summaryrefslogtreecommitdiff
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/acpi.h13
-rw-r--r--arch/riscv/include/asm/arch_hweight.h8
-rw-r--r--arch/riscv/include/asm/asm.h10
-rw-r--r--arch/riscv/include/asm/atomic.h165
-rw-r--r--arch/riscv/include/asm/barrier.h62
-rw-r--r--arch/riscv/include/asm/bitops.h183
-rw-r--r--arch/riscv/include/asm/bugs.h22
-rw-r--r--arch/riscv/include/asm/cache.h2
-rw-r--r--arch/riscv/include/asm/cacheflush.h31
-rw-r--r--arch/riscv/include/asm/cfi.h17
-rw-r--r--arch/riscv/include/asm/cmpxchg.h591
-rw-r--r--arch/riscv/include/asm/compat.h20
-rw-r--r--arch/riscv/include/asm/cpufeature-macros.h66
-rw-r--r--arch/riscv/include/asm/cpufeature.h136
-rw-r--r--arch/riscv/include/asm/crash_reserve.h (renamed from arch/riscv/include/asm/crash_core.h)4
-rw-r--r--arch/riscv/include/asm/csr.h37
-rw-r--r--arch/riscv/include/asm/dmi.h24
-rw-r--r--arch/riscv/include/asm/elf.h11
-rw-r--r--arch/riscv/include/asm/entry-common.h1
-rw-r--r--arch/riscv/include/asm/errata_list.h48
-rw-r--r--arch/riscv/include/asm/exec.h8
-rw-r--r--arch/riscv/include/asm/fence.h11
-rw-r--r--arch/riscv/include/asm/fpu.h16
-rw-r--r--arch/riscv/include/asm/ftrace.h134
-rw-r--r--arch/riscv/include/asm/futex.h4
-rw-r--r--arch/riscv/include/asm/hugetlb.h11
-rw-r--r--arch/riscv/include/asm/hwcap.h22
-rw-r--r--arch/riscv/include/asm/hwprobe.h5
-rw-r--r--arch/riscv/include/asm/insn-def.h4
-rw-r--r--arch/riscv/include/asm/insn.h2
-rw-r--r--arch/riscv/include/asm/io.h8
-rw-r--r--arch/riscv/include/asm/irq.h60
-rw-r--r--arch/riscv/include/asm/irqflags.h1
-rw-r--r--arch/riscv/include/asm/jump_label.h52
-rw-r--r--arch/riscv/include/asm/kasan.h4
-rw-r--r--arch/riscv/include/asm/kfence.h4
-rw-r--r--arch/riscv/include/asm/kvm_aia_aplic.h58
-rw-r--r--arch/riscv/include/asm/kvm_aia_imsic.h38
-rw-r--r--arch/riscv/include/asm/kvm_host.h38
-rw-r--r--arch/riscv/include/asm/kvm_nacl.h245
-rw-r--r--arch/riscv/include/asm/kvm_vcpu_pmu.h37
-rw-r--r--arch/riscv/include/asm/kvm_vcpu_sbi.h1
-rw-r--r--arch/riscv/include/asm/membarrier.h50
-rw-r--r--arch/riscv/include/asm/mmio.h5
-rw-r--r--arch/riscv/include/asm/mmiowb.h2
-rw-r--r--arch/riscv/include/asm/mmu.h16
-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/page.h46
-rw-r--r--arch/riscv/include/asm/perf_event.h3
-rw-r--r--arch/riscv/include/asm/pgalloc.h93
-rw-r--r--arch/riscv/include/asm/pgtable-64.h24
-rw-r--r--arch/riscv/include/asm/pgtable-bits.h1
-rw-r--r--arch/riscv/include/asm/pgtable.h149
-rw-r--r--arch/riscv/include/asm/processor.h58
-rw-r--r--arch/riscv/include/asm/ptdump.h22
-rw-r--r--arch/riscv/include/asm/sbi.h196
-rw-r--r--arch/riscv/include/asm/set_memory.h3
-rw-r--r--arch/riscv/include/asm/signal.h12
-rw-r--r--arch/riscv/include/asm/simd.h4
-rw-r--r--arch/riscv/include/asm/smp.h15
-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/string.h2
-rw-r--r--arch/riscv/include/asm/suspend.h4
-rw-r--r--arch/riscv/include/asm/switch_to.h44
-rw-r--r--arch/riscv/include/asm/sync_core.h29
-rw-r--r--arch/riscv/include/asm/syscall_table.h7
-rw-r--r--arch/riscv/include/asm/syscall_wrapper.h54
-rw-r--r--arch/riscv/include/asm/text-patching.h (renamed from arch/riscv/include/asm/patch.h)3
-rw-r--r--arch/riscv/include/asm/thread_info.h29
-rw-r--r--arch/riscv/include/asm/tlbflush.h52
-rw-r--r--arch/riscv/include/asm/topology.h4
-rw-r--r--arch/riscv/include/asm/trace.h54
-rw-r--r--arch/riscv/include/asm/uaccess.h47
-rw-r--r--arch/riscv/include/asm/unistd.h13
-rw-r--r--arch/riscv/include/asm/uprobes.h2
-rw-r--r--arch/riscv/include/asm/vdso/processor.h8
-rw-r--r--arch/riscv/include/asm/vdso/time_data.h (renamed from arch/riscv/include/asm/vdso/data.h)8
-rw-r--r--arch/riscv/include/asm/vdso/vsyscall.h4
-rw-r--r--arch/riscv/include/asm/vector.h241
-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/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.h3
-rw-r--r--arch/riscv/include/asm/vmalloc.h1
-rw-r--r--arch/riscv/include/asm/word-at-a-time.h3
-rw-r--r--arch/riscv/include/asm/xip_fixup.h30
-rw-r--r--arch/riscv/include/uapi/asm/Kbuild2
-rw-r--r--arch/riscv/include/uapi/asm/auxvec.h2
-rw-r--r--arch/riscv/include/uapi/asm/hwprobe.h32
-rw-r--r--arch/riscv/include/uapi/asm/kvm.h22
-rw-r--r--arch/riscv/include/uapi/asm/unistd.h41
-rw-r--r--arch/riscv/include/uapi/asm/vendor/thead.h3
97 files changed, 2740 insertions, 1230 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/acpi.h b/arch/riscv/include/asm/acpi.h
index 7dad0cf9d701..6e13695120bc 100644
--- a/arch/riscv/include/asm/acpi.h
+++ b/arch/riscv/include/asm/acpi.h
@@ -61,11 +61,14 @@ 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);
-u32 get_acpi_id_for_cpu(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);
-static inline int acpi_numa_get_nid(unsigned int cpu) { return NUMA_NO_NODE; }
void acpi_get_cbo_block_size(struct acpi_table_header *table, u32 *cbom_size,
u32 *cboz_size, u32 *cbop_size);
#else
@@ -87,4 +90,10 @@ static inline void acpi_get_cbo_block_size(struct acpi_table_header *table,
#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/arch_hweight.h b/arch/riscv/include/asm/arch_hweight.h
index 85b2c443823e..613769b9cdc9 100644
--- a/arch/riscv/include/asm/arch_hweight.h
+++ b/arch/riscv/include/asm/arch_hweight.h
@@ -26,9 +26,9 @@ static __always_inline unsigned int __arch_hweight32(unsigned int w)
asm (".option push\n"
".option arch,+zbb\n"
- CPOPW "%0, %0\n"
+ CPOPW "%0, %1\n"
".option pop\n"
- : "+r" (w) : :);
+ : "=r" (w) : "r" (w) :);
return w;
@@ -57,9 +57,9 @@ static __always_inline unsigned long __arch_hweight64(__u64 w)
asm (".option push\n"
".option arch,+zbb\n"
- "cpop %0, %0\n"
+ "cpop %0, %1\n"
".option pop\n"
- : "+r" (w) : :);
+ : "=r" (w) : "r" (w) :);
return w;
diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h
index b0487b39e674..776354895b81 100644
--- a/arch/riscv/include/asm/asm.h
+++ b/arch/riscv/include/asm/asm.h
@@ -183,6 +183,16 @@
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/atomic.h b/arch/riscv/include/asm/atomic.h
index f5dfef6c2153..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
@@ -222,77 +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
+#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;
}
@@ -304,17 +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);
}
@@ -325,17 +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);
}
@@ -346,17 +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 110752594228..e1d9bf1deca6 100644
--- a/arch/riscv/include/asm/barrier.h
+++ b/arch/riscv/include/asm/barrier.h
@@ -11,38 +11,23 @@
#define _ASM_RISCV_BARRIER_H
#ifndef __ASSEMBLY__
+#include <asm/cmpxchg.h>
+#include <asm/fence.h>
#define nop() __asm__ __volatile__ ("nop")
#define __nops(n) ".rept " #n "\nnop\n.endr\n"
#define nops(n) __asm__ __volatile__ (__nops(n))
-#define RISCV_FENCE(p, s) \
- __asm__ __volatile__ ("fence " #p "," #s : : : "memory")
/* 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
@@ -69,7 +54,36 @@ 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 329d8244a9b3..c6bd3d8354a9 100644
--- a/arch/riscv/include/asm/bitops.h
+++ b/arch/riscv/include/asm/bitops.h
@@ -22,6 +22,16 @@
#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>
@@ -37,8 +47,6 @@
static __always_inline unsigned long variable__ffs(unsigned long word)
{
- int num;
-
asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
RISCV_ISA_EXT_ZBB, 1)
: : : : legacy);
@@ -52,32 +60,7 @@ static __always_inline unsigned long variable__ffs(unsigned long word)
return word;
legacy:
- num = 0;
-#if BITS_PER_LONG == 64
- if ((word & 0xffffffff) == 0) {
- num += 32;
- word >>= 32;
- }
-#endif
- if ((word & 0xffff) == 0) {
- num += 16;
- word >>= 16;
- }
- if ((word & 0xff) == 0) {
- num += 8;
- word >>= 8;
- }
- if ((word & 0xf) == 0) {
- num += 4;
- word >>= 4;
- }
- if ((word & 0x3) == 0) {
- num += 2;
- word >>= 2;
- }
- if ((word & 0x1) == 0)
- num += 1;
- return num;
+ return generic___ffs(word);
}
/**
@@ -93,8 +76,6 @@ legacy:
static __always_inline unsigned long variable__fls(unsigned long word)
{
- int num;
-
asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
RISCV_ISA_EXT_ZBB, 1)
: : : : legacy);
@@ -108,32 +89,7 @@ static __always_inline unsigned long variable__fls(unsigned long word)
return BITS_PER_LONG - 1 - word;
legacy:
- num = BITS_PER_LONG - 1;
-#if BITS_PER_LONG == 64
- if (!(word & (~0ul << 32))) {
- num -= 32;
- word <<= 32;
- }
-#endif
- if (!(word & (~0ul << (BITS_PER_LONG - 16)))) {
- num -= 16;
- word <<= 16;
- }
- if (!(word & (~0ul << (BITS_PER_LONG - 8)))) {
- num -= 8;
- word <<= 8;
- }
- if (!(word & (~0ul << (BITS_PER_LONG - 4)))) {
- num -= 4;
- word <<= 4;
- }
- if (!(word & (~0ul << (BITS_PER_LONG - 2)))) {
- num -= 2;
- word <<= 2;
- }
- if (!(word & (~0ul << (BITS_PER_LONG - 1))))
- num -= 1;
- return num;
+ return generic___fls(word);
}
/**
@@ -149,46 +105,23 @@ legacy:
static __always_inline int variable_ffs(int x)
{
- int r;
-
- if (!x)
- return 0;
-
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" (r) : "r" (x) :);
+ : "=r" (x) : "r" (x) :);
- return r + 1;
+ return x + 1;
legacy:
- r = 1;
- if (!(x & 0xffff)) {
- x >>= 16;
- r += 16;
- }
- if (!(x & 0xff)) {
- x >>= 8;
- r += 8;
- }
- if (!(x & 0xf)) {
- x >>= 4;
- r += 4;
- }
- if (!(x & 3)) {
- x >>= 2;
- r += 2;
- }
- if (!(x & 1)) {
- x >>= 1;
- r += 1;
- }
- return r;
+ return generic_ffs(x);
}
/**
@@ -204,46 +137,23 @@ legacy:
static __always_inline int variable_fls(unsigned int x)
{
- int r;
-
- if (!x)
- return 0;
-
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" (r) : "r" (x) :);
+ : "=r" (x) : "r" (x) :);
- return 32 - r;
+ return 32 - x;
legacy:
- r = 32;
- if (!(x & 0xffff0000u)) {
- x <<= 16;
- r -= 16;
- }
- if (!(x & 0xff000000u)) {
- x <<= 8;
- r -= 8;
- }
- if (!(x & 0xf0000000u)) {
- x <<= 4;
- r -= 4;
- }
- if (!(x & 0xc0000000u)) {
- x <<= 2;
- r -= 2;
- }
- if (!(x & 0x80000000u)) {
- x <<= 1;
- r -= 1;
- }
- return r;
+ return generic_fls(x);
}
/**
@@ -260,7 +170,7 @@ legacy:
({ \
typeof(x) x_ = (x); \
__builtin_constant_p(x_) ? \
- (int)((x_ != 0) ? (32 - __builtin_clz(x_)) : 0) \
+ ((x_ != 0) ? (32 - __builtin_clz(x_)) : 0) \
: \
variable_fls(x_); \
})
@@ -312,44 +222,44 @@ legacy:
#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.
*/
-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.
*/
-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
*
@@ -360,13 +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
*
@@ -374,13 +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
*
@@ -388,40 +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
*
@@ -435,13 +345,13 @@ 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 inline bool xor_unlock_is_negative_byte(unsigned long mask,
+static __always_inline bool arch_xor_unlock_is_negative_byte(unsigned long mask,
volatile unsigned long *addr)
{
unsigned long res;
@@ -459,6 +369,9 @@ static inline bool xor_unlock_is_negative_byte(unsigned long mask,
#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 2174fe7bac9a..570e9d8acad1 100644
--- a/arch/riscv/include/asm/cache.h
+++ b/arch/riscv/include/asm/cache.h
@@ -26,8 +26,8 @@
#ifndef __ASSEMBLY__
-#ifdef CONFIG_RISCV_DMA_NONCOHERENT
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)
{
diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
index a129dac4521d..8de73f91bfa3 100644
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -13,6 +13,12 @@ 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_folio(struct folio *folio)
@@ -33,11 +39,30 @@ static inline void flush_dcache_page(struct page *page)
* 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)
+#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
-#define flush_cache_vmap(start, end) flush_tlb_kernel_range(start, end)
+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
diff --git a/arch/riscv/include/asm/cfi.h b/arch/riscv/include/asm/cfi.h
index 8f7a62257044..fb9696d7a3f2 100644
--- a/arch/riscv/include/asm/cfi.h
+++ b/arch/riscv/include/asm/cfi.h
@@ -13,11 +13,28 @@ 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/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 2f4726d3cfcc..427c41dde643 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -8,143 +8,104 @@
#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>
-#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 \
+ "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) \
+ : "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 __arch_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))) __arch_xchg((ptr), _x_, sizeof(*(ptr))); \
-})
+ _arch_xchg(ptr, x, ".rl", ".aqrl", "", RISCV_FULL_BARRIER, "")
#define xchg32(ptr, x) \
({ \
@@ -163,190 +124,164 @@
* 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 +295,120 @@
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;
+
+ asm goto(ALTERNATIVE("j %l[no_zawrs]", "nop",
+ 0, RISCV_ISA_EXT_ZAWRS, 1)
+ : : : : no_zawrs);
+
+ switch (size) {
+ case 1:
+ fallthrough;
+ case 2:
+ /* RISC-V doesn't have lr instructions on byte and half-word. */
+ goto no_zawrs;
+ 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/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
index 0bd11862b760..569140d6e639 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0-only */
/*
- * Copyright 2022-2023 Rivos, Inc
+ * Copyright 2022-2024 Rivos, Inc
*/
#ifndef _ASM_CPUFEATURE_H
@@ -8,9 +8,12 @@
#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/alternative-macros.h>
-#include <asm/errno.h>
+#include <asm/cpufeature-macros.h>
/*
* These are probed via a device_initcall(), via either the SBI or directly
@@ -28,29 +31,72 @@ struct riscv_isainfo {
DECLARE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo);
-DECLARE_PER_CPU(long, misaligned_access_speed);
-
/* Per-cpu ISA extensions. */
extern struct riscv_isainfo hart_isa[NR_CPUS];
-void riscv_user_isa_enable(void);
+extern u32 thead_vlenb_of;
-#ifdef CONFIG_RISCV_MISALIGNED
-bool unaligned_ctl_available(void);
-bool check_unaligned_access_emulated(int cpu);
+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)
+
+/* 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 check_unaligned_access_emulated_all_cpus(void);
+#if defined(CONFIG_RISCV_SCALAR_MISALIGNED)
+void check_unaligned_access_emulated(struct work_struct *work __always_unused);
void unaligned_emulation_finish(void);
+bool unaligned_ctl_available(void);
+DECLARE_PER_CPU(long, misaligned_access_speed);
#else
static inline bool unaligned_ctl_available(void)
{
return false;
}
+#endif
-static inline bool check_unaligned_access_emulated(int cpu)
+bool 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 false;
+ 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;
}
-
-static inline void unaligned_emulation_finish(void) {}
#endif
unsigned long riscv_get_elf_hwcap(void);
@@ -61,6 +107,7 @@ struct riscv_isa_ext_data {
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[];
@@ -68,60 +115,12 @@ extern const size_t riscv_isa_ext_count;
extern bool riscv_isa_fallback;
unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap);
-
-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 ext)
-{
- compiletime_assert(ext < RISCV_ISA_EXT_MAX,
- "ext must be < RISCV_ISA_EXT_MAX");
-
- if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
- asm goto(
- ALTERNATIVE("j %l[l_no]", "nop", 0, %[ext], 1)
- :
- : [ext] "i" (ext)
- :
- : l_no);
- } else {
- if (!__riscv_isa_extension_available(NULL, ext))
- goto l_no;
- }
-
- return true;
-l_no:
- return false;
-}
-
-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)) {
- asm goto(
- ALTERNATIVE("nop", "j %l[l_yes]", 0, %[ext], 1)
- :
- : [ext] "i" (ext)
- :
- : l_yes);
- } else {
- if (__riscv_isa_extension_available(NULL, ext))
- goto l_yes;
- }
-
- return false;
-l_yes:
- return true;
-}
-
static __always_inline bool riscv_cpu_has_extension_likely(int cpu, const unsigned long ext)
{
- if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_likely(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);
@@ -129,12 +128,13 @@ static __always_inline bool riscv_cpu_has_extension_likely(int cpu, const unsign
static __always_inline bool riscv_cpu_has_extension_unlikely(int cpu, const unsigned long ext)
{
- if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_unlikely(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);
}
-DECLARE_STATIC_KEY_FALSE(fast_misaligned_access_speed_key);
-
#endif
diff --git a/arch/riscv/include/asm/crash_core.h b/arch/riscv/include/asm/crash_reserve.h
index e1874b23feaf..013962e63587 100644
--- a/arch/riscv/include/asm/crash_core.h
+++ b/arch/riscv/include/asm/crash_reserve.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0-only */
-#ifndef _RISCV_CRASH_CORE_H
-#define _RISCV_CRASH_CORE_H
+#ifndef _RISCV_CRASH_RESERVE_H
+#define _RISCV_CRASH_RESERVE_H
#define CRASH_ALIGN PMD_SIZE
diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
index 2468c55933cd..6fed42e37705 100644
--- a/arch/riscv/include/asm/csr.h
+++ b/arch/riscv/include/asm/csr.h
@@ -30,6 +30,12 @@
#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)
@@ -119,6 +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
@@ -168,7 +178,8 @@
#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
@@ -194,6 +205,11 @@
/* 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
@@ -215,6 +231,12 @@
#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
#define CSR_TIME 0xc01
@@ -281,7 +303,7 @@
#define CSR_HPMCOUNTER30H 0xc9e
#define CSR_HPMCOUNTER31H 0xc9f
-#define CSR_SSCOUNTOVF 0xda0
+#define CSR_SCOUNTOVF 0xda0
#define CSR_SSTATUS 0x100
#define CSR_SIE 0x104
@@ -299,6 +321,15 @@
#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
@@ -381,6 +412,8 @@
#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
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/elf.h b/arch/riscv/include/asm/elf.h
index 06c236bfab53..c7aea7886d22 100644
--- a/arch/riscv/include/asm/elf.h
+++ b/arch/riscv/include/asm/elf.h
@@ -53,13 +53,9 @@ extern bool compat_elf_check_arch(Elf32_Ehdr *hdr);
#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
/*
@@ -139,10 +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
index 2293e535f865..b28ccc6cdeea 100644
--- a/arch/riscv/include/asm/entry-common.h
+++ b/arch/riscv/include/asm/entry-common.h
@@ -33,6 +33,7 @@ static inline int handle_misaligned_load(struct pt_regs *regs)
{
return -1;
}
+
static inline int handle_misaligned_store(struct pt_regs *regs)
{
return -1;
diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
index ea33288f8a25..6e426ed7919a 100644
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -12,8 +12,8 @@
#include <asm/vendorid_list.h>
#ifdef CONFIG_ERRATA_ANDES
-#define ERRATA_ANDESTECH_NO_IOCP 0
-#define ERRATA_ANDESTECH_NUMBER 1
+#define ERRATA_ANDES_NO_IOCP 0
+#define ERRATA_ANDES_NUMBER 1
#endif
#ifdef CONFIG_ERRATA_SIFIVE
@@ -23,9 +23,10 @@
#endif
#ifdef CONFIG_ERRATA_THEAD
-#define ERRATA_THEAD_PBMT 0
+#define ERRATA_THEAD_MAE 0
#define ERRATA_THEAD_PMU 1
-#define ERRATA_THEAD_NUMBER 2
+#define ERRATA_THEAD_GHOSTWRITE 2
+#define ERRATA_THEAD_NUMBER 3
#endif
#ifdef __ASSEMBLY__
@@ -43,30 +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, \
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,
@@ -83,11 +94,11 @@ 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)
@@ -112,15 +123,6 @@ asm volatile(ALTERNATIVE( \
#define THEAD_C9XX_RV_IRQ_PMU 17
#define THEAD_C9XX_CSR_SCOUNTEROF 0x5c5
-#define ALT_SBI_PMU_OVERFLOW(__ovl) \
-asm volatile(ALTERNATIVE( \
- "csrr %0, " __stringify(CSR_SSCOUNTOVF), \
- "csrr %0, " __stringify(THEAD_C9XX_CSR_SCOUNTEROF), \
- THEAD_VENDOR_ID, ERRATA_THEAD_PMU, \
- CONFIG_ERRATA_THEAD_PMU) \
- : "=r" (__ovl) : \
- : "memory")
-
#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/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/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 15055f9df4da..c4721ce44ca4 100644
--- a/arch/riscv/include/asm/ftrace.h
+++ b/arch/riscv/include/asm/ftrace.h
@@ -11,17 +11,6 @@
#if defined(CONFIG_FUNCTION_GRAPH_TRACER) && defined(CONFIG_FRAME_POINTER)
#define HAVE_FUNCTION_GRAPH_FP_TEST
#endif
-#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
-
-/*
- * Clang prior to 13 had "mcount" instead of "_mcount":
- * https://reviews.llvm.org/D98881
- */
-#if defined(CONFIG_CC_IS_GCC) || CONFIG_CLANG_VERSION >= 130000
-#define MCOUNT_NAME _mcount
-#else
-#define MCOUNT_NAME mcount
-#endif
#define ARCH_SUPPORTS_FTRACE_OPS 1
#ifndef __ASSEMBLY__
@@ -30,7 +19,7 @@ extern void *return_address(unsigned int level);
#define ftrace_return_address(n) return_address(n)
-void MCOUNT_NAME(void);
+void _mcount(void);
static inline unsigned long ftrace_call_adjust(unsigned long addr)
{
return addr;
@@ -80,7 +69,7 @@ struct dyn_arch_ftrace {
* 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)
@@ -134,44 +123,113 @@ struct dyn_ftrace;
int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
#define ftrace_init_nop ftrace_init_nop
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
+#define arch_ftrace_get_regs(regs) NULL
+#define HAVE_ARCH_FTRACE_REGS
struct ftrace_ops;
struct ftrace_regs;
-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
+#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;
+ 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;
+ };
+ };
+};
-static inline void __arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr)
+static __always_inline unsigned long ftrace_regs_get_instruction_pointer(const struct ftrace_regs
+ *fregs)
{
- regs->t1 = addr;
+ return arch_ftrace_regs(fregs)->epc;
}
-#define arch_ftrace_set_direct_caller(fregs, addr) \
- __arch_ftrace_set_direct_caller(&(fregs)->regs, addr)
-#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
-#endif /* __ASSEMBLY__ */
+static __always_inline void ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs,
+ unsigned long pc)
+{
+ arch_ftrace_regs(fregs)->epc = pc;
+}
-#endif /* CONFIG_DYNAMIC_FTRACE */
+static __always_inline unsigned long ftrace_regs_get_stack_pointer(const struct ftrace_regs *fregs)
+{
+ return arch_ftrace_regs(fregs)->sp;
+}
-#ifndef __ASSEMBLY__
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-struct fgraph_ret_regs {
- unsigned long a1;
- unsigned long a0;
- unsigned long s0;
- unsigned long ra;
-};
+static __always_inline unsigned long ftrace_regs_get_frame_pointer(const struct ftrace_regs *fregs)
+{
+ return arch_ftrace_regs(fregs)->s0;
+}
-static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs)
+static __always_inline unsigned long ftrace_regs_get_argument(struct ftrace_regs *fregs,
+ unsigned int n)
{
- return ret_regs->a0;
+ if (n < 8)
+ return arch_ftrace_regs(fregs)->args[n];
+ return 0;
}
-static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs)
+static __always_inline unsigned long ftrace_regs_get_return_value(const struct ftrace_regs *fregs)
{
- return ret_regs->s0;
+ return arch_ftrace_regs(fregs)->a0;
}
-#endif /* ifdef CONFIG_FUNCTION_GRAPH_TRACER */
-#endif
+
+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->a0, 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
+
+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_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/hugetlb.h b/arch/riscv/include/asm/hugetlb.h
index 22deb7a2a6ec..446126497768 100644
--- a/arch/riscv/include/asm/hugetlb.h
+++ b/arch/riscv/include/asm/hugetlb.h
@@ -5,11 +5,11 @@
#include <asm/cacheflush.h>
#include <asm/page.h>
-static inline void arch_clear_hugepage_flags(struct page *page)
+static inline void arch_clear_hugetlb_flags(struct folio *folio)
{
- clear_bit(PG_dcache_clean, &page->flags);
+ clear_bit(PG_dcache_clean, &folio->flags);
}
-#define arch_clear_hugepage_flags arch_clear_hugepage_flags
+#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags
#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
bool arch_hugetlb_migration_supported(struct hstate *h);
@@ -28,7 +28,8 @@ void set_huge_pte_at(struct mm_struct *mm,
#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 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,
@@ -44,7 +45,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
pte_t pte, int dirty);
#define __HAVE_ARCH_HUGE_PTEP_GET
-pte_t huge_ptep_get(pte_t *ptep);
+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
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 1f2d2599c655..869da082252a 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -80,6 +80,26 @@
#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_XLINUXENVCFG 127
@@ -88,8 +108,10 @@
#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
index 630507dff5ea..dd624523981c 100644
--- a/arch/riscv/include/asm/hwprobe.h
+++ b/arch/riscv/include/asm/hwprobe.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
/*
- * Copyright 2023 Rivos, Inc
+ * Copyright 2023-2024 Rivos, Inc
*/
#ifndef _ASM_HWPROBE_H
@@ -8,7 +8,7 @@
#include <uapi/asm/hwprobe.h>
-#define RISCV_HWPROBE_MAX_KEY 6
+#define RISCV_HWPROBE_MAX_KEY 11
static inline bool riscv_hwprobe_key_is_valid(__s64 key)
{
@@ -21,6 +21,7 @@ static inline bool hwprobe_key_is_bitmask(__s64 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:
return true;
}
diff --git a/arch/riscv/include/asm/insn-def.h b/arch/riscv/include/asm/insn-def.h
index e27179b26086..9a913010cdd9 100644
--- a/arch/riscv/include/asm/insn-def.h
+++ b/arch/riscv/include/asm/insn-def.h
@@ -196,4 +196,8 @@
INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0), \
RS1(base), SIMM12(4))
+#define RISCV_PAUSE ".4byte 0x100000f"
+#define ZAWRS_WRS_NTO ".4byte 0x00d00073"
+#define ZAWRS_WRS_STO ".4byte 0x01d00073"
+
#endif /* __ASM_INSN_DEF_H */
diff --git a/arch/riscv/include/asm/insn.h b/arch/riscv/include/asm/insn.h
index 06e439eeef9a..09fde95a5e8f 100644
--- a/arch/riscv/include/asm/insn.h
+++ b/arch/riscv/include/asm/insn.h
@@ -145,7 +145,7 @@
/* parts of opcode for RVF, RVD and RVQ */
#define RVFDQ_FL_FS_WIDTH_OFF 12
-#define RVFDQ_FL_FS_WIDTH_MASK GENMASK(3, 0)
+#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
diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h
index 42497d487a17..1c5c641075d2 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
diff --git a/arch/riscv/include/asm/irq.h b/arch/riscv/include/asm/irq.h
index 8e10a94430a2..7b038f3b7cb0 100644
--- a/arch/riscv/include/asm/irq.h
+++ b/arch/riscv/include/asm/irq.h
@@ -12,8 +12,68 @@
#include <asm-generic/irq.h>
+#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/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 4a35d787c019..87a71cc6d146 100644
--- a/arch/riscv/include/asm/jump_label.h
+++ b/arch/riscv/include/asm/jump_label.h
@@ -12,23 +12,32 @@
#include <linux/types.h>
#include <asm/asm.h>
+#define HAVE_JUMP_LABEL_BATCH
+
#define JUMP_LABEL_NOP_SIZE 4
+#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 goto(
- " .align 2 \n\t"
- " .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"
+ ARCH_STATIC_BRANCH_ASM("%0", "%l[label]")
: : "i"(&((char *)key)[branch]) : : label);
return false;
@@ -36,21 +45,20 @@ label:
return true;
}
+#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 goto(
- " .align 2 \n\t"
- " .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"
+ 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/kfence.h b/arch/riscv/include/asm/kfence.h
index 7388edd88986..d08bf7fb3aee 100644
--- a/arch/riscv/include/asm/kfence.h
+++ b/arch/riscv/include/asm/kfence.h
@@ -22,7 +22,9 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect)
else
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/kvm_aia_aplic.h b/arch/riscv/include/asm/kvm_aia_aplic.h
deleted file mode 100644
index 6dd1a4809ec1..000000000000
--- a/arch/riscv/include/asm/kvm_aia_aplic.h
+++ /dev/null
@@ -1,58 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2021 Western Digital Corporation or its affiliates.
- * Copyright (C) 2022 Ventana Micro Systems Inc.
- */
-#ifndef __KVM_RISCV_AIA_IMSIC_H
-#define __KVM_RISCV_AIA_IMSIC_H
-
-#include <linux/bitops.h>
-
-#define APLIC_MAX_IDC BIT(14)
-#define APLIC_MAX_SOURCE 1024
-
-#define APLIC_DOMAINCFG 0x0000
-#define APLIC_DOMAINCFG_RDONLY 0x80000000
-#define APLIC_DOMAINCFG_IE BIT(8)
-#define APLIC_DOMAINCFG_DM BIT(2)
-#define APLIC_DOMAINCFG_BE BIT(0)
-
-#define APLIC_SOURCECFG_BASE 0x0004
-#define APLIC_SOURCECFG_D BIT(10)
-#define APLIC_SOURCECFG_CHILDIDX_MASK 0x000003ff
-#define APLIC_SOURCECFG_SM_MASK 0x00000007
-#define APLIC_SOURCECFG_SM_INACTIVE 0x0
-#define APLIC_SOURCECFG_SM_DETACH 0x1
-#define APLIC_SOURCECFG_SM_EDGE_RISE 0x4
-#define APLIC_SOURCECFG_SM_EDGE_FALL 0x5
-#define APLIC_SOURCECFG_SM_LEVEL_HIGH 0x6
-#define APLIC_SOURCECFG_SM_LEVEL_LOW 0x7
-
-#define APLIC_IRQBITS_PER_REG 32
-
-#define APLIC_SETIP_BASE 0x1c00
-#define APLIC_SETIPNUM 0x1cdc
-
-#define APLIC_CLRIP_BASE 0x1d00
-#define APLIC_CLRIPNUM 0x1ddc
-
-#define APLIC_SETIE_BASE 0x1e00
-#define APLIC_SETIENUM 0x1edc
-
-#define APLIC_CLRIE_BASE 0x1f00
-#define APLIC_CLRIENUM 0x1fdc
-
-#define APLIC_SETIPNUM_LE 0x2000
-#define APLIC_SETIPNUM_BE 0x2004
-
-#define APLIC_GENMSI 0x3000
-
-#define APLIC_TARGET_BASE 0x3004
-#define APLIC_TARGET_HART_IDX_SHIFT 18
-#define APLIC_TARGET_HART_IDX_MASK 0x3fff
-#define APLIC_TARGET_GUEST_IDX_SHIFT 12
-#define APLIC_TARGET_GUEST_IDX_MASK 0x3f
-#define APLIC_TARGET_IPRIO_MASK 0xff
-#define APLIC_TARGET_EIID_MASK 0x7ff
-
-#endif
diff --git a/arch/riscv/include/asm/kvm_aia_imsic.h b/arch/riscv/include/asm/kvm_aia_imsic.h
deleted file mode 100644
index da5881d2bde0..000000000000
--- a/arch/riscv/include/asm/kvm_aia_imsic.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2021 Western Digital Corporation or its affiliates.
- * Copyright (C) 2022 Ventana Micro Systems Inc.
- */
-#ifndef __KVM_RISCV_AIA_IMSIC_H
-#define __KVM_RISCV_AIA_IMSIC_H
-
-#include <linux/types.h>
-#include <asm/csr.h>
-
-#define IMSIC_MMIO_PAGE_SHIFT 12
-#define IMSIC_MMIO_PAGE_SZ (1UL << IMSIC_MMIO_PAGE_SHIFT)
-#define IMSIC_MMIO_PAGE_LE 0x00
-#define IMSIC_MMIO_PAGE_BE 0x04
-
-#define IMSIC_MIN_ID 63
-#define IMSIC_MAX_ID 2048
-
-#define IMSIC_EIDELIVERY 0x70
-
-#define IMSIC_EITHRESHOLD 0x72
-
-#define IMSIC_EIP0 0x80
-#define IMSIC_EIP63 0xbf
-#define IMSIC_EIPx_BITS 32
-
-#define IMSIC_EIE0 0xc0
-#define IMSIC_EIE63 0xff
-#define IMSIC_EIEx_BITS 32
-
-#define IMSIC_FIRST IMSIC_EIDELIVERY
-#define IMSIC_LAST IMSIC_EIE63
-
-#define IMSIC_MMIO_SETIPNUM_LE 0x00
-#define IMSIC_MMIO_SETIPNUM_BE 0x04
-
-#endif
diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 484d04a92fa6..cc33e35cd628 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -43,6 +43,17 @@
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,
KVM_RISCV_HFENCE_GVMA_VMID_GPA,
@@ -69,12 +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 {
@@ -169,6 +186,7 @@ struct kvm_vcpu_csr {
struct kvm_vcpu_config {
u64 henvcfg;
u64 hstateen0;
+ unsigned long hedeleg;
};
struct kvm_vcpu_smstateen_csr {
@@ -211,6 +229,7 @@ struct kvm_vcpu_arch {
/* CPU context upon Guest VCPU reset */
struct kvm_cpu_context guest_reset_context;
+ spinlock_t reset_cntx_lock;
/* CPU CSR context upon Guest VCPU reset */
struct kvm_vcpu_csr guest_reset_csr;
@@ -252,8 +271,9 @@ struct kvm_vcpu_arch {
/* 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;
@@ -271,8 +291,17 @@ struct kvm_vcpu_arch {
} 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;
+}
+
static inline void kvm_arch_sync_events(struct kvm *kvm) {}
-static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
#define KVM_RISCV_GSTAGE_TLB_MIN_ORDER 12
@@ -374,8 +403,11 @@ 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, 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);
void kvm_riscv_vcpu_sbi_sta_reset(struct kvm_vcpu *vcpu);
void kvm_riscv_vcpu_record_steal_time(struct kvm_vcpu *vcpu);
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_pmu.h b/arch/riscv/include/asm/kvm_vcpu_pmu.h
index 395518a1664e..1d85b6617508 100644
--- a/arch/riscv/include/asm/kvm_vcpu_pmu.h
+++ b/arch/riscv/include/asm/kvm_vcpu_pmu.h
@@ -10,6 +10,7 @@
#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
@@ -20,7 +21,7 @@ static_assert(RISCV_KVM_MAX_COUNTERS <= 64);
struct kvm_fw_event {
/* Current value of the event */
- unsigned long value;
+ u64 value;
/* Event monitoring status */
bool started;
@@ -36,6 +37,7 @@ struct kvm_pmc {
bool started;
/* Monitoring event ID */
unsigned long event_idx;
+ struct kvm_vcpu *vcpu;
};
/* PMU data structure per vcpu */
@@ -50,6 +52,12 @@ struct kvm_pmu {
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)
@@ -57,11 +65,11 @@ struct kvm_pmu {
#if defined(CONFIG_32BIT)
#define KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS \
-{.base = CSR_CYCLEH, .count = 31, .func = kvm_riscv_vcpu_pmu_read_hpm }, \
-{.base = CSR_CYCLE, .count = 31, .func = kvm_riscv_vcpu_pmu_read_hpm },
+{.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 = 31, .func = kvm_riscv_vcpu_pmu_read_hpm },
+{.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);
@@ -82,9 +90,14 @@ int kvm_riscv_vcpu_pmu_ctr_cfg_match(struct kvm_vcpu *vcpu, unsigned long ctr_ba
unsigned long ctr_mask, unsigned long flags,
unsigned long eidx, u64 evtdata,
struct kvm_vcpu_sbi_return *retdata);
-int kvm_riscv_vcpu_pmu_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx,
+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);
@@ -92,8 +105,20 @@ void kvm_riscv_vcpu_pmu_reset(struct kvm_vcpu *vcpu);
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 = 0, .count = 0, .func = NULL },
+{.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)
diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h
index b96705258cf9..4ed6203cdd30 100644
--- a/arch/riscv/include/asm/kvm_vcpu_sbi.h
+++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h
@@ -85,6 +85,7 @@ 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;
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 4c58ee7f95ec..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. */
@@ -131,8 +132,8 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
* 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,ir" : : : "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 355504b37f8e..1cc90465d75b 100644
--- a/arch/riscv/include/asm/mmu.h
+++ b/arch/riscv/include/asm/mmu.h
@@ -19,15 +19,27 @@ typedef struct {
#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/page.h b/arch/riscv/include/asm/page.h
index 57e887bfa34c..125f5ecd9565 100644
--- a/arch/riscv/include/asm/page.h
+++ b/arch/riscv/include/asm/page.h
@@ -12,9 +12,7 @@
#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>
#define HPAGE_SHIFT PMD_SHIFT
#define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT)
@@ -37,7 +35,7 @@
* define the PAGE_OFFSET value for SV48 and SV39.
*/
#define PAGE_OFFSET_L4 _AC(0xffffaf8000000000, UL)
-#define PAGE_OFFSET_L3 _AC(0xffffffd800000000, UL)
+#define PAGE_OFFSET_L3 _AC(0xffffffd600000000, UL)
#else
#define PAGE_OFFSET _AC(CONFIG_PAGE_OFFSET, UL)
#endif /* CONFIG_64BIT */
@@ -89,7 +87,7 @@ typedef struct page *pgtable_t;
#define PTE_FMT "%08lx"
#endif
-#ifdef CONFIG_64BIT
+#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).
@@ -112,16 +110,19 @@ struct kernel_mapping {
/* 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 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))
@@ -134,12 +135,18 @@ extern phys_addr_t phys_ram_base;
#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); \
- (IS_ENABLED(CONFIG_XIP_KERNEL) && _y < phys_ram_base) ? \
- (void *)(_y + kernel_map.va_kernel_xip_pa_offset) : \
- (void *)(_y + kernel_map.va_kernel_pa_offset + XIP_OFFSET); \
+ (_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
@@ -147,12 +154,17 @@ void *linear_mapping_pa_to_va(unsigned long x);
#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 = (unsigned long)(y); \
- (IS_ENABLED(CONFIG_XIP_KERNEL) && _y < kernel_map.virt_addr + XIP_OFFSET) ? \
- (_y - kernel_map.va_kernel_xip_pa_offset) : \
- (_y - kernel_map.va_kernel_pa_offset - XIP_OFFSET); \
+ (_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; \
@@ -181,13 +193,15 @@ 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 phys_to_page(paddr) (pfn_to_page(phys_to_pfn(paddr)))
-
#define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x))
unsigned long kaslr_offset(void);
+static __always_inline void *pfn_to_kaddr(unsigned long pfn)
+{
+ return __va(pfn << PAGE_SHIFT);
+}
+
#endif /* __ASSEMBLY__ */
#define virt_addr_valid(vaddr) ({ \
diff --git a/arch/riscv/include/asm/perf_event.h b/arch/riscv/include/asm/perf_event.h
index 665bbc9b2f84..bcc928fd3785 100644
--- a/arch/riscv/include/asm/perf_event.h
+++ b/arch/riscv/include/asm/perf_event.h
@@ -8,6 +8,7 @@
#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
@@ -17,4 +18,6 @@
(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 c80bb9990d32..3e2aebea6312 100644
--- a/arch/riscv/include/asm/pgalloc.h
+++ b/arch/riscv/include/asm/pgalloc.h
@@ -8,13 +8,31 @@
#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>
+/*
+ * While riscv platforms with riscv_ipi_for_rfence as true require an IPI to
+ * perform TLB shootdown, some platforms with riscv_ipi_for_rfence as false use
+ * SBI to perform TLB shootdown. To keep software pagetable walkers safe in this
+ * case we switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the
+ * comment below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h
+ * for more details.
+ */
+static inline void riscv_tlb_remove_ptdesc(struct mmu_gather *tlb, void *pt)
+{
+ if (riscv_use_sbi_for_rfence()) {
+ tlb_remove_ptdesc(tlb, pt);
+ } else {
+ pagetable_dtor(pt);
+ tlb_remove_page_ptdesc(tlb, pt);
+ }
+}
+
static inline void pmd_populate_kernel(struct mm_struct *mm,
pmd_t *pmd, pte_t *pte)
{
@@ -79,15 +97,6 @@ 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)
{
@@ -95,46 +104,19 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud)
__pud_free(mm, pud);
}
-#define __pud_free_tlb(tlb, pud, addr) \
-do { \
- if (pgtable_l4_enabled) { \
- pagetable_pud_dtor(virt_to_ptdesc(pud)); \
- tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pud)); \
- } \
-} while (0)
-
-#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;
-}
-
-static inline void __p4d_free(struct mm_struct *mm, p4d_t *p4d)
-{
- BUG_ON((unsigned long)p4d & (PAGE_SIZE-1));
- free_page((unsigned long)p4d);
+ if (pgtable_l4_enabled)
+ riscv_tlb_remove_ptdesc(tlb, virt_to_ptdesc(pud));
}
-#define p4d_free p4d_free
-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)
{
if (pgtable_l5_enabled)
- __p4d_free(mm, p4d);
+ riscv_tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d));
}
-
-#define __p4d_free_tlb(tlb, p4d, addr) \
-do { \
- if (pgtable_l5_enabled) \
- tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(p4d)); \
-} while (0)
#endif /* __PAGETABLE_PMD_FOLDED */
static inline void sync_kernel_mappings(pgd_t *pgd)
@@ -148,9 +130,8 @@ 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 */
sync_kernel_mappings(pgd);
}
@@ -159,19 +140,19 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
#ifndef __PAGETABLE_PMD_FOLDED
-#define __pmd_free_tlb(tlb, pmd, addr) \
-do { \
- pagetable_pmd_dtor(virt_to_ptdesc(pmd)); \
- tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pmd)); \
-} while (0)
+static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
+ unsigned long addr)
+{
+ riscv_tlb_remove_ptdesc(tlb, virt_to_ptdesc(pmd));
+}
#endif /* __PAGETABLE_PMD_FOLDED */
-#define __pte_free_tlb(tlb, pte, buf) \
-do { \
- pagetable_pte_dtor(page_ptdesc(pte)); \
- tlb_remove_page_ptdesc((tlb), page_ptdesc(pte));\
-} while (0)
+static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
+ unsigned long addr)
+{
+ riscv_tlb_remove_ptdesc(tlb, page_ptdesc(pte));
+}
#endif /* CONFIG_MMU */
#endif /* _ASM_RISCV_PGALLOC_H */
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
index b99bd66107a6..0897dd99ab8d 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 */
@@ -190,7 +188,7 @@ static inline int pud_bad(pud_t pud)
}
#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);
}
@@ -400,4 +398,24 @@ static inline struct page *pgd_page(pgd_t pgd)
#define p4d_offset p4d_offset
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 int pmd_devmap(pmd_t pmd)
+{
+ return pte_devmap(pmd_pte(pmd));
+}
+
+static inline int pud_devmap(pud_t pud)
+{
+ return 0;
+}
+
+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 179bd4afece4..a8f5205cea54 100644
--- a/arch/riscv/include/asm/pgtable-bits.h
+++ b/arch/riscv/include/asm/pgtable-bits.h
@@ -19,6 +19,7 @@
#define _PAGE_SOFT (3 << 8) /* Reserved for software */
#define _PAGE_SPECIAL (1 << 8) /* RSW: 0x1 */
+#define _PAGE_DEVMAP (1 << 9) /* RSW, devmap */
#define _PAGE_TABLE _PAGE_PRESENT
/*
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 6066822e7396..050fdc49b5ad 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -55,6 +55,9 @@
#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
/*
@@ -84,7 +87,7 @@
* 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 - (phys_ram_base >> PAGE_SHIFT))
+#define vmemmap ((struct page *)VMEMMAP_START - vmemmap_start_pfn)
#define PCI_IO_SIZE SZ_16M
#define PCI_IO_END VMEMMAP_START
@@ -104,19 +107,13 @@
#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)
@@ -127,17 +124,11 @@
#define VA_USER_SV48 (UL(1) << (VA_BITS_SV48 - 1))
#define VA_USER_SV57 (UL(1) << (VA_BITS_SV57 - 1))
-#ifdef CONFIG_COMPAT
#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
-#define MMAP_VA_BITS ((VA_BITS >= VA_BITS_SV48) ? VA_BITS_SV48 : VA_BITS)
-#define MMAP_MIN_VA_BITS (VA_BITS_SV39)
-#endif /* CONFIG_COMPAT */
-
-#else
#include <asm/pgtable-32.h>
#endif /* CONFIG_64BIT */
@@ -145,11 +136,14 @@
#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)
@@ -168,7 +162,7 @@ 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 */
@@ -241,7 +235,7 @@ 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);
}
@@ -291,7 +285,6 @@ static inline pte_t pud_pte(pud_t pud)
}
#ifdef CONFIG_RISCV_ISA_SVNAPOT
-#include <asm/cpufeature.h>
static __always_inline bool has_svnapot(void)
{
@@ -353,6 +346,19 @@ 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);
@@ -393,6 +399,13 @@ 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)
@@ -434,14 +447,21 @@ 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
/*
@@ -477,6 +497,9 @@ 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
@@ -486,12 +509,19 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf,
*/
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 __HAVE_ARCH_UPDATE_MMU_TLB
-#define update_mmu_tlb update_mmu_cache
+#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)
@@ -517,23 +547,25 @@ static inline void set_pte(pte_t *ptep, pte_t 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(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);
}
+#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_ptes_set(mm, ptep, pteval, nr);
for (;;) {
- __set_pte_at(ptep, pteval);
+ __set_pte_at(mm, ptep, pteval);
if (--nr == 0)
break;
ptep++;
@@ -545,7 +577,7 @@ static inline void set_ptes(struct mm_struct *mm, unsigned long addr,
static inline void pte_clear(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
- __set_pte_at(ptep, __pte(0));
+ __set_pte_at(mm, ptep, __pte(0));
}
#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS /* defined in mm/pgtable.c */
@@ -595,6 +627,12 @@ 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)
{
@@ -618,6 +656,17 @@ 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)
@@ -644,6 +693,7 @@ 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);
@@ -660,6 +710,12 @@ 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)
{
@@ -707,18 +763,23 @@ 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)));
+}
+
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, pmdp, pmd);
- return __set_pte_at((pte_t *)pmdp, pmd_pte(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, pudp, pud);
- return __set_pte_at((pte_t *)pudp, pud_pte(pud));
+ return __set_pte_at(mm, (pte_t *)pudp, pud_pte(pud));
}
#ifdef CONFIG_PAGE_TABLE_CHECK
@@ -866,11 +927,11 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
*/
#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))
-#define TASK_SIZE (test_thread_flag(TIF_32BIT) ? \
+#define TASK_SIZE_32 (_AC(0x80000000, UL) - PAGE_SIZE)
+#define TASK_SIZE (is_compat_task() ? \
TASK_SIZE_32 : TASK_SIZE_64)
#else
#define TASK_SIZE TASK_SIZE_64
@@ -878,7 +939,6 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
#else
#define TASK_SIZE FIXADDR_START
-#define TASK_SIZE_MIN TASK_SIZE
#endif
#else /* CONFIG_MMU */
@@ -886,7 +946,7 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
#define PAGE_SHARED __pgprot(0)
#define PAGE_KERNEL __pgprot(0)
#define swapper_pg_dir NULL
-#define TASK_SIZE 0xffffffffUL
+#define TASK_SIZE _AC(-1, UL)
#define VMALLOC_START _AC(0, UL)
#define VMALLOC_END TASK_SIZE
@@ -914,6 +974,25 @@ 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 a8509cc31ab2..5f56eb9d114a 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -14,42 +14,19 @@
#include <asm/ptrace.h>
-#ifdef CONFIG_64BIT
-#define DEFAULT_MAP_WINDOW (UL(1) << (MMAP_VA_BITS - 1))
-#define STACK_TOP_MAX TASK_SIZE
-
#define arch_get_mmap_end(addr, len, flags) \
({ \
- unsigned long mmap_end; \
- typeof(addr) _addr = (addr); \
- if ((_addr) == 0 || (IS_ENABLED(CONFIG_COMPAT) && is_compat_task())) \
- mmap_end = STACK_TOP_MAX; \
- else if ((_addr) >= VA_USER_SV57) \
- mmap_end = STACK_TOP_MAX; \
- else if ((((_addr) >= VA_USER_SV48)) && (VA_BITS >= VA_BITS_SV48)) \
- mmap_end = VA_USER_SV48; \
- else \
- mmap_end = VA_USER_SV39; \
- mmap_end; \
+ STACK_TOP_MAX; \
})
#define arch_get_mmap_base(addr, base) \
({ \
- unsigned long mmap_base; \
- typeof(addr) _addr = (addr); \
- typeof(base) _base = (base); \
- unsigned long rnd_gap = DEFAULT_MAP_WINDOW - (_base); \
- if ((_addr) == 0 || (IS_ENABLED(CONFIG_COMPAT) && is_compat_task())) \
- mmap_base = (_base); \
- else if (((_addr) >= VA_USER_SV57) && (VA_BITS >= VA_BITS_SV57)) \
- mmap_base = VA_USER_SV57 - rnd_gap; \
- else if ((((_addr) >= VA_USER_SV48)) && (VA_BITS >= VA_BITS_SV48)) \
- mmap_base = VA_USER_SV48 - rnd_gap; \
- else \
- mmap_base = VA_USER_SV39 - rnd_gap; \
- mmap_base; \
+ base; \
})
+#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
@@ -58,6 +35,12 @@
#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.
@@ -69,6 +52,7 @@
#endif
#ifndef __ASSEMBLY__
+#include <linux/cpumask.h>
struct task_struct;
struct pt_regs;
@@ -118,11 +102,18 @@ struct thread_struct {
unsigned long s[12]; /* s[0]: frame pointer */
struct __riscv_d_ext_state fstate;
unsigned long bad_cause;
+ unsigned long envcfg;
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 */
@@ -184,6 +175,17 @@ 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/sbi.h b/arch/riscv/include/asm/sbi.h
index 6e68f8dff76b..3d250824178b 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 {
@@ -33,6 +34,7 @@ enum sbi_ext_id {
SBI_EXT_PMU = 0x504D55,
SBI_EXT_DBCN = 0x4442434E,
SBI_EXT_STA = 0x535441,
+ SBI_EXT_NACL = 0x4E41434C,
/* Experimentals extensions must lie within this range */
SBI_EXT_EXPERIMENTAL_START = 0x08000000,
@@ -131,6 +133,8 @@ 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,
};
union sbi_pmu_ctr_info {
@@ -147,8 +151,17 @@ union sbi_pmu_ctr_info {
};
};
+/* 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 {
@@ -232,20 +245,22 @@ enum sbi_pmu_ctr_type {
#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_VSINH (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,
@@ -266,7 +281,126 @@ struct sbi_sta_struct {
u8 pad[47];
} __packed;
-#define SBI_STA_SHMEM_DISABLE -1
+#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 spec version fields */
#define SBI_SPEC_VERSION_DEFAULT 0x1
@@ -284,6 +418,7 @@ struct sbi_sta_struct {
#define SBI_ERR_ALREADY_AVAILABLE -6
#define SBI_ERR_ALREADY_STARTED -7
#define SBI_ERR_ALREADY_STOPPED -8
+#define SBI_ERR_NO_SHMEM -9
extern unsigned long sbi_spec_version;
struct sbiret {
@@ -292,10 +427,13 @@ 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);
@@ -355,11 +493,27 @@ 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);
}
-int sbi_err_map_linux_errno(int err);
+static inline int sbi_err_map_linux_errno(int err)
+{
+ switch (err) {
+ case SBI_SUCCESS:
+ return 0;
+ case SBI_ERR_DENIED:
+ return -EPERM;
+ case SBI_ERR_INVALID_PARAM:
+ return -EINVAL;
+ case SBI_ERR_INVALID_ADDRESS:
+ return -EFAULT;
+ case SBI_ERR_NOT_SUPPORTED:
+ case SBI_ERR_FAILURE:
+ default:
+ return -ENOTSUPP;
+ };
+}
extern bool sbi_debug_console_available;
int sbi_debug_console_write(const char *bytes, unsigned int num_bytes);
@@ -370,13 +524,19 @@ 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
diff --git a/arch/riscv/include/asm/set_memory.h b/arch/riscv/include/asm/set_memory.h
index ec11001c3fe0..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
diff --git a/arch/riscv/include/asm/signal.h b/arch/riscv/include/asm/signal.h
deleted file mode 100644
index 956ae0a01bad..000000000000
--- a/arch/riscv/include/asm/signal.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-
-#ifndef __ASM_SIGNAL_H
-#define __ASM_SIGNAL_H
-
-#include <uapi/asm/signal.h>
-#include <uapi/asm/ptrace.h>
-
-asmlinkage __visible
-void do_work_pending(struct pt_regs *regs, unsigned long thread_info_flags);
-
-#endif
diff --git a/arch/riscv/include/asm/simd.h b/arch/riscv/include/asm/simd.h
index 54efbf523d49..adb50f3ec205 100644
--- a/arch/riscv/include/asm/simd.h
+++ b/arch/riscv/include/asm/simd.h
@@ -34,9 +34,9 @@ static __must_check inline bool may_use_simd(void)
return false;
/*
- * Nesting is acheived in preempt_v by spreading the control for
+ * 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 prempt_v if kernel V-context exists. Then,
+ * 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.
*/
diff --git a/arch/riscv/include/asm/smp.h b/arch/riscv/include/asm/smp.h
index 0d555847cde6..7ac80e9f2288 100644
--- a/arch/riscv/include/asm/smp.h
+++ b/arch/riscv/include/asm/smp.h
@@ -49,12 +49,7 @@ void riscv_ipi_disable(void);
bool riscv_ipi_have_virq_range(void);
/* Set the IPI interrupt numbers for arch (called by irqchip drivers) */
-void riscv_ipi_set_virq_range(int virq, int nr, bool use_for_rfence);
-
-/* Check if we can use IPIs for remote FENCEs */
-DECLARE_STATIC_KEY_FALSE(riscv_ipi_for_rfence);
-#define riscv_use_ipi_for_rfence() \
- static_branch_unlikely(&riscv_ipi_for_rfence)
+void riscv_ipi_set_virq_range(int virq, int nr);
/* Check other CPUs stop or not */
bool smp_crash_stop_failed(void);
@@ -104,16 +99,10 @@ static inline bool riscv_ipi_have_virq_range(void)
return false;
}
-static inline void riscv_ipi_set_virq_range(int virq, int nr,
- bool use_for_rfence)
+static inline void riscv_ipi_set_virq_range(int virq, int nr)
{
}
-static inline bool riscv_use_ipi_for_rfence(void)
-{
- return false;
-}
-
#endif /* CONFIG_SMP */
#if defined(CONFIG_HOTPLUG_CPU) && (CONFIG_SMP)
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/string.h b/arch/riscv/include/asm/string.h
index a96b1fea24fe..5ba77f60bf0b 100644
--- a/arch/riscv/include/asm/string.h
+++ b/arch/riscv/include/asm/string.h
@@ -19,6 +19,7 @@ extern asmlinkage void *__memcpy(void *, const void *, size_t);
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);
@@ -27,6 +28,7 @@ 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__)
diff --git a/arch/riscv/include/asm/suspend.h b/arch/riscv/include/asm/suspend.h
index 491296a335d0..4ffb022b097f 100644
--- a/arch/riscv/include/asm/suspend.h
+++ b/arch/riscv/include/asm/suspend.h
@@ -13,7 +13,6 @@ 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;
@@ -56,4 +55,7 @@ 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 7efdb0584d47..0e71eb82f920 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -8,6 +8,7 @@
#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>
@@ -69,17 +70,58 @@ static __always_inline bool has_fpu(void) { return false; }
#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_fpu(__prev, __next); \
- if (has_vector()) \
+ 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_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
index eeec04b7dae6..ac80216549ff 100644
--- a/arch/riscv/include/asm/syscall_wrapper.h
+++ b/arch/riscv/include/asm/syscall_wrapper.h
@@ -12,25 +12,52 @@
asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *);
-#define SC_RISCV_REGS_TO_ARGS(x, ...) \
- __MAP(x,__SC_ARGS \
- ,,regs->orig_a0,,regs->a1,,regs->a2 \
+#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 long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \
static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \
- asmlinkage long __riscv_compat_sys##name(const struct pt_regs *regs) \
+ __SYSCALL_SE_DEFINEx(x, compat_sys, name, __VA_ARGS__) \
{ \
- return __se_compat_sys##name(SC_RISCV_REGS_TO_ARGS(x,__VA_ARGS__)); \
+ return __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__)); \
} \
- static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \
+ asmlinkage long __riscv_compat_sys##name(const struct pt_regs *regs) \
{ \
- return __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__)); \
+ 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__))
@@ -51,19 +78,18 @@ asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *);
#define __SYSCALL_DEFINEx(x, name, ...) \
asmlinkage long __riscv_sys##name(const struct pt_regs *regs); \
ALLOW_ERROR_INJECTION(__riscv_sys##name, ERRNO); \
- static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \
static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \
- asmlinkage long __riscv_sys##name(const struct pt_regs *regs) \
- { \
- return __se_sys##name(SC_RISCV_REGS_TO_ARGS(x,__VA_ARGS__)); \
- } \
- static long __se_sys##name(__MAP(x,__SC_LONG,__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) \
diff --git a/arch/riscv/include/asm/patch.h b/arch/riscv/include/asm/text-patching.h
index e88b52d39eac..7228e266b9a1 100644
--- a/arch/riscv/include/asm/patch.h
+++ b/arch/riscv/include/asm/text-patching.h
@@ -6,9 +6,10 @@
#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_set_nosync(void *addr, u8 c, size_t len);
-int patch_text(void *addr, u32 *insns, int ninsns);
+int patch_text(void *addr, u32 *insns, size_t len);
extern int riscv_patch_in_stop_machine;
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index 5d473343634b..f5916a70879a 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -10,9 +10,15 @@
#include <asm/page.h>
#include <linux/const.h>
+#include <linux/sizes.h>
/* thread information allocation */
-#define THREAD_SIZE_ORDER CONFIG_THREAD_SIZE_ORDER
+#ifdef CONFIG_KASAN
+#define KASAN_STACK_ORDER 1
+#else
+#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)
/*
@@ -60,6 +66,13 @@ struct thread_info {
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
@@ -94,9 +107,10 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
* - pending work-to-be-done flags are in lowest half-word
* - other flags in upper half-word(s)
*/
-#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_NOTIFY_SIGNAL 9 /* signal notifications exist */
@@ -104,15 +118,12 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
#define TIF_32BIT 11 /* compat-mode 32bit process */
#define TIF_RISCV_V_DEFER_RESTORE 12 /* restore Vector before returing to user */
+#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_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL)
#define _TIF_UPROBE (1 << TIF_UPROBE)
#define _TIF_RISCV_V_DEFER_RESTORE (1 << TIF_RISCV_V_DEFER_RESTORE)
-#define _TIF_WORK_MASK \
- (_TIF_NOTIFY_RESUME | _TIF_SIGPENDING | _TIF_NEED_RESCHED | \
- _TIF_NOTIFY_SIGNAL | _TIF_UPROBE)
-
#endif /* _ASM_RISCV_THREAD_INFO_H */
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index 4112cc8d1d69..72e559934952 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -15,24 +15,34 @@
#define FLUSH_TLB_NO_ASID ((unsigned long)-1)
#ifdef CONFIG_MMU
-extern unsigned long asid_mask;
-
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,
@@ -55,27 +65,9 @@ void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
void arch_flush_tlb_batched_pending(struct mm_struct *mm);
void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
-#else /* CONFIG_SMP && CONFIG_MMU */
-
-#define flush_tlb_all() local_flush_tlb_all()
-#define flush_tlb_page(vma, addr) local_flush_tlb_page(addr)
-
-static inline void flush_tlb_range(struct vm_area_struct *vma,
- unsigned long start, unsigned long end)
-{
- local_flush_tlb_all();
-}
-
-/* Flush a range of kernel pages */
-static inline void flush_tlb_kernel_range(unsigned long start,
- unsigned long end)
-{
- local_flush_tlb_all();
-}
-
-#define flush_tlb_mm(mm) flush_tlb_all()
-#define flush_tlb_mm_range(mm, start, end, page_size) flush_tlb_all()
-#define local_flush_tlb_kernel_range(start, end) flush_tlb_all()
-#endif /* !CONFIG_SMP || !CONFIG_MMU */
+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
index 61183688bdd5..fe1a8bf6902d 100644
--- a/arch/riscv/include/asm/topology.h
+++ b/arch/riscv/include/asm/topology.h
@@ -4,6 +4,10 @@
#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
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 ec0cab9fbddd..fee56b0c8058 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
*/
@@ -130,7 +163,7 @@ 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; \
\
__chk_user_ptr(__gu_ptr); \
@@ -246,7 +279,7 @@ 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; \
\
@@ -293,13 +326,13 @@ 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);
@@ -314,12 +347,12 @@ 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; \
+ long __kr_err = 0; \
\
__get_user_nocheck(*((type *)(dst)), (type *)(src), __kr_err); \
if (unlikely(__kr_err)) \
@@ -328,7 +361,7 @@ do { \
#define __put_kernel_nofault(dst, src, type, err_label) \
do { \
- long __kr_err; \
+ long __kr_err = 0; \
\
__put_user_nocheck(*((type *)(src)), (type *)(dst), __kr_err); \
if (unlikely(__kr_err)) \
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 3fc7deda9190..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
diff --git a/arch/riscv/include/asm/vdso/processor.h b/arch/riscv/include/asm/vdso/processor.h
index 96b65a5396df..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)
{
@@ -14,16 +15,11 @@ static inline void cpu_relax(void)
__asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy));
#endif
-#ifdef CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE
/*
* Reduce instruction retirement.
* This assumes the PC changes.
*/
- __asm__ __volatile__ ("pause");
-#else
- /* Encoding of the pause instruction */
- __asm__ __volatile__ (".4byte 0x100000F");
-#endif
+ __asm__ __volatile__ (RISCV_PAUSE);
barrier();
}
diff --git a/arch/riscv/include/asm/vdso/data.h b/arch/riscv/include/asm/vdso/time_data.h
index dc2f76f58b76..dfa65228999b 100644
--- a/arch/riscv/include/asm/vdso/data.h
+++ b/arch/riscv/include/asm/vdso/time_data.h
@@ -1,12 +1,12 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __RISCV_ASM_VDSO_DATA_H
-#define __RISCV_ASM_VDSO_DATA_H
+#ifndef __RISCV_ASM_VDSO_TIME_DATA_H
+#define __RISCV_ASM_VDSO_TIME_DATA_H
#include <linux/types.h>
#include <vdso/datapage.h>
#include <asm/hwprobe.h>
-struct arch_vdso_data {
+struct arch_vdso_time_data {
/* Stash static answers to the hwprobe queries when all CPUs are selected. */
__u64 all_cpu_hwprobe_values[RISCV_HWPROBE_MAX_KEY + 1];
@@ -14,4 +14,4 @@ struct arch_vdso_data {
__u8 homogeneous_cpus;
};
-#endif /* __RISCV_ASM_VDSO_DATA_H */
+#endif /* __RISCV_ASM_VDSO_TIME_DATA_H */
diff --git a/arch/riscv/include/asm/vdso/vsyscall.h b/arch/riscv/include/asm/vdso/vsyscall.h
index 82fd5d83bd60..e8a9c4b53c0c 100644
--- a/arch/riscv/include/asm/vdso/vsyscall.h
+++ b/arch/riscv/include/asm/vdso/vsyscall.h
@@ -4,14 +4,10 @@
#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;
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index 0cd6f0a027d1..e8a83f55be2b 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -18,9 +18,31 @@
#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);
@@ -37,42 +59,65 @@ static inline u32 riscv_v_flags(void)
static __always_inline bool has_vector(void)
{
- return riscv_has_extension_unlikely(RISCV_ISA_EXT_v);
+ 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 = (regs->status & ~SR_VS) | SR_VS_CLEAN;
+ regs->status = __riscv_v_vstate_or(regs->status, CLEAN);
}
static inline void __riscv_v_vstate_dirty(struct pt_regs *regs)
{
- regs->status = (regs->status & ~SR_VS) | SR_VS_DIRTY;
+ regs->status = __riscv_v_vstate_or(regs->status, DIRTY);
}
static inline void riscv_v_vstate_off(struct pt_regs *regs)
{
- regs->status = (regs->status & ~SR_VS) | SR_VS_OFF;
+ regs->status = __riscv_v_vstate_or(regs->status, OFF);
}
static inline void riscv_v_vstate_on(struct pt_regs *regs)
{
- regs->status = (regs->status & ~SR_VS) | SR_VS_INITIAL;
+ regs->status = __riscv_v_vstate_or(regs->status, INITIAL);
}
static inline bool riscv_v_vstate_query(struct pt_regs *regs)
{
- return (regs->status & SR_VS) != 0;
+ return !__riscv_v_vstate_check(regs->status, OFF);
}
static __always_inline void riscv_v_enable(void)
{
- csr_set(CSR_SSTATUS, SR_VS);
+ 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)
{
- csr_clear(CSR_SSTATUS, SR_VS);
+ if (has_xtheadvector())
+ csr_clear(CSR_SSTATUS, SR_VS_THEAD);
+ else
+ csr_clear(CSR_SSTATUS, SR_VS);
}
static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest)
@@ -81,23 +126,65 @@ static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest)
"csrr %0, " __stringify(CSR_VSTART) "\n\t"
"csrr %1, " __stringify(CSR_VTYPE) "\n\t"
"csrr %2, " __stringify(CSR_VL) "\n\t"
- "csrr %3, " __stringify(CSR_VCSR) "\n\t"
- "csrr %4, " __stringify(CSR_VLENB) "\n\t"
: "=r" (dest->vstart), "=r" (dest->vtype), "=r" (dest->vl),
- "=r" (dest->vcsr), "=r" (dest->vlenb) : :);
+ "=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, +v\n\t"
+ ".option arch, +zve32x\n\t"
"vsetvl x0, %2, %1\n\t"
".option pop\n\t"
"csrw " __stringify(CSR_VSTART) ", %0\n\t"
- "csrw " __stringify(CSR_VCSR) ", %3\n\t"
- : : "r" (src->vstart), "r" (src->vtype), "r" (src->vl),
- "r" (src->vcsr) :);
+ : : "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,
@@ -107,19 +194,33 @@ static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to,
riscv_v_enable();
__vstate_csr_save(save_to);
- asm volatile (
- ".option push\n\t"
- ".option arch, +v\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");
+ 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();
}
@@ -129,19 +230,33 @@ static inline void __riscv_v_vstate_restore(struct __riscv_v_ext_state *restore_
unsigned long vl;
riscv_v_enable();
- asm volatile (
- ".option push\n\t"
- ".option arch, +v\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");
+ 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();
}
@@ -151,33 +266,41 @@ 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, +v\n\t"
- "vsetvli %0, x0, e8, m8, ta, ma\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) : "memory");
+ : "=&r" (vl) : "r" (vtype_inval));
+
riscv_v_disable();
}
static inline void riscv_v_vstate_discard(struct pt_regs *regs)
{
- if ((regs->status & SR_VS) == SR_VS_OFF)
- return;
-
- __riscv_v_vstate_discard();
- __riscv_v_vstate_dirty(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 ((regs->status & SR_VS) == SR_VS_DIRTY) {
+ if (__riscv_v_vstate_check(regs->status, DIRTY)) {
__riscv_v_vstate_save(vstate, vstate->datap);
__riscv_v_vstate_clean(regs);
}
@@ -186,7 +309,7 @@ static inline void riscv_v_vstate_save(struct __riscv_v_ext_state *vstate,
static inline void riscv_v_vstate_restore(struct __riscv_v_ext_state *vstate,
struct pt_regs *regs)
{
- if ((regs->status & SR_VS) != SR_VS_OFF) {
+ if (riscv_v_vstate_query(regs)) {
__riscv_v_vstate_restore(vstate, vstate->datap);
__riscv_v_vstate_clean(regs);
}
@@ -195,7 +318,7 @@ static inline void riscv_v_vstate_restore(struct __riscv_v_ext_state *vstate,
static inline void riscv_v_vstate_set_restore(struct task_struct *task,
struct pt_regs *regs)
{
- if ((regs->status & SR_VS) != SR_VS_OFF) {
+ if (riscv_v_vstate_query(regs)) {
set_tsk_thread_flag(task, TIF_RISCV_V_DEFER_RESTORE);
riscv_v_vstate_on(regs);
}
@@ -268,6 +391,9 @@ 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; }
@@ -284,4 +410,15 @@ static inline bool riscv_v_vstate_ctrl_user_allowed(void) { return false; }
#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/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 e55407ace0c3..a5150cdf34d8 100644
--- a/arch/riscv/include/asm/vendorid_list.h
+++ b/arch/riscv/include/asm/vendorid_list.h
@@ -5,7 +5,8 @@
#ifndef ASM_VENDOR_LIST_H
#define ASM_VENDOR_LIST_H
-#define ANDESTECH_VENDOR_ID 0x31e
+#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 51f6dfe19745..fefe94dc98e2 100644
--- a/arch/riscv/include/asm/vmalloc.h
+++ b/arch/riscv/include/asm/vmalloc.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
#ifndef _ASM_RISCV_VMALLOC_H
#define _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 f3f031e34191..3802cda71ab7 100644
--- a/arch/riscv/include/asm/word-at-a-time.h
+++ b/arch/riscv/include/asm/word-at-a-time.h
@@ -10,7 +10,8 @@
#include <asm/asm-extable.h>
-#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/wordpart.h>
struct word_at_a_time {
const unsigned long one_bits, high_bits;
diff --git a/arch/riscv/include/asm/xip_fixup.h b/arch/riscv/include/asm/xip_fixup.h
index b65bf6306f69..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
+ /* 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
- REG_L t1, _xip_phys_offset
- sub \reg, \reg, t1
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/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 10aaa83db89e..95050ebe9ad0 100644
--- a/arch/riscv/include/uapi/asm/auxvec.h
+++ b/arch/riscv/include/uapi/asm/auxvec.h
@@ -34,7 +34,7 @@
#define AT_L3_CACHEGEOMETRY 47
/* entries in ARCH_DLINFO */
-#define AT_VECTOR_SIZE_ARCH 9
+#define AT_VECTOR_SIZE_ARCH 10
#define AT_MINSIGSTKSZ 51
#endif /* _UAPI_ASM_RISCV_AUXVEC_H */
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index 9f2a8e3ff204..c3c1cc951cb9 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
/*
- * Copyright 2023 Rivos, Inc
+ * Copyright 2023-2024 Rivos, Inc
*/
#ifndef _UAPI_ASM_HWPROBE_H
@@ -54,11 +54,25 @@ struct riscv_hwprobe {
#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 (1 << 31)
+#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_KEY_CPUPERF_0 5
#define RISCV_HWPROBE_MISALIGNED_UNKNOWN (0 << 0)
#define RISCV_HWPROBE_MISALIGNED_EMULATED (1 << 0)
@@ -67,6 +81,20 @@ struct riscv_hwprobe {
#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
/* Increase RISCV_HWPROBE_MAX_KEY when adding items. */
/* Flags */
diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index 7499e88a947c..f06bc5efcd79 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -16,7 +16,6 @@
#include <asm/ptrace.h>
#define __KVM_HAVE_IRQ_LINE
-#define __KVM_HAVE_READONLY_MEM
#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
@@ -166,6 +165,23 @@ enum KVM_RISCV_ISA_EXT_ID {
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_MAX,
};
@@ -185,6 +201,7 @@ enum KVM_RISCV_SBI_EXT_ID {
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,
};
@@ -198,9 +215,6 @@ struct kvm_riscv_sbi_sta {
#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
diff --git a/arch/riscv/include/uapi/asm/unistd.h b/arch/riscv/include/uapi/asm/unistd.h
index 950ab3fd4409..81896bbbf727 100644
--- a/arch/riscv/include/uapi/asm/unistd.h
+++ b/arch/riscv/include/uapi/asm/unistd.h
@@ -14,41 +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)
-#endif
-__SYSCALL(__NR_riscv_flush_icache, sys_riscv_flush_icache)
-
-/*
- * Allows userspace to query the kernel for CPU architecture and
- * microarchitecture details across a given set of CPUs.
- */
-#ifndef __NR_riscv_hwprobe
-#define __NR_riscv_hwprobe (__NR_arch_specific_syscall + 14)
+#if __BITS_PER_LONG == 64
+#include <asm/unistd_64.h>
+#else
+#include <asm/unistd_32.h>
#endif
-__SYSCALL(__NR_riscv_hwprobe, sys_riscv_hwprobe)
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)