[PATCH v9 3/4] riscv: Decouple emulated unaligned accesses from access speed

From: Charlie Jenkins
Date: Fri Mar 08 2024 - 13:26:40 EST


Detecting if a system traps into the kernel on an unaligned access
can be performed separately from checking the speed of unaligned
accesses. This decoupling will make it possible to selectively enable
or disable each of these checks.

Signed-off-by: Charlie Jenkins <charlie@xxxxxxxxxxxx>
Reviewed-by: Conor Dooley <conor.dooley@xxxxxxxxxxxxx>
---
arch/riscv/include/asm/cpufeature.h | 2 +-
arch/riscv/kernel/cpufeature.c | 25 +++++++++++++++++++++----
arch/riscv/kernel/traps_misaligned.c | 15 +++++++--------
3 files changed, 29 insertions(+), 13 deletions(-)

diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index 466e1f591919..6fec91845aa0 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -37,7 +37,7 @@ void riscv_user_isa_enable(void);

#ifdef CONFIG_RISCV_MISALIGNED
bool unaligned_ctl_available(void);
-bool check_unaligned_access_emulated(int cpu);
+bool check_unaligned_access_emulated_all_cpus(void);
void unaligned_emulation_finish(void);
#else
static inline bool unaligned_ctl_available(void)
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 7878cddccc0d..abb3a2f53106 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -719,7 +719,8 @@ static int check_unaligned_access(void *param)
void *src;
long speed = RISCV_HWPROBE_MISALIGNED_SLOW;

- if (check_unaligned_access_emulated(cpu))
+ if (IS_ENABLED(CONFIG_RISCV_MISALIGNED) &&
+ per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_UNKNOWN)
return 0;

/* Make an unaligned destination buffer. */
@@ -896,8 +897,8 @@ static int riscv_offline_cpu(unsigned int cpu)
return 0;
}

-/* Measure unaligned access on all CPUs present at boot in parallel. */
-static int check_unaligned_access_all_cpus(void)
+/* Measure unaligned access speed on all CPUs present at boot in parallel. */
+static int check_unaligned_access_speed_all_cpus(void)
{
unsigned int cpu;
unsigned int cpu_count = num_possible_cpus();
@@ -935,7 +936,6 @@ static int check_unaligned_access_all_cpus(void)
riscv_online_cpu, riscv_offline_cpu);

out:
- unaligned_emulation_finish();
for_each_cpu(cpu, cpu_online_mask) {
if (bufs[cpu])
__free_pages(bufs[cpu], MISALIGNED_BUFFER_ORDER);
@@ -945,6 +945,23 @@ static int check_unaligned_access_all_cpus(void)
return 0;
}

+#ifdef CONFIG_RISCV_MISALIGNED
+static int check_unaligned_access_all_cpus(void)
+{
+ bool all_cpus_emulated = check_unaligned_access_emulated_all_cpus();
+
+ if (!all_cpus_emulated)
+ return check_unaligned_access_speed_all_cpus();
+
+ return 0;
+}
+#else
+static int check_unaligned_access_all_cpus(void)
+{
+ return check_unaligned_access_speed_all_cpus();
+}
+#endif
+
arch_initcall(check_unaligned_access_all_cpus);

void riscv_user_isa_enable(void)
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index c2ed4e689bf9..e55718179f42 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -596,7 +596,7 @@ int handle_misaligned_store(struct pt_regs *regs)
return 0;
}

-bool check_unaligned_access_emulated(int cpu)
+static bool check_unaligned_access_emulated(int cpu)
{
long *mas_ptr = per_cpu_ptr(&misaligned_access_speed, cpu);
unsigned long tmp_var, tmp_val;
@@ -623,7 +623,7 @@ bool check_unaligned_access_emulated(int cpu)
return misaligned_emu_detected;
}

-void unaligned_emulation_finish(void)
+bool check_unaligned_access_emulated_all_cpus(void)
{
int cpu;

@@ -632,13 +632,12 @@ void unaligned_emulation_finish(void)
* accesses emulated since tasks requesting such control can run on any
* CPU.
*/
- for_each_online_cpu(cpu) {
- if (per_cpu(misaligned_access_speed, cpu) !=
- RISCV_HWPROBE_MISALIGNED_EMULATED) {
- return;
- }
- }
+ for_each_online_cpu(cpu)
+ if (!check_unaligned_access_emulated(cpu))
+ return false;
+
unaligned_ctl = true;
+ return true;
}

bool unaligned_ctl_available(void)

--
2.43.2