From patchwork Tue Jan 26 11:21:16 2010 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Sheng Yang X-Patchwork-Id: 43688 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Received: from lists.gnu.org (lists.gnu.org [199.232.76.165]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by ozlabs.org (Postfix) with ESMTPS id E119AB7C06 for ; Tue, 26 Jan 2010 22:29:02 +1100 (EST) Received: from localhost ([127.0.0.1]:37805 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1NZjXr-0007jS-L1 for incoming@patchwork.ozlabs.org; Tue, 26 Jan 2010 06:25:19 -0500 Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43) id 1NZjUv-0007Lv-Fr for qemu-devel@nongnu.org; Tue, 26 Jan 2010 06:22:17 -0500 Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43) id 1NZjUq-0007Jg-M2 for qemu-devel@nongnu.org; Tue, 26 Jan 2010 06:22:16 -0500 Received: from [199.232.76.173] (port=38719 helo=monty-python.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1NZjUq-0007JV-5y for qemu-devel@nongnu.org; Tue, 26 Jan 2010 06:22:12 -0500 Received: from mga03.intel.com ([143.182.124.21]:52231) by monty-python.gnu.org with esmtp (Exim 4.60) (envelope-from ) id 1NZjUp-0002o4-M9 for qemu-devel@nongnu.org; Tue, 26 Jan 2010 06:22:12 -0500 Received: from azsmga001.ch.intel.com ([10.2.17.19]) by azsmga101.ch.intel.com with ESMTP; 26 Jan 2010 03:22:10 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.47,316,1257148800"; d="scan'208";a="236875268" Received: from syang10-desktop.sh.intel.com (HELO syang10-desktop) ([10.239.36.165]) by azsmga001.ch.intel.com with ESMTP; 26 Jan 2010 03:22:09 -0800 Received: from yasker by syang10-desktop with local (Exim 4.69) (envelope-from ) id 1NZjTy-0006NX-Ht; Tue, 26 Jan 2010 19:21:18 +0800 From: Sheng Yang To: Avi Kivity , Marcelo Tosatti Date: Tue, 26 Jan 2010 19:21:16 +0800 Message-Id: <1264504876-24493-1-git-send-email-sheng@linux.intel.com> X-Mailer: git-send-email 1.6.3.3 In-Reply-To: <366919FC-E282-4A23-8D9C-595D8583C97F@suse.de> References: <366919FC-E282-4A23-8D9C-595D8583C97F@suse.de> X-detected-operating-system: by monty-python.gnu.org: Genre and OS details not recognized. Cc: qemu-devel@nongnu.org, Sheng Yang , Alexander Graf , kvm@vger.kernel.org Subject: [Qemu-devel] [PATCH v3][uqmaster] kvm: Flush coalesced MMIO buffer periodly X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: qemu-devel.nongnu.org List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org Errors-To: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org The default action of coalesced MMIO is, cache the writing in buffer, until: 1. The buffer is full. 2. Or the exit to QEmu due to other reasons. But this would result in a very late writing in some condition. 1. The each time write to MMIO content is small. 2. The writing interval is big. 3. No need for input or accessing other devices frequently. This issue was observed in a experimental embbed system. The test image simply print "test" every 1 seconds. The output in QEmu meets expectation, but the output in KVM is delayed for seconds. Per Avi's suggestion, I hooked flushing coalesced MMIO buffer in VGA update handler. By this way, We don't need vcpu explicit exit to QEmu to handle this issue. Signed-off-by: Sheng Yang --- cpu-all.h | 2 ++ exec.c | 6 ++++++ kvm-all.c | 23 +++++++++++++++-------- kvm.h | 1 + vl.c | 2 ++ 5 files changed, 26 insertions(+), 8 deletions(-) diff --git a/cpu-all.h b/cpu-all.h index 57b69f8..1ccc9a8 100644 --- a/cpu-all.h +++ b/cpu-all.h @@ -915,6 +915,8 @@ void qemu_register_coalesced_mmio(target_phys_addr_t addr, ram_addr_t size); void qemu_unregister_coalesced_mmio(target_phys_addr_t addr, ram_addr_t size); +void qemu_flush_coalesced_mmio_buffer(void); + /*******************************************/ /* host CPU ticks (if available) */ diff --git a/exec.c b/exec.c index 1190591..6875370 100644 --- a/exec.c +++ b/exec.c @@ -2406,6 +2406,12 @@ void qemu_unregister_coalesced_mmio(target_phys_addr_t addr, ram_addr_t size) kvm_uncoalesce_mmio_region(addr, size); } +void qemu_flush_coalesced_mmio_buffer(void) +{ + if (kvm_enabled()) + kvm_flush_coalesced_mmio_buffer(); +} + ram_addr_t qemu_ram_alloc(ram_addr_t size) { RAMBlock *new_block; diff --git a/kvm-all.c b/kvm-all.c index 15ec38e..f8350c9 100644 --- a/kvm-all.c +++ b/kvm-all.c @@ -59,6 +59,9 @@ struct KVMState int vmfd; int regs_modified; int coalesced_mmio; +#ifdef KVM_CAP_COALESCED_MMIO + struct kvm_coalesced_mmio_ring *coalesced_mmio_ring; +#endif int broken_set_mem_region; int migration_log; int vcpu_events; @@ -200,6 +203,12 @@ int kvm_init_vcpu(CPUState *env) goto err; } +#ifdef KVM_CAP_COALESCED_MMIO + if (s->coalesced_mmio && !s->coalesced_mmio_ring) + s->coalesced_mmio_ring = (void *) env->kvm_run + + s->coalesced_mmio * PAGE_SIZE; +#endif + ret = kvm_arch_init_vcpu(env); if (ret == 0) { qemu_register_reset(kvm_reset_vcpu, env); @@ -466,10 +475,10 @@ int kvm_init(int smp_cpus) goto err; } + s->coalesced_mmio = 0; #ifdef KVM_CAP_COALESCED_MMIO s->coalesced_mmio = kvm_check_extension(s, KVM_CAP_COALESCED_MMIO); -#else - s->coalesced_mmio = 0; + s->coalesced_mmio_ring = NULL; #endif s->broken_set_mem_region = 1; @@ -544,14 +553,12 @@ static int kvm_handle_io(uint16_t port, void *data, int direction, int size, return 1; } -static void kvm_run_coalesced_mmio(CPUState *env, struct kvm_run *run) +void kvm_flush_coalesced_mmio_buffer(void) { #ifdef KVM_CAP_COALESCED_MMIO KVMState *s = kvm_state; - if (s->coalesced_mmio) { - struct kvm_coalesced_mmio_ring *ring; - - ring = (void *)run + (s->coalesced_mmio * TARGET_PAGE_SIZE); + if (s->coalesced_mmio_ring) { + struct kvm_coalesced_mmio_ring *ring = s->coalesced_mmio_ring; while (ring->first != ring->last) { struct kvm_coalesced_mmio *ent; @@ -609,7 +616,7 @@ int kvm_cpu_exec(CPUState *env) abort(); } - kvm_run_coalesced_mmio(env, run); + kvm_flush_coalesced_mmio_buffer(); ret = 0; /* exit loop */ switch (run->exit_reason) { diff --git a/kvm.h b/kvm.h index 1c93ac5..59cba18 100644 --- a/kvm.h +++ b/kvm.h @@ -53,6 +53,7 @@ void kvm_setup_guest_memory(void *start, size_t size); int kvm_coalesce_mmio_region(target_phys_addr_t start, ram_addr_t size); int kvm_uncoalesce_mmio_region(target_phys_addr_t start, ram_addr_t size); +void kvm_flush_coalesced_mmio_buffer(void); int kvm_insert_breakpoint(CPUState *current_env, target_ulong addr, target_ulong len, int type); diff --git a/vl.c b/vl.c index 2b0b653..1f0c536 100644 --- a/vl.c +++ b/vl.c @@ -3193,6 +3193,7 @@ static void gui_update(void *opaque) DisplayState *ds = opaque; DisplayChangeListener *dcl = ds->listeners; + qemu_flush_coalesced_mmio_buffer(); dpy_refresh(ds); while (dcl != NULL) { @@ -3208,6 +3209,7 @@ static void nographic_update(void *opaque) { uint64_t interval = GUI_REFRESH_INTERVAL; + qemu_flush_coalesced_mmio_buffer(); qemu_mod_timer(nographic_timer, interval + qemu_get_clock(rt_clock)); }