From mboxrd@z Thu Jan 1 00:00:00 1970 From: Stephen Boyd Subject: Re: [RFC/PATCH 3/3] ARM: Replace calls to __aeabi_{u}idiv with udiv/sdiv instructions Date: Mon, 23 Nov 2015 12:49:55 -0800 Message-ID: <20151123204955.GC19156@codeaurora.org> References: <1448068997-26631-1-git-send-email-sboyd@codeaurora.org> <1448068997-26631-4-git-send-email-sboyd@codeaurora.org> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: Content-Disposition: inline In-Reply-To: Sender: linux-kernel-owner@vger.kernel.org To: =?iso-8859-1?Q?M=E5ns_Rullg=E5rd?= Cc: linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org, linux-arm-msm@vger.kernel.org, Nicolas Pitre , Arnd Bergmann , Steven Rostedt List-Id: linux-arm-msm@vger.kernel.org On 11/21, M=E5ns Rullg=E5rd wrote: > Stephen Boyd writes: >=20 > > +static int module_patch_aeabi_uidiv(unsigned long loc, const Elf32= _Sym *sym) > > +{ > > + extern char __aeabi_uidiv[], __aeabi_idiv[]; > > + unsigned long udiv_addr =3D (unsigned long)__aeabi_uidiv; > > + unsigned long sdiv_addr =3D (unsigned long)__aeabi_idiv; > > + unsigned int udiv_insn, sdiv_insn, mask; > > + > > + if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) { > > + mask =3D HWCAP_IDIVT; > > + udiv_insn =3D __opcode_to_mem_thumb32(0xfbb0f0f1); > > + sdiv_insn =3D __opcode_to_mem_thumb32(0xfb90f0f1); > > + } else { > > + mask =3D HWCAP_IDIVA; > > + udiv_insn =3D __opcode_to_mem_arm(0xe730f110); > > + sdiv_insn =3D __opcode_to_mem_arm(0xe710f110); > > + } > > + > > + if (elf_hwcap & mask) { > > + if (sym->st_value =3D=3D udiv_addr) { > > + *(u32 *)loc =3D udiv_insn; > > + return 1; > > + } else if (sym->st_value =3D=3D sdiv_addr) { > > + *(u32 *)loc =3D sdiv_insn; > > + return 1; > > + } > > + } > > + > > + return 0; > > +} >=20 > [...] >=20 > > +static void __init patch_aeabi_uidiv(void) > > +{ > > + extern unsigned long *__start_udiv_loc[], *__stop_udiv_loc[]; > > + extern unsigned long *__start_idiv_loc[], *__stop_idiv_loc[]; > > + unsigned long **p; > > + unsigned int udiv_insn, sdiv_insn, mask; > > + > > + if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) { > > + mask =3D HWCAP_IDIVT; > > + udiv_insn =3D __opcode_to_mem_thumb32(0xfbb0f0f1); > > + sdiv_insn =3D __opcode_to_mem_thumb32(0xfb90f0f1); > > + } else { > > + mask =3D HWCAP_IDIVA; > > + udiv_insn =3D __opcode_to_mem_arm(0xe730f110); > > + sdiv_insn =3D __opcode_to_mem_arm(0xe710f110); > > + } > > + > > + if (elf_hwcap & mask) { > > + for (p =3D __start_udiv_loc; p < __stop_udiv_loc; p++) { > > + unsigned long *inst =3D *p; > > + *inst =3D udiv_insn; > > + } > > + for (p =3D __start_idiv_loc; p < __stop_idiv_loc; p++) { > > + unsigned long *inst =3D *p; > > + *inst =3D sdiv_insn; > > + } > > + } > > +} >=20 > These functions are rather similar. Perhaps they could be combined > somehow. >=20 Yes. I have this patch on top, just haven't folded it in because it doesn't reduce the lines of code. ----8<---- =46rom: Stephen Boyd Subject: [PATCH] consolidate with module code Signed-off-by: Stephen Boyd --- arch/arm/include/asm/setup.h | 3 +++ arch/arm/kernel/module.c | 16 +++++-------- arch/arm/kernel/setup.c | 54 +++++++++++++++++++++++++++---------= -------- 3 files changed, 42 insertions(+), 31 deletions(-) diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.= h index e0adb9f1bf94..3f251cdb94ef 100644 --- a/arch/arm/include/asm/setup.h +++ b/arch/arm/include/asm/setup.h @@ -25,4 +25,7 @@ extern int arm_add_memory(u64 start, u64 size); extern void early_print(const char *str, ...); extern void dump_machine_table(void); =20 +extern void patch_uidiv(void *addr, size_t size); +extern void patch_idiv(void *addr, size_t size); + #endif diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c index 064e6ae60e08..684a68f1085b 100644 --- a/arch/arm/kernel/module.c +++ b/arch/arm/kernel/module.c @@ -22,6 +22,7 @@ =20 #include #include +#include #include #include #include @@ -58,24 +59,19 @@ static int module_patch_aeabi_uidiv(unsigned long l= oc, const Elf32_Sym *sym) extern char __aeabi_uidiv[], __aeabi_idiv[]; unsigned long udiv_addr =3D (unsigned long)__aeabi_uidiv; unsigned long sdiv_addr =3D (unsigned long)__aeabi_idiv; - unsigned int udiv_insn, sdiv_insn, mask; + unsigned int mask; =20 - if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) { + if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) mask =3D HWCAP_IDIVT; - udiv_insn =3D __opcode_to_mem_thumb32(0xfbb0f0f1); - sdiv_insn =3D __opcode_to_mem_thumb32(0xfb90f0f1); - } else { + else mask =3D HWCAP_IDIVA; - udiv_insn =3D __opcode_to_mem_arm(0xe730f110); - sdiv_insn =3D __opcode_to_mem_arm(0xe710f110); - } =20 if (elf_hwcap & mask) { if (sym->st_value =3D=3D udiv_addr) { - *(u32 *)loc =3D udiv_insn; + patch_uidiv(&loc, sizeof(loc)); return 1; } else if (sym->st_value =3D=3D sdiv_addr) { - *(u32 *)loc =3D sdiv_insn; + patch_idiv(&loc, sizeof(loc)); return 1; } } diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index d2a3d165dcae..cb86012c47d1 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -376,33 +376,45 @@ void __init early_print(const char *str, ...) } =20 #ifdef CONFIG_ARM_PATCH_UIDIV +static void __init_or_module patch(u32 **addr, size_t count, u32 insn) +{ + for (; count !=3D 0; count -=3D 4) + **addr++ =3D insn; +} + +void __init_or_module patch_uidiv(void *addr, size_t size) +{ + if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) + patch(addr, size, __opcode_to_mem_thumb32(0xfbb0f0f1)); + else + patch(addr, size, __opcode_to_mem_arm(0xe730f110)); + +} + +void __init_or_module patch_idiv(void *addr, size_t size) +{ + if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) + patch(addr, size, __opcode_to_mem_thumb32(0xfb90f0f1)); + else + patch(addr, size, __opcode_to_mem_arm(0xe710f110)); +} + static void __init patch_aeabi_uidiv(void) { - extern unsigned long *__start_udiv_loc[], *__stop_udiv_loc[]; - extern unsigned long *__start_idiv_loc[], *__stop_idiv_loc[]; - unsigned long **p; - unsigned int udiv_insn, sdiv_insn, mask; + extern char __start_udiv_loc[], __stop_udiv_loc[]; + extern char __start_idiv_loc[], __stop_idiv_loc[]; + unsigned int mask; =20 - if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) { + if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) mask =3D HWCAP_IDIVT; - udiv_insn =3D __opcode_to_mem_thumb32(0xfbb0f0f1); - sdiv_insn =3D __opcode_to_mem_thumb32(0xfb90f0f1); - } else { + else mask =3D HWCAP_IDIVA; - udiv_insn =3D __opcode_to_mem_arm(0xe730f110); - sdiv_insn =3D __opcode_to_mem_arm(0xe710f110); - } =20 - if (elf_hwcap & mask) { - for (p =3D __start_udiv_loc; p < __stop_udiv_loc; p++) { - unsigned long *inst =3D *p; - *inst =3D udiv_insn; - } - for (p =3D __start_idiv_loc; p < __stop_idiv_loc; p++) { - unsigned long *inst =3D *p; - *inst =3D sdiv_insn; - } - } + if (!(elf_hwcap & mask)) + return; + + patch_uidiv(__start_udiv_loc, __stop_udiv_loc - __start_udiv_loc); + patch_idiv(__start_idiv_loc, __stop_idiv_loc - __start_idiv_loc); } #else static void __init patch_aeabi_uidiv(void) { } --=20 Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum, a Linux Foundation Collaborative Project