Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755260AbbKWUyz (ORCPT ); Mon, 23 Nov 2015 15:54:55 -0500 Received: from unicorn.mansr.com ([81.2.72.234]:36181 "EHLO unicorn.mansr.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754524AbbKWUyx convert rfc822-to-8bit (ORCPT ); Mon, 23 Nov 2015 15:54:53 -0500 From: =?iso-8859-1?Q?M=E5ns_Rullg=E5rd?= To: Stephen Boyd Cc: linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org, linux-arm-msm@vger.kernel.org, Nicolas Pitre , Arnd Bergmann , Steven Rostedt Subject: Re: [RFC/PATCH 3/3] ARM: Replace calls to __aeabi_{u}idiv with udiv/sdiv instructions References: <1448068997-26631-1-git-send-email-sboyd@codeaurora.org> <1448068997-26631-4-git-send-email-sboyd@codeaurora.org> <20151123204955.GC19156@codeaurora.org> Date: Mon, 23 Nov 2015 20:54:48 +0000 In-Reply-To: <20151123204955.GC19156@codeaurora.org> (Stephen Boyd's message of "Mon, 23 Nov 2015 12:49:55 -0800") Message-ID: User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/24.5 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 7274 Lines: 226 Stephen Boyd writes: > On 11/21, M?ns Rullg?rd wrote: >> Stephen Boyd writes: >> >> > +static int module_patch_aeabi_uidiv(unsigned long loc, const Elf32_Sym *sym) >> > +{ >> > + extern char __aeabi_uidiv[], __aeabi_idiv[]; >> > + unsigned long udiv_addr = (unsigned long)__aeabi_uidiv; >> > + unsigned long sdiv_addr = (unsigned long)__aeabi_idiv; >> > + unsigned int udiv_insn, sdiv_insn, mask; >> > + >> > + if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) { >> > + mask = HWCAP_IDIVT; >> > + udiv_insn = __opcode_to_mem_thumb32(0xfbb0f0f1); >> > + sdiv_insn = __opcode_to_mem_thumb32(0xfb90f0f1); >> > + } else { >> > + mask = HWCAP_IDIVA; >> > + udiv_insn = __opcode_to_mem_arm(0xe730f110); >> > + sdiv_insn = __opcode_to_mem_arm(0xe710f110); >> > + } >> > + >> > + if (elf_hwcap & mask) { >> > + if (sym->st_value == udiv_addr) { >> > + *(u32 *)loc = udiv_insn; >> > + return 1; >> > + } else if (sym->st_value == sdiv_addr) { >> > + *(u32 *)loc = sdiv_insn; >> > + return 1; >> > + } >> > + } >> > + >> > + return 0; >> > +} >> >> [...] >> >> > +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 = HWCAP_IDIVT; >> > + udiv_insn = __opcode_to_mem_thumb32(0xfbb0f0f1); >> > + sdiv_insn = __opcode_to_mem_thumb32(0xfb90f0f1); >> > + } else { >> > + mask = HWCAP_IDIVA; >> > + udiv_insn = __opcode_to_mem_arm(0xe730f110); >> > + sdiv_insn = __opcode_to_mem_arm(0xe710f110); >> > + } >> > + >> > + if (elf_hwcap & mask) { >> > + for (p = __start_udiv_loc; p < __stop_udiv_loc; p++) { >> > + unsigned long *inst = *p; >> > + *inst = udiv_insn; >> > + } >> > + for (p = __start_idiv_loc; p < __stop_idiv_loc; p++) { >> > + unsigned long *inst = *p; >> > + *inst = sdiv_insn; >> > + } >> > + } >> > +} >> >> These functions are rather similar. Perhaps they could be combined >> somehow. >> > > Yes. I have this patch on top, just haven't folded it in because > it doesn't reduce the lines of code. I don't see any reason to split it anyhow. The end result isn't any harder to understand than the intermediate. > ----8<---- > From: 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); > > +extern void patch_uidiv(void *addr, size_t size); > +extern void patch_idiv(void *addr, size_t size); Why not call things sdiv and udiv like the actual instructions? > #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 @@ > > #include > #include > +#include > #include > #include > #include > @@ -58,24 +59,19 @@ static int module_patch_aeabi_uidiv(unsigned long loc, const Elf32_Sym *sym) > extern char __aeabi_uidiv[], __aeabi_idiv[]; > unsigned long udiv_addr = (unsigned long)__aeabi_uidiv; > unsigned long sdiv_addr = (unsigned long)__aeabi_idiv; > - unsigned int udiv_insn, sdiv_insn, mask; > + unsigned int mask; > > - if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) { > + if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) > mask = HWCAP_IDIVT; > - udiv_insn = __opcode_to_mem_thumb32(0xfbb0f0f1); > - sdiv_insn = __opcode_to_mem_thumb32(0xfb90f0f1); > - } else { > + else > mask = HWCAP_IDIVA; > - udiv_insn = __opcode_to_mem_arm(0xe730f110); > - sdiv_insn = __opcode_to_mem_arm(0xe710f110); > - } > > if (elf_hwcap & mask) { > if (sym->st_value == udiv_addr) { > - *(u32 *)loc = udiv_insn; > + patch_uidiv(&loc, sizeof(loc)); > return 1; > } else if (sym->st_value == sdiv_addr) { > - *(u32 *)loc = 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, ...) > } > > #ifdef CONFIG_ARM_PATCH_UIDIV > +static void __init_or_module patch(u32 **addr, size_t count, u32 insn) > +{ > + for (; count != 0; count -= 4) > + **addr++ = 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; > > - if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) { > + if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) > mask = HWCAP_IDIVT; > - udiv_insn = __opcode_to_mem_thumb32(0xfbb0f0f1); > - sdiv_insn = __opcode_to_mem_thumb32(0xfb90f0f1); > - } else { > + else > mask = HWCAP_IDIVA; > - udiv_insn = __opcode_to_mem_arm(0xe730f110); > - sdiv_insn = __opcode_to_mem_arm(0xe710f110); > - } > > - if (elf_hwcap & mask) { > - for (p = __start_udiv_loc; p < __stop_udiv_loc; p++) { > - unsigned long *inst = *p; > - *inst = udiv_insn; > - } > - for (p = __start_idiv_loc; p < __stop_idiv_loc; p++) { > - unsigned long *inst = *p; > - *inst = 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) { } > -- > Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum, > a Linux Foundation Collaborative Project -- M?ns Rullg?rd mans@mansr.com -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/