From patchwork Thu Jan 11 04:34:08 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Benjamin Herrenschmidt X-Patchwork-Id: 858779 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=vger.kernel.org (client-ip=209.132.180.67; helo=vger.kernel.org; envelope-from=kvm-ppc-owner@vger.kernel.org; receiver=) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 3zHCjY5zMqz9t50 for ; Thu, 11 Jan 2018 15:35:29 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932068AbeAKEf3 (ORCPT ); Wed, 10 Jan 2018 23:35:29 -0500 Received: from gate.crashing.org ([63.228.1.57]:48473 "EHLO gate.crashing.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932067AbeAKEf2 (ORCPT ); Wed, 10 Jan 2018 23:35:28 -0500 Received: from pasglop.ozlabs.ibm.com (localhost.localdomain [127.0.0.1]) by gate.crashing.org (8.14.1/8.14.1) with ESMTP id w0B4YYbu010800; Wed, 10 Jan 2018 22:34:54 -0600 From: Benjamin Herrenschmidt To: kvm-ppc@vger.kernel.org, kvm@vger.kernel.org Cc: Benjamin Herrenschmidt Subject: [PATCH v3 11/16] powerpc/kvm/xive: Keep escalation interrupt masked unless ceded Date: Thu, 11 Jan 2018 15:34:08 +1100 Message-Id: <20180111043413.22655-11-benh@kernel.crashing.org> X-Mailer: git-send-email 2.14.3 In-Reply-To: <20180111043413.22655-1-benh@kernel.crashing.org> References: <20180111043413.22655-1-benh@kernel.crashing.org> Sender: kvm-ppc-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm-ppc@vger.kernel.org This works on top of the single escalation support. When in single escalation, with this change, we will keep the escalation interrupt disabled unless the VCPU is in H_CEDE (idle). In any other case, we know the VCPU will be rescheduled and thus there is no need to take escalation interrupts in the host whenever a guest interrupt fires. Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/kvm_host.h | 2 ++ arch/powerpc/kernel/asm-offsets.c | 3 ++ arch/powerpc/kvm/book3s_hv_rmhandlers.S | 64 +++++++++++++++++++++++++++++++-- arch/powerpc/kvm/book3s_xive.c | 30 ++++++++++++++++ 4 files changed, 97 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 2cf2cc6b389a..fef8133becc8 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -742,6 +742,8 @@ struct kvm_vcpu_arch { u8 xive_pushed; /* Is the VP pushed on the physical CPU ? */ u8 xive_esc_on; /* Is the escalation irq enabled ? */ union xive_tma_w01 xive_saved_state; /* W0..1 of XIVE thread state */ + u64 xive_esc_raddr; /* Escalation interrupt ESB real addr */ + u64 xive_esc_vaddr; /* Escalation interrupt ESB virt addr */ #endif #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 825089cf3e23..1672dffd94e2 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -734,6 +734,9 @@ int main(void) DEFINE(VCPU_XIVE_CAM_WORD, offsetof(struct kvm_vcpu, arch.xive_cam_word)); DEFINE(VCPU_XIVE_PUSHED, offsetof(struct kvm_vcpu, arch.xive_pushed)); + DEFINE(VCPU_XIVE_ESC_ON, offsetof(struct kvm_vcpu, arch.xive_esc_on)); + DEFINE(VCPU_XIVE_ESC_RADDR, offsetof(struct kvm_vcpu, arch.xive_esc_raddr)); + DEFINE(VCPU_XIVE_ESC_VADDR, offsetof(struct kvm_vcpu, arch.xive_esc_vaddr)); #endif #ifdef CONFIG_KVM_EXIT_TIMING diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index bc3fc39d482b..b76878a648ef 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1042,7 +1042,42 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300) * issue. */ li r0,0 - stb r0, VCPU_IRQ_PENDING(r4); + stb r0, VCPU_IRQ_PENDING(r4) + + /* + * In single escalation mode, if the escalation interrupt is + * on, we mask it. + */ + lbz r0, VCPU_XIVE_ESC_ON(r4) + cmpwi r0,0 + beq 1f + ld r10, VCPU_XIVE_ESC_RADDR(r4) + li r9, XIVE_ESB_SET_PQ_01 + ldcix r0, r10, r9 + sync + + /* We have a possible subtle race here: The escalation interrupt might + * have fired and be on its way to the host queue while we mask it, + * and if we unmask it early enough (re-cede right away), there is + * a theorical possibility that it fires again, thus landing in the + * target queue more than once which is a big no-no. + * + * Fortunately, solving this is rather easy. If the above load setting + * PQ to 01 returns a previous value where P is set, then we know the + * escalation interrupt is somewhere on its way to the host. In that + * case we simply don't clear the xive_esc_on flag below. It will be + * eventually cleared by the handler for the escalation interrupt. + * + * Then, when doing a cede, we check that flag again before re-enabling + * the escalation interrupt, and if set, we abort the cede. + */ + andi. r0, r0, XIVE_ESB_VAL_P + bne- 1f + + /* Now P is 0, we can clear the flag */ + li r0, 0 + stb r0, VCPU_XIVE_ESC_ON(r4) +1: no_xive: #endif /* CONFIG_KVM_XICS */ @@ -2755,7 +2790,32 @@ kvm_cede_prodded: /* we've ceded but we want to give control to the host */ kvm_cede_exit: ld r9, HSTATE_KVM_VCPU(r13) - b guest_exit_cont +#ifdef CONFIG_KVM_XICS + /* Abort if we still have a pending escalation */ + lbz r5, VCPU_XIVE_ESC_ON(r9) + cmpwi r5, 0 + beq 1f + li r0, 0 + stb r0, VCPU_CEDED(r9) +1: /* Enable XIVE escalation */ + li r5, XIVE_ESB_SET_PQ_00 + mfmsr r0 + andi. r0, r0, MSR_DR /* in real mode? */ + beq 1f + ld r10, VCPU_XIVE_ESC_VADDR(r9) + cmpdi r10, 0 + beq 3f + ldx r0, r10, r5 + b 2f +1: ld r10, VCPU_XIVE_ESC_RADDR(r9) + cmpdi r10, 0 + beq 3f + ldcix r0, r10, r5 +2: sync + li r0, 1 + stb r0, VCPU_XIVE_ESC_ON(r9) +#endif /* CONFIG_KVM_XICS */ +3: b guest_exit_cont /* Try to handle a machine check in real mode */ machine_check_realmode: diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index de78ac38f7ed..badfdbb857a2 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -89,6 +89,17 @@ static irqreturn_t xive_esc_irq(int irq, void *data) if (vcpu->arch.ceded) kvmppc_fast_vcpu_kick(vcpu); + /* Since we have the no-EOI flag, the interrupt is effectively + * disabled now. Clearing xive_esc_on means we won't bother + * doing so on the next entry. + * + * This also allows the entry code to know that if a PQ combination + * of 10 is observed while xive_esc_on is true, it means the queue + * contains an unprocessed escalation interrupt. We don't make use of + * that knowledge today but might (see comment in book3s_hv_rmhandler.S) + */ + vcpu->arch.xive_esc_on = false; + return IRQ_HANDLED; } @@ -134,6 +145,25 @@ static int xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio) goto error; } xc->esc_virq_names[prio] = name; + + /* In single escalation mode, we grab the ESB MMIO of the + * interrupt and mask it. Also populate the VCPU v/raddr + * of the ESB page for use by asm entry/exit code. Finally + * set the XIVE_IRQ_NO_EOI flag which will prevent the + * core code from performing an EOI on the escalation + * interrupt, thus leaving it effectively masked after + * it fires once. + */ + if (xc->xive->single_escalation) { + struct irq_data *d = irq_get_irq_data(xc->esc_virq[prio]); + struct xive_irq_data *xd = irq_data_get_irq_handler_data(d); + + xive_vm_esb_load(xd, XIVE_ESB_SET_PQ_01); + vcpu->arch.xive_esc_raddr = xd->eoi_page; + vcpu->arch.xive_esc_vaddr = (__force u64)xd->eoi_mmio; + xd->flags |= XIVE_IRQ_NO_EOI; + } + return 0; error: irq_dispose_mapping(xc->esc_virq[prio]);