riscv: vector: allow kernel-mode Vector with preemption

AndybnACT · palmer-dabbelt · commit 2080ff949307 · 2024-01-16T07:14:02.000-08:00
Add kernel_vstate to keep track of kernel-mode Vector registers when trap introduced context switch happens. Also, provide riscv_v_flags to let context save/restore routine track context status. Context tracking happens whenever the core starts its in-kernel Vector executions. An active (dirty) kernel task's V contexts will be saved to memory whenever a trap-introduced context switch happens. Or, when a softirq, which happens to nest on top of it, uses Vector. Context retoring happens when the execution transfer back to the original Kernel context where it first enable preempt_v. Also, provide a config CONFIG_RISCV_ISA_V_PREEMPTIVE to give users an option to disable preemptible kernel-mode Vector at build time. Users with constraint memory may want to disable this config as preemptible kernel-mode Vector needs extra space for tracking of per thread's kernel-mode V context. Or, users might as well want to disable it if all kernel-mode Vector code is time sensitive and cannot tolerate context switch overhead. Signed-off-by: Andy Chiu <andy.chiu@sifive.com> Tested-by: Björn Töpel <bjorn@rivosinc.com> Tested-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com> Link: https://lore.kernel.org/r/20240115055929.4736-11-andy.chiu@sifive.com Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
@@ -533,6 +533,20 @@ config RISCV_ISA_V_UCOPY_THRESHOLD
 	  Prefer using vectorized copy_to_user()/copy_from_user() when the
 	  workload size exceeds this value.
 
+config RISCV_ISA_V_PREEMPTIVE
+	bool "Run kernel-mode Vector with kernel preemption"
+	depends on PREEMPTION
+	depends on RISCV_ISA_V
+	default y
+	help
+	  Usually, in-kernel SIMD routines are run with preemption disabled.
+	  Functions which envoke long running SIMD thus must yield core's
+	  vector unit to prevent blocking other tasks for too long.
+
+	  This config allows kernel to run SIMD without explicitly disable
+	  preemption. Enabling this config will result in higher memory
+	  consumption due to the allocation of per-task's kernel Vector context.
+
 config TOOLCHAIN_HAS_ZBB
 	bool
 	default y
diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h
@@ -30,6 +30,11 @@ void xor_regs_5_(unsigned long bytes, unsigned long *__restrict p1,
 		 const unsigned long *__restrict p4,
 		 const unsigned long *__restrict p5);
 
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+asmlinkage void riscv_v_context_nesting_start(struct pt_regs *regs);
+asmlinkage void riscv_v_context_nesting_end(struct pt_regs *regs);
+#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */
+
 #endif /* CONFIG_RISCV_ISA_V */
 
 #define DECLARE_DO_ERROR_INFO(name)	asmlinkage void name(struct pt_regs *regs)
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
@@ -80,8 +80,35 @@ struct pt_regs;
  *  - bit 0: indicates whether the in-kernel Vector context is active. The
  *    activation of this state disables the preemption. On a non-RT kernel, it
  *    also disable bh.
+ *  - bits 8: is used for tracking preemptible kernel-mode Vector, when
+ *    RISCV_ISA_V_PREEMPTIVE is enabled. Calling kernel_vector_begin() does not
+ *    disable the preemption if the thread's kernel_vstate.datap is allocated.
+ *    Instead, the kernel set this bit field. Then the trap entry/exit code
+ *    knows if we are entering/exiting the context that owns preempt_v.
+ *     - 0: the task is not using preempt_v
+ *     - 1: the task is actively using preempt_v. But whether does the task own
+ *          the preempt_v context is decided by bits in RISCV_V_CTX_DEPTH_MASK.
+ *  - bit 16-23 are RISCV_V_CTX_DEPTH_MASK, used by context tracking routine
+ *     when preempt_v starts:
+ *     - 0: the task is actively using, and own preempt_v context.
+ *     - non-zero: the task was using preempt_v, but then took a trap within.
+ *       Thus, the task does not own preempt_v. Any use of Vector will have to
+ *       save preempt_v, if dirty, and fallback to non-preemptible kernel-mode
+ *       Vector.
+ *  - bit 30: The in-kernel preempt_v context is saved, and requries to be
+ *    restored when returning to the context that owns the preempt_v.
+ *  - bit 31: The in-kernel preempt_v context is dirty, as signaled by the
+ *    trap entry code. Any context switches out-of current task need to save
+ *    it to the task's in-kernel V context. Also, any traps nesting on-top-of
+ *    preempt_v requesting to use V needs a save.
  */
-#define RISCV_KERNEL_MODE_V	0x1
+#define RISCV_V_CTX_DEPTH_MASK		0x00ff0000
+
+#define RISCV_V_CTX_UNIT_DEPTH		0x00010000
+#define RISCV_KERNEL_MODE_V		0x00000001
+#define RISCV_PREEMPT_V			0x00000100
+#define RISCV_PREEMPT_V_DIRTY		0x80000000
+#define RISCV_PREEMPT_V_NEED_RESTORE	0x40000000
 
 /* CPU-specific state of a task */
 struct thread_struct {
@@ -95,6 +122,7 @@ struct thread_struct {
 	u32 vstate_ctrl;
 	struct __riscv_v_ext_state vstate;
 	unsigned long align_ctl;
+	struct __riscv_v_ext_state kernel_vstate;
 };
 
 /* Whitelist the fstate from the task_struct for hardened usercopy */
diff --git a/arch/riscv/include/asm/simd.h b/arch/riscv/include/asm/simd.h
@@ -12,6 +12,7 @@
 #include <linux/percpu.h>
 #include <linux/preempt.h>
 #include <linux/types.h>
+#include <linux/thread_info.h>
 
 #include <asm/vector.h>
 
@@ -28,12 +29,27 @@ static __must_check inline bool may_use_simd(void)
 	/*
 	 * RISCV_KERNEL_MODE_V is only set while preemption is disabled,
 	 * and is clear whenever preemption is enabled.
-	 *
-	 * Kernel-mode Vector temporarily disables bh. So we must not return
-	 * true on irq_disabled(). Otherwise we would fail the lockdep check
-	 * calling local_bh_enable()
 	 */
-	return !in_hardirq() && !in_nmi() && !irqs_disabled() && !(riscv_v_flags() & RISCV_KERNEL_MODE_V);
+	if (in_hardirq() || in_nmi())
+		return false;
+
+	/*
+	 * Nesting is acheived 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,
+	 * fallback to check non preempt_v if nesting happens, or if the config
+	 * is not set.
+	 */
+	if (IS_ENABLED(CONFIG_RISCV_ISA_V_PREEMPTIVE) && current->thread.kernel_vstate.datap) {
+		if (!riscv_preempt_v_started(current))
+			return true;
+	}
+	/*
+	 * Non-preemptible kernel-mode Vector temporarily disables bh. So we
+	 * must not return true on irq_disabled(). Otherwise we would fail the
+	 * lockdep check calling local_bh_enable()
+	 */
+	return !irqs_disabled() && !(riscv_v_flags() & RISCV_KERNEL_MODE_V);
 }
 
 #else /* ! CONFIG_RISCV_ISA_V */
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
@@ -28,10 +28,11 @@ void get_cpu_vector_context(void);
 void put_cpu_vector_context(void);
 void riscv_v_thread_free(struct task_struct *tsk);
 void __init riscv_v_setup_ctx_cache(void);
+void riscv_v_thread_alloc(struct task_struct *tsk);
 
 static inline u32 riscv_v_flags(void)
 {
-	return current->thread.riscv_v_flags;
+	return READ_ONCE(current->thread.riscv_v_flags);
 }
 
 static __always_inline bool has_vector(void)
@@ -200,14 +201,62 @@ static inline void riscv_v_vstate_set_restore(struct task_struct *task,
 	}
 }
 
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+static inline bool riscv_preempt_v_dirty(struct task_struct *task)
+{
+	return !!(task->thread.riscv_v_flags & RISCV_PREEMPT_V_DIRTY);
+}
+
+static inline bool riscv_preempt_v_restore(struct task_struct *task)
+{
+	return !!(task->thread.riscv_v_flags & RISCV_PREEMPT_V_NEED_RESTORE);
+}
+
+static inline void riscv_preempt_v_clear_dirty(struct task_struct *task)
+{
+	barrier();
+	task->thread.riscv_v_flags &= ~RISCV_PREEMPT_V_DIRTY;
+}
+
+static inline void riscv_preempt_v_set_restore(struct task_struct *task)
+{
+	barrier();
+	task->thread.riscv_v_flags |= RISCV_PREEMPT_V_NEED_RESTORE;
+}
+
+static inline bool riscv_preempt_v_started(struct task_struct *task)
+{
+	return !!(task->thread.riscv_v_flags & RISCV_PREEMPT_V);
+}
+
+#else /* !CONFIG_RISCV_ISA_V_PREEMPTIVE */
+static inline bool riscv_preempt_v_dirty(struct task_struct *task) { return false; }
+static inline bool riscv_preempt_v_restore(struct task_struct *task) { return false; }
+static inline bool riscv_preempt_v_started(struct task_struct *task) { return false; }
+#define riscv_preempt_v_clear_dirty(tsk)	do {} while (0)
+#define riscv_preempt_v_set_restore(tsk)	do {} while (0)
+#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */
+
 static inline void __switch_to_vector(struct task_struct *prev,
 				      struct task_struct *next)
 {
 	struct pt_regs *regs;
 
-	regs = task_pt_regs(prev);
-	riscv_v_vstate_save(&prev->thread.vstate, regs);
-	riscv_v_vstate_set_restore(next, task_pt_regs(next));
+	if (riscv_preempt_v_started(prev)) {
+		if (riscv_preempt_v_dirty(prev)) {
+			__riscv_v_vstate_save(&prev->thread.kernel_vstate,
+					      prev->thread.kernel_vstate.datap);
+			riscv_preempt_v_clear_dirty(prev);
+		}
+	} else {
+		regs = task_pt_regs(prev);
+		riscv_v_vstate_save(&prev->thread.vstate, regs);
+	}
+
+	if (riscv_preempt_v_started(next))
+		riscv_preempt_v_set_restore(next);
+	else
+		riscv_v_vstate_set_restore(next, task_pt_regs(next));
 }
 
 void riscv_v_vstate_ctrl_init(struct task_struct *tsk);
@@ -231,6 +280,7 @@ static inline bool riscv_v_vstate_ctrl_user_allowed(void) { return false; }
 #define riscv_v_vstate_on(regs)			do {} while (0)
 #define riscv_v_thread_free(tsk)		do {} while (0)
 #define  riscv_v_setup_ctx_cache()		do {} while (0)
+#define riscv_v_thread_alloc(tsk)		do {} while (0)
 
 #endif /* CONFIG_RISCV_ISA_V */
 
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
@@ -83,6 +83,10 @@ SYM_CODE_START(handle_exception)
 	/* Load the kernel shadow call stack pointer if coming from userspace */
 	scs_load_current_if_task_changed s5
 
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	move a0, sp
+	call riscv_v_context_nesting_start
+#endif
 	move a0, sp /* pt_regs */
 	la ra, ret_from_exception
 
@@ -138,6 +142,10 @@ SYM_CODE_START_NOALIGN(ret_from_exception)
 	 */
 	csrw CSR_SCRATCH, tp
 1:
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	move a0, sp
+	call riscv_v_context_nesting_end
+#endif
 	REG_L a0, PT_STATUS(sp)
 	/*
 	 * The current load reservation is effectively part of the processor's
diff --git a/arch/riscv/kernel/kernel_mode_vector.c b/arch/riscv/kernel/kernel_mode_vector.c
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c
