Merge tag 'riscv-for-linus-4.20-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/palmer/riscv-linux

Pull RISC-V updates from Palmer Dabbelt:
 "This patch set contains a lot (at least, for me) of improvements to
  the RISC-V kernel port:

   - The removal of some cacheinfo values that were bogus.

   - On systems with F but without D the kernel will not show the F
     extension to userspace, as it isn't actually supported.

   - Support for futexes.

   - Removal of some unused code.

   - Cleanup of some menuconfig entries.

   - Support for systems without a floating-point unit, and for building
     kernels that will never use the floating-point unit.

   - More fixes to the RV32I port, which regressed again. It's really
     time to get this into a regression test somewhere so I stop
     breaking it. Thanks to Zong for resurrecting it again!

   - Various fixes that resulted from a year old review of our original
     patch set that I finally got around to.

   - Various improvements to SMP support, largely based around having
     switched to logical hart numbering, as well as some interrupt
     improvements. This one is in the same patch set as above, thanks to
     Atish for sheparding everything though as my patch set was a bit of
     a mess.

  I'm pretty sure this is our largest patch set since the original
  kernel contribution, and it's certainly the one with the most
  contributors. While I don't have anything else I know I'm going to
  submit for the merge window, I would be somewhat surprised if I didn't
  screw anything up.

  Thanks for the help, everyone!"

* tag 'riscv-for-linus-4.20-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/palmer/riscv-linux: (31 commits)
  RISC-V: Cosmetic menuconfig changes
  riscv: move GCC version check for ARCH_SUPPORTS_INT128 to Kconfig
  RISC-V: remove the unused return_to_handler export
  RISC-V: Add futex support.
  RISC-V: Add FP register ptrace support for gdb.
  RISC-V: Mask out the F extension on systems without D
  RISC-V: Don't set cacheinfo.{physical_line_partition,attributes}
  RISC-V: Show IPI stats
  RISC-V: Show CPU ID and Hart ID separately in /proc/cpuinfo
  RISC-V: Use Linux logical CPU number instead of hartid
  RISC-V: Add logical CPU indexing for RISC-V
  RISC-V: Use WRITE_ONCE instead of direct access
  RISC-V: Use mmgrab()
  RISC-V: Rename im_okay_therefore_i_am to found_boot_cpu
  RISC-V: Rename riscv_of_processor_hart to riscv_of_processor_hartid
  RISC-V: Provide a cleaner raw_smp_processor_id()
  RISC-V: Disable preemption before enabling interrupts
  RISC-V: Comment on the TLB flush in smp_callin()
  RISC-V: Filter ISA and MMU values in cpuinfo
  RISC-V: Don't set cacheinfo.{physical_line_partition,attributes}
  ...

7 files changed, 192 insertions, 17 deletions

diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild
index efdbe311e936..6a646d9ea780 100644
--- a/arch/riscv/include/asm/Kbuild
+++ b/arch/riscv/include/asm/Kbuild
@@ -13,7 +13,6 @@ generic-y += errno.h
 generic-y += exec.h
 generic-y += fb.h
 generic-y += fcntl.h
-generic-y += futex.h
 generic-y += hardirq.h
 generic-y += hash.h
 generic-y += hw_irq.h
diff --git a/arch/riscv/include/asm/futex.h b/arch/riscv/include/asm/futex.h
new file mode 100644
index 000000000000..3b19eba1bc8e
--- /dev/null
+++ b/arch/riscv/include/asm/futex.h
@@ -0,0 +1,128 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2006  Ralf Baechle (ralf@linux-mips.org)
+ * Copyright (c) 2018  Jim Wilson (jimw@sifive.com)
+ */
+
+#ifndef _ASM_FUTEX_H
+#define _ASM_FUTEX_H
+
+#ifndef CONFIG_RISCV_ISA_A
+/*
+ * Use the generic interrupt disabling versions if the A extension
+ * is not supported.
+ */
+#ifdef CONFIG_SMP
+#error "Can't support generic futex calls without A extension on SMP"
+#endif
+#include <asm-generic/futex.h>
+
+#else /* CONFIG_RISCV_ISA_A */
+
+#include <linux/futex.h>
+#include <linux/uaccess.h>
+#include <linux/errno.h>
+#include <asm/asm.h>
+
+#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)	\
+{								\
+	uintptr_t tmp;						\
+	__enable_user_access();					\
+	__asm__ __volatile__ (					\
+	"1:	" insn "				\n"	\
+	"2:						\n"	\
+	"	.section .fixup,\"ax\"			\n"	\
+	"	.balign 4				\n"	\
+	"3:	li %[r],%[e]				\n"	\
+	"	jump 2b,%[t]				\n"	\
+	"	.previous				\n"	\
+	"	.section __ex_table,\"a\"		\n"	\
+	"	.balign " RISCV_SZPTR "			\n"	\
+	"	" RISCV_PTR " 1b, 3b			\n"	\
+	"	.previous				\n"	\
+	: [r] "+r" (ret), [ov] "=&r" (oldval),			\
+	  [u] "+m" (*uaddr), [t] "=&r" (tmp)			\
+	: [op] "Jr" (oparg), [e] "i" (-EFAULT)			\
+	: "memory");						\
+	__disable_user_access();				\
+}
+
+static inline int
+arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
+{
+	int oldval = 0, ret = 0;
+
+	pagefault_disable();
+
+	switch (op) {
+	case FUTEX_OP_SET:
+		__futex_atomic_op("amoswap.w.aqrl %[ov],%z[op],%[u]",
+				  ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_ADD:
+		__futex_atomic_op("amoadd.w.aqrl %[ov],%z[op],%[u]",
+				  ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_OR:
+		__futex_atomic_op("amoor.w.aqrl %[ov],%z[op],%[u]",
+				  ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_ANDN:
+		__futex_atomic_op("amoand.w.aqrl %[ov],%z[op],%[u]",
+				  ret, oldval, uaddr, ~oparg);
+		break;
+	case FUTEX_OP_XOR:
+		__futex_atomic_op("amoxor.w.aqrl %[ov],%z[op],%[u]",
+				  ret, oldval, uaddr, oparg);
+		break;
+	default:
+		ret = -ENOSYS;
+	}
+
+	pagefault_enable();
+
+	if (!ret)
+		*oval = oldval;
+
+	return ret;
+}
+
+static inline int
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
+{
+	int ret = 0;
+	u32 val;
+	uintptr_t tmp;
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+		return -EFAULT;
+
+	__enable_user_access();
+	__asm__ __volatile__ (
+	"1:	lr.w.aqrl %[v],%[u]			\n"
+	"	bne %[v],%z[ov],3f			\n"
+	"2:	sc.w.aqrl %[t],%z[nv],%[u]		\n"
+	"	bnez %[t],1b				\n"
+	"3:						\n"
+	"	.section .fixup,\"ax\"			\n"
+	"	.balign 4				\n"
+	"4:	li %[r],%[e]				\n"
+	"	jump 3b,%[t]				\n"
+	"	.previous				\n"
+	"	.section __ex_table,\"a\"		\n"
+	"	.balign " RISCV_SZPTR "			\n"
+	"	" RISCV_PTR " 1b, 4b			\n"
+	"	" RISCV_PTR " 2b, 4b			\n"
+	"	.previous				\n"
+	: [r] "+r" (ret), [v] "=&r" (val), [u] "+m" (*uaddr), [t] "=&r" (tmp)
+	: [ov] "Jr" (oldval), [nv] "Jr" (newval), [e] "i" (-EFAULT)
+	: "memory");
+	__disable_user_access();
+
+	*uval = val;
+	return ret;
+}
+
+#endif /* CONFIG_RISCV_ISA_A */
+#endif /* _ASM_FUTEX_H */
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index 3fe4af8147d2..50de774d827a 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -88,7 +88,7 @@ static inline void wait_for_interrupt(void)
 }
 
 struct device_node;
-extern int riscv_of_processor_hart(struct device_node *node);
+int riscv_of_processor_hartid(struct device_node *node);
 
 extern void riscv_fill_hwcap(void);
 
diff --git a/arch/riscv/include/asm/smp.h b/arch/riscv/include/asm/smp.h
index 36016845461d..41aa73b476f4 100644
--- a/arch/riscv/include/asm/smp.h
+++ b/arch/riscv/include/asm/smp.h
@@ -14,16 +14,24 @@
 #ifndef _ASM_RISCV_SMP_H
 #define _ASM_RISCV_SMP_H
 
-/* This both needs asm-offsets.h and is used when generating it. */
-#ifndef GENERATING_ASM_OFFSETS
-#include <asm/asm-offsets.h>
-#endif
-
 #include <linux/cpumask.h>
 #include <linux/irqreturn.h>
+#include <linux/thread_info.h>
+
+#define INVALID_HARTID ULONG_MAX
+/*
+ * Mapping between linux logical cpu index and hartid.
+ */
+extern unsigned long __cpuid_to_hartid_map[NR_CPUS];
+#define cpuid_to_hartid_map(cpu)    __cpuid_to_hartid_map[cpu]
+
+struct seq_file;
 
 #ifdef CONFIG_SMP
 
+/* print IPI stats */
+void show_ipi_stats(struct seq_file *p, int prec);
+
 /* SMP initialization hook for setup_arch */
 void __init setup_smp(void);
 
@@ -33,14 +41,31 @@ void arch_send_call_function_ipi_mask(struct cpumask *mask);
 /* Hook for the generic smp_call_function_single() routine. */
 void arch_send_call_function_single_ipi(int cpu);
 
+int riscv_hartid_to_cpuid(int hartid);
+void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out);
+
 /*
- * This is particularly ugly: it appears we can't actually get the definition
- * of task_struct here, but we need access to the CPU this task is running on.
- * Instead of using C we're using asm-offsets.h to get the current processor
- * ID.
+ * Obtains the hart ID of the currently executing task.  This relies on
+ * THREAD_INFO_IN_TASK, but we define that unconditionally.
  */
-#define raw_smp_processor_id() (*((int*)((char*)get_current() + TASK_TI_CPU)))
+#define raw_smp_processor_id() (current_thread_info()->cpu)
 
-#endif /* CONFIG_SMP */
+#else
+
+static inline void show_ipi_stats(struct seq_file *p, int prec)
+{
+}
 
+static inline int riscv_hartid_to_cpuid(int hartid)
+{
+	return 0;
+}
+
+static inline void riscv_cpuid_to_hartid_mask(const struct cpumask *in,
+					      struct cpumask *out)
+{
+	cpumask_set_cpu(cpuid_to_hartid_map(0), out);
+}
+
+#endif /* CONFIG_SMP */
 #endif /* _ASM_RISCV_SMP_H */
diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index dd6b05bff75b..733559083f24 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -18,6 +18,7 @@
 #include <asm/ptrace.h>
 #include <asm/csr.h>
 
+#ifdef CONFIG_FPU
 extern void __fstate_save(struct task_struct *save_to);
 extern void __fstate_restore(struct task_struct *restore_from);
 
@@ -55,6 +56,14 @@ static inline void __switch_to_aux(struct task_struct *prev,
 	fstate_restore(next, task_pt_regs(next));
 }
 
+extern bool has_fpu;
+#else
+#define has_fpu false
+#define fstate_save(task, regs) do { } while (0)
+#define fstate_restore(task, regs) do { } while (0)
+#define __switch_to_aux(__prev, __next) do { } while (0)
+#endif
+
 extern struct task_struct *__switch_to(struct task_struct *,
 				       struct task_struct *);
 
@@ -62,7 +71,8 @@ extern struct task_struct *__switch_to(struct task_struct *,
 do {							\
 	struct task_struct *__prev = (prev);		\
 	struct task_struct *__next = (next);		\
-	__switch_to_aux(__prev, __next);		\
+	if (has_fpu)					\
+		__switch_to_aux(__prev, __next);	\
 	((last) = __switch_to(__prev, __next));		\
 } while (0)
 
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index 85c2d8bae957..54fee0cadb1e 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -16,6 +16,7 @@
 #define _ASM_RISCV_TLBFLUSH_H
 
 #include <linux/mm_types.h>
+#include <asm/smp.h>
 
 /*
  * Flush entire local TLB.  'sfence.vma' implicitly fences with the instruction
@@ -49,13 +50,22 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 
 #include <asm/sbi.h>
 
+static inline void remote_sfence_vma(struct cpumask *cmask, unsigned long start,
+				     unsigned long size)
+{
+	struct cpumask hmask;
+
+	cpumask_clear(&hmask);
+	riscv_cpuid_to_hartid_mask(cmask, &hmask);
+	sbi_remote_sfence_vma(hmask.bits, start, size);
+}
+
 #define flush_tlb_all() sbi_remote_sfence_vma(NULL, 0, -1)
 #define flush_tlb_page(vma, addr) flush_tlb_range(vma, addr, 0)
 #define flush_tlb_range(vma, start, end) \
-	sbi_remote_sfence_vma(mm_cpumask((vma)->vm_mm)->bits, \
-			      start, (end) - (start))
+	remote_sfence_vma(mm_cpumask((vma)->vm_mm), start, (end) - (start))
 #define flush_tlb_mm(mm) \
-	sbi_remote_sfence_vma(mm_cpumask(mm)->bits, 0, -1)
+	remote_sfence_vma(mm_cpumask(mm), 0, -1)
 
 #endif /* CONFIG_SMP */
 
diff --git a/arch/riscv/include/uapi/asm/elf.h b/arch/riscv/include/uapi/asm/elf.h
index 1e0dfc36aab9..644a00ce6e2e 100644
--- a/arch/riscv/include/uapi/asm/elf.h
+++ b/arch/riscv/include/uapi/asm/elf.h
@@ -19,7 +19,10 @@ typedef unsigned long elf_greg_t;
 typedef struct user_regs_struct elf_gregset_t;
 #define ELF_NGREG (sizeof(elf_gregset_t) / sizeof(elf_greg_t))
 
+/* We don't support f without d, or q.  */
+typedef __u64 elf_fpreg_t;
 typedef union __riscv_fp_state elf_fpregset_t;
+#define ELF_NFPREG (sizeof(struct __riscv_d_ext_state) / sizeof(elf_fpreg_t))
 
 #if __riscv_xlen == 64
 #define ELF_RISCV_R_SYM(r_info)		ELF64_R_SYM(r_info)