From patchwork Wed May 15 01:37:24 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Shawn Landden X-Patchwork-Id: 1099835 Return-Path: X-Original-To: patchwork-incoming@ozlabs.org Delivered-To: patchwork-incoming@ozlabs.org Received: from lists.ozlabs.org (lists.ozlabs.org [203.11.71.2]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 453cfN5hgFz9s9N for ; Wed, 15 May 2019 11:39:08 +1000 (AEST) Authentication-Results: ozlabs.org; dmarc=none (p=none dis=none) header.from=git.icu Received: from lists.ozlabs.org (lists.ozlabs.org [IPv6:2401:3900:2:1::3]) by lists.ozlabs.org (Postfix) with ESMTP id 453cfN4pVGzDqNQ for ; Wed, 15 May 2019 11:39:08 +1000 (AEST) X-Original-To: linuxppc-dev@lists.ozlabs.org Delivered-To: linuxppc-dev@lists.ozlabs.org Authentication-Results: lists.ozlabs.org; spf=pass (mailfrom) smtp.mailfrom=git.icu (client-ip=163.172.180.134; helo=git.icu; envelope-from=shawn@git.icu; receiver=) Authentication-Results: lists.ozlabs.org; dmarc=none (p=none dis=none) header.from=git.icu Received: from git.icu (git.icu [163.172.180.134]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 453ccc060LzDqNd for ; Wed, 15 May 2019 11:37:36 +1000 (AEST) Received: from localhost.localdomain (minicloud.parqtec.unicamp.br [143.106.167.126]) by git.icu (Postfix) with ESMTPSA id 993B82206D1; Wed, 15 May 2019 01:37:31 +0000 (UTC) From: Shawn Landden To: Subject: [v4 PATCH 1/2] [PowerPC] Add simd.h implementation Date: Tue, 14 May 2019 22:37:24 -0300 Message-Id: <20190515013725.2198-1-shawn@git.icu> X-Mailer: git-send-email 2.21.0.1020.gf2820cf01a In-Reply-To: <20190513005104.20140-1-shawn@git.icu> References: <20190513005104.20140-1-shawn@git.icu> MIME-Version: 1.0 X-BeenThere: linuxppc-dev@lists.ozlabs.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Paul Mackerras , Shawn Landden , linuxppc-dev@lists.ozlabs.org Errors-To: linuxppc-dev-bounces+patchwork-incoming=ozlabs.org@lists.ozlabs.org Sender: "Linuxppc-dev" Based off the x86 one. WireGuard really wants to be able to do SIMD in interrupts, so it can accelerate its in-bound path. Signed-off-by: Shawn Landden --- arch/powerpc/include/asm/simd.h | 17 +++++++++++++++++ arch/powerpc/kernel/process.c | 30 ++++++++++++++++++++++++++++++ 2 files changed, 47 insertions(+) create mode 100644 arch/powerpc/include/asm/simd.h diff --git a/arch/powerpc/include/asm/simd.h b/arch/powerpc/include/asm/simd.h new file mode 100644 index 000000000..2fe26f258 --- /dev/null +++ b/arch/powerpc/include/asm/simd.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +/* + * may_use_simd - whether it is allowable at this time to issue SIMD + * instructions or access the SIMD register file + * + * It's always ok in process context (ie "not interrupt") + * but it is sometimes ok even from an irq. + */ +#ifdef CONFIG_PPC_FPU +extern bool may_use_simd(void); +#else +static inline bool may_use_simd(void) +{ + return false; +} +#endif diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index dd9e0d538..ef534831f 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -345,6 +345,36 @@ static int restore_altivec(struct task_struct *tsk) } return 0; } + +/* + * Were we in user mode when we were + * interrupted? + * + * Doing kernel_altivec/vsx_begin/end() is ok if we are running + * in an interrupt context from user mode - we'll just + * save the FPU state as required. + */ +static bool interrupted_user_mode(void) +{ + struct pt_regs *regs = get_irq_regs(); + + return regs && user_mode(regs); +} + +/* + * Can we use FPU in kernel mode with the + * whole "kernel_fpu/altivec/vsx_begin/end()" sequence? + * + * It's always ok in process context (ie "not interrupt") + * but it is sometimes ok even from an irq. + */ +bool may_use_simd(void) +{ + return !in_interrupt() || + interrupted_user_mode(); +} +EXPORT_SYMBOL(may_use_simd); + #else #define loadvec(thr) 0 static inline int restore_altivec(struct task_struct *tsk) { return 0; } From patchwork Wed May 15 01:37:25 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Shawn Landden X-Patchwork-Id: 1099836 Return-Path: X-Original-To: patchwork-incoming@ozlabs.org Delivered-To: patchwork-incoming@ozlabs.org Received: from lists.ozlabs.org (lists.ozlabs.org [IPv6:2401:3900:2:1::3]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 453cgm6Vt3z9s9N for ; Wed, 15 May 2019 11:40:20 +1000 (AEST) Authentication-Results: ozlabs.org; dmarc=none (p=none dis=none) header.from=git.icu Received: from lists.ozlabs.org (lists.ozlabs.org [IPv6:2401:3900:2:1::3]) by lists.ozlabs.org (Postfix) with ESMTP id 453cgm5hRVzDqPW for ; Wed, 15 May 2019 11:40:20 +1000 (AEST) X-Original-To: linuxppc-dev@lists.ozlabs.org Delivered-To: linuxppc-dev@lists.ozlabs.org Authentication-Results: lists.ozlabs.org; spf=pass (mailfrom) smtp.mailfrom=git.icu (client-ip=163.172.180.134; helo=git.icu; envelope-from=shawn@git.icu; receiver=) Authentication-Results: lists.ozlabs.org; dmarc=none (p=none dis=none) header.from=git.icu Received: from git.icu (git.icu [163.172.180.134]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 453ccj4JFhzDqNR for ; Wed, 15 May 2019 11:37:41 +1000 (AEST) Received: from localhost.localdomain (minicloud.parqtec.unicamp.br [143.106.167.126]) by git.icu (Postfix) with ESMTPSA id B4631220702; Wed, 15 May 2019 01:37:36 +0000 (UTC) From: Shawn Landden To: Subject: [v4 PATCH 2/2] [PowerPC] Allow use of SIMD in interrupts from kernel code Date: Tue, 14 May 2019 22:37:25 -0300 Message-Id: <20190515013725.2198-2-shawn@git.icu> X-Mailer: git-send-email 2.21.0.1020.gf2820cf01a In-Reply-To: <20190515013725.2198-1-shawn@git.icu> References: <20190513005104.20140-1-shawn@git.icu> <20190515013725.2198-1-shawn@git.icu> MIME-Version: 1.0 X-BeenThere: linuxppc-dev@lists.ozlabs.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Paul Mackerras , Shawn Landden , linuxppc-dev@lists.ozlabs.org Errors-To: linuxppc-dev-bounces+patchwork-incoming=ozlabs.org@lists.ozlabs.org Sender: "Linuxppc-dev" This second patch is separate because it could be wrong, like I am not sure about how kernel thread migration works, and it is even allowing simd in preemptible kernel code. v4: fix build without CONFIG_AVX Signed-off-by: Shawn Landden --- arch/powerpc/include/asm/switch_to.h | 15 +--- arch/powerpc/kernel/process.c | 117 +++++++++++++++++++-------- 2 files changed, 88 insertions(+), 44 deletions(-) diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h index 5b03d8a82..c79f7d24a 100644 --- a/arch/powerpc/include/asm/switch_to.h +++ b/arch/powerpc/include/asm/switch_to.h @@ -30,10 +30,7 @@ extern void enable_kernel_fp(void); extern void flush_fp_to_thread(struct task_struct *); extern void giveup_fpu(struct task_struct *); extern void save_fpu(struct task_struct *); -static inline void disable_kernel_fp(void) -{ - msr_check_and_clear(MSR_FP); -} +extern void disable_kernel_fp(void); #else static inline void save_fpu(struct task_struct *t) { } static inline void flush_fp_to_thread(struct task_struct *t) { } @@ -44,10 +41,7 @@ extern void enable_kernel_altivec(void); extern void flush_altivec_to_thread(struct task_struct *); extern void giveup_altivec(struct task_struct *); extern void save_altivec(struct task_struct *); -static inline void disable_kernel_altivec(void) -{ - msr_check_and_clear(MSR_VEC); -} +extern void disable_kernel_altivec(void); #else static inline void save_altivec(struct task_struct *t) { } static inline void __giveup_altivec(struct task_struct *t) { } @@ -56,10 +50,7 @@ static inline void __giveup_altivec(struct task_struct *t) { } #ifdef CONFIG_VSX extern void enable_kernel_vsx(void); extern void flush_vsx_to_thread(struct task_struct *); -static inline void disable_kernel_vsx(void) -{ - msr_check_and_clear(MSR_FP|MSR_VEC|MSR_VSX); -} +extern void disable_kernel_vsx(void); #endif #ifdef CONFIG_SPE diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index ef534831f..0136fd132 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -170,6 +170,29 @@ void __msr_check_and_clear(unsigned long bits) EXPORT_SYMBOL(__msr_check_and_clear); #ifdef CONFIG_PPC_FPU +/* + * Track whether the kernel is using the FPU state + * currently. + * + * This flag is used: + * + * - by IRQ context code to potentially use the FPU + * if it's unused. + * + * - to debug kernel_fpu/altivec/vsx_begin()/end() correctness + */ +static DEFINE_PER_CPU(bool, in_kernel_fpu); + +static bool kernel_fpu_disabled(void) +{ + return this_cpu_read(in_kernel_fpu); +} + +static bool interrupted_kernel_fpu_idle(void) +{ + return !kernel_fpu_disabled(); +} + static void __giveup_fpu(struct task_struct *tsk) { unsigned long msr; @@ -230,7 +253,8 @@ void enable_kernel_fp(void) { unsigned long cpumsr; - WARN_ON(preemptible()); + WARN_ON_ONCE(this_cpu_read(in_kernel_fpu)); + this_cpu_write(in_kernel_fpu, true); cpumsr = msr_check_and_set(MSR_FP); @@ -251,6 +275,15 @@ void enable_kernel_fp(void) } EXPORT_SYMBOL(enable_kernel_fp); +void disable_kernel_fp(void) +{ + WARN_ON_ONCE(!this_cpu_read(in_kernel_fpu)); + this_cpu_write(in_kernel_fpu, false); + + msr_check_and_clear(MSR_FP); +} +EXPORT_SYMBOL(disable_kernel_fp); + static int restore_fp(struct task_struct *tsk) { if (tsk->thread.load_fp || tm_active_with_fp(tsk)) { @@ -260,6 +293,37 @@ static int restore_fp(struct task_struct *tsk) } return 0; } + +/* + * Were we in user mode when we were + * interrupted? + * + * Doing kernel_altivec/vsx_begin/end() is ok if we are running + * in an interrupt context from user mode - we'll just + * save the FPU state as required. + */ +static bool interrupted_user_mode(void) +{ + struct pt_regs *regs = get_irq_regs(); + + return regs && user_mode(regs); +} + +/* + * Can we use FPU in kernel mode with the + * whole "kernel_fpu/altivec/vsx_begin/end()" sequence? + * + * It's always ok in process context (ie "not interrupt") + * but it is sometimes ok even from an irq. + */ +bool may_use_simd(void) +{ + return !in_interrupt() || + interrupted_user_mode() || + interrupted_kernel_fpu_idle(); +} +EXPORT_SYMBOL(may_use_simd); + #else static int restore_fp(struct task_struct *tsk) { return 0; } #endif /* CONFIG_PPC_FPU */ @@ -295,7 +359,8 @@ void enable_kernel_altivec(void) { unsigned long cpumsr; - WARN_ON(preemptible()); + WARN_ON_ONCE(this_cpu_read(in_kernel_fpu)); + this_cpu_write(in_kernel_fpu, true); cpumsr = msr_check_and_set(MSR_VEC); @@ -316,6 +381,14 @@ void enable_kernel_altivec(void) } EXPORT_SYMBOL(enable_kernel_altivec); +extern void disable_kernel_altivec(void) +{ + WARN_ON_ONCE(!this_cpu_read(in_kernel_fpu)); + this_cpu_write(in_kernel_fpu, false); + msr_check_and_clear(MSR_VEC); +} +EXPORT_SYMBOL(disable_kernel_altivec); + /* * Make sure the VMX/Altivec register state in the * the thread_struct is up to date for task tsk. @@ -346,35 +419,6 @@ static int restore_altivec(struct task_struct *tsk) return 0; } -/* - * Were we in user mode when we were - * interrupted? - * - * Doing kernel_altivec/vsx_begin/end() is ok if we are running - * in an interrupt context from user mode - we'll just - * save the FPU state as required. - */ -static bool interrupted_user_mode(void) -{ - struct pt_regs *regs = get_irq_regs(); - - return regs && user_mode(regs); -} - -/* - * Can we use FPU in kernel mode with the - * whole "kernel_fpu/altivec/vsx_begin/end()" sequence? - * - * It's always ok in process context (ie "not interrupt") - * but it is sometimes ok even from an irq. - */ -bool may_use_simd(void) -{ - return !in_interrupt() || - interrupted_user_mode(); -} -EXPORT_SYMBOL(may_use_simd); - #else #define loadvec(thr) 0 static inline int restore_altivec(struct task_struct *tsk) { return 0; } @@ -411,7 +455,8 @@ void enable_kernel_vsx(void) { unsigned long cpumsr; - WARN_ON(preemptible()); + WARN_ON_ONCE(this_cpu_read(in_kernel_fpu)); + this_cpu_write(in_kernel_fpu, true); cpumsr = msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX); @@ -433,6 +478,14 @@ void enable_kernel_vsx(void) } EXPORT_SYMBOL(enable_kernel_vsx); +void disable_kernel_vsx(void) +{ + WARN_ON_ONCE(!this_cpu_read(in_kernel_fpu)); + this_cpu_write(in_kernel_fpu, false); + msr_check_and_clear(MSR_FP|MSR_VEC|MSR_VSX); +} +EXPORT_SYMBOL(disable_kernel_vsx); + void flush_vsx_to_thread(struct task_struct *tsk) { if (tsk->thread.regs) {