From b8f5cfd6824ee7122e714ffc7e893432dd7beae5 Mon Sep 17 00:00:00 2001 From: Eduardo Habkost Date: Tue, 24 Jun 2014 23:04:44 -0300 Subject: pc: Move q35 compat props to PC_COMPAT_* For each compat property on PC_Q35_COMPAT_*, there are only two possibilities: * If the device is never instantiated when using a machine other than pc-q35, then the compat property can be safely added to PC_COMPAT_*; * If the device can be instantiated when using a machine other than pc-q35, that means the other machines also need the compat property to be set. That means we don't need separate PC_Q35_COMPAT_* macros at all, today. The hpet.hpet-intcap case is interesting: piix and q35 do have something that emulates different defaults, but the machine-specific default is applied _after_ compat_props are applied, by simply checking if the property is zero (which is the real default on the hpet code). The hpet.hpet-intcap=0x4 compat property can (should?) be applied to piix too, because 0x4 was the default on both piix and q35 before the hpet-intcap property was introduced. Now, if one day we change the default HPET intcap on one of the PC machine-types again, we may want to introduce PC_{Q35,I440FX}_COMPAT macros. But while we don't need that, we can keep the code simple. Signed-off-by: Eduardo Habkost Cc: Liu Ping Fan Cc: Peter Maydell Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- include/hw/i386/pc.h | 55 +++++++++++++++++----------------------------------- 1 file changed, 18 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h index 486e98feac..81718b8430 100644 --- a/include/hw/i386/pc.h +++ b/include/hw/i386/pc.h @@ -294,43 +294,6 @@ int e820_add_entry(uint64_t, uint64_t, uint32_t); int e820_get_num_entries(void); bool e820_get_entry(int, uint32_t, uint64_t *, uint64_t *); -#define PC_Q35_COMPAT_2_0 \ - PC_COMPAT_2_0, \ - {\ - .driver = "ICH9-LPC",\ - .property = "memory-hotplug-support",\ - .value = "off",\ - },{\ - .driver = "xio3130-downstream",\ - .property = COMPAT_PROP_PCP,\ - .value = "off",\ - },{\ - .driver = "ioh3420",\ - .property = COMPAT_PROP_PCP,\ - .value = "off",\ - } - -#define PC_Q35_COMPAT_1_7 \ - PC_COMPAT_1_7, \ - PC_Q35_COMPAT_2_0, \ - {\ - .driver = "hpet",\ - .property = HPET_INTCAP,\ - .value = stringify(4),\ - } - -#define PC_Q35_COMPAT_1_6 \ - PC_COMPAT_1_6, \ - PC_Q35_COMPAT_1_7 - -#define PC_Q35_COMPAT_1_5 \ - PC_COMPAT_1_5, \ - PC_Q35_COMPAT_1_6 - -#define PC_Q35_COMPAT_1_4 \ - PC_COMPAT_1_4, \ - PC_Q35_COMPAT_1_5 - #define PC_COMPAT_2_0 \ {\ .driver = "virtio-scsi-pci",\ @@ -370,6 +333,19 @@ bool e820_get_entry(int, uint32_t, uint64_t *, uint64_t *); .driver = "virtio-net-pci",\ .property = "guest_announce",\ .value = "off",\ + },\ + {\ + .driver = "ICH9-LPC",\ + .property = "memory-hotplug-support",\ + .value = "off",\ + },{\ + .driver = "xio3130-downstream",\ + .property = COMPAT_PROP_PCP,\ + .value = "off",\ + },{\ + .driver = "ioh3420",\ + .property = COMPAT_PROP_PCP,\ + .value = "off",\ } #define PC_COMPAT_1_7 \ @@ -383,6 +359,11 @@ bool e820_get_entry(int, uint32_t, uint64_t *, uint64_t *); .driver = "PIIX4_PM",\ .property = "acpi-pci-hotplug-with-bridge-support",\ .value = "off",\ + },\ + {\ + .driver = "hpet",\ + .property = HPET_INTCAP,\ + .value = stringify(4),\ } #define PC_COMPAT_1_6 \ -- cgit v1.2.3-55-g7522 From fa118d1f8be40860469e8e23745d0202bdf229ba Mon Sep 17 00:00:00 2001 From: Eduardo Habkost Date: Tue, 24 Jun 2014 19:57:55 -0300 Subject: pc: Fix "prog_if" typo on PC_COMPAT_2_0 The property name is "prog_if", not "prof_if". Signed-off-by: Eduardo Habkost Reported-by: BALATON Zoltan Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- include/hw/i386/pc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h index 81718b8430..1c0c382d8c 100644 --- a/include/hw/i386/pc.h +++ b/include/hw/i386/pc.h @@ -321,7 +321,7 @@ bool e820_get_entry(int, uint32_t, uint64_t *, uint64_t *); },\ {\ .driver = "pci-serial-2x",\ - .property = "prof_if",\ + .property = "prog_if",\ .value = stringify(0),\ },\ {\ -- cgit v1.2.3-55-g7522 From 1af878e0497a885b6cbdd3a6d91d399f4851d99c Mon Sep 17 00:00:00 2001 From: Eduardo Habkost Date: Thu, 26 Jun 2014 18:33:18 -0300 Subject: numa: Keep track of NUMA nodes present on the command-line Based on "enable sparse node numbering" patch from Nishanth Aravamudan, but without the code to actually support sparse node IDs. This just adds the code to keep track of present/non-present nodes on the command-line, without changing any behavior. Signed-off-by: Nishanth Aravamudan [Rename max_numa_node to max_numa_nodeid -Eduardo] [Initialize max_numa_nodeid to 0 -Eduardo] [Use MAX() macro when setting max_numa_nodeid -Eduardo] Signed-off-by: Eduardo Habkost Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin Reviewed-by: Hu Tao Reviewed-by: Eric Blake --- include/sysemu/sysemu.h | 7 ++++++- numa.c | 2 ++ vl.c | 3 +++ 3 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h index 285c45baf2..d8539fd602 100644 --- a/include/sysemu/sysemu.h +++ b/include/sysemu/sysemu.h @@ -146,11 +146,16 @@ extern int mem_prealloc; */ #define MAX_CPUMASK_BITS 255 -extern int nb_numa_nodes; +extern int nb_numa_nodes; /* Number of NUMA nodes */ +extern int max_numa_nodeid; /* Highest specified NUMA node ID, plus one. + * For all nodes, nodeid < max_numa_nodeid + */ + typedef struct node_info { uint64_t node_mem; DECLARE_BITMAP(node_cpu, MAX_CPUMASK_BITS); struct HostMemoryBackend *node_memdev; + bool present; } NodeInfo; extern NodeInfo numa_info[MAX_NODES]; void set_numa_nodes(void); diff --git a/numa.c b/numa.c index 6c2eae7ef3..db10f954dd 100644 --- a/numa.c +++ b/numa.c @@ -106,6 +106,8 @@ static void numa_node_parse(NumaNodeOptions *node, QemuOpts *opts, Error **errp) numa_info[nodenr].node_mem = object_property_get_int(o, "size", NULL); numa_info[nodenr].node_memdev = MEMORY_BACKEND(o); } + numa_info[nodenr].present = true; + max_numa_nodeid = MAX(max_numa_nodeid, nodenr + 1); } int numa_init_func(QemuOpts *opts, void *opaque) diff --git a/vl.c b/vl.c index a1686ef6c4..41ddcd2678 100644 --- a/vl.c +++ b/vl.c @@ -196,6 +196,7 @@ static QTAILQ_HEAD(, FWBootEntry) fw_boot_order = QTAILQ_HEAD_INITIALIZER(fw_boot_order); int nb_numa_nodes; +int max_numa_nodeid; NodeInfo numa_info[MAX_NODES]; uint8_t qemu_uuid[16]; @@ -2984,10 +2985,12 @@ int main(int argc, char **argv, char **envp) for (i = 0; i < MAX_NODES; i++) { numa_info[i].node_mem = 0; + numa_info[i].present = false; bitmap_zero(numa_info[i].node_cpu, MAX_CPUMASK_BITS); } nb_numa_nodes = 0; + max_numa_nodeid = 0; nb_nics = 0; bdrv_init_with_whitelist(); -- cgit v1.2.3-55-g7522 From 3fd74b84076488ae44ba5f3cfed22ff056c5199c Mon Sep 17 00:00:00 2001 From: Damjan Marion Date: Thu, 26 Jun 2014 23:01:32 +0200 Subject: vhost-user: fix regions provied with VHOST_USER_SET_MEM_TABLE message Old code was affected by memory gaps which resulted in buffer pointers pointing to address outside of the mapped regions. Here we are introducing following changes: - new function qemu_get_ram_block_host_ptr() returns host pointer to the ram block, it is needed to calculate offset of specific region in the host memory - new field mmap_offset is added to the VhostUserMemoryRegion. It contains offset where specific region starts in the mapped memory. As there is stil no wider adoption of vhost-user agreement was made that we will not bump version number due to this change - other fileds in VhostUserMemoryRegion struct are not changed, as they are all needed for usermode app implementation - region data is not taken from ram_list.blocks anymore, instead we use region data which is alredy calculated for use in vhost-net - Now multiple regions can have same FD and user applicaton can call mmap() multiple times with the same FD but with different offset (user needs to take care for offset page alignment) Signed-off-by: Damjan Marion Acked-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin Signed-off-by: Damjan Marion --- docs/specs/vhost-user.txt | 7 ++++--- exec.c | 7 +++++++ hw/virtio/vhost-user.c | 23 ++++++++++++++--------- include/exec/ram_addr.h | 1 + 4 files changed, 26 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/docs/specs/vhost-user.txt b/docs/specs/vhost-user.txt index 2641390244..6abb6977ff 100644 --- a/docs/specs/vhost-user.txt +++ b/docs/specs/vhost-user.txt @@ -78,13 +78,14 @@ Depending on the request type, payload can be: Padding: 32-bit A region is: - --------------------------------------- - | guest address | size | user address | - --------------------------------------- + ----------------------------------------------------- + | guest address | size | user address | mmap offset | + ----------------------------------------------------- Guest address: a 64-bit guest address of the region Size: a 64-bit size User address: a 64-bit user address + mmmap offset: 64-bit offset where region starts in the mapped memory In QEMU the vhost-user message is implemented with the following struct: diff --git a/exec.c b/exec.c index c8494051a6..a94c5832f4 100644 --- a/exec.c +++ b/exec.c @@ -1456,6 +1456,13 @@ int qemu_get_ram_fd(ram_addr_t addr) return block->fd; } +void *qemu_get_ram_block_host_ptr(ram_addr_t addr) +{ + RAMBlock *block = qemu_get_ram_block(addr); + + return block->host; +} + /* Return a host pointer to ram allocated with qemu_ram_alloc. With the exception of the softmmu code in this file, this should only be used for local memory (e.g. video ram) that the device owns, diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index 0df6a936a0..38e580642f 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -14,6 +14,7 @@ #include "sysemu/kvm.h" #include "qemu/error-report.h" #include "qemu/sockets.h" +#include "exec/ram_addr.h" #include #include @@ -47,6 +48,7 @@ typedef struct VhostUserMemoryRegion { uint64_t guest_phys_addr; uint64_t memory_size; uint64_t userspace_addr; + uint64_t mmap_offset; } VhostUserMemoryRegion; typedef struct VhostUserMemory { @@ -183,10 +185,10 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request, { VhostUserMsg msg; VhostUserRequest msg_request; - RAMBlock *block = 0; struct vhost_vring_file *file = 0; int need_reply = 0; int fds[VHOST_MEMORY_MAX_NREGIONS]; + int i, fd; size_t fd_num = 0; assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER); @@ -212,14 +214,17 @@ static int vhost_user_call(struct vhost_dev *dev, unsigned long int request, break; case VHOST_SET_MEM_TABLE: - QTAILQ_FOREACH(block, &ram_list.blocks, next) - { - if (block->fd > 0) { - msg.memory.regions[fd_num].userspace_addr = - (uintptr_t) block->host; - msg.memory.regions[fd_num].memory_size = block->length; - msg.memory.regions[fd_num].guest_phys_addr = block->offset; - fds[fd_num++] = block->fd; + for (i = 0; i < dev->mem->nregions; ++i) { + struct vhost_memory_region *reg = dev->mem->regions + i; + fd = qemu_get_ram_fd(reg->guest_phys_addr); + if (fd > 0) { + msg.memory.regions[fd_num].userspace_addr = reg->userspace_addr; + msg.memory.regions[fd_num].memory_size = reg->memory_size; + msg.memory.regions[fd_num].guest_phys_addr = reg->guest_phys_addr; + msg.memory.regions[fd_num].mmap_offset = reg->userspace_addr - + (uintptr_t) qemu_get_ram_block_host_ptr(reg->guest_phys_addr); + assert(fd_num < VHOST_MEMORY_MAX_NREGIONS); + fds[fd_num++] = fd; } } diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h index 55ca67681f..e9eb831ee3 100644 --- a/include/exec/ram_addr.h +++ b/include/exec/ram_addr.h @@ -29,6 +29,7 @@ ram_addr_t qemu_ram_alloc_from_ptr(ram_addr_t size, void *host, MemoryRegion *mr); ram_addr_t qemu_ram_alloc(ram_addr_t size, MemoryRegion *mr); int qemu_get_ram_fd(ram_addr_t addr); +void *qemu_get_ram_block_host_ptr(ram_addr_t addr); void *qemu_get_ram_ptr(ram_addr_t addr); void qemu_ram_free(ram_addr_t addr); void qemu_ram_free_from_ptr(ram_addr_t addr); -- cgit v1.2.3-55-g7522 From 1b5fc0dea469976fcbf6dc2e8f2637a2154af2fb Mon Sep 17 00:00:00 2001 From: Greg Kurz Date: Tue, 24 Jun 2014 19:15:31 +0200 Subject: virtio: introduce device specific migration calls In order to migrate virtio subsections, they should be streamed after the device itself. We need the device specific code to be called from the common migration code to achieve this. This patch introduces load and save methods for this purpose. Suggested-by: Andreas Färber Signed-off-by: Greg Kurz Reviewed-by: Alexander Graf Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/block/virtio-blk.c | 2 +- hw/char/virtio-serial-bus.c | 2 +- hw/net/virtio-net.c | 2 +- hw/scsi/virtio-scsi.c | 2 +- hw/virtio/virtio-balloon.c | 2 +- hw/virtio/virtio-rng.c | 2 +- hw/virtio/virtio.c | 13 ++++++++++++- include/hw/virtio/virtio.h | 4 +++- 8 files changed, 21 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index a222e3f9a4..5e2693a568 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -635,7 +635,7 @@ static int virtio_blk_load(QEMUFile *f, void *opaque, int version_id) if (version_id != 2) return -EINVAL; - ret = virtio_load(vdev, f); + ret = virtio_load(vdev, f, version_id); if (ret) { return ret; } diff --git a/hw/char/virtio-serial-bus.c b/hw/char/virtio-serial-bus.c index e2174b10bb..f919ec2440 100644 --- a/hw/char/virtio-serial-bus.c +++ b/hw/char/virtio-serial-bus.c @@ -670,7 +670,7 @@ static int virtio_serial_load(QEMUFile *f, void *opaque, int version_id) } /* The virtio device */ - ret = virtio_load(VIRTIO_DEVICE(s), f); + ret = virtio_load(VIRTIO_DEVICE(s), f, version_id); if (ret) { return ret; } diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index ea1a081993..acfe91ccb6 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -1362,7 +1362,7 @@ static int virtio_net_load(QEMUFile *f, void *opaque, int version_id) if (version_id < 2 || version_id > VIRTIO_NET_VM_VERSION) return -EINVAL; - ret = virtio_load(vdev, f); + ret = virtio_load(vdev, f, version_id); if (ret) { return ret; } diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c index 8c8c9d1f61..6b4fd6f625 100644 --- a/hw/scsi/virtio-scsi.c +++ b/hw/scsi/virtio-scsi.c @@ -549,7 +549,7 @@ static int virtio_scsi_load(QEMUFile *f, void *opaque, int version_id) VirtIODevice *vdev = VIRTIO_DEVICE(opaque); int ret; - ret = virtio_load(vdev, f); + ret = virtio_load(vdev, f, version_id); if (ret) { return ret; } diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c index 2a2e58a297..165592e1d7 100644 --- a/hw/virtio/virtio-balloon.c +++ b/hw/virtio/virtio-balloon.c @@ -343,7 +343,7 @@ static int virtio_balloon_load(QEMUFile *f, void *opaque, int version_id) if (version_id != 1) return -EINVAL; - ret = virtio_load(vdev, f); + ret = virtio_load(vdev, f, version_id); if (ret) { return ret; } diff --git a/hw/virtio/virtio-rng.c b/hw/virtio/virtio-rng.c index b6ab3610cb..025de81345 100644 --- a/hw/virtio/virtio-rng.c +++ b/hw/virtio/virtio-rng.c @@ -113,7 +113,7 @@ static int virtio_rng_load(QEMUFile *f, void *opaque, int version_id) if (version_id != 1) { return -EINVAL; } - virtio_load(vdev, f); + virtio_load(vdev, f, version_id); /* We may have an element ready but couldn't process it due to a quota * limit. Make sure to try again after live migration when the quota may diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c index c1d538c5f3..7f9ac5e0b9 100644 --- a/hw/virtio/virtio.c +++ b/hw/virtio/virtio.c @@ -843,6 +843,7 @@ void virtio_save(VirtIODevice *vdev, QEMUFile *f) { BusState *qbus = qdev_get_parent_bus(DEVICE(vdev)); VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); + VirtioDeviceClass *vdc = VIRTIO_DEVICE_GET_CLASS(vdev); int i; if (k->save_config) { @@ -877,6 +878,10 @@ void virtio_save(VirtIODevice *vdev, QEMUFile *f) k->save_queue(qbus->parent, i, f); } } + + if (vdc->save != NULL) { + vdc->save(vdev, f); + } } int virtio_set_features(VirtIODevice *vdev, uint32_t val) @@ -895,7 +900,7 @@ int virtio_set_features(VirtIODevice *vdev, uint32_t val) return bad ? -1 : 0; } -int virtio_load(VirtIODevice *vdev, QEMUFile *f) +int virtio_load(VirtIODevice *vdev, QEMUFile *f, int version_id) { int i, ret; int32_t config_len; @@ -904,6 +909,7 @@ int virtio_load(VirtIODevice *vdev, QEMUFile *f) uint32_t supported_features; BusState *qbus = qdev_get_parent_bus(DEVICE(vdev)); VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); + VirtioDeviceClass *vdc = VIRTIO_DEVICE_GET_CLASS(vdev); if (k->load_config) { ret = k->load_config(qbus->parent, f); @@ -983,6 +989,11 @@ int virtio_load(VirtIODevice *vdev, QEMUFile *f) } virtio_notify_vector(vdev, VIRTIO_NO_VECTOR); + + if (vdc->load != NULL) { + return vdc->load(vdev, f, version_id); + } + return 0; } diff --git a/include/hw/virtio/virtio.h b/include/hw/virtio/virtio.h index 3e54e90aad..3505ce511e 100644 --- a/include/hw/virtio/virtio.h +++ b/include/hw/virtio/virtio.h @@ -150,6 +150,8 @@ typedef struct VirtioDeviceClass { * must mask in frontend instead. */ void (*guest_notifier_mask)(VirtIODevice *vdev, int n, bool mask); + void (*save)(VirtIODevice *vdev, QEMUFile *f); + int (*load)(VirtIODevice *vdev, QEMUFile *f, int version_id); } VirtioDeviceClass; void virtio_init(VirtIODevice *vdev, const char *name, @@ -184,7 +186,7 @@ void virtio_notify(VirtIODevice *vdev, VirtQueue *vq); void virtio_save(VirtIODevice *vdev, QEMUFile *f); -int virtio_load(VirtIODevice *vdev, QEMUFile *f); +int virtio_load(VirtIODevice *vdev, QEMUFile *f, int version_id); void virtio_notify_config(VirtIODevice *vdev); -- cgit v1.2.3-55-g7522 From 98ed8ecfc9dd9e22e4251251492f062dde32c3c4 Mon Sep 17 00:00:00 2001 From: Greg Kurz Date: Tue, 24 Jun 2014 19:26:29 +0200 Subject: exec: introduce target_words_bigendian() helper We currently have a virtio_is_big_endian() helper that provides the target endianness to the virtio code. As of today, the helper returns a fixed compile-time value. Of course, this will have to change if we want to support target endianness changes at run-time. Let's move the TARGET_WORDS_BIGENDIAN bits out to a new helper and have virtio_is_big_endian() implemented on top of it. This patch doesn't change any functionality. Signed-off-by: Greg Kurz Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- exec.c | 8 ++------ hw/virtio/virtio-pci.c | 3 --- include/hw/virtio/virtio.h | 6 ++++++ 3 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/exec.c b/exec.c index a94c5832f4..18d6c35942 100644 --- a/exec.c +++ b/exec.c @@ -2759,14 +2759,12 @@ int cpu_memory_rw_debug(CPUState *cpu, target_ulong addr, } #endif -#if !defined(CONFIG_USER_ONLY) - /* * A helper function for the _utterly broken_ virtio device model to find out if * it's running on a big endian machine. Don't do this at home kids! */ -bool virtio_is_big_endian(void); -bool virtio_is_big_endian(void) +bool target_words_bigendian(void); +bool target_words_bigendian(void) { #if defined(TARGET_WORDS_BIGENDIAN) return true; @@ -2775,8 +2773,6 @@ bool virtio_is_big_endian(void) #endif } -#endif - #ifndef CONFIG_USER_ONLY bool cpu_physical_memory_is_io(hwaddr phys_addr) { diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c index 57e1e6141e..e11f759e94 100644 --- a/hw/virtio/virtio-pci.c +++ b/hw/virtio/virtio-pci.c @@ -89,9 +89,6 @@ /* Flags track per-device state like workarounds for quirks in older guests. */ #define VIRTIO_PCI_FLAG_BUS_MASTER_BUG (1 << 0) -/* HACK for virtio to determine if it's running a big endian guest */ -bool virtio_is_big_endian(void); - static void virtio_pci_bus_new(VirtioBusState *bus, size_t bus_size, VirtIOPCIProxy *dev); diff --git a/include/hw/virtio/virtio.h b/include/hw/virtio/virtio.h index 3505ce511e..9000ee2f50 100644 --- a/include/hw/virtio/virtio.h +++ b/include/hw/virtio/virtio.h @@ -255,4 +255,10 @@ void virtio_queue_set_host_notifier_fd_handler(VirtQueue *vq, bool assign, bool set_handler); void virtio_queue_notify_vq(VirtQueue *vq); void virtio_irq(VirtQueue *vq); + +bool target_words_bigendian(void); +static inline bool virtio_is_big_endian(void) +{ + return target_words_bigendian(); +} #endif -- cgit v1.2.3-55-g7522 From bf7663c4bd8f8f619d6dbb5780025d92ace250a8 Mon Sep 17 00:00:00 2001 From: Greg Kurz Date: Tue, 24 Jun 2014 19:33:21 +0200 Subject: cpu: introduce CPUClass::virtio_is_big_endian() If we want to support targets that can change endianness (modern PPC and ARM for the moment), we need to add a per-CPU class method to be called from the virtio code. The virtio_ prefix in the name is a hint for people to avoid misusage (aka. anywhere but from the virtio code). The default behaviour is to return the compile-time default target endianness. Suggested-by: Peter Maydell Signed-off-by: Greg Kurz Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- include/qom/cpu.h | 1 + qom/cpu.c | 6 ++++++ 2 files changed, 7 insertions(+) (limited to 'include') diff --git a/include/qom/cpu.h b/include/qom/cpu.h index 4b352a28fa..1aafbf5f34 100644 --- a/include/qom/cpu.h +++ b/include/qom/cpu.h @@ -116,6 +116,7 @@ typedef struct CPUClass { CPUUnassignedAccess do_unassigned_access; void (*do_unaligned_access)(CPUState *cpu, vaddr addr, int is_write, int is_user, uintptr_t retaddr); + bool (*virtio_is_big_endian)(CPUState *cpu); int (*memory_rw_debug)(CPUState *cpu, vaddr addr, uint8_t *buf, int len, bool is_write); void (*dump_state)(CPUState *cpu, FILE *f, fprintf_function cpu_fprintf, diff --git a/qom/cpu.c b/qom/cpu.c index fada2d4b92..b32dd0a562 100644 --- a/qom/cpu.c +++ b/qom/cpu.c @@ -196,6 +196,11 @@ static int cpu_common_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg) return 0; } +bool target_words_bigendian(void); +static bool cpu_common_virtio_is_big_endian(CPUState *cpu) +{ + return target_words_bigendian(); +} void cpu_dump_state(CPUState *cpu, FILE *f, fprintf_function cpu_fprintf, int flags) @@ -334,6 +339,7 @@ static void cpu_class_init(ObjectClass *klass, void *data) k->write_elf64_note = cpu_common_write_elf64_note; k->gdb_read_register = cpu_common_gdb_read_register; k->gdb_write_register = cpu_common_gdb_write_register; + k->virtio_is_big_endian = cpu_common_virtio_is_big_endian; dc->realize = cpu_common_realizefn; /* * Reason: CPUs still need special care by board code: wiring up -- cgit v1.2.3-55-g7522 From 616a655219a92ae7cf5d6a7862e6489c6282009e Mon Sep 17 00:00:00 2001 From: Greg Kurz Date: Tue, 24 Jun 2014 19:38:54 +0200 Subject: virtio: add endian-ambivalent support to VirtIODevice Some CPU families can dynamically change their endianness. This means we can have little endian ppc or big endian arm guests for example. This has an impact on legacy virtio data structures since they are target endian. We hence introduce a new property to track the endianness of each virtio device. It is reasonnably assumed that endianness won't change while the device is in use : we hence capture the device endianness when it gets reset. We migrate this property in a subsection, after the device descriptor. This means the load code must not rely on it until it is restored. As a consequence, the vring sanity checks had to be moved after the call to vmstate_load_state(). We enforce paranoia by poisoning the property at the begining of virtio_load(). Signed-off-by: Greg Kurz Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/virtio/virtio-pci.c | 8 ++-- hw/virtio/virtio.c | 99 ++++++++++++++++++++++++++++++++++++++++------ include/hw/virtio/virtio.h | 13 ++++-- 3 files changed, 101 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c index e11f759e94..317324f23d 100644 --- a/hw/virtio/virtio-pci.c +++ b/hw/virtio/virtio-pci.c @@ -406,13 +406,13 @@ static uint64_t virtio_pci_config_read(void *opaque, hwaddr addr, break; case 2: val = virtio_config_readw(vdev, addr); - if (virtio_is_big_endian()) { + if (virtio_is_big_endian(vdev)) { val = bswap16(val); } break; case 4: val = virtio_config_readl(vdev, addr); - if (virtio_is_big_endian()) { + if (virtio_is_big_endian(vdev)) { val = bswap32(val); } break; @@ -440,13 +440,13 @@ static void virtio_pci_config_write(void *opaque, hwaddr addr, virtio_config_writeb(vdev, addr, val); break; case 2: - if (virtio_is_big_endian()) { + if (virtio_is_big_endian(vdev)) { val = bswap16(val); } virtio_config_writew(vdev, addr, val); break; case 4: - if (virtio_is_big_endian()) { + if (virtio_is_big_endian(vdev)) { val = bswap32(val); } virtio_config_writel(vdev, addr, val); diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c index 7b317ce279..a0676e06af 100644 --- a/hw/virtio/virtio.c +++ b/hw/virtio/virtio.c @@ -545,6 +545,27 @@ void virtio_set_status(VirtIODevice *vdev, uint8_t val) vdev->status = val; } +bool target_words_bigendian(void); +static enum virtio_device_endian virtio_default_endian(void) +{ + if (target_words_bigendian()) { + return VIRTIO_DEVICE_ENDIAN_BIG; + } else { + return VIRTIO_DEVICE_ENDIAN_LITTLE; + } +} + +static enum virtio_device_endian virtio_current_cpu_endian(void) +{ + CPUClass *cc = CPU_GET_CLASS(current_cpu); + + if (cc->virtio_is_big_endian(current_cpu)) { + return VIRTIO_DEVICE_ENDIAN_BIG; + } else { + return VIRTIO_DEVICE_ENDIAN_LITTLE; + } +} + void virtio_reset(void *opaque) { VirtIODevice *vdev = opaque; @@ -552,6 +573,13 @@ void virtio_reset(void *opaque) int i; virtio_set_status(vdev, 0); + if (current_cpu) { + /* Guest initiated reset */ + vdev->device_endian = virtio_current_cpu_endian(); + } else { + /* System reset */ + vdev->device_endian = virtio_default_endian(); + } if (k->reset) { k->reset(vdev); @@ -840,6 +868,24 @@ void virtio_notify_config(VirtIODevice *vdev) virtio_notify_vector(vdev, vdev->config_vector); } +static bool virtio_device_endian_needed(void *opaque) +{ + VirtIODevice *vdev = opaque; + + assert(vdev->device_endian != VIRTIO_DEVICE_ENDIAN_UNKNOWN); + return vdev->device_endian != virtio_default_endian(); +} + +static const VMStateDescription vmstate_virtio_device_endian = { + .name = "virtio/device_endian", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT8(device_endian, VirtIODevice), + VMSTATE_END_OF_LIST() + } +}; + static const VMStateDescription vmstate_virtio = { .name = "virtio", .version_id = 1, @@ -847,6 +893,13 @@ static const VMStateDescription vmstate_virtio = { .minimum_version_id_old = 1, .fields = (VMStateField[]) { VMSTATE_END_OF_LIST() + }, + .subsections = (VMStateSubsection[]) { + { + .vmsd = &vmstate_virtio_device_endian, + .needed = &virtio_device_endian_needed + }, + { 0 } } }; @@ -925,6 +978,12 @@ int virtio_load(VirtIODevice *vdev, QEMUFile *f, int version_id) VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); VirtioDeviceClass *vdc = VIRTIO_DEVICE_GET_CLASS(vdev); + /* + * We poison the endianness to ensure it does not get used before + * subsections have been loaded. + */ + vdev->device_endian = VIRTIO_DEVICE_ENDIAN_UNKNOWN; + if (k->load_config) { ret = k->load_config(qbus->parent, f); if (ret) @@ -977,18 +1036,7 @@ int virtio_load(VirtIODevice *vdev, QEMUFile *f, int version_id) vdev->vq[i].notification = true; if (vdev->vq[i].pa) { - uint16_t nheads; virtqueue_init(&vdev->vq[i]); - nheads = vring_avail_idx(&vdev->vq[i]) - vdev->vq[i].last_avail_idx; - /* Check it isn't doing very strange things with descriptor numbers. */ - if (nheads > vdev->vq[i].vring.num) { - error_report("VQ %d size 0x%x Guest index 0x%x " - "inconsistent with Host index 0x%x: delta 0x%x", - i, vdev->vq[i].vring.num, - vring_avail_idx(&vdev->vq[i]), - vdev->vq[i].last_avail_idx, nheads); - return -1; - } } else if (vdev->vq[i].last_avail_idx) { error_report("VQ %d address 0x0 " "inconsistent with Host index 0x%x", @@ -1011,7 +1059,33 @@ int virtio_load(VirtIODevice *vdev, QEMUFile *f, int version_id) } } - return vmstate_load_state(f, &vmstate_virtio, vdev, 1); + /* Subsections */ + ret = vmstate_load_state(f, &vmstate_virtio, vdev, 1); + if (ret) { + return ret; + } + + if (vdev->device_endian == VIRTIO_DEVICE_ENDIAN_UNKNOWN) { + vdev->device_endian = virtio_default_endian(); + } + + for (i = 0; i < num; i++) { + if (vdev->vq[i].pa) { + uint16_t nheads; + nheads = vring_avail_idx(&vdev->vq[i]) - vdev->vq[i].last_avail_idx; + /* Check it isn't doing strange things with descriptor numbers. */ + if (nheads > vdev->vq[i].vring.num) { + error_report("VQ %d size 0x%x Guest index 0x%x " + "inconsistent with Host index 0x%x: delta 0x%x", + i, vdev->vq[i].vring.num, + vring_avail_idx(&vdev->vq[i]), + vdev->vq[i].last_avail_idx, nheads); + return -1; + } + } + } + + return 0; } void virtio_cleanup(VirtIODevice *vdev) @@ -1068,6 +1142,7 @@ void virtio_init(VirtIODevice *vdev, const char *name, } vdev->vmstate = qemu_add_vm_change_state_handler(virtio_vmstate_change, vdev); + vdev->device_endian = virtio_default_endian(); } hwaddr virtio_queue_get_desc_addr(VirtIODevice *vdev, int n) diff --git a/include/hw/virtio/virtio.h b/include/hw/virtio/virtio.h index 9000ee2f50..a60104ca24 100644 --- a/include/hw/virtio/virtio.h +++ b/include/hw/virtio/virtio.h @@ -104,6 +104,12 @@ typedef struct VirtQueueElement #define VIRTIO_DEVICE(obj) \ OBJECT_CHECK(VirtIODevice, (obj), TYPE_VIRTIO_DEVICE) +enum virtio_device_endian { + VIRTIO_DEVICE_ENDIAN_UNKNOWN, + VIRTIO_DEVICE_ENDIAN_LITTLE, + VIRTIO_DEVICE_ENDIAN_BIG, +}; + struct VirtIODevice { DeviceState parent_obj; @@ -121,6 +127,7 @@ struct VirtIODevice bool vm_running; VMChangeStateEntry *vmstate; char *bus_name; + uint8_t device_endian; }; typedef struct VirtioDeviceClass { @@ -256,9 +263,9 @@ void virtio_queue_set_host_notifier_fd_handler(VirtQueue *vq, bool assign, void virtio_queue_notify_vq(VirtQueue *vq); void virtio_irq(VirtQueue *vq); -bool target_words_bigendian(void); -static inline bool virtio_is_big_endian(void) +static inline bool virtio_is_big_endian(VirtIODevice *vdev) { - return target_words_bigendian(); + assert(vdev->device_endian != VIRTIO_DEVICE_ENDIAN_UNKNOWN); + return vdev->device_endian == VIRTIO_DEVICE_ENDIAN_BIG; } #endif -- cgit v1.2.3-55-g7522 From 0f5d1d2a49778863db54b4b1ac2dc008a8f21f11 Mon Sep 17 00:00:00 2001 From: Greg Kurz Date: Tue, 24 Jun 2014 19:39:55 +0200 Subject: virtio: memory accessors for endian-ambivalent targets This is the virtio-access.h header file taken from Rusty's "endian-ambivalent targets using legacy virtio" patch. It introduces helpers that should be used when accessing vring data or by drivers for data that contains headers. The virtio config space is also target endian, but the current code already handles that with the virtio_is_big_endian() helper. There is no obvious benefit at using the virtio accessors in this case. Now we have two distinct paths: a fast inline one for fixed endian targets, and a slow out-of-line one for targets that define the new TARGET_IS_BIENDIAN macro. Signed-off-by: Rusty Russell [ relicensed virtio-access.h to GPLv2+ on Rusty's request, pass &address_space_memory to physical memory accessors, per-device endianness, virtio tswap16 and tswap64 helpers, faspath for fixed endian targets, Greg Kurz ] Cc: Cédric Le Goater Signed-off-by: Greg Kurz Reviewed-by: Alexander Graf Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- include/hw/virtio/virtio-access.h | 170 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 170 insertions(+) create mode 100644 include/hw/virtio/virtio-access.h (limited to 'include') diff --git a/include/hw/virtio/virtio-access.h b/include/hw/virtio/virtio-access.h new file mode 100644 index 0000000000..46456fd9da --- /dev/null +++ b/include/hw/virtio/virtio-access.h @@ -0,0 +1,170 @@ +/* + * Virtio Accessor Support: In case your target can change endian. + * + * Copyright IBM, Corp. 2013 + * + * Authors: + * Rusty Russell + * + * 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. + * + */ +#ifndef _QEMU_VIRTIO_ACCESS_H +#define _QEMU_VIRTIO_ACCESS_H +#include "hw/virtio/virtio.h" +#include "exec/address-spaces.h" + +static inline bool virtio_access_is_big_endian(VirtIODevice *vdev) +{ +#if defined(TARGET_IS_BIENDIAN) + return virtio_is_big_endian(vdev); +#elif defined(TARGET_WORDS_BIGENDIAN) + return true; +#else + return false; +#endif +} + +static inline uint16_t virtio_lduw_phys(VirtIODevice *vdev, hwaddr pa) +{ + if (virtio_access_is_big_endian(vdev)) { + return lduw_be_phys(&address_space_memory, pa); + } + return lduw_le_phys(&address_space_memory, pa); +} + +static inline uint32_t virtio_ldl_phys(VirtIODevice *vdev, hwaddr pa) +{ + if (virtio_access_is_big_endian(vdev)) { + return ldl_be_phys(&address_space_memory, pa); + } + return ldl_le_phys(&address_space_memory, pa); +} + +static inline uint64_t virtio_ldq_phys(VirtIODevice *vdev, hwaddr pa) +{ + if (virtio_access_is_big_endian(vdev)) { + return ldq_be_phys(&address_space_memory, pa); + } + return ldq_le_phys(&address_space_memory, pa); +} + +static inline void virtio_stw_phys(VirtIODevice *vdev, hwaddr pa, + uint16_t value) +{ + if (virtio_access_is_big_endian(vdev)) { + stw_be_phys(&address_space_memory, pa, value); + } else { + stw_le_phys(&address_space_memory, pa, value); + } +} + +static inline void virtio_stl_phys(VirtIODevice *vdev, hwaddr pa, + uint32_t value) +{ + if (virtio_access_is_big_endian(vdev)) { + stl_be_phys(&address_space_memory, pa, value); + } else { + stl_le_phys(&address_space_memory, pa, value); + } +} + +static inline void virtio_stw_p(VirtIODevice *vdev, void *ptr, uint16_t v) +{ + if (virtio_access_is_big_endian(vdev)) { + stw_be_p(ptr, v); + } else { + stw_le_p(ptr, v); + } +} + +static inline void virtio_stl_p(VirtIODevice *vdev, void *ptr, uint32_t v) +{ + if (virtio_access_is_big_endian(vdev)) { + stl_be_p(ptr, v); + } else { + stl_le_p(ptr, v); + } +} + +static inline void virtio_stq_p(VirtIODevice *vdev, void *ptr, uint64_t v) +{ + if (virtio_access_is_big_endian(vdev)) { + stq_be_p(ptr, v); + } else { + stq_le_p(ptr, v); + } +} + +static inline int virtio_lduw_p(VirtIODevice *vdev, const void *ptr) +{ + if (virtio_access_is_big_endian(vdev)) { + return lduw_be_p(ptr); + } else { + return lduw_le_p(ptr); + } +} + +static inline int virtio_ldl_p(VirtIODevice *vdev, const void *ptr) +{ + if (virtio_access_is_big_endian(vdev)) { + return ldl_be_p(ptr); + } else { + return ldl_le_p(ptr); + } +} + +static inline uint64_t virtio_ldq_p(VirtIODevice *vdev, const void *ptr) +{ + if (virtio_access_is_big_endian(vdev)) { + return ldq_be_p(ptr); + } else { + return ldq_le_p(ptr); + } +} + +static inline uint16_t virtio_tswap16(VirtIODevice *vdev, uint16_t s) +{ +#ifdef HOST_WORDS_BIGENDIAN + return virtio_access_is_big_endian(vdev) ? s : bswap16(s); +#else + return virtio_access_is_big_endian(vdev) ? bswap16(s) : s; +#endif +} + +static inline void virtio_tswap16s(VirtIODevice *vdev, uint16_t *s) +{ + *s = virtio_tswap16(vdev, *s); +} + +static inline uint32_t virtio_tswap32(VirtIODevice *vdev, uint32_t s) +{ +#ifdef HOST_WORDS_BIGENDIAN + return virtio_access_is_big_endian(vdev) ? s : bswap32(s); +#else + return virtio_access_is_big_endian(vdev) ? bswap32(s) : s; +#endif +} + +static inline void virtio_tswap32s(VirtIODevice *vdev, uint32_t *s) +{ + *s = virtio_tswap32(vdev, *s); +} + +static inline uint64_t virtio_tswap64(VirtIODevice *vdev, uint64_t s) +{ +#ifdef HOST_WORDS_BIGENDIAN + return virtio_access_is_big_endian(vdev) ? s : bswap64(s); +#else + return virtio_access_is_big_endian(vdev) ? bswap64(s) : s; +#endif +} + +static inline void virtio_tswap64s(VirtIODevice *vdev, uint64_t *s) +{ + *s = virtio_tswap64(vdev, *s); +} +#endif /* _QEMU_VIRTIO_ACCESS_H */ -- cgit v1.2.3-55-g7522