[PATCH v2 0/2] riscv: Use CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS to set misaligned access speed

[PATCH v2 0/2] riscv: Use CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS to set misaligned access speed

[Charlie Jenkins]

If CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS is enabled, no time needs to
be spent in the misaligned access speed probe. Disable the probe in this
case and set respective uses to "fast" misaligned accesses. On riscv,
this config is selected if RISCV_EFFICIENT_UNALIGNED_ACCESS is selected,
which is dependent on NONPORTABLE.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
---
Changes in v2:
- Move around definitions to reduce ifdefs (Clément)
- Make RISCV_MISALIGNED depend on !HAVE_EFFICIENT_UNALIGNED_ACCESS
  (Clément)
- Link to v1: https://lore.kernel.org/r/20240131-disable_misaligned_probe_config-v1-0-98d155e9cda8@rivosinc.com

---
Charlie Jenkins (2):
      riscv: lib: Introduce has_fast_misaligned_access function
      riscv: Disable misaligned access probe when CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS

 arch/riscv/Kconfig                               |   1 +
 arch/riscv/include/asm/cpufeature.h              |  22 +-
 arch/riscv/include/asm/misaligned_access_speed.h |  29 +++
 arch/riscv/kernel/Makefile                       |   3 +
 arch/riscv/kernel/cpufeature.c                   | 255 ----------------------
 arch/riscv/kernel/misaligned_access_speed.c      | 265 +++++++++++++++++++++++
 arch/riscv/kernel/sys_hwprobe.c                  |   4 +
 arch/riscv/lib/csum.c                            |   7 +-
 8 files changed, 321 insertions(+), 265 deletions(-)
---
base-commit: 6613476e225e090cc9aad49be7fa504e290dd33d
change-id: 20240131-disable_misaligned_probe_config-043aea375f93
-- 
- Charlie

[PATCH v2 1/2] riscv: lib: Introduce has_fast_misaligned_access function

[Charlie Jenkins]

Create has_fast_misaligned_access to avoid needing to explicitly check
the fast_misaligned_access_speed_key static key.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
---
 arch/riscv/include/asm/cpufeature.h | 15 ++++++++++-----
 arch/riscv/lib/csum.c               |  7 ++-----
 2 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index 5a626ed2c47a..eb3ac304fc42 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright 2022-2023 Rivos, Inc
+ * Copyright 2022-2024 Rivos, Inc
  */
 
 #ifndef _ASM_CPUFEATURE_H
@@ -28,8 +28,6 @@ struct riscv_isainfo {
 
 DECLARE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo);
 
-DECLARE_PER_CPU(long, misaligned_access_speed);
-
 /* Per-cpu ISA extensions. */
 extern struct riscv_isainfo hart_isa[NR_CPUS];
 
@@ -53,6 +51,15 @@ static inline bool check_unaligned_access_emulated(int cpu)
 static inline void unaligned_emulation_finish(void) {}
 #endif
 
+DECLARE_PER_CPU(long, misaligned_access_speed);
+
+DECLARE_STATIC_KEY_FALSE(fast_misaligned_access_speed_key);
+
+static __always_inline bool has_fast_misaligned_accesses(void)
+{
+	return static_branch_likely(&fast_misaligned_access_speed_key);
+}
+
 unsigned long riscv_get_elf_hwcap(void);
 
 struct riscv_isa_ext_data {
@@ -135,6 +142,4 @@ static __always_inline bool riscv_cpu_has_extension_unlikely(int cpu, const unsi
 	return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
 }
 
-DECLARE_STATIC_KEY_FALSE(fast_misaligned_access_speed_key);
-
 #endif
diff --git a/arch/riscv/lib/csum.c b/arch/riscv/lib/csum.c
index af3df5274ccb..ea2f668fab71 100644
--- a/arch/riscv/lib/csum.c
+++ b/arch/riscv/lib/csum.c
@@ -3,7 +3,7 @@
  * Checksum library
  *
  * Influenced by arch/arm64/lib/csum.c
- * Copyright (C) 2023 Rivos Inc.
+ * Copyright (C) 2023-2024 Rivos Inc.
  */
 #include <linux/bitops.h>
 #include <linux/compiler.h>
@@ -318,10 +318,7 @@ unsigned int do_csum(const unsigned char *buff, int len)
 	 * branches. The largest chunk of overlap was delegated into the
 	 * do_csum_common function.
 	 */
-	if (static_branch_likely(&fast_misaligned_access_speed_key))
-		return do_csum_no_alignment(buff, len);
-
-	if (((unsigned long)buff & OFFSET_MASK) == 0)
+	if (has_fast_misaligned_accesses() || (((unsigned long)buff & OFFSET_MASK) == 0b101))
 		return do_csum_no_alignment(buff, len);
 
 	return do_csum_with_alignment(buff, len);

-- 
2.43.0

[PATCH v2 2/2] riscv: Disable misaligned access probe when CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS

[Charlie Jenkins]

When CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS is selected, the cpus can be
set to have fast misaligned access without needing to probe.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
---
 arch/riscv/Kconfig                               |   1 +
 arch/riscv/include/asm/cpufeature.h              |   7 +
 arch/riscv/include/asm/misaligned_access_speed.h |  29 +++
 arch/riscv/kernel/Makefile                       |   3 +
 arch/riscv/kernel/cpufeature.c                   | 255 ----------------------
 arch/riscv/kernel/misaligned_access_speed.c      | 265 +++++++++++++++++++++++
 arch/riscv/kernel/sys_hwprobe.c                  |   4 +
 7 files changed, 309 insertions(+), 255 deletions(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index bffbd869a068..3223d2d08f74 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -690,6 +690,7 @@ config THREAD_SIZE_ORDER
 config RISCV_MISALIGNED
 	bool "Support misaligned load/store traps for kernel and userspace"
 	select SYSCTL_ARCH_UNALIGN_ALLOW
+	depends on !HAVE_EFFICIENT_UNALIGNED_ACCESS
 	default y
 	help
 	  Say Y here if you want the kernel to embed support for misaligned
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index eb3ac304fc42..3a29d8e30e05 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -51,6 +51,7 @@ static inline bool check_unaligned_access_emulated(int cpu)
 static inline void unaligned_emulation_finish(void) {}
 #endif
 
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 DECLARE_PER_CPU(long, misaligned_access_speed);
 
 DECLARE_STATIC_KEY_FALSE(fast_misaligned_access_speed_key);
@@ -59,6 +60,12 @@ static __always_inline bool has_fast_misaligned_accesses(void)
 {
 	return static_branch_likely(&fast_misaligned_access_speed_key);
 }
+#else
+static __always_inline bool has_fast_misaligned_accesses(void)
+{
+	return true;
+}
+#endif
 
 unsigned long riscv_get_elf_hwcap(void);
 
diff --git a/arch/riscv/include/asm/misaligned_access_speed.h b/arch/riscv/include/asm/misaligned_access_speed.h
new file mode 100644
index 000000000000..81df2aa6fa6b
--- /dev/null
+++ b/arch/riscv/include/asm/misaligned_access_speed.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2024 Rivos, Inc
+ */
+
+#ifndef _ASM_MISALIGNED_ACCESS_SPEED_H
+#define _ASM_MISALIGNED_ACCESS_SPEED_H
+
+#include <linux/compiler_attributes.h>
+#include <linux/jump_label.h>
+#include <linux/percpu.h>
+#include <linux/types.h>
+
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+DECLARE_PER_CPU(long, misaligned_access_speed);
+
+DECLARE_STATIC_KEY_FALSE(fast_misaligned_access_speed_key);
+
+static __always_inline bool has_fast_misaligned_accesses(void)
+{
+	return static_branch_likely(&fast_misaligned_access_speed_key);
+}
+#else
+static __always_inline bool has_fast_misaligned_accesses(void)
+{
+	return static_branch_likely(&fast_misaligned_access_speed_key);
+}
+#endif
+#endif
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index f71910718053..8be7f17da9ab 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -62,6 +62,9 @@ obj-y	+= tests/
 obj-$(CONFIG_MMU) += vdso.o vdso/
 
 obj-$(CONFIG_RISCV_MISALIGNED)	+= traps_misaligned.o
+ifneq ($(RISCV_EFFICIENT_UNALIGNED_ACCESS), y)
+obj-y	+= misaligned_access_speed.o
+endif
 obj-$(CONFIG_FPU)		+= fpu.o
 obj-$(CONFIG_RISCV_ISA_V)	+= vector.o
 obj-$(CONFIG_RISCV_ISA_V)	+= kernel_mode_vector.o
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 89920f84d0a3..319670af5704 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -11,7 +11,6 @@
 #include <linux/cpu.h>
 #include <linux/cpuhotplug.h>
 #include <linux/ctype.h>
-#include <linux/jump_label.h>
 #include <linux/log2.h>
 #include <linux/memory.h>
 #include <linux/module.h>
@@ -21,20 +20,12 @@
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
 #include <asm/hwcap.h>
-#include <asm/hwprobe.h>
 #include <asm/patch.h>
 #include <asm/processor.h>
 #include <asm/vector.h>
 
-#include "copy-unaligned.h"
-
 #define NUM_ALPHA_EXTS ('z' - 'a' + 1)
 
-#define MISALIGNED_ACCESS_JIFFIES_LG2 1
-#define MISALIGNED_BUFFER_SIZE 0x4000
-#define MISALIGNED_BUFFER_ORDER get_order(MISALIGNED_BUFFER_SIZE)
-#define MISALIGNED_COPY_SIZE ((MISALIGNED_BUFFER_SIZE / 2) - 0x80)
-
 unsigned long elf_hwcap __read_mostly;
 
 /* Host ISA bitmap */
@@ -43,11 +34,6 @@ static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly;
 /* Per-cpu ISA extensions. */
 struct riscv_isainfo hart_isa[NR_CPUS];
 
-/* Performance information */
-DEFINE_PER_CPU(long, misaligned_access_speed);
-
-static cpumask_t fast_misaligned_access;
-
 /**
  * riscv_isa_extension_base() - Get base extension word
  *
@@ -706,247 +692,6 @@ unsigned long riscv_get_elf_hwcap(void)
 	return hwcap;
 }
 
-static int check_unaligned_access(void *param)
-{
-	int cpu = smp_processor_id();
-	u64 start_cycles, end_cycles;
-	u64 word_cycles;
-	u64 byte_cycles;
-	int ratio;
-	unsigned long start_jiffies, now;
-	struct page *page = param;
-	void *dst;
-	void *src;
-	long speed = RISCV_HWPROBE_MISALIGNED_SLOW;
-
-	if (check_unaligned_access_emulated(cpu))
-		return 0;
-
-	/* Make an unaligned destination buffer. */
-	dst = (void *)((unsigned long)page_address(page) | 0x1);
-	/* Unalign src as well, but differently (off by 1 + 2 = 3). */
-	src = dst + (MISALIGNED_BUFFER_SIZE / 2);
-	src += 2;
-	word_cycles = -1ULL;
-	/* Do a warmup. */
-	__riscv_copy_words_unaligned(dst, src, MISALIGNED_COPY_SIZE);
-	preempt_disable();
-	start_jiffies = jiffies;
-	while ((now = jiffies) == start_jiffies)
-		cpu_relax();
-
-	/*
-	 * For a fixed amount of time, repeatedly try the function, and take
-	 * the best time in cycles as the measurement.
-	 */
-	while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) {
-		start_cycles = get_cycles64();
-		/* Ensure the CSR read can't reorder WRT to the copy. */
-		mb();
-		__riscv_copy_words_unaligned(dst, src, MISALIGNED_COPY_SIZE);
-		/* Ensure the copy ends before the end time is snapped. */
-		mb();
-		end_cycles = get_cycles64();
-		if ((end_cycles - start_cycles) < word_cycles)
-			word_cycles = end_cycles - start_cycles;
-	}
-
-	byte_cycles = -1ULL;
-	__riscv_copy_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE);
-	start_jiffies = jiffies;
-	while ((now = jiffies) == start_jiffies)
-		cpu_relax();
-
-	while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) {
-		start_cycles = get_cycles64();
-		mb();
-		__riscv_copy_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE);
-		mb();
-		end_cycles = get_cycles64();
-		if ((end_cycles - start_cycles) < byte_cycles)
-			byte_cycles = end_cycles - start_cycles;
-	}
-
-	preempt_enable();
-
-	/* Don't divide by zero. */
-	if (!word_cycles || !byte_cycles) {
-		pr_warn("cpu%d: rdtime lacks granularity needed to measure unaligned access speed\n",
-			cpu);
-
-		return 0;
-	}
-
-	if (word_cycles < byte_cycles)
-		speed = RISCV_HWPROBE_MISALIGNED_FAST;
-
-	ratio = div_u64((byte_cycles * 100), word_cycles);
-	pr_info("cpu%d: Ratio of byte access time to unaligned word access is %d.%02d, unaligned accesses are %s\n",
-		cpu,
-		ratio / 100,
-		ratio % 100,
-		(speed == RISCV_HWPROBE_MISALIGNED_FAST) ? "fast" : "slow");
-
-	per_cpu(misaligned_access_speed, cpu) = speed;
-
-	/*
-	 * Set the value of fast_misaligned_access of a CPU. These operations
-	 * are atomic to avoid race conditions.
-	 */
-	if (speed == RISCV_HWPROBE_MISALIGNED_FAST)
-		cpumask_set_cpu(cpu, &fast_misaligned_access);
-	else
-		cpumask_clear_cpu(cpu, &fast_misaligned_access);
-
-	return 0;
-}
-
-static void check_unaligned_access_nonboot_cpu(void *param)
-{
-	unsigned int cpu = smp_processor_id();
-	struct page **pages = param;
-
-	if (smp_processor_id() != 0)
-		check_unaligned_access(pages[cpu]);
-}
-
-DEFINE_STATIC_KEY_FALSE(fast_misaligned_access_speed_key);
-
-static void modify_unaligned_access_branches(cpumask_t *mask, int weight)
-{
-	if (cpumask_weight(mask) == weight)
-		static_branch_enable_cpuslocked(&fast_misaligned_access_speed_key);
-	else
-		static_branch_disable_cpuslocked(&fast_misaligned_access_speed_key);
-}
-
-static void set_unaligned_access_static_branches_except_cpu(int cpu)
-{
-	/*
-	 * Same as set_unaligned_access_static_branches, except excludes the
-	 * given CPU from the result. When a CPU is hotplugged into an offline
-	 * state, this function is called before the CPU is set to offline in
-	 * the cpumask, and thus the CPU needs to be explicitly excluded.
-	 */
-
-	cpumask_t fast_except_me;
-
-	cpumask_and(&fast_except_me, &fast_misaligned_access, cpu_online_mask);
-	cpumask_clear_cpu(cpu, &fast_except_me);
-
-	modify_unaligned_access_branches(&fast_except_me, num_online_cpus() - 1);
-}
-
-static void set_unaligned_access_static_branches(void)
-{
-	/*
-	 * This will be called after check_unaligned_access_all_cpus so the
-	 * result of unaligned access speed for all CPUs will be available.
-	 *
-	 * To avoid the number of online cpus changing between reading
-	 * cpu_online_mask and calling num_online_cpus, cpus_read_lock must be
-	 * held before calling this function.
-	 */
-
-	cpumask_t fast_and_online;
-
-	cpumask_and(&fast_and_online, &fast_misaligned_access, cpu_online_mask);
-
-	modify_unaligned_access_branches(&fast_and_online, num_online_cpus());
-}
-
-static int lock_and_set_unaligned_access_static_branch(void)
-{
-	cpus_read_lock();
-	set_unaligned_access_static_branches();
-	cpus_read_unlock();
-
-	return 0;
-}
-
-arch_initcall_sync(lock_and_set_unaligned_access_static_branch);
-
-static int riscv_online_cpu(unsigned int cpu)
-{
-	static struct page *buf;
-
-	/* We are already set since the last check */
-	if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_UNKNOWN)
-		goto exit;
-
-	buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
-	if (!buf) {
-		pr_warn("Allocation failure, not measuring misaligned performance\n");
-		return -ENOMEM;
-	}
-
-	check_unaligned_access(buf);
-	__free_pages(buf, MISALIGNED_BUFFER_ORDER);
-
-exit:
-	set_unaligned_access_static_branches();
-
-	return 0;
-}
-
-static int riscv_offline_cpu(unsigned int cpu)
-{
-	set_unaligned_access_static_branches_except_cpu(cpu);
-
-	return 0;
-}
-
-/* Measure unaligned access on all CPUs present at boot in parallel. */
-static int check_unaligned_access_all_cpus(void)
-{
-	unsigned int cpu;
-	unsigned int cpu_count = num_possible_cpus();
-	struct page **bufs = kzalloc(cpu_count * sizeof(struct page *),
-				     GFP_KERNEL);
-
-	if (!bufs) {
-		pr_warn("Allocation failure, not measuring misaligned performance\n");
-		return 0;
-	}
-
-	/*
-	 * Allocate separate buffers for each CPU so there's no fighting over
-	 * cache lines.
-	 */
-	for_each_cpu(cpu, cpu_online_mask) {
-		bufs[cpu] = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
-		if (!bufs[cpu]) {
-			pr_warn("Allocation failure, not measuring misaligned performance\n");
-			goto out;
-		}
-	}
-
-	/* Check everybody except 0, who stays behind to tend jiffies. */
-	on_each_cpu(check_unaligned_access_nonboot_cpu, bufs, 1);
-
-	/* Check core 0. */
-	smp_call_on_cpu(0, check_unaligned_access, bufs[0], true);
-
-	/*
-	 * Setup hotplug callbacks for any new CPUs that come online or go
-	 * offline.
-	 */
-	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online",
-				  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);
-	}
-
-	kfree(bufs);
-	return 0;
-}
-
-arch_initcall(check_unaligned_access_all_cpus);
-
 void riscv_user_isa_enable(void)
 {
 	if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_ZICBOZ))
diff --git a/arch/riscv/kernel/misaligned_access_speed.c b/arch/riscv/kernel/misaligned_access_speed.c
new file mode 100644
index 000000000000..b725c07dd1af
--- /dev/null
+++ b/arch/riscv/kernel/misaligned_access_speed.c
@@ -0,0 +1,265 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2024 Rivos Inc.
+ */
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/jump_label.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/types.h>
+#include <asm/cpufeature.h>
+#include <asm/hwprobe.h>
+
+#include "copy-unaligned.h"
+
+#define MISALIGNED_ACCESS_JIFFIES_LG2 1
+#define MISALIGNED_BUFFER_SIZE 0x4000
+#define MISALIGNED_BUFFER_ORDER get_order(MISALIGNED_BUFFER_SIZE)
+#define MISALIGNED_COPY_SIZE ((MISALIGNED_BUFFER_SIZE / 2) - 0x80)
+
+DEFINE_PER_CPU(long, misaligned_access_speed);
+
+static cpumask_t fast_misaligned_access;
+
+static int check_unaligned_access(void *param)
+{
+	int cpu = smp_processor_id();
+	u64 start_cycles, end_cycles;
+	u64 word_cycles;
+	u64 byte_cycles;
+	int ratio;
+	unsigned long start_jiffies, now;
+	struct page *page = param;
+	void *dst;
+	void *src;
+	long speed = RISCV_HWPROBE_MISALIGNED_SLOW;
+
+	if (check_unaligned_access_emulated(cpu))
+		return 0;
+
+	/* Make an unaligned destination buffer. */
+	dst = (void *)((unsigned long)page_address(page) | 0x1);
+	/* Unalign src as well, but differently (off by 1 + 2 = 3). */
+	src = dst + (MISALIGNED_BUFFER_SIZE / 2);
+	src += 2;
+	word_cycles = -1ULL;
+	/* Do a warmup. */
+	__riscv_copy_words_unaligned(dst, src, MISALIGNED_COPY_SIZE);
+	preempt_disable();
+	start_jiffies = jiffies;
+	while ((now = jiffies) == start_jiffies)
+		cpu_relax();
+
+	/*
+	 * For a fixed amount of time, repeatedly try the function, and take
+	 * the best time in cycles as the measurement.
+	 */
+	while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) {
+		start_cycles = get_cycles64();
+		/* Ensure the CSR read can't reorder WRT to the copy. */
+		mb();
+		__riscv_copy_words_unaligned(dst, src, MISALIGNED_COPY_SIZE);
+		/* Ensure the copy ends before the end time is snapped. */
+		mb();
+		end_cycles = get_cycles64();
+		if ((end_cycles - start_cycles) < word_cycles)
+			word_cycles = end_cycles - start_cycles;
+	}
+
+	byte_cycles = -1ULL;
+	__riscv_copy_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE);
+	start_jiffies = jiffies;
+	while ((now = jiffies) == start_jiffies)
+		cpu_relax();
+
+	while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) {
+		start_cycles = get_cycles64();
+		mb();
+		__riscv_copy_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE);
+		mb();
+		end_cycles = get_cycles64();
+		if ((end_cycles - start_cycles) < byte_cycles)
+			byte_cycles = end_cycles - start_cycles;
+	}
+
+	preempt_enable();
+
+	/* Don't divide by zero. */
+	if (!word_cycles || !byte_cycles) {
+		pr_warn("cpu%d: rdtime lacks granularity needed to measure unaligned access speed\n",
+			cpu);
+
+		return 0;
+	}
+
+	if (word_cycles < byte_cycles)
+		speed = RISCV_HWPROBE_MISALIGNED_FAST;
+
+	ratio = div_u64((byte_cycles * 100), word_cycles);
+	pr_info("cpu%d: Ratio of byte access time to unaligned word access is %d.%02d, unaligned accesses are %s\n",
+		cpu,
+		ratio / 100,
+		ratio % 100,
+		(speed == RISCV_HWPROBE_MISALIGNED_FAST) ? "fast" : "slow");
+
+	per_cpu(misaligned_access_speed, cpu) = speed;
+
+	/*
+	 * Set the value of fast_misaligned_access of a CPU. These operations
+	 * are atomic to avoid race conditions.
+	 */
+	if (speed == RISCV_HWPROBE_MISALIGNED_FAST)
+		cpumask_set_cpu(cpu, &fast_misaligned_access);
+	else
+		cpumask_clear_cpu(cpu, &fast_misaligned_access);
+
+	return 0;
+}
+
+static void check_unaligned_access_nonboot_cpu(void *param)
+{
+	unsigned int cpu = smp_processor_id();
+	struct page **pages = param;
+
+	if (smp_processor_id() != 0)
+		check_unaligned_access(pages[cpu]);
+}
+
+DEFINE_STATIC_KEY_FALSE(fast_misaligned_access_speed_key);
+
+static void modify_unaligned_access_branches(cpumask_t *mask, int weight)
+{
+	if (cpumask_weight(mask) == weight)
+		static_branch_enable_cpuslocked(&fast_misaligned_access_speed_key);
+	else
+		static_branch_disable_cpuslocked(&fast_misaligned_access_speed_key);
+}
+
+static void set_unaligned_access_static_branches_except_cpu(int cpu)
+{
+	/*
+	 * Same as set_unaligned_access_static_branches, except excludes the
+	 * given CPU from the result. When a CPU is hotplugged into an offline
+	 * state, this function is called before the CPU is set to offline in
+	 * the cpumask, and thus the CPU needs to be explicitly excluded.
+	 */
+
+	cpumask_t fast_except_me;
+
+	cpumask_and(&fast_except_me, &fast_misaligned_access, cpu_online_mask);
+	cpumask_clear_cpu(cpu, &fast_except_me);
+
+	modify_unaligned_access_branches(&fast_except_me, num_online_cpus() - 1);
+}
+
+static void set_unaligned_access_static_branches(void)
+{
+	/*
+	 * This will be called after check_unaligned_access_all_cpus so the
+	 * result of unaligned access speed for all CPUs will be available.
+	 *
+	 * To avoid the number of online cpus changing between reading
+	 * cpu_online_mask and calling num_online_cpus, cpus_read_lock must be
+	 * held before calling this function.
+	 */
+
+	cpumask_t fast_and_online;
+
+	cpumask_and(&fast_and_online, &fast_misaligned_access, cpu_online_mask);
+
+	modify_unaligned_access_branches(&fast_and_online, num_online_cpus());
+}
+
+static int lock_and_set_unaligned_access_static_branch(void)
+{
+	cpus_read_lock();
+	set_unaligned_access_static_branches();
+	cpus_read_unlock();
+
+	return 0;
+}
+
+arch_initcall_sync(lock_and_set_unaligned_access_static_branch);
+
+static int riscv_online_cpu(unsigned int cpu)
+{
+	static struct page *buf;
+
+	/* We are already set since the last check */
+	if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_UNKNOWN)
+		goto exit;
+
+	buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
+	if (!buf) {
+		pr_warn("Allocation failure, not measuring misaligned performance\n");
+		return -ENOMEM;
+	}
+
+	check_unaligned_access(buf);
+	__free_pages(buf, MISALIGNED_BUFFER_ORDER);
+
+exit:
+	set_unaligned_access_static_branches();
+
+	return 0;
+}
+
+static int riscv_offline_cpu(unsigned int cpu)
+{
+	set_unaligned_access_static_branches_except_cpu(cpu);
+
+	return 0;
+}
+
+/* Measure unaligned access on all CPUs present at boot in parallel. */
+static int check_unaligned_access_all_cpus(void)
+{
+	unsigned int cpu;
+	unsigned int cpu_count = num_possible_cpus();
+	struct page **bufs = kzalloc(cpu_count * sizeof(struct page *),
+				     GFP_KERNEL);
+
+	if (!bufs) {
+		pr_warn("Allocation failure, not measuring misaligned performance\n");
+		return 0;
+	}
+
+	/*
+	 * Allocate separate buffers for each CPU so there's no fighting over
+	 * cache lines.
+	 */
+	for_each_cpu(cpu, cpu_online_mask) {
+		bufs[cpu] = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
+		if (!bufs[cpu]) {
+			pr_warn("Allocation failure, not measuring misaligned performance\n");
+			goto out;
+		}
+	}
+
+	/* Check everybody except 0, who stays behind to tend jiffies. */
+	on_each_cpu(check_unaligned_access_nonboot_cpu, bufs, 1);
+
+	/* Check core 0. */
+	smp_call_on_cpu(0, check_unaligned_access, bufs[0], true);
+
+	/*
+	 * Setup hotplug callbacks for any new CPUs that come online or go
+	 * offline.
+	 */
+	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online",
+				  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);
+	}
+
+	kfree(bufs);
+	return 0;
+}
+
+arch_initcall(check_unaligned_access_all_cpus);
diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c
index a7c56b41efd2..3f1a6edfdb08 100644
--- a/arch/riscv/kernel/sys_hwprobe.c
+++ b/arch/riscv/kernel/sys_hwprobe.c
@@ -149,6 +149,7 @@ static bool hwprobe_ext0_has(const struct cpumask *cpus, unsigned long ext)
 
 static u64 hwprobe_misaligned(const struct cpumask *cpus)
 {
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 	int cpu;
 	u64 perf = -1ULL;
 
@@ -168,6 +169,9 @@ static u64 hwprobe_misaligned(const struct cpumask *cpus)
 		return RISCV_HWPROBE_MISALIGNED_UNKNOWN;
 
 	return perf;
+#else
+	return RISCV_HWPROBE_MISALIGNED_FAST;
+#endif
 }
 
 static void hwprobe_one_pair(struct riscv_hwprobe *pair,

-- 
2.43.0

Re: [PATCH v2 2/2] riscv: Disable misaligned access probe when CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS

[Elliot Berman]

Hi Charlie,

On Thu, Feb 01, 2024 at 03:30:46PM -0800, Charlie Jenkins wrote:
> When CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS is selected, the cpus can be
> set to have fast misaligned access without needing to probe.
> 
> Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
> ---
>  arch/riscv/Kconfig                               |   1 +
>  arch/riscv/include/asm/cpufeature.h              |   7 +
>  arch/riscv/include/asm/misaligned_access_speed.h |  29 +++
>  arch/riscv/kernel/Makefile                       |   3 +
>  arch/riscv/kernel/cpufeature.c                   | 255 ----------------------
>  arch/riscv/kernel/misaligned_access_speed.c      | 265 +++++++++++++++++++++++
>  arch/riscv/kernel/sys_hwprobe.c                  |   4 +
>  7 files changed, 309 insertions(+), 255 deletions(-)
> 
> diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
> index f71910718053..8be7f17da9ab 100644
> --- a/arch/riscv/kernel/Makefile
> +++ b/arch/riscv/kernel/Makefile
> @@ -62,6 +62,9 @@ obj-y	+= tests/
>  obj-$(CONFIG_MMU) += vdso.o vdso/
>  
>  obj-$(CONFIG_RISCV_MISALIGNED)	+= traps_misaligned.o
> +ifneq ($(RISCV_EFFICIENT_UNALIGNED_ACCESS), y)

Should this be CONFIG_RISCV_EFFICIENT_UNALIGNED_ACCESS ?

> +obj-y	+= misaligned_access_speed.o
> +endif
>  obj-$(CONFIG_FPU)		+= fpu.o
>  obj-$(CONFIG_RISCV_ISA_V)	+= vector.o
>  obj-$(CONFIG_RISCV_ISA_V)	+= kernel_mode_vector.o

Re: [PATCH v2 2/2] riscv: Disable misaligned access probe when CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS

[Charlie Jenkins]

On Thu, Feb 01, 2024 at 08:31:10PM -0800, Elliot Berman wrote:
> Hi Charlie,
> 
> On Thu, Feb 01, 2024 at 03:30:46PM -0800, Charlie Jenkins wrote:
> > When CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS is selected, the cpus can be
> > set to have fast misaligned access without needing to probe.
> > 
> > Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
> > ---
> >  arch/riscv/Kconfig                               |   1 +
> >  arch/riscv/include/asm/cpufeature.h              |   7 +
> >  arch/riscv/include/asm/misaligned_access_speed.h |  29 +++
> >  arch/riscv/kernel/Makefile                       |   3 +
> >  arch/riscv/kernel/cpufeature.c                   | 255 ----------------------
> >  arch/riscv/kernel/misaligned_access_speed.c      | 265 +++++++++++++++++++++++
> >  arch/riscv/kernel/sys_hwprobe.c                  |   4 +
> >  7 files changed, 309 insertions(+), 255 deletions(-)
> > 
> > diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
> > index f71910718053..8be7f17da9ab 100644
> > --- a/arch/riscv/kernel/Makefile
> > +++ b/arch/riscv/kernel/Makefile
> > @@ -62,6 +62,9 @@ obj-y	+= tests/
> >  obj-$(CONFIG_MMU) += vdso.o vdso/
> >  
> >  obj-$(CONFIG_RISCV_MISALIGNED)	+= traps_misaligned.o
> > +ifneq ($(RISCV_EFFICIENT_UNALIGNED_ACCESS), y)
> 
> Should this be CONFIG_RISCV_EFFICIENT_UNALIGNED_ACCESS ?

Oh thank you Elliot! Yes it is. I was going back and forth on whether I
wanted this to be CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS or
CONFIG_RISCV_EFFICIENT_UNALIGNED_ACCESS and I must have mistyped when I
was changing it. I settled on CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
everywhere else so this should also use that instead. These two configs
are effectively the same since the only way to select
CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS is by selecting
CONFIG_RISCV_EFFICIENT_UNALIGNED_ACCESS.

- Charlie

> 
> > +obj-y	+= misaligned_access_speed.o
> > +endif
> >  obj-$(CONFIG_FPU)		+= fpu.o
> >  obj-$(CONFIG_RISCV_ISA_V)	+= vector.o
> >  obj-$(CONFIG_RISCV_ISA_V)	+= kernel_mode_vector.o

Re: [PATCH v2 1/2] riscv: lib: Introduce has_fast_misaligned_access function

[Eric Biggers]

On Thu, Feb 01, 2024 at 03:30:45PM -0800, Charlie Jenkins wrote:
> -	if (((unsigned long)buff & OFFSET_MASK) == 0)
> +	if (has_fast_misaligned_accesses() || (((unsigned long)buff & OFFSET_MASK) == 0b101))
>  		return do_csum_no_alignment(buff, len);

Why did the 0 change into 0b101?

- Eric

Re: [PATCH v2 2/2] riscv: Disable misaligned access probe when CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS

[Eric Biggers]

On Thu, Feb 01, 2024 at 03:30:46PM -0800, Charlie Jenkins wrote:
> diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
> index eb3ac304fc42..3a29d8e30e05 100644
> --- a/arch/riscv/include/asm/cpufeature.h
> +++ b/arch/riscv/include/asm/cpufeature.h
> @@ -51,6 +51,7 @@ static inline bool check_unaligned_access_emulated(int cpu)
>  static inline void unaligned_emulation_finish(void) {}
>  #endif
>  
> +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS

#ifdef..#else..#endif is more readable than #ifndef..#else..#endif.

> diff --git a/arch/riscv/include/asm/misaligned_access_speed.h b/arch/riscv/include/asm/misaligned_access_speed.h
> new file mode 100644
> index 000000000000..81df2aa6fa6b
> --- /dev/null
> +++ b/arch/riscv/include/asm/misaligned_access_speed.h

This new header file isn't included from anywhere.

> diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
> index f71910718053..8be7f17da9ab 100644
> --- a/arch/riscv/kernel/Makefile
> +++ b/arch/riscv/kernel/Makefile
> @@ -62,6 +62,9 @@ obj-y	+= tests/
>  obj-$(CONFIG_MMU) += vdso.o vdso/
>  
>  obj-$(CONFIG_RISCV_MISALIGNED)	+= traps_misaligned.o
> +ifneq ($(RISCV_EFFICIENT_UNALIGNED_ACCESS), y)
> +obj-y	+= misaligned_access_speed.o
> +endif

CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS

> diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c
> index a7c56b41efd2..3f1a6edfdb08 100644
> --- a/arch/riscv/kernel/sys_hwprobe.c
> +++ b/arch/riscv/kernel/sys_hwprobe.c
> @@ -149,6 +149,7 @@ static bool hwprobe_ext0_has(const struct cpumask *cpus, unsigned long ext)
>  
>  static u64 hwprobe_misaligned(const struct cpumask *cpus)
>  {
> +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
>  	int cpu;
>  	u64 perf = -1ULL;
>  
> @@ -168,6 +169,9 @@ static u64 hwprobe_misaligned(const struct cpumask *cpus)
>  		return RISCV_HWPROBE_MISALIGNED_UNKNOWN;
>  
>  	return perf;
> +#else
> +	return RISCV_HWPROBE_MISALIGNED_FAST;
> +#endif

#ifdef..#else..#endif is more readable than #ifndef..#else..#endif.

- Eric

Re: [PATCH v2 1/2] riscv: lib: Introduce has_fast_misaligned_access function

[Charlie Jenkins]

On Fri, Feb 02, 2024 at 02:49:39PM -0800, Eric Biggers wrote:
> On Thu, Feb 01, 2024 at 03:30:45PM -0800, Charlie Jenkins wrote:
> > -	if (((unsigned long)buff & OFFSET_MASK) == 0)
> > +	if (has_fast_misaligned_accesses() || (((unsigned long)buff & OFFSET_MASK) == 0b101))
> >  		return do_csum_no_alignment(buff, len);
> 
> Why did the 0 change into 0b101?
> 
> - Eric

Whoops, thank you.

- Charlie

Re: [PATCH v2 2/2] riscv: Disable misaligned access probe when CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS

[Charlie Jenkins]

On Fri, Feb 02, 2024 at 03:01:01PM -0800, Eric Biggers wrote:
> On Thu, Feb 01, 2024 at 03:30:46PM -0800, Charlie Jenkins wrote:
> > diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
> > index eb3ac304fc42..3a29d8e30e05 100644
> > --- a/arch/riscv/include/asm/cpufeature.h
> > +++ b/arch/riscv/include/asm/cpufeature.h
> > @@ -51,6 +51,7 @@ static inline bool check_unaligned_access_emulated(int cpu)
> >  static inline void unaligned_emulation_finish(void) {}
> >  #endif
> >  
> > +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
> 
> #ifdef..#else..#endif is more readable than #ifndef..#else..#endif.
> 
> > diff --git a/arch/riscv/include/asm/misaligned_access_speed.h b/arch/riscv/include/asm/misaligned_access_speed.h
> > new file mode 100644
> > index 000000000000..81df2aa6fa6b
> > --- /dev/null
> > +++ b/arch/riscv/include/asm/misaligned_access_speed.h
> 
> This new header file isn't included from anywhere.
> 

I thought I deleted that...

> > diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
> > index f71910718053..8be7f17da9ab 100644
> > --- a/arch/riscv/kernel/Makefile
> > +++ b/arch/riscv/kernel/Makefile
> > @@ -62,6 +62,9 @@ obj-y	+= tests/
> >  obj-$(CONFIG_MMU) += vdso.o vdso/
> >  
> >  obj-$(CONFIG_RISCV_MISALIGNED)	+= traps_misaligned.o
> > +ifneq ($(RISCV_EFFICIENT_UNALIGNED_ACCESS), y)
> > +obj-y	+= misaligned_access_speed.o
> > +endif
> 
> CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
> 
> > diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c
> > index a7c56b41efd2..3f1a6edfdb08 100644
> > --- a/arch/riscv/kernel/sys_hwprobe.c
> > +++ b/arch/riscv/kernel/sys_hwprobe.c
> > @@ -149,6 +149,7 @@ static bool hwprobe_ext0_has(const struct cpumask *cpus, unsigned long ext)
> >  
> >  static u64 hwprobe_misaligned(const struct cpumask *cpus)
> >  {
> > +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
> >  	int cpu;
> >  	u64 perf = -1ULL;
> >  
> > @@ -168,6 +169,9 @@ static u64 hwprobe_misaligned(const struct cpumask *cpus)
> >  		return RISCV_HWPROBE_MISALIGNED_UNKNOWN;
> >  
> >  	return perf;
> > +#else
> > +	return RISCV_HWPROBE_MISALIGNED_FAST;
> > +#endif
> 
> #ifdef..#else..#endif is more readable than #ifndef..#else..#endif.
> 
> - Eric

Thanks for pointing these out, I will send a v3.

- Charlie