* [Qemu-devel] [PATCH 01/67] linux-headers: update
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
@ 2016-12-15 0:43 ` Michael Roth
2016-12-15 0:43 ` [Qemu-devel] [PATCH 02/67] hw/ppc/spapr: Move code related to "ibm, pa-features" to a separate function Michael Roth
` (66 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:43 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Cornelia Huck
From: Cornelia Huck <cornelia.huck@de.ibm.com>
Update headers against 4.8-rc2.
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
---
include/standard-headers/linux/input-event-codes.h | 32 ++++++++
include/standard-headers/linux/input.h | 1 +
include/standard-headers/linux/virtio_config.h | 10 ++-
include/standard-headers/linux/virtio_ids.h | 1 +
include/standard-headers/linux/virtio_net.h | 3 +
include/standard-headers/linux/virtio_vsock.h | 94 ++++++++++++++++++++++
| 4 +-
| 2 +
| 41 ++++++++++
| 4 +-
| 18 ++++-
| 33 ++++++++
12 files changed, 236 insertions(+), 7 deletions(-)
create mode 100644 include/standard-headers/linux/virtio_vsock.h
diff --git a/include/standard-headers/linux/input-event-codes.h b/include/standard-headers/linux/input-event-codes.h
index 354f0de..5c10f7e 100644
--- a/include/standard-headers/linux/input-event-codes.h
+++ b/include/standard-headers/linux/input-event-codes.h
@@ -611,6 +611,37 @@
#define KEY_KBDINPUTASSIST_ACCEPT 0x264
#define KEY_KBDINPUTASSIST_CANCEL 0x265
+/* Diagonal movement keys */
+#define KEY_RIGHT_UP 0x266
+#define KEY_RIGHT_DOWN 0x267
+#define KEY_LEFT_UP 0x268
+#define KEY_LEFT_DOWN 0x269
+
+#define KEY_ROOT_MENU 0x26a /* Show Device's Root Menu */
+/* Show Top Menu of the Media (e.g. DVD) */
+#define KEY_MEDIA_TOP_MENU 0x26b
+#define KEY_NUMERIC_11 0x26c
+#define KEY_NUMERIC_12 0x26d
+/*
+ * Toggle Audio Description: refers to an audio service that helps blind and
+ * visually impaired consumers understand the action in a program. Note: in
+ * some countries this is referred to as "Video Description".
+ */
+#define KEY_AUDIO_DESC 0x26e
+#define KEY_3D_MODE 0x26f
+#define KEY_NEXT_FAVORITE 0x270
+#define KEY_STOP_RECORD 0x271
+#define KEY_PAUSE_RECORD 0x272
+#define KEY_VOD 0x273 /* Video on Demand */
+#define KEY_UNMUTE 0x274
+#define KEY_FASTREVERSE 0x275
+#define KEY_SLOWREVERSE 0x276
+/*
+ * Control a data application associated with the currently viewed channel,
+ * e.g. teletext or data broadcast application (MHEG, MHP, HbbTV, etc.)
+ */
+#define KEY_DATA 0x275
+
#define BTN_TRIGGER_HAPPY 0x2c0
#define BTN_TRIGGER_HAPPY1 0x2c0
#define BTN_TRIGGER_HAPPY2 0x2c1
@@ -749,6 +780,7 @@
#define SW_ROTATE_LOCK 0x0c /* set = rotate locked/disabled */
#define SW_LINEIN_INSERT 0x0d /* set = inserted */
#define SW_MUTE_DEVICE 0x0e /* set = device disabled */
+#define SW_PEN_INSERTED 0x0f /* set = pen inserted */
#define SW_MAX_ 0x0f
#define SW_CNT (SW_MAX_+1)
diff --git a/include/standard-headers/linux/input.h b/include/standard-headers/linux/input.h
index a52b202..7361a16 100644
--- a/include/standard-headers/linux/input.h
+++ b/include/standard-headers/linux/input.h
@@ -244,6 +244,7 @@ struct input_mask {
#define BUS_ATARI 0x1B
#define BUS_SPI 0x1C
#define BUS_RMI 0x1D
+#define BUS_CEC 0x1E
/*
* MT_TOOL types
diff --git a/include/standard-headers/linux/virtio_config.h b/include/standard-headers/linux/virtio_config.h
index b30d0cb..b777069 100644
--- a/include/standard-headers/linux/virtio_config.h
+++ b/include/standard-headers/linux/virtio_config.h
@@ -49,7 +49,7 @@
* transport being used (eg. virtio_ring), the rest are per-device feature
* bits. */
#define VIRTIO_TRANSPORT_F_START 28
-#define VIRTIO_TRANSPORT_F_END 33
+#define VIRTIO_TRANSPORT_F_END 34
#ifndef VIRTIO_CONFIG_NO_LEGACY
/* Do we get callbacks when the ring is completely used, even if we've
@@ -63,4 +63,12 @@
/* v1.0 compliant. */
#define VIRTIO_F_VERSION_1 32
+/*
+ * If clear - device has the IOMMU bypass quirk feature.
+ * If set - use platform tools to detect the IOMMU.
+ *
+ * Note the reverse polarity (compared to most other features),
+ * this is for compatibility with legacy systems.
+ */
+#define VIRTIO_F_IOMMU_PLATFORM 33
#endif /* _LINUX_VIRTIO_CONFIG_H */
diff --git a/include/standard-headers/linux/virtio_ids.h b/include/standard-headers/linux/virtio_ids.h
index 77925f5..3228d58 100644
--- a/include/standard-headers/linux/virtio_ids.h
+++ b/include/standard-headers/linux/virtio_ids.h
@@ -41,5 +41,6 @@
#define VIRTIO_ID_CAIF 12 /* Virtio caif */
#define VIRTIO_ID_GPU 16 /* virtio GPU */
#define VIRTIO_ID_INPUT 18 /* virtio input */
+#define VIRTIO_ID_VSOCK 19 /* virtio vsock transport */
#endif /* _LINUX_VIRTIO_IDS_H */
diff --git a/include/standard-headers/linux/virtio_net.h b/include/standard-headers/linux/virtio_net.h
index a78f33e..30ff249 100644
--- a/include/standard-headers/linux/virtio_net.h
+++ b/include/standard-headers/linux/virtio_net.h
@@ -35,6 +35,7 @@
#define VIRTIO_NET_F_CSUM 0 /* Host handles pkts w/ partial csum */
#define VIRTIO_NET_F_GUEST_CSUM 1 /* Guest handles pkts w/ partial csum */
#define VIRTIO_NET_F_CTRL_GUEST_OFFLOADS 2 /* Dynamic offload configuration. */
+#define VIRTIO_NET_F_MTU 3 /* Initial MTU advice */
#define VIRTIO_NET_F_MAC 5 /* Host has given MAC address. */
#define VIRTIO_NET_F_GUEST_TSO4 7 /* Guest can handle TSOv4 in. */
#define VIRTIO_NET_F_GUEST_TSO6 8 /* Guest can handle TSOv6 in. */
@@ -73,6 +74,8 @@ struct virtio_net_config {
* Legal values are between 1 and 0x8000
*/
uint16_t max_virtqueue_pairs;
+ /* Default maximum transmit unit advice */
+ uint16_t mtu;
} QEMU_PACKED;
/*
diff --git a/include/standard-headers/linux/virtio_vsock.h b/include/standard-headers/linux/virtio_vsock.h
new file mode 100644
index 0000000..be44321
--- /dev/null
+++ b/include/standard-headers/linux/virtio_vsock.h
@@ -0,0 +1,94 @@
+/*
+ * This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so
+ * anyone can use the definitions to implement compatible drivers/servers:
+ *
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS''
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
+ * Copyright (C) Red Hat, Inc., 2013-2015
+ * Copyright (C) Asias He <asias@redhat.com>, 2013
+ * Copyright (C) Stefan Hajnoczi <stefanha@redhat.com>, 2015
+ */
+
+#ifndef _LINUX_VIRTIO_VSOCK_H
+#define _LINUX_VIRTIO_VSOCK_H
+
+#include "standard-headers/linux/types.h"
+#include "standard-headers/linux/virtio_ids.h"
+#include "standard-headers/linux/virtio_config.h"
+
+struct virtio_vsock_config {
+ uint64_t guest_cid;
+} QEMU_PACKED;
+
+enum virtio_vsock_event_id {
+ VIRTIO_VSOCK_EVENT_TRANSPORT_RESET = 0,
+};
+
+struct virtio_vsock_event {
+ uint32_t id;
+} QEMU_PACKED;
+
+struct virtio_vsock_hdr {
+ uint64_t src_cid;
+ uint64_t dst_cid;
+ uint32_t src_port;
+ uint32_t dst_port;
+ uint32_t len;
+ uint16_t type; /* enum virtio_vsock_type */
+ uint16_t op; /* enum virtio_vsock_op */
+ uint32_t flags;
+ uint32_t buf_alloc;
+ uint32_t fwd_cnt;
+} QEMU_PACKED;
+
+enum virtio_vsock_type {
+ VIRTIO_VSOCK_TYPE_STREAM = 1,
+};
+
+enum virtio_vsock_op {
+ VIRTIO_VSOCK_OP_INVALID = 0,
+
+ /* Connect operations */
+ VIRTIO_VSOCK_OP_REQUEST = 1,
+ VIRTIO_VSOCK_OP_RESPONSE = 2,
+ VIRTIO_VSOCK_OP_RST = 3,
+ VIRTIO_VSOCK_OP_SHUTDOWN = 4,
+
+ /* To send payload */
+ VIRTIO_VSOCK_OP_RW = 5,
+
+ /* Tell the peer our credit info */
+ VIRTIO_VSOCK_OP_CREDIT_UPDATE = 6,
+ /* Request the peer to send the credit info to us */
+ VIRTIO_VSOCK_OP_CREDIT_REQUEST = 7,
+};
+
+/* VIRTIO_VSOCK_OP_SHUTDOWN flags values */
+enum virtio_vsock_shutdown {
+ VIRTIO_VSOCK_SHUTDOWN_RCV = 1,
+ VIRTIO_VSOCK_SHUTDOWN_SEND = 2,
+};
+
+#endif /* _LINUX_VIRTIO_VSOCK_H */
--git a/linux-headers/asm-arm/kvm.h b/linux-headers/asm-arm/kvm.h
index c98e4dc..541268c 100644
--- a/linux-headers/asm-arm/kvm.h
+++ b/linux-headers/asm-arm/kvm.h
@@ -139,8 +139,8 @@ struct kvm_arch_memory_slot {
#define ARM_CP15_REG64(...) __ARM_CP15_REG64(__VA_ARGS__)
#define KVM_REG_ARM_TIMER_CTL ARM_CP15_REG32(0, 14, 3, 1)
-#define KVM_REG_ARM_TIMER_CNT ARM_CP15_REG64(1, 14)
-#define KVM_REG_ARM_TIMER_CVAL ARM_CP15_REG64(3, 14)
+#define KVM_REG_ARM_TIMER_CNT ARM_CP15_REG64(1, 14)
+#define KVM_REG_ARM_TIMER_CVAL ARM_CP15_REG64(3, 14)
/* Normal registers are mapped as coprocessor 16. */
#define KVM_REG_ARM_CORE (0x0010 << KVM_REG_ARM_COPROC_SHIFT)
--git a/linux-headers/asm-arm64/kvm.h b/linux-headers/asm-arm64/kvm.h
index 7d82d1f..fd5a276 100644
--- a/linux-headers/asm-arm64/kvm.h
+++ b/linux-headers/asm-arm64/kvm.h
@@ -87,9 +87,11 @@ struct kvm_regs {
/* Supported VGICv3 address types */
#define KVM_VGIC_V3_ADDR_TYPE_DIST 2
#define KVM_VGIC_V3_ADDR_TYPE_REDIST 3
+#define KVM_VGIC_ITS_ADDR_TYPE 4
#define KVM_VGIC_V3_DIST_SIZE SZ_64K
#define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K)
+#define KVM_VGIC_V3_ITS_SIZE (2 * SZ_64K)
#define KVM_ARM_VCPU_POWER_OFF 0 /* CPU is started in OFF state */
#define KVM_ARM_VCPU_EL1_32BIT 1 /* CPU running a 32bit VM */
--git a/linux-headers/asm-s390/kvm.h b/linux-headers/asm-s390/kvm.h
index 09ae5dc..ac63ca6 100644
--- a/linux-headers/asm-s390/kvm.h
+++ b/linux-headers/asm-s390/kvm.h
@@ -93,6 +93,47 @@ struct kvm_s390_vm_cpu_machine {
__u64 fac_list[256];
};
+#define KVM_S390_VM_CPU_PROCESSOR_FEAT 2
+#define KVM_S390_VM_CPU_MACHINE_FEAT 3
+
+#define KVM_S390_VM_CPU_FEAT_NR_BITS 1024
+#define KVM_S390_VM_CPU_FEAT_ESOP 0
+#define KVM_S390_VM_CPU_FEAT_SIEF2 1
+#define KVM_S390_VM_CPU_FEAT_64BSCAO 2
+#define KVM_S390_VM_CPU_FEAT_SIIF 3
+#define KVM_S390_VM_CPU_FEAT_GPERE 4
+#define KVM_S390_VM_CPU_FEAT_GSLS 5
+#define KVM_S390_VM_CPU_FEAT_IB 6
+#define KVM_S390_VM_CPU_FEAT_CEI 7
+#define KVM_S390_VM_CPU_FEAT_IBS 8
+#define KVM_S390_VM_CPU_FEAT_SKEY 9
+#define KVM_S390_VM_CPU_FEAT_CMMA 10
+#define KVM_S390_VM_CPU_FEAT_PFMFI 11
+#define KVM_S390_VM_CPU_FEAT_SIGPIF 12
+struct kvm_s390_vm_cpu_feat {
+ __u64 feat[16];
+};
+
+#define KVM_S390_VM_CPU_PROCESSOR_SUBFUNC 4
+#define KVM_S390_VM_CPU_MACHINE_SUBFUNC 5
+/* for "test bit" instructions MSB 0 bit ordering, for "query" raw blocks */
+struct kvm_s390_vm_cpu_subfunc {
+ __u8 plo[32]; /* always */
+ __u8 ptff[16]; /* with TOD-clock steering */
+ __u8 kmac[16]; /* with MSA */
+ __u8 kmc[16]; /* with MSA */
+ __u8 km[16]; /* with MSA */
+ __u8 kimd[16]; /* with MSA */
+ __u8 klmd[16]; /* with MSA */
+ __u8 pckmo[16]; /* with MSA3 */
+ __u8 kmctr[16]; /* with MSA4 */
+ __u8 kmf[16]; /* with MSA4 */
+ __u8 kmo[16]; /* with MSA4 */
+ __u8 pcc[16]; /* with MSA4 */
+ __u8 ppno[16]; /* with MSA5 */
+ __u8 reserved[1824];
+};
+
/* kvm attributes for crypto */
#define KVM_S390_VM_CRYPTO_ENABLE_AES_KW 0
#define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW 1
--git a/linux-headers/asm-x86/unistd_x32.h b/linux-headers/asm-x86/unistd_x32.h
index 0230779..e5aea76 100644
--- a/linux-headers/asm-x86/unistd_x32.h
+++ b/linux-headers/asm-x86/unistd_x32.h
@@ -306,9 +306,7 @@
#define __NR_vmsplice (__X32_SYSCALL_BIT + 532)
#define __NR_move_pages (__X32_SYSCALL_BIT + 533)
#define __NR_preadv (__X32_SYSCALL_BIT + 534)
-#define __NR_preadv2 (__X32_SYSCALL_BIT + 534)
#define __NR_pwritev (__X32_SYSCALL_BIT + 535)
-#define __NR_pwritev2 (__X32_SYSCALL_BIT + 535)
#define __NR_rt_tgsigqueueinfo (__X32_SYSCALL_BIT + 536)
#define __NR_recvmmsg (__X32_SYSCALL_BIT + 537)
#define __NR_sendmmsg (__X32_SYSCALL_BIT + 538)
@@ -319,5 +317,7 @@
#define __NR_io_setup (__X32_SYSCALL_BIT + 543)
#define __NR_io_submit (__X32_SYSCALL_BIT + 544)
#define __NR_execveat (__X32_SYSCALL_BIT + 545)
+#define __NR_preadv2 (__X32_SYSCALL_BIT + 546)
+#define __NR_pwritev2 (__X32_SYSCALL_BIT + 547)
#endif /* _ASM_X86_UNISTD_X32_H */
--git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h
index e60e21b..4806e06 100644
--- a/linux-headers/linux/kvm.h
+++ b/linux-headers/linux/kvm.h
@@ -866,6 +866,10 @@ struct kvm_ppc_smmu_info {
#define KVM_CAP_ARM_PMU_V3 126
#define KVM_CAP_VCPU_ATTRIBUTES 127
#define KVM_CAP_MAX_VCPU_ID 128
+#define KVM_CAP_X2APIC_API 129
+#define KVM_CAP_S390_USER_INSTR0 130
+#define KVM_CAP_MSI_DEVID 131
+#define KVM_CAP_PPC_HTM 132
#ifdef KVM_CAP_IRQ_ROUTING
@@ -878,7 +882,10 @@ struct kvm_irq_routing_msi {
__u32 address_lo;
__u32 address_hi;
__u32 data;
- __u32 pad;
+ union {
+ __u32 pad;
+ __u32 devid;
+ };
};
struct kvm_irq_routing_s390_adapter {
@@ -1024,12 +1031,14 @@ struct kvm_one_reg {
__u64 addr;
};
+#define KVM_MSI_VALID_DEVID (1U << 0)
struct kvm_msi {
__u32 address_lo;
__u32 address_hi;
__u32 data;
__u32 flags;
- __u8 pad[16];
+ __u32 devid;
+ __u8 pad[12];
};
struct kvm_arm_device_addr {
@@ -1074,6 +1083,8 @@ enum kvm_device_type {
#define KVM_DEV_TYPE_FLIC KVM_DEV_TYPE_FLIC
KVM_DEV_TYPE_ARM_VGIC_V3,
#define KVM_DEV_TYPE_ARM_VGIC_V3 KVM_DEV_TYPE_ARM_VGIC_V3
+ KVM_DEV_TYPE_ARM_VGIC_ITS,
+#define KVM_DEV_TYPE_ARM_VGIC_ITS KVM_DEV_TYPE_ARM_VGIC_ITS
KVM_DEV_TYPE_MAX,
};
@@ -1313,4 +1324,7 @@ struct kvm_assigned_msix_entry {
__u16 padding[3];
};
+#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0)
+#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1)
+
#endif /* __LINUX_KVM_H */
--git a/linux-headers/linux/vhost.h b/linux-headers/linux/vhost.h
index 571294c..ac7a1f1 100644
--- a/linux-headers/linux/vhost.h
+++ b/linux-headers/linux/vhost.h
@@ -47,6 +47,32 @@ struct vhost_vring_addr {
__u64 log_guest_addr;
};
+/* no alignment requirement */
+struct vhost_iotlb_msg {
+ __u64 iova;
+ __u64 size;
+ __u64 uaddr;
+#define VHOST_ACCESS_RO 0x1
+#define VHOST_ACCESS_WO 0x2
+#define VHOST_ACCESS_RW 0x3
+ __u8 perm;
+#define VHOST_IOTLB_MISS 1
+#define VHOST_IOTLB_UPDATE 2
+#define VHOST_IOTLB_INVALIDATE 3
+#define VHOST_IOTLB_ACCESS_FAIL 4
+ __u8 type;
+};
+
+#define VHOST_IOTLB_MSG 0x1
+
+struct vhost_msg {
+ int type;
+ union {
+ struct vhost_iotlb_msg iotlb;
+ __u8 padding[64];
+ };
+};
+
struct vhost_memory_region {
__u64 guest_phys_addr;
__u64 memory_size; /* bytes */
@@ -146,6 +172,8 @@ struct vhost_memory {
#define VHOST_F_LOG_ALL 26
/* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */
#define VHOST_NET_F_VIRTIO_NET_HDR 27
+/* Vhost have device IOTLB */
+#define VHOST_F_DEVICE_IOTLB 63
/* VHOST_SCSI specific definitions */
@@ -175,4 +203,9 @@ struct vhost_scsi_target {
#define VHOST_SCSI_SET_EVENTS_MISSED _IOW(VHOST_VIRTIO, 0x43, __u32)
#define VHOST_SCSI_GET_EVENTS_MISSED _IOW(VHOST_VIRTIO, 0x44, __u32)
+/* VHOST_VSOCK specific defines */
+
+#define VHOST_VSOCK_SET_GUEST_CID _IOW(VHOST_VIRTIO, 0x60, __u64)
+#define VHOST_VSOCK_SET_RUNNING _IOW(VHOST_VIRTIO, 0x61, int)
+
#endif
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 02/67] hw/ppc/spapr: Move code related to "ibm, pa-features" to a separate function
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
2016-12-15 0:43 ` [Qemu-devel] [PATCH 01/67] linux-headers: update Michael Roth
@ 2016-12-15 0:43 ` Michael Roth
2016-12-15 0:43 ` [Qemu-devel] [PATCH 03/67] hw/ppc/spapr: Fix the selection of the processor features Michael Roth
` (65 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:43 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Thomas Huth, David Gibson
From: Thomas Huth <thuth@redhat.com>
The function spapr_populate_cpu_dt() has become quite big
already, and since we likely have to extend the pa-features
property for every new processor generation, it is nicer
if we put the related code into a separate function.
Signed-off-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
(cherry picked from commit 230bf719d3a3b144a4ffa441e5d6170ef0ad8999)
---
hw/ppc/spapr.c | 66 ++++++++++++++++++++++++++++++++--------------------------
1 file changed, 36 insertions(+), 30 deletions(-)
diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index 30d6800..36d9077 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -594,6 +594,41 @@ static int spapr_populate_memory(sPAPRMachineState *spapr, void *fdt)
return 0;
}
+/* Populate the "ibm,pa-features" property */
+static void spapr_populate_pa_features(CPUPPCState *env, void *fdt, int offset)
+{
+ uint8_t pa_features_206[] = { 6, 0,
+ 0xf6, 0x1f, 0xc7, 0x00, 0x80, 0xc0 };
+ uint8_t pa_features_207[] = { 24, 0,
+ 0xf6, 0x1f, 0xc7, 0xc0, 0x80, 0xf0,
+ 0x80, 0x00, 0x00, 0x00, 0x00, 0x00,
+ 0x00, 0x00, 0x00, 0x00, 0x80, 0x00,
+ 0x80, 0x00, 0x80, 0x00, 0x80, 0x00 };
+ uint8_t *pa_features;
+ size_t pa_size;
+
+ if (env->mmu_model == POWERPC_MMU_2_06) {
+ pa_features = pa_features_206;
+ pa_size = sizeof(pa_features_206);
+ } else { /* env->mmu_model == POWERPC_MMU_2_07 */
+ pa_features = pa_features_207;
+ pa_size = sizeof(pa_features_207);
+ }
+
+ if (env->ci_large_pages) {
+ /*
+ * Note: we keep CI large pages off by default because a 64K capable
+ * guest provisioned with large pages might otherwise try to map a qemu
+ * framebuffer (or other kind of memory mapped PCI BAR) using 64K pages
+ * even if that qemu runs on a 4k host.
+ * We dd this bit back here if we are confident this is not an issue
+ */
+ pa_features[3] |= 0x20;
+ }
+
+ _FDT((fdt_setprop(fdt, offset, "ibm,pa-features", pa_features, pa_size)));
+}
+
static void spapr_populate_cpu_dt(CPUState *cs, void *fdt, int offset,
sPAPRMachineState *spapr)
{
@@ -621,24 +656,6 @@ static void spapr_populate_cpu_dt(CPUState *cs, void *fdt, int offset,
_FDT((fdt_setprop_cell(fdt, offset, "ibm,my-drc-index", drc_index)));
}
- /* Note: we keep CI large pages off for now because a 64K capable guest
- * provisioned with large pages might otherwise try to map a qemu
- * framebuffer (or other kind of memory mapped PCI BAR) using 64K pages
- * even if that qemu runs on a 4k host.
- *
- * We can later add this bit back when we are confident this is not
- * an issue (!HV KVM or 64K host)
- */
- uint8_t pa_features_206[] = { 6, 0,
- 0xf6, 0x1f, 0xc7, 0x00, 0x80, 0xc0 };
- uint8_t pa_features_207[] = { 24, 0,
- 0xf6, 0x1f, 0xc7, 0xc0, 0x80, 0xf0,
- 0x80, 0x00, 0x00, 0x00, 0x00, 0x00,
- 0x00, 0x00, 0x00, 0x00, 0x80, 0x00,
- 0x80, 0x00, 0x80, 0x00, 0x80, 0x00 };
- uint8_t *pa_features;
- size_t pa_size;
-
_FDT((fdt_setprop_cell(fdt, offset, "reg", index)));
_FDT((fdt_setprop_string(fdt, offset, "device_type", "cpu")));
@@ -705,18 +722,7 @@ static void spapr_populate_cpu_dt(CPUState *cs, void *fdt, int offset,
page_sizes_prop, page_sizes_prop_size)));
}
- /* Do the ibm,pa-features property, adjust it for ci-large-pages */
- if (env->mmu_model == POWERPC_MMU_2_06) {
- pa_features = pa_features_206;
- pa_size = sizeof(pa_features_206);
- } else /* env->mmu_model == POWERPC_MMU_2_07 */ {
- pa_features = pa_features_207;
- pa_size = sizeof(pa_features_207);
- }
- if (env->ci_large_pages) {
- pa_features[3] |= 0x20;
- }
- _FDT((fdt_setprop(fdt, offset, "ibm,pa-features", pa_features, pa_size)));
+ spapr_populate_pa_features(env, fdt, offset);
_FDT((fdt_setprop_cell(fdt, offset, "ibm,chip-id",
cs->cpu_index / vcpus_per_socket)));
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 03/67] hw/ppc/spapr: Fix the selection of the processor features
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
2016-12-15 0:43 ` [Qemu-devel] [PATCH 01/67] linux-headers: update Michael Roth
2016-12-15 0:43 ` [Qemu-devel] [PATCH 02/67] hw/ppc/spapr: Move code related to "ibm, pa-features" to a separate function Michael Roth
@ 2016-12-15 0:43 ` Michael Roth
2016-12-15 0:43 ` [Qemu-devel] [PATCH 04/67] ppc: Check the availability of transactional memory Michael Roth
` (64 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:43 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Thomas Huth, David Gibson
From: Thomas Huth <thuth@redhat.com>
The current code uses pa_features_206 for POWERPC_MMU_2_06, and
for everything else, it uses pa_features_207. This is bad in some
cases because there is also a "degraded" MMU version of ISA 2.06,
called POWERPC_MMU_2_06a, which should of course use the flags for
2.06 instead. And there is also the possibility that the user runs
the pseries machine with a POWER5+ or even 970 processor. In that
case we certainly do not want to set the flags for 2.07, and rather
simply skip the setting of the pa-features property instead.
Signed-off-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
(cherry picked from commit 4cbec30d769a73853b60dc7f275e6e7da9ab5162)
---
hw/ppc/spapr.c | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index 36d9077..9f0d99b 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -607,12 +607,19 @@ static void spapr_populate_pa_features(CPUPPCState *env, void *fdt, int offset)
uint8_t *pa_features;
size_t pa_size;
- if (env->mmu_model == POWERPC_MMU_2_06) {
+ switch (env->mmu_model) {
+ case POWERPC_MMU_2_06:
+ case POWERPC_MMU_2_06a:
pa_features = pa_features_206;
pa_size = sizeof(pa_features_206);
- } else { /* env->mmu_model == POWERPC_MMU_2_07 */
+ break;
+ case POWERPC_MMU_2_07:
+ case POWERPC_MMU_2_07a:
pa_features = pa_features_207;
pa_size = sizeof(pa_features_207);
+ break;
+ default:
+ return;
}
if (env->ci_large_pages) {
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 04/67] ppc: Check the availability of transactional memory
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (2 preceding siblings ...)
2016-12-15 0:43 ` [Qemu-devel] [PATCH 03/67] hw/ppc/spapr: Fix the selection of the processor features Michael Roth
@ 2016-12-15 0:43 ` Michael Roth
2016-12-15 0:43 ` [Qemu-devel] [PATCH 05/67] virtio: zero vq->inuse in virtio_reset() Michael Roth
` (63 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:43 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Thomas Huth, David Gibson
From: Thomas Huth <thuth@redhat.com>
KVM-PR currently does not support transactional memory, and the
implementation in TCG is just a fake. We should not announce TM
support in the ibm,pa-features property when running on such a
system, so disable it by default and only enable it if the KVM
implementation supports it (i.e. recent versions of KVM-HV).
These changes are based on some earlier work from Anton Blanchard
(thanks!).
Signed-off-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
(cherry picked from commit bac3bf287ab60e264b636f5f00c116a19b655762)
---
hw/ppc/spapr.c | 5 ++++-
target-ppc/kvm.c | 7 +++++++
target-ppc/kvm_ppc.h | 6 ++++++
3 files changed, 17 insertions(+), 1 deletion(-)
diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index 9f0d99b..82723d1 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -603,7 +603,7 @@ static void spapr_populate_pa_features(CPUPPCState *env, void *fdt, int offset)
0xf6, 0x1f, 0xc7, 0xc0, 0x80, 0xf0,
0x80, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x80, 0x00,
- 0x80, 0x00, 0x80, 0x00, 0x80, 0x00 };
+ 0x80, 0x00, 0x80, 0x00, 0x00, 0x00 };
uint8_t *pa_features;
size_t pa_size;
@@ -632,6 +632,9 @@ static void spapr_populate_pa_features(CPUPPCState *env, void *fdt, int offset)
*/
pa_features[3] |= 0x20;
}
+ if (kvmppc_has_cap_htm() && pa_size > 24) {
+ pa_features[24] |= 0x80; /* Transactional memory support */
+ }
_FDT((fdt_setprop(fdt, offset, "ibm,pa-features", pa_features, pa_size)));
}
diff --git a/target-ppc/kvm.c b/target-ppc/kvm.c
index dcb68b9..f26a141 100644
--- a/target-ppc/kvm.c
+++ b/target-ppc/kvm.c
@@ -79,6 +79,7 @@ static int cap_ppc_watchdog;
static int cap_papr;
static int cap_htab_fd;
static int cap_fixup_hcalls;
+static int cap_htm; /* Hardware transactional memory support */
static uint32_t debug_inst_opcode;
@@ -121,6 +122,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
* only activated after this by kvmppc_set_papr() */
cap_htab_fd = kvm_check_extension(s, KVM_CAP_PPC_HTAB_FD);
cap_fixup_hcalls = kvm_check_extension(s, KVM_CAP_PPC_FIXUP_HCALL);
+ cap_htm = kvm_vm_check_extension(s, KVM_CAP_PPC_HTM);
if (!cap_interrupt_level) {
fprintf(stderr, "KVM: Couldn't find level irq capability. Expect the "
@@ -2339,6 +2341,11 @@ bool kvmppc_has_cap_fixup_hcalls(void)
return cap_fixup_hcalls;
}
+bool kvmppc_has_cap_htm(void)
+{
+ return cap_htm;
+}
+
static PowerPCCPUClass *ppc_cpu_get_family_class(PowerPCCPUClass *pcc)
{
ObjectClass *oc = OBJECT_CLASS(pcc);
diff --git a/target-ppc/kvm_ppc.h b/target-ppc/kvm_ppc.h
index 5461d10..e45c815 100644
--- a/target-ppc/kvm_ppc.h
+++ b/target-ppc/kvm_ppc.h
@@ -54,6 +54,7 @@ void kvmppc_hash64_free_pteg(uint64_t token);
void kvmppc_hash64_write_pte(CPUPPCState *env, target_ulong pte_index,
target_ulong pte0, target_ulong pte1);
bool kvmppc_has_cap_fixup_hcalls(void);
+bool kvmppc_has_cap_htm(void);
int kvmppc_enable_hwrng(void);
int kvmppc_put_books_sregs(PowerPCCPU *cpu);
PowerPCCPUClass *kvm_ppc_get_host_cpu_class(void);
@@ -244,6 +245,11 @@ static inline bool kvmppc_has_cap_fixup_hcalls(void)
abort();
}
+static inline bool kvmppc_has_cap_htm(void)
+{
+ return false;
+}
+
static inline int kvmppc_enable_hwrng(void)
{
return -1;
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 05/67] virtio: zero vq->inuse in virtio_reset()
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (3 preceding siblings ...)
2016-12-15 0:43 ` [Qemu-devel] [PATCH 04/67] ppc: Check the availability of transactional memory Michael Roth
@ 2016-12-15 0:43 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 06/67] virtio-balloon: discard virtqueue element on reset Michael Roth
` (62 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:43 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Stefan Hajnoczi, Michael S. Tsirkin
From: Stefan Hajnoczi <stefanha@redhat.com>
vq->inuse must be zeroed upon device reset like most other virtqueue
fields.
In theory, virtio_reset() just needs assert(vq->inuse == 0) since
devices must clean up in-flight requests during reset (requests cannot
not be leaked!).
In practice, it is difficult to achieve vq->inuse == 0 across reset
because balloon, blk, 9p, etc implement various different strategies for
cleaning up requests. Most devices call g_free(elem) directly without
telling virtio.c that the VirtQueueElement is cleaned up. Therefore
vq->inuse is not decremented during reset.
This patch zeroes vq->inuse and trusts that devices are not leaking
VirtQueueElements across reset.
I will send a follow-up series that refactors request life-cycle across
all devices and converts vq->inuse = 0 into assert(vq->inuse == 0) but
this more invasive approach is not appropriate for stable trees.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Cc: qemu-stable <qemu-stable@nongnu.org>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Ladi Prosek <lprosek@redhat.com>
(cherry picked from commit 4b7f91ed0270a371e1933efa21ba600b6da23ab9)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/virtio/virtio.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c
index 74c085c..e8a13a5 100644
--- a/hw/virtio/virtio.c
+++ b/hw/virtio/virtio.c
@@ -822,6 +822,7 @@ void virtio_reset(void *opaque)
vdev->vq[i].signalled_used_valid = false;
vdev->vq[i].notification = true;
vdev->vq[i].vring.num = vdev->vq[i].vring.num_default;
+ vdev->vq[i].inuse = 0;
}
}
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 06/67] virtio-balloon: discard virtqueue element on reset
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (4 preceding siblings ...)
2016-12-15 0:43 ` [Qemu-devel] [PATCH 05/67] virtio: zero vq->inuse in virtio_reset() Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 07/67] vnc: fix qemu crash because of SIGSEGV Michael Roth
` (61 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel
Cc: qemu-stable, Ladi Prosek, Michael S. Tsirkin, Roman Kagan,
Stefan Hajnoczi
From: Ladi Prosek <lprosek@redhat.com>
The one pending element is being freed but not discarded on device
reset, which causes svq->inuse to creep up, eventually hitting the
"Virtqueue size exceeded" error.
Properly discarding the element on device reset makes sure that its
buffers are unmapped and the inuse counter stays balanced.
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Roman Kagan <rkagan@virtuozzo.com>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Ladi Prosek <lprosek@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit 104e70cae78bd4afd95d948c6aff188f10508a9c)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/virtio/virtio-balloon.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c
index 5af429a..ad4189a 100644
--- a/hw/virtio/virtio-balloon.c
+++ b/hw/virtio/virtio-balloon.c
@@ -463,6 +463,7 @@ static void virtio_balloon_device_reset(VirtIODevice *vdev)
VirtIOBalloon *s = VIRTIO_BALLOON(vdev);
if (s->stats_vq_elem != NULL) {
+ virtqueue_discard(s->svq, s->stats_vq_elem, 0);
g_free(s->stats_vq_elem);
s->stats_vq_elem = NULL;
}
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 07/67] vnc: fix qemu crash because of SIGSEGV
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (5 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 06/67] virtio-balloon: discard virtqueue element on reset Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 08/67] 9pfs: fix potential segfault during walk Michael Roth
` (60 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Gonglei, Gerd Hoffmann, Daniel P. Berrange
From: Gonglei <arei.gonglei@huawei.com>
The backtrace is:
0x00007f0b75cdf880 in pixman_image_get_stride () from /lib64/libpixman-1.so.0
0x00007f0b77bcb3cf in vnc_server_fb_stride (vd=0x7f0b7a1a2bb0) at ui/vnc.c:680
vnc_dpy_copy (dcl=0x7f0b7a1a2c00, src_x=224, src_y=263, dst_x=319, dst_y=363, w=1, h=1) at ui/vnc.c:915
0x00007f0b77bbcc35 in dpy_gfx_copy (con=0x7f0b7a146210, src_x=src_x@entry=224, src_y=src_y@entry=263, dst_x=dst_x@entry=319,
dst_y=dst_y@entry=363, w=1, h=1) at ui/console.c:1575
0x00007f0b77bbda4e in qemu_console_copy (con=<optimized out>, src_x=src_x@entry=224, src_y=src_y@entry=263, dst_x=dst_x@entry=319,
dst_y=dst_y@entry=363, w=<optimized out>, h=<optimized out>) at ui/console.c:2111
0x00007f0b77ac0980 in cirrus_do_copy (h=<optimized out>, w=<optimized out>, src=<optimized out>, dst=<optimized out>, s=0x7f0b7b086090) at hw/display/cirrus_vga.c:774
cirrus_bitblt_videotovideo_copy (s=0x7f0b7b086090) at hw/display/cirrus_vga.c:793
cirrus_bitblt_videotovideo (s=0x7f0b7b086090) at hw/display/cirrus_vga.c:915
cirrus_bitblt_start (s=0x7f0b7b086090) at hw/display/cirrus_vga.c:1056
0x00007f0b77965cfb in memory_region_write_accessor (mr=0x7f0b7b096e40, addr=320, value=<optimized out>, size=1, shift=<optimized out>,mask=<optimized out>, attrs=...) at /root/rpmbuild/BUILD/master/qemu/memory.c:525
0x00007f0b77963f59 in access_with_adjusted_size (addr=addr@entry=320, value=value@entry=0x7f0b69a268d8, size=size@entry=4,
access_size_min=<optimized out>, access_size_max=<optimized out>, access=access@entry=0x7f0b77965c80 <memory_region_write_accessor>,
mr=mr@entry=0x7f0b7b096e40, attrs=attrs@entry=...) at /root/rpmbuild/BUILD/master/qemu/memory.c:591
0x00007f0b77968315 in memory_region_dispatch_write (mr=mr@entry=0x7f0b7b096e40, addr=addr@entry=320, data=18446744073709551362,
size=size@entry=4, attrs=attrs@entry=...) at /root/rpmbuild/BUILD/master/qemu/memory.c:1262
0x00007f0b779256a9 in address_space_write_continue (mr=0x7f0b7b096e40, l=4, addr1=320, len=4, buf=0x7f0b77713028 "\002\377\377\377",
attrs=..., addr=4273930560, as=0x7f0b7827d280 <address_space_memory>) at /root/rpmbuild/BUILD/master/qemu/exec.c:2544
address_space_write (as=<optimized out>, addr=<optimized out>, attrs=..., buf=<optimized out>, len=<optimized out>) at /root/rpmbuild/BUILD/master/qemu/exec.c:2601
0x00007f0b77925c1d in address_space_rw (as=<optimized out>, addr=<optimized out>, attrs=..., attrs@entry=...,
buf=buf@entry=0x7f0b77713028 "\002\377\377\377", len=<optimized out>, is_write=<optimized out>) at /root/rpmbuild/BUILD/master/qemu/exec.c:2703
0x00007f0b77962f53 in kvm_cpu_exec (cpu=cpu@entry=0x7f0b79fcc2d0) at /root/rpmbuild/BUILD/master/qemu/kvm-all.c:1965
0x00007f0b77950cc6 in qemu_kvm_cpu_thread_fn (arg=0x7f0b79fcc2d0) at /root/rpmbuild/BUILD/master/qemu/cpus.c:1078
0x00007f0b744b3dc5 in start_thread (arg=0x7f0b69a27700) at pthread_create.c:308
0x00007f0b70d3d66d in clone () from /lib64/libc.so.6
The code path while meeting segfault:
vnc_dpy_copy
vnc_update_client
vnc_disconnect_finish [while vnc_disconnect_start() is invoked because somethins wrong]
vnc_update_server_surface
vd->server = NULL;
vnc_server_fb_stride
pixman_image_get_stride(vd->server)
Let's add a non-NULL check before calling vnc_server_fb_stride() to avoid segmentation fault.
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: Daniel P. Berrange <berrange@redhat.com>
Reported-by: Yanying Zhuang <ann.zhuangyanying@huawei.com>
Signed-off-by: Gonglei <arei.gonglei@huawei.com>
Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Message-id: 1472788698-120964-1-git-send-email-arei.gonglei@huawei.com
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit 3e10c3ecfcaf604d8b400d6e463e1a186ce97d9b)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
ui/vnc.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/ui/vnc.c b/ui/vnc.c
index d1087c9..76a3273 100644
--- a/ui/vnc.c
+++ b/ui/vnc.c
@@ -911,6 +911,10 @@ static void vnc_dpy_copy(DisplayChangeListener *dcl,
}
}
+ if (!vd->server) {
+ /* no client connected */
+ return;
+ }
/* do bitblit op on the local surface too */
pitch = vnc_server_fb_stride(vd);
src_row = vnc_server_fb_ptr(vd, src_x, src_y);
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 08/67] 9pfs: fix potential segfault during walk
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (6 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 07/67] vnc: fix qemu crash because of SIGSEGV Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 09/67] scsi: mptsas: use g_new0 to allocate MPTSASRequest object Michael Roth
` (59 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Greg Kurz
From: Greg Kurz <groug@kaod.org>
If the call to fid_to_qid() returns an error, we will call v9fs_path_free()
on uninitialized paths.
It is a regression introduced by the following commit:
56f101ecce0e 9pfs: handle walk of ".." in the root directory
Let's fix this by initializing dpath and path before calling fid_to_qid().
Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Cédric Le Goater <clg@kaod.org>
[groug: updated the changelog to indicate this is regression and to provide
the offending commit SHA1]
Signed-off-by: Greg Kurz <groug@kaod.org>
(cherry picked from commit 13fd08e631ec0c3ff5ad1bdcb6a4474c7d9a024f)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/9pfs/9p.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/hw/9pfs/9p.c b/hw/9pfs/9p.c
index dfe293d..91a4970 100644
--- a/hw/9pfs/9p.c
+++ b/hw/9pfs/9p.c
@@ -1320,13 +1320,14 @@ static void v9fs_walk(void *opaque)
goto out_nofid;
}
+ v9fs_path_init(&dpath);
+ v9fs_path_init(&path);
+
err = fid_to_qid(pdu, fidp, &qid);
if (err < 0) {
goto out;
}
- v9fs_path_init(&dpath);
- v9fs_path_init(&path);
/*
* Both dpath and path initially poin to fidp.
* Needed to handle request with nwnames == 0
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 09/67] scsi: mptsas: use g_new0 to allocate MPTSASRequest object
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (7 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 08/67] 9pfs: fix potential segfault during walk Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 10/67] scsi: pvscsi: limit process IO loop to ring size Michael Roth
` (58 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Li Qiang, Prasad J Pandit, Paolo Bonzini
From: Li Qiang <liqiang6-s@360.cn>
When processing IO request in mptsas, it uses g_new to allocate
a 'req' object. If an error occurs before 'req->sreq' is
allocated, It could lead to an OOB write in mptsas_free_request
function. Use g_new0 to avoid it.
Reported-by: Li Qiang <liqiang6-s@360.cn>
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Message-Id: <1473684251-17476-1-git-send-email-ppandit@redhat.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 670e56d3ed2918b3861d9216f2c0540d9e9ae0d5)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/scsi/mptsas.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/hw/scsi/mptsas.c b/hw/scsi/mptsas.c
index 0e0a22f..eaae1bb 100644
--- a/hw/scsi/mptsas.c
+++ b/hw/scsi/mptsas.c
@@ -304,7 +304,7 @@ static int mptsas_process_scsi_io_request(MPTSASState *s,
goto bad;
}
- req = g_new(MPTSASRequest, 1);
+ req = g_new0(MPTSASRequest, 1);
QTAILQ_INSERT_TAIL(&s->pending, req, next);
req->scsi_io = *scsi_io;
req->dev = s;
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 10/67] scsi: pvscsi: limit process IO loop to ring size
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (8 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 09/67] scsi: mptsas: use g_new0 to allocate MPTSASRequest object Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 11/67] qemu-char: avoid segfault if user lacks of permisson of a given logfile Michael Roth
` (57 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Prasad J Pandit, Paolo Bonzini
From: Prasad J Pandit <pjp@fedoraproject.org>
Vmware Paravirtual SCSI emulator while processing IO requests
could run into an infinite loop if 'pvscsi_ring_pop_req_descr'
always returned positive value. Limit IO loop to the ring size.
Cc: qemu-stable@nongnu.org
Reported-by: Li Qiang <liqiang6-s@360.cn>
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Message-Id: <1473845952-30785-1-git-send-email-ppandit@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit d251157ac1928191af851d199a9ff255d330bec9)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/scsi/vmw_pvscsi.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/hw/scsi/vmw_pvscsi.c b/hw/scsi/vmw_pvscsi.c
index 5116f4a..aaaae0a 100644
--- a/hw/scsi/vmw_pvscsi.c
+++ b/hw/scsi/vmw_pvscsi.c
@@ -251,8 +251,11 @@ static hwaddr
pvscsi_ring_pop_req_descr(PVSCSIRingInfo *mgr)
{
uint32_t ready_ptr = RS_GET_FIELD(mgr, reqProdIdx);
+ uint32_t ring_size = PVSCSI_MAX_NUM_PAGES_REQ_RING
+ * PVSCSI_MAX_NUM_REQ_ENTRIES_PER_PAGE;
- if (ready_ptr != mgr->consumed_ptr) {
+ if (ready_ptr != mgr->consumed_ptr
+ && ready_ptr - mgr->consumed_ptr < ring_size) {
uint32_t next_ready_ptr =
mgr->consumed_ptr++ & mgr->txr_len_mask;
uint32_t next_ready_page =
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 11/67] qemu-char: avoid segfault if user lacks of permisson of a given logfile
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (9 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 10/67] scsi: pvscsi: limit process IO loop to ring size Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 12/67] scsi-disk: change disk serial length from 20 to 36 Michael Roth
` (56 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Lin Ma, Paolo Bonzini
From: Lin Ma <lma@suse.com>
Function qemu_chr_alloc returns NULL if it failed to open logfile by any reason,
says no write permission. For backends tty, stdio and msmouse, They need to
check this return value to avoid segfault in this case.
Signed-off-by: Lin Ma <lma@suse.com>
Cc: qemu-stable <qemu-stable@nongnu.org>
Message-Id: <20160914062250.22226-1-lma@suse.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 71200fb9664c2967a1cdd22b68b0da3a8b2b3eb7)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
backends/msmouse.c | 3 +++
qemu-char.c | 6 ++++++
2 files changed, 9 insertions(+)
diff --git a/backends/msmouse.c b/backends/msmouse.c
index aeb9055..aceb6dc 100644
--- a/backends/msmouse.c
+++ b/backends/msmouse.c
@@ -159,6 +159,9 @@ static CharDriverState *qemu_chr_open_msmouse(const char *id,
CharDriverState *chr;
chr = qemu_chr_alloc(common, errp);
+ if (!chr) {
+ return NULL;
+ }
chr->chr_write = msmouse_chr_write;
chr->chr_close = msmouse_chr_close;
chr->chr_accept_input = msmouse_chr_accept_input;
diff --git a/qemu-char.c b/qemu-char.c
index 5f82ebb..fdb23f5 100644
--- a/qemu-char.c
+++ b/qemu-char.c
@@ -1223,6 +1223,9 @@ static CharDriverState *qemu_chr_open_stdio(const char *id,
sigaction(SIGCONT, &act, NULL);
chr = qemu_chr_open_fd(0, 1, common, errp);
+ if (!chr) {
+ return NULL;
+ }
chr->chr_close = qemu_chr_close_stdio;
chr->chr_set_echo = qemu_chr_set_echo_stdio;
if (opts->has_signal) {
@@ -1679,6 +1682,9 @@ static CharDriverState *qemu_chr_open_tty_fd(int fd,
tty_serial_init(fd, 115200, 'N', 8, 1);
chr = qemu_chr_open_fd(fd, fd, backend, errp);
+ if (!chr) {
+ return NULL;
+ }
chr->chr_ioctl = tty_serial_ioctl;
chr->chr_close = qemu_chr_close_tty;
return chr;
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 12/67] scsi-disk: change disk serial length from 20 to 36
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (10 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 11/67] qemu-char: avoid segfault if user lacks of permisson of a given logfile Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 13/67] vmw_pvscsi: check page count while initialising descriptor rings Michael Roth
` (55 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Rony Weng, Paolo Bonzini
From: Rony Weng <ronyweng@synology.com>
Openstack Cinder assigns volume a 36 characters uuid as serial.
QEMU will shrinks the uuid to 20 characters, which does not match
the original uuid.
Note that there is no limit to the length of the serial number in
the SCSI spec. 20 was copy-pasted from virtio-blk which in turn was
copy-pasted from ATA; 36 is even more arbitrary. However, bumping it
up too much might cause issues (e.g. 252 seems to make sense because
then the maximum amount of returned data is 256; but who knows there's
no off-by-one somewhere for such a nicely rounded number).
Signed-off-by: Rony Weng <ronyweng@synology.com>
Message-Id: <1472457138-23386-1-git-send-email-ronyweng@synology.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 48b6206305b8d56524ac2ee347b68e6e0a528559)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/scsi/scsi-disk.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c
index 836a155..0e1bb68 100644
--- a/hw/scsi/scsi-disk.c
+++ b/hw/scsi/scsi-disk.c
@@ -599,8 +599,8 @@ static int scsi_disk_emulate_inquiry(SCSIRequest *req, uint8_t *outbuf)
}
l = strlen(s->serial);
- if (l > 20) {
- l = 20;
+ if (l > 36) {
+ l = 36;
}
DPRINTF("Inquiry EVPD[Serial number] "
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 13/67] vmw_pvscsi: check page count while initialising descriptor rings
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (11 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 12/67] scsi-disk: change disk serial length from 20 to 36 Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 14/67] scsi: mptconfig: fix an assert expression Michael Roth
` (54 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Prasad J Pandit, Paolo Bonzini
From: Prasad J Pandit <pjp@fedoraproject.org>
Vmware Paravirtual SCSI emulation uses command descriptors to
process SCSI commands. These descriptors come with their ring
buffers. A guest could set the page count for these rings to
an arbitrary value, leading to infinite loop or OOB access.
Add check to avoid it.
Reported-by: Tom Victor <vv474172261@gmail.com>
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Message-Id: <1472626169-12989-1-git-send-email-ppandit@redhat.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 7f61f4690dd153be98900a2a508b88989e692753)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/scsi/vmw_pvscsi.c | 19 +++++++++----------
1 file changed, 9 insertions(+), 10 deletions(-)
diff --git a/hw/scsi/vmw_pvscsi.c b/hw/scsi/vmw_pvscsi.c
index aaaae0a..4d94b36 100644
--- a/hw/scsi/vmw_pvscsi.c
+++ b/hw/scsi/vmw_pvscsi.c
@@ -152,7 +152,7 @@ pvscsi_log2(uint32_t input)
return log;
}
-static int
+static void
pvscsi_ring_init_data(PVSCSIRingInfo *m, PVSCSICmdDescSetupRings *ri)
{
int i;
@@ -160,10 +160,6 @@ pvscsi_ring_init_data(PVSCSIRingInfo *m, PVSCSICmdDescSetupRings *ri)
uint32_t req_ring_size, cmp_ring_size;
m->rs_pa = ri->ringsStatePPN << VMW_PAGE_SHIFT;
- if ((ri->reqRingNumPages > PVSCSI_SETUP_RINGS_MAX_NUM_PAGES)
- || (ri->cmpRingNumPages > PVSCSI_SETUP_RINGS_MAX_NUM_PAGES)) {
- return -1;
- }
req_ring_size = ri->reqRingNumPages * PVSCSI_MAX_NUM_REQ_ENTRIES_PER_PAGE;
cmp_ring_size = ri->cmpRingNumPages * PVSCSI_MAX_NUM_CMP_ENTRIES_PER_PAGE;
txr_len_log2 = pvscsi_log2(req_ring_size - 1);
@@ -195,8 +191,6 @@ pvscsi_ring_init_data(PVSCSIRingInfo *m, PVSCSICmdDescSetupRings *ri)
/* Flush ring state page changes */
smp_wmb();
-
- return 0;
}
static int
@@ -749,7 +743,7 @@ pvscsi_dbg_dump_tx_rings_config(PVSCSICmdDescSetupRings *rc)
trace_pvscsi_tx_rings_num_pages("Confirm Ring", rc->cmpRingNumPages);
for (i = 0; i < rc->cmpRingNumPages; i++) {
- trace_pvscsi_tx_rings_ppn("Confirm Ring", rc->reqRingPPNs[i]);
+ trace_pvscsi_tx_rings_ppn("Confirm Ring", rc->cmpRingPPNs[i]);
}
}
@@ -782,11 +776,16 @@ pvscsi_on_cmd_setup_rings(PVSCSIState *s)
trace_pvscsi_on_cmd_arrived("PVSCSI_CMD_SETUP_RINGS");
- pvscsi_dbg_dump_tx_rings_config(rc);
- if (pvscsi_ring_init_data(&s->rings, rc) < 0) {
+ if (!rc->reqRingNumPages
+ || rc->reqRingNumPages > PVSCSI_SETUP_RINGS_MAX_NUM_PAGES
+ || !rc->cmpRingNumPages
+ || rc->cmpRingNumPages > PVSCSI_SETUP_RINGS_MAX_NUM_PAGES) {
return PVSCSI_COMMAND_PROCESSING_FAILED;
}
+ pvscsi_dbg_dump_tx_rings_config(rc);
+ pvscsi_ring_init_data(&s->rings, rc);
+
s->rings_info_valid = TRUE;
return PVSCSI_COMMAND_PROCESSING_SUCCEEDED;
}
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 14/67] scsi: mptconfig: fix an assert expression
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (12 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 13/67] vmw_pvscsi: check page count while initialising descriptor rings Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 15/67] scsi: mptconfig: fix misuse of MPTSAS_CONFIG_PACK Michael Roth
` (53 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Prasad J Pandit, Paolo Bonzini
From: Prasad J Pandit <pjp@fedoraproject.org>
When LSI SAS1068 Host Bus emulator builds configuration page
headers, mptsas_config_pack() should assert that the size
fits in a byte. However, the size is expressed in 32-bit
units, so up to 1020 bytes fit. The assertion was only
allowing replies up to 252 bytes, so fix it.
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Message-Id: <1472645167-30765-2-git-send-email-ppandit@redhat.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit cf2bce203a45d7437029d108357fb23fea0967b6)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/scsi/mptconfig.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/hw/scsi/mptconfig.c b/hw/scsi/mptconfig.c
index 7071854..3e4f400 100644
--- a/hw/scsi/mptconfig.c
+++ b/hw/scsi/mptconfig.c
@@ -158,7 +158,7 @@ static size_t mptsas_config_pack(uint8_t **data, const char *fmt, ...)
va_end(ap);
if (data) {
- assert(ret < 256 && (ret % 4) == 0);
+ assert(ret / 4 < 256 && (ret % 4) == 0);
stb_p(*data + 1, ret / 4);
}
return ret;
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 15/67] scsi: mptconfig: fix misuse of MPTSAS_CONFIG_PACK
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (13 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 14/67] scsi: mptconfig: fix an assert expression Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 16/67] crypto: ensure XTS is only used with ciphers with 16 byte blocks Michael Roth
` (52 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Paolo Bonzini
From: Paolo Bonzini <pbonzini@redhat.com>
These issues cause respectively a QEMU crash and a leak of 2 bytes of
stack. They were discovered by VictorV of 360 Marvel Team.
Reported-by: Tom Victor <i-tangtianwen@360.cm>
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 65a8e1f6413a0f6f79894da710b5d6d43361d27d)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/scsi/mptconfig.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/hw/scsi/mptconfig.c b/hw/scsi/mptconfig.c
index 3e4f400..87a416a 100644
--- a/hw/scsi/mptconfig.c
+++ b/hw/scsi/mptconfig.c
@@ -203,7 +203,7 @@ size_t mptsas_config_manufacturing_1(MPTSASState *s, uint8_t **data, int address
{
/* VPD - all zeros */
return MPTSAS_CONFIG_PACK(1, MPI_CONFIG_PAGETYPE_MANUFACTURING, 0x00,
- "s256");
+ "*s256");
}
static
@@ -328,7 +328,7 @@ size_t mptsas_config_ioc_0(MPTSASState *s, uint8_t **data, int address)
return MPTSAS_CONFIG_PACK(0, MPI_CONFIG_PAGETYPE_IOC, 0x01,
"*l*lwwb*b*b*blww",
pcic->vendor_id, pcic->device_id, pcic->revision,
- pcic->subsystem_vendor_id,
+ pcic->class_id, pcic->subsystem_vendor_id,
pcic->subsystem_id);
}
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 16/67] crypto: ensure XTS is only used with ciphers with 16 byte blocks
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (14 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 15/67] scsi: mptconfig: fix misuse of MPTSAS_CONFIG_PACK Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 17/67] iothread: Stop threads before main() quits Michael Roth
` (51 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Daniel P. Berrange
From: "Daniel P. Berrange" <berrange@redhat.com>
The XTS cipher mode needs to be used with a cipher which has
a block size of 16 bytes. If a mis-matching block size is used,
the code will either corrupt memory beyond the IV array, or
not fully encrypt/decrypt the IV.
This fixes a memory corruption crash when attempting to use
cast5-128 with xts, since the former has an 8 byte block size.
A test case is added to ensure the cipher creation fails with
such an invalid combination.
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Daniel P. Berrange <berrange@redhat.com>
(cherry picked from commit a5d2f44d0d3e7523670e103a8c37faed29ff2b76)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
crypto/cipher-gcrypt.c | 6 ++++++
crypto/cipher-nettle.c | 12 +++++++-----
tests/test-crypto-cipher.c | 43 +++++++++++++++++++++++++++++++++++--------
3 files changed, 48 insertions(+), 13 deletions(-)
diff --git a/crypto/cipher-gcrypt.c b/crypto/cipher-gcrypt.c
index ede2f70..3652aa1 100644
--- a/crypto/cipher-gcrypt.c
+++ b/crypto/cipher-gcrypt.c
@@ -192,6 +192,12 @@ QCryptoCipher *qcrypto_cipher_new(QCryptoCipherAlgorithm alg,
}
if (cipher->mode == QCRYPTO_CIPHER_MODE_XTS) {
+ if (ctx->blocksize != XTS_BLOCK_SIZE) {
+ error_setg(errp,
+ "Cipher block size %zu must equal XTS block size %d",
+ ctx->blocksize, XTS_BLOCK_SIZE);
+ goto error;
+ }
ctx->iv = g_new0(uint8_t, ctx->blocksize);
}
diff --git a/crypto/cipher-nettle.c b/crypto/cipher-nettle.c
index 70909fb..0267da5 100644
--- a/crypto/cipher-nettle.c
+++ b/crypto/cipher-nettle.c
@@ -361,6 +361,13 @@ QCryptoCipher *qcrypto_cipher_new(QCryptoCipherAlgorithm alg,
goto error;
}
+ if (mode == QCRYPTO_CIPHER_MODE_XTS &&
+ ctx->blocksize != XTS_BLOCK_SIZE) {
+ error_setg(errp, "Cipher block size %zu must equal XTS block size %d",
+ ctx->blocksize, XTS_BLOCK_SIZE);
+ goto error;
+ }
+
ctx->iv = g_new0(uint8_t, ctx->blocksize);
cipher->opaque = ctx;
@@ -456,11 +463,6 @@ int qcrypto_cipher_decrypt(QCryptoCipher *cipher,
break;
case QCRYPTO_CIPHER_MODE_XTS:
- if (ctx->blocksize != XTS_BLOCK_SIZE) {
- error_setg(errp, "Block size must be %d not %zu",
- XTS_BLOCK_SIZE, ctx->blocksize);
- return -1;
- }
xts_decrypt(ctx->ctx, ctx->ctx_tweak,
ctx->alg_encrypt_wrapper, ctx->alg_decrypt_wrapper,
ctx->iv, len, out, in);
diff --git a/tests/test-crypto-cipher.c b/tests/test-crypto-cipher.c
index 1b5130d..b89dfa2 100644
--- a/tests/test-crypto-cipher.c
+++ b/tests/test-crypto-cipher.c
@@ -370,6 +370,17 @@ static QCryptoCipherTestData test_data[] = {
"eb4a427d1923ce3ff262735779a418f2"
"0a282df920147beabe421ee5319d0568",
},
+ {
+ /* Bad config - cast5-128 has 8 byte block size
+ * which is incompatible with XTS
+ */
+ .path = "/crypto/cipher/cast5-xts-128",
+ .alg = QCRYPTO_CIPHER_ALG_CAST5_128,
+ .mode = QCRYPTO_CIPHER_MODE_XTS,
+ .key =
+ "27182818284590452353602874713526"
+ "31415926535897932384626433832795",
+ }
};
@@ -432,15 +443,23 @@ static void test_cipher(const void *opaque)
const QCryptoCipherTestData *data = opaque;
QCryptoCipher *cipher;
- uint8_t *key, *iv, *ciphertext, *plaintext, *outtext;
- size_t nkey, niv, nciphertext, nplaintext;
- char *outtexthex;
+ uint8_t *key, *iv = NULL, *ciphertext = NULL,
+ *plaintext = NULL, *outtext = NULL;
+ size_t nkey, niv = 0, nciphertext = 0, nplaintext = 0;
+ char *outtexthex = NULL;
size_t ivsize, keysize, blocksize;
+ Error *err = NULL;
nkey = unhex_string(data->key, &key);
- niv = unhex_string(data->iv, &iv);
- nciphertext = unhex_string(data->ciphertext, &ciphertext);
- nplaintext = unhex_string(data->plaintext, &plaintext);
+ if (data->iv) {
+ niv = unhex_string(data->iv, &iv);
+ }
+ if (data->ciphertext) {
+ nciphertext = unhex_string(data->ciphertext, &ciphertext);
+ }
+ if (data->plaintext) {
+ nplaintext = unhex_string(data->plaintext, &plaintext);
+ }
g_assert(nciphertext == nplaintext);
@@ -449,8 +468,15 @@ static void test_cipher(const void *opaque)
cipher = qcrypto_cipher_new(
data->alg, data->mode,
key, nkey,
- &error_abort);
- g_assert(cipher != NULL);
+ &err);
+ if (data->plaintext) {
+ g_assert(err == NULL);
+ g_assert(cipher != NULL);
+ } else {
+ error_free_or_abort(&err);
+ g_assert(cipher == NULL);
+ goto cleanup;
+ }
keysize = qcrypto_cipher_get_key_len(data->alg);
blocksize = qcrypto_cipher_get_block_len(data->alg);
@@ -498,6 +524,7 @@ static void test_cipher(const void *opaque)
g_assert_cmpstr(outtexthex, ==, data->plaintext);
+ cleanup:
g_free(outtext);
g_free(outtexthex);
g_free(key);
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 17/67] iothread: Stop threads before main() quits
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (15 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 16/67] crypto: ensure XTS is only used with ciphers with 16 byte blocks Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 18/67] scsi-disk: Cleaning up around tray open state Michael Roth
` (50 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Fam Zheng, Stefan Hajnoczi
From: Fam Zheng <famz@redhat.com>
Right after main_loop ends, we release various things but keep iothread
alive. The latter is not prepared to the sudden change of resources.
Specifically, after bdrv_close_all(), virtio-scsi dataplane get a
surprise at the empty BlockBackend:
(gdb) bt
at /usr/src/debug/qemu-2.6.0/hw/scsi/virtio-scsi.c:543
at /usr/src/debug/qemu-2.6.0/hw/scsi/virtio-scsi.c:577
It is because the d->conf.blk->root is set to NULL, then
blk_get_aio_context() returns qemu_aio_context, whereas s->ctx is still
pointing to the iothread:
hw/scsi/virtio-scsi.c:543:
if (s->dataplane_started) {
assert(blk_get_aio_context(d->conf.blk) == s->ctx);
}
To fix this, let's stop iothreads before doing bdrv_close_all().
Cc: qemu-stable@nongnu.org
Signed-off-by: Fam Zheng <famz@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Message-id: 1473326931-9699-1-git-send-email-famz@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit dce8921b2baaf95974af8176406881872067adfa)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
include/sysemu/iothread.h | 1 +
iothread.c | 24 ++++++++++++++++++++----
vl.c | 2 ++
3 files changed, 23 insertions(+), 4 deletions(-)
diff --git a/include/sysemu/iothread.h b/include/sysemu/iothread.h
index 2eefea1..68ac2de 100644
--- a/include/sysemu/iothread.h
+++ b/include/sysemu/iothread.h
@@ -35,5 +35,6 @@ typedef struct {
char *iothread_get_id(IOThread *iothread);
AioContext *iothread_get_aio_context(IOThread *iothread);
+void iothread_stop_all(void);
#endif /* IOTHREAD_H */
diff --git a/iothread.c b/iothread.c
index f183d38..fb08a60 100644
--- a/iothread.c
+++ b/iothread.c
@@ -54,16 +54,25 @@ static void *iothread_run(void *opaque)
return NULL;
}
-static void iothread_instance_finalize(Object *obj)
+static int iothread_stop(Object *object, void *opaque)
{
- IOThread *iothread = IOTHREAD(obj);
+ IOThread *iothread;
- if (!iothread->ctx) {
- return;
+ iothread = (IOThread *)object_dynamic_cast(object, TYPE_IOTHREAD);
+ if (!iothread || !iothread->ctx) {
+ return 0;
}
iothread->stopping = true;
aio_notify(iothread->ctx);
qemu_thread_join(&iothread->thread);
+ return 0;
+}
+
+static void iothread_instance_finalize(Object *obj)
+{
+ IOThread *iothread = IOTHREAD(obj);
+
+ iothread_stop(obj, NULL);
qemu_cond_destroy(&iothread->init_done_cond);
qemu_mutex_destroy(&iothread->init_done_lock);
aio_context_unref(iothread->ctx);
@@ -174,3 +183,10 @@ IOThreadInfoList *qmp_query_iothreads(Error **errp)
object_child_foreach(container, query_one_iothread, &prev);
return head;
}
+
+void iothread_stop_all(void)
+{
+ Object *container = object_get_objects_root();
+
+ object_child_foreach(container, iothread_stop, NULL);
+}
diff --git a/vl.c b/vl.c
index b3c80d5..3414e1a 100644
--- a/vl.c
+++ b/vl.c
@@ -121,6 +121,7 @@ int main(int argc, char **argv)
#include "crypto/init.h"
#include "sysemu/replay.h"
#include "qapi/qmp/qerror.h"
+#include "sysemu/iothread.h"
#define MAX_VIRTIO_CONSOLES 1
#define MAX_SCLP_CONSOLES 1
@@ -4603,6 +4604,7 @@ int main(int argc, char **argv, char **envp)
trace_init_vcpu_events();
main_loop();
replay_disable_events();
+ iothread_stop_all();
bdrv_close_all();
pause_all_vcpus();
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 18/67] scsi-disk: Cleaning up around tray open state
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (16 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 17/67] iothread: Stop threads before main() quits Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 19/67] virtio-scsi: Don't abort when media is ejected Michael Roth
` (49 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Fam Zheng, Paolo Bonzini
From: Fam Zheng <famz@redhat.com>
Even if tray is not open, it can be empty (blk_is_inserted() == false).
Handle both cases correctly by replacing the s->tray_open checks with
blk_is_available(), which is an AND of the two.
Also simplify successive checks of them into blk_is_available(), in a
couple cases.
Signed-off-by: Fam Zheng <famz@redhat.com>
Message-Id: <1473848224-24809-2-git-send-email-famz@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit cd723b85601baa7a0eeffbac83421357a70d81ee)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/scsi/scsi-disk.c | 22 ++++++++--------------
1 file changed, 8 insertions(+), 14 deletions(-)
diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c
index 0e1bb68..f1b115c 100644
--- a/hw/scsi/scsi-disk.c
+++ b/hw/scsi/scsi-disk.c
@@ -396,7 +396,7 @@ static void scsi_read_data(SCSIRequest *req)
return;
}
- if (s->tray_open) {
+ if (!blk_is_available(req->dev->conf.blk)) {
scsi_read_complete(r, -ENOMEDIUM);
return;
}
@@ -519,7 +519,7 @@ static void scsi_write_data(SCSIRequest *req)
scsi_write_complete_noio(r, 0);
return;
}
- if (s->tray_open) {
+ if (!blk_is_available(req->dev->conf.blk)) {
scsi_write_complete_noio(r, -ENOMEDIUM);
return;
}
@@ -792,10 +792,7 @@ static inline bool media_is_dvd(SCSIDiskState *s)
if (s->qdev.type != TYPE_ROM) {
return false;
}
- if (!blk_is_inserted(s->qdev.conf.blk)) {
- return false;
- }
- if (s->tray_open) {
+ if (!blk_is_available(s->qdev.conf.blk)) {
return false;
}
blk_get_geometry(s->qdev.conf.blk, &nb_sectors);
@@ -808,10 +805,7 @@ static inline bool media_is_cd(SCSIDiskState *s)
if (s->qdev.type != TYPE_ROM) {
return false;
}
- if (!blk_is_inserted(s->qdev.conf.blk)) {
- return false;
- }
- if (s->tray_open) {
+ if (!blk_is_available(s->qdev.conf.blk)) {
return false;
}
blk_get_geometry(s->qdev.conf.blk, &nb_sectors);
@@ -875,7 +869,7 @@ static int scsi_read_dvd_structure(SCSIDiskState *s, SCSIDiskReq *r,
}
if (format != 0xff) {
- if (s->tray_open || !blk_is_inserted(s->qdev.conf.blk)) {
+ if (!blk_is_available(s->qdev.conf.blk)) {
scsi_check_condition(r, SENSE_CODE(NO_MEDIUM));
return -1;
}
@@ -1857,7 +1851,7 @@ static int32_t scsi_disk_emulate_command(SCSIRequest *req, uint8_t *buf)
break;
default:
- if (s->tray_open || !blk_is_inserted(s->qdev.conf.blk)) {
+ if (!blk_is_available(s->qdev.conf.blk)) {
scsi_check_condition(r, SENSE_CODE(NO_MEDIUM));
return 0;
}
@@ -1886,7 +1880,7 @@ static int32_t scsi_disk_emulate_command(SCSIRequest *req, uint8_t *buf)
memset(outbuf, 0, r->buflen);
switch (req->cmd.buf[0]) {
case TEST_UNIT_READY:
- assert(!s->tray_open && blk_is_inserted(s->qdev.conf.blk));
+ assert(blk_is_available(s->qdev.conf.blk));
break;
case INQUIRY:
buflen = scsi_disk_emulate_inquiry(req, outbuf);
@@ -2126,7 +2120,7 @@ static int32_t scsi_disk_dma_command(SCSIRequest *req, uint8_t *buf)
command = buf[0];
- if (s->tray_open || !blk_is_inserted(s->qdev.conf.blk)) {
+ if (!blk_is_available(s->qdev.conf.blk)) {
scsi_check_condition(r, SENSE_CODE(NO_MEDIUM));
return 0;
}
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 19/67] virtio-scsi: Don't abort when media is ejected
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (17 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 18/67] scsi-disk: Cleaning up around tray open state Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 20/67] ahci: clear aiocb in ncq_cb Michael Roth
` (48 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Fam Zheng, Paolo Bonzini
From: Fam Zheng <famz@redhat.com>
With an ejected block backend, blk_get_aio_context() would return
qemu_aio_context. In this case don't assert.
Signed-off-by: Fam Zheng <famz@redhat.com>
Message-Id: <1473848224-24809-3-git-send-email-famz@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 2a2d69f490c1b1dc6b6d2aef385ee7b654497a77)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/scsi/virtio-scsi.c | 15 +++++++++------
1 file changed, 9 insertions(+), 6 deletions(-)
diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c
index ce57ef6..e596b64 100644
--- a/hw/scsi/virtio-scsi.c
+++ b/hw/scsi/virtio-scsi.c
@@ -236,6 +236,13 @@ static void virtio_scsi_cancel_notify(Notifier *notifier, void *data)
g_free(n);
}
+static inline void virtio_scsi_ctx_check(VirtIOSCSI *s, SCSIDevice *d)
+{
+ if (s->dataplane_started && d && blk_is_available(d->conf.blk)) {
+ assert(blk_get_aio_context(d->conf.blk) == s->ctx);
+ }
+}
+
/* Return 0 if the request is ready to be completed and return to guest;
* -EINPROGRESS if the request is submitted and will be completed later, in the
* case of async cancellation. */
@@ -247,9 +254,7 @@ static int virtio_scsi_do_tmf(VirtIOSCSI *s, VirtIOSCSIReq *req)
int target;
int ret = 0;
- if (s->dataplane_started && d) {
- assert(blk_get_aio_context(d->conf.blk) == s->ctx);
- }
+ virtio_scsi_ctx_check(s, d);
/* Here VIRTIO_SCSI_S_OK means "FUNCTION COMPLETE". */
req->resp.tmf.response = VIRTIO_SCSI_S_OK;
@@ -539,9 +544,7 @@ static bool virtio_scsi_handle_cmd_req_prepare(VirtIOSCSI *s, VirtIOSCSIReq *req
virtio_scsi_complete_cmd_req(req);
return false;
}
- if (s->dataplane_started) {
- assert(blk_get_aio_context(d->conf.blk) == s->ctx);
- }
+ virtio_scsi_ctx_check(s, d);
req->sreq = scsi_req_new(d, req->req.cmd.tag,
virtio_scsi_get_lun(req->req.cmd.lun),
req->req.cmd.cdb, req);
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 20/67] ahci: clear aiocb in ncq_cb
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (18 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 19/67] virtio-scsi: Don't abort when media is ejected Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-19 23:07 ` John Snow
2016-12-15 0:44 ` [Qemu-devel] [PATCH 21/67] s390x/css: handle cssid 255 correctly Michael Roth
` (47 subsequent siblings)
67 siblings, 1 reply; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, John Snow
From: John Snow <jsnow@redhat.com>
Similar to existing fixes for IDE (87ac25fd) and ATAPI (7f951b2d), the
AIOCB must be cleared in the callback. Otherwise, we may accidentally
try to reset a dangling pointer in bdrv_aio_cancel() from a port reset.
Signed-off-by: John Snow <jsnow@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 1474575040-32079-2-git-send-email-jsnow@redhat.com
Signed-off-by: John Snow <jsnow@redhat.com>
(cherry picked from commit df403bc58859c893ebd0accda07678e84d15dc5d)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/ide/ahci.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/hw/ide/ahci.c b/hw/ide/ahci.c
index f3438ad..63ead21 100644
--- a/hw/ide/ahci.c
+++ b/hw/ide/ahci.c
@@ -948,6 +948,7 @@ static void ncq_cb(void *opaque, int ret)
NCQTransferState *ncq_tfs = (NCQTransferState *)opaque;
IDEState *ide_state = &ncq_tfs->drive->port.ifs[0];
+ ncq_tfs->aiocb = NULL;
if (ret == -ECANCELED) {
return;
}
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* Re: [Qemu-devel] [PATCH 20/67] ahci: clear aiocb in ncq_cb
2016-12-15 0:44 ` [Qemu-devel] [PATCH 20/67] ahci: clear aiocb in ncq_cb Michael Roth
@ 2016-12-19 23:07 ` John Snow
2016-12-21 16:56 ` Michael Roth
0 siblings, 1 reply; 71+ messages in thread
From: John Snow @ 2016-12-19 23:07 UTC (permalink / raw)
To: Michael Roth, qemu-devel; +Cc: qemu-stable, Jeff Cody
Hi, some more considerations:
e7bd708ec85e40fd51569bb90c52d6613ffd8f45
atapi: classify read_cd as conditionally returning data
This fixes problems with certain operating systems being unable to read
from the CDROM.
99868af3d0a75cf6a515a9aa81bf0d7bcb39eadb
dma-helpers: explicitly pass alignment into DMA helpers
I believe this does fix MACIO for some platforms, but I'm not sure how
annoying it would be to backport due to the DMA alignment changes. Low
priority.
c47ee043dc2cc85da710e87524144a720598c096
block-backend: Always notify on blk_eject
This fixes a legitimate bug in some versions of libvirt.
ca44141d5fb801dd5903102acefd0f2d8e8bb6a1
ide: Fix memory leak in ide_register_restart_cb()
Not important, but not risky or hard to backport either. Skippable.
9da82227caa74fb6fbea224dad91fe5b7cc115a5
ide: fix DMA register transitions
This is only theoretical. Safely skipped.
e305a16510afa74eec20390479e349402e55ef4c portio: keep references on portio
Doesn't look important as it doesn't actually FIX a leak.
There were some fixes for Transactional Block Jobs as well in the 2.8
window, but as we still haven't quite finished nailing down incremental
backups, it may not be too important to backport to 2.7 -- I don't think
anyone is using this yet.
The series in question is:
https://lists.nongnu.org/archive/html/qemu-devel/2016-11/msg01392.html
On 12/14/2016 07:44 PM, Michael Roth wrote:
> From: John Snow <jsnow@redhat.com>
>
> Similar to existing fixes for IDE (87ac25fd) and ATAPI (7f951b2d), the
> AIOCB must be cleared in the callback. Otherwise, we may accidentally
> try to reset a dangling pointer in bdrv_aio_cancel() from a port reset.
>
> Signed-off-by: John Snow <jsnow@redhat.com>
> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
> Message-id: 1474575040-32079-2-git-send-email-jsnow@redhat.com
> Signed-off-by: John Snow <jsnow@redhat.com>
> (cherry picked from commit df403bc58859c893ebd0accda07678e84d15dc5d)
> Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
> ---
> hw/ide/ahci.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/hw/ide/ahci.c b/hw/ide/ahci.c
> index f3438ad..63ead21 100644
> --- a/hw/ide/ahci.c
> +++ b/hw/ide/ahci.c
> @@ -948,6 +948,7 @@ static void ncq_cb(void *opaque, int ret)
> NCQTransferState *ncq_tfs = (NCQTransferState *)opaque;
> IDEState *ide_state = &ncq_tfs->drive->port.ifs[0];
>
> + ncq_tfs->aiocb = NULL;
> if (ret == -ECANCELED) {
> return;
> }
>
--
—js
^ permalink raw reply [flat|nested] 71+ messages in thread* Re: [Qemu-devel] [PATCH 20/67] ahci: clear aiocb in ncq_cb
2016-12-19 23:07 ` John Snow
@ 2016-12-21 16:56 ` Michael Roth
0 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-21 16:56 UTC (permalink / raw)
To: John Snow, qemu-devel; +Cc: qemu-stable, Jeff Cody
Quoting John Snow (2016-12-19 17:07:17)
> Hi, some more considerations:
>
>
> e7bd708ec85e40fd51569bb90c52d6613ffd8f45
> atapi: classify read_cd as conditionally returning data
>
> This fixes problems with certain operating systems being unable to read
> from the CDROM.
applied.
>
>
> 99868af3d0a75cf6a515a9aa81bf0d7bcb39eadb
> dma-helpers: explicitly pass alignment into DMA helpers
>
> I believe this does fix MACIO for some platforms, but I'm not sure how
> annoying it would be to backport due to the DMA alignment changes. Low
> priority.
Seems to apply cleanly, but change seems mechanical. I assume the macio fix
comes from the follow-up be1e343995ef81fc05d9a4e1ec263ca171d842e7.
both applied.
>
>
> c47ee043dc2cc85da710e87524144a720598c096
> block-backend: Always notify on blk_eject
>
> This fixes a legitimate bug in some versions of libvirt.
applied, but modified to avoid the need for 2d76e724 since that
requires qapi api changes.
>
>
> ca44141d5fb801dd5903102acefd0f2d8e8bb6a1
> ide: Fix memory leak in ide_register_restart_cb()
>
> Not important, but not risky or hard to backport either. Skippable.
applied.
>
>
> 9da82227caa74fb6fbea224dad91fe5b7cc115a5
> ide: fix DMA register transitions
>
> This is only theoretical. Safely skipped.
Slight chance some OSs might not deal with this as expected so I'd opt
to leave it out if there haven't been any observed bugs around it.
>
>
> e305a16510afa74eec20390479e349402e55ef4c portio: keep references on portio
>
> Doesn't look important as it doesn't actually FIX a leak.
Agreed, but went ahead and pulled it in since it's a context dependency for
ca44141.
>
>
> There were some fixes for Transactional Block Jobs as well in the 2.8
> window, but as we still haven't quite finished nailing down incremental
> backups, it may not be too important to backport to 2.7 -- I don't think
> anyone is using this yet.
>
> The series in question is:
> https://lists.nongnu.org/archive/html/qemu-devel/2016-11/msg01392.html
There are some interdependencies between this and bae8196+ that I don't
trust myself to properly untangle. And backporting bae8196 seems risky.
I think I'd need a direct backport for 2.7, but at this point there's not
really any time left for all that so I'll opt to leave these out for
2.7.1.
Thanks for all the suggestions.
>
> On 12/14/2016 07:44 PM, Michael Roth wrote:
> > From: John Snow <jsnow@redhat.com>
> >
> > Similar to existing fixes for IDE (87ac25fd) and ATAPI (7f951b2d), the
> > AIOCB must be cleared in the callback. Otherwise, we may accidentally
> > try to reset a dangling pointer in bdrv_aio_cancel() from a port reset.
> >
> > Signed-off-by: John Snow <jsnow@redhat.com>
> > Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
> > Message-id: 1474575040-32079-2-git-send-email-jsnow@redhat.com
> > Signed-off-by: John Snow <jsnow@redhat.com>
> > (cherry picked from commit df403bc58859c893ebd0accda07678e84d15dc5d)
> > Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
> > ---
> > hw/ide/ahci.c | 1 +
> > 1 file changed, 1 insertion(+)
> >
> > diff --git a/hw/ide/ahci.c b/hw/ide/ahci.c
> > index f3438ad..63ead21 100644
> > --- a/hw/ide/ahci.c
> > +++ b/hw/ide/ahci.c
> > @@ -948,6 +948,7 @@ static void ncq_cb(void *opaque, int ret)
> > NCQTransferState *ncq_tfs = (NCQTransferState *)opaque;
> > IDEState *ide_state = &ncq_tfs->drive->port.ifs[0];
> >
> > + ncq_tfs->aiocb = NULL;
> > if (ret == -ECANCELED) {
> > return;
> > }
> >
>
> --
> —js
>
^ permalink raw reply [flat|nested] 71+ messages in thread
* [Qemu-devel] [PATCH 21/67] s390x/css: handle cssid 255 correctly
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (19 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 20/67] ahci: clear aiocb in ncq_cb Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 22/67] vfio/pci: Fix regression in MSI routing configuration Michael Roth
` (46 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Cornelia Huck
From: Cornelia Huck <cornelia.huck@de.ibm.com>
The cssid 255 is reserved but still valid from an architectural
point of view. However, feeding a bogus schid of 0xffffffff into
the virtio hypercall will lead to a crash:
Stack trace of thread 138363:
#0 0x00000000100d168c css_find_subch (qemu-system-s390x)
#1 0x00000000100d3290 virtio_ccw_hcall_notify
#2 0x00000000100cbf60 s390_virtio_hypercall
#3 0x000000001010ff7a handle_hypercall
#4 0x0000000010079ed4 kvm_cpu_exec (qemu-system-s390x)
#5 0x00000000100609b4 qemu_kvm_cpu_thread_fn
#6 0x000003ff8b887bb4 start_thread (libpthread.so.0)
#7 0x000003ff8b78df0a thread_start (libc.so.6)
This is because the css array was only allocated for 0..254
instead of 0..255.
Let's fix this by bumping MAX_CSSID to 255 and fencing off the
reserved cssid of 255 during css image allocation.
Reported-by: Christian Borntraeger <borntraeger@de.ibm.com>
Tested-by: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
(cherry picked from commit 882b3b97697affb36ca3d174f42f846232008979)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/s390x/css.c | 8 +++-----
include/hw/s390x/css.h | 2 +-
2 files changed, 4 insertions(+), 6 deletions(-)
diff --git a/hw/s390x/css.c b/hw/s390x/css.c
index bb8e4be..b0e81ef 100644
--- a/hw/s390x/css.c
+++ b/hw/s390x/css.c
@@ -141,7 +141,8 @@ out_err:
int css_create_css_image(uint8_t cssid, bool default_image)
{
trace_css_new_image(cssid, default_image ? "(default)" : "");
- if (cssid > MAX_CSSID) {
+ /* 255 is reserved */
+ if (cssid == 255) {
return -EINVAL;
}
if (channel_subsys.css[cssid]) {
@@ -1267,7 +1268,7 @@ bool css_schid_final(int m, uint8_t cssid, uint8_t ssid, uint16_t schid)
uint8_t real_cssid;
real_cssid = (!m && (cssid == 0)) ? channel_subsys.default_cssid : cssid;
- if (real_cssid > MAX_CSSID || ssid > MAX_SSID ||
+ if (ssid > MAX_SSID ||
!channel_subsys.css[real_cssid] ||
!channel_subsys.css[real_cssid]->sch_set[ssid]) {
return true;
@@ -1282,9 +1283,6 @@ static int css_add_virtual_chpid(uint8_t cssid, uint8_t chpid, uint8_t type)
CssImage *css;
trace_css_chpid_add(cssid, chpid, type);
- if (cssid > MAX_CSSID) {
- return -EINVAL;
- }
css = channel_subsys.css[cssid];
if (!css) {
return -EINVAL;
diff --git a/include/hw/s390x/css.h b/include/hw/s390x/css.h
index 1da63e3..c96c862 100644
--- a/include/hw/s390x/css.h
+++ b/include/hw/s390x/css.h
@@ -20,7 +20,7 @@
#define MAX_DEVNO 65535
#define MAX_SCHID 65535
#define MAX_SSID 3
-#define MAX_CSSID 254 /* 255 is reserved */
+#define MAX_CSSID 255
#define MAX_CHPID 255
#define MAX_CIWS 62
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 22/67] vfio/pci: Fix regression in MSI routing configuration
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (20 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 21/67] s390x/css: handle cssid 255 correctly Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 23/67] qcow2: fix encryption during cow of sectors Michael Roth
` (45 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel
Cc: qemu-stable, David Gibson, Alex Williamson, Peter Xu, Gavin Shan
From: David Gibson <david@gibson.dropbear.id.au>
d1f6af6 "kvm-irqchip: simplify kvm_irqchip_add_msi_route" was a cleanup
of kvmchip routing configuration, that was mostly intended for x86.
However, it also contains a subtle change in behaviour which breaks EEH[1]
error recovery on certain VFIO passthrough devices on spapr guests. So far
it's only been seen on a BCM5719 NIC on a POWER8 server, but there may be
other hardware with the same problem. It's also possible there could be
circumstances where it causes a bug on x86 as well, though I don't know of
any obvious candidates.
Prior to d1f6af6, both vfio_msix_vector_do_use() and
vfio_add_kvm_msi_virq() used msg == NULL as a special flag to mark this
as the "dummy" vector used to make the host hardware state sync with the
guest expected hardware state in terms of MSI configuration.
Specifically that flag caused vfio_add_kvm_msi_virq() to become a no-op,
meaning the dummy irq would always be delivered via qemu. d1f6af6 changed
vfio_add_kvm_msi_virq() so it takes a vector number instead of the msg
parameter, and determines the correct message itself. The test for !msg
was removed, and not replaced with anything there or in the caller.
With an spapr guest which has a VFIO device, if an EEH error occurs on the
host hardware, then the device will be isolated then reset. This is a
combination of host and guest action, mediated by some EEH related
hypercalls. I haven't fully traced the mechanics, but somehow installing
the kvm irqchip route for the dummy irq on the BCM5719 means that after EEH
reset and recovery, at least some irqs are no longer delivered to the
guest.
In particular, the guest never gets the link up event, and so the NIC is
effectively dead.
[1] EEH (Enhanced Error Handling) is an IBM POWER server specific PCI-*
error reporting and recovery mechanism. The concept is somewhat
similar to PCI-E AER, but the details are different.
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1373802
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Gavin Shan <gwshan@au1.ibm.com>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Cc: qemu-stable@nongnu.org
Fixes: d1f6af6a17a6 ("kvm-irqchip: simplify kvm_irqchip_add_msi_route")
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
(cherry picked from commit 6d17a018d09801a2b18133a4febd81433bb0cf85)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/vfio/pci.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 7bfa17c..a5a620a 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -496,7 +496,9 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr,
vfio_update_kvm_msi_virq(vector, *msg, pdev);
}
} else {
- vfio_add_kvm_msi_virq(vdev, vector, nr, true);
+ if (msg) {
+ vfio_add_kvm_msi_virq(vdev, vector, nr, true);
+ }
}
/*
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 23/67] qcow2: fix encryption during cow of sectors
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (21 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 22/67] vfio/pci: Fix regression in MSI routing configuration Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 24/67] iscsi: Fix divide-by-zero regression on raw SG devices Michael Roth
` (44 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Daniel P. Berrange, Kevin Wolf
From: "Daniel P. Berrange" <berrange@redhat.com>
Broken in previous commit:
commit aaa4d20b4972bb1a811ce929502e6741835d584e
Author: Kevin Wolf <kwolf@redhat.com>
Date: Wed Jun 1 15:21:05 2016 +0200
qcow2: Make copy_sectors() byte based
The copy_sectors() code was originally using the 'sector'
parameter for encryption, which was passed in by the caller
from the QCowL2Meta.offset field (aka the guest logical
offset).
After the change, the code is using 'cluster_offset' which
was passed in from QCow2L2Meta.alloc_offset field (aka the
host physical offset).
This would cause the data to be encrypted using an incorrect
initialization vector which will in turn cause later reads
to return garbage.
Although current qcow2 built-in encryption is blocked from
usage in the emulator, one could still hit this if writing
to the file via qemu-{img,io,nbd} commands.
Cc: qemu-stable@nongnu.org
Signed-off-by: Daniel P. Berrange <berrange@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit bb9f8dd0e15a9744b8d09d06ecb6a18ca3dcc173)
Conflicts:
tests/qemu-iotests/group
* drop context dependancy on non-2.7 iotest groups
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
block/qcow2-cluster.c | 2 +-
tests/qemu-iotests/158 | 80 ++++++++++++++++++++++++++++++++++++++++++++++
tests/qemu-iotests/158.out | 36 +++++++++++++++++++++
tests/qemu-iotests/group | 1 +
4 files changed, 118 insertions(+), 1 deletion(-)
create mode 100755 tests/qemu-iotests/158
create mode 100644 tests/qemu-iotests/158.out
diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c
index f941835..9ba2d71 100644
--- a/block/qcow2-cluster.c
+++ b/block/qcow2-cluster.c
@@ -427,7 +427,7 @@ static int coroutine_fn do_perform_cow(BlockDriverState *bs,
if (bs->encrypted) {
Error *err = NULL;
- int64_t sector = (cluster_offset + offset_in_cluster)
+ int64_t sector = (src_cluster_offset + offset_in_cluster)
>> BDRV_SECTOR_BITS;
assert(s->cipher);
assert((offset_in_cluster & ~BDRV_SECTOR_MASK) == 0);
diff --git a/tests/qemu-iotests/158 b/tests/qemu-iotests/158
new file mode 100755
index 0000000..a6cdd6d
--- /dev/null
+++ b/tests/qemu-iotests/158
@@ -0,0 +1,80 @@
+#!/bin/bash
+#
+# Test encrypted read/write using backing files
+#
+# Copyright (C) 2015 Red Hat, Inc.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program. If not, see <http://www.gnu.org/licenses/>.
+#
+
+# creator
+owner=berrange@redhat.com
+
+seq=`basename $0`
+echo "QA output created by $seq"
+
+here=`pwd`
+status=1 # failure is the default!
+
+_cleanup()
+{
+ _cleanup_test_img
+}
+trap "_cleanup; exit \$status" 0 1 2 3 15
+
+# get standard environment, filters and checks
+. ./common.rc
+. ./common.filter
+
+_supported_fmt qcow2
+_supported_proto generic
+_supported_os Linux
+
+
+size=128M
+TEST_IMG_BASE=$TEST_IMG.base
+
+TEST_IMG_SAVE=$TEST_IMG
+TEST_IMG=$TEST_IMG_BASE
+echo "== create base =="
+IMGOPTS="encryption=on" _make_test_img $size
+TEST_IMG=$TEST_IMG_SAVE
+
+echo
+echo "== writing whole image =="
+echo "astrochicken" | $QEMU_IO -c "write -P 0xa 0 $size" "$TEST_IMG_BASE" | _filter_qemu_io | _filter_testdir
+
+echo
+echo "== verify pattern =="
+echo "astrochicken" | $QEMU_IO -c "read -P 0xa 0 $size" "$TEST_IMG_BASE" | _filter_qemu_io | _filter_testdir
+
+echo "== create overlay =="
+IMGOPTS="encryption=on" _make_test_img -b "$TEST_IMG_BASE" $size
+
+echo
+echo "== writing part of a cluster =="
+echo "astrochicken" | $QEMU_IO -c "write -P 0xe 0 1024" "$TEST_IMG" | _filter_qemu_io | _filter_testdir
+
+echo
+echo "== verify pattern =="
+echo "astrochicken" | $QEMU_IO -c "read -P 0xe 0 1024" "$TEST_IMG" | _filter_qemu_io | _filter_testdir
+echo
+echo "== verify pattern =="
+echo "astrochicken" | $QEMU_IO -c "read -P 0xa 1024 64512" "$TEST_IMG" | _filter_qemu_io | _filter_testdir
+
+
+# success, all done
+echo "*** done"
+rm -f $seq.full
+status=0
diff --git a/tests/qemu-iotests/158.out b/tests/qemu-iotests/158.out
new file mode 100644
index 0000000..b3f37e2
--- /dev/null
+++ b/tests/qemu-iotests/158.out
@@ -0,0 +1,36 @@
+QA output created by 158
+== create base ==
+Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=134217728 encryption=on
+
+== writing whole image ==
+Disk image 'TEST_DIR/t.qcow2.base' is encrypted.
+password:
+wrote 134217728/134217728 bytes at offset 0
+128 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+== verify pattern ==
+Disk image 'TEST_DIR/t.qcow2.base' is encrypted.
+password:
+read 134217728/134217728 bytes at offset 0
+128 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+== create overlay ==
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 backing_file=TEST_DIR/t.IMGFMT.base encryption=on
+
+== writing part of a cluster ==
+Disk image 'TEST_DIR/t.qcow2' is encrypted.
+password:
+wrote 1024/1024 bytes at offset 0
+1 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+== verify pattern ==
+Disk image 'TEST_DIR/t.qcow2' is encrypted.
+password:
+read 1024/1024 bytes at offset 0
+1 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+
+== verify pattern ==
+Disk image 'TEST_DIR/t.qcow2' is encrypted.
+password:
+read 64512/64512 bytes at offset 1024
+63 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
+*** done
diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group
index 50ddeed..ad3518d 100644
--- a/tests/qemu-iotests/group
+++ b/tests/qemu-iotests/group
@@ -157,4 +157,5 @@
155 rw auto
156 rw auto quick
157 auto
+158 rw auto quick
162 auto quick
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 24/67] iscsi: Fix divide-by-zero regression on raw SG devices
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (22 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 23/67] qcow2: fix encryption during cow of sectors Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 25/67] block: reintroduce bdrv_flush_all Michael Roth
` (43 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Eric Blake, Paolo Bonzini
From: Eric Blake <eblake@redhat.com>
When qemu uses iscsi devices in sg mode, iscsilun->block_size
is left at 0. Prior to commits cf081fca and similar, when
block limits were tracked in sectors, this did not matter:
various block limits were just left at 0. But when we started
scaling by block size, this caused SIGFPE.
Then, in a later patch, commit a5b8dd2c added an assertion to
bdrv_open_common() that request_alignment is always non-zero;
which was not true for SG mode. Rather than relax that assertion,
we can just provide a sane value (we don't know of any SG device
with a block size smaller than qemu's default sizing of 512 bytes).
One possible solution for SG mode is to just blindly skip ALL
of iscsi_refresh_limits(), since we already short circuit so
many other things in sg mode. But this patch takes a slightly
more conservative approach, and merely guarantees that scaling
will succeed, while still using multiples of the original size
where possible. Resulting limits may still be zero in SG mode
(that is, we mostly only fix block_size used as a denominator
or which affect assertions, not all uses).
Reported-by: Holger Schranz <holger@fam-schranz.de>
Signed-off-by: Eric Blake <eblake@redhat.com>
CC: qemu-stable@nongnu.org
Message-Id: <1473283640-15756-1-git-send-email-eblake@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 95eaa78537c734fa3cb3373d47ba8c0099a36ff0)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
block/iscsi.c | 13 ++++++++-----
1 file changed, 8 insertions(+), 5 deletions(-)
diff --git a/block/iscsi.c b/block/iscsi.c
index 95ce9e1..b2b4e5d 100644
--- a/block/iscsi.c
+++ b/block/iscsi.c
@@ -1813,19 +1813,22 @@ static void iscsi_refresh_limits(BlockDriverState *bs, Error **errp)
IscsiLun *iscsilun = bs->opaque;
uint64_t max_xfer_len = iscsilun->use_16_for_rw ? 0xffffffff : 0xffff;
+ unsigned int block_size = MAX(BDRV_SECTOR_SIZE, iscsilun->block_size);
- bs->bl.request_alignment = iscsilun->block_size;
+ assert(iscsilun->block_size >= BDRV_SECTOR_SIZE || bs->sg);
+
+ bs->bl.request_alignment = block_size;
if (iscsilun->bl.max_xfer_len) {
max_xfer_len = MIN(max_xfer_len, iscsilun->bl.max_xfer_len);
}
- if (max_xfer_len * iscsilun->block_size < INT_MAX) {
+ if (max_xfer_len * block_size < INT_MAX) {
bs->bl.max_transfer = max_xfer_len * iscsilun->block_size;
}
if (iscsilun->lbp.lbpu) {
- if (iscsilun->bl.max_unmap < 0xffffffff / iscsilun->block_size) {
+ if (iscsilun->bl.max_unmap < 0xffffffff / block_size) {
bs->bl.max_pdiscard =
iscsilun->bl.max_unmap * iscsilun->block_size;
}
@@ -1835,7 +1838,7 @@ static void iscsi_refresh_limits(BlockDriverState *bs, Error **errp)
bs->bl.pdiscard_alignment = iscsilun->block_size;
}
- if (iscsilun->bl.max_ws_len < 0xffffffff / iscsilun->block_size) {
+ if (iscsilun->bl.max_ws_len < 0xffffffff / block_size) {
bs->bl.max_pwrite_zeroes =
iscsilun->bl.max_ws_len * iscsilun->block_size;
}
@@ -1846,7 +1849,7 @@ static void iscsi_refresh_limits(BlockDriverState *bs, Error **errp)
bs->bl.pwrite_zeroes_alignment = iscsilun->block_size;
}
if (iscsilun->bl.opt_xfer_len &&
- iscsilun->bl.opt_xfer_len < INT_MAX / iscsilun->block_size) {
+ iscsilun->bl.opt_xfer_len < INT_MAX / block_size) {
bs->bl.opt_transfer = pow2floor(iscsilun->bl.opt_xfer_len *
iscsilun->block_size);
}
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 25/67] block: reintroduce bdrv_flush_all
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (23 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 24/67] iscsi: Fix divide-by-zero regression on raw SG devices Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 26/67] qemu: use bdrv_flush_all for vm_stop et al Michael Roth
` (42 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, John Snow, Kevin Wolf
From: John Snow <jsnow@redhat.com>
Commit fe1a9cbc moved the flush_all routine from the bdrv layer to the
block-backend layer. In doing so, however, the semantics of the routine
changed slightly such that flush_all now used blk_flush instead of
bdrv_flush.
blk_flush can fail if the attached device model reports that it is not
"available," (i.e. the tray is open.) This changed the semantics of
flush_all such that it can now fail for e.g. open CDROM drives.
Reintroduce bdrv_flush_all to regain the old semantics without having to
alter the behavior of blk_flush or blk_flush_all, which are already
'doing the right thing.'
Signed-off-by: John Snow <jsnow@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Acked-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 4085f5c7a239567a292876f46cb59d9b19bcf6ac)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
block/io.c | 25 +++++++++++++++++++++++++
include/block/block.h | 1 +
2 files changed, 26 insertions(+)
diff --git a/block/io.c b/block/io.c
index 420944d..487755a 100644
--- a/block/io.c
+++ b/block/io.c
@@ -1615,6 +1615,31 @@ int coroutine_fn bdrv_co_pwrite_zeroes(BdrvChild *child, int64_t offset,
BDRV_REQ_ZERO_WRITE | flags);
}
+/*
+ * Flush ALL BDSes regardless of if they are reachable via a BlkBackend or not.
+ */
+int bdrv_flush_all(void)
+{
+ BdrvNextIterator it;
+ BlockDriverState *bs = NULL;
+ int result = 0;
+
+ for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
+ AioContext *aio_context = bdrv_get_aio_context(bs);
+ int ret;
+
+ aio_context_acquire(aio_context);
+ ret = bdrv_flush(bs);
+ if (ret < 0 && !result) {
+ result = ret;
+ }
+ aio_context_release(aio_context);
+ }
+
+ return result;
+}
+
+
typedef struct BdrvCoGetBlockStatusData {
BlockDriverState *bs;
BlockDriverState *base;
diff --git a/include/block/block.h b/include/block/block.h
index 11c162d..acddf3b 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -336,6 +336,7 @@ int bdrv_inactivate_all(void);
/* Ensure contents are flushed to disk. */
int bdrv_flush(BlockDriverState *bs);
int coroutine_fn bdrv_co_flush(BlockDriverState *bs);
+int bdrv_flush_all(void);
void bdrv_close_all(void);
void bdrv_drain(BlockDriverState *bs);
void coroutine_fn bdrv_co_drain(BlockDriverState *bs);
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 26/67] qemu: use bdrv_flush_all for vm_stop et al
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (24 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 25/67] block: reintroduce bdrv_flush_all Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 27/67] block-backend: remove blk_flush_all Michael Roth
` (41 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, John Snow, Kevin Wolf
From: John Snow <jsnow@redhat.com>
Reimplement bdrv_flush_all for vm_stop. In contrast to blk_flush_all,
bdrv_flush_all does not have device model restrictions. This allows
us to flush and halt unconditionally without error.
This allows us to do things like migrate when we have a device with
an open tray, but has a node that may need to be flushed, or nodes
that aren't currently attached to any device and need to be flushed.
Specifically, this allows us to migrate when we have a CDROM with
an open tray.
Signed-off-by: John Snow <jsnow@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Acked-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 22af08eacf6b5aa0e6c0581e547380b3eb4f95e9)
Conflicts:
cpus.c
* drop context dependancy on 6d0ceb80
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
cpus.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/cpus.c b/cpus.c
index 84c3520..7e73c03 100644
--- a/cpus.c
+++ b/cpus.c
@@ -745,7 +745,7 @@ static int do_vm_stop(RunState state)
}
bdrv_drain_all();
- ret = blk_flush_all();
+ ret = bdrv_flush_all();
return ret;
}
@@ -1488,7 +1488,7 @@ int vm_stop_force_state(RunState state)
bdrv_drain_all();
/* Make sure to return an error if the flush in a previous vm_stop()
* failed. */
- return blk_flush_all();
+ return bdrv_flush_all();
}
}
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 27/67] block-backend: remove blk_flush_all
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (25 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 26/67] qemu: use bdrv_flush_all for vm_stop et al Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 28/67] migrate: Fix cpu-throttle-increment regression in HMP Michael Roth
` (40 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, John Snow, Kevin Wolf
From: John Snow <jsnow@redhat.com>
We can teach Xen to drain and flush each device as it needs to, instead
of trying to flush ALL devices. This removes the last user of
blk_flush_all.
The function is therefore removed under the premise that any new uses
of blk_flush_all would be the wrong paradigm: either flush the single
device that requires flushing, or use an appropriate flush_all mechanism
from outside of the BlkBackend layer.
Signed-off-by: John Snow <jsnow@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Acked-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 49137bf6845eaecad51a047fc06dd11c56118460)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
block/block-backend.c | 22 ----------------------
hw/i386/xen/xen_platform.c | 2 --
hw/ide/piix.c | 4 ++++
include/sysemu/block-backend.h | 1 -
4 files changed, 4 insertions(+), 25 deletions(-)
diff --git a/block/block-backend.c b/block/block-backend.c
index effa038..a67a463 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -1624,28 +1624,6 @@ int blk_commit_all(void)
return 0;
}
-int blk_flush_all(void)
-{
- BlockBackend *blk = NULL;
- int result = 0;
-
- while ((blk = blk_all_next(blk)) != NULL) {
- AioContext *aio_context = blk_get_aio_context(blk);
- int ret;
-
- aio_context_acquire(aio_context);
- if (blk_is_inserted(blk)) {
- ret = blk_flush(blk);
- if (ret < 0 && !result) {
- result = ret;
- }
- }
- aio_context_release(aio_context);
- }
-
- return result;
-}
-
/* throttling disk I/O limits */
void blk_set_io_limits(BlockBackend *blk, ThrottleConfig *cfg)
diff --git a/hw/i386/xen/xen_platform.c b/hw/i386/xen/xen_platform.c
index aa78393..f85635c 100644
--- a/hw/i386/xen/xen_platform.c
+++ b/hw/i386/xen/xen_platform.c
@@ -134,8 +134,6 @@ static void platform_fixed_ioport_writew(void *opaque, uint32_t addr, uint32_t v
devices, and bit 2 the non-primary-master IDE devices. */
if (val & UNPLUG_ALL_IDE_DISKS) {
DPRINTF("unplug disks\n");
- blk_drain_all();
- blk_flush_all();
pci_unplug_disks(pci_dev->bus);
}
if (val & UNPLUG_ALL_NICS) {
diff --git a/hw/ide/piix.c b/hw/ide/piix.c
index c190fca..d5777fd 100644
--- a/hw/ide/piix.c
+++ b/hw/ide/piix.c
@@ -179,6 +179,10 @@ int pci_piix3_xen_ide_unplug(DeviceState *dev)
if (di != NULL && !di->media_cd) {
BlockBackend *blk = blk_by_legacy_dinfo(di);
DeviceState *ds = blk_get_attached_dev(blk);
+
+ blk_drain(blk);
+ blk_flush(blk);
+
if (ds) {
blk_detach_dev(blk, ds);
}
diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h
index 2da4905..b1ba74f 100644
--- a/include/sysemu/block-backend.h
+++ b/include/sysemu/block-backend.h
@@ -149,7 +149,6 @@ BlockAIOCB *blk_aio_ioctl(BlockBackend *blk, unsigned long int req, void *buf,
int blk_co_pdiscard(BlockBackend *blk, int64_t offset, int count);
int blk_co_flush(BlockBackend *blk);
int blk_flush(BlockBackend *blk);
-int blk_flush_all(void);
int blk_commit_all(void);
void blk_drain(BlockBackend *blk);
void blk_drain_all(void);
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 28/67] migrate: Fix cpu-throttle-increment regression in HMP
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (26 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 27/67] block-backend: remove blk_flush_all Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 29/67] qht: simplify qht_reset_size Michael Roth
` (39 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Eric Blake, Juan Quintela
From: Eric Blake <eblake@redhat.com>
Commit 69ef1f3 accidentally broke migrate_set_parameter's ability
to set the cpu-throttle-increment to anything other than the
default, because it forgot to parse the user's string into an
integer.
CC: qemu-stable@nongnu.org
Signed-off-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit bb2b777cf9a2862fe31a40256659ff49ae3d2006)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hmp.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/hmp.c b/hmp.c
index cc2056e..bb45f7f 100644
--- a/hmp.c
+++ b/hmp.c
@@ -1284,6 +1284,7 @@ void hmp_migrate_set_parameter(Monitor *mon, const QDict *qdict)
break;
case MIGRATION_PARAMETER_CPU_THROTTLE_INCREMENT:
has_cpu_throttle_increment = true;
+ use_int_value = true;
break;
case MIGRATION_PARAMETER_TLS_CREDS:
has_tls_creds = true;
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 29/67] qht: simplify qht_reset_size
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (27 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 28/67] migrate: Fix cpu-throttle-increment regression in HMP Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 30/67] qht: fix unlock-after-free segfault upon resizing Michael Roth
` (38 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Emilio G. Cota, Paolo Bonzini
From: "Emilio G. Cota" <cota@braap.org>
Sometimes gcc doesn't pick up the fact that 'new' is properly
set if 'resize == true', which may generate an unnecessary
build warning.
Fix it by removing 'resize' and directly checking that 'new'
is non-NULL.
Signed-off-by: Emilio G. Cota <cota@braap.org>
Message-Id: <1475706880-10667-2-git-send-email-cota@braap.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit f555a9d0b3c785b698f32e6879e97d0a4b387314)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
util/qht.c | 8 +++-----
1 file changed, 3 insertions(+), 5 deletions(-)
diff --git a/util/qht.c b/util/qht.c
index 16a8d79..af8da3c 100644
--- a/util/qht.c
+++ b/util/qht.c
@@ -410,10 +410,9 @@ void qht_reset(struct qht *ht)
bool qht_reset_size(struct qht *ht, size_t n_elems)
{
- struct qht_map *new;
+ struct qht_map *new = NULL;
struct qht_map *map;
size_t n_buckets;
- bool resize = false;
n_buckets = qht_elems_to_buckets(n_elems);
@@ -421,18 +420,17 @@ bool qht_reset_size(struct qht *ht, size_t n_elems)
map = ht->map;
if (n_buckets != map->n_buckets) {
new = qht_map_create(n_buckets);
- resize = true;
}
qht_map_lock_buckets(map);
qht_map_reset__all_locked(map);
- if (resize) {
+ if (new) {
qht_do_resize(ht, new);
}
qht_map_unlock_buckets(map);
qemu_mutex_unlock(&ht->lock);
- return resize;
+ return !!new;
}
static inline
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 30/67] qht: fix unlock-after-free segfault upon resizing
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (28 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 29/67] qht: simplify qht_reset_size Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 31/67] char: fix missing return in error path for chardev TLS init Michael Roth
` (37 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Emilio G. Cota, Paolo Bonzini
From: "Emilio G. Cota" <cota@braap.org>
The old map's bucket locks are being unlocked *after*
that same old map has been passed to RCU for destruction.
This is a bug that can cause a segfault, since there's
no guarantee that the deletion will be deferred (e.g.
there may be no concurrent readers).
The segfault is easily triggered in RHEL6/CentOS6 with qht-test,
particularly on a single-core system or by pinning qht-test
to a single core.
Fix it by unlocking the map's bucket locks right after having
published the new map, and (crucially) before marking the map
for deletion via call_rcu().
While at it, expand qht_do_resize() to atomically do (1) a reset,
(2) a resize, or (3) a reset+resize. This simplifies the calling
code, since the new function (qht_do_resize_reset()) acquires
and releases the buckets' locks.
Note that no qht_do_reset inline is provided, since it would have
no users--qht_reset() already performs a reset without taking
ht->lock.
Reported-by: Peter Maydell <peter.maydell@linaro.org>
Reported-by: Daniel P. Berrange <berrange@redhat.com>
Signed-off-by: Emilio G. Cota <cota@braap.org>
Message-Id: <1475706880-10667-3-git-send-email-cota@braap.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 76b553b308dc8671eb672b889b38889b1231cf1e)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
util/qht.c | 49 ++++++++++++++++++++++++++++---------------------
1 file changed, 28 insertions(+), 21 deletions(-)
diff --git a/util/qht.c b/util/qht.c
index af8da3c..6c61aca 100644
--- a/util/qht.c
+++ b/util/qht.c
@@ -133,7 +133,8 @@ struct qht_map {
/* trigger a resize when n_added_buckets > n_buckets / div */
#define QHT_NR_ADDED_BUCKETS_THRESHOLD_DIV 8
-static void qht_do_resize(struct qht *ht, struct qht_map *new);
+static void qht_do_resize_reset(struct qht *ht, struct qht_map *new,
+ bool reset);
static void qht_grow_maybe(struct qht *ht);
#ifdef QHT_DEBUG
@@ -408,6 +409,16 @@ void qht_reset(struct qht *ht)
qht_map_unlock_buckets(map);
}
+static inline void qht_do_resize(struct qht *ht, struct qht_map *new)
+{
+ qht_do_resize_reset(ht, new, false);
+}
+
+static inline void qht_do_resize_and_reset(struct qht *ht, struct qht_map *new)
+{
+ qht_do_resize_reset(ht, new, true);
+}
+
bool qht_reset_size(struct qht *ht, size_t n_elems)
{
struct qht_map *new = NULL;
@@ -421,13 +432,7 @@ bool qht_reset_size(struct qht *ht, size_t n_elems)
if (n_buckets != map->n_buckets) {
new = qht_map_create(n_buckets);
}
-
- qht_map_lock_buckets(map);
- qht_map_reset__all_locked(map);
- if (new) {
- qht_do_resize(ht, new);
- }
- qht_map_unlock_buckets(map);
+ qht_do_resize_and_reset(ht, new);
qemu_mutex_unlock(&ht->lock);
return !!new;
@@ -559,9 +564,7 @@ static __attribute__((noinline)) void qht_grow_maybe(struct qht *ht)
if (qht_map_needs_resize(map)) {
struct qht_map *new = qht_map_create(map->n_buckets * 2);
- qht_map_lock_buckets(map);
qht_do_resize(ht, new);
- qht_map_unlock_buckets(map);
}
qemu_mutex_unlock(&ht->lock);
}
@@ -737,24 +740,31 @@ static void qht_map_copy(struct qht *ht, void *p, uint32_t hash, void *userp)
}
/*
- * Call with ht->lock and all bucket locks held.
- *
- * Creating the @new map here would add unnecessary delay while all the locks
- * are held--holding up the bucket locks is particularly bad, since no writes
- * can occur while these are held. Thus, we let callers create the new map,
- * hopefully without the bucket locks held.
+ * Atomically perform a resize and/or reset.
+ * Call with ht->lock held.
*/
-static void qht_do_resize(struct qht *ht, struct qht_map *new)
+static void qht_do_resize_reset(struct qht *ht, struct qht_map *new, bool reset)
{
struct qht_map *old;
old = ht->map;
- g_assert_cmpuint(new->n_buckets, !=, old->n_buckets);
+ qht_map_lock_buckets(old);
+ if (reset) {
+ qht_map_reset__all_locked(old);
+ }
+
+ if (new == NULL) {
+ qht_map_unlock_buckets(old);
+ return;
+ }
+
+ g_assert_cmpuint(new->n_buckets, !=, old->n_buckets);
qht_map_iter__all_locked(ht, old, qht_map_copy, new);
qht_map_debug__all_locked(new);
atomic_rcu_set(&ht->map, new);
+ qht_map_unlock_buckets(old);
call_rcu(old, qht_map_destroy, rcu);
}
@@ -766,12 +776,9 @@ bool qht_resize(struct qht *ht, size_t n_elems)
qemu_mutex_lock(&ht->lock);
if (n_buckets != ht->map->n_buckets) {
struct qht_map *new;
- struct qht_map *old = ht->map;
new = qht_map_create(n_buckets);
- qht_map_lock_buckets(old);
qht_do_resize(ht, new);
- qht_map_unlock_buckets(old);
ret = true;
}
qemu_mutex_unlock(&ht->lock);
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 31/67] char: fix missing return in error path for chardev TLS init
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (29 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 30/67] qht: fix unlock-after-free segfault upon resizing Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 32/67] qmp: fix object-add assert() without props Michael Roth
` (36 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Daniel P. Berrange, Michael Tokarev
From: "Daniel P. Berrange" <berrange@redhat.com>
If the qio_channel_tls_new_(server|client) methods fail,
we disconnect the client. Unfortunately a missing return
means we then go on to try and run the TLS handshake on
a NULL I/O channel. This gives predictably segfaulty
results.
The main way to trigger this is to request a bogus TLS
priority string for the TLS credentials. e.g.
-object tls-creds-x509,id=tls0,priority=wibble,...
Most other ways appear impossible to trigger except
perhaps if OOM conditions cause gnutls initialization
to fail.
Signed-off-by: Daniel P. Berrange <berrange@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
(cherry picked from commit 660a2d83e026496db6b3eaec2256a2cdd6c74de8)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
qemu-char.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/qemu-char.c b/qemu-char.c
index fdb23f5..90e9627 100644
--- a/qemu-char.c
+++ b/qemu-char.c
@@ -3096,6 +3096,7 @@ static void tcp_chr_tls_init(CharDriverState *chr)
if (tioc == NULL) {
error_free(err);
tcp_chr_disconnect(chr);
+ return;
}
object_unref(OBJECT(s->ioc));
s->ioc = QIO_CHANNEL(tioc);
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 32/67] qmp: fix object-add assert() without props
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (30 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 31/67] char: fix missing return in error path for chardev TLS init Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 33/67] qapi: Fix crash when 'any' or 'null' parameter is missing Michael Roth
` (35 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Marc-André Lureau, Markus Armbruster
From: Marc-André Lureau <marcandre.lureau@redhat.com>
Since commit ad739706bbadee49, user_creatable_add_type() expects to be
given a qdict. However, if object-add is called without props, you reach
the assert: "qemu/qom/object_interfaces.c:115: user_creatable_add_type:
Assertion `qdict' failed.", because the qdict isn't created in this
case (it's optional).
Furthermore, qmp_input_visitor_new() is not meant to be called without a
dict, and a further commit will assert in this situation.
If none given, create an empty qdict in qmp to avoid the
user_creatable_add_type() assert(qdict).
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-Id: <20160922203927.28241-2-marcandre.lureau@redhat.com>
Tested-by: Xiao Long Jiang <zxiaol@linux.vnet.ibm.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Markus Armbruster <armbru@redhat.com>
(cherry picked from commit e64c75a9752c5d0fd64eb2e684c656a5ea7d03c6)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
qmp.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/qmp.c b/qmp.c
index b6d531e..c485abe 100644
--- a/qmp.c
+++ b/qmp.c
@@ -654,7 +654,7 @@ void qmp_add_client(const char *protocol, const char *fdname,
void qmp_object_add(const char *type, const char *id,
bool has_props, QObject *props, Error **errp)
{
- const QDict *pdict = NULL;
+ QDict *pdict;
Visitor *v;
Object *obj;
@@ -664,14 +664,18 @@ void qmp_object_add(const char *type, const char *id,
error_setg(errp, QERR_INVALID_PARAMETER_TYPE, "props", "dict");
return;
}
+ QINCREF(pdict);
+ } else {
+ pdict = qdict_new();
}
- v = qmp_input_visitor_new(props, true);
+ v = qmp_input_visitor_new(QOBJECT(pdict), true);
obj = user_creatable_add_type(type, id, pdict, v, errp);
visit_free(v);
if (obj) {
object_unref(obj);
}
+ QDECREF(pdict);
}
void qmp_object_del(const char *id, Error **errp)
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 33/67] qapi: Fix crash when 'any' or 'null' parameter is missing
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (31 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 32/67] qmp: fix object-add assert() without props Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 34/67] tests/test-qmp-input-strict: Cover missing struct members Michael Roth
` (34 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Marc-André Lureau, Markus Armbruster
From: Marc-André Lureau <marcandre.lureau@redhat.com>
Unlike the other visit methods, visit_type_any() and visit_type_null()
neglect to check whether qmp_input_get_object() succeeded. They crash
when it fails. Reproducer:
{ "execute": "qom-set",
"arguments": { "path": "/machine", "property": "rtc-time" } }
Will crash with:
qapi/qapi-visit-core.c:277: visit_type_any: Assertion `!err != !*obj'
failed
Broken in commit 5c678ee. Fix by adding the missing error checks.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-Id: <20160922203927.28241-3-marcandre.lureau@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
[Commit message rephrased]
Signed-off-by: Markus Armbruster <armbru@redhat.com>
(cherry picked from commit c489780203f9b22aca5539ec7589b7140bdc951f)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
qapi/qmp-input-visitor.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/qapi/qmp-input-visitor.c b/qapi/qmp-input-visitor.c
index 64dd392..fc91e74 100644
--- a/qapi/qmp-input-visitor.c
+++ b/qapi/qmp-input-visitor.c
@@ -338,6 +338,12 @@ static void qmp_input_type_any(Visitor *v, const char *name, QObject **obj,
QmpInputVisitor *qiv = to_qiv(v);
QObject *qobj = qmp_input_get_object(qiv, name, true);
+ if (!qobj) {
+ error_setg(errp, QERR_MISSING_PARAMETER, name ? name : "null");
+ *obj = NULL;
+ return;
+ }
+
qobject_incref(qobj);
*obj = qobj;
}
@@ -347,6 +353,11 @@ static void qmp_input_type_null(Visitor *v, const char *name, Error **errp)
QmpInputVisitor *qiv = to_qiv(v);
QObject *qobj = qmp_input_get_object(qiv, name, true);
+ if (!qobj) {
+ error_setg(errp, QERR_MISSING_PARAMETER, name ? name : "null");
+ return;
+ }
+
if (qobject_type(qobj) != QTYPE_QNULL) {
error_setg(errp, QERR_INVALID_PARAMETER_TYPE, name ? name : "null",
"null");
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 34/67] tests/test-qmp-input-strict: Cover missing struct members
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (32 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 33/67] qapi: Fix crash when 'any' or 'null' parameter is missing Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 35/67] rbd: shift byte count as a 64-bit value Michael Roth
` (33 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Markus Armbruster
From: Markus Armbruster <armbru@redhat.com>
These tests would have caught the bug fixed by the previous commit.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <1475594630-24758-1-git-send-email-armbru@redhat.com>
(cherry picked from commit bce3035a44c40bd3ec29d3162025fd350f2d8dbf)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
tests/test-qmp-input-strict.c | 46 +++++++++++++++++++++++++++++++++++++++++++
1 file changed, 46 insertions(+)
diff --git a/tests/test-qmp-input-strict.c b/tests/test-qmp-input-strict.c
index 814550a..d87f8b8 100644
--- a/tests/test-qmp-input-strict.c
+++ b/tests/test-qmp-input-strict.c
@@ -193,6 +193,50 @@ static void test_validate_fail_struct_nested(TestInputVisitorData *data,
g_assert(!udp);
}
+static void test_validate_fail_struct_missing(TestInputVisitorData *data,
+ const void *unused)
+{
+ Error *err = NULL;
+ Visitor *v;
+ QObject *any;
+ GenericAlternate *alt;
+ bool present;
+ int en;
+ int64_t i64;
+ uint32_t u32;
+ int8_t i8;
+ char *str;
+ double dbl;
+
+ v = validate_test_init(data, "{}");
+ visit_start_struct(v, NULL, NULL, 0, &error_abort);
+ visit_start_struct(v, "struct", NULL, 0, &err);
+ error_free_or_abort(&err);
+ visit_start_list(v, "list", NULL, 0, &err);
+ error_free_or_abort(&err);
+ visit_start_alternate(v, "alternate", &alt, sizeof(*alt), false, &err);
+ error_free_or_abort(&err);
+ visit_optional(v, "optional", &present);
+ g_assert(!present);
+ visit_type_enum(v, "enum", &en, EnumOne_lookup, &err);
+ error_free_or_abort(&err);
+ visit_type_int(v, "i64", &i64, &err);
+ error_free_or_abort(&err);
+ visit_type_uint32(v, "u32", &u32, &err);
+ error_free_or_abort(&err);
+ visit_type_int8(v, "i8", &i8, &err);
+ error_free_or_abort(&err);
+ visit_type_str(v, "i8", &str, &err);
+ error_free_or_abort(&err);
+ visit_type_number(v, "dbl", &dbl, &err);
+ error_free_or_abort(&err);
+ visit_type_any(v, "any", &any, &err);
+ error_free_or_abort(&err);
+ visit_type_null(v, "null", &err);
+ error_free_or_abort(&err);
+ visit_end_struct(v, NULL);
+}
+
static void test_validate_fail_list(TestInputVisitorData *data,
const void *unused)
{
@@ -316,6 +360,8 @@ int main(int argc, char **argv)
&testdata, test_validate_fail_struct);
validate_test_add("/visitor/input-strict/fail/struct-nested",
&testdata, test_validate_fail_struct_nested);
+ validate_test_add("/visitor/input-strict/fail/struct-missing",
+ &testdata, test_validate_fail_struct_missing);
validate_test_add("/visitor/input-strict/fail/list",
&testdata, test_validate_fail_list);
validate_test_add("/visitor/input-strict/fail/union-flat",
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 35/67] rbd: shift byte count as a 64-bit value
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (33 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 34/67] tests/test-qmp-input-strict: Cover missing struct members Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 36/67] ppc/kvm: Mark 64kB page size support as disabled if not available Michael Roth
` (32 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Paolo Bonzini, kwolf, eblake
From: Paolo Bonzini <pbonzini@redhat.com>
Otherwise, reads of more than 2GB fail. Until commit
7bbca9e290a9c7c217b5a24fc6094e91e54bd05d, reads of 2^41
bytes succeeded at least theoretically.
In fact, pdiscard ought to receive a 64-bit integer as the
count for the same reason.
Reported by Coverity.
Fixes: 7bbca9e290a9c7c217b5a24fc6094e91e54bd05d
Cc: qemu-stable@nongnu.org
Cc: kwolf@redhat.com
Cc: eblake@redhat.com
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit e948f663e9334249c394b88926addcdd3f9e35cd)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
block/rbd.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/block/rbd.c b/block/rbd.c
index 0106fea..5cefdbb 100644
--- a/block/rbd.c
+++ b/block/rbd.c
@@ -737,7 +737,7 @@ static BlockAIOCB *qemu_rbd_aio_readv(BlockDriverState *bs,
void *opaque)
{
return rbd_start_aio(bs, sector_num << BDRV_SECTOR_BITS, qiov,
- nb_sectors << BDRV_SECTOR_BITS, cb, opaque,
+ (int64_t) nb_sectors << BDRV_SECTOR_BITS, cb, opaque,
RBD_AIO_READ);
}
@@ -749,7 +749,7 @@ static BlockAIOCB *qemu_rbd_aio_writev(BlockDriverState *bs,
void *opaque)
{
return rbd_start_aio(bs, sector_num << BDRV_SECTOR_BITS, qiov,
- nb_sectors << BDRV_SECTOR_BITS, cb, opaque,
+ (int64_t) nb_sectors << BDRV_SECTOR_BITS, cb, opaque,
RBD_AIO_WRITE);
}
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 36/67] ppc/kvm: Mark 64kB page size support as disabled if not available
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (34 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 35/67] rbd: shift byte count as a 64-bit value Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 37/67] throttle: Correct access to wrong BlockBackendPublic structures Michael Roth
` (31 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Thomas Huth, David Gibson
From: Thomas Huth <thuth@redhat.com>
QEMU currently refuses to start with KVM-PR and only prints out
qemu: fatal: Unknown MMU model 851972
when being started there. This is because commit 4322e8ced5aaac719
("ppc: Fix 64K pages support in full emulation") introduced a new
POWERPC_MMU_64K bit to indicate support for this page size, but
it never gets cleared on KVM-PR if the host kernel does not support
this. Thus we've got to turn off this bit in the mmu_model for KVM-PR.
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
(cherry picked from commit 0d594f5565837fe2886a8aa307ef8abb65eab8f7)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
target-ppc/kvm.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/target-ppc/kvm.c b/target-ppc/kvm.c
index f26a141..5680f8b 100644
--- a/target-ppc/kvm.c
+++ b/target-ppc/kvm.c
@@ -429,6 +429,7 @@ static void kvm_fixup_page_sizes(PowerPCCPU *cpu)
CPUPPCState *env = &cpu->env;
long rampagesize;
int iq, ik, jq, jk;
+ bool has_64k_pages = false;
/* We only handle page sizes for 64-bit server guests for now */
if (!(env->mmu_model & POWERPC_MMU_64)) {
@@ -472,6 +473,9 @@ static void kvm_fixup_page_sizes(PowerPCCPU *cpu)
ksps->enc[jk].page_shift)) {
continue;
}
+ if (ksps->enc[jk].page_shift == 16) {
+ has_64k_pages = true;
+ }
qsps->enc[jq].page_shift = ksps->enc[jk].page_shift;
qsps->enc[jq].pte_enc = ksps->enc[jk].pte_enc;
if (++jq >= PPC_PAGE_SIZES_MAX_SZ) {
@@ -486,6 +490,9 @@ static void kvm_fixup_page_sizes(PowerPCCPU *cpu)
if (!(smmu_info.flags & KVM_PPC_1T_SEGMENTS)) {
env->mmu_model &= ~POWERPC_MMU_1TSEG;
}
+ if (!has_64k_pages) {
+ env->mmu_model &= ~POWERPC_MMU_64K;
+ }
}
#else /* defined (TARGET_PPC64) */
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 37/67] throttle: Correct access to wrong BlockBackendPublic structures
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (35 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 36/67] ppc/kvm: Mark 64kB page size support as disabled if not available Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 38/67] qemu-iotests: Test I/O in a single drive from a throttling group Michael Roth
` (30 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Alberto Garcia, Kevin Wolf
From: Alberto Garcia <berto@igalia.com>
In 27ccdd52598290f0f8b58be56e235aff7aebfaf3 the throttling fields were
moved from BlockDriverState to BlockBackend. However in a few cases
the code started using throttling fields from the active BlockBackend
instead of the round-robin token, making the algorithm behave
incorrectly.
This can cause starvation if there's a throttling group with several
drives but only one of them has I/O.
Cc: qemu-stable@nongnu.org
Reported-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Alberto Garcia <berto@igalia.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 6bf77e1c2dc24da1bade16e8a9a637f3b127314d)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
block/throttle-groups.c | 27 +++++++++++++++++++++++----
1 file changed, 23 insertions(+), 4 deletions(-)
diff --git a/block/throttle-groups.c b/block/throttle-groups.c
index 59545e2..17b2efb 100644
--- a/block/throttle-groups.c
+++ b/block/throttle-groups.c
@@ -168,6 +168,22 @@ static BlockBackend *throttle_group_next_blk(BlockBackend *blk)
return blk_by_public(next);
}
+/*
+ * Return whether a BlockBackend has pending requests.
+ *
+ * This assumes that tg->lock is held.
+ *
+ * @blk: the BlockBackend
+ * @is_write: the type of operation (read/write)
+ * @ret: whether the BlockBackend has pending requests.
+ */
+static inline bool blk_has_pending_reqs(BlockBackend *blk,
+ bool is_write)
+{
+ const BlockBackendPublic *blkp = blk_get_public(blk);
+ return blkp->pending_reqs[is_write];
+}
+
/* Return the next BlockBackend in the round-robin sequence with pending I/O
* requests.
*
@@ -188,7 +204,7 @@ static BlockBackend *next_throttle_token(BlockBackend *blk, bool is_write)
/* get next bs round in round robin style */
token = throttle_group_next_blk(token);
- while (token != start && !blkp->pending_reqs[is_write]) {
+ while (token != start && !blk_has_pending_reqs(token, is_write)) {
token = throttle_group_next_blk(token);
}
@@ -196,10 +212,13 @@ static BlockBackend *next_throttle_token(BlockBackend *blk, bool is_write)
* then decide the token is the current bs because chances are
* the current bs get the current request queued.
*/
- if (token == start && !blkp->pending_reqs[is_write]) {
+ if (token == start && !blk_has_pending_reqs(token, is_write)) {
token = blk;
}
+ /* Either we return the original BB, or one with pending requests */
+ assert(token == blk || blk_has_pending_reqs(token, is_write));
+
return token;
}
@@ -257,7 +276,7 @@ static void schedule_next_request(BlockBackend *blk, bool is_write)
/* Check if there's any pending request to schedule next */
token = next_throttle_token(blk, is_write);
- if (!blkp->pending_reqs[is_write]) {
+ if (!blk_has_pending_reqs(token, is_write)) {
return;
}
@@ -271,7 +290,7 @@ static void schedule_next_request(BlockBackend *blk, bool is_write)
qemu_co_queue_next(&blkp->throttled_reqs[is_write])) {
token = blk;
} else {
- ThrottleTimers *tt = &blkp->throttle_timers;
+ ThrottleTimers *tt = &blk_get_public(token)->throttle_timers;
int64_t now = qemu_clock_get_ns(tt->clock_type);
timer_mod(tt->timers[is_write], now + 1);
tg->any_timer_armed[is_write] = true;
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 38/67] qemu-iotests: Test I/O in a single drive from a throttling group
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (36 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 37/67] throttle: Correct access to wrong BlockBackendPublic structures Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 39/67] net: rtl8139: limit processing of ring descriptors Michael Roth
` (29 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Alberto Garcia, Kevin Wolf
From: Alberto Garcia <berto@igalia.com>
iotest 093 contains a test that creates a throttling group with
several drives and performs I/O in all of them. This patch adds a new
test that creates a similar setup but only performs I/O in one of the
drives at the same time.
This is useful to test that the round robin algorithm is behaving
properly in these scenarios, and is specifically written using the
regression introduced in 27ccdd52598290f0f8b58be56e as an example.
Signed-off-by: Alberto Garcia <berto@igalia.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit a26ddb43963e77aeebc2a4f011d27b2d9c017f21)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
tests/qemu-iotests/093 | 33 ++++++++++++++++++++++++++++-----
tests/qemu-iotests/093.out | 4 ++--
2 files changed, 30 insertions(+), 7 deletions(-)
diff --git a/tests/qemu-iotests/093 b/tests/qemu-iotests/093
index ffcb271..2ed393a 100755
--- a/tests/qemu-iotests/093
+++ b/tests/qemu-iotests/093
@@ -53,7 +53,7 @@ class ThrottleTestCase(iotests.QMPTestCase):
result = self.vm.qmp("block_set_io_throttle", conv_keys=False, **params)
self.assert_qmp(result, 'return', {})
- def do_test_throttle(self, ndrives, seconds, params):
+ def do_test_throttle(self, ndrives, seconds, params, first_drive = 0):
def check_limit(limit, num):
# IO throttling algorithm is discrete, allow 10% error so the test
# is more robust
@@ -85,12 +85,14 @@ class ThrottleTestCase(iotests.QMPTestCase):
# Send I/O requests to all drives
for i in range(rd_nr):
for drive in range(0, ndrives):
- self.vm.hmp_qemu_io("drive%d" % drive, "aio_read %d %d" %
+ idx = first_drive + drive
+ self.vm.hmp_qemu_io("drive%d" % idx, "aio_read %d %d" %
(i * rq_size, rq_size))
for i in range(wr_nr):
for drive in range(0, ndrives):
- self.vm.hmp_qemu_io("drive%d" % drive, "aio_write %d %d" %
+ idx = first_drive + drive
+ self.vm.hmp_qemu_io("drive%d" % idx, "aio_write %d %d" %
(i * rq_size, rq_size))
# We'll store the I/O stats for each drive in these arrays
@@ -105,15 +107,17 @@ class ThrottleTestCase(iotests.QMPTestCase):
# Read the stats before advancing the clock
for i in range(0, ndrives):
+ idx = first_drive + i
start_rd_bytes[i], start_rd_iops[i], start_wr_bytes[i], \
- start_wr_iops[i] = self.blockstats('drive%d' % i)
+ start_wr_iops[i] = self.blockstats('drive%d' % idx)
self.vm.qtest("clock_step %d" % ns)
# Read the stats after advancing the clock
for i in range(0, ndrives):
+ idx = first_drive + i
end_rd_bytes[i], end_rd_iops[i], end_wr_bytes[i], \
- end_wr_iops[i] = self.blockstats('drive%d' % i)
+ end_wr_iops[i] = self.blockstats('drive%d' % idx)
# Check that the I/O is within the limits and evenly distributed
for i in range(0, ndrives):
@@ -129,6 +133,7 @@ class ThrottleTestCase(iotests.QMPTestCase):
self.assertTrue(check_limit(params['iops_rd'], rd_iops))
self.assertTrue(check_limit(params['iops_wr'], wr_iops))
+ # Connect N drives to a VM and test I/O in all of them
def test_all(self):
params = {"bps": 4096,
"bps_rd": 4096,
@@ -146,6 +151,24 @@ class ThrottleTestCase(iotests.QMPTestCase):
self.configure_throttle(ndrives, limits)
self.do_test_throttle(ndrives, 5, limits)
+ # Connect N drives to a VM and test I/O in just one of them a time
+ def test_one(self):
+ params = {"bps": 4096,
+ "bps_rd": 4096,
+ "bps_wr": 4096,
+ "iops": 10,
+ "iops_rd": 10,
+ "iops_wr": 10,
+ }
+ # Repeat the test for each one of the drives
+ for drive in range(0, self.max_drives):
+ # Pick each out of all possible params and test
+ for tk in params:
+ limits = dict([(k, 0) for k in params])
+ limits[tk] = params[tk] * self.max_drives
+ self.configure_throttle(self.max_drives, limits)
+ self.do_test_throttle(1, 5, limits, drive)
+
def test_burst(self):
params = {"bps": 4096,
"bps_rd": 4096,
diff --git a/tests/qemu-iotests/093.out b/tests/qemu-iotests/093.out
index 914e373..2f7d390 100644
--- a/tests/qemu-iotests/093.out
+++ b/tests/qemu-iotests/093.out
@@ -1,5 +1,5 @@
-.....
+.......
----------------------------------------------------------------------
-Ran 5 tests
+Ran 7 tests
OK
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 39/67] net: rtl8139: limit processing of ring descriptors
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (37 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 38/67] qemu-iotests: Test I/O in a single drive from a throttling group Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 40/67] memory: Replace skip_dump flag with "ram_device" Michael Roth
` (28 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Prasad J Pandit, Jason Wang
From: Prasad J Pandit <pjp@fedoraproject.org>
RTL8139 ethernet controller in C+ mode supports multiple
descriptor rings, each with maximum of 64 descriptors. While
processing transmit descriptor ring in 'rtl8139_cplus_transmit',
it does not limit the descriptor count and runs forever. Add
check to avoid it.
Reported-by: Andrew Henderson <hendersa@icculus.org>
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Signed-off-by: Jason Wang <jasowang@redhat.com>
(cherry picked from commit c7c35916692fe010fef25ac338443d3fe40be225)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/net/rtl8139.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/hw/net/rtl8139.c b/hw/net/rtl8139.c
index 3345bc6..f05e59c 100644
--- a/hw/net/rtl8139.c
+++ b/hw/net/rtl8139.c
@@ -2350,7 +2350,7 @@ static void rtl8139_cplus_transmit(RTL8139State *s)
{
int txcount = 0;
- while (rtl8139_cplus_transmit_one(s))
+ while (txcount < 64 && rtl8139_cplus_transmit_one(s))
{
++txcount;
}
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 40/67] memory: Replace skip_dump flag with "ram_device"
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (38 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 39/67] net: rtl8139: limit processing of ring descriptors Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 41/67] memory: Don't use memcpy for ram_device regions Michael Roth
` (27 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Alex Williamson
From: Alex Williamson <alex.williamson@redhat.com>
Setting skip_dump on a MemoryRegion allows us to modify one specific
code path, but the restriction we're trying to address encompasses
more than that. If we have a RAM MemoryRegion backed by a physical
device, it not only restricts our ability to dump that region, but
also affects how we should manipulate it. Here we recognize that
MemoryRegions do not change to sometimes allow dumps and other times
not, so we replace setting the skip_dump flag with a new initializer
so that we know exactly the type of region to which we're applying
this behavior.
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 21e00fa55f3fdfcbb20da7c6876c91ef3609b387)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/vfio/common.c | 9 ++++-----
hw/vfio/spapr.c | 2 +-
include/exec/memory.h | 41 ++++++++++++++++++++++++++++-------------
memory.c | 13 +++++++++----
memory_mapping.c | 2 +-
5 files changed, 43 insertions(+), 24 deletions(-)
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index b313e7c..b818723 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -723,12 +723,11 @@ int vfio_region_mmap(VFIORegion *region)
name = g_strdup_printf("%s mmaps[%d]",
memory_region_name(region->mem), i);
- memory_region_init_ram_ptr(®ion->mmaps[i].mem,
- memory_region_owner(region->mem),
- name, region->mmaps[i].size,
- region->mmaps[i].mmap);
+ memory_region_init_ram_device_ptr(®ion->mmaps[i].mem,
+ memory_region_owner(region->mem),
+ name, region->mmaps[i].size,
+ region->mmaps[i].mmap);
g_free(name);
- memory_region_set_skip_dump(®ion->mmaps[i].mem);
memory_region_add_subregion(region->mem, region->mmaps[i].offset,
®ion->mmaps[i].mem);
diff --git a/hw/vfio/spapr.c b/hw/vfio/spapr.c
index 7443d34..4409bcc 100644
--- a/hw/vfio/spapr.c
+++ b/hw/vfio/spapr.c
@@ -25,7 +25,7 @@ static bool vfio_prereg_listener_skipped_section(MemoryRegionSection *section)
}
return !memory_region_is_ram(section->mr) ||
- memory_region_is_skip_dump(section->mr);
+ memory_region_is_ram_device(section->mr);
}
static void *vfio_prereg_gpa_to_vaddr(MemoryRegionSection *section, hwaddr gpa)
diff --git a/include/exec/memory.h b/include/exec/memory.h
index 3e4d416..4d2aa63 100644
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -188,7 +188,7 @@ struct MemoryRegion {
void (*destructor)(MemoryRegion *mr);
uint64_t align;
bool terminates;
- bool skip_dump;
+ bool ram_device;
bool enabled;
bool warning_printed; /* For reservations */
uint8_t vga_logging_count;
@@ -426,6 +426,30 @@ void memory_region_init_ram_ptr(MemoryRegion *mr,
void *ptr);
/**
+ * memory_region_init_ram_device_ptr: Initialize RAM device memory region from
+ * a user-provided pointer.
+ *
+ * A RAM device represents a mapping to a physical device, such as to a PCI
+ * MMIO BAR of an vfio-pci assigned device. The memory region may be mapped
+ * into the VM address space and access to the region will modify memory
+ * directly. However, the memory region should not be included in a memory
+ * dump (device may not be enabled/mapped at the time of the dump), and
+ * operations incompatible with manipulating MMIO should be avoided. Replaces
+ * skip_dump flag.
+ *
+ * @mr: the #MemoryRegion to be initialized.
+ * @owner: the object that tracks the region's reference count
+ * @name: the name of the region.
+ * @size: size of the region.
+ * @ptr: memory to be mapped; must contain at least @size bytes.
+ */
+void memory_region_init_ram_device_ptr(MemoryRegion *mr,
+ struct Object *owner,
+ const char *name,
+ uint64_t size,
+ void *ptr);
+
+/**
* memory_region_init_alias: Initialize a memory region that aliases all or a
* part of another memory region.
*
@@ -551,22 +575,13 @@ static inline bool memory_region_is_ram(MemoryRegion *mr)
}
/**
- * memory_region_is_skip_dump: check whether a memory region should not be
- * dumped
- *
- * Returns %true is a memory region should not be dumped(e.g. VFIO BAR MMAP).
+ * memory_region_is_ram_device: check whether a memory region is a ram device
*
- * @mr: the memory region being queried
- */
-bool memory_region_is_skip_dump(MemoryRegion *mr);
-
-/**
- * memory_region_set_skip_dump: Set skip_dump flag, dump will ignore this memory
- * region
+ * Returns %true is a memory region is a device backed ram region
*
* @mr: the memory region being queried
*/
-void memory_region_set_skip_dump(MemoryRegion *mr);
+bool memory_region_is_ram_device(MemoryRegion *mr);
/**
* memory_region_is_romd: check whether a memory region is in ROMD mode
diff --git a/memory.c b/memory.c
index 0eb6895..94c55ae 100644
--- a/memory.c
+++ b/memory.c
@@ -1359,9 +1359,14 @@ void memory_region_init_ram_ptr(MemoryRegion *mr,
mr->ram_block = qemu_ram_alloc_from_ptr(size, ptr, mr, &error_fatal);
}
-void memory_region_set_skip_dump(MemoryRegion *mr)
+void memory_region_init_ram_device_ptr(MemoryRegion *mr,
+ Object *owner,
+ const char *name,
+ uint64_t size,
+ void *ptr)
{
- mr->skip_dump = true;
+ memory_region_init_ram_ptr(mr, owner, name, size, ptr);
+ mr->ram_device = true;
}
void memory_region_init_alias(MemoryRegion *mr,
@@ -1494,9 +1499,9 @@ const char *memory_region_name(const MemoryRegion *mr)
return mr->name;
}
-bool memory_region_is_skip_dump(MemoryRegion *mr)
+bool memory_region_is_ram_device(MemoryRegion *mr)
{
- return mr->skip_dump;
+ return mr->ram_device;
}
uint8_t memory_region_get_dirty_log_mask(MemoryRegion *mr)
diff --git a/memory_mapping.c b/memory_mapping.c
index e3e0d95..6a39d71 100644
--- a/memory_mapping.c
+++ b/memory_mapping.c
@@ -206,7 +206,7 @@ static void guest_phys_blocks_region_add(MemoryListener *listener,
/* we only care about RAM */
if (!memory_region_is_ram(section->mr) ||
- memory_region_is_skip_dump(section->mr)) {
+ memory_region_is_ram_device(section->mr)) {
return;
}
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 41/67] memory: Don't use memcpy for ram_device regions
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (39 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 40/67] memory: Replace skip_dump flag with "ram_device" Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 42/67] acpi/ipmi: Initialize the fwinfo before fetching it Michael Roth
` (26 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Alex Williamson
From: Alex Williamson <alex.williamson@redhat.com>
With a vfio assigned device we lay down a base MemoryRegion registered
as an IO region, giving us read & write accessors. If the region
supports mmap, we lay down a higher priority sub-region MemoryRegion
on top of the base layer initialized as a RAM device pointer to the
mmap. Finally, if we have any quirks for the device (ie. address
ranges that need additional virtualization support), we put another IO
sub-region on top of the mmap MemoryRegion. When this is flattened,
we now potentially have sub-page mmap MemoryRegions exposed which
cannot be directly mapped through KVM.
This is as expected, but a subtle detail of this is that we end up
with two different access mechanisms through QEMU. If we disable the
mmap MemoryRegion, we make use of the IO MemoryRegion and service
accesses using pread and pwrite to the vfio device file descriptor.
If the mmap MemoryRegion is enabled and results in one of these
sub-page gaps, QEMU handles the access as RAM, using memcpy to the
mmap. Using either pread/pwrite or the mmap directly should be
correct, but using memcpy causes us problems. I expect that not only
does memcpy not necessarily honor the original width and alignment in
performing a copy, but it potentially also uses processor instructions
not intended for MMIO spaces. It turns out that this has been a
problem for Realtek NIC assignment, which has such a quirk that
creates a sub-page mmap MemoryRegion access.
To resolve this, we disable memory_access_is_direct() for ram_device
regions since QEMU assumes that it can use memcpy for those regions.
Instead we access through MemoryRegionOps, which replaces the memcpy
with simple de-references of standard sizes to the host memory.
With this patch we attempt to provide unrestricted access to the RAM
device, allowing byte through qword access as well as unaligned
access. The assumption here is that accesses initiated by the VM are
driven by a device specific driver, which knows the device
capabilities. If unaligned accesses are not supported by the device,
we don't want them to work in a VM by performing multiple aligned
accesses to compose the unaligned access. A down-side of this
philosophy is that the xp command from the monitor attempts to use
the largest available access weidth, unaware of the underlying
device. Using memcpy had this same restriction, but at least now an
operator can dump individual registers, even if blocks of device
memory may result in access widths beyond the capabilities of a
given device (RTL NICs only support up to dword).
Reported-by: Thorsten Kohfeldt <thorsten.kohfeldt@gmx.de>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 4a2e242bbb306ef5c16ce9e7bb2da3bd8a4eb098)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
include/exec/memory.h | 6 +++--
memory.c | 67 +++++++++++++++++++++++++++++++++++++++++++++++++++
trace-events | 2 ++
3 files changed, 73 insertions(+), 2 deletions(-)
diff --git a/include/exec/memory.h b/include/exec/memory.h
index 4d2aa63..10ec0a2 100644
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -1446,9 +1446,11 @@ void *qemu_map_ram_ptr(RAMBlock *ram_block, ram_addr_t addr);
static inline bool memory_access_is_direct(MemoryRegion *mr, bool is_write)
{
if (is_write) {
- return memory_region_is_ram(mr) && !mr->readonly;
+ return memory_region_is_ram(mr) &&
+ !mr->readonly && !memory_region_is_ram_device(mr);
} else {
- return memory_region_is_ram(mr) || memory_region_is_romd(mr);
+ return (memory_region_is_ram(mr) && !memory_region_is_ram_device(mr)) ||
+ memory_region_is_romd(mr);
}
}
diff --git a/memory.c b/memory.c
index 94c55ae..e44aea9 100644
--- a/memory.c
+++ b/memory.c
@@ -1132,6 +1132,71 @@ const MemoryRegionOps unassigned_mem_ops = {
.endianness = DEVICE_NATIVE_ENDIAN,
};
+static uint64_t memory_region_ram_device_read(void *opaque,
+ hwaddr addr, unsigned size)
+{
+ MemoryRegion *mr = opaque;
+ uint64_t data = (uint64_t)~0;
+
+ switch (size) {
+ case 1:
+ data = *(uint8_t *)(mr->ram_block->host + addr);
+ break;
+ case 2:
+ data = *(uint16_t *)(mr->ram_block->host + addr);
+ break;
+ case 4:
+ data = *(uint32_t *)(mr->ram_block->host + addr);
+ break;
+ case 8:
+ data = *(uint64_t *)(mr->ram_block->host + addr);
+ break;
+ }
+
+ trace_memory_region_ram_device_read(get_cpu_index(), mr, addr, data, size);
+
+ return data;
+}
+
+static void memory_region_ram_device_write(void *opaque, hwaddr addr,
+ uint64_t data, unsigned size)
+{
+ MemoryRegion *mr = opaque;
+
+ trace_memory_region_ram_device_write(get_cpu_index(), mr, addr, data, size);
+
+ switch (size) {
+ case 1:
+ *(uint8_t *)(mr->ram_block->host + addr) = (uint8_t)data;
+ break;
+ case 2:
+ *(uint16_t *)(mr->ram_block->host + addr) = (uint16_t)data;
+ break;
+ case 4:
+ *(uint32_t *)(mr->ram_block->host + addr) = (uint32_t)data;
+ break;
+ case 8:
+ *(uint64_t *)(mr->ram_block->host + addr) = data;
+ break;
+ }
+}
+
+static const MemoryRegionOps ram_device_mem_ops = {
+ .read = memory_region_ram_device_read,
+ .write = memory_region_ram_device_write,
+ .endianness = DEVICE_NATIVE_ENDIAN,
+ .valid = {
+ .min_access_size = 1,
+ .max_access_size = 8,
+ .unaligned = true,
+ },
+ .impl = {
+ .min_access_size = 1,
+ .max_access_size = 8,
+ .unaligned = true,
+ },
+};
+
bool memory_region_access_valid(MemoryRegion *mr,
hwaddr addr,
unsigned size,
@@ -1367,6 +1432,8 @@ void memory_region_init_ram_device_ptr(MemoryRegion *mr,
{
memory_region_init_ram_ptr(mr, owner, name, size, ptr);
mr->ram_device = true;
+ mr->ops = &ram_device_mem_ops;
+ mr->opaque = mr;
}
void memory_region_init_alias(MemoryRegion *mr,
diff --git a/trace-events b/trace-events
index 616cc52..3b4c2f5 100644
--- a/trace-events
+++ b/trace-events
@@ -139,6 +139,8 @@ memory_region_subpage_read(int cpu_index, void *mr, uint64_t offset, uint64_t va
memory_region_subpage_write(int cpu_index, void *mr, uint64_t offset, uint64_t value, unsigned size) "cpu %d mr %p offset %#"PRIx64" value %#"PRIx64" size %u"
memory_region_tb_read(int cpu_index, uint64_t addr, uint64_t value, unsigned size) "cpu %d addr %#"PRIx64" value %#"PRIx64" size %u"
memory_region_tb_write(int cpu_index, uint64_t addr, uint64_t value, unsigned size) "cpu %d addr %#"PRIx64" value %#"PRIx64" size %u"
+memory_region_ram_device_read(int cpu_index, void *mr, uint64_t addr, uint64_t value, unsigned size) "cpu %d mr %p addr %#"PRIx64" value %#"PRIx64" size %u"
+memory_region_ram_device_write(int cpu_index, void *mr, uint64_t addr, uint64_t value, unsigned size) "cpu %d mr %p addr %#"PRIx64" value %#"PRIx64" size %u"
### Guest events, keep at bottom
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 42/67] acpi/ipmi: Initialize the fwinfo before fetching it
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (40 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 41/67] memory: Don't use memcpy for ram_device regions Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 43/67] net: fix sending of data with -net socket, listen backend Michael Roth
` (25 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Corey Minyard, Michael S. Tsirkin
From: Corey Minyard <cminyard@mvista.com>
The initialization was missed before, resulting in some
bad data in the smbus case.
Signed-off-by: Corey Minyard <cminyard@mvista.com>
Cc: qemu-stable@nongnu.org
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit 698ae42b9124dce23e03d0fea2e635b70540ef13)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/acpi/ipmi.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/hw/acpi/ipmi.c b/hw/acpi/ipmi.c
index 7e74ce4..651e2e9 100644
--- a/hw/acpi/ipmi.c
+++ b/hw/acpi/ipmi.c
@@ -99,6 +99,7 @@ void build_acpi_ipmi_devices(Aml *scope, BusState *bus)
ii = IPMI_INTERFACE(obj);
iic = IPMI_INTERFACE_GET_CLASS(obj);
+ memset(&info, 0, sizeof(info));
iic->get_fwinfo(ii, &info);
aml_append(scope, aml_ipmi_device(&info));
}
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 43/67] net: fix sending of data with -net socket, listen backend
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (41 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 42/67] acpi/ipmi: Initialize the fwinfo before fetching it Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 44/67] target-ppc: Fix CPU migration from qemu-2.6 <-> later versions Michael Roth
` (24 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Daniel P. Berrange, Jason Wang
From: "Daniel P. Berrange" <berrange@redhat.com>
The use of -net socket,listen was broken in the following
commit
commit 16a3df403b10c4ac347159e39005fd520b2648bb
Author: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
Date: Fri May 13 15:35:19 2016 +0800
net/net: Add SocketReadState for reuse codes
This function is from net/socket.c, move it to net.c and net.h.
Add SocketReadState to make others reuse net_fill_rstate().
suggestion from jason.
This refactored the state out of NetSocketState into a
separate SocketReadState. This refactoring requires
that a callback is provided to be triggered upon
completion of a packet receive from the guest.
The patch only registered this callback in the codepaths
hit by -net socket,connect, not -net socket,listen. So
as a result packets sent by the guest in the latter case
get dropped on the floor.
This bug is hidden because net_fill_rstate() silently
does nothing if the callback is not set.
This patch adds in the middle callback registration
and also adds an assert so that QEMU aborts if there
are any other codepaths hit which are missing the
callback.
Signed-off-by: Daniel P. Berrange <berrange@redhat.com>
Reviewed-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
(cherry picked from commit e79cd4068063ea2859199002a049010a11202939)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
net/net.c | 5 ++---
net/socket.c | 1 +
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/net/net.c b/net/net.c
index d51cb29..19b4d9e 100644
--- a/net/net.c
+++ b/net/net.c
@@ -1648,9 +1648,8 @@ int net_fill_rstate(SocketReadState *rs, const uint8_t *buf, int size)
if (rs->index >= rs->packet_len) {
rs->index = 0;
rs->state = 0;
- if (rs->finalize) {
- rs->finalize(rs);
- }
+ assert(rs->finalize);
+ rs->finalize(rs);
}
break;
}
diff --git a/net/socket.c b/net/socket.c
index 3f98eef..dcae1ae 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -522,6 +522,7 @@ static int net_socket_listen_init(NetClientState *peer,
s->fd = -1;
s->listen_fd = fd;
s->nc.link_down = true;
+ net_socket_rs_init(&s->rs, net_socket_rs_finalize);
qemu_set_fd_handler(s->listen_fd, net_socket_accept, NULL, s);
return 0;
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 44/67] target-ppc: Fix CPU migration from qemu-2.6 <-> later versions
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (42 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 43/67] net: fix sending of data with -net socket, listen backend Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 45/67] virtio: allow per-device-class legacy features Michael Roth
` (23 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, David Gibson
From: David Gibson <david@gibson.dropbear.id.au>
When migration for target-ppc was converted to vmstate, several
VMSTATE_EQUAL() checks were foolishly included of things that really
should be internal state. Specifically we verified equality of the
insns_flags and insns_flags2 fields, which are used within TCG to
determine which groups of instructions are available on this cpu
model. Between qemu-2.6 and qemu-2.7 we made some changes to these
classes which broke migration.
This path fixes migration both forwards and backwards. On migration
from 2.6 to later versions we import the fields into teporary
variables, which we then ignore. In migration backwards, we populate
the temporary fields from the runtime fields, but mask out the bits
which were added after qemu-2.6, allowing the VMSTATE_EQUAL in
qemu-2.6 to accept the stream.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Greg Kurz <groug@kaod.org>
(cherry picked from commit 16a2497bd44cac1856e259654fd304079bd1dcdc)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
target-ppc/cpu.h | 6 ++++++
target-ppc/machine.c | 29 +++++++++++++++++++++++++----
2 files changed, 31 insertions(+), 4 deletions(-)
diff --git a/target-ppc/cpu.h b/target-ppc/cpu.h
index 786ab5c..d4d1509 100644
--- a/target-ppc/cpu.h
+++ b/target-ppc/cpu.h
@@ -1164,6 +1164,12 @@ struct PowerPCCPU {
int cpu_dt_id;
uint32_t max_compat;
uint32_t cpu_version;
+
+ /* fields used only during migration for compatibility hacks */
+ target_ulong mig_msr_mask;
+ uint64_t mig_insns_flags;
+ uint64_t mig_insns_flags2;
+ uint32_t mig_nb_BATs;
};
static inline PowerPCCPU *ppc_env_get_cpu(CPUPPCState *env)
diff --git a/target-ppc/machine.c b/target-ppc/machine.c
index 4820f22..56a59e0 100644
--- a/target-ppc/machine.c
+++ b/target-ppc/machine.c
@@ -141,6 +141,21 @@ static void cpu_pre_save(void *opaque)
PowerPCCPU *cpu = opaque;
CPUPPCState *env = &cpu->env;
int i;
+ uint64_t insns_compat_mask =
+ PPC_INSNS_BASE | PPC_ISEL | PPC_STRING | PPC_MFTB
+ | PPC_FLOAT | PPC_FLOAT_FSEL | PPC_FLOAT_FRES
+ | PPC_FLOAT_FSQRT | PPC_FLOAT_FRSQRTE | PPC_FLOAT_FRSQRTES
+ | PPC_FLOAT_STFIWX | PPC_FLOAT_EXT
+ | PPC_CACHE | PPC_CACHE_ICBI | PPC_CACHE_DCBZ
+ | PPC_MEM_SYNC | PPC_MEM_EIEIO | PPC_MEM_TLBIE | PPC_MEM_TLBSYNC
+ | PPC_64B | PPC_64BX | PPC_ALTIVEC
+ | PPC_SEGMENT_64B | PPC_SLBI | PPC_POPCNTB | PPC_POPCNTWD;
+ uint64_t insns_compat_mask2 = PPC2_VSX | PPC2_VSX207 | PPC2_DFP | PPC2_DBRX
+ | PPC2_PERM_ISA206 | PPC2_DIVE_ISA206
+ | PPC2_ATOMIC_ISA206 | PPC2_FP_CVT_ISA206
+ | PPC2_FP_TST_ISA206 | PPC2_BCTAR_ISA207
+ | PPC2_LSQ_ISA207 | PPC2_ALTIVEC_207
+ | PPC2_ISA205 | PPC2_ISA207S | PPC2_FP_CVT_S64 | PPC2_TM;
env->spr[SPR_LR] = env->lr;
env->spr[SPR_CTR] = env->ctr;
@@ -162,6 +177,12 @@ static void cpu_pre_save(void *opaque)
env->spr[SPR_IBAT4U + 2*i] = env->IBAT[0][i+4];
env->spr[SPR_IBAT4U + 2*i + 1] = env->IBAT[1][i+4];
}
+
+ /* Hacks for migration compatibility between 2.6, 2.7 & 2.8 */
+ cpu->mig_msr_mask = env->msr_mask;
+ cpu->mig_insns_flags = env->insns_flags & insns_compat_mask;
+ cpu->mig_insns_flags2 = env->insns_flags2 & insns_compat_mask2;
+ cpu->mig_nb_BATs = env->nb_BATs;
}
static int cpu_post_load(void *opaque, int version_id)
@@ -562,10 +583,10 @@ const VMStateDescription vmstate_ppc_cpu = {
/* FIXME: access_type? */
/* Sanity checking */
- VMSTATE_UINTTL_EQUAL(env.msr_mask, PowerPCCPU),
- VMSTATE_UINT64_EQUAL(env.insns_flags, PowerPCCPU),
- VMSTATE_UINT64_EQUAL(env.insns_flags2, PowerPCCPU),
- VMSTATE_UINT32_EQUAL(env.nb_BATs, PowerPCCPU),
+ VMSTATE_UINTTL(mig_msr_mask, PowerPCCPU),
+ VMSTATE_UINT64(mig_insns_flags, PowerPCCPU),
+ VMSTATE_UINT64(mig_insns_flags2, PowerPCCPU),
+ VMSTATE_UINT32(mig_nb_BATs, PowerPCCPU),
VMSTATE_END_OF_LIST()
},
.subsections = (const VMStateDescription*[]) {
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 45/67] virtio: allow per-device-class legacy features
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (43 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 44/67] target-ppc: Fix CPU migration from qemu-2.6 <-> later versions Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 46/67] virtio-net: mark VIRTIO_NET_F_GSO as legacy Michael Roth
` (22 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Michael S. Tsirkin
From: "Michael S. Tsirkin" <mst@redhat.com>
Legacy features are those that transitional devices only
expose on the legacy interface.
Allow different ones per device class.
Cc: qemu-stable@nongnu.org # dependency for the next patch
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
(cherry picked from commit 9b706dbbbb81f5cb7c67e491d38cd6077205e056)
Conflicts:
hw/virtio/virtio.c
* drop context dep on ff4c07df
* resolv func dep on ff4c07df creating vdc variable in
virtio_device_class_init()
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/s390x/virtio-ccw.c | 4 +++-
hw/virtio/virtio-pci.c | 4 +++-
hw/virtio/virtio.c | 3 +++
include/hw/virtio/virtio.h | 5 +++++
4 files changed, 14 insertions(+), 2 deletions(-)
diff --git a/hw/s390x/virtio-ccw.c b/hw/s390x/virtio-ccw.c
index a554a24..f6f5e79 100644
--- a/hw/s390x/virtio-ccw.c
+++ b/hw/s390x/virtio-ccw.c
@@ -330,6 +330,8 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw)
if (!ccw.cda) {
ret = -EFAULT;
} else {
+ VirtioDeviceClass *vdc = VIRTIO_DEVICE_GET_CLASS(vdev);
+
features.index = address_space_ldub(&address_space_memory,
ccw.cda
+ sizeof(features.features),
@@ -339,7 +341,7 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw)
if (dev->revision >= 1) {
/* Don't offer legacy features for modern devices. */
features.features = (uint32_t)
- (vdev->host_features & ~VIRTIO_LEGACY_FEATURES);
+ (vdev->host_features & ~vdc->legacy_features);
} else {
features.features = (uint32_t)vdev->host_features;
}
diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index 755f921..46711a2 100644
--- a/hw/virtio/virtio-pci.c
+++ b/hw/virtio/virtio-pci.c
@@ -1192,7 +1192,9 @@ static uint64_t virtio_pci_common_read(void *opaque, hwaddr addr,
break;
case VIRTIO_PCI_COMMON_DF:
if (proxy->dfselect <= 1) {
- val = (vdev->host_features & ~VIRTIO_LEGACY_FEATURES) >>
+ VirtioDeviceClass *vdc = VIRTIO_DEVICE_GET_CLASS(vdev);
+
+ val = (vdev->host_features & ~vdc->legacy_features) >>
(32 * proxy->dfselect);
}
break;
diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c
index e8a13a5..f31140a 100644
--- a/hw/virtio/virtio.c
+++ b/hw/virtio/virtio.c
@@ -1966,12 +1966,15 @@ static Property virtio_properties[] = {
static void virtio_device_class_init(ObjectClass *klass, void *data)
{
/* Set the default value here. */
+ VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
DeviceClass *dc = DEVICE_CLASS(klass);
dc->realize = virtio_device_realize;
dc->unrealize = virtio_device_unrealize;
dc->bus_type = TYPE_VIRTIO_BUS;
dc->props = virtio_properties;
+
+ vdc->legacy_features |= VIRTIO_LEGACY_FEATURES;
}
static const TypeInfo virtio_device_info = {
diff --git a/include/hw/virtio/virtio.h b/include/hw/virtio/virtio.h
index d2490c1..d51341d 100644
--- a/include/hw/virtio/virtio.h
+++ b/include/hw/virtio/virtio.h
@@ -112,6 +112,11 @@ typedef struct VirtioDeviceClass {
void (*set_config)(VirtIODevice *vdev, const uint8_t *config);
void (*reset)(VirtIODevice *vdev);
void (*set_status)(VirtIODevice *vdev, uint8_t val);
+ /* For transitional devices, this is a bitmap of features
+ * that are only exposed on the legacy interface but not
+ * the modern one.
+ */
+ uint64_t legacy_features;
/* Test and clear event pending status.
* Should be called after unmask to avoid losing events.
* If backend does not support masking,
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 46/67] virtio-net: mark VIRTIO_NET_F_GSO as legacy
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (44 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 45/67] virtio: allow per-device-class legacy features Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 47/67] block: Don't mark node clean after failed flush Michael Roth
` (21 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Michael S. Tsirkin
From: "Michael S. Tsirkin" <mst@redhat.com>
virtio 1.0 spec says this is a legacy feature bit,
hide it from guests in modern mode.
Note: for cross-version migration compatibility,
we keep the bit set in host_features.
The result will be that a guest migrating cross-version
will see host features change under it.
As guests only seem to read it once, this should
not be an issue. Meanwhile, will work to fix guests to
ignore this bit in virtio1 mode, too.
Cc: qemu-stable@nongnu.org
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
(cherry picked from commit 2a083ffd2e37ef08769749a5c7cfc6ca65c9f8ea)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/net/virtio-net.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 01f1351..abc48d8 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -1904,6 +1904,7 @@ static void virtio_net_class_init(ObjectClass *klass, void *data)
vdc->guest_notifier_pending = virtio_net_guest_notifier_pending;
vdc->load = virtio_net_load_device;
vdc->save = virtio_net_save_device;
+ vdc->legacy_features |= (0x1 << VIRTIO_NET_F_GSO);
}
static const TypeInfo virtio_net_info = {
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 47/67] block: Don't mark node clean after failed flush
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (45 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 46/67] virtio-net: mark VIRTIO_NET_F_GSO as legacy Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 48/67] vhost: adapt vhost_verify_ring_mappings() to virtio 1 ring layout Michael Roth
` (20 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Kevin Wolf, Stefan Hajnoczi
From: Kevin Wolf <kwolf@redhat.com>
Commit 3ff2f67a changed bdrv_co_flush() so that no flush is issues if
the image hasn't been dirtied since the last flush. This is not quite
correct: The condition should be that the image hasn't been dirtied
since the last _successful_ flush. This patch changes the logic
accordingly.
Without this fix, subsequent bdrv_co_flush() calls would return success
without actually doing anything even though the image is still dirty.
The difference is visible in some blkdebug test cases where error
messages incorrectly disappeared after commit 3ff2f67a.
Cc: qemu-stable@nongnu.org
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Denis V. Lunev <den@openvz.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: John Snow <jsnow@redhat.com>
Message-id: 1478300595-10090-1-git-send-email-kwolf@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit e6af1e085416378918cca357bf2abd8b90224667)
Conflicts:
block/io.c
* remove context dep on 9972354
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
block/io.c | 4 +++-
tests/qemu-iotests/026.out | 22 ++++++++++++++++++++++
tests/qemu-iotests/026.out.nocache | 22 ++++++++++++++++++++++
tests/qemu-iotests/071.out | 2 ++
4 files changed, 49 insertions(+), 1 deletion(-)
diff --git a/block/io.c b/block/io.c
index 487755a..e579eda 100644
--- a/block/io.c
+++ b/block/io.c
@@ -2381,7 +2381,9 @@ flush_parent:
ret = bs->file ? bdrv_co_flush(bs->file->bs) : 0;
out:
/* Notify any pending flushes that we have completed */
- bs->flushed_gen = current_gen;
+ if (ret == 0) {
+ bs->flushed_gen = current_gen;
+ }
bs->active_flush_req = NULL;
/* Return value is ignored - it's ok if wait queue is empty */
qemu_co_queue_next(&bs->flush_queue);
diff --git a/tests/qemu-iotests/026.out b/tests/qemu-iotests/026.out
index 8531735..59b8f74 100644
--- a/tests/qemu-iotests/026.out
+++ b/tests/qemu-iotests/026.out
@@ -14,6 +14,7 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: l1_update; errno: 5; imm: off; once: off; write
+Failed to flush the L2 table cache: Input/output error
Failed to flush the refcount block cache: Input/output error
write failed: Input/output error
@@ -22,6 +23,7 @@ This means waste of disk space, but no harm to data.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: l1_update; errno: 5; imm: off; once: off; write -b
+Failed to flush the L2 table cache: Input/output error
Failed to flush the refcount block cache: Input/output error
write failed: Input/output error
@@ -40,6 +42,7 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: l1_update; errno: 28; imm: off; once: off; write
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
@@ -48,6 +51,7 @@ This means waste of disk space, but no harm to data.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: l1_update; errno: 28; imm: off; once: off; write -b
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
@@ -286,12 +290,14 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_load; errno: 5; imm: off; once: off; write
+Failed to flush the L2 table cache: Input/output error
Failed to flush the refcount block cache: Input/output error
write failed: Input/output error
No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_load; errno: 5; imm: off; once: off; write -b
+Failed to flush the L2 table cache: Input/output error
Failed to flush the refcount block cache: Input/output error
write failed: Input/output error
No errors were found on the image.
@@ -308,12 +314,14 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_load; errno: 28; imm: off; once: off; write
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_load; errno: 28; imm: off; once: off; write -b
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
No errors were found on the image.
@@ -330,12 +338,14 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_update_part; errno: 5; imm: off; once: off; write
+Failed to flush the L2 table cache: Input/output error
Failed to flush the refcount block cache: Input/output error
write failed: Input/output error
No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_update_part; errno: 5; imm: off; once: off; write -b
+Failed to flush the L2 table cache: Input/output error
Failed to flush the refcount block cache: Input/output error
write failed: Input/output error
No errors were found on the image.
@@ -352,12 +362,14 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_update_part; errno: 28; imm: off; once: off; write
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_update_part; errno: 28; imm: off; once: off; write -b
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
No errors were found on the image.
@@ -374,12 +386,14 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_alloc; errno: 5; imm: off; once: off; write
+Failed to flush the L2 table cache: Input/output error
Failed to flush the refcount block cache: Input/output error
write failed: Input/output error
No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_alloc; errno: 5; imm: off; once: off; write -b
+Failed to flush the L2 table cache: Input/output error
Failed to flush the refcount block cache: Input/output error
write failed: Input/output error
No errors were found on the image.
@@ -396,12 +410,14 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_alloc; errno: 28; imm: off; once: off; write
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_alloc; errno: 28; imm: off; once: off; write -b
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
No errors were found on the image.
@@ -513,6 +529,7 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_alloc_write_blocks; errno: 28; imm: off; once: off; write
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
@@ -521,6 +538,7 @@ This means waste of disk space, but no harm to data.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_alloc_write_blocks; errno: 28; imm: off; once: off; write -b
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
@@ -539,6 +557,7 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_alloc_write_table; errno: 28; imm: off; once: off; write
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
@@ -547,6 +566,7 @@ This means waste of disk space, but no harm to data.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_alloc_write_table; errno: 28; imm: off; once: off; write -b
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
@@ -611,6 +631,7 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: l1_grow_write_table; errno: 5; imm: off; once: off
+Failed to flush the L2 table cache: Input/output error
Failed to flush the refcount block cache: Input/output error
write failed: Input/output error
No errors were found on the image.
@@ -622,6 +643,7 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: l1_grow_write_table; errno: 28; imm: off; once: off
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
No errors were found on the image.
diff --git a/tests/qemu-iotests/026.out.nocache b/tests/qemu-iotests/026.out.nocache
index 672d77c..b4aeebc 100644
--- a/tests/qemu-iotests/026.out.nocache
+++ b/tests/qemu-iotests/026.out.nocache
@@ -14,6 +14,7 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: l1_update; errno: 5; imm: off; once: off; write
+Failed to flush the L2 table cache: Input/output error
Failed to flush the refcount block cache: Input/output error
write failed: Input/output error
@@ -22,6 +23,7 @@ This means waste of disk space, but no harm to data.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: l1_update; errno: 5; imm: off; once: off; write -b
+Failed to flush the L2 table cache: Input/output error
Failed to flush the refcount block cache: Input/output error
write failed: Input/output error
@@ -40,6 +42,7 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: l1_update; errno: 28; imm: off; once: off; write
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
@@ -48,6 +51,7 @@ This means waste of disk space, but no harm to data.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: l1_update; errno: 28; imm: off; once: off; write -b
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
@@ -294,12 +298,14 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_load; errno: 5; imm: off; once: off; write
+Failed to flush the L2 table cache: Input/output error
Failed to flush the refcount block cache: Input/output error
write failed: Input/output error
No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_load; errno: 5; imm: off; once: off; write -b
+Failed to flush the L2 table cache: Input/output error
Failed to flush the refcount block cache: Input/output error
write failed: Input/output error
No errors were found on the image.
@@ -316,12 +322,14 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_load; errno: 28; imm: off; once: off; write
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_load; errno: 28; imm: off; once: off; write -b
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
No errors were found on the image.
@@ -338,12 +346,14 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_update_part; errno: 5; imm: off; once: off; write
+Failed to flush the L2 table cache: Input/output error
Failed to flush the refcount block cache: Input/output error
write failed: Input/output error
No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_update_part; errno: 5; imm: off; once: off; write -b
+Failed to flush the L2 table cache: Input/output error
Failed to flush the refcount block cache: Input/output error
write failed: Input/output error
No errors were found on the image.
@@ -360,12 +370,14 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_update_part; errno: 28; imm: off; once: off; write
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_update_part; errno: 28; imm: off; once: off; write -b
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
No errors were found on the image.
@@ -382,12 +394,14 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_alloc; errno: 5; imm: off; once: off; write
+Failed to flush the L2 table cache: Input/output error
Failed to flush the refcount block cache: Input/output error
write failed: Input/output error
No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_alloc; errno: 5; imm: off; once: off; write -b
+Failed to flush the L2 table cache: Input/output error
Failed to flush the refcount block cache: Input/output error
write failed: Input/output error
No errors were found on the image.
@@ -404,12 +418,14 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_alloc; errno: 28; imm: off; once: off; write
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_alloc; errno: 28; imm: off; once: off; write -b
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
No errors were found on the image.
@@ -521,6 +537,7 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_alloc_write_blocks; errno: 28; imm: off; once: off; write
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
@@ -529,6 +546,7 @@ This means waste of disk space, but no harm to data.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_alloc_write_blocks; errno: 28; imm: off; once: off; write -b
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
@@ -547,6 +565,7 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_alloc_write_table; errno: 28; imm: off; once: off; write
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
@@ -555,6 +574,7 @@ This means waste of disk space, but no harm to data.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: refblock_alloc_write_table; errno: 28; imm: off; once: off; write -b
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
@@ -619,6 +639,7 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: l1_grow_write_table; errno: 5; imm: off; once: off
+Failed to flush the L2 table cache: Input/output error
Failed to flush the refcount block cache: Input/output error
write failed: Input/output error
No errors were found on the image.
@@ -630,6 +651,7 @@ No errors were found on the image.
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
Event: l1_grow_write_table; errno: 28; imm: off; once: off
+Failed to flush the L2 table cache: No space left on device
Failed to flush the refcount block cache: No space left on device
write failed: No space left on device
No errors were found on the image.
diff --git a/tests/qemu-iotests/071.out b/tests/qemu-iotests/071.out
index 8c6851e..8ff423f 100644
--- a/tests/qemu-iotests/071.out
+++ b/tests/qemu-iotests/071.out
@@ -86,5 +86,7 @@ read failed: Input/output error
{"return": ""}
{"return": {}}
{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN"}
+QEMU_PROG: Failed to flush the L2 table cache: Input/output error
+QEMU_PROG: Failed to flush the refcount block cache: Input/output error
*** done
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 48/67] vhost: adapt vhost_verify_ring_mappings() to virtio 1 ring layout
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (46 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 47/67] block: Don't mark node clean after failed flush Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 49/67] slirp: Fix access to freed memory Michael Roth
` (19 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Greg Kurz, Michael S. Tsirkin
From: Greg Kurz <groug@kaod.org>
With virtio 1, the vring layout is split in 3 separate regions of
contiguous memory for the descriptor table, the available ring and the
used ring, as opposed with legacy virtio which uses a single region.
In case of memory re-mapping, the code ensures it doesn't affect the
vring mapping. This is done in vhost_verify_ring_mappings() which assumes
the device is legacy.
This patch changes vhost_verify_ring_mappings() to check the mappings of
each part of the vring separately.
This works for legacy mappings as well.
Cc: qemu-stable@nongnu.org
Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit f1f9e6c5961ffb36fd4a81cd7edcded7bfad2ab2)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/virtio/vhost.c | 79 +++++++++++++++++++++++++++++++++++------------
include/hw/virtio/vhost.h | 4 +++
2 files changed, 64 insertions(+), 19 deletions(-)
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index 3d0c807..b89f253 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -421,32 +421,73 @@ static inline void vhost_dev_log_resize(struct vhost_dev *dev, uint64_t size)
dev->log_size = size;
}
+
+static int vhost_verify_ring_part_mapping(void *part,
+ uint64_t part_addr,
+ uint64_t part_size,
+ uint64_t start_addr,
+ uint64_t size)
+{
+ hwaddr l;
+ void *p;
+ int r = 0;
+
+ if (!ranges_overlap(start_addr, size, part_addr, part_size)) {
+ return 0;
+ }
+ l = part_size;
+ p = cpu_physical_memory_map(part_addr, &l, 1);
+ if (!p || l != part_size) {
+ r = -ENOMEM;
+ }
+ if (p != part) {
+ r = -EBUSY;
+ }
+ cpu_physical_memory_unmap(p, l, 0, 0);
+ return r;
+}
+
static int vhost_verify_ring_mappings(struct vhost_dev *dev,
uint64_t start_addr,
uint64_t size)
{
- int i;
+ int i, j;
int r = 0;
+ const char *part_name[] = {
+ "descriptor table",
+ "available ring",
+ "used ring"
+ };
- for (i = 0; !r && i < dev->nvqs; ++i) {
+ for (i = 0; i < dev->nvqs; ++i) {
struct vhost_virtqueue *vq = dev->vqs + i;
- hwaddr l;
- void *p;
- if (!ranges_overlap(start_addr, size, vq->ring_phys, vq->ring_size)) {
- continue;
+ j = 0;
+ r = vhost_verify_ring_part_mapping(vq->desc, vq->desc_phys,
+ vq->desc_size, start_addr, size);
+ if (!r) {
+ break;
}
- l = vq->ring_size;
- p = cpu_physical_memory_map(vq->ring_phys, &l, 1);
- if (!p || l != vq->ring_size) {
- error_report("Unable to map ring buffer for ring %d", i);
- r = -ENOMEM;
+
+ j++;
+ r = vhost_verify_ring_part_mapping(vq->avail, vq->avail_phys,
+ vq->avail_size, start_addr, size);
+ if (!r) {
+ break;
}
- if (p != vq->ring) {
- error_report("Ring buffer relocated for ring %d", i);
- r = -EBUSY;
+
+ j++;
+ r = vhost_verify_ring_part_mapping(vq->used, vq->used_phys,
+ vq->used_size, start_addr, size);
+ if (!r) {
+ break;
}
- cpu_physical_memory_unmap(p, l, 0, 0);
+ }
+
+ if (r == -ENOMEM) {
+ error_report("Unable to map %s for ring %d", part_name[j], i);
+ } else if (r == -EBUSY) {
+ error_report("%s relocated for ring %d", part_name[j], i);
}
return r;
}
@@ -857,15 +898,15 @@ static int vhost_virtqueue_start(struct vhost_dev *dev,
}
}
- s = l = virtio_queue_get_desc_size(vdev, idx);
- a = virtio_queue_get_desc_addr(vdev, idx);
+ vq->desc_size = s = l = virtio_queue_get_desc_size(vdev, idx);
+ vq->desc_phys = a = virtio_queue_get_desc_addr(vdev, idx);
vq->desc = cpu_physical_memory_map(a, &l, 0);
if (!vq->desc || l != s) {
r = -ENOMEM;
goto fail_alloc_desc;
}
- s = l = virtio_queue_get_avail_size(vdev, idx);
- a = virtio_queue_get_avail_addr(vdev, idx);
+ vq->avail_size = s = l = virtio_queue_get_avail_size(vdev, idx);
+ vq->avail_phys = a = virtio_queue_get_avail_addr(vdev, idx);
vq->avail = cpu_physical_memory_map(a, &l, 0);
if (!vq->avail || l != s) {
r = -ENOMEM;
diff --git a/include/hw/virtio/vhost.h b/include/hw/virtio/vhost.h
index e433089..56b567f 100644
--- a/include/hw/virtio/vhost.h
+++ b/include/hw/virtio/vhost.h
@@ -14,6 +14,10 @@ struct vhost_virtqueue {
void *avail;
void *used;
int num;
+ unsigned long long desc_phys;
+ unsigned desc_size;
+ unsigned long long avail_phys;
+ unsigned avail_size;
unsigned long long used_phys;
unsigned used_size;
void *ring;
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 49/67] slirp: Fix access to freed memory
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (47 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 48/67] vhost: adapt vhost_verify_ring_mappings() to virtio 1 ring layout Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 50/67] qcow2: Inform block layer about discard boundaries Michael Roth
` (18 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Samuel Thibault
From: Samuel Thibault <samuel.thibault@ens-lyon.org>
if_start() goes through the slirp->if_fastq and slirp->if_batchq
list of pending messages, and accesses ifm->ifq_so->so_nqueued of its
elements if ifm->ifq_so != NULL. When freeing a socket, we thus need
to make sure that any pending message for this socket does not refer
to the socket any more.
Signed-off-by: Samuel Thibault <samuel.thibault@ens-lyon.org>
Tested-by: Brian Candler <b.candler@pobox.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit ea64d5f08817b5e79e17135dce516c7583107f91)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
slirp/socket.c | 17 +++++++++++++++++
1 file changed, 17 insertions(+)
diff --git a/slirp/socket.c b/slirp/socket.c
index 280050a..6c18971 100644
--- a/slirp/socket.c
+++ b/slirp/socket.c
@@ -66,6 +66,23 @@ void
sofree(struct socket *so)
{
Slirp *slirp = so->slirp;
+ struct mbuf *ifm;
+
+ for (ifm = (struct mbuf *) slirp->if_fastq.qh_link;
+ (struct quehead *) ifm != &slirp->if_fastq;
+ ifm = ifm->ifq_next) {
+ if (ifm->ifq_so == so) {
+ ifm->ifq_so = NULL;
+ }
+ }
+
+ for (ifm = (struct mbuf *) slirp->if_batchq.qh_link;
+ (struct quehead *) ifm != &slirp->if_batchq;
+ ifm = ifm->ifq_next) {
+ if (ifm->ifq_so == so) {
+ ifm->ifq_so = NULL;
+ }
+ }
if (so->so_emu==EMU_RSH && so->extra) {
sofree(so->extra);
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 50/67] qcow2: Inform block layer about discard boundaries
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (48 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 49/67] slirp: Fix access to freed memory Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 51/67] block: Let write zeroes fallback work even with small max_transfer Michael Roth
` (17 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Eric Blake, Kevin Wolf
From: Eric Blake <eblake@redhat.com>
At the qcow2 layer, discard is only possible on a per-cluster
basis; at the moment, qcow2 silently rounds any unaligned
requests to this granularity. However, an upcoming patch will
fix a regression in the block layer ignoring too much of an
unaligned discard request, by changing the block layer to
break up a discard request at alignment boundaries; for that
to work, the block layer must know about our limits.
However, we can't go one step further by changing
qcow2_discard_clusters() to assert that requests are always
aligned, since that helper function is reached on paths
outside of the block layer.
CC: qemu-stable@nongnu.org
Signed-off-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit ecdbead659f037dc572bba9eb1cd31a5a1a9ad9a)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
block/qcow2.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/block/qcow2.c b/block/qcow2.c
index 91ef4df..497df0f 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -1204,6 +1204,7 @@ static void qcow2_refresh_limits(BlockDriverState *bs, Error **errp)
bs->bl.request_alignment = BDRV_SECTOR_SIZE;
}
bs->bl.pwrite_zeroes_alignment = s->cluster_size;
+ bs->bl.pdiscard_alignment = s->cluster_size;
}
static int qcow2_set_key(BlockDriverState *bs, const char *key)
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 51/67] block: Let write zeroes fallback work even with small max_transfer
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (49 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 50/67] qcow2: Inform block layer about discard boundaries Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 52/67] block: Return -ENOTSUP rather than assert on unaligned discards Michael Roth
` (16 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Eric Blake, Denis V. Lunev, Kevin Wolf
From: Eric Blake <eblake@redhat.com>
Commit 443668ca rewrote the write_zeroes logic to guarantee that
an unaligned request never crosses a cluster boundary. But
in the rewrite, the new code assumed that at most one iteration
would be needed to get to an alignment boundary.
However, it is easy to trigger an assertion failure: the Linux
kernel limits loopback devices to advertise a max_transfer of
only 64k. Any operation that requires falling back to writes
rather than more efficient zeroing must obey max_transfer during
that fallback, which means an unaligned head may require multiple
iterations of the write fallbacks before reaching the aligned
boundaries, when layering a format with clusters larger than 64k
atop the protocol of file access to a loopback device.
Test case:
$ qemu-img create -f qcow2 -o cluster_size=1M file 10M
$ losetup /dev/loop2 /path/to/file
$ qemu-io -f qcow2 /dev/loop2
qemu-io> w 7m 1k
qemu-io> w -z 8003584 2093056
In fairness to Denis (as the original listed author of the culprit
commit), the faulty logic for at most one iteration is probably all
my fault in reworking his idea. But the solution is to restore what
was in place prior to that commit: when dealing with an unaligned
head or tail, iterate as many times as necessary while fragmenting
the operation at max_transfer boundaries.
Reported-by: Ed Swierk <eswierk@skyportsystems.com>
CC: qemu-stable@nongnu.org
CC: Denis V. Lunev <den@openvz.org>
Signed-off-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit b2f95feec5e4d546b932848dd421ec3361e8ef77)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
block/io.c | 13 ++++++++-----
1 file changed, 8 insertions(+), 5 deletions(-)
diff --git a/block/io.c b/block/io.c
index e579eda..959e140 100644
--- a/block/io.c
+++ b/block/io.c
@@ -1179,6 +1179,8 @@ static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs,
int max_write_zeroes = MIN_NON_ZERO(bs->bl.max_pwrite_zeroes, INT_MAX);
int alignment = MAX(bs->bl.pwrite_zeroes_alignment,
bs->bl.request_alignment);
+ int max_transfer = MIN_NON_ZERO(bs->bl.max_transfer,
+ MAX_WRITE_ZEROES_BOUNCE_BUFFER);
assert(alignment % bs->bl.request_alignment == 0);
head = offset % alignment;
@@ -1194,9 +1196,12 @@ static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs,
* boundaries.
*/
if (head) {
- /* Make a small request up to the first aligned sector. */
- num = MIN(count, alignment - head);
- head = 0;
+ /* Make a small request up to the first aligned sector. For
+ * convenience, limit this request to max_transfer even if
+ * we don't need to fall back to writes. */
+ num = MIN(MIN(count, max_transfer), alignment - head);
+ head = (head + num) % alignment;
+ assert(num < max_write_zeroes);
} else if (tail && num > alignment) {
/* Shorten the request to the last aligned sector. */
num -= tail;
@@ -1222,8 +1227,6 @@ static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs,
if (ret == -ENOTSUP) {
/* Fall back to bounce buffer if write zeroes is unsupported */
- int max_transfer = MIN_NON_ZERO(bs->bl.max_transfer,
- MAX_WRITE_ZEROES_BOUNCE_BUFFER);
BdrvRequestFlags write_flags = flags & ~BDRV_REQ_ZERO_WRITE;
if ((flags & BDRV_REQ_FUA) &&
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 52/67] block: Return -ENOTSUP rather than assert on unaligned discards
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (50 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 51/67] block: Let write zeroes fallback work even with small max_transfer Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 53/67] block: Pass unaligned discard requests to drivers Michael Roth
` (15 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Eric Blake, Kevin Wolf
From: Eric Blake <eblake@redhat.com>
Right now, the block layer rounds discard requests, so that
individual drivers are able to assert that discard requests
will never be unaligned. But there are some ISCSI devices
that track and coalesce multiple unaligned requests, turning it
into an actual discard if the requests eventually cover an
entire page, which implies that it is better to always pass
discard requests as low down the stack as possible.
In isolation, this patch has no semantic effect, since the
block layer currently never passes an unaligned request through.
But the block layer already has code that silently ignores
drivers that return -ENOTSUP for a discard request that cannot
be honored (as well as drivers that return 0 even when nothing
was done). But the next patch will update the block layer to
fragment discard requests, so that clients are guaranteed that
they are either dealing with an unaligned head or tail, or an
aligned core, making it similar to the block layer semantics of
write zero fragmentation.
CC: qemu-stable@nongnu.org
Signed-off-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 49228d1e95e1be879c57f5dbccb44405670e343d)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
block/iscsi.c | 4 +++-
block/qcow2.c | 5 +++++
block/sheepdog.c | 5 +++--
3 files changed, 11 insertions(+), 3 deletions(-)
diff --git a/block/iscsi.c b/block/iscsi.c
index b2b4e5d..8bc5f7e 100644
--- a/block/iscsi.c
+++ b/block/iscsi.c
@@ -1048,7 +1048,9 @@ coroutine_fn iscsi_co_pdiscard(BlockDriverState *bs, int64_t offset, int count)
struct IscsiTask iTask;
struct unmap_list list;
- assert(is_byte_request_lun_aligned(offset, count, iscsilun));
+ if (!is_byte_request_lun_aligned(offset, count, iscsilun)) {
+ return -ENOTSUP;
+ }
if (!iscsilun->lbp.lbpu) {
/* UNMAP is not supported by the target */
diff --git a/block/qcow2.c b/block/qcow2.c
index 497df0f..3a80be0 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -2486,6 +2486,11 @@ static coroutine_fn int qcow2_co_pdiscard(BlockDriverState *bs,
int ret;
BDRVQcow2State *s = bs->opaque;
+ if (!QEMU_IS_ALIGNED(offset | count, s->cluster_size)) {
+ assert(count < s->cluster_size);
+ return -ENOTSUP;
+ }
+
qemu_co_mutex_lock(&s->lock);
ret = qcow2_discard_clusters(bs, offset, count >> BDRV_SECTOR_BITS,
QCOW2_DISCARD_REQUEST, false);
diff --git a/block/sheepdog.c b/block/sheepdog.c
index 66e1cb2..314b470 100644
--- a/block/sheepdog.c
+++ b/block/sheepdog.c
@@ -2820,8 +2820,9 @@ static coroutine_fn int sd_co_pdiscard(BlockDriverState *bs, int64_t offset,
iov.iov_len = sizeof(zero);
discard_iov.iov = &iov;
discard_iov.niov = 1;
- assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
- assert((count & (BDRV_SECTOR_SIZE - 1)) == 0);
+ if (!QEMU_IS_ALIGNED(offset | count, BDRV_SECTOR_SIZE)) {
+ return -ENOTSUP;
+ }
acb = sd_aio_setup(bs, &discard_iov, offset >> BDRV_SECTOR_BITS,
count >> BDRV_SECTOR_BITS);
acb->aiocb_type = AIOCB_DISCARD_OBJ;
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 53/67] block: Pass unaligned discard requests to drivers
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (51 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 52/67] block: Return -ENOTSUP rather than assert on unaligned discards Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 54/67] block/curl: Use BDRV_SECTOR_SIZE Michael Roth
` (14 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Eric Blake, Kevin Wolf
From: Eric Blake <eblake@redhat.com>
Discard is advisory, so rounding the requests to alignment
boundaries is never semantically wrong from the data that
the guest sees. But at least the Dell Equallogic iSCSI SANs
has an interesting property that its advertised discard
alignment is 15M, yet documents that discarding a sequence
of 1M slices will eventually result in the 15M page being
marked as discarded, and it is possible to observe which
pages have been discarded.
Between commits 9f1963b and b8d0a980, we converted the block
layer to a byte-based interface that ultimately ignores any
unaligned head or tail based on the driver's advertised
discard granularity, which means that qemu 2.7 refuses to
pass any discard request smaller than 15M down to the Dell
Equallogic hardware. This is a slight regression in behavior
compared to earlier qemu, where a guest executing discards
in power-of-2 chunks used to be able to get every page
discarded, but is now left with various pages still allocated
because the guest requests did not align with the hardware's
15M pages.
Since the SCSI specification says nothing about a minimum
discard granularity, and only documents the preferred
alignment, it is best if the block layer gives the driver
every bit of information about discard requests, rather than
rounding it to alignment boundaries early.
Rework the block layer discard algorithm to mirror the write
zero algorithm: always peel off any unaligned head or tail
and manage that in isolation, then do the bulk of the request
on an aligned boundary. The fallback when the driver returns
-ENOTSUP for an unaligned request is to silently ignore that
portion of the discard request; but for devices that can pass
the partial request all the way down to hardware, this can
result in the hardware coalescing requests and discarding
aligned pages after all.
Reported by: Peter Lieven <pl@kamp.de>
CC: qemu-stable@nongnu.org
Signed-off-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 3482b9bc411a9a12b2efde1018e1ddc906cd817e)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
block/io.c | 45 ++++++++++++++++++++++++++++++++-------------
1 file changed, 32 insertions(+), 13 deletions(-)
diff --git a/block/io.c b/block/io.c
index 959e140..5147080 100644
--- a/block/io.c
+++ b/block/io.c
@@ -2437,7 +2437,7 @@ int coroutine_fn bdrv_co_pdiscard(BlockDriverState *bs, int64_t offset,
{
BdrvTrackedRequest req;
int max_pdiscard, ret;
- int head, align;
+ int head, tail, align;
if (!bs->drv) {
return -ENOMEDIUM;
@@ -2460,19 +2460,15 @@ int coroutine_fn bdrv_co_pdiscard(BlockDriverState *bs, int64_t offset,
return 0;
}
- /* Discard is advisory, so ignore any unaligned head or tail */
+ /* Discard is advisory, but some devices track and coalesce
+ * unaligned requests, so we must pass everything down rather than
+ * round here. Still, most devices will just silently ignore
+ * unaligned requests (by returning -ENOTSUP), so we must fragment
+ * the request accordingly. */
align = MAX(bs->bl.pdiscard_alignment, bs->bl.request_alignment);
assert(align % bs->bl.request_alignment == 0);
head = offset % align;
- if (head) {
- head = MIN(count, align - head);
- count -= head;
- offset += head;
- }
- count = QEMU_ALIGN_DOWN(count, align);
- if (!count) {
- return 0;
- }
+ tail = (offset + count) % align;
tracked_request_begin(&req, bs, offset, count, BDRV_TRACKED_DISCARD);
@@ -2483,11 +2479,34 @@ int coroutine_fn bdrv_co_pdiscard(BlockDriverState *bs, int64_t offset,
max_pdiscard = QEMU_ALIGN_DOWN(MIN_NON_ZERO(bs->bl.max_pdiscard, INT_MAX),
align);
- assert(max_pdiscard);
+ assert(max_pdiscard >= bs->bl.request_alignment);
while (count > 0) {
int ret;
- int num = MIN(count, max_pdiscard);
+ int num = count;
+
+ if (head) {
+ /* Make small requests to get to alignment boundaries. */
+ num = MIN(count, align - head);
+ if (!QEMU_IS_ALIGNED(num, bs->bl.request_alignment)) {
+ num %= bs->bl.request_alignment;
+ }
+ head = (head + num) % align;
+ assert(num < max_pdiscard);
+ } else if (tail) {
+ if (num > align) {
+ /* Shorten the request to the last aligned cluster. */
+ num -= tail;
+ } else if (!QEMU_IS_ALIGNED(tail, bs->bl.request_alignment) &&
+ tail > bs->bl.request_alignment) {
+ tail %= bs->bl.request_alignment;
+ num -= tail;
+ }
+ }
+ /* limit request size */
+ if (num > max_pdiscard) {
+ num = max_pdiscard;
+ }
if (bs->drv->bdrv_co_pdiscard) {
ret = bs->drv->bdrv_co_pdiscard(bs, offset, num);
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 54/67] block/curl: Use BDRV_SECTOR_SIZE
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (52 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 53/67] block: Pass unaligned discard requests to drivers Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 55/67] block/curl: Fix return value from curl_read_cb Michael Roth
` (13 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Max Reitz, Jeff Cody
From: Max Reitz <mreitz@redhat.com>
Currently, curl defines its own constant SECTOR_SIZE. There is no
advantage over using the global BDRV_SECTOR_SIZE, so drop it.
Cc: qemu-stable@nongnu.org
Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-id: 20161025025431.24714-2-mreitz@redhat.com
Signed-off-by: Jeff Cody <jcody@redhat.com>
(cherry picked from commit 9054d9f6b00a3f0576b1a7310a3886d1783ad382)
Conflicts:
block/curl.c
* drop context dep on fffb6e1 / aio_bh_schedule_oneshot
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
block/curl.c | 11 +++++------
1 file changed, 5 insertions(+), 6 deletions(-)
diff --git a/block/curl.c b/block/curl.c
index 426fb4d..a764e32 100644
--- a/block/curl.c
+++ b/block/curl.c
@@ -73,7 +73,6 @@ static CURLMcode __curl_multi_socket_action(CURLM *multi_handle,
#define CURL_NUM_STATES 8
#define CURL_NUM_ACB 8
-#define SECTOR_SIZE 512
#define READ_AHEAD_DEFAULT (256 * 1024)
#define CURL_TIMEOUT_DEFAULT 5
#define CURL_TIMEOUT_MAX 10000
@@ -725,12 +724,12 @@ static void curl_readv_bh_cb(void *p)
qemu_bh_delete(acb->bh);
acb->bh = NULL;
- size_t start = acb->sector_num * SECTOR_SIZE;
+ size_t start = acb->sector_num * BDRV_SECTOR_SIZE;
size_t end;
// In case we have the requested data already (e.g. read-ahead),
// we can just call the callback and be done.
- switch (curl_find_buf(s, start, acb->nb_sectors * SECTOR_SIZE, acb)) {
+ switch (curl_find_buf(s, start, acb->nb_sectors * BDRV_SECTOR_SIZE, acb)) {
case FIND_RET_OK:
qemu_aio_unref(acb);
// fall through
@@ -749,7 +748,7 @@ static void curl_readv_bh_cb(void *p)
}
acb->start = 0;
- acb->end = (acb->nb_sectors * SECTOR_SIZE);
+ acb->end = (acb->nb_sectors * BDRV_SECTOR_SIZE);
state->buf_off = 0;
g_free(state->orig_buf);
@@ -766,8 +765,8 @@ static void curl_readv_bh_cb(void *p)
state->acb[0] = acb;
snprintf(state->range, 127, "%zd-%zd", start, end);
- DPRINTF("CURL (AIO): Reading %d at %zd (%s)\n",
- (acb->nb_sectors * SECTOR_SIZE), start, state->range);
+ DPRINTF("CURL (AIO): Reading %llu at %zd (%s)\n",
+ (acb->nb_sectors * BDRV_SECTOR_SIZE), start, state->range);
curl_easy_setopt(state->curl, CURLOPT_RANGE, state->range);
curl_multi_add_handle(s->multi, state->curl);
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 55/67] block/curl: Fix return value from curl_read_cb
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (53 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 54/67] block/curl: Use BDRV_SECTOR_SIZE Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 56/67] block/curl: Remember all sockets Michael Roth
` (12 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Max Reitz, Jeff Cody
From: Max Reitz <mreitz@redhat.com>
While commit 38bbc0a580f9f10570b1d1b5d3e92f0e6feb2970 is correct in that
the callback is supposed to return the number of bytes handled; what it
does not mention is that libcurl will throw an error if the callback did
not "handle" all of the data passed to it.
Therefore, if the callback receives some data that it cannot handle
(either because the receive buffer has not been set up yet or because it
would not fit into the receive buffer) and we have to ignore it, we
still have to report that the data has been handled.
Obviously, this should not happen normally. But it does happen at least
for FTP connections where some data (that we do not expect) may be
generated when the connection is established.
Cc: qemu-stable@nongnu.org
Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-id: 20161025025431.24714-3-mreitz@redhat.com
Signed-off-by: Jeff Cody <jcody@redhat.com>
(cherry picked from commit 4e7676571bccb42dd49b5efbb91ac49077ea5197)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
block/curl.c | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/block/curl.c b/block/curl.c
index a764e32..f47f4e6 100644
--- a/block/curl.c
+++ b/block/curl.c
@@ -213,12 +213,13 @@ static size_t curl_read_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
DPRINTF("CURL: Just reading %zd bytes\n", realsize);
- if (!s || !s->orig_buf)
- return 0;
+ if (!s || !s->orig_buf) {
+ goto read_end;
+ }
if (s->buf_off >= s->buf_len) {
/* buffer full, read nothing */
- return 0;
+ goto read_end;
}
realsize = MIN(realsize, s->buf_len - s->buf_off);
memcpy(s->orig_buf + s->buf_off, ptr, realsize);
@@ -239,7 +240,9 @@ static size_t curl_read_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
}
}
- return realsize;
+read_end:
+ /* curl will error out if we do not return this value */
+ return size * nmemb;
}
static int curl_find_buf(BDRVCURLState *s, size_t start, size_t len,
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 56/67] block/curl: Remember all sockets
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (54 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 55/67] block/curl: Fix return value from curl_read_cb Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 57/67] block/curl: Do not wait for data beyond EOF Michael Roth
` (11 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Max Reitz, Jeff Cody
From: Max Reitz <mreitz@redhat.com>
For some connection types (like FTP, generally), more than one socket
may be used (in FTP's case: control vs. data stream). As of commit
838ef602498b8d1985a231a06f5e328e2946a81d ("curl: Eliminate unnecessary
use of curl_multi_socket_all"), we have to remember all of the sockets
used by libcurl, but in fact we only did that for a single one. Since
one libcurl connection may use multiple sockets, however, we have to
remember them all.
Cc: qemu-stable@nongnu.org
Signed-off-by: Max Reitz <mreitz@redhat.com>
Message-id: 20161025025431.24714-4-mreitz@redhat.com
Signed-off-by: Jeff Cody <jcody@redhat.com>
(cherry picked from commit ff5ca1664af85b24a4180d595ea6873fd3deac57)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
block/curl.c | 47 +++++++++++++++++++++++++++++++++++++++++------
1 file changed, 41 insertions(+), 6 deletions(-)
diff --git a/block/curl.c b/block/curl.c
index f47f4e6..600d032 100644
--- a/block/curl.c
+++ b/block/curl.c
@@ -105,12 +105,17 @@ typedef struct CURLAIOCB {
size_t end;
} CURLAIOCB;
+typedef struct CURLSocket {
+ int fd;
+ QLIST_ENTRY(CURLSocket) next;
+} CURLSocket;
+
typedef struct CURLState
{
struct BDRVCURLState *s;
CURLAIOCB *acb[CURL_NUM_ACB];
CURL *curl;
- curl_socket_t sock_fd;
+ QLIST_HEAD(, CURLSocket) sockets;
char *orig_buf;
size_t buf_start;
size_t buf_off;
@@ -164,10 +169,27 @@ static int curl_sock_cb(CURL *curl, curl_socket_t fd, int action,
{
BDRVCURLState *s;
CURLState *state = NULL;
+ CURLSocket *socket;
+
curl_easy_getinfo(curl, CURLINFO_PRIVATE, (char **)&state);
- state->sock_fd = fd;
s = state->s;
+ QLIST_FOREACH(socket, &state->sockets, next) {
+ if (socket->fd == fd) {
+ if (action == CURL_POLL_REMOVE) {
+ QLIST_REMOVE(socket, next);
+ g_free(socket);
+ }
+ break;
+ }
+ }
+ if (!socket) {
+ socket = g_new0(CURLSocket, 1);
+ socket->fd = fd;
+ QLIST_INSERT_HEAD(&state->sockets, socket, next);
+ }
+ socket = NULL;
+
DPRINTF("CURL (AIO): Sock action %d on fd %d\n", action, (int)fd);
switch (action) {
case CURL_POLL_IN:
@@ -355,6 +377,7 @@ static void curl_multi_check_completion(BDRVCURLState *s)
static void curl_multi_do(void *arg)
{
CURLState *s = (CURLState *)arg;
+ CURLSocket *socket, *next_socket;
int running;
int r;
@@ -362,10 +385,13 @@ static void curl_multi_do(void *arg)
return;
}
- do {
- r = curl_multi_socket_action(s->s->multi, s->sock_fd, 0, &running);
- } while(r == CURLM_CALL_MULTI_PERFORM);
-
+ /* Need to use _SAFE because curl_multi_socket_action() may trigger
+ * curl_sock_cb() which might modify this list */
+ QLIST_FOREACH_SAFE(socket, &s->sockets, next, next_socket) {
+ do {
+ r = curl_multi_socket_action(s->s->multi, socket->fd, 0, &running);
+ } while (r == CURLM_CALL_MULTI_PERFORM);
+ }
}
static void curl_multi_read(void *arg)
@@ -469,6 +495,7 @@ static CURLState *curl_init_state(BlockDriverState *bs, BDRVCURLState *s)
#endif
}
+ QLIST_INIT(&state->sockets);
state->s = s;
return state;
@@ -478,6 +505,14 @@ static void curl_clean_state(CURLState *s)
{
if (s->s->multi)
curl_multi_remove_handle(s->s->multi, s->curl);
+
+ while (!QLIST_EMPTY(&s->sockets)) {
+ CURLSocket *socket = QLIST_FIRST(&s->sockets);
+
+ QLIST_REMOVE(socket, next);
+ g_free(socket);
+ }
+
s->in_use = 0;
}
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 57/67] block/curl: Do not wait for data beyond EOF
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (55 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 56/67] block/curl: Remember all sockets Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 58/67] vhost: drop legacy vring layout bits Michael Roth
` (10 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Max Reitz, Jeff Cody
From: Max Reitz <mreitz@redhat.com>
libcurl will only give us as much data as there is, not more. The block
layer will deny requests beyond the end of file for us; but since this
block driver is still using a sector-based interface, we can still get
in trouble if the file size is not a multiple of 512.
While we have already made sure not to attempt transfers beyond the end
of the file, we are currently still trying to receive data from there if
the original request exceeds the file size. This patch fixes this issue
and invokes qemu_iovec_memset() on the iovec's tail.
Cc: qemu-stable@nongnu.org
Signed-off-by: Max Reitz <mreitz@redhat.com>
Message-id: 20161025025431.24714-5-mreitz@redhat.com
Signed-off-by: Jeff Cody <jcody@redhat.com>
(cherry picked from commit 4e504535c16dfa66290281e704384abfaca08673)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
block/curl.c | 32 +++++++++++++++++++++++---------
1 file changed, 23 insertions(+), 9 deletions(-)
diff --git a/block/curl.c b/block/curl.c
index 600d032..db0b25b 100644
--- a/block/curl.c
+++ b/block/curl.c
@@ -254,8 +254,17 @@ static size_t curl_read_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
continue;
if ((s->buf_off >= acb->end)) {
+ size_t request_length = acb->nb_sectors * BDRV_SECTOR_SIZE;
+
qemu_iovec_from_buf(acb->qiov, 0, s->orig_buf + acb->start,
acb->end - acb->start);
+
+ if (acb->end - acb->start < request_length) {
+ size_t offset = acb->end - acb->start;
+ qemu_iovec_memset(acb->qiov, offset, 0,
+ request_length - offset);
+ }
+
acb->common.cb(acb->common.opaque, 0);
qemu_aio_unref(acb);
s->acb[i] = NULL;
@@ -272,6 +281,8 @@ static int curl_find_buf(BDRVCURLState *s, size_t start, size_t len,
{
int i;
size_t end = start + len;
+ size_t clamped_end = MIN(end, s->len);
+ size_t clamped_len = clamped_end - start;
for (i=0; i<CURL_NUM_STATES; i++) {
CURLState *state = &s->states[i];
@@ -286,12 +297,15 @@ static int curl_find_buf(BDRVCURLState *s, size_t start, size_t len,
// Does the existing buffer cover our section?
if ((start >= state->buf_start) &&
(start <= buf_end) &&
- (end >= state->buf_start) &&
- (end <= buf_end))
+ (clamped_end >= state->buf_start) &&
+ (clamped_end <= buf_end))
{
char *buf = state->orig_buf + (start - state->buf_start);
- qemu_iovec_from_buf(acb->qiov, 0, buf, len);
+ qemu_iovec_from_buf(acb->qiov, 0, buf, clamped_len);
+ if (clamped_len < len) {
+ qemu_iovec_memset(acb->qiov, clamped_len, 0, len - clamped_len);
+ }
acb->common.cb(acb->common.opaque, 0);
return FIND_RET_OK;
@@ -301,13 +315,13 @@ static int curl_find_buf(BDRVCURLState *s, size_t start, size_t len,
if (state->in_use &&
(start >= state->buf_start) &&
(start <= buf_fend) &&
- (end >= state->buf_start) &&
- (end <= buf_fend))
+ (clamped_end >= state->buf_start) &&
+ (clamped_end <= buf_fend))
{
int j;
acb->start = start - state->buf_start;
- acb->end = acb->start + len;
+ acb->end = acb->start + clamped_len;
for (j=0; j<CURL_NUM_ACB; j++) {
if (!state->acb[j]) {
@@ -786,13 +800,13 @@ static void curl_readv_bh_cb(void *p)
}
acb->start = 0;
- acb->end = (acb->nb_sectors * BDRV_SECTOR_SIZE);
+ acb->end = MIN(acb->nb_sectors * BDRV_SECTOR_SIZE, s->len - start);
state->buf_off = 0;
g_free(state->orig_buf);
state->buf_start = start;
- state->buf_len = acb->end + s->readahead_size;
- end = MIN(start + state->buf_len, s->len) - 1;
+ state->buf_len = MIN(acb->end + s->readahead_size, s->len - start);
+ end = start + state->buf_len - 1;
state->orig_buf = g_try_malloc(state->buf_len);
if (state->buf_len && state->orig_buf == NULL) {
curl_clean_state(state);
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 58/67] vhost: drop legacy vring layout bits
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (56 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 57/67] block/curl: Do not wait for data beyond EOF Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 59/67] ivshmem: Fix 64 bit memory bar configuration Michael Roth
` (9 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Greg Kurz, Michael S. Tsirkin
From: Greg Kurz <groug@kaod.org>
The legacy vring layout is not used anymore as we use the separate
mappings even for legacy devices.
This patch simply removes it.
This also fixes a bug with virtio 1 devices when the vring descriptor table
is mapped at a higher address than the used vring because the following
function may return an insanely great value:
hwaddr virtio_queue_get_ring_size(VirtIODevice *vdev, int n)
{
return vdev->vq[n].vring.used - vdev->vq[n].vring.desc +
virtio_queue_get_used_size(vdev, n);
}
and the mapping fails.
Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit 1cdce7c54d26e64f5eddb10a6f4f7dd938dfc2c4)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/virtio/vhost.c | 13 -------------
include/hw/virtio/vhost.h | 3 ---
2 files changed, 16 deletions(-)
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index b89f253..e01fdd7 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -920,14 +920,6 @@ static int vhost_virtqueue_start(struct vhost_dev *dev,
goto fail_alloc_used;
}
- vq->ring_size = s = l = virtio_queue_get_ring_size(vdev, idx);
- vq->ring_phys = a = virtio_queue_get_ring_addr(vdev, idx);
- vq->ring = cpu_physical_memory_map(a, &l, 1);
- if (!vq->ring || l != s) {
- r = -ENOMEM;
- goto fail_alloc_ring;
- }
-
r = vhost_virtqueue_set_addr(dev, vq, vhost_vq_index, dev->log_enabled);
if (r < 0) {
r = -errno;
@@ -957,9 +949,6 @@ static int vhost_virtqueue_start(struct vhost_dev *dev,
fail_kick:
fail_alloc:
- cpu_physical_memory_unmap(vq->ring, virtio_queue_get_ring_size(vdev, idx),
- 0, 0);
-fail_alloc_ring:
cpu_physical_memory_unmap(vq->used, virtio_queue_get_used_size(vdev, idx),
0, 0);
fail_alloc_used:
@@ -1000,8 +989,6 @@ static void vhost_virtqueue_stop(struct vhost_dev *dev,
vhost_vq_index);
}
- cpu_physical_memory_unmap(vq->ring, virtio_queue_get_ring_size(vdev, idx),
- 0, virtio_queue_get_ring_size(vdev, idx));
cpu_physical_memory_unmap(vq->used, virtio_queue_get_used_size(vdev, idx),
1, virtio_queue_get_used_size(vdev, idx));
cpu_physical_memory_unmap(vq->avail, virtio_queue_get_avail_size(vdev, idx),
diff --git a/include/hw/virtio/vhost.h b/include/hw/virtio/vhost.h
index 56b567f..1fe5aad 100644
--- a/include/hw/virtio/vhost.h
+++ b/include/hw/virtio/vhost.h
@@ -20,9 +20,6 @@ struct vhost_virtqueue {
unsigned avail_size;
unsigned long long used_phys;
unsigned used_size;
- void *ring;
- unsigned long long ring_phys;
- unsigned ring_size;
EventNotifier masked_notifier;
};
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 59/67] ivshmem: Fix 64 bit memory bar configuration
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (57 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 58/67] vhost: drop legacy vring layout bits Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 60/67] pci-assign: sync MSI/MSI-X cap and table with PCIDevice Michael Roth
` (8 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Zhuang Yanying, Michael S. Tsirkin
From: Zhuang Yanying <ann.zhuangyanying@huawei.com>
Device ivshmem property use64=0 is designed to make the device
expose a 32 bit shared memory BAR instead of 64 bit one. The
default is a 64 bit BAR, except pc-1.2 and older retain a 32 bit
BAR. A 32 bit BAR can support only up to 1 GiB of shared memory.
This worked as designed until commit 5400c02 accidentally flipped
its sense: since then, we misinterpret use64=0 as use64=1 and vice
versa. Worse, the default got flipped as well. Devices
ivshmem-plain and ivshmem-doorbell are not affected.
Fix by restoring the test of IVShmemState member not_legacy_32bit
that got messed up in commit 5400c02. Also update its
initialization for devices ivhsmem-plain and ivshmem-doorbell.
Without that, they'd regress to 32 bit BARs.
Cc: qemu-stable@nongnu.org
Signed-off-by: Zhuang Yanying <ann.zhuangyanying@huawei.com>
Reviewed-by: Gonglei <arei.gonglei@huawei.com>
Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
(cherry picked from commit be4e0d737527d8670dc271712faae0de6a181b4e)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/misc/ivshmem.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/hw/misc/ivshmem.c b/hw/misc/ivshmem.c
index 40a2ebc..81783d5 100644
--- a/hw/misc/ivshmem.c
+++ b/hw/misc/ivshmem.c
@@ -859,7 +859,7 @@ static void ivshmem_common_realize(PCIDevice *dev, Error **errp)
pci_register_bar(dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY,
&s->ivshmem_mmio);
- if (!s->not_legacy_32bit) {
+ if (s->not_legacy_32bit) {
attr |= PCI_BASE_ADDRESS_MEM_TYPE_64;
}
@@ -1045,6 +1045,7 @@ static void ivshmem_plain_init(Object *obj)
ivshmem_check_memdev_is_busy,
OBJ_PROP_LINK_UNREF_ON_RELEASE,
&error_abort);
+ s->not_legacy_32bit = 1;
}
static void ivshmem_plain_realize(PCIDevice *dev, Error **errp)
@@ -1116,6 +1117,7 @@ static void ivshmem_doorbell_init(Object *obj)
s->features |= (1 << IVSHMEM_MSI);
s->legacy_size = SIZE_MAX; /* whatever the server sends */
+ s->not_legacy_32bit = 1;
}
static void ivshmem_doorbell_realize(PCIDevice *dev, Error **errp)
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 60/67] pci-assign: sync MSI/MSI-X cap and table with PCIDevice
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (58 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 59/67] ivshmem: Fix 64 bit memory bar configuration Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 61/67] rules.mak: Use -r instead of -Wl, -r to fix building when PIE is default Michael Roth
` (7 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Peter Xu, Paolo Bonzini
From: Peter Xu <peterx@redhat.com>
Since commit e1d4fb2d ("kvm-irqchip: x86: add msi route notify fn"),
kvm_irqchip_add_msi_route() starts to use pci_get_msi_message() to fetch
MSI info. This requires that we setup MSI related fields in PCIDevice.
For most devices, that won't be a problem, as long as we are using
general interfaces like msi_init()/msix_init().
However, for pci-assign devices, MSI/MSI-X is treated differently - PCI
assign devices are maintaining its own MSI table and cap information in
AssignedDevice struct. however that's not synced up with PCIDevice's
fields. That will leads to pci_get_msi_message() failed to find correct
MSI capability, even with an NULL msix_table.
A quick fix is to sync up the two places: both the capability bits and
table address for MSI/MSI-X.
Reported-by: Changlimin <changlimin@h3c.com>
Tested-by: Changlimin <changlimin@h3c.com>
Cc: qemu-stable@nongnu.org
Fixes: e1d4fb2d ("kvm-irqchip: x86: add msi route notify fn")
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <1480042522-16551-1-git-send-email-peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 64e184e2608d3c93dda1bba8ae6dc2185b5228fb)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/i386/kvm/pci-assign.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/hw/i386/kvm/pci-assign.c b/hw/i386/kvm/pci-assign.c
index 8238fbc..87dcbdd 100644
--- a/hw/i386/kvm/pci-assign.c
+++ b/hw/i386/kvm/pci-assign.c
@@ -1251,6 +1251,7 @@ static int assigned_device_pci_cap_init(PCIDevice *pci_dev, Error **errp)
error_propagate(errp, local_err);
return -ENOTSUP;
}
+ dev->dev.cap_present |= QEMU_PCI_CAP_MSI;
dev->cap.available |= ASSIGNED_DEVICE_CAP_MSI;
/* Only 32-bit/no-mask currently supported */
ret = pci_add_capability2(pci_dev, PCI_CAP_ID_MSI, pos, 10,
@@ -1285,6 +1286,7 @@ static int assigned_device_pci_cap_init(PCIDevice *pci_dev, Error **errp)
error_propagate(errp, local_err);
return -ENOTSUP;
}
+ dev->dev.cap_present |= QEMU_PCI_CAP_MSIX;
dev->cap.available |= ASSIGNED_DEVICE_CAP_MSIX;
ret = pci_add_capability2(pci_dev, PCI_CAP_ID_MSIX, pos, 12,
&local_err);
@@ -1648,6 +1650,7 @@ static void assigned_dev_register_msix_mmio(AssignedDevice *dev, Error **errp)
dev->msix_table = NULL;
return;
}
+ dev->dev.msix_table = (uint8_t *)dev->msix_table;
assigned_dev_msix_reset(dev);
@@ -1665,6 +1668,7 @@ static void assigned_dev_unregister_msix_mmio(AssignedDevice *dev)
error_report("error unmapping msix_table! %s", strerror(errno));
}
dev->msix_table = NULL;
+ dev->dev.msix_table = NULL;
}
static const VMStateDescription vmstate_assigned_device = {
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 61/67] rules.mak: Use -r instead of -Wl, -r to fix building when PIE is default
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (59 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 60/67] pci-assign: sync MSI/MSI-X cap and table with PCIDevice Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 62/67] intel_iommu: fix incorrect device invalidate Michael Roth
` (6 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Adrian Bunk, Paolo Bonzini
From: Adrian Bunk <bunk@stusta.de>
Building qemu fails in distributions where gcc enables PIE by default
(e.g. Debian unstable) with:
/usr/bin/ld: -r and -pie may not be used together
Use -r instead of -Wl,-r to avoid gcc passing -pie to the linker
when PIE is enabled and a relocatable object is passed.
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Message-Id: <20161127162817.15144-1-bunk@stusta.de>
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit c96f0ee6a67ca6277366e78ce5d84d5c20dd596f)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
rules.mak | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/rules.mak b/rules.mak
index 99cd0b3..97f1aa1 100644
--- a/rules.mak
+++ b/rules.mak
@@ -92,7 +92,7 @@ module-common.o: CFLAGS += $(DSO_OBJ_CFLAGS)
$(if $(findstring /,$@),$(call quiet-command,cp $@ $(subst /,-,$@), " CP $(subst /,-,$@)"))
-LD_REL := $(CC) -nostdlib -Wl,-r $(LD_REL_FLAGS)
+LD_REL := $(CC) -nostdlib -r $(LD_REL_FLAGS)
%.mo:
$(call quiet-command,$(LD_REL) -o $@ $^," LD -r $(TARGET_DIR)$@")
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 62/67] intel_iommu: fix incorrect device invalidate
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (60 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 61/67] rules.mak: Use -r instead of -Wl, -r to fix building when PIE is default Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 63/67] vhost-user-test: Use libqos instead of pxe-virtio.rom Michael Roth
` (5 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Peter Xu, Michael S. Tsirkin
From: Peter Xu <peterx@redhat.com>
"mask" needs to be inverted before use.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit 6cb99acc2808cc41e2d772a23e9cc564515535cc)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/i386/intel_iommu.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index 28c31a2..a22545b 100644
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -985,6 +985,7 @@ static void vtd_context_device_invalidate(IntelIOMMUState *s,
mask = 7; /* Mask bit 2:0 in the SID field */
break;
}
+ mask = ~mask;
VTD_DPRINTF(INV, "device-selective invalidation source 0x%"PRIx16
" mask %"PRIu16, source_id, mask);
vtd_bus = vtd_find_as_from_bus_num(s, VTD_SID_TO_BUS(source_id));
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 63/67] vhost-user-test: Use libqos instead of pxe-virtio.rom
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (61 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 62/67] intel_iommu: fix incorrect device invalidate Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 64/67] vl: Delay initialization of memory backends Michael Roth
` (4 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Eduardo Habkost
From: Eduardo Habkost <ehabkost@redhat.com>
vhost-user-test relies on iPXE just to initialize the virtio-net
device, and doesn't do any actual packet tx/rx testing.
In addition to that, the test relies on TCG, which is
imcompatible with vhost. The test only worked by accident: a bug
the memory backend initialization made memory regions not have
the DIRTY_MEMORY_CODE bit set in dirty_log_mask.
This changes vhost-user-test to initialize the virtio-net device
using libqos, and not use TCG nor pxe-virtio.rom.
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
(cherry picked from commit cdafe929615ec5eca71bcd5a3d12bab5678e5886)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
tests/Makefile.include | 2 +-
tests/vhost-user-test.c | 37 ++++++++++++++++++++++++++++++++++---
2 files changed, 35 insertions(+), 4 deletions(-)
diff --git a/tests/Makefile.include b/tests/Makefile.include
index 14be491..03382b5 100644
--- a/tests/Makefile.include
+++ b/tests/Makefile.include
@@ -622,7 +622,7 @@ tests/usb-hcd-ehci-test$(EXESUF): tests/usb-hcd-ehci-test.o $(libqos-usb-obj-y)
tests/usb-hcd-xhci-test$(EXESUF): tests/usb-hcd-xhci-test.o $(libqos-usb-obj-y)
tests/pc-cpu-test$(EXESUF): tests/pc-cpu-test.o
tests/postcopy-test$(EXESUF): tests/postcopy-test.o
-tests/vhost-user-test$(EXESUF): tests/vhost-user-test.o qemu-char.o qemu-timer.o $(qtest-obj-y) $(test-io-obj-y)
+tests/vhost-user-test$(EXESUF): tests/vhost-user-test.o qemu-char.o qemu-timer.o $(qtest-obj-y) $(test-io-obj-y) $(libqos-virtio-obj-y)
tests/qemu-iotests/socket_scm_helper$(EXESUF): tests/qemu-iotests/socket_scm_helper.o
tests/test-qemu-opts$(EXESUF): tests/test-qemu-opts.o $(test-util-obj-y)
tests/test-write-threshold$(EXESUF): tests/test-write-threshold.o $(test-block-obj-y)
diff --git a/tests/vhost-user-test.c b/tests/vhost-user-test.c
index 27b10c1..b89a551 100644
--- a/tests/vhost-user-test.c
+++ b/tests/vhost-user-test.c
@@ -16,8 +16,13 @@
#include "qemu/sockets.h"
#include "sysemu/char.h"
#include "sysemu/sysemu.h"
+#include "libqos/libqos.h"
+#include "libqos/pci-pc.h"
+#include "libqos/virtio-pci.h"
#include <linux/vhost.h>
+#include <linux/virtio_ids.h>
+#include <linux/virtio_net.h>
#include <sys/vfs.h>
/* GLIB version compatibility flags */
@@ -29,14 +34,13 @@
#define HAVE_MONOTONIC_TIME
#endif
-#define QEMU_CMD_ACCEL " -machine accel=tcg"
#define QEMU_CMD_MEM " -m %d -object memory-backend-file,id=mem,size=%dM,"\
"mem-path=%s,share=on -numa node,memdev=mem"
#define QEMU_CMD_CHR " -chardev socket,id=%s,path=%s%s"
#define QEMU_CMD_NETDEV " -netdev vhost-user,id=net0,chardev=%s,vhostforce"
-#define QEMU_CMD_NET " -device virtio-net-pci,netdev=net0,romfile=./pc-bios/pxe-virtio.rom"
+#define QEMU_CMD_NET " -device virtio-net-pci,netdev=net0"
-#define QEMU_CMD QEMU_CMD_ACCEL QEMU_CMD_MEM QEMU_CMD_CHR \
+#define QEMU_CMD QEMU_CMD_MEM QEMU_CMD_CHR \
QEMU_CMD_NETDEV QEMU_CMD_NET
#define HUGETLBFS_MAGIC 0x958458f6
@@ -136,6 +140,30 @@ typedef struct TestServer {
static const char *tmpfs;
static const char *root;
+static void init_virtio_dev(TestServer *s)
+{
+ QPCIBus *bus;
+ QVirtioPCIDevice *dev;
+ uint32_t features;
+
+ bus = qpci_init_pc();
+ g_assert_nonnull(bus);
+
+ dev = qvirtio_pci_device_find(bus, VIRTIO_ID_NET);
+ g_assert_nonnull(dev);
+
+ qvirtio_pci_device_enable(dev);
+ qvirtio_reset(&qvirtio_pci, &dev->vdev);
+ qvirtio_set_acknowledge(&qvirtio_pci, &dev->vdev);
+ qvirtio_set_driver(&qvirtio_pci, &dev->vdev);
+
+ features = qvirtio_get_features(&qvirtio_pci, &dev->vdev);
+ features = features & VIRTIO_NET_F_MAC;
+ qvirtio_set_features(&qvirtio_pci, &dev->vdev, features);
+
+ qvirtio_set_driver_ok(&qvirtio_pci, &dev->vdev);
+}
+
static void wait_for_fds(TestServer *s)
{
gint64 end_time;
@@ -548,6 +576,7 @@ static void test_migrate(void)
from = qtest_start(cmd);
g_free(cmd);
+ init_virtio_dev(s);
wait_for_fds(s);
size = get_log_size(s);
g_assert_cmpint(size, ==, (2 * 1024 * 1024) / (VHOST_LOG_PAGE * 8));
@@ -662,6 +691,7 @@ static void test_reconnect_subprocess(void)
qtest_start(cmd);
g_free(cmd);
+ init_virtio_dev(s);
wait_for_fds(s);
wait_for_rings_started(s, 2);
@@ -728,6 +758,7 @@ int main(int argc, char **argv)
s = qtest_start(qemu_cmd);
g_free(qemu_cmd);
+ init_virtio_dev(server);
qtest_add_data_func("/vhost-user/read-guest-mem", server, read_guest_mem);
qtest_add_func("/vhost-user/migrate", test_migrate);
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 64/67] vl: Delay initialization of memory backends
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (62 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 63/67] vhost-user-test: Use libqos instead of pxe-virtio.rom Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:44 ` [Qemu-devel] [PATCH 65/67] Revert "megasas: remove useless check for cmd->frame" Michael Roth
` (3 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Eduardo Habkost
From: Eduardo Habkost <ehabkost@redhat.com>
Initialization of memory backends may take a while when
prealloc=yes is used, depending on their size. Initializing
memory backends before chardevs may delay the creation of monitor
sockets, and trigger timeouts on management software that waits
until the monitor socket is created by QEMU. See, for example,
the bug report at:
https://bugzilla.redhat.com/show_bug.cgi?id=1371211
In addition to that, allocating memory before calling
configure_accelerator() breaks the tcg_enabled() checks at
memory_region_init_*().
This patch fixes those problems by adding "memory-backend-*"
classes to the delayed-initialization list.
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
(cherry picked from commit 6546d0dba6c211c1a3eac1252a4f50a0c151a08a)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
vl.c | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/vl.c b/vl.c
index 3414e1a..6a218ce 100644
--- a/vl.c
+++ b/vl.c
@@ -2811,6 +2811,19 @@ static bool object_create_initial(const char *type)
return false;
}
+ /* Memory allocation by backends needs to be done
+ * after configure_accelerator() (due to the tcg_enabled()
+ * checks at memory_region_init_*()).
+ *
+ * Also, allocation of large amounts of memory may delay
+ * chardev initialization for too long, and trigger timeouts
+ * on software that waits for a monitor socket to be created
+ * (e.g. libvirt).
+ */
+ if (g_str_has_prefix(type, "memory-backend-")) {
+ return false;
+ }
+
return true;
}
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 65/67] Revert "megasas: remove useless check for cmd->frame"
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (63 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 64/67] vl: Delay initialization of memory backends Michael Roth
@ 2016-12-15 0:44 ` Michael Roth
2016-12-15 0:45 ` [Qemu-devel] [PATCH 66/67] msmouse: Fix segfault caused by free the chr before chardev cleanup Michael Roth
` (2 subsequent siblings)
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:44 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Paolo Bonzini
From: Paolo Bonzini <pbonzini@redhat.com>
This reverts commit 8cc46787b5b58f01a11c919c7ff939ed009e27fc.
It turns out that cmd->frame can be NULL and thus the commit
can cause a SIGSEGV
Reported-by: Holger Schranz <holger@fam-schranz.de>
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 421cc3e7e89cb807d3c5f6de486abb2167c8e792)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/scsi/megasas.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/hw/scsi/megasas.c b/hw/scsi/megasas.c
index e968302..52a4123 100644
--- a/hw/scsi/megasas.c
+++ b/hw/scsi/megasas.c
@@ -1981,7 +1981,11 @@ static void megasas_handle_frame(MegasasState *s, uint64_t frame_addr,
break;
}
if (frame_status != MFI_STAT_INVALID_STATUS) {
- cmd->frame->header.cmd_status = frame_status;
+ if (cmd->frame) {
+ cmd->frame->header.cmd_status = frame_status;
+ } else {
+ megasas_frame_set_cmd_status(s, frame_addr, frame_status);
+ }
megasas_unmap_frame(s, cmd);
megasas_complete_frame(s, cmd->context);
}
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 66/67] msmouse: Fix segfault caused by free the chr before chardev cleanup.
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (64 preceding siblings ...)
2016-12-15 0:44 ` [Qemu-devel] [PATCH 65/67] Revert "megasas: remove useless check for cmd->frame" Michael Roth
@ 2016-12-15 0:45 ` Michael Roth
2016-12-15 0:45 ` [Qemu-devel] [PATCH 67/67] vfio/pci: Fix vfio_rtl8168_quirk_data_read address offset Michael Roth
2016-12-15 6:14 ` [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Stefan Weil
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:45 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Lin Ma, Paolo Bonzini
From: Lin Ma <lma@suse.com>
Segfault happens when leaving qemu with msmouse backend:
#0 0x00007fa8526ac975 in raise () at /lib64/libc.so.6
#1 0x00007fa8526add8a in abort () at /lib64/libc.so.6
#2 0x0000558be78846ab in error_exit (err=16, msg=0x558be799da10 ...
#3 0x0000558be7884717 in qemu_mutex_destroy (mutex=0x558be93be750) at ...
#4 0x0000558be7549951 in qemu_chr_free_common (chr=0x558be93be750) at ...
#5 0x0000558be754999c in qemu_chr_free (chr=0x558be93be750) at ...
#6 0x0000558be7549a20 in qemu_chr_delete (chr=0x558be93be750) at ...
#7 0x0000558be754a8ef in qemu_chr_cleanup () at qemu-char.c:4643
#8 0x0000558be755843e in main (argc=5, argv=0x7ffe925d7118, ...
The chr was freed by msmouse close callback before chardev cleanup,
Then qemu_mutex_destroy triggered raise().
Because freeing chr is handled by qemu_chr_free_common, Remove the free from
msmouse_chr_close to avoid double free.
Fixes: c1111a24a3358ecd2f17be7c8b117cfe8bc5e5f8
Cc: qemu-stable@nongnu.org
Signed-off-by: Lin Ma <lma@suse.com>
Message-Id: <20160915143158.4796-1-lma@suse.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 9e14037f05e99ca3b8a33d8be9a2a636bbf09326)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
backends/msmouse.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/backends/msmouse.c b/backends/msmouse.c
index aceb6dc..85d08f7 100644
--- a/backends/msmouse.c
+++ b/backends/msmouse.c
@@ -139,7 +139,6 @@ static void msmouse_chr_close (struct CharDriverState *chr)
qemu_input_handler_unregister(mouse->hs);
g_free(mouse);
- g_free(chr);
}
static QemuInputHandler msmouse_handler = {
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* [Qemu-devel] [PATCH 67/67] vfio/pci: Fix vfio_rtl8168_quirk_data_read address offset
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (65 preceding siblings ...)
2016-12-15 0:45 ` [Qemu-devel] [PATCH 66/67] msmouse: Fix segfault caused by free the chr before chardev cleanup Michael Roth
@ 2016-12-15 0:45 ` Michael Roth
2016-12-15 6:14 ` [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Stefan Weil
67 siblings, 0 replies; 71+ messages in thread
From: Michael Roth @ 2016-12-15 0:45 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-stable, Thorsten Kohfeldt, Alex Williamson
From: Thorsten Kohfeldt <thorsten.kohfeldt@gmx.de>
Introductory comment for rtl8168 VFIO MSI-X quirk states:
At BAR2 offset 0x70 there is a dword data register,
offset 0x74 is a dword address register.
vfio: vfio_bar_read(0000:05:00.0:BAR2+0x70, 4) = 0xfee00398 // read data
Thus, correct offset for data read is 0x70,
but function vfio_rtl8168_quirk_data_read() wrongfully uses offset 0x74.
Signed-off-by: Thorsten Kohfeldt <thorsten.kohfeldt@gmx.de>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
(cherry picked from commit 31e6a7b17b35711eb44f0e686b5ba68d15bfe4c1)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
hw/vfio/pci-quirks.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/hw/vfio/pci-quirks.c b/hw/vfio/pci-quirks.c
index bec694c..1e97bc4 100644
--- a/hw/vfio/pci-quirks.c
+++ b/hw/vfio/pci-quirks.c
@@ -898,7 +898,7 @@ static uint64_t vfio_rtl8168_quirk_data_read(void *opaque,
{
VFIOrtl8168Quirk *rtl = opaque;
VFIOPCIDevice *vdev = rtl->vdev;
- uint64_t data = vfio_region_read(&vdev->bars[2].region, addr + 0x74, size);
+ uint64_t data = vfio_region_read(&vdev->bars[2].region, addr + 0x70, size);
if (rtl->enabled && (vdev->pdev.cap_present & QEMU_PCI_CAP_MSIX)) {
hwaddr offset = rtl->addr & 0xfff;
--
1.9.1
^ permalink raw reply related [flat|nested] 71+ messages in thread* Re: [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20
2016-12-15 0:43 [Qemu-devel] [PATCH 00/67] Patch Round-up for stable 2.7.1, freeze on 2016-12-20 Michael Roth
` (66 preceding siblings ...)
2016-12-15 0:45 ` [Qemu-devel] [PATCH 67/67] vfio/pci: Fix vfio_rtl8168_quirk_data_read address offset Michael Roth
@ 2016-12-15 6:14 ` Stefan Weil
67 siblings, 0 replies; 71+ messages in thread
From: Stefan Weil @ 2016-12-15 6:14 UTC (permalink / raw)
To: Michael Roth, qemu-devel
Cc: qemu-stable, Michael S. Tsirkin, Gerd Hoffmann, Kevin Wolf
On 12/15/16 01:43, Michael Roth wrote:
> Hi everyone,
>
> The following new patches are queued for QEMU stable v2.7.1:
>
> https://github.com/mdroth/qemu/commits/stable-2.7-staging
>
> The release is planned for 2016-12-23:
>
> http://wiki.qemu.org/Planning/2.7
>
> Please respond here or CC qemu-stable@nongnu.org on any patches you
> think should be included in the release.
>
> Testing/feedback is greatly appreciated.
>
> Thanks!
http://patchwork.ozlabs.org/patch/705682/
[for-2.8] ui/gtk: fix "Copy" menu item segfault
(still missing in git)
Regards,
Stefan
^ permalink raw reply [flat|nested] 71+ messages in thread