Config registers are mapped as type 1 */
#define KVM_REG_RISCV_CONFIG (0x01 << KVM_REG_RISCV_TYPE_SHIFT)
@@ -122,8 +235,15 @@ enum KVM_RISCV_ISA_EXT_ID {
/* Control and status registers are mapped as type 3 */
#define KVM_REG_RISCV_CSR (0x03 << KVM_REG_RISCV_TYPE_SHIFT)
+#define KVM_REG_RISCV_CSR_GENERAL (0x0 << KVM_REG_RISCV_SUBTYPE_SHIFT)
+#define KVM_REG_RISCV_CSR_AIA (0x1 << KVM_REG_RISCV_SUBTYPE_SHIFT)
+#define KVM_REG_RISCV_CSR_SMSTATEEN (0x2 << KVM_REG_RISCV_SUBTYPE_SHIFT)
#define KVM_REG_RISCV_CSR_REG(name) \
(offsetof(struct kvm_riscv_csr, name) / sizeof(unsigned long))
+#define KVM_REG_RISCV_CSR_AIA_REG(name) \
+ (offsetof(struct kvm_riscv_aia_csr, name) / sizeof(unsigned long))
+#define KVM_REG_RISCV_CSR_SMSTATEEN_REG(name) \
+ (offsetof(struct kvm_riscv_smstateen_csr, name) / sizeof(unsigned long))
/* Timer registers are mapped as type 4 */
#define KVM_REG_RISCV_TIMER (0x04 << KVM_REG_RISCV_TYPE_SHIFT)
@@ -142,6 +262,111 @@ enum KVM_RISCV_ISA_EXT_ID {
/* ISA Extension registers are mapped as type 7 */
#define KVM_REG_RISCV_ISA_EXT (0x07 << KVM_REG_RISCV_TYPE_SHIFT)
+#define KVM_REG_RISCV_ISA_SINGLE (0x0 << KVM_REG_RISCV_SUBTYPE_SHIFT)
+#define KVM_REG_RISCV_ISA_MULTI_EN (0x1 << KVM_REG_RISCV_SUBTYPE_SHIFT)
+#define KVM_REG_RISCV_ISA_MULTI_DIS (0x2 << KVM_REG_RISCV_SUBTYPE_SHIFT)
+#define KVM_REG_RISCV_ISA_MULTI_REG(__ext_id) \
+ ((__ext_id) / __BITS_PER_LONG)
+#define KVM_REG_RISCV_ISA_MULTI_MASK(__ext_id) \
+ (1UL << ((__ext_id) % __BITS_PER_LONG))
+#define KVM_REG_RISCV_ISA_MULTI_REG_LAST \
+ KVM_REG_RISCV_ISA_MULTI_REG(KVM_RISCV_ISA_EXT_MAX - 1)
+
+/* SBI extension registers are mapped as type 8 */
+#define KVM_REG_RISCV_SBI_EXT (0x08 << KVM_REG_RISCV_TYPE_SHIFT)
+#define KVM_REG_RISCV_SBI_SINGLE (0x0 << KVM_REG_RISCV_SUBTYPE_SHIFT)
+#define KVM_REG_RISCV_SBI_MULTI_EN (0x1 << KVM_REG_RISCV_SUBTYPE_SHIFT)
+#define KVM_REG_RISCV_SBI_MULTI_DIS (0x2 << KVM_REG_RISCV_SUBTYPE_SHIFT)
+#define KVM_REG_RISCV_SBI_MULTI_REG(__ext_id) \
+ ((__ext_id) / __BITS_PER_LONG)
+#define KVM_REG_RISCV_SBI_MULTI_MASK(__ext_id) \
+ (1UL << ((__ext_id) % __BITS_PER_LONG))
+#define KVM_REG_RISCV_SBI_MULTI_REG_LAST \
+ KVM_REG_RISCV_SBI_MULTI_REG(KVM_RISCV_SBI_EXT_MAX - 1)
+
+/* V extension registers are mapped as type 9 */
+#define KVM_REG_RISCV_VECTOR (0x09 << KVM_REG_RISCV_TYPE_SHIFT)
+#define KVM_REG_RISCV_VECTOR_CSR_REG(name) \
+ (offsetof(struct __riscv_v_ext_state, name) / sizeof(unsigned long))
+#define KVM_REG_RISCV_VECTOR_REG(n) \
+ ((n) + sizeof(struct __riscv_v_ext_state) / sizeof(unsigned long))
+
+/* Registers for specific SBI extensions are mapped as type 10 */
+#define KVM_REG_RISCV_SBI_STATE (0x0a << KVM_REG_RISCV_TYPE_SHIFT)
+#define KVM_REG_RISCV_SBI_STA (0x0 << KVM_REG_RISCV_SUBTYPE_SHIFT)
+#define KVM_REG_RISCV_SBI_STA_REG(name) \
+ (offsetof(struct kvm_riscv_sbi_sta, name) / sizeof(unsigned long))
+
+/* Device Control API: RISC-V AIA */
+#define KVM_DEV_RISCV_APLIC_ALIGN 0x1000
+#define KVM_DEV_RISCV_APLIC_SIZE 0x4000
+#define KVM_DEV_RISCV_APLIC_MAX_HARTS 0x4000
+#define KVM_DEV_RISCV_IMSIC_ALIGN 0x1000
+#define KVM_DEV_RISCV_IMSIC_SIZE 0x1000
+
+#define KVM_DEV_RISCV_AIA_GRP_CONFIG 0
+#define KVM_DEV_RISCV_AIA_CONFIG_MODE 0
+#define KVM_DEV_RISCV_AIA_CONFIG_IDS 1
+#define KVM_DEV_RISCV_AIA_CONFIG_SRCS 2
+#define KVM_DEV_RISCV_AIA_CONFIG_GROUP_BITS 3
+#define KVM_DEV_RISCV_AIA_CONFIG_GROUP_SHIFT 4
+#define KVM_DEV_RISCV_AIA_CONFIG_HART_BITS 5
+#define KVM_DEV_RISCV_AIA_CONFIG_GUEST_BITS 6
+
+/*
+ * Modes of RISC-V AIA device:
+ * 1) EMUL (aka Emulation): Trap-n-emulate IMSIC
+ * 2) HWACCEL (aka HW Acceleration): Virtualize IMSIC using IMSIC guest files
+ * 3) AUTO (aka Automatic): Virtualize IMSIC using IMSIC guest files whenever
+ * available otherwise fallback to trap-n-emulation
+ */
+#define KVM_DEV_RISCV_AIA_MODE_EMUL 0
+#define KVM_DEV_RISCV_AIA_MODE_HWACCEL 1
+#define KVM_DEV_RISCV_AIA_MODE_AUTO 2
+
+#define KVM_DEV_RISCV_AIA_IDS_MIN 63
+#define KVM_DEV_RISCV_AIA_IDS_MAX 2048
+#define KVM_DEV_RISCV_AIA_SRCS_MAX 1024
+#define KVM_DEV_RISCV_AIA_GROUP_BITS_MAX 8
+#define KVM_DEV_RISCV_AIA_GROUP_SHIFT_MIN 24
+#define KVM_DEV_RISCV_AIA_GROUP_SHIFT_MAX 56
+#define KVM_DEV_RISCV_AIA_HART_BITS_MAX 16
+#define KVM_DEV_RISCV_AIA_GUEST_BITS_MAX 8
+
+#define KVM_DEV_RISCV_AIA_GRP_ADDR 1
+#define KVM_DEV_RISCV_AIA_ADDR_APLIC 0
+#define KVM_DEV_RISCV_AIA_ADDR_IMSIC(__vcpu) (1 + (__vcpu))
+#define KVM_DEV_RISCV_AIA_ADDR_MAX \
+ (1 + KVM_DEV_RISCV_APLIC_MAX_HARTS)
+
+#define KVM_DEV_RISCV_AIA_GRP_CTRL 2
+#define KVM_DEV_RISCV_AIA_CTRL_INIT 0
+
+/*
+ * The device attribute type contains the memory mapped offset of the
+ * APLIC register (range 0x0000-0x3FFF) and it must be 4-byte aligned.
+ */
+#define KVM_DEV_RISCV_AIA_GRP_APLIC 3
+
+/*
+ * The lower 12-bits of the device attribute type contains the iselect
+ * value of the IMSIC register (range 0x70-0xFF) whereas the higher order
+ * bits contains the VCPU id.
+ */
+#define KVM_DEV_RISCV_AIA_GRP_IMSIC 4
+#define KVM_DEV_RISCV_AIA_IMSIC_ISEL_BITS 12
+#define KVM_DEV_RISCV_AIA_IMSIC_ISEL_MASK \
+ ((1U << KVM_DEV_RISCV_AIA_IMSIC_ISEL_BITS) - 1)
+#define KVM_DEV_RISCV_AIA_IMSIC_MKATTR(__vcpu, __isel) \
+ (((__vcpu) << KVM_DEV_RISCV_AIA_IMSIC_ISEL_BITS) | \
+ ((__isel) & KVM_DEV_RISCV_AIA_IMSIC_ISEL_MASK))
+#define KVM_DEV_RISCV_AIA_IMSIC_GET_ISEL(__attr) \
+ ((__attr) & KVM_DEV_RISCV_AIA_IMSIC_ISEL_MASK)
+#define KVM_DEV_RISCV_AIA_IMSIC_GET_VCPU(__attr) \
+ ((__attr) >> KVM_DEV_RISCV_AIA_IMSIC_ISEL_BITS)
+
+/* One single KVM irqchip, ie. the AIA */
+#define KVM_NR_IRQCHIPS 1
#endif
diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h
index 882547f6bd5c..a38268b19c3d 100644
--- a/arch/riscv/include/uapi/asm/ptrace.h
+++ b/arch/riscv/include/uapi/asm/ptrace.h
@@ -10,6 +10,11 @@
#include <linux/types.h>
+#define PTRACE_GETFDPIC 33
+
+#define PTRACE_GETFDPIC_EXEC 0
+#define PTRACE_GETFDPIC_INTERP 1
+
/*
* User-mode register state for core dumps, ptrace, sigcontext
*
@@ -71,12 +76,57 @@ struct __riscv_q_ext_state {
__u32 reserved[3];
};
+struct __riscv_ctx_hdr {
+ __u32 magic;
+ __u32 size;
+};
+
+struct __riscv_extra_ext_header {
+ __u32 __padding[129] __attribute__((aligned(16)));
+ /*
+ * Reserved for expansion of sigcontext structure. Currently zeroed
+ * upon signal, and must be zero upon sigreturn.
+ */
+ __u32 reserved;
+ struct __riscv_ctx_hdr hdr;
+};
+
union __riscv_fp_state {
struct __riscv_f_ext_state f;
struct __riscv_d_ext_state d;
struct __riscv_q_ext_state q;
};
+struct __riscv_v_ext_state {
+ unsigned long vstart;
+ unsigned long vl;
+ unsigned long vtype;
+ unsigned long vcsr;
+ unsigned long vlenb;
+ void *datap;
+ /*
+ * In signal handler, datap will be set a correct user stack offset
+ * and vector registers will be copied to the address of datap
+ * pointer.
+ */
+};
+
+struct __riscv_v_regset_state {
+ unsigned long vstart;
+ unsigned long vl;
+ unsigned long vtype;
+ unsigned long vcsr;
+ unsigned long vlenb;
+ char vreg[];
+};
+
+/*
+ * According to spec: The number of bits in a single vector register,
+ * VLEN >= ELEN, which must be a power of 2, and must be no greater than
+ * 2^16 = 65536bits = 8192bytes
+ */
+#define RISCV_MAX_VLENB (8192)
+
#endif /* __ASSEMBLY__ */
#endif /* _UAPI_ASM_RISCV_PTRACE_H */
diff --git a/arch/riscv/include/uapi/asm/setup.h b/arch/riscv/include/uapi/asm/setup.h
new file mode 100644
index 000000000000..66b13a522880
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/setup.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+
+#ifndef _UAPI_ASM_RISCV_SETUP_H
+#define _UAPI_ASM_RISCV_SETUP_H
+
+#define COMMAND_LINE_SIZE 1024
+
+#endif /* _UAPI_ASM_RISCV_SETUP_H */
diff --git a/arch/riscv/include/uapi/asm/sigcontext.h b/arch/riscv/include/uapi/asm/sigcontext.h
index 84f2dfcfdbce..cd4f175dc837 100644
--- a/arch/riscv/include/uapi/asm/sigcontext.h
+++ b/arch/riscv/include/uapi/asm/sigcontext.h
@@ -8,15 +8,33 @@
#include <asm/ptrace.h>
+/* The Magic number for signal context frame header. */
+#define RISCV_V_MAGIC 0x53465457
+#define END_MAGIC 0x0
+
+/* The size of END signal context header. */
+#define END_HDR_SIZE 0x0
+
+#ifndef __ASSEMBLY__
+
+struct __sc_riscv_v_state {
+ struct __riscv_v_ext_state v_state;
+} __attribute__((aligned(16)));
+
/*
* Signal context structure
*
* This contains the context saved before a signal handler is invoked;
- * it is restored by sys_sigreturn / sys_rt_sigreturn.
+ * it is restored by sys_rt_sigreturn.
*/
struct sigcontext {
struct user_regs_struct sc_regs;
- union __riscv_fp_state sc_fpregs;
+ union {
+ union __riscv_fp_state sc_fpregs;
+ struct __riscv_extra_ext_header sc_extdesc;
+ };
};
+#endif /*!__ASSEMBLY__*/
+
#endif /* _UAPI_ASM_RISCV_SIGCONTEXT_H */
diff --git a/arch/riscv/include/uapi/asm/ucontext.h b/arch/riscv/include/uapi/asm/ucontext.h
index 44eb993950e5..516bd0bb0da5 100644
--- a/arch/riscv/include/uapi/asm/ucontext.h
+++ b/arch/riscv/include/uapi/asm/ucontext.h
@@ -15,19 +15,23 @@ struct ucontext {
struct ucontext *uc_link;
stack_t uc_stack;
sigset_t uc_sigmask;
- /* There's some padding here to allow sigset_t to be expanded in the
+ /*
+ * There's some padding here to allow sigset_t to be expanded in the
* future. Though this is unlikely, other architectures put uc_sigmask
* at the end of this structure and explicitly state it can be
- * expanded, so we didn't want to box ourselves in here. */
+ * expanded, so we didn't want to box ourselves in here.
+ */
__u8 __unused[1024 / 8 - sizeof(sigset_t)];
- /* We can't put uc_sigmask at the end of this structure because we need
+ /*
+ * We can't put uc_sigmask at the end of this structure because we need
* to be able to expand sigcontext in the future. For example, the
* vector ISA extension will almost certainly add ISA state. We want
* to ensure all user-visible ISA state can be saved and restored via a
* ucontext, so we're putting this at the end in order to allow for
* infinite extensibility. Since we know this will be extended and we
* assume sigset_t won't be extended an extreme amount, we're
- * prioritizing this. */
+ * prioritizing this.
+ */
struct sigcontext uc_mcontext;
};
diff --git a/arch/riscv/include/uapi/asm/unistd.h b/arch/riscv/include/uapi/asm/unistd.h
index 73d7cdd2ec49..81896bbbf727 100644
--- a/arch/riscv/include/uapi/asm/unistd.h
+++ b/arch/riscv/include/uapi/asm/unistd.h
@@ -14,32 +14,10 @@
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <https://www.gnu.org/licenses/>.
*/
+#include <asm/bitsperlong.h>
-#if defined(__LP64__) && !defined(__SYSCALL_COMPAT)
-#define __ARCH_WANT_NEW_STAT
-#define __ARCH_WANT_SET_GET_RLIMIT
-#endif /* __LP64__ */
-
-#define __ARCH_WANT_SYS_CLONE3
-#define __ARCH_WANT_MEMFD_SECRET
-
-#include <asm-generic/unistd.h>
-
-/*
- * Allows the instruction cache to be flushed from userspace. Despite RISC-V
- * having a direct 'fence.i' instruction available to userspace (which we
- * can't trap!), that's not actually viable when running on Linux because the
- * kernel might schedule a process on another hart. There is no way for
- * userspace to handle this without invoking the kernel (as it doesn't know the
- * thread->hart mappings), so we've defined a RISC-V specific system call to
- * flush the instruction cache.
- *
- * __NR_riscv_flush_icache is defined to flush the instruction cache over an
- * address range, with the flush applying to either all threads or just the
- * caller. We don't currently do anything with the address range, that's just
- * in there for forwards compatibility.
- */
-#ifndef __NR_riscv_flush_icache
-#define __NR_riscv_flush_icache (__NR_arch_specific_syscall + 15)
+#if __BITS_PER_LONG == 64
+#include <asm/unistd_64.h>
+#else
+#include <asm/unistd_32.h>
#endif
-__SYSCALL(__NR_riscv_flush_icache, sys_riscv_flush_icache)
diff --git a/arch/riscv/include/uapi/asm/vendor/sifive.h b/arch/riscv/include/uapi/asm/vendor/sifive.h
new file mode 100644
index 000000000000..9f3278a4b298
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/vendor/sifive.h
@@ -0,0 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#define RISCV_HWPROBE_VENDOR_EXT_XSFVQMACCDOD (1 << 0)
+#define RISCV_HWPROBE_VENDOR_EXT_XSFVQMACCQOQ (1 << 1)
+#define RISCV_HWPROBE_VENDOR_EXT_XSFVFNRCLIPXFQF (1 << 2)
+#define RISCV_HWPROBE_VENDOR_EXT_XSFVFWMACCQQQ (1 << 3)
diff --git a/arch/riscv/include/uapi/asm/vendor/thead.h b/arch/riscv/include/uapi/asm/vendor/thead.h
new file mode 100644
index 000000000000..43790ebe5faf
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/vendor/thead.h
@@ -0,0 +1,3 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#define RISCV_HWPROBE_VENDOR_EXT_XTHEADVECTOR (1 << 0)