From patchwork Sun Jun 11 23:58:29 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Nicholas Piggin X-Patchwork-Id: 774410 Return-Path: X-Original-To: patchwork-incoming@ozlabs.org Delivered-To: patchwork-incoming@ozlabs.org Received: from lists.ozlabs.org (lists.ozlabs.org [103.22.144.68]) (using TLSv1.2 with cipher ADH-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 3wmD1S6LYdz9s72 for ; Mon, 12 Jun 2017 10:15:08 +1000 (AEST) Authentication-Results: ozlabs.org; dkim=fail reason="signature verification failed" (2048-bit key; unprotected) header.d=gmail.com header.i=@gmail.com header.b="nMySdzdJ"; dkim-atps=neutral Received: from lists.ozlabs.org (lists.ozlabs.org [IPv6:2401:3900:2:1::3]) by lists.ozlabs.org (Postfix) with ESMTP id 3wmD1S5Fh3zDqP3 for ; Mon, 12 Jun 2017 10:15:08 +1000 (AEST) Authentication-Results: lists.ozlabs.org; dkim=fail reason="signature verification failed" (2048-bit key; unprotected) header.d=gmail.com header.i=@gmail.com header.b="nMySdzdJ"; dkim-atps=neutral X-Original-To: linuxppc-dev@lists.ozlabs.org Delivered-To: linuxppc-dev@lists.ozlabs.org Received: from mail-pg0-x241.google.com (mail-pg0-x241.google.com [IPv6:2607:f8b0:400e:c05::241]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 3wmChj3CVdzDqLV for ; Mon, 12 Jun 2017 10:00:37 +1000 (AEST) Authentication-Results: lists.ozlabs.org; dkim=pass (2048-bit key; unprotected) header.d=gmail.com header.i=@gmail.com header.b="nMySdzdJ"; dkim-atps=neutral Received: by mail-pg0-x241.google.com with SMTP id v14so12765264pgn.1 for ; Sun, 11 Jun 2017 17:00:37 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=from:to:cc:subject:date:message-id:in-reply-to:references; bh=DCNeQGe9f9F92wlhboy80MDC6yTzUWyxsXmdyMfSixk=; b=nMySdzdJ8nw/Ym0KrxCirMhLq/2SLcHcud5RCJmAgsqyeSflPc4yaxEjhU7h0Zmet4 lHS0zYaKC3JAjstZPqx3gzCHIXPeCKXIWa9Q1UxXlJvlQciBRFMCIWIISTnU77IiCRY6 IFjUKARbR51rYjif/8gCFevzRwVrT5M5+sCKrZHnsruNltKiK6V9GEjk7FV8Ytr8AzAu cQe85oRy13GkIuQbD1dd3w9JeTr7jf8r1HWM66q1+2QmiZrrqSeQQOkSz1CQze85Jx7A Vx189ucNQjQR2A7pr7g82Up/SOFi2HqbRN9RFHfibpOx2qQhoKKdr9OOndj+DdMxg0IH mcHw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references; bh=DCNeQGe9f9F92wlhboy80MDC6yTzUWyxsXmdyMfSixk=; b=VXoafqsnXhC9X94+SezwkGJU4QEhHG76t6yrmaj2eAfkW6lGIDePAapXVSs8PQ11vu s+n0VDOXv10dLg/9nAbjueF7ii3Z6ESEbtH8bfN3I9M8/cgj2jZC2pg/TvsYHDkLsrRX 0oDt0TllGxD/EYe8AmeKriJvRnhVzHq5cJ/uuvqIzkEsepWG/xl1oLl5Y+B68ZOTABdq iYg8j2U6xCThAjLQCS1gOD4AJTSgVuQQPTQUjoeycA/Ye1GLuRwxT7TM6UlJAmnVST74 wyUJFalDp4LqWeaEp/4y4lG/uHBZhSQJGeK+PvacgC6gSMOTxkVG6DfLdE0ZByh2iFFs BXjA== X-Gm-Message-State: AODbwcCPCMC80/a/AwzCsjXWo4NEEbol6tGb1noJEGTs8S9AstrN7bYc WeD1kuxW+gFgo2sD X-Received: by 10.101.89.5 with SMTP id f5mr28054929pgu.203.1497225635135; Sun, 11 Jun 2017 17:00:35 -0700 (PDT) Received: from roar.au.ibm.com ([210.185.119.63]) by smtp.gmail.com with ESMTPSA id c14sm14427211pfk.42.2017.06.11.17.00.31 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Sun, 11 Jun 2017 17:00:34 -0700 (PDT) From: Nicholas Piggin To: linuxppc-dev@lists.ozlabs.org Subject: [PATCH 08/14] powerpc/64s: idle avoid SRR usage in idle sleep/wake paths Date: Mon, 12 Jun 2017 09:58:29 +1000 Message-Id: <20170611235835.7400-9-npiggin@gmail.com> X-Mailer: git-send-email 2.11.0 In-Reply-To: <20170611235835.7400-1-npiggin@gmail.com> References: <20170611235835.7400-1-npiggin@gmail.com> X-BeenThere: linuxppc-dev@lists.ozlabs.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: "Gautham R . Shenoy" , Nicholas Piggin , "Shreyas B . Prabhu" Errors-To: linuxppc-dev-bounces+patchwork-incoming=ozlabs.org@lists.ozlabs.org Sender: "Linuxppc-dev" Idle code now always runs at the 0xc... effective address whether in real or virtual mode. This means rfid can be ditched, along with a lot of SRR manipulations. In the wakeup path, carry SRR1 around in r12. Use mtmsrd to change MSR states as required. This also balances the return prediction for the idle call, by doing blr rather than rfid to return to the idle caller. On POWER9, 2-process context switch on different cores, with snooze disabled, increases performance by 2%. --- arch/powerpc/kernel/exceptions-64s.S | 1 + arch/powerpc/kernel/idle_book3s.S | 57 +++++++++++++++------------------ arch/powerpc/kvm/book3s_hv_rmhandlers.S | 8 ++++- 3 files changed, 33 insertions(+), 33 deletions(-) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index fec7c933d095..c3d0aef089a7 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -130,6 +130,7 @@ EXC_VIRT_NONE(0x4100, 0x100) #ifdef CONFIG_PPC_P7_NAP EXC_COMMON_BEGIN(system_reset_idle_common) + mfspr r12,SPRN_SRR1 b pnv_powersave_wakeup #endif diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index 35cf5bb7daed..6305d4d7a268 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -111,7 +111,7 @@ core_idle_lock_held: * r3 - PNV_THREAD_NAP/SLEEP/WINKLE in POWER8 * - Requested PSSCR value in POWER9 * - * Address of idle handler to 'rfid' to in r4 + * Address of idle handler to branch to in realmode in r4 */ pnv_powersave_common: /* Use r3 to pass state nap/sleep/winkle */ @@ -121,14 +121,14 @@ pnv_powersave_common: * need to save PC, some CR bits and the NV GPRs, * but for now an interrupt frame will do. */ + mtctr r4 + mflr r0 std r0,16(r1) stdu r1,-INT_FRAME_SIZE(r1) std r0,_LINK(r1) std r0,_NIP(r1) - mfmsr r9 - /* We haven't lost state ... yet */ li r0,0 stb r0,PACA_NAPSTATELOST(r13) @@ -138,7 +138,6 @@ pnv_powersave_common: SAVE_NVGPRS(r1) mfcr r5 std r5,_CCR(r1) - std r9,_MSR(r1) std r1,PACAR1(r13) /* @@ -148,12 +147,8 @@ pnv_powersave_common: * the MMU context to the guest. */ LOAD_REG_IMMEDIATE(r7, MSR_IDLE) - li r6, MSR_RI - andc r6, r9, r6 - mtmsrd r6, 1 /* clear RI before setting SRR0/1 */ - mtspr SPRN_SRR0, r4 - mtspr SPRN_SRR1, r7 - rfid + mtmsrd r7,0 + bctr .globl pnv_enter_arch207_idle_mode pnv_enter_arch207_idle_mode: @@ -305,11 +300,10 @@ _GLOBAL(power7_idle_insn) b pnv_powersave_common #define CHECK_HMI_INTERRUPT \ - mfspr r0,SPRN_SRR1; \ BEGIN_FTR_SECTION_NESTED(66); \ - rlwinm r0,r0,45-31,0xf; /* extract wake reason field (P8) */ \ + rlwinm r0,r12,45-31,0xf; /* extract wake reason field (P8) */ \ FTR_SECTION_ELSE_NESTED(66); \ - rlwinm r0,r0,45-31,0xe; /* P7 wake reason field is 3 bits */ \ + rlwinm r0,r12,45-31,0xe; /* P7 wake reason field is 3 bits */ \ ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_ARCH_207S, 66); \ cmpwi r0,0xa; /* Hypervisor maintenance ? */ \ bne 20f; \ @@ -388,17 +382,17 @@ pnv_powersave_wakeup_mce: /* * Now put the original SRR1 with SRR1_WAKEMCE_RESVD as the wake - * reason into SRR1, which allows reuse of the system reset wakeup + * reason into r12, which allows reuse of the system reset wakeup * code without being mistaken for another type of wakeup. */ - oris r3,r3,SRR1_WAKEMCE_RESVD@h - mtspr SPRN_SRR1,r3 + oris r12,r3,SRR1_WAKEMCE_RESVD@h b pnv_powersave_wakeup /* * Called from reset vector for powersave wakeups. * cr3 - set to gt if waking up with partial/complete hypervisor state loss + * r12 - SRR1 */ .global pnv_powersave_wakeup pnv_powersave_wakeup: @@ -408,8 +402,10 @@ BEGIN_FTR_SECTION BEGIN_FTR_SECTION_NESTED(70) bl power9_dd1_recover_paca END_FTR_SECTION_NESTED_IFSET(CPU_FTR_POWER9_DD1, 70) + ld r1,PACAR1(r13) bl pnv_restore_hyp_resource_arch300 FTR_SECTION_ELSE + ld r1,PACAR1(r13) bl pnv_restore_hyp_resource_arch207 ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300) @@ -429,7 +425,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300) #endif /* Return SRR1 from power7_nap() */ - mfspr r3,SPRN_SRR1 + mr r3,r12 blt cr3,pnv_wakeup_noloss b pnv_wakeup_loss @@ -503,7 +499,6 @@ pnv_restore_hyp_resource_arch207: * r4 - PACA_THREAD_IDLE_STATE */ pnv_wakeup_tb_loss: - ld r1,PACAR1(r13) /* * Before entering any idle state, the NVGPRs are saved in the stack. * If there was a state loss, or PACA_NAPSTATELOST was set, then the @@ -529,9 +524,9 @@ pnv_wakeup_tb_loss: * is required to return back to reset vector after hypervisor state * restore is complete. */ + mr r19,r12 mr r18,r4 mflr r17 - mfspr r16,SPRN_SRR1 BEGIN_FTR_SECTION CHECK_HMI_INTERRUPT END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) @@ -781,7 +776,7 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) hypervisor_state_restored: - mtspr SPRN_SRR1,r16 + mr r12,r19 mtlr r17 blr /* return to pnv_powersave_wakeup */ @@ -797,20 +792,19 @@ fastsleep_workaround_at_exit: */ .global pnv_wakeup_loss pnv_wakeup_loss: - ld r1,PACAR1(r13) BEGIN_FTR_SECTION CHECK_HMI_INTERRUPT END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) REST_NVGPRS(r1) REST_GPR(2, r1) + ld r4,PACAKMSR(r13) + ld r5,_LINK(r1) ld r6,_CCR(r1) - ld r4,_MSR(r1) - ld r5,_NIP(r1) addi r1,r1,INT_FRAME_SIZE + mtlr r5 mtcr r6 - mtspr SPRN_SRR1,r4 - mtspr SPRN_SRR0,r5 - rfid + mtmsrd r4 + blr /* * R3 here contains the value that will be returned to the caller @@ -823,12 +817,11 @@ pnv_wakeup_noloss: BEGIN_FTR_SECTION CHECK_HMI_INTERRUPT END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) - ld r1,PACAR1(r13) - ld r6,_CCR(r1) - ld r4,_MSR(r1) + ld r4,PACAKMSR(r13) ld r5,_NIP(r1) + ld r6,_CCR(r1) addi r1,r1,INT_FRAME_SIZE + mtlr r5 mtcr r6 - mtspr SPRN_SRR1,r4 - mtspr SPRN_SRR0,r5 - rfid + mtmsrd r4 + blr diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index bdb3f76ceb6b..eb5b78b6bacf 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -329,15 +329,21 @@ kvm_novcpu_exit: * We come in here when wakened from nap mode. * Relocation is off and most register values are lost. * r13 points to the PACA. + * r3 contains the SRR1 wakeup value, SRR1 is trashed. */ .globl kvm_start_guest kvm_start_guest: - /* Set runlatch bit the minute you wake up from nap */ mfspr r0, SPRN_CTRLF ori r0, r0, 1 mtspr SPRN_CTRLT, r0 + /* + * Could avoid this and pass it through in r3. For now, + * code expects it to be in SRR1. + */ + mtspr r3,SPRN_SRR1 + ld r2,PACATOC(r13) li r0,KVM_HWTHREAD_IN_KVM