riscv: Allocate user's vector context in the first-use trap

Vector unit is disabled by default for all user processes. Thus, a
process will take a trap (illegal instruction) into kernel at the first
time when it uses Vector. Only after then, the kernel allocates V
context and starts take care of the context for that user process.

Suggested-by: Richard Henderson <richard.henderson@linaro.org>
Link: https://lore.kernel.org/r/3923eeee-e4dc-0911-40bf-84c34aee962d@linaro.org
Signed-off-by: Andy Chiu <andy.chiu@sifive.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20230605110724.21391-12-andy.chiu@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

4 files changed, 150 insertions, 2 deletions

diff --git a/arch/riscv/include/asm/insn.h b/arch/riscv/include/asm/insn.h
index 8d5c84f2d5ef..4e1505cef8aa 100644
--- a/arch/riscv/include/asm/insn.h
+++ b/arch/riscv/include/asm/insn.h
@@ -137,6 +137,26 @@
 #define RVG_OPCODE_JALR		0x67
 #define RVG_OPCODE_JAL		0x6f
 #define RVG_OPCODE_SYSTEM	0x73
+#define RVG_SYSTEM_CSR_OFF	20
+#define RVG_SYSTEM_CSR_MASK	GENMASK(12, 0)
+
+/* parts of opcode for RVF, RVD and RVQ */
+#define RVFDQ_FL_FS_WIDTH_OFF	12
+#define RVFDQ_FL_FS_WIDTH_MASK	GENMASK(3, 0)
+#define RVFDQ_FL_FS_WIDTH_W	2
+#define RVFDQ_FL_FS_WIDTH_D	3
+#define RVFDQ_LS_FS_WIDTH_Q	4
+#define RVFDQ_OPCODE_FL		0x07
+#define RVFDQ_OPCODE_FS		0x27
+
+/* parts of opcode for RVV */
+#define RVV_OPCODE_VECTOR	0x57
+#define RVV_VL_VS_WIDTH_8	0
+#define RVV_VL_VS_WIDTH_16	5
+#define RVV_VL_VS_WIDTH_32	6
+#define RVV_VL_VS_WIDTH_64	7
+#define RVV_OPCODE_VL		RVFDQ_OPCODE_FL
+#define RVV_OPCODE_VS		RVFDQ_OPCODE_FS
 
 /* parts of opcode for RVC*/
 #define RVC_OPCODE_C0		0x0
@@ -304,6 +324,15 @@ static __always_inline bool riscv_insn_is_branch(u32 code)
 	(RVC_X(x_, RVC_B_IMM_7_6_OPOFF, RVC_B_IMM_7_6_MASK) << RVC_B_IMM_7_6_OFF) | \
 	(RVC_IMM_SIGN(x_) << RVC_B_IMM_SIGN_OFF); })
 
+#define RVG_EXTRACT_SYSTEM_CSR(x) \
+	({typeof(x) x_ = (x); RV_X(x_, RVG_SYSTEM_CSR_OFF, RVG_SYSTEM_CSR_MASK); })
+
+#define RVFDQ_EXTRACT_FL_FS_WIDTH(x) \
+	({typeof(x) x_ = (x); RV_X(x_, RVFDQ_FL_FS_WIDTH_OFF, \
+				   RVFDQ_FL_FS_WIDTH_MASK); })
+
+#define RVV_EXRACT_VL_VS_WIDTH(x) RVFDQ_EXTRACT_FL_FS_WIDTH(x)
+
 /*
  * Get the immediate from a J-type instruction.
  *
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index ce6a75e9cf62..8e56da67b5cf 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -21,6 +21,7 @@
 
 extern unsigned long riscv_v_vsize;
 int riscv_v_setup_vsize(void);
+bool riscv_v_first_use_handler(struct pt_regs *regs);
 
 static __always_inline bool has_vector(void)
 {
@@ -165,6 +166,7 @@ struct pt_regs;
 
 static inline int riscv_v_setup_vsize(void) { return -EOPNOTSUPP; }
 static __always_inline bool has_vector(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; }
 #define riscv_v_vsize (0)
 #define riscv_v_vstate_save(task, regs)		do {} while (0)
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 8c258b78c925..05ffdcd1424e 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -26,6 +26,7 @@
 #include <asm/ptrace.h>
 #include <asm/syscall.h>
 #include <asm/thread_info.h>
+#include <asm/vector.h>
 
 int show_unhandled_signals = 1;
 
@@ -145,8 +146,29 @@ DO_ERROR_INFO(do_trap_insn_misaligned,
 	SIGBUS, BUS_ADRALN, "instruction address misaligned");
 DO_ERROR_INFO(do_trap_insn_fault,
 	SIGSEGV, SEGV_ACCERR, "instruction access fault");
-DO_ERROR_INFO(do_trap_insn_illegal,
-	SIGILL, ILL_ILLOPC, "illegal instruction");
+
+asmlinkage __visible __trap_section void do_trap_insn_illegal(struct pt_regs *regs)
+{
+	if (user_mode(regs)) {
+		irqentry_enter_from_user_mode(regs);
+
+		local_irq_enable();
+
+		if (!riscv_v_first_use_handler(regs))
+			do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->epc,
+				      "Oops - illegal instruction");
+
+		irqentry_exit_to_user_mode(regs);
+	} else {
+		irqentry_state_t state = irqentry_nmi_enter(regs);
+
+		do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->epc,
+			      "Oops - illegal instruction");
+
+		irqentry_nmi_exit(regs, state);
+	}
+}
+
 DO_ERROR_INFO(do_trap_load_fault,
 	SIGSEGV, SEGV_ACCERR, "load access fault");
 #ifndef CONFIG_RISCV_M_MODE
diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c
index 120f1ce9abf9..9d81d1b2a7f3 100644
--- a/arch/riscv/kernel/vector.c
+++ b/arch/riscv/kernel/vector.c
@@ -4,10 +4,19 @@
  * Author: Andy Chiu <andy.chiu@sifive.com>
  */
 #include <linux/export.h>
+#include <linux/sched/signal.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/uaccess.h>
 
+#include <asm/thread_info.h>
+#include <asm/processor.h>
+#include <asm/insn.h>
 #include <asm/vector.h>
 #include <asm/csr.h>
 #include <asm/elf.h>
+#include <asm/ptrace.h>
 #include <asm/bug.h>
 
 unsigned long riscv_v_vsize __read_mostly;
@@ -34,3 +43,89 @@ int riscv_v_setup_vsize(void)
 
 	return 0;
 }
+
+static bool insn_is_vector(u32 insn_buf)
+{
+	u32 opcode = insn_buf & __INSN_OPCODE_MASK;
+	u32 width, csr;
+
+	/*
+	 * All V-related instructions, including CSR operations are 4-Byte. So,
+	 * do not handle if the instruction length is not 4-Byte.
+	 */
+	if (unlikely(GET_INSN_LENGTH(insn_buf) != 4))
+		return false;
+
+	switch (opcode) {
+	case RVV_OPCODE_VECTOR:
+		return true;
+	case RVV_OPCODE_VL:
+	case RVV_OPCODE_VS:
+		width = RVV_EXRACT_VL_VS_WIDTH(insn_buf);
+		if (width == RVV_VL_VS_WIDTH_8 || width == RVV_VL_VS_WIDTH_16 ||
+		    width == RVV_VL_VS_WIDTH_32 || width == RVV_VL_VS_WIDTH_64)
+			return true;
+
+		break;
+	case RVG_OPCODE_SYSTEM:
+		csr = RVG_EXTRACT_SYSTEM_CSR(insn_buf);
+		if ((csr >= CSR_VSTART && csr <= CSR_VCSR) ||
+		    (csr >= CSR_VL && csr <= CSR_VLENB))
+			return true;
+	}
+
+	return false;
+}
+
+static int riscv_v_thread_zalloc(void)
+{
+	void *datap;
+
+	datap = kzalloc(riscv_v_vsize, GFP_KERNEL);
+	if (!datap)
+		return -ENOMEM;
+
+	current->thread.vstate.datap = datap;
+	memset(&current->thread.vstate, 0, offsetof(struct __riscv_v_ext_state,
+						    datap));
+	return 0;
+}
+
+bool riscv_v_first_use_handler(struct pt_regs *regs)
+{
+	u32 __user *epc = (u32 __user *)regs->epc;
+	u32 insn = (u32)regs->badaddr;
+
+	/* Do not handle if V is not supported, or disabled */
+	if (!(ELF_HWCAP & COMPAT_HWCAP_ISA_V))
+		return false;
+
+	/* If V has been enabled then it is not the first-use trap */
+	if (riscv_v_vstate_query(regs))
+		return false;
+
+	/* Get the instruction */
+	if (!insn) {
+		if (__get_user(insn, epc))
+			return false;
+	}
+
+	/* Filter out non-V instructions */
+	if (!insn_is_vector(insn))
+		return false;
+
+	/* Sanity check. datap should be null by the time of the first-use trap */
+	WARN_ON(current->thread.vstate.datap);
+
+	/*
+	 * Now we sure that this is a V instruction. And it executes in the
+	 * context where VS has been off. So, try to allocate the user's V
+	 * context and resume execution.
+	 */
+	if (riscv_v_thread_zalloc()) {
+		force_sig(SIGBUS);
+		return true;
+	}
+	riscv_v_vstate_on(regs);
+	return true;
+}