Merge patch series "riscv: Create and document PR_RISCV_SET_ICACHE_FLUSH_CTX prctl"

Charlie Jenkins <charlie@rivosinc.com> says:

Improve the performance of icache flushing by creating a new prctl flag
PR_RISCV_SET_ICACHE_FLUSH_CTX. The interface is left generic to allow
for future expansions such as with the proposed J extension [1].

Documentation is also provided to explain the use case.

Patch sent to add PR_RISCV_SET_ICACHE_FLUSH_CTX to man-pages [2].

[1] https://github.com/riscv/riscv-j-extension
[2] https://lore.kernel.org/linux-man/20240124-fencei_prctl-v1-1-0bddafcef331@rivosinc.com

* b4-shazam-merge:
  cpumask: Add assign cpu
  documentation: Document PR_RISCV_SET_ICACHE_FLUSH_CTX prctl
  riscv: Include riscv_set_icache_flush_ctx prctl
  riscv: Remove unnecessary irqflags processor.h include

Link: https://lore.kernel.org/r/20240312-fencei-v13-0-4b6bdc2bbf32@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

Documentation/arch/riscv/cmodx.rst

@@ -0,0 +1,98 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============================================================================
+Concurrent Modification and Execution of Instructions (CMODX) for RISC-V Linux
+==============================================================================
+
+CMODX is a programming technique where a program executes instructions that were
+modified by the program itself. Instruction storage and the instruction cache
+(icache) are not guaranteed to be synchronized on RISC-V hardware. Therefore, the
+program must enforce its own synchronization with the unprivileged fence.i
+instruction.
+
+However, the default Linux ABI prohibits the use of fence.i in userspace
+applications. At any point the scheduler may migrate a task onto a new hart. If
+migration occurs after the userspace synchronized the icache and instruction
+storage with fence.i, the icache on the new hart will no longer be clean. This
+is due to the behavior of fence.i only affecting the hart that it is called on.
+Thus, the hart that the task has been migrated to may not have synchronized
+instruction storage and icache.
+
+There are two ways to solve this problem: use the riscv_flush_icache() syscall,
+or use the ``PR_RISCV_SET_ICACHE_FLUSH_CTX`` prctl() and emit fence.i in
+userspace. The syscall performs a one-off icache flushing operation. The prctl
+changes the Linux ABI to allow userspace to emit icache flushing operations.
+
+As an aside, "deferred" icache flushes can sometimes be triggered in the kernel.
+At the time of writing, this only occurs during the riscv_flush_icache() syscall
+and when the kernel uses copy_to_user_page(). These deferred flushes happen only
+when the memory map being used by a hart changes. If the prctl() context caused
+an icache flush, this deferred icache flush will be skipped as it is redundant.
+Therefore, there will be no additional flush when using the riscv_flush_icache()
+syscall inside of the prctl() context.
+
+prctl() Interface
+---------------------
+
+Call prctl() with ``PR_RISCV_SET_ICACHE_FLUSH_CTX`` as the first argument. The
+remaining arguments will be delegated to the riscv_set_icache_flush_ctx
+function detailed below.
+
+.. kernel-doc:: arch/riscv/mm/cacheflush.c
+	:identifiers: riscv_set_icache_flush_ctx
+
+Example usage:
+
+The following files are meant to be compiled and linked with each other. The
+modify_instruction() function replaces an add with 0 with an add with one,
+causing the instruction sequence in get_value() to change from returning a zero
+to returning a one.
+
+cmodx.c::
+
+	#include <stdio.h>
+	#include <sys/prctl.h>
+
+	extern int get_value();
+	extern void modify_instruction();
+
+	int main()
+	{
+		int value = get_value();
+		printf("Value before cmodx: %d\n", value);
+
+		// Call prctl before first fence.i is called inside modify_instruction
+		prctl(PR_RISCV_SET_ICACHE_FLUSH_CTX_ON, PR_RISCV_CTX_SW_FENCEI, PR_RISCV_SCOPE_PER_PROCESS);
+		modify_instruction();
+		// Call prctl after final fence.i is called in process
+		prctl(PR_RISCV_SET_ICACHE_FLUSH_CTX_OFF, PR_RISCV_CTX_SW_FENCEI, PR_RISCV_SCOPE_PER_PROCESS);
+
+		value = get_value();
+		printf("Value after cmodx: %d\n", value);
+		return 0;
+	}
+
+cmodx.S::
+
+	.option norvc
+
+	.text
+	.global modify_instruction
+	modify_instruction:
+	lw a0, new_insn
+	lui a5,%hi(old_insn)
+	sw  a0,%lo(old_insn)(a5)
+	fence.i
+	ret
+
+	.section modifiable, "awx"
+	.global get_value
+	get_value:
+	li a0, 0
+	old_insn:
+	addi a0, a0, 0
+	ret
+
+	.data
+	new_insn:
+	addi a0, a0, 1

Documentation/arch/riscv/index.rst

@@ -13,6 +13,7 @@ RISC-V architecture
     patch-acceptance
     uabi
     vector
+    cmodx
 
     features
 

arch/riscv/include/asm/irqflags.h

@@ -7,7 +7,6 @@
 #ifndef _ASM_RISCV_IRQFLAGS_H
 #define _ASM_RISCV_IRQFLAGS_H
 
-#include <asm/processor.h>
 #include <asm/csr.h>
 
 /* read interrupt enabled status */

arch/riscv/include/asm/mmu.h

@@ -19,6 +19,8 @@ typedef struct {
 #ifdef CONFIG_SMP
 	/* A local icache flush is needed before user execution can resume. */
 	cpumask_t icache_stale_mask;
+	/* Force local icache flush on all migrations. */
+	bool force_icache_flush;
 #endif
 #ifdef CONFIG_BINFMT_ELF_FDPIC
 	unsigned long exec_fdpic_loadmap;

arch/riscv/include/asm/processor.h

@@ -68,6 +68,7 @@
 #endif
 
 #ifndef __ASSEMBLY__
+#include <linux/cpumask.h>
 
 struct task_struct;
 struct pt_regs;
@@ -122,6 +123,12 @@ struct thread_struct {
 	struct __riscv_v_ext_state vstate;
 	unsigned long align_ctl;
 	struct __riscv_v_ext_state kernel_vstate;
+#ifdef CONFIG_SMP
+	/* Flush the icache on migration */
+	bool force_icache_flush;
+	/* A forced icache flush is not needed if migrating to the previous cpu. */
+	unsigned int prev_cpu;
+#endif
 };
 
 /* Whitelist the fstate from the task_struct for hardened usercopy */
@@ -183,6 +190,9 @@ extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val);
 #define GET_UNALIGN_CTL(tsk, addr)	get_unalign_ctl((tsk), (addr))
 #define SET_UNALIGN_CTL(tsk, val)	set_unalign_ctl((tsk), (val))
 
+#define RISCV_SET_ICACHE_FLUSH_CTX(arg1, arg2)	riscv_set_icache_flush_ctx(arg1, arg2)
+extern int riscv_set_icache_flush_ctx(unsigned long ctx, unsigned long per_thread);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_RISCV_PROCESSOR_H */

arch/riscv/include/asm/switch_to.h

@@ -8,6 +8,7 @@
 
 #include <linux/jump_label.h>
 #include <linux/sched/task_stack.h>
+#include <linux/mm_types.h>
 #include <asm/vector.h>
 #include <asm/cpufeature.h>
 #include <asm/processor.h>
@@ -72,14 +73,36 @@ static __always_inline bool has_fpu(void) { return false; }
 extern struct task_struct *__switch_to(struct task_struct *,
 				       struct task_struct *);
 
+static inline bool switch_to_should_flush_icache(struct task_struct *task)
+{
+#ifdef CONFIG_SMP
+	bool stale_mm = task->mm && task->mm->context.force_icache_flush;
+	bool stale_thread = task->thread.force_icache_flush;
+	bool thread_migrated = smp_processor_id() != task->thread.prev_cpu;
+
+	return thread_migrated && (stale_mm || stale_thread);
+#else
+	return false;
+#endif
+}
+
+#ifdef CONFIG_SMP
+#define __set_prev_cpu(thread) ((thread).prev_cpu = smp_processor_id())
+#else
+#define __set_prev_cpu(thread)
+#endif
+
 #define switch_to(prev, next, last)			\
 do {							\
 	struct task_struct *__prev = (prev);		\
 	struct task_struct *__next = (next);		\
+	__set_prev_cpu(__prev->thread);			\
 	if (has_fpu())					\
 		__switch_to_fpu(__prev, __next);	\
 	if (has_vector())					\
 		__switch_to_vector(__prev, __next);	\
+	if (switch_to_should_flush_icache(__next))	\
+		local_flush_icache_all();		\
 	((last) = __switch_to(__prev, __next));		\
 } while (0)
 

arch/riscv/mm/cacheflush.c

@@ -5,6 +5,7 @@
 
 #include <linux/acpi.h>
 #include <linux/of.h>
+#include <linux/prctl.h>
 #include <asm/acpi.h>
 #include <asm/cacheflush.h>
 
@@ -152,3 +153,115 @@ void __init riscv_init_cbo_blocksizes(void)
 	if (cboz_block_size)
 		riscv_cboz_block_size = cboz_block_size;
 }
+
+#ifdef CONFIG_SMP
+static void set_icache_stale_mask(void)
+{
+	cpumask_t *mask;
+	bool stale_cpu;
+
+	/*
+	 * Mark every other hart's icache as needing a flush for
+	 * this MM. Maintain the previous value of the current
+	 * cpu to handle the case when this function is called
+	 * concurrently on different harts.
+	 */
+	mask = &current->mm->context.icache_stale_mask;
+	stale_cpu = cpumask_test_cpu(smp_processor_id(), mask);
+
+	cpumask_setall(mask);
+	cpumask_assign_cpu(smp_processor_id(), mask, stale_cpu);
+}
+#endif
+
+/**
+ * riscv_set_icache_flush_ctx() - Enable/disable icache flushing instructions in
+ * userspace.
+ * @ctx: Set the type of icache flushing instructions permitted/prohibited in
+ *	 userspace. Supported values described below.
+ *
+ * Supported values for ctx:
+ *
+ * * %PR_RISCV_CTX_SW_FENCEI_ON: Allow fence.i in user space.
+ *
+ * * %PR_RISCV_CTX_SW_FENCEI_OFF: Disallow fence.i in user space. All threads in
+ *   a process will be affected when ``scope == PR_RISCV_SCOPE_PER_PROCESS``.
+ *   Therefore, caution must be taken; use this flag only when you can guarantee
+ *   that no thread in the process will emit fence.i from this point onward.
+ *
+ * @scope: Set scope of where icache flushing instructions are allowed to be
+ *	   emitted. Supported values described below.
+ *
+ * Supported values for scope:
+ *
+ * * %PR_RISCV_SCOPE_PER_PROCESS: Ensure the icache of any thread in this process
+ *                               is coherent with instruction storage upon
+ *                               migration.
+ *
+ * * %PR_RISCV_SCOPE_PER_THREAD: Ensure the icache of the current thread is
+ *                              coherent with instruction storage upon
+ *                              migration.
+ *
+ * When ``scope == PR_RISCV_SCOPE_PER_PROCESS``, all threads in the process are
+ * permitted to emit icache flushing instructions. Whenever any thread in the
+ * process is migrated, the corresponding hart's icache will be guaranteed to be
+ * consistent with instruction storage. This does not enforce any guarantees
+ * outside of migration. If a thread modifies an instruction that another thread
+ * may attempt to execute, the other thread must still emit an icache flushing
+ * instruction before attempting to execute the potentially modified
+ * instruction. This must be performed by the user-space program.
+ *
+ * In per-thread context (eg. ``scope == PR_RISCV_SCOPE_PER_THREAD``) only the
+ * thread calling this function is permitted to emit icache flushing
+ * instructions. When the thread is migrated, the corresponding hart's icache
+ * will be guaranteed to be consistent with instruction storage.
+ *
+ * On kernels configured without SMP, this function is a nop as migrations
+ * across harts will not occur.
+ */
+int riscv_set_icache_flush_ctx(unsigned long ctx, unsigned long scope)
+{
+#ifdef CONFIG_SMP
+	switch (ctx) {
+	case PR_RISCV_CTX_SW_FENCEI_ON:
+		switch (scope) {
+		case PR_RISCV_SCOPE_PER_PROCESS:
+			current->mm->context.force_icache_flush = true;
+			break;
+		case PR_RISCV_SCOPE_PER_THREAD:
+			current->thread.force_icache_flush = true;
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	case PR_RISCV_CTX_SW_FENCEI_OFF:
+		switch (scope) {
+		case PR_RISCV_SCOPE_PER_PROCESS:
+			current->mm->context.force_icache_flush = false;
+
+			set_icache_stale_mask();
+			break;
+		case PR_RISCV_SCOPE_PER_THREAD:
+			current->thread.force_icache_flush = false;
+
+			set_icache_stale_mask();
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+#else
+	switch (ctx) {
+	case PR_RISCV_CTX_SW_FENCEI_ON:
+	case PR_RISCV_CTX_SW_FENCEI_OFF:
+		return 0;
+	default:
+		return -EINVAL;
+	}
+#endif
+}

arch/riscv/mm/context.c

@@ -15,6 +15,7 @@
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
 #include <asm/mmu_context.h>
+#include <asm/switch_to.h>
 
 #ifdef CONFIG_MMU
 
@@ -297,21 +298,23 @@ static inline void set_mm(struct mm_struct *prev,
  *
  * The "cpu" argument must be the current local CPU number.
  */
-static inline void flush_icache_deferred(struct mm_struct *mm, unsigned int cpu)
+static inline void flush_icache_deferred(struct mm_struct *mm, unsigned int cpu,
+					 struct task_struct *task)
 {
 #ifdef CONFIG_SMP
-	cpumask_t *mask = &mm->context.icache_stale_mask;
+	if (cpumask_test_and_clear_cpu(cpu, &mm->context.icache_stale_mask)) {
-
-	if (cpumask_test_cpu(cpu, mask)) {
-		cpumask_clear_cpu(cpu, mask);
 		/*
 		 * Ensure the remote hart's writes are visible to this hart.
 		 * This pairs with a barrier in flush_icache_mm.
 		 */
 		smp_mb();
-		local_flush_icache_all();
-	}
 
+		/*
+		 * If cache will be flushed in switch_to, no need to flush here.
+		 */
+		if (!(task && switch_to_should_flush_icache(task)))
+			local_flush_icache_all();
+	}
 #endif
 }
 
@@ -334,5 +337,5 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 
 	set_mm(prev, next, cpu);
 
-	flush_icache_deferred(next, cpu);
+	flush_icache_deferred(next, cpu, task);
 }

include/linux/cpumask.h

@@ -493,6 +493,22 @@ static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp)
 	__clear_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
 
+/**
+ * cpumask_assign_cpu - assign a cpu in a cpumask
+ * @cpu: cpu number (< nr_cpu_ids)
+ * @dstp: the cpumask pointer
+ * @bool: the value to assign
+ */
+static __always_inline void cpumask_assign_cpu(int cpu, struct cpumask *dstp, bool value)
+{
+	assign_bit(cpumask_check(cpu), cpumask_bits(dstp), value);
+}
+
+static __always_inline void __cpumask_assign_cpu(int cpu, struct cpumask *dstp, bool value)
+{
+	__assign_bit(cpumask_check(cpu), cpumask_bits(dstp), value);
+}
+
 /**
  * cpumask_test_cpu - test for a cpu in a cpumask
  * @cpu: cpu number (< nr_cpu_ids)

include/uapi/linux/prctl.h

@@ -306,4 +306,10 @@ struct prctl_mm_map {
 # define PR_RISCV_V_VSTATE_CTRL_NEXT_MASK	0xc
 # define PR_RISCV_V_VSTATE_CTRL_MASK		0x1f
 
+#define PR_RISCV_SET_ICACHE_FLUSH_CTX	71
+# define PR_RISCV_CTX_SW_FENCEI_ON	0
+# define PR_RISCV_CTX_SW_FENCEI_OFF	1
+# define PR_RISCV_SCOPE_PER_PROCESS	0
+# define PR_RISCV_SCOPE_PER_THREAD	1
+
 #endif /* _LINUX_PRCTL_H */

kernel/sys.c

@@ -146,6 +146,9 @@
 #ifndef RISCV_V_GET_CONTROL
 # define RISCV_V_GET_CONTROL()		(-EINVAL)
 #endif
+#ifndef RISCV_SET_ICACHE_FLUSH_CTX
+# define RISCV_SET_ICACHE_FLUSH_CTX(a, b)	(-EINVAL)
+#endif
 
 /*
  * this is where the system-wide overflow UID and GID are defined, for
@@ -2757,6 +2760,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_RISCV_V_GET_CONTROL:
 		error = RISCV_V_GET_CONTROL();
 		break;
+	case PR_RISCV_SET_ICACHE_FLUSH_CTX:
+		error = RISCV_SET_ICACHE_FLUSH_CTX(arg2, arg3);
+		break;
 	default:
 		error = -EINVAL;
 		break;