[PATCH v8 0/2] riscv: Create and document PR_RISCV_SET_ICACHE_FLUSH_CTX prctl

[PATCH v8 0/2] riscv: Create and document PR_RISCV_SET_ICACHE_FLUSH_CTX prctl

[Charlie Jenkins]

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.

[1] https://github.com/riscv/riscv-j-extension

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
---
Changes in v8:
- Only flush icache if migrated to different cpu (Alex)
- Move flushing to switch_to to catch per-thread flushing properly
- Link to v7: https://lore.kernel.org/r/20240112-fencei-v7-0-78f0614e1db0@rivosinc.com

Changes in v7:
- Change "per_thread" parameter to "scope" and provide constants for the
  parameter.
- Link to v6: https://lore.kernel.org/r/20240109-fencei-v6-0-04116e51445c@rivosinc.com

Changes in v6:
- Fixup documentation formatting
- Link to v5: https://lore.kernel.org/r/20240108-fencei-v5-0-aa1e51d7222f@rivosinc.com

Changes in v5:
- Minor documentation changes (Randy)
- Link to v4: https://lore.kernel.org/r/20240107-fencei-v4-0-d4cf2fb905d3@rivosinc.com

Changes in v4:
- Add OFF flag to disallow fence.i in userspace (Atish)
- Fix documentation issues (Atish)
- Link to v3: https://lore.kernel.org/r/20231213-fencei-v3-0-b75158238eb7@rivosinc.com

Changes in v3:
- Check if value force_icache_flush set on thread, rather than in mm
  twice (Clément)
- Link to v2: https://lore.kernel.org/r/20231130-fencei-v2-0-2cb623ab1b1f@rivosinc.com

Changes in v2:
- Fix kernel-doc comment (Conor)
- Link to v1: https://lore.kernel.org/r/20231122-fencei-v1-0-bec0811cb212@rivosinc.com

---
Charlie Jenkins (2):
      riscv: Include riscv_set_icache_flush_ctx prctl
      documentation: Document PR_RISCV_SET_ICACHE_FLUSH_CTX prctl

 Documentation/arch/riscv/cmodx.rst   | 96 ++++++++++++++++++++++++++++++++++++
 Documentation/arch/riscv/index.rst   |  1 +
 arch/riscv/include/asm/mmu.h         |  4 ++
 arch/riscv/include/asm/mmu_context.h |  3 ++
 arch/riscv/include/asm/processor.h   |  7 +++
 arch/riscv/include/asm/switch_to.h   | 17 +++++++
 arch/riscv/mm/cacheflush.c           | 67 +++++++++++++++++++++++++
 arch/riscv/mm/context.c              | 14 ++++--
 include/uapi/linux/prctl.h           |  6 +++
 kernel/sys.c                         |  6 +++
 10 files changed, 218 insertions(+), 3 deletions(-)
---
base-commit: b85ea95d086471afb4ad062012a4d73cd328fa86
change-id: 20231117-fencei-f9f60d784fa0
-- 
- Charlie

[PATCH v8 1/2] riscv: Include riscv_set_icache_flush_ctx prctl

[Charlie Jenkins]

Support new prctl with key PR_RISCV_SET_ICACHE_FLUSH_CTX to enable
optimization of cross modifying code. This prctl enables userspace code
to use icache flushing instructions such as fence.i with the guarantee
that the icache will continue to be clean after thread migration.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
---
 arch/riscv/include/asm/mmu.h         |  4 +++
 arch/riscv/include/asm/mmu_context.h |  3 ++
 arch/riscv/include/asm/processor.h   |  7 ++++
 arch/riscv/include/asm/switch_to.h   | 17 +++++++++
 arch/riscv/mm/cacheflush.c           | 67 ++++++++++++++++++++++++++++++++++++
 arch/riscv/mm/context.c              | 14 ++++++--
 include/uapi/linux/prctl.h           |  6 ++++
 kernel/sys.c                         |  6 ++++
 8 files changed, 121 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
index 355504b37f8e..f437b9a7f5b3 100644
--- a/arch/riscv/include/asm/mmu.h
+++ b/arch/riscv/include/asm/mmu.h
@@ -19,6 +19,10 @@ 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;
+	/* The most recent cpu a thread in this mm has been migrated to. */
+	unsigned int prev_cpu;
 #endif
 #ifdef CONFIG_BINFMT_ELF_FDPIC
 	unsigned long exec_fdpic_loadmap;
diff --git a/arch/riscv/include/asm/mmu_context.h b/arch/riscv/include/asm/mmu_context.h
index 7030837adc1a..195a2e90f3f9 100644
--- a/arch/riscv/include/asm/mmu_context.h
+++ b/arch/riscv/include/asm/mmu_context.h
@@ -29,6 +29,9 @@ static inline int init_new_context(struct task_struct *tsk,
 {
 #ifdef CONFIG_MMU
 	atomic_long_set(&mm->context.id, 0);
+#endif
+#ifdef CONFIG_SMP
+	mm->context.prev_cpu = tsk->thread.prev_cpu;
 #endif
 	return 0;
 }
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index f19f861cda54..1cad05f579ad 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -84,6 +84,10 @@ struct thread_struct {
 	unsigned long vstate_ctrl;
 	struct __riscv_v_ext_state vstate;
 	unsigned long align_ctl;
+#ifdef CONFIG_SMP
+	bool force_icache_flush;
+	unsigned int prev_cpu;
+#endif
 };
 
 /* Whitelist the fstate from the task_struct for hardened usercopy */
@@ -145,6 +149,9 @@ 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 */
diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index f90d8e42f3c7..6a94431dc193 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/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>
@@ -73,6 +74,17 @@ 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)
+{
+	unsigned int cpu = smp_processor_id();
+	bool stale_mm = task->mm && (task->mm->context.force_icache_flush &&
+				     (cpu != task->mm->context.prev_cpu));
+	bool stale_thread = task->thread.force_icache_flush &&
+			    (cpu != task->thread.prev_cpu);
+
+	return stale_mm || stale_thread;
+}
+
 #define switch_to(prev, next, last)			\
 do {							\
 	struct task_struct *__prev = (prev);		\
@@ -81,7 +93,12 @@ do {							\
 		__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));		\
+	__next->thread.prev_cpu = smp_processor_id();	\
+	if (__next->mm)					\
+		__next->mm->context.prev_cpu = smp_processor_id();	\
 } while (0)
 
 #endif /* _ASM_RISCV_SWITCH_TO_H */
diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
index 55a34f2020a8..ff545f19f07a 100644
--- a/arch/riscv/mm/cacheflush.c
+++ b/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 +153,69 @@ void __init riscv_init_cbo_blocksizes(void)
 	if (cboz_block_size)
 		riscv_cboz_block_size = cboz_block_size;
 }
+
+/**
+ * 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 userspace.
+ *
+ * * %PR_RISCV_CTX_SW_FENCEI_OFF: Disallow fence.i in userspace. When ``scope ==
+ *   PR_RISCV_SCOPE_PER_PROCESS``, this will effect all threads in a process.
+ *   Therefore, caution must be taken -- only use this flag 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. Note 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 userspace 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;
+		}
+	}
+#endif
+	return 0;
+}
diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c
index 217fd4de6134..b059dc0fae91 100644
--- a/arch/riscv/mm/context.c
+++ b/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
 
@@ -297,19 +298,26 @@ 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_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
@@ -332,5 +340,5 @@ 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);
 }
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 370ed14b1ae0..524d546d697b 100644
--- a/include/uapi/linux/prctl.h
+++ b/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 */
diff --git a/kernel/sys.c b/kernel/sys.c
index 420d9cb9cc8e..e806a8a67c36 100644
--- a/kernel/sys.c
+++ b/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
@@ -2739,6 +2742,9 @@ 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;

-- 
2.34.1

Re: [PATCH v8 1/2] riscv: Include riscv_set_icache_flush_ctx prctl

[Alexandre Ghiti]

Hi Charlie,

On 17/01/2024 03:54, Charlie Jenkins wrote:
> Support new prctl with key PR_RISCV_SET_ICACHE_FLUSH_CTX to enable
> optimization of cross modifying code. This prctl enables userspace code
> to use icache flushing instructions such as fence.i with the guarantee
> that the icache will continue to be clean after thread migration.
>
> Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
> Reviewed-by: Atish Patra <atishp@rivosinc.com>
> ---
>   arch/riscv/include/asm/mmu.h         |  4 +++
>   arch/riscv/include/asm/mmu_context.h |  3 ++
>   arch/riscv/include/asm/processor.h   |  7 ++++
>   arch/riscv/include/asm/switch_to.h   | 17 +++++++++
>   arch/riscv/mm/cacheflush.c           | 67 ++++++++++++++++++++++++++++++++++++
>   arch/riscv/mm/context.c              | 14 ++++++--
>   include/uapi/linux/prctl.h           |  6 ++++
>   kernel/sys.c                         |  6 ++++
>   8 files changed, 121 insertions(+), 3 deletions(-)
>
> diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
> index 355504b37f8e..f437b9a7f5b3 100644
> --- a/arch/riscv/include/asm/mmu.h
> +++ b/arch/riscv/include/asm/mmu.h
> @@ -19,6 +19,10 @@ 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;
> +	/* The most recent cpu a thread in this mm has been migrated to. */
> +	unsigned int prev_cpu;


Why would we need a prev_cpu on mm? Why don't we only need to have a 
prev_cpu per thread, i.e. per task_struct? It makes little sense to me 
to have that on mm since it's shared by multiple threads (by 
definition), so the prev_cpu on mm could be anything.


>   #endif
>   #ifdef CONFIG_BINFMT_ELF_FDPIC
>   	unsigned long exec_fdpic_loadmap;
> diff --git a/arch/riscv/include/asm/mmu_context.h b/arch/riscv/include/asm/mmu_context.h
> index 7030837adc1a..195a2e90f3f9 100644
> --- a/arch/riscv/include/asm/mmu_context.h
> +++ b/arch/riscv/include/asm/mmu_context.h
> @@ -29,6 +29,9 @@ static inline int init_new_context(struct task_struct *tsk,
>   {
>   #ifdef CONFIG_MMU
>   	atomic_long_set(&mm->context.id, 0);
> +#endif
> +#ifdef CONFIG_SMP
> +	mm->context.prev_cpu = tsk->thread.prev_cpu;
>   #endif
>   	return 0;
>   }
> diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
> index f19f861cda54..1cad05f579ad 100644
> --- a/arch/riscv/include/asm/processor.h
> +++ b/arch/riscv/include/asm/processor.h
> @@ -84,6 +84,10 @@ struct thread_struct {
>   	unsigned long vstate_ctrl;
>   	struct __riscv_v_ext_state vstate;
>   	unsigned long align_ctl;
> +#ifdef CONFIG_SMP
> +	bool force_icache_flush;
> +	unsigned int prev_cpu;
> +#endif
>   };
>   
>   /* Whitelist the fstate from the task_struct for hardened usercopy */
> @@ -145,6 +149,9 @@ 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 */
> diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
> index f90d8e42f3c7..6a94431dc193 100644
> --- a/arch/riscv/include/asm/switch_to.h
> +++ b/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>
> @@ -73,6 +74,17 @@ 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)
> +{
> +	unsigned int cpu = smp_processor_id();
> +	bool stale_mm = task->mm && (task->mm->context.force_icache_flush &&
> +				     (cpu != task->mm->context.prev_cpu));
> +	bool stale_thread = task->thread.force_icache_flush &&
> +			    (cpu != task->thread.prev_cpu);
> +
> +	return stale_mm || stale_thread;


Here the test would become:

return ((task->mm && task->mm->context.force_icache_flush) || 
task->thread.force_icache_flush) && (cpu != task->thread.prev_cpu);

And do we really need to check task->mm is not null?


> +}
> +
>   #define switch_to(prev, next, last)			\
>   do {							\
>   	struct task_struct *__prev = (prev);		\
> @@ -81,7 +93,12 @@ do {							\
>   		__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));		\
> +	__next->thread.prev_cpu = smp_processor_id();	\
> +	if (__next->mm)					\
> +		__next->mm->context.prev_cpu = smp_processor_id();	\
>   } while (0)


And just to make sure I understand this: you moved the test in 
switch_to() because 2 threads with the same mm could be scheduled one 
after the other on the same cpu and then switch_mm() would not be called?


>   
>   #endif /* _ASM_RISCV_SWITCH_TO_H */
> diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
> index 55a34f2020a8..ff545f19f07a 100644
> --- a/arch/riscv/mm/cacheflush.c
> +++ b/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 +153,69 @@ void __init riscv_init_cbo_blocksizes(void)
>   	if (cboz_block_size)
>   		riscv_cboz_block_size = cboz_block_size;
>   }
> +
> +/**
> + * 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 userspace.
> + *
> + * * %PR_RISCV_CTX_SW_FENCEI_OFF: Disallow fence.i in userspace. When ``scope ==
> + *   PR_RISCV_SCOPE_PER_PROCESS``, this will effect all threads in a process.
> + *   Therefore, caution must be taken -- only use this flag 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. Note 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 userspace 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;
> +		}
> +	}
> +#endif
> +	return 0;
> +}
> diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c
> index 217fd4de6134..b059dc0fae91 100644
> --- a/arch/riscv/mm/context.c
> +++ b/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
>   
> @@ -297,19 +298,26 @@ 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_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
> @@ -332,5 +340,5 @@ 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);
>   }
> diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
> index 370ed14b1ae0..524d546d697b 100644
> --- a/include/uapi/linux/prctl.h
> +++ b/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 */
> diff --git a/kernel/sys.c b/kernel/sys.c
> index 420d9cb9cc8e..e806a8a67c36 100644
> --- a/kernel/sys.c
> +++ b/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
> @@ -2739,6 +2742,9 @@ 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;
>

Re: [PATCH v8 1/2] riscv: Include riscv_set_icache_flush_ctx prctl

[Charlie Jenkins]

On Wed, Jan 17, 2024 at 09:42:43AM +0100, Alexandre Ghiti wrote:
> Hi Charlie,
> 
> On 17/01/2024 03:54, Charlie Jenkins wrote:
> > Support new prctl with key PR_RISCV_SET_ICACHE_FLUSH_CTX to enable
> > optimization of cross modifying code. This prctl enables userspace code
> > to use icache flushing instructions such as fence.i with the guarantee
> > that the icache will continue to be clean after thread migration.
> > 
> > Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
> > Reviewed-by: Atish Patra <atishp@rivosinc.com>
> > ---
> >   arch/riscv/include/asm/mmu.h         |  4 +++
> >   arch/riscv/include/asm/mmu_context.h |  3 ++
> >   arch/riscv/include/asm/processor.h   |  7 ++++
> >   arch/riscv/include/asm/switch_to.h   | 17 +++++++++
> >   arch/riscv/mm/cacheflush.c           | 67 ++++++++++++++++++++++++++++++++++++
> >   arch/riscv/mm/context.c              | 14 ++++++--
> >   include/uapi/linux/prctl.h           |  6 ++++
> >   kernel/sys.c                         |  6 ++++
> >   8 files changed, 121 insertions(+), 3 deletions(-)
> > 
> > diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
> > index 355504b37f8e..f437b9a7f5b3 100644
> > --- a/arch/riscv/include/asm/mmu.h
> > +++ b/arch/riscv/include/asm/mmu.h
> > @@ -19,6 +19,10 @@ 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;
> > +	/* The most recent cpu a thread in this mm has been migrated to. */
> > +	unsigned int prev_cpu;
> 
> 
> Why would we need a prev_cpu on mm? Why don't we only need to have a
> prev_cpu per thread, i.e. per task_struct? It makes little sense to me to
> have that on mm since it's shared by multiple threads (by definition), so
> the prev_cpu on mm could be anything.
> 

Yes you are correct, I will remove that.

> 
> >   #endif
> >   #ifdef CONFIG_BINFMT_ELF_FDPIC
> >   	unsigned long exec_fdpic_loadmap;
> > diff --git a/arch/riscv/include/asm/mmu_context.h b/arch/riscv/include/asm/mmu_context.h
> > index 7030837adc1a..195a2e90f3f9 100644
> > --- a/arch/riscv/include/asm/mmu_context.h
> > +++ b/arch/riscv/include/asm/mmu_context.h
> > @@ -29,6 +29,9 @@ static inline int init_new_context(struct task_struct *tsk,
> >   {
> >   #ifdef CONFIG_MMU
> >   	atomic_long_set(&mm->context.id, 0);
> > +#endif
> > +#ifdef CONFIG_SMP
> > +	mm->context.prev_cpu = tsk->thread.prev_cpu;
> >   #endif
> >   	return 0;
> >   }
> > diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
> > index f19f861cda54..1cad05f579ad 100644
> > --- a/arch/riscv/include/asm/processor.h
> > +++ b/arch/riscv/include/asm/processor.h
> > @@ -84,6 +84,10 @@ struct thread_struct {
> >   	unsigned long vstate_ctrl;
> >   	struct __riscv_v_ext_state vstate;
> >   	unsigned long align_ctl;
> > +#ifdef CONFIG_SMP
> > +	bool force_icache_flush;
> > +	unsigned int prev_cpu;
> > +#endif
> >   };
> >   /* Whitelist the fstate from the task_struct for hardened usercopy */
> > @@ -145,6 +149,9 @@ 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 */
> > diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
> > index f90d8e42f3c7..6a94431dc193 100644
> > --- a/arch/riscv/include/asm/switch_to.h
> > +++ b/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>
> > @@ -73,6 +74,17 @@ 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)
> > +{
> > +	unsigned int cpu = smp_processor_id();
> > +	bool stale_mm = task->mm && (task->mm->context.force_icache_flush &&
> > +				     (cpu != task->mm->context.prev_cpu));
> > +	bool stale_thread = task->thread.force_icache_flush &&
> > +			    (cpu != task->thread.prev_cpu);
> > +
> > +	return stale_mm || stale_thread;
> 
> 
> Here the test would become:
> 
> return ((task->mm && task->mm->context.force_icache_flush) ||
> task->thread.force_icache_flush) && (cpu != task->thread.prev_cpu);
> 
> And do we really need to check task->mm is not null?

mm can be null if the task is associated with a kernel thread. So the
check is necessary.

> 
> 
> > +}
> > +
> >   #define switch_to(prev, next, last)			\
> >   do {							\
> >   	struct task_struct *__prev = (prev);		\
> > @@ -81,7 +93,12 @@ do {							\
> >   		__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));		\
> > +	__next->thread.prev_cpu = smp_processor_id();	\
> > +	if (__next->mm)					\
> > +		__next->mm->context.prev_cpu = smp_processor_id();	\
> >   } while (0)
> 
> 
> And just to make sure I understand this: you moved the test in switch_to()
> because 2 threads with the same mm could be scheduled one after the other on
> the same cpu and then switch_mm() would not be called?
> 

Yes exactly.

- Charlie

> 
> >   #endif /* _ASM_RISCV_SWITCH_TO_H */
> > diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
> > index 55a34f2020a8..ff545f19f07a 100644
> > --- a/arch/riscv/mm/cacheflush.c
> > +++ b/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 +153,69 @@ void __init riscv_init_cbo_blocksizes(void)
> >   	if (cboz_block_size)
> >   		riscv_cboz_block_size = cboz_block_size;
> >   }
> > +
> > +/**
> > + * 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 userspace.
> > + *
> > + * * %PR_RISCV_CTX_SW_FENCEI_OFF: Disallow fence.i in userspace. When ``scope ==
> > + *   PR_RISCV_SCOPE_PER_PROCESS``, this will effect all threads in a process.
> > + *   Therefore, caution must be taken -- only use this flag 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. Note 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 userspace 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;
> > +		}
> > +	}
> > +#endif
> > +	return 0;
> > +}
> > diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c
> > index 217fd4de6134..b059dc0fae91 100644
> > --- a/arch/riscv/mm/context.c
> > +++ b/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
> > @@ -297,19 +298,26 @@ 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_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
> > @@ -332,5 +340,5 @@ 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);
> >   }
> > diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
> > index 370ed14b1ae0..524d546d697b 100644
> > --- a/include/uapi/linux/prctl.h
> > +++ b/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 */
> > diff --git a/kernel/sys.c b/kernel/sys.c
> > index 420d9cb9cc8e..e806a8a67c36 100644
> > --- a/kernel/sys.c
> > +++ b/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
> > @@ -2739,6 +2742,9 @@ 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;
> > 

Re: [PATCH v8 1/2] riscv: Include riscv_set_icache_flush_ctx prctl

[Alexandre Ghiti]

On 19/01/2024 00:16, Charlie Jenkins wrote:
> On Wed, Jan 17, 2024 at 09:42:43AM +0100, Alexandre Ghiti wrote:
>> Hi Charlie,
>>
>> On 17/01/2024 03:54, Charlie Jenkins wrote:
>>> Support new prctl with key PR_RISCV_SET_ICACHE_FLUSH_CTX to enable
>>> optimization of cross modifying code. This prctl enables userspace code
>>> to use icache flushing instructions such as fence.i with the guarantee
>>> that the icache will continue to be clean after thread migration.
>>>
>>> Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
>>> Reviewed-by: Atish Patra <atishp@rivosinc.com>
>>> ---
>>>    arch/riscv/include/asm/mmu.h         |  4 +++
>>>    arch/riscv/include/asm/mmu_context.h |  3 ++
>>>    arch/riscv/include/asm/processor.h   |  7 ++++
>>>    arch/riscv/include/asm/switch_to.h   | 17 +++++++++
>>>    arch/riscv/mm/cacheflush.c           | 67 ++++++++++++++++++++++++++++++++++++
>>>    arch/riscv/mm/context.c              | 14 ++++++--
>>>    include/uapi/linux/prctl.h           |  6 ++++
>>>    kernel/sys.c                         |  6 ++++
>>>    8 files changed, 121 insertions(+), 3 deletions(-)
>>>
>>> diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
>>> index 355504b37f8e..f437b9a7f5b3 100644
>>> --- a/arch/riscv/include/asm/mmu.h
>>> +++ b/arch/riscv/include/asm/mmu.h
>>> @@ -19,6 +19,10 @@ 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;
>>> +	/* The most recent cpu a thread in this mm has been migrated to. */
>>> +	unsigned int prev_cpu;
>>
>> Why would we need a prev_cpu on mm? Why don't we only need to have a
>> prev_cpu per thread, i.e. per task_struct? It makes little sense to me to
>> have that on mm since it's shared by multiple threads (by definition), so
>> the prev_cpu on mm could be anything.
>>
> Yes you are correct, I will remove that.
>
>>>    #endif
>>>    #ifdef CONFIG_BINFMT_ELF_FDPIC
>>>    	unsigned long exec_fdpic_loadmap;
>>> diff --git a/arch/riscv/include/asm/mmu_context.h b/arch/riscv/include/asm/mmu_context.h
>>> index 7030837adc1a..195a2e90f3f9 100644
>>> --- a/arch/riscv/include/asm/mmu_context.h
>>> +++ b/arch/riscv/include/asm/mmu_context.h
>>> @@ -29,6 +29,9 @@ static inline int init_new_context(struct task_struct *tsk,
>>>    {
>>>    #ifdef CONFIG_MMU
>>>    	atomic_long_set(&mm->context.id, 0);
>>> +#endif
>>> +#ifdef CONFIG_SMP
>>> +	mm->context.prev_cpu = tsk->thread.prev_cpu;
>>>    #endif
>>>    	return 0;
>>>    }
>>> diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
>>> index f19f861cda54..1cad05f579ad 100644
>>> --- a/arch/riscv/include/asm/processor.h
>>> +++ b/arch/riscv/include/asm/processor.h
>>> @@ -84,6 +84,10 @@ struct thread_struct {
>>>    	unsigned long vstate_ctrl;
>>>    	struct __riscv_v_ext_state vstate;
>>>    	unsigned long align_ctl;
>>> +#ifdef CONFIG_SMP
>>> +	bool force_icache_flush;
>>> +	unsigned int prev_cpu;
>>> +#endif
>>>    };
>>>    /* Whitelist the fstate from the task_struct for hardened usercopy */
>>> @@ -145,6 +149,9 @@ 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 */
>>> diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
>>> index f90d8e42f3c7..6a94431dc193 100644
>>> --- a/arch/riscv/include/asm/switch_to.h
>>> +++ b/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>
>>> @@ -73,6 +74,17 @@ 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)
>>> +{
>>> +	unsigned int cpu = smp_processor_id();
>>> +	bool stale_mm = task->mm && (task->mm->context.force_icache_flush &&
>>> +				     (cpu != task->mm->context.prev_cpu));
>>> +	bool stale_thread = task->thread.force_icache_flush &&
>>> +			    (cpu != task->thread.prev_cpu);
>>> +
>>> +	return stale_mm || stale_thread;
>>
>> Here the test would become:
>>
>> return ((task->mm && task->mm->context.force_icache_flush) ||
>> task->thread.force_icache_flush) && (cpu != task->thread.prev_cpu);
>>
>> And do we really need to check task->mm is not null?
> mm can be null if the task is associated with a kernel thread. So the
> check is necessary.


Yes, you're right, thanks


>>
>>> +}
>>> +
>>>    #define switch_to(prev, next, last)			\
>>>    do {							\
>>>    	struct task_struct *__prev = (prev);		\
>>> @@ -81,7 +93,12 @@ do {							\
>>>    		__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));		\
>>> +	__next->thread.prev_cpu = smp_processor_id();	\
>>> +	if (__next->mm)					\
>>> +		__next->mm->context.prev_cpu = smp_processor_id();	\
>>>    } while (0)
>>
>> And just to make sure I understand this: you moved the test in switch_to()
>> because 2 threads with the same mm could be scheduled one after the other on
>> the same cpu and then switch_mm() would not be called?
>>
> Yes exactly.


Very good catch then!

Thanks,

Alex


>
> - Charlie
>
>>>    #endif /* _ASM_RISCV_SWITCH_TO_H */
>>> diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
>>> index 55a34f2020a8..ff545f19f07a 100644
>>> --- a/arch/riscv/mm/cacheflush.c
>>> +++ b/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 +153,69 @@ void __init riscv_init_cbo_blocksizes(void)
>>>    	if (cboz_block_size)
>>>    		riscv_cboz_block_size = cboz_block_size;
>>>    }
>>> +
>>> +/**
>>> + * 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 userspace.
>>> + *
>>> + * * %PR_RISCV_CTX_SW_FENCEI_OFF: Disallow fence.i in userspace. When ``scope ==
>>> + *   PR_RISCV_SCOPE_PER_PROCESS``, this will effect all threads in a process.
>>> + *   Therefore, caution must be taken -- only use this flag 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. Note 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 userspace 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;
>>> +		}
>>> +	}
>>> +#endif
>>> +	return 0;
>>> +}
>>> diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c
>>> index 217fd4de6134..b059dc0fae91 100644
>>> --- a/arch/riscv/mm/context.c
>>> +++ b/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
>>> @@ -297,19 +298,26 @@ 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_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
>>> @@ -332,5 +340,5 @@ 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);
>>>    }
>>> diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
>>> index 370ed14b1ae0..524d546d697b 100644
>>> --- a/include/uapi/linux/prctl.h
>>> +++ b/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 */
>>> diff --git a/kernel/sys.c b/kernel/sys.c
>>> index 420d9cb9cc8e..e806a8a67c36 100644
>>> --- a/kernel/sys.c
>>> +++ b/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
>>> @@ -2739,6 +2742,9 @@ 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;
>>>
> _______________________________________________
> linux-riscv mailing list
> linux-riscv@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-riscv

Re: [PATCH v8 1/2] riscv: Include riscv_set_icache_flush_ctx prctl

[Charlie Jenkins]

On Fri, Jan 19, 2024 at 09:05:12AM +0100, Alexandre Ghiti wrote:
> On 19/01/2024 00:16, Charlie Jenkins wrote:
> > On Wed, Jan 17, 2024 at 09:42:43AM +0100, Alexandre Ghiti wrote:
> > > Hi Charlie,
> > > 
> > > On 17/01/2024 03:54, Charlie Jenkins wrote:
> > > > Support new prctl with key PR_RISCV_SET_ICACHE_FLUSH_CTX to enable
> > > > optimization of cross modifying code. This prctl enables userspace code
> > > > to use icache flushing instructions such as fence.i with the guarantee
> > > > that the icache will continue to be clean after thread migration.
> > > > 
> > > > Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
> > > > Reviewed-by: Atish Patra <atishp@rivosinc.com>
> > > > ---
> > > >    arch/riscv/include/asm/mmu.h         |  4 +++
> > > >    arch/riscv/include/asm/mmu_context.h |  3 ++
> > > >    arch/riscv/include/asm/processor.h   |  7 ++++
> > > >    arch/riscv/include/asm/switch_to.h   | 17 +++++++++
> > > >    arch/riscv/mm/cacheflush.c           | 67 ++++++++++++++++++++++++++++++++++++
> > > >    arch/riscv/mm/context.c              | 14 ++++++--
> > > >    include/uapi/linux/prctl.h           |  6 ++++
> > > >    kernel/sys.c                         |  6 ++++
> > > >    8 files changed, 121 insertions(+), 3 deletions(-)
> > > > 
> > > > diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
> > > > index 355504b37f8e..f437b9a7f5b3 100644
> > > > --- a/arch/riscv/include/asm/mmu.h
> > > > +++ b/arch/riscv/include/asm/mmu.h
> > > > @@ -19,6 +19,10 @@ 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;
> > > > +	/* The most recent cpu a thread in this mm has been migrated to. */
> > > > +	unsigned int prev_cpu;
> > > 
> > > Why would we need a prev_cpu on mm? Why don't we only need to have a
> > > prev_cpu per thread, i.e. per task_struct? It makes little sense to me to
> > > have that on mm since it's shared by multiple threads (by definition), so
> > > the prev_cpu on mm could be anything.
> > > 
> > Yes you are correct, I will remove that.
> > 

To add more context to the case that I was overlooking when I wrote this
code, this is the case that fails. I will send out a new version without
prev_cpu on mm.

- Thread A is migrated to CPU A so the mm sets prev_cpu to CPU A.
- Thread B is doing cmodx on CPU B so the icache is not synchronized with instruction storage on CPU A or CPU B.
- Thread A doesn't flush the icache.
- Thread B migrates to CPU A and the icache is not flushed because prev_cpu is CPU A.
- CPU A icache is still not synchronized with instruction storage.

- Charlie

> > > >    #endif
> > > >    #ifdef CONFIG_BINFMT_ELF_FDPIC
> > > >    	unsigned long exec_fdpic_loadmap;
> > > > diff --git a/arch/riscv/include/asm/mmu_context.h b/arch/riscv/include/asm/mmu_context.h
> > > > index 7030837adc1a..195a2e90f3f9 100644
> > > > --- a/arch/riscv/include/asm/mmu_context.h
> > > > +++ b/arch/riscv/include/asm/mmu_context.h
> > > > @@ -29,6 +29,9 @@ static inline int init_new_context(struct task_struct *tsk,
> > > >    {
> > > >    #ifdef CONFIG_MMU
> > > >    	atomic_long_set(&mm->context.id, 0);
> > > > +#endif
> > > > +#ifdef CONFIG_SMP
> > > > +	mm->context.prev_cpu = tsk->thread.prev_cpu;
> > > >    #endif
> > > >    	return 0;
> > > >    }
> > > > diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
> > > > index f19f861cda54..1cad05f579ad 100644
> > > > --- a/arch/riscv/include/asm/processor.h
> > > > +++ b/arch/riscv/include/asm/processor.h
> > > > @@ -84,6 +84,10 @@ struct thread_struct {
> > > >    	unsigned long vstate_ctrl;
> > > >    	struct __riscv_v_ext_state vstate;
> > > >    	unsigned long align_ctl;
> > > > +#ifdef CONFIG_SMP
> > > > +	bool force_icache_flush;
> > > > +	unsigned int prev_cpu;
> > > > +#endif
> > > >    };
> > > >    /* Whitelist the fstate from the task_struct for hardened usercopy */
> > > > @@ -145,6 +149,9 @@ 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 */
> > > > diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
> > > > index f90d8e42f3c7..6a94431dc193 100644
> > > > --- a/arch/riscv/include/asm/switch_to.h
> > > > +++ b/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>
> > > > @@ -73,6 +74,17 @@ 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)
> > > > +{
> > > > +	unsigned int cpu = smp_processor_id();
> > > > +	bool stale_mm = task->mm && (task->mm->context.force_icache_flush &&
> > > > +				     (cpu != task->mm->context.prev_cpu));
> > > > +	bool stale_thread = task->thread.force_icache_flush &&
> > > > +			    (cpu != task->thread.prev_cpu);
> > > > +
> > > > +	return stale_mm || stale_thread;
> > > 
> > > Here the test would become:
> > > 
> > > return ((task->mm && task->mm->context.force_icache_flush) ||
> > > task->thread.force_icache_flush) && (cpu != task->thread.prev_cpu);
> > > 
> > > And do we really need to check task->mm is not null?
> > mm can be null if the task is associated with a kernel thread. So the
> > check is necessary.
> 
> 
> Yes, you're right, thanks
> 
> 
> > > 
> > > > +}
> > > > +
> > > >    #define switch_to(prev, next, last)			\
> > > >    do {							\
> > > >    	struct task_struct *__prev = (prev);		\
> > > > @@ -81,7 +93,12 @@ do {							\
> > > >    		__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));		\
> > > > +	__next->thread.prev_cpu = smp_processor_id();	\
> > > > +	if (__next->mm)					\
> > > > +		__next->mm->context.prev_cpu = smp_processor_id();	\
> > > >    } while (0)
> > > 
> > > And just to make sure I understand this: you moved the test in switch_to()
> > > because 2 threads with the same mm could be scheduled one after the other on
> > > the same cpu and then switch_mm() would not be called?
> > > 
> > Yes exactly.
> 
> 
> Very good catch then!
> 
> Thanks,
> 
> Alex
> 
> 
> > 
> > - Charlie
> > 
> > > >    #endif /* _ASM_RISCV_SWITCH_TO_H */
> > > > diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
> > > > index 55a34f2020a8..ff545f19f07a 100644
> > > > --- a/arch/riscv/mm/cacheflush.c
> > > > +++ b/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 +153,69 @@ void __init riscv_init_cbo_blocksizes(void)
> > > >    	if (cboz_block_size)
> > > >    		riscv_cboz_block_size = cboz_block_size;
> > > >    }
> > > > +
> > > > +/**
> > > > + * 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 userspace.
> > > > + *
> > > > + * * %PR_RISCV_CTX_SW_FENCEI_OFF: Disallow fence.i in userspace. When ``scope ==
> > > > + *   PR_RISCV_SCOPE_PER_PROCESS``, this will effect all threads in a process.
> > > > + *   Therefore, caution must be taken -- only use this flag 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. Note 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 userspace 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;
> > > > +		}
> > > > +	}
> > > > +#endif
> > > > +	return 0;
> > > > +}
> > > > diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c
> > > > index 217fd4de6134..b059dc0fae91 100644
> > > > --- a/arch/riscv/mm/context.c
> > > > +++ b/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
> > > > @@ -297,19 +298,26 @@ 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_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
> > > > @@ -332,5 +340,5 @@ 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);
> > > >    }
> > > > diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
> > > > index 370ed14b1ae0..524d546d697b 100644
> > > > --- a/include/uapi/linux/prctl.h
> > > > +++ b/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 */
> > > > diff --git a/kernel/sys.c b/kernel/sys.c
> > > > index 420d9cb9cc8e..e806a8a67c36 100644
> > > > --- a/kernel/sys.c
> > > > +++ b/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
> > > > @@ -2739,6 +2742,9 @@ 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;
> > > > 
> > _______________________________________________
> > linux-riscv mailing list
> > linux-riscv@lists.infradead.org
> > http://lists.infradead.org/mailman/listinfo/linux-riscv

[PATCH v8 2/2] documentation: Document PR_RISCV_SET_ICACHE_FLUSH_CTX prctl

[Charlie Jenkins]

Provide documentation that explains how to properly do CMODX in riscv.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
---
 Documentation/arch/riscv/cmodx.rst | 96 ++++++++++++++++++++++++++++++++++++++
 Documentation/arch/riscv/index.rst |  1 +
 2 files changed, 97 insertions(+)

diff --git a/Documentation/arch/riscv/cmodx.rst b/Documentation/arch/riscv/cmodx.rst
new file mode 100644
index 000000000000..2ad46129d812
--- /dev/null
+++ b/Documentation/arch/riscv/cmodx.rst
@@ -0,0 +1,96 @@
+.. 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 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();
+
+		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
diff --git a/Documentation/arch/riscv/index.rst b/Documentation/arch/riscv/index.rst
index 4dab0cb4b900..eecf347ce849 100644
--- a/Documentation/arch/riscv/index.rst
+++ b/Documentation/arch/riscv/index.rst
@@ -13,6 +13,7 @@ RISC-V architecture
     patch-acceptance
     uabi
     vector
+    cmodx
 
     features
 

-- 
2.34.1