[PW_SID:966141] Optimize GCD performance on RISC-V by selecting implementation at runtime

arch/riscv/Kconfig

@@ -95,6 +95,7 @@ config RISCV
 	select CLINT_TIMER if RISCV_M_MODE
 	select CLONE_BACKWARDS
 	select COMMON_CLK
+	select CPU_NO_EFFICIENT_FFS if !RISCV_ISA_ZBB
 	select CPU_PM if CPU_IDLE || HIBERNATION || SUSPEND
 	select EDAC_SUPPORT
 	select FRAME_POINTER if PERF_EVENTS || (FUNCTION_TRACER && !DYNAMIC_FTRACE)

arch/riscv/kernel/setup.c

@@ -21,6 +21,7 @@
 #include <linux/efi.h>
 #include <linux/crash_dump.h>
 #include <linux/panic_notifier.h>
+#include <linux/jump_label.h>
 
 #include <asm/acpi.h>
 #include <asm/alternative.h>
@@ -51,6 +52,8 @@ atomic_t hart_lottery __section(".sdata")
 ;
 unsigned long boot_cpu_hartid;
 
+DECLARE_STATIC_KEY_TRUE(efficient_ffs_key);
+
 /*
  * Place kernel memory regions on the resource tree so that
  * kexec-tools can retrieve them from /proc/iomem. While there
@@ -361,6 +364,9 @@ void __init setup_arch(char **cmdline_p)
 
 	riscv_user_isa_enable();
 	riscv_spinlock_init();
+
+	if (!IS_ENABLED(CONFIG_RISCV_ISA_ZBB) || !riscv_isa_extension_available(NULL, ZBB))
+		static_branch_disable(&efficient_ffs_key);
 }
 
 bool arch_cpu_is_hotpluggable(int cpu)

lib/math/gcd.c

@@ -2,6 +2,7 @@
 #include <linux/kernel.h>
 #include <linux/gcd.h>
 #include <linux/export.h>
+#include <linux/jump_label.h>
 
 /*
  * This implements the binary GCD algorithm. (Often attributed to Stein,
@@ -11,16 +12,13 @@
  * has decent hardware division.
  */
 
+DEFINE_STATIC_KEY_TRUE(efficient_ffs_key);
+
 #if !defined(CONFIG_CPU_NO_EFFICIENT_FFS)
 
 /* If __ffs is available, the even/odd algorithm benchmarks slower. */
 
-/**
- * gcd - calculate and return the greatest common divisor of 2 unsigned longs
- * @a: first value
- * @b: second value
- */
-unsigned long gcd(unsigned long a, unsigned long b)
+static unsigned long binary_gcd(unsigned long a, unsigned long b)
 {
 	unsigned long r = a | b;
 
@@ -44,16 +42,27 @@ unsigned long gcd(unsigned long a, unsigned long b)
 	}
 }
 
-#else
+#endif
 
 /* If normalization is done by loops, the even/odd algorithm is a win. */
+
+/**
+ * gcd - calculate and return the greatest common divisor of 2 unsigned longs
+ * @a: first value
+ * @b: second value
+ */
 unsigned long gcd(unsigned long a, unsigned long b)
 {
 	unsigned long r = a | b;
 
 	if (!a || !b)
 		return r;
 
+#if !defined(CONFIG_CPU_NO_EFFICIENT_FFS)
+	if (static_branch_likely(&efficient_ffs_key))
+		return binary_gcd(a, b);
+#endif
+
 	/* Isolate lsbit of r */
 	r &= -r;
 
@@ -80,6 +89,4 @@ unsigned long gcd(unsigned long a, unsigned long b)
 	}
 }
 
-#endif
-
 EXPORT_SYMBOL_GPL(gcd);