Merge tag 'csky-for-linus-5.7-rc1' of git://github.com/c-sky/csky-linux

Pull csky updates from Guo Ren:

 - Add kproobes/uprobes support

 - Add lockdep, rseq, gcov support

 - Fixup init_fpu

 - Fixup ftrace_modify deadlock

 - Fixup speculative execution on IO area

* tag 'csky-for-linus-5.7-rc1' of git://github.com/c-sky/csky-linux:
  csky: Fixup cpu speculative execution to IO area
  csky: Add uprobes support
  csky: Add kprobes supported
  csky: Enable LOCKDEP_SUPPORT
  csky: Enable the gcov function
  csky: Fixup get wrong psr value from phyical reg
  csky/ftrace: Fixup ftrace_modify_code deadlock without CPU_HAS_ICACHE_INS
  csky: Implement ftrace with regs
  csky: Add support for restartable sequence
  csky: Implement ptrace regs and stack API
  csky: Fixup init_fpu compile warning with __init

arch/csky/Kconfig

@@ -3,6 +3,7 @@ config CSKY
 	def_bool y
 	select ARCH_32BIT_OFF_T
 	select ARCH_HAS_DMA_PREP_COHERENT
+	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_USE_BUILTIN_BSWAP
@@ -38,16 +39,22 @@ config CSKY
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_COPY_THREAD_TLS
 	select HAVE_DYNAMIC_FTRACE
+	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZO
 	select HAVE_KERNEL_LZMA
+	select HAVE_KPROBES if !CPU_CK610
+	select HAVE_KPROBES_ON_FTRACE if !CPU_CK610
+	select HAVE_KRETPROBES if !CPU_CK610
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_DMA_CONTIGUOUS
+	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_RSEQ
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
 	select MAY_HAVE_SPARSE_IRQ
@@ -65,6 +72,12 @@ config CSKY
 	select PCI_SYSCALL if PCI
 	select PCI_MSI if PCI
 
+config LOCKDEP_SUPPORT
+	def_bool y
+
+config ARCH_SUPPORTS_UPROBES
+	def_bool y if !CPU_CK610
+
 config CPU_HAS_CACHEV2
 	bool
 

arch/csky/abiv1/inc/abi/entry.h

@@ -172,10 +172,7 @@
 	addi	r6, 0xe
 	cpwcr	r6, cpcr30
 
-	lsri	r6, 28
-	addi	r6, 2
-	lsli	r6, 28
-	addi	r6, 0xe
+	movi	r6, 0
 	cpwcr	r6, cpcr31
 .endm
 

arch/csky/abiv2/fpu.c

@@ -10,11 +10,6 @@
 #define MTCR_DIST	0xC0006420
 #define MFCR_DIST	0xC0006020
 
-void __init init_fpu(void)
-{
-	mtcr("cr<1, 2>", 0);
-}
-
 /*
  * fpu_libc_helper() is to help libc to excute:
  *  - mfcr %a, cr<1, 2>

arch/csky/abiv2/inc/abi/entry.h

@@ -100,6 +100,66 @@
 	rte
 .endm
 
+.macro SAVE_REGS_FTRACE
+	subi    sp, 152
+	stw	tls, (sp, 0)
+	stw	lr, (sp, 4)
+
+	mfcr	lr, psr
+	stw	lr, (sp, 12)
+
+	addi    lr, sp, 152
+	stw	lr, (sp, 16)
+
+	stw     a0, (sp, 20)
+	stw     a0, (sp, 24)
+	stw     a1, (sp, 28)
+	stw     a2, (sp, 32)
+	stw     a3, (sp, 36)
+
+	addi	sp, 40
+	stm	r4-r13, (sp)
+
+	addi    sp, 40
+	stm     r16-r30, (sp)
+#ifdef CONFIG_CPU_HAS_HILO
+	mfhi	lr
+	stw	lr, (sp, 60)
+	mflo	lr
+	stw	lr, (sp, 64)
+	mfcr	lr, cr14
+	stw	lr, (sp, 68)
+#endif
+	subi	sp, 80
+.endm
+
+.macro	RESTORE_REGS_FTRACE
+	ldw	tls, (sp, 0)
+	ldw	a0, (sp, 16)
+	mtcr	a0, ss0
+
+#ifdef CONFIG_CPU_HAS_HILO
+	ldw	a0, (sp, 140)
+	mthi	a0
+	ldw	a0, (sp, 144)
+	mtlo	a0
+	ldw	a0, (sp, 148)
+	mtcr	a0, cr14
+#endif
+
+	ldw     a0, (sp, 24)
+	ldw     a1, (sp, 28)
+	ldw     a2, (sp, 32)
+	ldw     a3, (sp, 36)
+
+	addi	sp, 40
+	ldm	r4-r13, (sp)
+	addi    sp, 40
+	ldm     r16-r30, (sp)
+	addi    sp, 72
+	mfcr	sp, ss0
+.endm
+
 .macro SAVE_SWITCH_STACK
 	subi    sp, 64
 	stm	r4-r11, (sp)
@@ -230,11 +290,8 @@
 	addi	r6, 0x1ce
 	mtcr	r6, cr<30, 15> /* Set MSA0 */
 
-	lsri	r6, 28
-	addi	r6, 2
-	lsli	r6, 28
-	addi	r6, 0x1ce
-	mtcr	r6, cr<31, 15> /* Set MSA1 */
+	movi    r6, 0
+	mtcr	r6, cr<31, 15> /* Clr MSA1 */
 
 	/* enable MMU */
 	mfcr    r6, cr18

arch/csky/abiv2/inc/abi/fpu.h

@@ -9,7 +9,8 @@
 
 int fpu_libc_helper(struct pt_regs *regs);
 void fpu_fpe(struct pt_regs *regs);
-void __init init_fpu(void);
+
+static inline void init_fpu(void) { mtcr("cr<1, 2>", 0); }
 
 void save_to_user_fp(struct user_fp *user_fp);
 void restore_from_user_fp(struct user_fp *user_fp);

arch/csky/abiv2/mcount.S

@@ -3,6 +3,8 @@
 
 #include <linux/linkage.h>
 #include <asm/ftrace.h>
+#include <abi/entry.h>
+#include <asm/asm-offsets.h>
 
 /*
  * csky-gcc with -pg will put the following asm after prologue:
@@ -44,6 +46,22 @@
 	jmp	t1
 .endm
 
+.macro mcount_enter_regs
+	subi	sp, 8
+	stw	lr, (sp, 0)
+	stw	r8, (sp, 4)
+	SAVE_REGS_FTRACE
+.endm
+
+.macro mcount_exit_regs
+	RESTORE_REGS_FTRACE
+	ldw	t1, (sp, 0)
+	ldw	r8, (sp, 4)
+	ldw	lr, (sp, 8)
+	addi	sp, 12
+	jmp	t1
+.endm
+
 .macro save_return_regs
 	subi	sp, 16
 	stw	a0, (sp, 0)
@@ -122,6 +140,8 @@ ENTRY(ftrace_caller)
 	ldw	a0, (sp, 16)
 	subi	a0, 4
 	ldw	a1, (sp, 24)
+	lrw	a2, function_trace_op
+	ldw	a2, (a2, 0)
 
 	nop
 GLOBAL(ftrace_call)
@@ -157,3 +177,31 @@ ENTRY(return_to_handler)
 	jmp	lr
 END(return_to_handler)
 #endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+ENTRY(ftrace_regs_caller)
+	mcount_enter_regs
+
+	lrw	t1, PT_FRAME_SIZE
+	add	t1, sp
+
+	ldw	a0, (t1, 0)
+	subi	a0, 4
+	ldw	a1, (t1, 8)
+	lrw	a2, function_trace_op
+	ldw	a2, (a2, 0)
+	mov	a3, sp
+
+	nop
+GLOBAL(ftrace_regs_call)
+	nop32_stub
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	nop
+GLOBAL(ftrace_graph_regs_call)
+	nop32_stub
+#endif
+
+	mcount_exit_regs
+ENDPROC(ftrace_regs_caller)
+#endif /* CONFIG_DYNAMIC_FTRACE */

arch/csky/include/asm/ftrace.h

@@ -10,6 +10,8 @@
 
 #define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
 
+#define ARCH_SUPPORTS_FTRACE_OPS 1
+
 #define MCOUNT_ADDR	((unsigned long)_mcount)
 
 #ifndef __ASSEMBLY__

arch/csky/include/asm/kprobes.h

@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_CSKY_KPROBES_H
+#define __ASM_CSKY_KPROBES_H
+
+#include <asm-generic/kprobes.h>
+
+#ifdef CONFIG_KPROBES
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/percpu.h>
+
+#define __ARCH_WANT_KPROBES_INSN_SLOT
+#define MAX_INSN_SIZE			1
+
+#define flush_insn_slot(p)		do { } while (0)
+#define kretprobe_blacklist_size	0
+
+#include <asm/probes.h>
+
+struct prev_kprobe {
+	struct kprobe *kp;
+	unsigned int status;
+};
+
+/* Single step context for kprobe */
+struct kprobe_step_ctx {
+	unsigned long ss_pending;
+	unsigned long match_addr;
+};
+
+/* per-cpu kprobe control block */
+struct kprobe_ctlblk {
+	unsigned int kprobe_status;
+	unsigned long saved_sr;
+	struct prev_kprobe prev_kprobe;
+	struct kprobe_step_ctx ss_ctx;
+};
+
+void arch_remove_kprobe(struct kprobe *p);
+int kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr);
+int kprobe_breakpoint_handler(struct pt_regs *regs);
+int kprobe_single_step_handler(struct pt_regs *regs);
+void kretprobe_trampoline(void);
+void __kprobes *trampoline_probe_handler(struct pt_regs *regs);
+
+#endif /* CONFIG_KPROBES */
+#endif /* __ASM_CSKY_KPROBES_H */

arch/csky/include/asm/probes.h

@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_PROBES_H
+#define __ASM_CSKY_PROBES_H
+
+typedef u32 probe_opcode_t;
+typedef void (probes_handler_t) (u32 opcode, long addr, struct pt_regs *);
+
+/* architecture specific copy of original instruction */
+struct arch_probe_insn {
+	probe_opcode_t *insn;
+	probes_handler_t *handler;
+	/* restore address after simulation */
+	unsigned long restore;
+};
+
+#ifdef CONFIG_KPROBES
+typedef u32 kprobe_opcode_t;
+struct arch_specific_insn {
+	struct arch_probe_insn api;
+};
+#endif
+
+#endif /* __ASM_CSKY_PROBES_H */

arch/csky/include/asm/processor.h

@@ -43,6 +43,7 @@ extern struct cpuinfo_csky cpu_data[];
 struct thread_struct {
 	unsigned long  ksp;       /* kernel stack pointer */
 	unsigned long  sr;        /* saved status register */
+	unsigned long  trap_no;   /* saved status register */
 
 	/* FPU regs */
 	struct user_fp __aligned(16) user_fp;

arch/csky/include/asm/ptrace.h

@@ -7,11 +7,14 @@
 #include <uapi/asm/ptrace.h>
 #include <asm/traps.h>
 #include <linux/types.h>
+#include <linux/compiler.h>
 
 #ifndef __ASSEMBLY__
 
 #define PS_S	0x80000000 /* Supervisor Mode */
 
+#define USR_BKPT	0x1464
+
 #define arch_has_single_step() (1)
 #define current_pt_regs() \
 ({ (struct pt_regs *)((char *)current_thread_info() + THREAD_SIZE) - 1; })
@@ -22,6 +25,18 @@
 #define instruction_pointer(regs) ((regs)->pc)
 #define profile_pc(regs) instruction_pointer(regs)
 
+static inline void instruction_pointer_set(struct pt_regs *regs,
+					   unsigned long val)
+{
+	regs->pc = val;
+}
+
+#if defined(__CSKYABIV2__)
+#define MAX_REG_OFFSET offsetof(struct pt_regs, dcsr)
+#else
+#define MAX_REG_OFFSET offsetof(struct pt_regs, regs[9])
+#endif
+
 static inline bool in_syscall(struct pt_regs const *regs)
 {
 	return ((regs->sr >> 16) & 0xff) == VEC_TRAP0;
@@ -37,5 +52,33 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
 	return regs->a0;
 }
 
+/* Valid only for Kernel mode traps. */
+static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
+	return regs->usp;
+}
+
+extern int regs_query_register_offset(const char *name);
+extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
+						unsigned int n);
+
+/*
+ * regs_get_register() - get register value from its offset
+ * @regs:      pt_regs from which register value is gotten
+ * @offset:    offset of the register.
+ *
+ * regs_get_register returns the value of a register whose offset from @regs.
+ * The @offset is the offset of the register in struct pt_regs.
+ * If @offset is bigger than MAX_REG_OFFSET, this returns 0.
+ */
+static inline unsigned long regs_get_register(struct pt_regs *regs,
+						unsigned int offset)
+{
+	if (unlikely(offset > MAX_REG_OFFSET))
+		return 0;
+
+	return *(unsigned long *)((unsigned long)regs + offset);
+}
+
 #endif /* __ASSEMBLY__ */
 #endif /* __ASM_CSKY_PTRACE_H */