From: Nicolas Pitre <nicolas.pitre@linaro.org>
Date: Sat, 12 Dec 2015 01:49:21 +0000 (+0100)
Subject: ARM: 8477/1: runtime patch udiv/sdiv instructions into __aeabi_{u}idiv()
X-Git-Url: https://git.karo-electronics.de/?a=commitdiff_plain;h=42f25bddd0a226d2431e057b9e01c5cc61067e12;p=linux-beck.git

ARM: 8477/1: runtime patch udiv/sdiv instructions into __aeabi_{u}idiv()

The ARM compiler inserts calls to __aeabi_idiv() and
__aeabi_uidiv() when it needs to perform division on signed and
unsigned integers. If a processor has support for the sdiv and
udiv instructions, the kernel may overwrite the beginning of those
functions with those instructions and a "bx lr" to get better
performance.

To ensure that those functions are aligned to a 32-bit word for easier
patching (which might not always be the case in Thumb mode) and that
the two patched instructions end up in the same cache line, a 8-byte
alignment is enforced when ARM_PATCH_IDIV is selected.

This was heavily inspired by a previous patch from Stephen Boyd.

Signed-off-by: Nicolas Pitre <nico@linaro.org>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 9f1eeb2e7d75..6e644fd68ad2 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1603,6 +1603,24 @@ config THUMB2_AVOID_R_ARM_THM_JUMP11
 config ARM_ASM_UNIFIED
 	bool
 
+config ARM_PATCH_IDIV
+	bool "Runtime patch udiv/sdiv instructions into __aeabi_{u}idiv()"
+	depends on CPU_32v7 && !XIP_KERNEL
+	default y
+	help
+	  The ARM compiler inserts calls to __aeabi_idiv() and
+	  __aeabi_uidiv() when it needs to perform division on signed
+	  and unsigned integers. Some v7 CPUs have support for the sdiv
+	  and udiv instructions that can be used to implement those
+	  functions.
+
+	  Enabling this option allows the kernel to modify itself to
+	  replace the first two instructions of these library functions
+	  with the sdiv or udiv plus "bx lr" instructions when the CPU
+	  it is running on supports them. Typically this will be faster
+	  and less power intensive than running the original library
+	  code to do integer division.
+
 config AEABI
 	bool "Use the ARM EABI to compile the kernel"
 	help
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 20edd349d379..e07f567487cd 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -375,6 +375,72 @@ void __init early_print(const char *str, ...)
 	printk("%s", buf);
 }
 
+#ifdef CONFIG_ARM_PATCH_IDIV
+
+static inline u32 __attribute_const__ sdiv_instruction(void)
+{
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
+		/* "sdiv r0, r0, r1" */
+		u32 insn = __opcode_thumb32_compose(0xfb90, 0xf0f1);
+		return __opcode_to_mem_thumb32(insn);
+	}
+
+	/* "sdiv r0, r0, r1" */
+	return __opcode_to_mem_arm(0xe710f110);
+}
+
+static inline u32 __attribute_const__ udiv_instruction(void)
+{
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
+		/* "udiv r0, r0, r1" */
+		u32 insn = __opcode_thumb32_compose(0xfbb0, 0xf0f1);
+		return __opcode_to_mem_thumb32(insn);
+	}
+
+	/* "udiv r0, r0, r1" */
+	return __opcode_to_mem_arm(0xe730f110);
+}
+
+static inline u32 __attribute_const__ bx_lr_instruction(void)
+{
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
+		/* "bx lr; nop" */
+		u32 insn = __opcode_thumb32_compose(0x4770, 0x46c0);
+		return __opcode_to_mem_thumb32(insn);
+	}
+
+	/* "bx lr" */
+	return __opcode_to_mem_arm(0xe12fff1e);
+}
+
+static void __init patch_aeabi_idiv(void)
+{
+	extern void __aeabi_uidiv(void);
+	extern void __aeabi_idiv(void);
+	uintptr_t fn_addr;
+	unsigned int mask;
+
+	mask = IS_ENABLED(CONFIG_THUMB2_KERNEL) ? HWCAP_IDIVT : HWCAP_IDIVA;
+	if (!(elf_hwcap & mask))
+		return;
+
+	pr_info("CPU: div instructions available: patching division code\n");
+
+	fn_addr = ((uintptr_t)&__aeabi_uidiv) & ~1;
+	((u32 *)fn_addr)[0] = udiv_instruction();
+	((u32 *)fn_addr)[1] = bx_lr_instruction();
+	flush_icache_range(fn_addr, fn_addr + 8);
+
+	fn_addr = ((uintptr_t)&__aeabi_idiv) & ~1;
+	((u32 *)fn_addr)[0] = sdiv_instruction();
+	((u32 *)fn_addr)[1] = bx_lr_instruction();
+	flush_icache_range(fn_addr, fn_addr + 8);
+}
+
+#else
+static inline void patch_aeabi_idiv(void) { }
+#endif
+
 static void __init cpuid_init_hwcaps(void)
 {
 	int block;
@@ -642,6 +708,7 @@ static void __init setup_processor(void)
 	elf_hwcap = list->elf_hwcap;
 
 	cpuid_init_hwcaps();
+	patch_aeabi_idiv();
 
 #ifndef CONFIG_ARM_THUMB
 	elf_hwcap &= ~(HWCAP_THUMB | HWCAP_IDIVT);
diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib/lib1funcs.S
index af2267f6a529..9397b2e532af 100644
--- a/arch/arm/lib/lib1funcs.S
+++ b/arch/arm/lib/lib1funcs.S
@@ -205,6 +205,10 @@ Boston, MA 02111-1307, USA.  */
 .endm
 
 
+#ifdef CONFIG_ARM_PATCH_IDIV
+	.align	3
+#endif
+
 ENTRY(__udivsi3)
 ENTRY(__aeabi_uidiv)
 UNWIND(.fnstart)
@@ -253,6 +257,10 @@ UNWIND(.fnstart)
 UNWIND(.fnend)
 ENDPROC(__umodsi3)
 
+#ifdef CONFIG_ARM_PATCH_IDIV
+	.align 3
+#endif
+
 ENTRY(__divsi3)
 ENTRY(__aeabi_idiv)
 UNWIND(.fnstart)