[RFC PATCH v4 3/8] RISC-V: Add arch functions for non-retentive suspend entry/exit

[Anup Patel <anup.patel@wdc.com>]

The hart registers and CSRs are not preserved in non-retentative
suspend state so we provide arch specific helper functions which
will save/restore hart context upon entry/exit to non-retentive
suspend state. These helper functions can be used by cpuidle
drivers for non-retentive suspend entry/exit.

Signed-off-by: Anup Patel <anup.patel@wdc.com>
---
 arch/riscv/include/asm/asm.h      |  17 +++++
 arch/riscv/include/asm/suspend.h  |  35 +++++++++
 arch/riscv/kernel/Makefile        |   2 +
 arch/riscv/kernel/asm-offsets.c   |   3 +
 arch/riscv/kernel/head.S          |  11 ---
 arch/riscv/kernel/suspend.c       |  86 +++++++++++++++++++++
 arch/riscv/kernel/suspend_entry.S | 123 ++++++++++++++++++++++++++++++
 7 files changed, 266 insertions(+), 11 deletions(-)
 create mode 100644 arch/riscv/include/asm/suspend.h
 create mode 100644 arch/riscv/kernel/suspend.c
 create mode 100644 arch/riscv/kernel/suspend_entry.S

diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h
index 618d7c5af1a2..6c93f2806eb7 100644
--- a/arch/riscv/include/asm/asm.h
+++ b/arch/riscv/include/asm/asm.h
@@ -67,4 +67,21 @@
 #error "Unexpected __SIZEOF_SHORT__"
 #endif
 
+#ifdef __ASSEMBLY__
+
+/* Common assembly source macros */
+
+#ifdef CONFIG_XIP_KERNEL
+.macro XIP_FIXUP_OFFSET reg
+	REG_L t0, _xip_fixup
+	add \reg, \reg, t0
+.endm
+_xip_fixup: .dword CONFIG_PHYS_RAM_BASE - CONFIG_XIP_PHYS_ADDR - XIP_OFFSET
+#else
+.macro XIP_FIXUP_OFFSET reg
+.endm
+#endif /* CONFIG_XIP_KERNEL */
+
+#endif
+
 #endif /* _ASM_RISCV_ASM_H */
diff --git a/arch/riscv/include/asm/suspend.h b/arch/riscv/include/asm/suspend.h
new file mode 100644
index 000000000000..63e9f434fb89
--- /dev/null
+++ b/arch/riscv/include/asm/suspend.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ */
+
+#ifndef _ASM_RISCV_SUSPEND_H
+#define _ASM_RISCV_SUSPEND_H
+
+#include <asm/ptrace.h>
+
+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 tvec;
+	unsigned long ie;
+#ifdef CONFIG_MMU
+	unsigned long satp;
+#endif
+};
+
+/* Low-level CPU suspend entry function */
+int __cpu_suspend_enter(struct suspend_context *context);
+
+/* High-level CPU suspend which will save context and call finish() */
+int cpu_suspend(unsigned long arg,
+		int (*finish)(unsigned long arg,
+			      unsigned long entry,
+			      unsigned long context));
+
+/* Low-level CPU resume entry function */
+int __cpu_resume_enter(unsigned long hartid, unsigned long context);
+
+#endif
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index d3081e4d9600..5a2fc649ad11 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -47,6 +47,8 @@ obj-$(CONFIG_SMP)		+= cpu_ops_spinwait.o
 obj-$(CONFIG_MODULES)		+= module.o
 obj-$(CONFIG_MODULE_SECTIONS)	+= module-sections.o
 
+obj-$(CONFIG_CPU_PM)		+= suspend_entry.o suspend.o
+
 obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o ftrace.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= mcount-dyn.o
 
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
index 9ef33346853c..2628dfd0f77d 100644
--- a/arch/riscv/kernel/asm-offsets.c
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -10,6 +10,7 @@
 #include <linux/sched.h>
 #include <asm/thread_info.h>
 #include <asm/ptrace.h>
+#include <asm/suspend.h>
 
 void asm_offsets(void);
 
@@ -111,6 +112,8 @@ void asm_offsets(void)
 	OFFSET(PT_BADADDR, pt_regs, badaddr);
 	OFFSET(PT_CAUSE, pt_regs, cause);
 
+	OFFSET(SUSPEND_CONTEXT_REGS, suspend_context, regs);
+
 	/*
 	 * THREAD_{F,X}* might be larger than a S-type offset can handle, but
 	 * these are used in performance-sensitive assembly so we can't resort
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index a44c0bc9c2f3..03bf2edfe9b2 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -15,17 +15,6 @@
 #include <asm/image.h>
 #include "efi-header.S"
 
-#ifdef CONFIG_XIP_KERNEL
-.macro XIP_FIXUP_OFFSET reg
-	REG_L t0, _xip_fixup
-	add \reg, \reg, t0
-.endm
-_xip_fixup: .dword CONFIG_PHYS_RAM_BASE - CONFIG_XIP_PHYS_ADDR - XIP_OFFSET
-#else
-.macro XIP_FIXUP_OFFSET reg
-.endm
-#endif /* CONFIG_XIP_KERNEL */
-
 __HEAD
 ENTRY(_start)
 	/*
diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c
new file mode 100644
index 000000000000..49dddec30e99
--- /dev/null
+++ b/arch/riscv/kernel/suspend.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/ftrace.h>
+#include <asm/csr.h>
+#include <asm/suspend.h>
+
+static void suspend_save_csrs(struct suspend_context *context)
+{
+	context->scratch = csr_read(CSR_SCRATCH);
+	context->tvec = csr_read(CSR_TVEC);
+	context->ie = csr_read(CSR_IE);
+
+	/*
+	 * No need to save/restore IP CSR (i.e. MIP or SIP) because:
+	 *
+	 * 1. For no-MMU (M-mode) kernel, the bits in MIP are set by
+	 *    external devices (such as interrupt controller, timer, etc).
+	 * 2. For MMU (S-mode) kernel, the bits in SIP are set by
+	 *    M-mode firmware and external devices (such as interrupt
+	 *    controller, etc).
+	 */
+
+#ifdef CONFIG_MMU
+	context->satp = csr_read(CSR_SATP);
+#endif
+}
+
+static void suspend_restore_csrs(struct suspend_context *context)
+{
+	csr_write(CSR_SCRATCH, context->scratch);
+	csr_write(CSR_TVEC, context->tvec);
+	csr_write(CSR_IE, context->ie);
+
+#ifdef CONFIG_MMU
+	csr_write(CSR_SATP, context->satp);
+#endif
+}
+
+int cpu_suspend(unsigned long arg,
+		int (*finish)(unsigned long arg,
+			      unsigned long entry,
+			      unsigned long context))
+{
+	int rc = 0;
+	struct suspend_context context = { 0 };
+
+	/* Finisher should be non-NULL */
+	if (!finish)
+		return -EINVAL;
+
+	/* Save additional CSRs*/
+	suspend_save_csrs(&context);
+
+	/*
+	 * Function graph tracer state gets incosistent when the kernel
+	 * calls functions that never return (aka finishers) hence disable
+	 * graph tracing during their execution.
+	 */
+	pause_graph_tracing();
+
+	/* Save context on stack */
+	if (__cpu_suspend_enter(&context)) {
+		/* Call the finisher */
+		rc = finish(arg, __pa_symbol(__cpu_resume_enter),
+			    (ulong)&context);
+
+		/*
+		 * Should never reach here, unless the suspend finisher
+		 * fails. Successful cpu_suspend() should return from
+		 * __cpu_resume_entry()
+		 */
+		if (!rc)
+			rc = -EOPNOTSUPP;
+	}
+
+	/* Enable function graph tracer */
+	unpause_graph_tracing();
+
+	/* Restore additional CSRs */
+	suspend_restore_csrs(&context);
+
+	return rc;
+}
diff --git a/arch/riscv/kernel/suspend_entry.S b/arch/riscv/kernel/suspend_entry.S
new file mode 100644
index 000000000000..b8d20decfc28
--- /dev/null
+++ b/arch/riscv/kernel/suspend_entry.S
@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/csr.h>
+
+	.text
+	.altmacro
+	.option norelax
+
+ENTRY(__cpu_suspend_enter)
+	/* Save registers (except A0 and T0-T6) */
+	REG_S	ra, (SUSPEND_CONTEXT_REGS + PT_RA)(a0)
+	REG_S	sp, (SUSPEND_CONTEXT_REGS + PT_SP)(a0)
+	REG_S	gp, (SUSPEND_CONTEXT_REGS + PT_GP)(a0)
+	REG_S	tp, (SUSPEND_CONTEXT_REGS + PT_TP)(a0)
+	REG_S	s0, (SUSPEND_CONTEXT_REGS + PT_S0)(a0)
+	REG_S	s1, (SUSPEND_CONTEXT_REGS + PT_S1)(a0)
+	REG_S	a1, (SUSPEND_CONTEXT_REGS + PT_A1)(a0)
+	REG_S	a2, (SUSPEND_CONTEXT_REGS + PT_A2)(a0)
+	REG_S	a3, (SUSPEND_CONTEXT_REGS + PT_A3)(a0)
+	REG_S	a4, (SUSPEND_CONTEXT_REGS + PT_A4)(a0)
+	REG_S	a5, (SUSPEND_CONTEXT_REGS + PT_A5)(a0)
+	REG_S	a6, (SUSPEND_CONTEXT_REGS + PT_A6)(a0)
+	REG_S	a7, (SUSPEND_CONTEXT_REGS + PT_A7)(a0)
+	REG_S	s2, (SUSPEND_CONTEXT_REGS + PT_S2)(a0)
+	REG_S	s3, (SUSPEND_CONTEXT_REGS + PT_S3)(a0)
+	REG_S	s4, (SUSPEND_CONTEXT_REGS + PT_S4)(a0)
+	REG_S	s5, (SUSPEND_CONTEXT_REGS + PT_S5)(a0)
+	REG_S	s6, (SUSPEND_CONTEXT_REGS + PT_S6)(a0)
+	REG_S	s7, (SUSPEND_CONTEXT_REGS + PT_S7)(a0)
+	REG_S	s8, (SUSPEND_CONTEXT_REGS + PT_S8)(a0)
+	REG_S	s9, (SUSPEND_CONTEXT_REGS + PT_S9)(a0)
+	REG_S	s10, (SUSPEND_CONTEXT_REGS + PT_S10)(a0)
+	REG_S	s11, (SUSPEND_CONTEXT_REGS + PT_S11)(a0)
+
+	/* Save CSRs */
+	csrr	t0, CSR_EPC
+	REG_S	t0, (SUSPEND_CONTEXT_REGS + PT_EPC)(a0)
+	csrr	t0, CSR_STATUS
+	REG_S	t0, (SUSPEND_CONTEXT_REGS + PT_STATUS)(a0)
+	csrr	t0, CSR_TVAL
+	REG_S	t0, (SUSPEND_CONTEXT_REGS + PT_BADADDR)(a0)
+	csrr	t0, CSR_CAUSE
+	REG_S	t0, (SUSPEND_CONTEXT_REGS + PT_CAUSE)(a0)
+
+	/* Return non-zero value */
+	li	a0, 1
+
+	/* Return to C code */
+	ret
+END(__cpu_suspend_enter)
+
+ENTRY(__cpu_resume_enter)
+	/* Load the global pointer */
+	.option push
+	.option norelax
+		la gp, __global_pointer$
+	.option pop
+
+#ifdef CONFIG_MMU
+	/* Save A0 and A1 */
+	add	t0, a0, zero
+	add	t1, a1, zero
+
+	/* Enable MMU */
+	la	a0, swapper_pg_dir
+	XIP_FIXUP_OFFSET a0
+	call	relocate_enable_mmu
+
+	/* Restore A0 and A1 */
+	add	a0, t0, zero
+	add	a1, t1, zero
+#endif
+
+	/* Make A0 point to suspend context */
+	add	a0, a1, zero
+
+	/* Restore CSRs */
+	REG_L	t0, (SUSPEND_CONTEXT_REGS + PT_EPC)(a0)
+	csrw	CSR_EPC, t0
+	REG_L	t0, (SUSPEND_CONTEXT_REGS + PT_STATUS)(a0)
+	csrw	CSR_STATUS, t0
+	REG_L	t0, (SUSPEND_CONTEXT_REGS + PT_BADADDR)(a0)
+	csrw	CSR_TVAL, t0
+	REG_L	t0, (SUSPEND_CONTEXT_REGS + PT_CAUSE)(a0)
+	csrw	CSR_CAUSE, t0
+
+	/* Restore registers (except A0 and T0-T6) */
+	REG_L	ra, (SUSPEND_CONTEXT_REGS + PT_RA)(a0)
+	REG_L	sp, (SUSPEND_CONTEXT_REGS + PT_SP)(a0)
+	REG_L	gp, (SUSPEND_CONTEXT_REGS + PT_GP)(a0)
+	REG_L	tp, (SUSPEND_CONTEXT_REGS + PT_TP)(a0)
+	REG_L	s0, (SUSPEND_CONTEXT_REGS + PT_S0)(a0)
+	REG_L	s1, (SUSPEND_CONTEXT_REGS + PT_S1)(a0)
+	REG_L	a1, (SUSPEND_CONTEXT_REGS + PT_A1)(a0)
+	REG_L	a2, (SUSPEND_CONTEXT_REGS + PT_A2)(a0)
+	REG_L	a3, (SUSPEND_CONTEXT_REGS + PT_A3)(a0)
+	REG_L	a4, (SUSPEND_CONTEXT_REGS + PT_A4)(a0)
+	REG_L	a5, (SUSPEND_CONTEXT_REGS + PT_A5)(a0)
+	REG_L	a6, (SUSPEND_CONTEXT_REGS + PT_A6)(a0)
+	REG_L	a7, (SUSPEND_CONTEXT_REGS + PT_A7)(a0)
+	REG_L	s2, (SUSPEND_CONTEXT_REGS + PT_S2)(a0)
+	REG_L	s3, (SUSPEND_CONTEXT_REGS + PT_S3)(a0)
+	REG_L	s4, (SUSPEND_CONTEXT_REGS + PT_S4)(a0)
+	REG_L	s5, (SUSPEND_CONTEXT_REGS + PT_S5)(a0)
+	REG_L	s6, (SUSPEND_CONTEXT_REGS + PT_S6)(a0)
+	REG_L	s7, (SUSPEND_CONTEXT_REGS + PT_S7)(a0)
+	REG_L	s8, (SUSPEND_CONTEXT_REGS + PT_S8)(a0)
+	REG_L	s9, (SUSPEND_CONTEXT_REGS + PT_S9)(a0)
+	REG_L	s10, (SUSPEND_CONTEXT_REGS + PT_S10)(a0)
+	REG_L	s11, (SUSPEND_CONTEXT_REGS + PT_S11)(a0)
+
+	/* Return zero value */
+	add	a0, zero, zero
+
+	/* Return to C code */
+	ret
+END(__cpu_resume_enter)
-- 
2.25.1