diff options
Diffstat (limited to 'hw')
57 files changed, 877 insertions, 1320 deletions
diff --git a/hw/9pfs/9p-synth.h b/hw/9pfs/9p-synth.h index eaf5a0c293..82962512a1 100644 --- a/hw/9pfs/9p-synth.h +++ b/hw/9pfs/9p-synth.h @@ -13,9 +13,6 @@ #ifndef HW_9PFS_SYNTH_H #define HW_9PFS_SYNTH_H 1 -#include <unistd.h> -#include <sys/types.h> -#include <limits.h> typedef struct V9fsSynthNode V9fsSynthNode; typedef ssize_t (*v9fs_synth_read)(void *buf, int len, off_t offset, diff --git a/hw/9pfs/9p.h b/hw/9pfs/9p.h index edcd51be15..1a19418a8c 100644 --- a/hw/9pfs/9p.h +++ b/hw/9pfs/9p.h @@ -1,9 +1,7 @@ #ifndef _QEMU_9P_H #define _QEMU_9P_H -#include <sys/types.h> #include <dirent.h> -#include <sys/time.h> #include <utime.h> #include <sys/resource.h> #include <glib.h> diff --git a/hw/acpi/aml-build.c b/hw/acpi/aml-build.c index 603068b5ea..667553514e 100644 --- a/hw/acpi/aml-build.c +++ b/hw/acpi/aml-build.c @@ -1451,7 +1451,7 @@ build_header(GArray *linker, GArray *table_data, h->checksum = 0; /* Checksum to be filled in by Guest linker */ bios_linker_loader_add_checksum(linker, ACPI_BUILD_TABLE_FILE, - table_data->data, h, len, &h->checksum); + table_data, h, len, &h->checksum); } void *acpi_data_push(GArray *table_data, unsigned size) diff --git a/hw/acpi/bios-linker-loader.c b/hw/acpi/bios-linker-loader.c index e04d60ad3f..ace9abbd3e 100644 --- a/hw/acpi/bios-linker-loader.c +++ b/hw/acpi/bios-linker-loader.c @@ -25,6 +25,13 @@ #include "qemu/bswap.h" +/* + * Linker/loader is a paravirtualized interface that passes commands to guest. + * The commands can be used to request guest to + * - allocate memory chunks and initialize them from QEMU FW CFG files + * - link allocated chunks by storing pointer to one chunk into another + * - calculate ACPI checksum of part of the chunk and store into same chunk + */ #define BIOS_LINKER_LOADER_FILESZ FW_CFG_MAX_FILE_PATH struct BiosLinkerLoaderEntry { @@ -88,6 +95,12 @@ enum { BIOS_LINKER_LOADER_ALLOC_ZONE_FSEG = 0x2, }; +/* + * bios_linker_loader_init: allocate a new linker file blob array. + * + * After initialization, linker commands can be added, and will + * be stored in the array. + */ GArray *bios_linker_loader_init(void) { return g_array_new(false, true /* clear */, 1); @@ -99,6 +112,16 @@ void *bios_linker_loader_cleanup(GArray *linker) return g_array_free(linker, false); } +/* + * bios_linker_loader_alloc: ask guest to load file into guest memory. + * + * @linker: linker file blob array + * @file: file to be loaded + * @alloc_align: required minimal alignment in bytes. Must be a power of 2. + * @alloc_fseg: request allocation in FSEG zone (useful for the RSDP ACPI table) + * + * Note: this command must precede any other linker command using this file. + */ void bios_linker_loader_alloc(GArray *linker, const char *file, uint32_t alloc_align, @@ -106,6 +129,8 @@ void bios_linker_loader_alloc(GArray *linker, { BiosLinkerLoaderEntry entry; + assert(!(alloc_align & (alloc_align - 1))); + memset(&entry, 0, sizeof entry); strncpy(entry.alloc.file, file, sizeof entry.alloc.file - 1); entry.command = cpu_to_le32(BIOS_LINKER_LOADER_COMMAND_ALLOCATE); @@ -118,23 +143,77 @@ void bios_linker_loader_alloc(GArray *linker, g_array_prepend_vals(linker, &entry, sizeof entry); } +/* + * bios_linker_loader_add_checksum: ask guest to add checksum of file data + * into (same) file at the specified pointer. + * + * Checksum calculation simply sums -X for each byte X in the range + * using 8-bit math (i.e. ACPI checksum). + * + * @linker: linker file blob array + * @file: file that includes the checksum to be calculated + * and the data to be checksummed + * @table: @file blob contents + * @start, @size: range of data to checksum + * @checksum: location of the checksum to be patched within file blob + * + * Notes: + * - checksum byte initial value must have been pushed into @table + * and reside at address @checksum. + * - @size bytes must have been pushed into @table and reside at address + * @start. + * - Guest calculates checksum of specified range of data, result is added to + * initial value at @checksum into copy of @file in Guest memory. + * - Range might include the checksum itself. + * - To avoid confusion, caller must always put 0x0 at @checksum. + * - @file must be loaded into Guest memory using bios_linker_loader_alloc + */ void bios_linker_loader_add_checksum(GArray *linker, const char *file, - void *table, + GArray *table, void *start, unsigned size, uint8_t *checksum) { BiosLinkerLoaderEntry entry; + ptrdiff_t checksum_offset = (gchar *)checksum - table->data; + ptrdiff_t start_offset = (gchar *)start - table->data; + + assert(checksum_offset >= 0); + assert(start_offset >= 0); + assert(checksum_offset + 1 <= table->len); + assert(start_offset + size <= table->len); + assert(*checksum == 0x0); memset(&entry, 0, sizeof entry); strncpy(entry.cksum.file, file, sizeof entry.cksum.file - 1); entry.command = cpu_to_le32(BIOS_LINKER_LOADER_COMMAND_ADD_CHECKSUM); - entry.cksum.offset = cpu_to_le32(checksum - (uint8_t *)table); - entry.cksum.start = cpu_to_le32((uint8_t *)start - (uint8_t *)table); + entry.cksum.offset = cpu_to_le32(checksum_offset); + entry.cksum.start = cpu_to_le32(start_offset); entry.cksum.length = cpu_to_le32(size); g_array_append_vals(linker, &entry, sizeof entry); } +/* + * bios_linker_loader_add_pointer: ask guest to add address of source file + * into destination file at the specified pointer. + * + * @linker: linker file blob array + * @dest_file: destination file that must be changed + * @src_file: source file who's address must be taken + * @table: @dest_file blob contents array + * @pointer: location of the pointer to be patched within destination file blob + * @pointer_size: size of pointer to be patched, in bytes + * + * Notes: + * - @pointer_size bytes must have been pushed into @table + * and reside at address @pointer. + * - Guest address is added to initial value at @pointer + * into copy of @dest_file in Guest memory. + * e.g. to get start of src_file in guest memory, put 0x0 there + * to get address of a field at offset 0x10 in src_file, put 0x10 there + * - Both @dest_file and @src_file must be + * loaded into Guest memory using bios_linker_loader_alloc + */ void bios_linker_loader_add_pointer(GArray *linker, const char *dest_file, const char *src_file, @@ -142,7 +221,10 @@ void bios_linker_loader_add_pointer(GArray *linker, uint8_t pointer_size) { BiosLinkerLoaderEntry entry; - size_t offset = (gchar *)pointer - table->data; + ptrdiff_t offset = (gchar *)pointer - table->data; + + assert(offset >= 0); + assert(offset + pointer_size <= table->len); memset(&entry, 0, sizeof entry); strncpy(entry.pointer.dest_file, dest_file, @@ -150,7 +232,6 @@ void bios_linker_loader_add_pointer(GArray *linker, strncpy(entry.pointer.src_file, src_file, sizeof entry.pointer.src_file - 1); entry.command = cpu_to_le32(BIOS_LINKER_LOADER_COMMAND_ADD_POINTER); - assert(table->len >= offset + pointer_size); entry.pointer.offset = cpu_to_le32(offset); entry.pointer.size = pointer_size; assert(pointer_size == 1 || pointer_size == 2 || diff --git a/hw/acpi/ich9.c b/hw/acpi/ich9.c index 4f9ce05d04..72202545e0 100644 --- a/hw/acpi/ich9.c +++ b/hw/acpi/ich9.c @@ -240,7 +240,7 @@ static void pm_powerdown_req(Notifier *n, void *opaque) } void ich9_pm_init(PCIDevice *lpc_pci, ICH9LPCPMRegs *pm, - bool smm_enabled, bool enable_tco, + bool smm_enabled, qemu_irq sci_irq) { memory_region_init(&pm->io, OBJECT(lpc_pci), "ich9-pm", ICH9_PMIO_SIZE); @@ -264,10 +264,8 @@ void ich9_pm_init(PCIDevice *lpc_pci, ICH9LPCPMRegs *pm, pm->smm_enabled = smm_enabled; - pm->enable_tco = enable_tco; - if (pm->enable_tco) { - acpi_pm_tco_init(&pm->tco_regs, &pm->io); - } + pm->enable_tco = true; + acpi_pm_tco_init(&pm->tco_regs, &pm->io); pm->irq = sci_irq; qemu_register_reset(pm_reset, pm); diff --git a/hw/arm/boot.c b/hw/arm/boot.c index cce8c7cd1c..0a56d34cfe 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -437,8 +437,10 @@ static int load_dtb(hwaddr addr, const struct arm_boot_info *binfo, return 0; } - acells = qemu_fdt_getprop_cell(fdt, "/", "#address-cells"); - scells = qemu_fdt_getprop_cell(fdt, "/", "#size-cells"); + acells = qemu_fdt_getprop_cell(fdt, "/", "#address-cells", + NULL, &error_fatal); + scells = qemu_fdt_getprop_cell(fdt, "/", "#size-cells", + NULL, &error_fatal); if (acells == 0 || scells == 0) { fprintf(stderr, "dtb file invalid (#address-cells or #size-cells 0)\n"); goto fail; diff --git a/hw/arm/sysbus-fdt.c b/hw/arm/sysbus-fdt.c index 68a3de5cf8..04afeae226 100644 --- a/hw/arm/sysbus-fdt.c +++ b/hw/arm/sysbus-fdt.c @@ -22,6 +22,11 @@ */ #include "qemu/osdep.h" +#include <libfdt.h> +#include "qemu-common.h" +#ifdef CONFIG_LINUX +#include <linux/vfio.h> +#endif #include "hw/arm/sysbus-fdt.h" #include "qemu/error-report.h" #include "sysemu/device_tree.h" @@ -29,6 +34,7 @@ #include "sysemu/sysemu.h" #include "hw/vfio/vfio-platform.h" #include "hw/vfio/vfio-calxeda-xgmac.h" +#include "hw/vfio/vfio-amd-xgbe.h" #include "hw/arm/fdt.h" /* @@ -57,6 +63,146 @@ typedef struct NodeCreationPair { int (*add_fdt_node_fn)(SysBusDevice *sbdev, void *opaque); } NodeCreationPair; +/* helpers */ + +typedef struct HostProperty { + const char *name; + bool optional; +} HostProperty; + +#ifdef CONFIG_LINUX + +/** + * copy_properties_from_host + * + * copies properties listed in an array from host device tree to + * guest device tree. If a non optional property is not found, the + * function asserts. An optional property is ignored if not found + * in the host device tree. + * @props: array of HostProperty to copy + * @nb_props: number of properties in the array + * @host_dt: host device tree blob + * @guest_dt: guest device tree blob + * @node_path: host dt node path where the property is supposed to be + found + * @nodename: guest node name the properties should be added to + */ +static void copy_properties_from_host(HostProperty *props, int nb_props, + void *host_fdt, void *guest_fdt, + char *node_path, char *nodename) +{ + int i, prop_len; + const void *r; + Error *err = NULL; + + for (i = 0; i < nb_props; i++) { + r = qemu_fdt_getprop(host_fdt, node_path, + props[i].name, + &prop_len, + props[i].optional ? &err : &error_fatal); + if (r) { + qemu_fdt_setprop(guest_fdt, nodename, + props[i].name, r, prop_len); + } else { + if (prop_len != -FDT_ERR_NOTFOUND) { + /* optional property not returned although property exists */ + error_report_err(err); + } else { + error_free(err); + } + } + } +} + +/* clock properties whose values are copied/pasted from host */ +static HostProperty clock_copied_properties[] = { + {"compatible", false}, + {"#clock-cells", false}, + {"clock-frequency", true}, + {"clock-output-names", true}, +}; + +/** + * fdt_build_clock_node + * + * Build a guest clock node, used as a dependency from a passthrough'ed + * device. Most information are retrieved from the host clock node. + * Also check the host clock is a fixed one. + * + * @host_fdt: host device tree blob from which info are retrieved + * @guest_fdt: guest device tree blob where the clock node is added + * @host_phandle: phandle of the clock in host device tree + * @guest_phandle: phandle to assign to the guest node + */ +static void fdt_build_clock_node(void *host_fdt, void *guest_fdt, + uint32_t host_phandle, + uint32_t guest_phandle) +{ + char *node_path = NULL; + char *nodename; + const void *r; + int ret, node_offset, prop_len, path_len = 16; + + node_offset = fdt_node_offset_by_phandle(host_fdt, host_phandle); + if (node_offset <= 0) { + error_setg(&error_fatal, + "not able to locate clock handle %d in host device tree", + host_phandle); + } + node_path = g_malloc(path_len); + while ((ret = fdt_get_path(host_fdt, node_offset, node_path, path_len)) + == -FDT_ERR_NOSPACE) { + path_len += 16; + node_path = g_realloc(node_path, path_len); + } + if (ret < 0) { + error_setg(&error_fatal, + "not able to retrieve node path for clock handle %d", + host_phandle); + } + + r = qemu_fdt_getprop(host_fdt, node_path, "compatible", &prop_len, + &error_fatal); + if (strcmp(r, "fixed-clock")) { + error_setg(&error_fatal, + "clock handle %d is not a fixed clock", host_phandle); + } + + nodename = strrchr(node_path, '/'); + qemu_fdt_add_subnode(guest_fdt, nodename); + + copy_properties_from_host(clock_copied_properties, + ARRAY_SIZE(clock_copied_properties), + host_fdt, guest_fdt, + node_path, nodename); + + qemu_fdt_setprop_cell(guest_fdt, nodename, "phandle", guest_phandle); + + g_free(node_path); +} + +/** + * sysfs_to_dt_name: convert the name found in sysfs into the node name + * for instance e0900000.xgmac is converted into xgmac@e0900000 + * @sysfs_name: directory name in sysfs + * + * returns the device tree name upon success or NULL in case the sysfs name + * does not match the expected format + */ +static char *sysfs_to_dt_name(const char *sysfs_name) +{ + gchar **substrings = g_strsplit(sysfs_name, ".", 2); + char *dt_name = NULL; + + if (!substrings || !substrings[0] || !substrings[1]) { + goto out; + } + dt_name = g_strdup_printf("%s@%s", substrings[1], substrings[0]); +out: + g_strfreev(substrings); + return dt_name; +} + /* Device Specific Code */ /** @@ -71,7 +217,7 @@ static int add_calxeda_midway_xgmac_fdt_node(SysBusDevice *sbdev, void *opaque) PlatformBusDevice *pbus = data->pbus; void *fdt = data->fdt; const char *parent_node = data->pbus_node_name; - int compat_str_len, i, ret = -1; + int compat_str_len, i; char *nodename; uint32_t *irq_attr, *reg_attr; uint64_t mmio_base, irq_number; @@ -96,12 +242,8 @@ static int add_calxeda_midway_xgmac_fdt_node(SysBusDevice *sbdev, void *opaque) reg_attr[2 * i + 1] = cpu_to_be32( memory_region_size(&vdev->regions[i]->mem)); } - ret = qemu_fdt_setprop(fdt, nodename, "reg", reg_attr, - vbasedev->num_regions * 2 * sizeof(uint32_t)); - if (ret) { - error_report("could not set reg property of node %s", nodename); - goto fail_reg; - } + qemu_fdt_setprop(fdt, nodename, "reg", reg_attr, + vbasedev->num_regions * 2 * sizeof(uint32_t)); irq_attr = g_new(uint32_t, vbasedev->num_irqs * 3); for (i = 0; i < vbasedev->num_irqs; i++) { @@ -111,22 +253,173 @@ static int add_calxeda_midway_xgmac_fdt_node(SysBusDevice *sbdev, void *opaque) irq_attr[3 * i + 1] = cpu_to_be32(irq_number); irq_attr[3 * i + 2] = cpu_to_be32(GIC_FDT_IRQ_FLAGS_LEVEL_HI); } - ret = qemu_fdt_setprop(fdt, nodename, "interrupts", + qemu_fdt_setprop(fdt, nodename, "interrupts", irq_attr, vbasedev->num_irqs * 3 * sizeof(uint32_t)); - if (ret) { - error_report("could not set interrupts property of node %s", - nodename); + g_free(irq_attr); + g_free(reg_attr); + g_free(nodename); + return 0; +} + +/* AMD xgbe properties whose values are copied/pasted from host */ +static HostProperty amd_xgbe_copied_properties[] = { + {"compatible", false}, + {"dma-coherent", true}, + {"amd,per-channel-interrupt", true}, + {"phy-mode", false}, + {"mac-address", true}, + {"amd,speed-set", false}, + {"amd,serdes-blwc", true}, + {"amd,serdes-cdr-rate", true}, + {"amd,serdes-pq-skew", true}, + {"amd,serdes-tx-amp", true}, + {"amd,serdes-dfe-tap-config", true}, + {"amd,serdes-dfe-tap-enable", true}, + {"clock-names", false}, +}; + +/** + * add_amd_xgbe_fdt_node + * + * Generates the combined xgbe/phy node following kernel >=4.2 + * binding documentation: + * Documentation/devicetree/bindings/net/amd-xgbe.txt: + * Also 2 clock nodes are created (dma and ptp) + * + * Asserts in case of error + */ +static int add_amd_xgbe_fdt_node(SysBusDevice *sbdev, void *opaque) +{ + PlatformBusFDTData *data = opaque; + PlatformBusDevice *pbus = data->pbus; + VFIOPlatformDevice *vdev = VFIO_PLATFORM_DEVICE(sbdev); + VFIODevice *vbasedev = &vdev->vbasedev; + VFIOINTp *intp; + const char *parent_node = data->pbus_node_name; + char **node_path, *nodename, *dt_name; + void *guest_fdt = data->fdt, *host_fdt; + const void *r; + int i, prop_len; + uint32_t *irq_attr, *reg_attr, *host_clock_phandles; + uint64_t mmio_base, irq_number; + uint32_t guest_clock_phandles[2]; + + host_fdt = load_device_tree_from_sysfs(); + + dt_name = sysfs_to_dt_name(vbasedev->name); + if (!dt_name) { + error_setg(&error_fatal, "%s incorrect sysfs device name %s", + __func__, vbasedev->name); + } + node_path = qemu_fdt_node_path(host_fdt, dt_name, vdev->compat, + &error_fatal); + if (!node_path || !node_path[0]) { + error_setg(&error_fatal, "%s unable to retrieve node path for %s/%s", + __func__, dt_name, vdev->compat); } + + if (node_path[1]) { + error_setg(&error_fatal, "%s more than one node matching %s/%s!", + __func__, dt_name, vdev->compat); + } + + g_free(dt_name); + + if (vbasedev->num_regions != 5) { + error_setg(&error_fatal, "%s Does the host dt node combine XGBE/PHY?", + __func__); + } + + /* generate nodes for DMA_CLK and PTP_CLK */ + r = qemu_fdt_getprop(host_fdt, node_path[0], "clocks", + &prop_len, &error_fatal); + if (prop_len != 8) { + error_setg(&error_fatal, "%s clocks property should contain 2 handles", + __func__); + } + host_clock_phandles = (uint32_t *)r; + guest_clock_phandles[0] = qemu_fdt_alloc_phandle(guest_fdt); + guest_clock_phandles[1] = qemu_fdt_alloc_phandle(guest_fdt); + + /** + * clock handles fetched from host dt are in be32 layout whereas + * rest of the code uses cpu layout. Also guest clock handles are + * in cpu layout. + */ + fdt_build_clock_node(host_fdt, guest_fdt, + be32_to_cpu(host_clock_phandles[0]), + guest_clock_phandles[0]); + + fdt_build_clock_node(host_fdt, guest_fdt, + be32_to_cpu(host_clock_phandles[1]), + guest_clock_phandles[1]); + + /* combined XGBE/PHY node */ + mmio_base = platform_bus_get_mmio_addr(pbus, sbdev, 0); + nodename = g_strdup_printf("%s/%s@%" PRIx64, parent_node, + vbasedev->name, mmio_base); + qemu_fdt_add_subnode(guest_fdt, nodename); + + copy_properties_from_host(amd_xgbe_copied_properties, + ARRAY_SIZE(amd_xgbe_copied_properties), + host_fdt, guest_fdt, + node_path[0], nodename); + + qemu_fdt_setprop_cells(guest_fdt, nodename, "clocks", + guest_clock_phandles[0], + guest_clock_phandles[1]); + + reg_attr = g_new(uint32_t, vbasedev->num_regions * 2); + for (i = 0; i < vbasedev->num_regions; i++) { + mmio_base = platform_bus_get_mmio_addr(pbus, sbdev, i); + reg_attr[2 * i] = cpu_to_be32(mmio_base); + reg_attr[2 * i + 1] = cpu_to_be32( + memory_region_size(&vdev->regions[i]->mem)); + } + qemu_fdt_setprop(guest_fdt, nodename, "reg", reg_attr, + vbasedev->num_regions * 2 * sizeof(uint32_t)); + + irq_attr = g_new(uint32_t, vbasedev->num_irqs * 3); + for (i = 0; i < vbasedev->num_irqs; i++) { + irq_number = platform_bus_get_irqn(pbus, sbdev , i) + + data->irq_start; + irq_attr[3 * i] = cpu_to_be32(GIC_FDT_IRQ_TYPE_SPI); + irq_attr[3 * i + 1] = cpu_to_be32(irq_number); + /* + * General device interrupt and PCS auto-negotiation interrupts are + * level-sensitive while the 4 per-channel interrupts are edge + * sensitive + */ + QLIST_FOREACH(intp, &vdev->intp_list, next) { + if (intp->pin == i) { + break; + } + } + if (intp->flags & VFIO_IRQ_INFO_AUTOMASKED) { + irq_attr[3 * i + 2] = cpu_to_be32(GIC_FDT_IRQ_FLAGS_LEVEL_HI); + } else { + irq_attr[3 * i + 2] = cpu_to_be32(GIC_FDT_IRQ_FLAGS_EDGE_LO_HI); + } + } + qemu_fdt_setprop(guest_fdt, nodename, "interrupts", + irq_attr, vbasedev->num_irqs * 3 * sizeof(uint32_t)); + + g_free(host_fdt); + g_strfreev(node_path); g_free(irq_attr); -fail_reg: g_free(reg_attr); g_free(nodename); - return ret; + return 0; } +#endif /* CONFIG_LINUX */ + /* list of supported dynamic sysbus devices */ static const NodeCreationPair add_fdt_node_functions[] = { +#ifdef CONFIG_LINUX {TYPE_VFIO_CALXEDA_XGMAC, add_calxeda_midway_xgmac_fdt_node}, + {TYPE_VFIO_AMD_XGBE, add_amd_xgbe_fdt_node}, +#endif {"", NULL}, /* last element */ }; diff --git a/hw/arm/vexpress.c b/hw/arm/vexpress.c index 3154aeaa95..726c4e0c55 100644 --- a/hw/arm/vexpress.c +++ b/hw/arm/vexpress.c @@ -478,8 +478,10 @@ static void vexpress_modify_dtb(const struct arm_boot_info *info, void *fdt) uint32_t acells, scells, intc; const VEDBoardInfo *daughterboard = (const VEDBoardInfo *)info; - acells = qemu_fdt_getprop_cell(fdt, "/", "#address-cells"); - scells = qemu_fdt_getprop_cell(fdt, "/", "#size-cells"); + acells = qemu_fdt_getprop_cell(fdt, "/", "#address-cells", + NULL, &error_fatal); + scells = qemu_fdt_getprop_cell(fdt, "/", "#size-cells", + NULL, &error_fatal); intc = find_int_controller(fdt); if (!intc) { /* Not fatal, we just won't provide virtio. This will diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index 8cf9a2167f..b8b3ece8ca 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -359,7 +359,8 @@ build_rsdp(GArray *rsdp_table, GArray *linker, unsigned rsdt) rsdp->checksum = 0; /* Checksum to be filled by Guest linker */ bios_linker_loader_add_checksum(linker, ACPI_BUILD_RSDP_FILE, - rsdp, rsdp, sizeof *rsdp, &rsdp->checksum); + rsdp_table, rsdp, sizeof *rsdp, + &rsdp->checksum); return rsdp_table; } diff --git a/hw/audio/gusemu.h b/hw/audio/gusemu.h index 331bb6fec0..b7f0751268 100644 --- a/hw/audio/gusemu.h +++ b/hw/audio/gusemu.h @@ -34,7 +34,6 @@ typedef signed char GUSchar; typedef signed short GUSsample; #else - #include <stdint.h> typedef int8_t GUSchar; typedef uint8_t GUSbyte; typedef uint16_t GUSword; diff --git a/hw/block/dataplane/virtio-blk.c b/hw/block/dataplane/virtio-blk.c index 0d9978109c..36f3d2b813 100644 --- a/hw/block/dataplane/virtio-blk.c +++ b/hw/block/dataplane/virtio-blk.c @@ -18,8 +18,6 @@ #include "qemu/thread.h" #include "qemu/error-report.h" #include "hw/virtio/virtio-access.h" -#include "hw/virtio/dataplane/vring.h" -#include "hw/virtio/dataplane/vring-accessors.h" #include "sysemu/block-backend.h" #include "hw/virtio/virtio-blk.h" #include "virtio-blk.h" @@ -28,7 +26,6 @@ #include "qom/object_interfaces.h" struct VirtIOBlockDataPlane { - bool started; bool starting; bool stopping; bool disabled; @@ -36,7 +33,7 @@ struct VirtIOBlockDataPlane { VirtIOBlkConf *conf; VirtIODevice *vdev; - Vring vring; /* virtqueue vring */ + VirtQueue *vq; /* virtqueue vring */ EventNotifier *guest_notifier; /* irq */ QEMUBH *bh; /* bh for guest notification */ @@ -49,93 +46,26 @@ struct VirtIOBlockDataPlane { */ IOThread *iothread; AioContext *ctx; - EventNotifier host_notifier; /* doorbell */ /* Operation blocker on BDS */ Error *blocker; - void (*saved_complete_request)(struct VirtIOBlockReq *req, - unsigned char status); }; /* Raise an interrupt to signal guest, if necessary */ -static void notify_guest(VirtIOBlockDataPlane *s) +void virtio_blk_data_plane_notify(VirtIOBlockDataPlane *s) { - if (!vring_should_notify(s->vdev, &s->vring)) { - return; - } - - event_notifier_set(s->guest_notifier); + qemu_bh_schedule(s->bh); } static void notify_guest_bh(void *opaque) { VirtIOBlockDataPlane *s = opaque; - notify_guest(s); -} - -static void complete_request_vring(VirtIOBlockReq *req, unsigned char status) -{ - VirtIOBlockDataPlane *s = req->dev->dataplane; - stb_p(&req->in->status, status); - - vring_push(s->vdev, &req->dev->dataplane->vring, &req->elem, req->in_len); - - /* Suppress notification to guest by BH and its scheduled - * flag because requests are completed as a batch after io - * plug & unplug is introduced, and the BH can still be - * executed in dataplane aio context even after it is - * stopped, so needn't worry about notification loss with BH. - */ - qemu_bh_schedule(s->bh); -} - -static void handle_notify(EventNotifier *e) -{ - VirtIOBlockDataPlane *s = container_of(e, VirtIOBlockDataPlane, - host_notifier); - VirtIOBlock *vblk = VIRTIO_BLK(s->vdev); - - event_notifier_test_and_clear(&s->host_notifier); - blk_io_plug(s->conf->conf.blk); - for (;;) { - MultiReqBuffer mrb = {}; - - /* Disable guest->host notifies to avoid unnecessary vmexits */ - vring_disable_notification(s->vdev, &s->vring); - - for (;;) { - VirtIOBlockReq *req = vring_pop(s->vdev, &s->vring, - sizeof(VirtIOBlockReq)); - - if (req == NULL) { - break; /* no more requests */ - } - - virtio_blk_init_request(vblk, req); - trace_virtio_blk_data_plane_process_request(s, req->elem.out_num, - req->elem.in_num, - req->elem.index); - - virtio_blk_handle_request(req, &mrb); - } - - if (mrb.num_reqs) { - virtio_blk_submit_multireq(s->conf->conf.blk, &mrb); - } - - if (likely(!vring_more_avail(s->vdev, &s->vring))) { /* vring emptied */ - /* Re-enable guest->host notifies and stop processing the vring. - * But if the guest has snuck in more descriptors, keep processing. - */ - if (vring_enable_notification(s->vdev, &s->vring)) { - break; - } - } else { /* fatal error */ - break; - } + if (!virtio_should_notify(s->vdev, s->vq)) { + return; } - blk_io_unplug(s->conf->conf.blk); + + event_notifier_set(s->guest_notifier); } static void data_plane_set_up_op_blockers(VirtIOBlockDataPlane *s) @@ -260,23 +190,14 @@ void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s) BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(s->vdev))); VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); VirtIOBlock *vblk = VIRTIO_BLK(s->vdev); - VirtQueue *vq; int r; - if (s->started || s->disabled) { - return; - } - - if (s->starting) { + if (vblk->dataplane_started || s->starting) { return; } s->starting = true; - - vq = virtio_get_queue(s->vdev, 0); - if (!vring_setup(&s->vring, s->vdev, 0)) { - goto fail_vring; - } + s->vq = virtio_get_queue(s->vdev, 0); /* Set up guest notifier (irq) */ r = k->set_guest_notifiers(qbus->parent, 1, true); @@ -285,7 +206,7 @@ void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s) "ensure -enable-kvm is set\n", r); goto fail_guest_notifiers; } - s->guest_notifier = virtio_queue_get_guest_notifier(vq); + s->guest_notifier = virtio_queue_get_guest_notifier(s->vq); /* Set up virtqueue notify */ r = k->set_host_notifier(qbus->parent, 0, true); @@ -293,34 +214,28 @@ void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s) fprintf(stderr, "virtio-blk failed to set host notifier (%d)\n", r); goto fail_host_notifier; } - s->host_notifier = *virtio_queue_get_host_notifier(vq); - - s->saved_complete_request = vblk->complete_request; - vblk->complete_request = complete_request_vring; s->starting = false; - s->started = true; + vblk->dataplane_started = true; trace_virtio_blk_data_plane_start(s); blk_set_aio_context(s->conf->conf.blk, s->ctx); /* Kick right away to begin processing requests already in vring */ - event_notifier_set(virtio_queue_get_host_notifier(vq)); + event_notifier_set(virtio_queue_get_host_notifier(s->vq)); /* Get this show started by hooking up our callbacks */ aio_context_acquire(s->ctx); - aio_set_event_notifier(s->ctx, &s->host_notifier, true, - handle_notify); + virtio_queue_aio_set_host_notifier_handler(s->vq, s->ctx, true, true); aio_context_release(s->ctx); return; fail_host_notifier: k->set_guest_notifiers(qbus->parent, 1, false); fail_guest_notifiers: - vring_teardown(&s->vring, s->vdev, 0); s->disabled = true; - fail_vring: s->starting = false; + vblk->dataplane_started = true; } /* Context: QEMU global mutex held */ @@ -330,39 +245,34 @@ void virtio_blk_data_plane_stop(VirtIOBlockDataPlane *s) VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); VirtIOBlock *vblk = VIRTIO_BLK(s->vdev); + if (!vblk->dataplane_started || s->stopping) { + return; + } /* Better luck next time. */ if (s->disabled) { s->disabled = false; - return; - } - if (!s->started || s->stopping) { + vblk->dataplane_started = false; return; } s->stopping = true; - vblk->complete_request = s->saved_complete_request; trace_virtio_blk_data_plane_stop(s); aio_context_acquire(s->ctx); /* Stop notifications for new requests from guest */ - aio_set_event_notifier(s->ctx, &s->host_notifier, true, NULL); + virtio_queue_aio_set_host_notifier_handler(s->vq, s->ctx, false, false); /* Drain and switch bs back to the QEMU main loop */ blk_set_aio_context(s->conf->conf.blk, qemu_get_aio_context()); aio_context_release(s->ctx); - /* Sync vring state back to virtqueue so that non-dataplane request - * processing can continue when we disable the host notifier below. - */ - vring_teardown(&s->vring, s->vdev, 0); - k->set_host_notifier(qbus->parent, 0, false); /* Clean up guest notifier (irq) */ k->set_guest_notifiers(qbus->parent, 1, false); - s->started = false; + vblk->dataplane_started = false; s->stopping = false; } diff --git a/hw/block/dataplane/virtio-blk.h b/hw/block/dataplane/virtio-blk.h index c88d40e72c..0714c11a2b 100644 --- a/hw/block/dataplane/virtio-blk.h +++ b/hw/block/dataplane/virtio-blk.h @@ -26,5 +26,6 @@ void virtio_blk_data_plane_destroy(VirtIOBlockDataPlane *s); void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s); void virtio_blk_data_plane_stop(VirtIOBlockDataPlane *s); void virtio_blk_data_plane_drain(VirtIOBlockDataPlane *s); +void virtio_blk_data_plane_notify(VirtIOBlockDataPlane *s); #endif /* HW_DATAPLANE_VIRTIO_BLK_H */ diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index c427698fcb..cb710f16fa 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -21,7 +21,6 @@ #include "sysemu/blockdev.h" #include "hw/virtio/virtio-blk.h" #include "dataplane/virtio-blk.h" -#include "migration/migration.h" #include "block/scsi.h" #ifdef __linux__ # include <scsi/sg.h> @@ -45,8 +44,7 @@ void virtio_blk_free_request(VirtIOBlockReq *req) } } -static void virtio_blk_complete_request(VirtIOBlockReq *req, - unsigned char status) +static void virtio_blk_req_complete(VirtIOBlockReq *req, unsigned char status) { VirtIOBlock *s = req->dev; VirtIODevice *vdev = VIRTIO_DEVICE(s); @@ -55,12 +53,11 @@ static void virtio_blk_complete_request(VirtIOBlockReq *req, stb_p(&req->in->status, status); virtqueue_push(s->vq, &req->elem, req->in_len); - virtio_notify(vdev, s->vq); -} - -static void virtio_blk_req_complete(VirtIOBlockReq *req, unsigned char status) -{ - req->dev->complete_request(req, status); + if (s->dataplane) { + virtio_blk_data_plane_notify(s->dataplane); + } else { + virtio_notify(vdev, s->vq); + } } static int virtio_blk_handle_rw_error(VirtIOBlockReq *req, int error, @@ -589,7 +586,7 @@ static void virtio_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq) /* Some guests kick before setting VIRTIO_CONFIG_S_DRIVER_OK so start * dataplane here instead of waiting for .set_status(). */ - if (s->dataplane) { + if (s->dataplane && !s->dataplane_started) { virtio_blk_data_plane_start(s->dataplane); return; } @@ -852,36 +849,6 @@ static const BlockDevOps virtio_block_ops = { .resize_cb = virtio_blk_resize, }; -/* Disable dataplane thread during live migration since it does not - * update the dirty memory bitmap yet. - */ -static void virtio_blk_migration_state_changed(Notifier *notifier, void *data) -{ - VirtIOBlock *s = container_of(notifier, VirtIOBlock, - migration_state_notifier); - MigrationState *mig = data; - Error *err = NULL; - - if (migration_in_setup(mig)) { - if (!s->dataplane) { - return; - } - virtio_blk_data_plane_destroy(s->dataplane); - s->dataplane = NULL; - } else if (migration_has_finished(mig) || - migration_has_failed(mig)) { - if (s->dataplane) { - return; - } - blk_drain_all(); /* complete in-flight non-dataplane requests */ - virtio_blk_data_plane_create(VIRTIO_DEVICE(s), &s->conf, - &s->dataplane, &err); - if (err != NULL) { - error_report_err(err); - } - } -} - static void virtio_blk_device_realize(DeviceState *dev, Error **errp) { VirtIODevice *vdev = VIRTIO_DEVICE(dev); @@ -916,15 +883,12 @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp) s->sector_mask = (s->conf.conf.logical_block_size / BDRV_SECTOR_SIZE) - 1; s->vq = virtio_add_queue(vdev, 128, virtio_blk_handle_output); - s->complete_request = virtio_blk_complete_request; virtio_blk_data_plane_create(vdev, conf, &s->dataplane, &err); if (err != NULL) { error_propagate(errp, err); virtio_cleanup(vdev); return; } - s->migration_state_notifier.notify = virtio_blk_migration_state_changed; - add_migration_state_change_notifier(&s->migration_state_notifier); s->change = qemu_add_vm_change_state_handler(virtio_blk_dma_restart_cb, s); register_savevm(dev, "virtio-blk", virtio_blk_id++, 2, @@ -940,7 +904,6 @@ static void virtio_blk_device_unrealize(DeviceState *dev, Error **errp) VirtIODevice *vdev = VIRTIO_DEVICE(dev); VirtIOBlock *s = VIRTIO_BLK(dev); - remove_migration_state_change_notifier(&s->migration_state_notifier); virtio_blk_data_plane_destroy(s->dataplane); s->dataplane = NULL; qemu_del_vm_change_state_handler(s->change); diff --git a/hw/display/vga_int.h b/hw/display/vga_int.h index 40ba6a4207..bdb43a5a34 100644 --- a/hw/display/vga_int.h +++ b/hw/display/vga_int.h @@ -25,7 +25,6 @@ #define HW_VGA_INT_H 1 #include <hw/hw.h> -#include "qapi/error.h" #include "exec/memory.h" #define ST01_V_RETRACE 0x08 diff --git a/hw/dma/etraxfs_dma.c b/hw/dma/etraxfs_dma.c index 9cbb16580e..d5650eb885 100644 --- a/hw/dma/etraxfs_dma.c +++ b/hw/dma/etraxfs_dma.c @@ -440,13 +440,16 @@ static int channel_out_run(struct fs_dma_ctrl *ctrl, int c) D(printf("channel %d pushes %x %u bytes eop=%u\n", c, saved_data_buf, len, out_eop)); - if (ctrl->channels[c].client->client.push) - ctrl->channels[c].client->client.push( - ctrl->channels[c].client->client.opaque, - buf, len, out_eop); - else + if (ctrl->channels[c].client->client.push) { + if (len > 0) { + ctrl->channels[c].client->client.push( + ctrl->channels[c].client->client.opaque, + buf, len, out_eop); + } + } else { printf("WARNING: DMA ch%d dataloss," " no attached client.\n", c); + } saved_data_buf += len; diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c index 4554eb88bc..52c9470a54 100644 --- a/hw/i386/acpi-build.c +++ b/hw/i386/acpi-build.c @@ -2532,7 +2532,8 @@ build_rsdp(GArray *rsdp_table, GArray *linker, unsigned rsdt) rsdp->checksum = 0; /* Checksum to be filled by Guest linker */ bios_linker_loader_add_checksum(linker, ACPI_BUILD_RSDP_FILE, - rsdp, rsdp, sizeof *rsdp, &rsdp->checksum); + rsdp_table, rsdp, sizeof *rsdp, + &rsdp->checksum); return rsdp_table; } diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c index 208a224226..46522c90da 100644 --- a/hw/i386/pc_q35.c +++ b/hw/i386/pc_q35.c @@ -81,11 +81,9 @@ static void pc_q35_init(MachineState *machine) * If it doesn't, we need to split it in chunks below and above 4G. * In any case, try to make sure that guest addresses aligned at * 1G boundaries get mapped to host addresses aligned at 1G boundaries. - * For old machine types, use whatever split we used historically to avoid - * breaking migration. */ if (machine->ram_size >= 0xb0000000) { - lowmem = pcmc->gigabyte_align ? 0x80000000 : 0xb0000000; + lowmem = 0x80000000; } else { lowmem = 0xb0000000; } @@ -116,10 +114,6 @@ static void pc_q35_init(MachineState *machine) } pc_cpus_init(pcms); - if (!pcmc->has_acpi_build) { - /* only machine types 1.7 & older need this */ - pc_acpi_init("q35-acpi-dsdt.aml"); - } kvmclock_create(); @@ -225,7 +219,7 @@ static void pc_q35_init(MachineState *machine) (pcms->vmport != ON_OFF_AUTO_ON), 0xff0104); /* connect pm stuff to lpc */ - ich9_lpc_pm_init(lpc, pc_machine_is_smm_enabled(pcms), !mc->no_tco); + ich9_lpc_pm_init(lpc, pc_machine_is_smm_enabled(pcms)); /* ahci and SATA device, for q35 1 ahci controller is built-in */ ahci = pci_create_simple_multifunction(host_bus, @@ -259,62 +253,6 @@ static void pc_q35_init(MachineState *machine) } } -/* Looking for a pc_compat_2_4() function? It doesn't exist. - * pc_compat_*() functions that run on machine-init time and - * change global QEMU state are deprecated. Please don't create - * one, and implement any pc-*-2.4 (and newer) compat code in - * HW_COMPAT_*, PC_COMPAT_*, or * pc_*_machine_options(). - */ - -static void pc_compat_2_3(MachineState *machine) -{ - PCMachineState *pcms = PC_MACHINE(machine); - savevm_skip_section_footers(); - if (kvm_enabled()) { - pcms->smm = ON_OFF_AUTO_OFF; - } - global_state_set_optional(); - savevm_skip_configuration(); -} - -static void pc_compat_2_2(MachineState *machine) -{ - pc_compat_2_3(machine); - machine->suppress_vmdesc = true; -} - -static void pc_compat_2_1(MachineState *machine) -{ - pc_compat_2_2(machine); - x86_cpu_change_kvm_default("svm", NULL); -} - -static void pc_compat_2_0(MachineState *machine) -{ - pc_compat_2_1(machine); -} - -static void pc_compat_1_7(MachineState *machine) -{ - pc_compat_2_0(machine); - x86_cpu_change_kvm_default("x2apic", NULL); -} - -static void pc_compat_1_6(MachineState *machine) -{ - pc_compat_1_7(machine); -} - -static void pc_compat_1_5(MachineState *machine) -{ - pc_compat_1_6(machine); -} - -static void pc_compat_1_4(MachineState *machine) -{ - pc_compat_1_5(machine); -} - #define DEFINE_Q35_MACHINE(suffix, name, compatfn, optionfn) \ static void pc_init_##suffix(MachineState *machine) \ { \ @@ -336,7 +274,6 @@ static void pc_q35_machine_options(MachineClass *m) m->default_machine_opts = "firmware=bios-256k.bin"; m->default_display = "std"; m->no_floppy = 1; - m->no_tco = 0; } static void pc_q35_2_6_machine_options(MachineClass *m) @@ -371,112 +308,3 @@ static void pc_q35_2_4_machine_options(MachineClass *m) DEFINE_Q35_MACHINE(v2_4, "pc-q35-2.4", NULL, pc_q35_2_4_machine_options); - - -static void pc_q35_2_3_machine_options(MachineClass *m) -{ - pc_q35_2_4_machine_options(m); - m->hw_version = "2.3.0"; - m->no_floppy = 0; - m->no_tco = 1; - SET_MACHINE_COMPAT(m, PC_COMPAT_2_3); -} - -DEFINE_Q35_MACHINE(v2_3, "pc-q35-2.3", pc_compat_2_3, - pc_q35_2_3_machine_options); - - -static void pc_q35_2_2_machine_options(MachineClass *m) -{ - PCMachineClass *pcmc = PC_MACHINE_CLASS(m); - pc_q35_2_3_machine_options(m); - m->hw_version = "2.2.0"; - SET_MACHINE_COMPAT(m, PC_COMPAT_2_2); - pcmc->rsdp_in_ram = false; -} - -DEFINE_Q35_MACHINE(v2_2, "pc-q35-2.2", pc_compat_2_2, - pc_q35_2_2_machine_options); - - -static void pc_q35_2_1_machine_options(MachineClass *m) -{ - PCMachineClass *pcmc = PC_MACHINE_CLASS(m); - pc_q35_2_2_machine_options(m); - m->hw_version = "2.1.0"; - m->default_display = NULL; - SET_MACHINE_COMPAT(m, PC_COMPAT_2_1); - pcmc->smbios_uuid_encoded = false; - pcmc->enforce_aligned_dimm = false; -} - -DEFINE_Q35_MACHINE(v2_1, "pc-q35-2.1", pc_compat_2_1, - pc_q35_2_1_machine_options); - - -static void pc_q35_2_0_machine_options(MachineClass *m) -{ - PCMachineClass *pcmc = PC_MACHINE_CLASS(m); - pc_q35_2_1_machine_options(m); - m->hw_version = "2.0.0"; - SET_MACHINE_COMPAT(m, PC_COMPAT_2_0); - pcmc->has_reserved_memory = false; - pcmc->smbios_legacy_mode = true; - pcmc->acpi_data_size = 0x10000; -} - -DEFINE_Q35_MACHINE(v2_0, "pc-q35-2.0", pc_compat_2_0, - pc_q35_2_0_machine_options); - - -static void pc_q35_1_7_machine_options(MachineClass *m) -{ - PCMachineClass *pcmc = PC_MACHINE_CLASS(m); - pc_q35_2_0_machine_options(m); - m->hw_version = "1.7.0"; - m->default_machine_opts = NULL; - m->option_rom_has_mr = true; - SET_MACHINE_COMPAT(m, PC_COMPAT_1_7); - pcmc->smbios_defaults = false; - pcmc->gigabyte_align = false; -} - -DEFINE_Q35_MACHINE(v1_7, "pc-q35-1.7", pc_compat_1_7, - pc_q35_1_7_machine_options); - - -static void pc_q35_1_6_machine_options(MachineClass *m) -{ - PCMachineClass *pcmc = PC_MACHINE_CLASS(m); - pc_q35_machine_options(m); - m->hw_version = "1.6.0"; - m->rom_file_has_mr = false; - SET_MACHINE_COMPAT(m, PC_COMPAT_1_6); - pcmc->has_acpi_build = false; -} - -DEFINE_Q35_MACHINE(v1_6, "pc-q35-1.6", pc_compat_1_6, - pc_q35_1_6_machine_options); - - -static void pc_q35_1_5_machine_options(MachineClass *m) -{ - pc_q35_1_6_machine_options(m); - m->hw_version = "1.5.0"; - SET_MACHINE_COMPAT(m, PC_COMPAT_1_5); -} - -DEFINE_Q35_MACHINE(v1_5, "pc-q35-1.5", pc_compat_1_5, - pc_q35_1_5_machine_options); - - -static void pc_q35_1_4_machine_options(MachineClass *m) -{ - pc_q35_1_5_machine_options(m); - m->hw_version = "1.4.0"; - m->hot_add_cpu = NULL; - SET_MACHINE_COMPAT(m, PC_COMPAT_1_4); -} - -DEFINE_Q35_MACHINE(v1_4, "pc-q35-1.4", pc_compat_1_4, - pc_q35_1_4_machine_options); diff --git a/hw/isa/lpc_ich9.c b/hw/isa/lpc_ich9.c index 6cf2eb607d..4e896b29f1 100644 --- a/hw/isa/lpc_ich9.c +++ b/hw/isa/lpc_ich9.c @@ -369,13 +369,13 @@ static void ich9_set_sci(void *opaque, int irq_num, int level) } } -void ich9_lpc_pm_init(PCIDevice *lpc_pci, bool smm_enabled, bool enable_tco) +void ich9_lpc_pm_init(PCIDevice *lpc_pci, bool smm_enabled) { ICH9LPCState *lpc = ICH9_LPC_DEVICE(lpc_pci); qemu_irq sci_irq; sci_irq = qemu_allocate_irq(ich9_set_sci, lpc, 0); - ich9_pm_init(lpc_pci, &lpc->pm, smm_enabled, enable_tco, sci_irq); + ich9_pm_init(lpc_pci, &lpc->pm, smm_enabled, sci_irq); ich9_lpc_reset(&lpc->d.qdev); } diff --git a/hw/mem/pc-dimm.c b/hw/mem/pc-dimm.c index 1aa12c64d0..650f0f89f4 100644 --- a/hw/mem/pc-dimm.c +++ b/hw/mem/pc-dimm.c @@ -192,32 +192,6 @@ int qmp_pc_dimm_device_list(Object *obj, void *opaque) return 0; } -ram_addr_t get_current_ram_size(void) -{ - MemoryDeviceInfoList *info_list = NULL; - MemoryDeviceInfoList **prev = &info_list; - MemoryDeviceInfoList *info; - ram_addr_t size = ram_size; - - qmp_pc_dimm_device_list(qdev_get_machine(), &prev); - for (info = info_list; info; info = info->next) { - MemoryDeviceInfo *value = info->value; - - if (value) { - switch (value->type) { - case MEMORY_DEVICE_INFO_KIND_DIMM: - size += value->u.dimm->size; - break; - default: - break; - } - } - } - qapi_free_MemoryDeviceInfoList(info_list); - - return size; -} - static int pc_dimm_slot2bitmap(Object *obj, void *opaque) { unsigned long *bitmap = opaque; diff --git a/hw/net/fsl_etsec/registers.h b/hw/net/fsl_etsec/registers.h index 7ad7686470..6fb96842b8 100644 --- a/hw/net/fsl_etsec/registers.h +++ b/hw/net/fsl_etsec/registers.h @@ -24,7 +24,6 @@ #ifndef _ETSEC_REGISTERS_H_ #define _ETSEC_REGISTERS_H_ -#include <stdint.h> enum eTSEC_Register_Access_Type { ACC_RW = 1, /* Read/Write */ diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c index 3940a04b65..6e1032fc18 100644 --- a/hw/net/vhost_net.c +++ b/hw/net/vhost_net.c @@ -36,7 +36,6 @@ #include "standard-headers/linux/virtio_ring.h" #include "hw/virtio/vhost.h" #include "hw/virtio/virtio-bus.h" -#include "hw/virtio/virtio-access.h" struct vhost_net { struct vhost_dev dev; @@ -197,27 +196,6 @@ static void vhost_net_set_vq_index(struct vhost_net *net, int vq_index) net->dev.vq_index = vq_index; } -static int vhost_net_set_vnet_endian(VirtIODevice *dev, NetClientState *peer, - bool set) -{ - int r = 0; - - if (virtio_vdev_has_feature(dev, VIRTIO_F_VERSION_1) || - (virtio_legacy_is_cross_endian(dev) && !virtio_is_big_endian(dev))) { - r = qemu_set_vnet_le(peer, set); - if (r) { - error_report("backend does not support LE vnet headers"); - } - } else if (virtio_legacy_is_cross_endian(dev)) { - r = qemu_set_vnet_be(peer, set); - if (r) { - error_report("backend does not support BE vnet headers"); - } - } - - return r; -} - static int vhost_net_start_one(struct vhost_net *net, VirtIODevice *dev) { @@ -298,25 +276,32 @@ int vhost_net_start(VirtIODevice *dev, NetClientState *ncs, BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(dev))); VirtioBusState *vbus = VIRTIO_BUS(qbus); VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(vbus); - int r, e, i, j; + int r, e, i; if (!k->set_guest_notifiers) { error_report("binding does not support guest notifiers"); return -ENOSYS; } - for (j = 0; j < total_queues; j++) { - r = vhost_net_set_vnet_endian(dev, ncs[j].peer, true); - if (r < 0) { - goto err_endian; + for (i = 0; i < total_queues; i++) { + struct vhost_net *net; + + net = get_vhost_net(ncs[i].peer); + vhost_net_set_vq_index(net, i * 2); + + /* Suppress the masking guest notifiers on vhost user + * because vhost user doesn't interrupt masking/unmasking + * properly. + */ + if (net->nc->info->type == NET_CLIENT_OPTIONS_KIND_VHOST_USER) { + dev->use_guest_notifier_mask = false; } - vhost_net_set_vq_index(get_vhost_net(ncs[j].peer), j * 2); - } + } r = k->set_guest_notifiers(qbus->parent, total_queues * 2, true); if (r < 0) { error_report("Error binding guest notifier: %d", -r); - goto err_endian; + goto err; } for (i = 0; i < total_queues; i++) { @@ -338,10 +323,7 @@ err_start: fprintf(stderr, "vhost guest notifier cleanup failed: %d\n", e); fflush(stderr); } -err_endian: - while (--j >= 0) { - vhost_net_set_vnet_endian(dev, ncs[j].peer, false); - } +err: return r; } @@ -363,8 +345,6 @@ void vhost_net_stop(VirtIODevice *dev, NetClientState *ncs, fflush(stderr); } assert(r >= 0); - - assert(vhost_net_set_vnet_endian(dev, ncs[0].peer, false) >= 0); } void vhost_net_cleanup(struct vhost_net *net) diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index de696e8dd0..5798f87d8e 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -129,6 +129,13 @@ static void virtio_net_vhost_status(VirtIONet *n, uint8_t status) if (!n->vhost_started) { int r, i; + if (n->needs_vnet_hdr_swap) { + error_report("backend does not support %s vnet headers; " + "falling back on userspace virtio", + virtio_is_big_endian(vdev) ? "BE" : "LE"); + return; + } + /* Any packets outstanding? Purge them to avoid touching rings * when vhost is running. */ @@ -153,6 +160,59 @@ static void virtio_net_vhost_status(VirtIONet *n, uint8_t status) } } +static int virtio_net_set_vnet_endian_one(VirtIODevice *vdev, + NetClientState *peer, + bool enable) +{ + if (virtio_is_big_endian(vdev)) { + return qemu_set_vnet_be(peer, enable); + } else { + return qemu_set_vnet_le(peer, enable); + } +} + +static bool virtio_net_set_vnet_endian(VirtIODevice *vdev, NetClientState *ncs, + int queues, bool enable) +{ + int i; + + for (i = 0; i < queues; i++) { + if (virtio_net_set_vnet_endian_one(vdev, ncs[i].peer, enable) < 0 && + enable) { + while (--i >= 0) { + virtio_net_set_vnet_endian_one(vdev, ncs[i].peer, false); + } + + return true; + } + } + + return false; +} + +static void virtio_net_vnet_endian_status(VirtIONet *n, uint8_t status) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(n); + int queues = n->multiqueue ? n->max_queues : 1; + + if (virtio_net_started(n, status)) { + /* Before using the device, we tell the network backend about the + * endianness to use when parsing vnet headers. If the backend + * can't do it, we fallback onto fixing the headers in the core + * virtio-net code. + */ + n->needs_vnet_hdr_swap = virtio_net_set_vnet_endian(vdev, n->nic->ncs, + queues, true); + } else if (virtio_net_started(n, vdev->status)) { + /* After using the device, we need to reset the network backend to + * the default (guest native endianness), otherwise the guest may + * lose network connectivity if it is rebooted into a different + * endianness. + */ + virtio_net_set_vnet_endian(vdev, n->nic->ncs, queues, false); + } +} + static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status) { VirtIONet *n = VIRTIO_NET(vdev); @@ -160,6 +220,7 @@ static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status) int i; uint8_t queue_status; + virtio_net_vnet_endian_status(n, status); virtio_net_vhost_status(n, status); for (i = 0; i < n->max_queues; i++) { @@ -963,7 +1024,10 @@ static void receive_header(VirtIONet *n, const struct iovec *iov, int iov_cnt, void *wbuf = (void *)buf; work_around_broken_dhclient(wbuf, wbuf + n->host_hdr_len, size - n->host_hdr_len); - virtio_net_hdr_swap(VIRTIO_DEVICE(n), wbuf); + + if (n->needs_vnet_hdr_swap) { + virtio_net_hdr_swap(VIRTIO_DEVICE(n), wbuf); + } iov_from_buf(iov, iov_cnt, 0, buf, sizeof(struct virtio_net_hdr)); } else { struct virtio_net_hdr hdr = { @@ -1184,7 +1248,7 @@ static int32_t virtio_net_flush_tx(VirtIONetQueue *q) error_report("virtio-net header incorrect"); exit(1); } - if (virtio_needs_swap(vdev)) { + if (n->needs_vnet_hdr_swap) { virtio_net_hdr_swap(vdev, (void *) &mhdr); sg2[0].iov_base = &mhdr; sg2[0].iov_len = n->guest_hdr_len; diff --git a/hw/pci-bridge/dec.c b/hw/pci-bridge/dec.c index 40ff0d0632..840c96198a 100644 --- a/hw/pci-bridge/dec.c +++ b/hw/pci-bridge/dec.c @@ -52,9 +52,9 @@ static int dec_map_irq(PCIDevice *pci_dev, int irq_num) return irq_num; } -static int dec_pci_bridge_initfn(PCIDevice *pci_dev) +static void dec_pci_bridge_realize(PCIDevice *pci_dev, Error **errp) { - return pci_bridge_initfn(pci_dev, TYPE_PCI_BUS); + pci_bridge_initfn(pci_dev, TYPE_PCI_BUS); } static void dec_21154_pci_bridge_class_init(ObjectClass *klass, void *data) @@ -62,7 +62,7 @@ static void dec_21154_pci_bridge_class_init(ObjectClass *klass, void *data) DeviceClass *dc = DEVICE_CLASS(klass); PCIDeviceClass *k = PCI_DEVICE_CLASS(klass); - k->init = dec_pci_bridge_initfn; + k->realize = dec_pci_bridge_realize; k->exit = pci_bridge_exitfn; k->vendor_id = PCI_VENDOR_ID_DEC; k->device_id = PCI_DEVICE_ID_DEC_21154; diff --git a/hw/pci-bridge/i82801b11.c b/hw/pci-bridge/i82801b11.c index b143f8cb79..5c40708ba8 100644 --- a/hw/pci-bridge/i82801b11.c +++ b/hw/pci-bridge/i82801b11.c @@ -62,10 +62,7 @@ static int i82801b11_bridge_initfn(PCIDevice *d) { int rc; - rc = pci_bridge_initfn(d, TYPE_PCI_BUS); - if (rc < 0) { - return rc; - } + pci_bridge_initfn(d, TYPE_PCI_BUS); rc = pci_bridge_ssvid_init(d, I82801ba_SSVID_OFFSET, I82801ba_SSVID_SVID, I82801ba_SSVID_SSID); diff --git a/hw/pci-bridge/ioh3420.c b/hw/pci-bridge/ioh3420.c index 8ac4240bb1..0937fa34be 100644 --- a/hw/pci-bridge/ioh3420.c +++ b/hw/pci-bridge/ioh3420.c @@ -98,11 +98,7 @@ static int ioh3420_initfn(PCIDevice *d) PCIESlot *s = PCIE_SLOT(d); int rc; - rc = pci_bridge_initfn(d, TYPE_PCIE_BUS); - if (rc < 0) { - return rc; - } - + pci_bridge_initfn(d, TYPE_PCIE_BUS); pcie_port_init_reg(d); rc = pci_bridge_ssvid_init(d, IOH_EP_SSVID_OFFSET, @@ -130,7 +126,7 @@ static int ioh3420_initfn(PCIDevice *d) goto err_pcie_cap; } pcie_cap_root_init(d); - rc = pcie_aer_init(d, IOH_EP_AER_OFFSET); + rc = pcie_aer_init(d, IOH_EP_AER_OFFSET, PCI_ERR_SIZEOF); if (rc < 0) { goto err; } diff --git a/hw/pci-bridge/pci_bridge_dev.c b/hw/pci-bridge/pci_bridge_dev.c index c9a7e2b2a3..100bb5ebf6 100644 --- a/hw/pci-bridge/pci_bridge_dev.c +++ b/hw/pci-bridge/pci_bridge_dev.c @@ -53,10 +53,8 @@ static int pci_bridge_dev_initfn(PCIDevice *dev) PCIBridgeDev *bridge_dev = PCI_BRIDGE_DEV(dev); int err; - err = pci_bridge_initfn(dev, TYPE_PCI_BUS); - if (err) { - goto bridge_error; - } + pci_bridge_initfn(dev, TYPE_PCI_BUS); + if (bridge_dev->flags & (1 << PCI_BRIDGE_DEV_F_SHPC_REQ)) { dev->config[PCI_INTERRUPT_PIN] = 0x1; memory_region_init(&bridge_dev->bar, OBJECT(dev), "shpc-bar", @@ -95,7 +93,7 @@ slotid_error: } shpc_error: pci_bridge_exitfn(dev); -bridge_error: + return err; } diff --git a/hw/pci-bridge/xio3130_downstream.c b/hw/pci-bridge/xio3130_downstream.c index 9eb3d8895f..cf1ee63aba 100644 --- a/hw/pci-bridge/xio3130_downstream.c +++ b/hw/pci-bridge/xio3130_downstream.c @@ -61,11 +61,7 @@ static int xio3130_downstream_initfn(PCIDevice *d) PCIESlot *s = PCIE_SLOT(d); int rc; - rc = pci_bridge_initfn(d, TYPE_PCIE_BUS); - if (rc < 0) { - return rc; - } - + pci_bridge_initfn(d, TYPE_PCIE_BUS); pcie_port_init_reg(d); rc = msi_init(d, XIO3130_MSI_OFFSET, XIO3130_MSI_NR_VECTOR, @@ -93,7 +89,7 @@ static int xio3130_downstream_initfn(PCIDevice *d) goto err_pcie_cap; } pcie_cap_arifwd_init(d); - rc = pcie_aer_init(d, XIO3130_AER_OFFSET); + rc = pcie_aer_init(d, XIO3130_AER_OFFSET, PCI_ERR_SIZEOF); if (rc < 0) { goto err; } diff --git a/hw/pci-bridge/xio3130_upstream.c b/hw/pci-bridge/xio3130_upstream.c index 7d255a6d52..164ef58c46 100644 --- a/hw/pci-bridge/xio3130_upstream.c +++ b/hw/pci-bridge/xio3130_upstream.c @@ -57,11 +57,7 @@ static int xio3130_upstream_initfn(PCIDevice *d) PCIEPort *p = PCIE_PORT(d); int rc; - rc = pci_bridge_initfn(d, TYPE_PCIE_BUS); - if (rc < 0) { - return rc; - } - + pci_bridge_initfn(d, TYPE_PCIE_BUS); pcie_port_init_reg(d); rc = msi_init(d, XIO3130_MSI_OFFSET, XIO3130_MSI_NR_VECTOR, @@ -82,7 +78,7 @@ static int xio3130_upstream_initfn(PCIDevice *d) } pcie_cap_flr_init(d); pcie_cap_deverr_init(d); - rc = pcie_aer_init(d, XIO3130_AER_OFFSET); + rc = pcie_aer_init(d, XIO3130_AER_OFFSET, PCI_ERR_SIZEOF); if (rc < 0) { goto err; } diff --git a/hw/pci-host/apb.c b/hw/pci-host/apb.c index 75dee50bc3..aaef7bb3a1 100644 --- a/hw/pci-host/apb.c +++ b/hw/pci-host/apb.c @@ -635,12 +635,7 @@ static void pci_apb_set_irq(void *opaque, int irq_num, int level) static int apb_pci_bridge_initfn(PCIDevice *dev) { - int rc; - - rc = pci_bridge_initfn(dev, TYPE_PCI_BUS); - if (rc < 0) { - return rc; - } + pci_bridge_initfn(dev, TYPE_PCI_BUS); /* * command register: diff --git a/hw/pci/msix.c b/hw/pci/msix.c index eb4ef113d1..537fdba747 100644 --- a/hw/pci/msix.c +++ b/hw/pci/msix.c @@ -80,10 +80,10 @@ static void msix_clr_pending(PCIDevice *dev, int vector) static bool msix_vector_masked(PCIDevice *dev, unsigned int vector, bool fmask) { unsigned offset = vector * PCI_MSIX_ENTRY_SIZE; - uint32_t *data = (uint32_t *)&dev->msix_table[offset + PCI_MSIX_ENTRY_DATA]; + uint8_t *data = &dev->msix_table[offset + PCI_MSIX_ENTRY_DATA]; /* MSIs on Xen can be remapped into pirqs. In those cases, masking * and unmasking go through the PV evtchn path. */ - if (xen_is_pirq_msi(*data)) { + if (xen_enabled() && xen_is_pirq_msi(pci_get_long(data))) { return false; } return fmask || dev->msix_table[offset + PCI_MSIX_ENTRY_VECTOR_CTRL] & diff --git a/hw/pci/pci.c b/hw/pci/pci.c index b282120b12..e67664deb3 100644 --- a/hw/pci/pci.c +++ b/hw/pci/pci.c @@ -278,9 +278,9 @@ static void pcibus_reset(BusState *qbus) } } -static void pci_host_bus_register(PCIBus *bus, DeviceState *parent) +static void pci_host_bus_register(DeviceState *host) { - PCIHostState *host_bridge = PCI_HOST_BRIDGE(parent); + PCIHostState *host_bridge = PCI_HOST_BRIDGE(host); QLIST_INSERT_HEAD(&pci_host_bridges, host_bridge, next); } @@ -331,7 +331,6 @@ const char *pci_root_bus_path(PCIDevice *dev) } static void pci_bus_init(PCIBus *bus, DeviceState *parent, - const char *name, MemoryRegion *address_space_mem, MemoryRegion *address_space_io, uint8_t devfn_min) @@ -344,7 +343,7 @@ static void pci_bus_init(PCIBus *bus, DeviceState *parent, /* host bridge */ QLIST_INIT(&bus->child); - pci_host_bus_register(bus, parent); + pci_host_bus_register(parent); } bool pci_bus_is_express(PCIBus *bus) @@ -364,8 +363,7 @@ void pci_bus_new_inplace(PCIBus *bus, size_t bus_size, DeviceState *parent, uint8_t devfn_min, const char *typename) { qbus_create_inplace(bus, bus_size, typename, parent, name); - pci_bus_init(bus, parent, name, address_space_mem, - address_space_io, devfn_min); + pci_bus_init(bus, parent, address_space_mem, address_space_io, devfn_min); } PCIBus *pci_bus_new(DeviceState *parent, const char *name, @@ -376,8 +374,7 @@ PCIBus *pci_bus_new(DeviceState *parent, const char *name, PCIBus *bus; bus = PCI_BUS(qbus_create(typename, parent, name)); - pci_bus_init(bus, parent, name, address_space_mem, - address_space_io, devfn_min); + pci_bus_init(bus, parent, address_space_mem, address_space_io, devfn_min); return bus; } diff --git a/hw/pci/pci_bridge.c b/hw/pci/pci_bridge.c index 7eab9d57c5..3cf30bd334 100644 --- a/hw/pci/pci_bridge.c +++ b/hw/pci/pci_bridge.c @@ -333,7 +333,7 @@ void pci_bridge_reset(DeviceState *qdev) } /* default qdev initialization function for PCI-to-PCI bridge */ -int pci_bridge_initfn(PCIDevice *dev, const char *typename) +void pci_bridge_initfn(PCIDevice *dev, const char *typename) { PCIBus *parent = dev->bus; PCIBridge *br = PCI_BRIDGE(dev); @@ -379,7 +379,6 @@ int pci_bridge_initfn(PCIDevice *dev, const char *typename) br->windows = pci_bridge_region_init(br); QLIST_INIT(&sec_bus->child); QLIST_INSERT_HEAD(&parent->child, sec_bus, sibling); - return 0; } /* default qdev clean up function for PCI-to-PCI bridge */ diff --git a/hw/pci/pcie.c b/hw/pci/pcie.c index 435a6cfd57..4aca0c5912 100644 --- a/hw/pci/pcie.c +++ b/hw/pci/pcie.c @@ -608,7 +608,7 @@ void pcie_add_capability(PCIDevice *dev, assert(offset >= PCI_CONFIG_SPACE_SIZE); assert(offset < offset + size); - assert(offset + size < PCIE_CONFIG_SPACE_SIZE); + assert(offset + size <= PCIE_CONFIG_SPACE_SIZE); assert(size >= 8); assert(pci_is_express(dev)); diff --git a/hw/pci/pcie_aer.c b/hw/pci/pcie_aer.c index a9d9d06208..e2d4e68ba3 100644 --- a/hw/pci/pcie_aer.c +++ b/hw/pci/pcie_aer.c @@ -95,12 +95,12 @@ static void aer_log_clear_all_err(PCIEAERLog *aer_log) aer_log->log_num = 0; } -int pcie_aer_init(PCIDevice *dev, uint16_t offset) +int pcie_aer_init(PCIDevice *dev, uint16_t offset, uint16_t size) { PCIExpressDevice *exp; pcie_add_capability(dev, PCI_EXT_CAP_ID_ERR, PCI_ERR_VER, - offset, PCI_ERR_SIZEOF); + offset, size); exp = &dev->exp; exp->aer_cap = offset; @@ -371,7 +371,7 @@ static void pcie_aer_msg_root_port(PCIDevice *dev, const PCIEAERMsg *msg) * * Walk up the bus tree from the device, propagate the error message. */ -static void pcie_aer_msg(PCIDevice *dev, const PCIEAERMsg *msg) +void pcie_aer_msg(PCIDevice *dev, const PCIEAERMsg *msg) { uint8_t type; diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index e214a34257..c119f55824 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -1528,7 +1528,7 @@ static int htab_load(QEMUFile *f, void *opaque, int version_id) section_hdr = qemu_get_be32(f); if (section_hdr) { - Error *local_err; + Error *local_err = NULL; /* First section gives the htab size */ spapr_reallocate_hpt(spapr, section_hdr, &local_err); diff --git a/hw/ppc/spapr_hcall.c b/hw/ppc/spapr_hcall.c index 6e9b6be58c..1733482de6 100644 --- a/hw/ppc/spapr_hcall.c +++ b/hw/ppc/spapr_hcall.c @@ -386,6 +386,65 @@ static target_ulong h_set_xdabr(PowerPCCPU *cpu, sPAPRMachineState *spapr, return H_SUCCESS; } +static target_ulong h_page_init(PowerPCCPU *cpu, sPAPRMachineState *spapr, + target_ulong opcode, target_ulong *args) +{ + target_ulong flags = args[0]; + hwaddr dst = args[1]; + hwaddr src = args[2]; + hwaddr len = TARGET_PAGE_SIZE; + uint8_t *pdst, *psrc; + target_long ret = H_SUCCESS; + + if (flags & ~(H_ICACHE_SYNCHRONIZE | H_ICACHE_INVALIDATE + | H_COPY_PAGE | H_ZERO_PAGE)) { + qemu_log_mask(LOG_UNIMP, "h_page_init: Bad flags (" TARGET_FMT_lx "\n", + flags); + return H_PARAMETER; + } + + /* Map-in destination */ + if (!is_ram_address(spapr, dst) || (dst & ~TARGET_PAGE_MASK) != 0) { + return H_PARAMETER; + } + pdst = cpu_physical_memory_map(dst, &len, 1); + if (!pdst || len != TARGET_PAGE_SIZE) { + return H_PARAMETER; + } + + if (flags & H_COPY_PAGE) { + /* Map-in source, copy to destination, and unmap source again */ + if (!is_ram_address(spapr, src) || (src & ~TARGET_PAGE_MASK) != 0) { + ret = H_PARAMETER; + goto unmap_out; + } + psrc = cpu_physical_memory_map(src, &len, 0); + if (!psrc || len != TARGET_PAGE_SIZE) { + ret = H_PARAMETER; + goto unmap_out; + } + memcpy(pdst, psrc, len); + cpu_physical_memory_unmap(psrc, len, 0, len); + } else if (flags & H_ZERO_PAGE) { + memset(pdst, 0, len); /* Just clear the destination page */ + } + + if (kvm_enabled() && (flags & H_ICACHE_SYNCHRONIZE) != 0) { + kvmppc_dcbst_range(cpu, pdst, len); + } + if (flags & (H_ICACHE_SYNCHRONIZE | H_ICACHE_INVALIDATE)) { + if (kvm_enabled()) { + kvmppc_icbi_range(cpu, pdst, len); + } else { + tb_flush(CPU(cpu)); + } + } + +unmap_out: + cpu_physical_memory_unmap(pdst, TARGET_PAGE_SIZE, 1, len); + return ret; +} + #define FLAGS_REGISTER_VPA 0x0000200000000000ULL #define FLAGS_REGISTER_DTL 0x0000400000000000ULL #define FLAGS_REGISTER_SLBSHADOW 0x0000600000000000ULL @@ -1045,6 +1104,7 @@ static void hypercall_register_types(void) spapr_register_hypercall(H_SET_SPRG0, h_set_sprg0); spapr_register_hypercall(H_SET_DABR, h_set_dabr); spapr_register_hypercall(H_SET_XDABR, h_set_xdabr); + spapr_register_hypercall(H_PAGE_INIT, h_page_init); spapr_register_hypercall(H_SET_MODE, h_set_mode); /* "debugger" hcalls (also used by SLOF). Note: We do -not- differenciate diff --git a/hw/scsi/virtio-scsi-dataplane.c b/hw/scsi/virtio-scsi-dataplane.c index 8340326a50..367e47643f 100644 --- a/hw/scsi/virtio-scsi-dataplane.c +++ b/hw/scsi/virtio-scsi-dataplane.c @@ -39,14 +39,10 @@ void virtio_scsi_set_iothread(VirtIOSCSI *s, IOThread *iothread) } } -static VirtIOSCSIVring *virtio_scsi_vring_init(VirtIOSCSI *s, - VirtQueue *vq, - EventNotifierHandler *handler, - int n) +static int virtio_scsi_vring_init(VirtIOSCSI *s, VirtQueue *vq, int n) { BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(s))); VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus); - VirtIOSCSIVring *r; int rc; /* Set up virtqueue notify */ @@ -55,105 +51,17 @@ static VirtIOSCSIVring *virtio_scsi_vring_init(VirtIOSCSI *s, fprintf(stderr, "virtio-scsi: Failed to set host notifier (%d)\n", rc); s->dataplane_fenced = true; - return NULL; + return rc; } - r = g_new(VirtIOSCSIVring, 1); - r->host_notifier = *virtio_queue_get_host_notifier(vq); - r->guest_notifier = *virtio_queue_get_guest_notifier(vq); - aio_set_event_notifier(s->ctx, &r->host_notifier, true, handler); - - r->parent = s; - - if (!vring_setup(&r->vring, VIRTIO_DEVICE(s), n)) { - fprintf(stderr, "virtio-scsi: VRing setup failed\n"); - goto fail_vring; - } - return r; - -fail_vring: - aio_set_event_notifier(s->ctx, &r->host_notifier, true, NULL); - k->set_host_notifier(qbus->parent, n, false); - g_free(r); - return NULL; -} - -VirtIOSCSIReq *virtio_scsi_pop_req_vring(VirtIOSCSI *s, - VirtIOSCSIVring *vring) -{ - VirtIOSCSICommon *vs = (VirtIOSCSICommon *)s; - VirtIOSCSIReq *req; - - req = vring_pop((VirtIODevice *)s, &vring->vring, - sizeof(VirtIOSCSIReq) + vs->cdb_size); - if (!req) { - return NULL; - } - virtio_scsi_init_req(s, NULL, req); - req->vring = vring; - return req; -} - -void virtio_scsi_vring_push_notify(VirtIOSCSIReq *req) -{ - VirtIODevice *vdev = VIRTIO_DEVICE(req->vring->parent); - - vring_push(vdev, &req->vring->vring, &req->elem, - req->qsgl.size + req->resp_iov.size); - - if (vring_should_notify(vdev, &req->vring->vring)) { - event_notifier_set(&req->vring->guest_notifier); - } + virtio_queue_aio_set_host_notifier_handler(vq, s->ctx, true, true); + return 0; } -static void virtio_scsi_iothread_handle_ctrl(EventNotifier *notifier) +void virtio_scsi_dataplane_notify(VirtIODevice *vdev, VirtIOSCSIReq *req) { - VirtIOSCSIVring *vring = container_of(notifier, - VirtIOSCSIVring, host_notifier); - VirtIOSCSI *s = VIRTIO_SCSI(vring->parent); - VirtIOSCSIReq *req; - - event_notifier_test_and_clear(notifier); - while ((req = virtio_scsi_pop_req_vring(s, vring))) { - virtio_scsi_handle_ctrl_req(s, req); - } -} - -static void virtio_scsi_iothread_handle_event(EventNotifier *notifier) -{ - VirtIOSCSIVring *vring = container_of(notifier, - VirtIOSCSIVring, host_notifier); - VirtIOSCSI *s = vring->parent; - VirtIODevice *vdev = VIRTIO_DEVICE(s); - - event_notifier_test_and_clear(notifier); - - if (!(vdev->status & VIRTIO_CONFIG_S_DRIVER_OK)) { - return; - } - - if (s->events_dropped) { - virtio_scsi_push_event(s, NULL, VIRTIO_SCSI_T_NO_EVENT, 0); - } -} - -static void virtio_scsi_iothread_handle_cmd(EventNotifier *notifier) -{ - VirtIOSCSIVring *vring = container_of(notifier, - VirtIOSCSIVring, host_notifier); - VirtIOSCSI *s = (VirtIOSCSI *)vring->parent; - VirtIOSCSIReq *req, *next; - QTAILQ_HEAD(, VirtIOSCSIReq) reqs = QTAILQ_HEAD_INITIALIZER(reqs); - - event_notifier_test_and_clear(notifier); - while ((req = virtio_scsi_pop_req_vring(s, vring))) { - if (virtio_scsi_handle_cmd_req_prepare(s, req)) { - QTAILQ_INSERT_TAIL(&reqs, req, next); - } - } - - QTAILQ_FOREACH_SAFE(req, &reqs, next, next) { - virtio_scsi_handle_cmd_req_submit(s, req); + if (virtio_should_notify(vdev, req->vq)) { + event_notifier_set(virtio_queue_get_guest_notifier(req->vq)); } } @@ -163,46 +71,10 @@ static void virtio_scsi_clear_aio(VirtIOSCSI *s) VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(s); int i; - if (s->ctrl_vring) { - aio_set_event_notifier(s->ctx, &s->ctrl_vring->host_notifier, - true, NULL); - } - if (s->event_vring) { - aio_set_event_notifier(s->ctx, &s->event_vring->host_notifier, - true, NULL); - } - if (s->cmd_vrings) { - for (i = 0; i < vs->conf.num_queues && s->cmd_vrings[i]; i++) { - aio_set_event_notifier(s->ctx, &s->cmd_vrings[i]->host_notifier, - true, NULL); - } - } -} - -static void virtio_scsi_vring_teardown(VirtIOSCSI *s) -{ - VirtIODevice *vdev = VIRTIO_DEVICE(s); - VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(s); - int i; - - if (s->ctrl_vring) { - vring_teardown(&s->ctrl_vring->vring, vdev, 0); - g_free(s->ctrl_vring); - s->ctrl_vring = NULL; - } - if (s->event_vring) { - vring_teardown(&s->event_vring->vring, vdev, 1); - g_free(s->event_vring); - s->event_vring = NULL; - } - if (s->cmd_vrings) { - for (i = 0; i < vs->conf.num_queues && s->cmd_vrings[i]; i++) { - vring_teardown(&s->cmd_vrings[i]->vring, vdev, 2 + i); - g_free(s->cmd_vrings[i]); - s->cmd_vrings[i] = NULL; - } - free(s->cmd_vrings); - s->cmd_vrings = NULL; + virtio_queue_aio_set_host_notifier_handler(vs->ctrl_vq, s->ctx, false, false); + virtio_queue_aio_set_host_notifier_handler(vs->event_vq, s->ctx, false, false); + for (i = 0; i < vs->conf.num_queues; i++) { + virtio_queue_aio_set_host_notifier_handler(vs->cmd_vqs[i], s->ctx, false, false); } } @@ -229,30 +101,21 @@ void virtio_scsi_dataplane_start(VirtIOSCSI *s) if (rc != 0) { fprintf(stderr, "virtio-scsi: Failed to set guest notifiers (%d), " "ensure -enable-kvm is set\n", rc); - s->dataplane_fenced = true; goto fail_guest_notifiers; } aio_context_acquire(s->ctx); - s->ctrl_vring = virtio_scsi_vring_init(s, vs->ctrl_vq, - virtio_scsi_iothread_handle_ctrl, - 0); - if (!s->ctrl_vring) { + rc = virtio_scsi_vring_init(s, vs->ctrl_vq, 0); + if (rc) { goto fail_vrings; } - s->event_vring = virtio_scsi_vring_init(s, vs->event_vq, - virtio_scsi_iothread_handle_event, - 1); - if (!s->event_vring) { + rc = virtio_scsi_vring_init(s, vs->event_vq, 1); + if (rc) { goto fail_vrings; } - s->cmd_vrings = g_new(VirtIOSCSIVring *, vs->conf.num_queues); for (i = 0; i < vs->conf.num_queues; i++) { - s->cmd_vrings[i] = - virtio_scsi_vring_init(s, vs->cmd_vqs[i], - virtio_scsi_iothread_handle_cmd, - i + 2); - if (!s->cmd_vrings[i]) { + rc = virtio_scsi_vring_init(s, vs->cmd_vqs[i], i + 2); + if (rc) { goto fail_vrings; } } @@ -265,13 +128,14 @@ void virtio_scsi_dataplane_start(VirtIOSCSI *s) fail_vrings: virtio_scsi_clear_aio(s); aio_context_release(s->ctx); - virtio_scsi_vring_teardown(s); for (i = 0; i < vs->conf.num_queues + 2; i++) { k->set_host_notifier(qbus->parent, i, false); } k->set_guest_notifiers(qbus->parent, vs->conf.num_queues + 2, false); fail_guest_notifiers: + s->dataplane_fenced = true; s->dataplane_starting = false; + s->dataplane_started = true; } /* Context: QEMU global mutex held */ @@ -282,12 +146,14 @@ void virtio_scsi_dataplane_stop(VirtIOSCSI *s) VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(s); int i; + if (!s->dataplane_started || s->dataplane_stopping) { + return; + } + /* Better luck next time. */ if (s->dataplane_fenced) { s->dataplane_fenced = false; - return; - } - if (!s->dataplane_started || s->dataplane_stopping) { + s->dataplane_started = false; return; } s->dataplane_stopping = true; @@ -295,24 +161,12 @@ void virtio_scsi_dataplane_stop(VirtIOSCSI *s) aio_context_acquire(s->ctx); - aio_set_event_notifier(s->ctx, &s->ctrl_vring->host_notifier, - true, NULL); - aio_set_event_notifier(s->ctx, &s->event_vring->host_notifier, - true, NULL); - for (i = 0; i < vs->conf.num_queues; i++) { - aio_set_event_notifier(s->ctx, &s->cmd_vrings[i]->host_notifier, - true, NULL); - } + virtio_scsi_clear_aio(s); blk_drain_all(); /* ensure there are no in-flight requests */ aio_context_release(s->ctx); - /* Sync vring state back to virtqueue so that non-dataplane request - * processing can continue when we disable the host notifier below. - */ - virtio_scsi_vring_teardown(s); - for (i = 0; i < vs->conf.num_queues + 2; i++) { k->set_host_notifier(qbus->parent, i, false); } diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c index 5b29baccf3..0c30d2e692 100644 --- a/hw/scsi/virtio-scsi.c +++ b/hw/scsi/virtio-scsi.c @@ -23,7 +23,6 @@ #include <block/scsi.h> #include <hw/virtio/virtio-bus.h> #include "hw/virtio/virtio-access.h" -#include "migration/migration.h" static inline int virtio_scsi_get_lun(uint8_t *lun) { @@ -43,7 +42,8 @@ static inline SCSIDevice *virtio_scsi_device_find(VirtIOSCSI *s, uint8_t *lun) void virtio_scsi_init_req(VirtIOSCSI *s, VirtQueue *vq, VirtIOSCSIReq *req) { - const size_t zero_skip = offsetof(VirtIOSCSIReq, vring); + const size_t zero_skip = + offsetof(VirtIOSCSIReq, resp_iov) + sizeof(req->resp_iov); req->vq = vq; req->dev = s; @@ -66,11 +66,10 @@ static void virtio_scsi_complete_req(VirtIOSCSIReq *req) VirtIODevice *vdev = VIRTIO_DEVICE(s); qemu_iovec_from_buf(&req->resp_iov, 0, &req->resp, req->resp_size); - if (req->vring) { - assert(req->vq == NULL); - virtio_scsi_vring_push_notify(req); + virtqueue_push(vq, &req->elem, req->qsgl.size + req->resp_iov.size); + if (s->dataplane_started) { + virtio_scsi_dataplane_notify(vdev, req); } else { - virtqueue_push(vq, &req->elem, req->qsgl.size + req->resp_iov.size); virtio_notify(vdev, vq); } @@ -417,7 +416,7 @@ static void virtio_scsi_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq) VirtIOSCSI *s = (VirtIOSCSI *)vdev; VirtIOSCSIReq *req; - if (s->ctx && !s->dataplane_disabled) { + if (s->ctx && !s->dataplane_started) { virtio_scsi_dataplane_start(s); return; } @@ -567,7 +566,7 @@ static void virtio_scsi_handle_cmd(VirtIODevice *vdev, VirtQueue *vq) VirtIOSCSIReq *req, *next; QTAILQ_HEAD(, VirtIOSCSIReq) reqs = QTAILQ_HEAD_INITIALIZER(reqs); - if (s->ctx && !s->dataplane_disabled) { + if (s->ctx && !s->dataplane_started) { virtio_scsi_dataplane_start(s); return; } @@ -687,11 +686,7 @@ void virtio_scsi_push_event(VirtIOSCSI *s, SCSIDevice *dev, aio_context_acquire(s->ctx); } - if (s->dataplane_started) { - req = virtio_scsi_pop_req_vring(s, s->event_vring); - } else { - req = virtio_scsi_pop_req(s, vs->event_vq); - } + req = virtio_scsi_pop_req(s, vs->event_vq); if (!req) { s->events_dropped = true; goto out; @@ -733,7 +728,7 @@ static void virtio_scsi_handle_event(VirtIODevice *vdev, VirtQueue *vq) { VirtIOSCSI *s = VIRTIO_SCSI(vdev); - if (s->ctx && !s->dataplane_disabled) { + if (s->ctx && !s->dataplane_started) { virtio_scsi_dataplane_start(s); return; } @@ -901,31 +896,6 @@ void virtio_scsi_common_realize(DeviceState *dev, Error **errp, } } -/* Disable dataplane thread during live migration since it does not - * update the dirty memory bitmap yet. - */ -static void virtio_scsi_migration_state_changed(Notifier *notifier, void *data) -{ - VirtIOSCSI *s = container_of(notifier, VirtIOSCSI, - migration_state_notifier); - MigrationState *mig = data; - - if (migration_in_setup(mig)) { - if (!s->dataplane_started) { - return; - } - virtio_scsi_dataplane_stop(s); - s->dataplane_disabled = true; - } else if (migration_has_finished(mig) || - migration_has_failed(mig)) { - if (s->dataplane_started) { - return; - } - blk_drain_all(); /* complete in-flight non-dataplane requests */ - s->dataplane_disabled = false; - } -} - static void virtio_scsi_device_realize(DeviceState *dev, Error **errp) { VirtIODevice *vdev = VIRTIO_DEVICE(dev); @@ -956,8 +926,6 @@ static void virtio_scsi_device_realize(DeviceState *dev, Error **errp) register_savevm(dev, "virtio-scsi", virtio_scsi_id++, 1, virtio_scsi_save, virtio_scsi_load, s); - s->migration_state_notifier.notify = virtio_scsi_migration_state_changed; - add_migration_state_change_notifier(&s->migration_state_notifier); error_setg(&s->blocker, "block device is in use by data plane"); @@ -991,8 +959,6 @@ static void virtio_scsi_device_unrealize(DeviceState *dev, Error **errp) error_free(s->blocker); unregister_savevm(dev, "virtio-scsi", s); - remove_migration_state_change_notifier(&s->migration_state_notifier); - virtio_scsi_common_unrealize(dev, errp); } diff --git a/hw/timer/Makefile.objs b/hw/timer/Makefile.objs index 133bd0d455..5cfea6e0da 100644 --- a/hw/timer/Makefile.objs +++ b/hw/timer/Makefile.objs @@ -25,7 +25,6 @@ obj-$(CONFIG_OMAP) += omap_gptimer.o obj-$(CONFIG_OMAP) += omap_synctimer.o obj-$(CONFIG_PXA2XX) += pxa2xx_timer.o obj-$(CONFIG_SH4) += sh_timer.o -obj-$(CONFIG_TUSB6010) += tusb6010.o obj-$(CONFIG_DIGIC) += digic-timer.o obj-$(CONFIG_MC146818RTC) += mc146818rtc.o diff --git a/hw/usb/Makefile.objs b/hw/usb/Makefile.objs index 8f00fbd8f6..2717027d34 100644 --- a/hw/usb/Makefile.objs +++ b/hw/usb/Makefile.objs @@ -10,6 +10,8 @@ common-obj-$(CONFIG_USB_EHCI_SYSBUS) += hcd-ehci-sysbus.o common-obj-$(CONFIG_USB_XHCI) += hcd-xhci.o common-obj-$(CONFIG_USB_MUSB) += hcd-musb.o +obj-$(CONFIG_TUSB6010) += tusb6010.o + # emulated usb devices common-obj-$(CONFIG_USB) += dev-hub.o common-obj-$(CONFIG_USB) += dev-hid.o diff --git a/hw/usb/core.c b/hw/usb/core.c index bea5e1ee8b..45fa00c517 100644 --- a/hw/usb/core.c +++ b/hw/usb/core.c @@ -129,9 +129,16 @@ static void do_token_setup(USBDevice *s, USBPacket *p) } usb_packet_copy(p, s->setup_buf, p->iov.size); + s->setup_index = 0; p->actual_length = 0; s->setup_len = (s->setup_buf[7] << 8) | s->setup_buf[6]; - s->setup_index = 0; + if (s->setup_len > sizeof(s->data_buf)) { + fprintf(stderr, + "usb_generic_handle_packet: ctrl buffer too small (%d > %zu)\n", + s->setup_len, sizeof(s->data_buf)); + p->status = USB_RET_STALL; + return; + } request = (s->setup_buf[0] << 8) | s->setup_buf[1]; value = (s->setup_buf[3] << 8) | s->setup_buf[2]; @@ -152,13 +159,6 @@ static void do_token_setup(USBDevice *s, USBPacket *p) } s->setup_state = SETUP_STATE_DATA; } else { - if (s->setup_len > sizeof(s->data_buf)) { - fprintf(stderr, - "usb_generic_handle_packet: ctrl buffer too small (%d > %zu)\n", - s->setup_len, sizeof(s->data_buf)); - p->status = USB_RET_STALL; - return; - } if (s->setup_len == 0) s->setup_state = SETUP_STATE_ACK; else @@ -177,7 +177,7 @@ static void do_token_in(USBDevice *s, USBPacket *p) request = (s->setup_buf[0] << 8) | s->setup_buf[1]; value = (s->setup_buf[3] << 8) | s->setup_buf[2]; index = (s->setup_buf[5] << 8) | s->setup_buf[4]; - + switch(s->setup_state) { case SETUP_STATE_ACK: if (!(s->setup_buf[0] & USB_DIR_IN)) { diff --git a/hw/usb/desc.h b/hw/usb/desc.h index 8e8db03a0c..4d81c68e0e 100644 --- a/hw/usb/desc.h +++ b/hw/usb/desc.h @@ -1,7 +1,6 @@ #ifndef QEMU_HW_USB_DESC_H #define QEMU_HW_USB_DESC_H -#include <inttypes.h> #include <wchar.h> /* binary representation */ diff --git a/hw/usb/dev-network.c b/hw/usb/dev-network.c index 985a6298bf..c6abd38c2a 100644 --- a/hw/usb/dev-network.c +++ b/hw/usb/dev-network.c @@ -654,7 +654,8 @@ typedef struct USBNetState { static int is_rndis(USBNetState *s) { - return s->dev.config->bConfigurationValue == DEV_RNDIS_CONFIG_VALUE; + return s->dev.config ? + s->dev.config->bConfigurationValue == DEV_RNDIS_CONFIG_VALUE : 0; } static int ndis_query(USBNetState *s, uint32_t oid, @@ -915,8 +916,9 @@ static int rndis_query_response(USBNetState *s, bufoffs = le32_to_cpu(buf->InformationBufferOffset) + 8; buflen = le32_to_cpu(buf->InformationBufferLength); - if (bufoffs + buflen > length) + if (buflen > length || bufoffs >= length || bufoffs + buflen > length) { return USB_RET_STALL; + } infobuflen = ndis_query(s, le32_to_cpu(buf->OID), bufoffs + (uint8_t *) buf, buflen, infobuf, @@ -961,8 +963,9 @@ static int rndis_set_response(USBNetState *s, bufoffs = le32_to_cpu(buf->InformationBufferOffset) + 8; buflen = le32_to_cpu(buf->InformationBufferLength); - if (bufoffs + buflen > length) + if (buflen > length || bufoffs >= length || bufoffs + buflen > length) { return USB_RET_STALL; + } ret = ndis_set(s, le32_to_cpu(buf->OID), bufoffs + (uint8_t *) buf, buflen); @@ -1212,8 +1215,9 @@ static void usb_net_handle_dataout(USBNetState *s, USBPacket *p) if (le32_to_cpu(msg->MessageType) == RNDIS_PACKET_MSG) { uint32_t offs = 8 + le32_to_cpu(msg->DataOffset); uint32_t size = le32_to_cpu(msg->DataLength); - if (offs + size <= len) + if (offs < len && size < len && offs + size <= len) { qemu_send_packet(qemu_get_queue(s->nic), s->out_buf + offs, size); + } } s->out_ptr -= len; memmove(s->out_buf, &s->out_buf[len], s->out_ptr); diff --git a/hw/usb/hcd-ohci.c b/hw/usb/hcd-ohci.c index bed55dda78..17ed4617ef 100644 --- a/hw/usb/hcd-ohci.c +++ b/hw/usb/hcd-ohci.c @@ -1347,16 +1347,6 @@ static void ohci_frame_boundary(void *opaque) */ static int ohci_bus_start(OHCIState *ohci) { - ohci->eof_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, - ohci_frame_boundary, - ohci); - - if (ohci->eof_timer == NULL) { - trace_usb_ohci_bus_eof_timer_failed(ohci->name); - ohci_die(ohci); - return 0; - } - trace_usb_ohci_start(ohci->name); /* Delay the first SOF event by one frame time as @@ -1373,11 +1363,7 @@ static int ohci_bus_start(OHCIState *ohci) static void ohci_bus_stop(OHCIState *ohci) { trace_usb_ohci_stop(ohci->name); - if (ohci->eof_timer) { - timer_del(ohci->eof_timer); - timer_free(ohci->eof_timer); - } - ohci->eof_timer = NULL; + timer_del(ohci->eof_timer); } /* Sets a flag in a port status register but only set it if the port is @@ -1907,6 +1893,9 @@ static void usb_ohci_init(OHCIState *ohci, DeviceState *dev, usb_packet_init(&ohci->usb_packet); ohci->async_td = 0; + + ohci->eof_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, + ohci_frame_boundary, ohci); } #define TYPE_PCI_OHCI "pci-ohci" @@ -1976,6 +1965,9 @@ static void usb_ohci_exit(PCIDevice *dev) if (!ohci->masterbus) { usb_bus_release(&s->bus); } + + timer_del(s->eof_timer); + timer_free(s->eof_timer); } static void usb_ohci_reset_pci(DeviceState *d) @@ -2041,23 +2033,13 @@ static bool ohci_eof_timer_needed(void *opaque) { OHCIState *ohci = opaque; - return ohci->eof_timer != NULL; -} - -static int ohci_eof_timer_pre_load(void *opaque) -{ - OHCIState *ohci = opaque; - - ohci_bus_start(ohci); - - return 0; + return timer_pending(ohci->eof_timer); } static const VMStateDescription vmstate_ohci_eof_timer = { .name = "ohci-core/eof-timer", .version_id = 1, .minimum_version_id = 1, - .pre_load = ohci_eof_timer_pre_load, .needed = ohci_eof_timer_needed, .fields = (VMStateField[]) { VMSTATE_TIMER_PTR(eof_timer, OHCIState), diff --git a/hw/usb/hcd-uhci.c b/hw/usb/hcd-uhci.c index 5ccfb8395a..c370240be2 100644 --- a/hw/usb/hcd-uhci.c +++ b/hw/usb/hcd-uhci.c @@ -773,8 +773,22 @@ static int uhci_handle_td(UHCIState *s, UHCIQueue *q, uint32_t qh_addr, bool spd; bool queuing = (q != NULL); uint8_t pid = td->token & 0xff; - UHCIAsync *async = uhci_async_find_td(s, td_addr); + UHCIAsync *async; + + switch (pid) { + case USB_TOKEN_OUT: + case USB_TOKEN_SETUP: + case USB_TOKEN_IN: + break; + default: + /* invalid pid : frame interrupted */ + s->status |= UHCI_STS_HCPERR; + s->cmd &= ~UHCI_CMD_RS; + uhci_update_irq(s); + return TD_RESULT_STOP_FRAME; + } + async = uhci_async_find_td(s, td_addr); if (async) { if (uhci_queue_verify(async->queue, qh_addr, td, td_addr, queuing)) { assert(q == NULL || q == async->queue); @@ -880,11 +894,7 @@ static int uhci_handle_td(UHCIState *s, UHCIQueue *q, uint32_t qh_addr, break; default: - /* invalid pid : frame interrupted */ - uhci_async_free(async); - s->status |= UHCI_STS_HCPERR; - uhci_update_irq(s); - return TD_RESULT_STOP_FRAME; + abort(); /* Never to execute */ } if (async->packet.status == USB_RET_ASYNC) { diff --git a/hw/timer/tusb6010.c b/hw/usb/tusb6010.c index 9f6af90806..9f6af90806 100644 --- a/hw/timer/tusb6010.c +++ b/hw/usb/tusb6010.c diff --git a/hw/vfio/Makefile.objs b/hw/vfio/Makefile.objs index d3248633c1..ceddbb8f99 100644 --- a/hw/vfio/Makefile.objs +++ b/hw/vfio/Makefile.objs @@ -3,4 +3,5 @@ obj-$(CONFIG_SOFTMMU) += common.o obj-$(CONFIG_PCI) += pci.o pci-quirks.o obj-$(CONFIG_SOFTMMU) += platform.o obj-$(CONFIG_SOFTMMU) += calxeda-xgmac.o +obj-$(CONFIG_SOFTMMU) += amd-xgbe.o endif diff --git a/hw/vfio/amd-xgbe.c b/hw/vfio/amd-xgbe.c new file mode 100644 index 0000000000..2c60310cf9 --- /dev/null +++ b/hw/vfio/amd-xgbe.c @@ -0,0 +1,56 @@ +/* + * AMD XGBE VFIO device + * + * Copyright Linaro Limited, 2015 + * + * Authors: + * Eric Auger <eric.auger@linaro.org> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "hw/vfio/vfio-amd-xgbe.h" + +static void amd_xgbe_realize(DeviceState *dev, Error **errp) +{ + VFIOPlatformDevice *vdev = VFIO_PLATFORM_DEVICE(dev); + VFIOAmdXgbeDeviceClass *k = VFIO_AMD_XGBE_DEVICE_GET_CLASS(dev); + + vdev->compat = g_strdup("amd,xgbe-seattle-v1a"); + + k->parent_realize(dev, errp); +} + +static const VMStateDescription vfio_platform_amd_xgbe_vmstate = { + .name = TYPE_VFIO_AMD_XGBE, + .unmigratable = 1, +}; + +static void vfio_amd_xgbe_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VFIOAmdXgbeDeviceClass *vcxc = + VFIO_AMD_XGBE_DEVICE_CLASS(klass); + vcxc->parent_realize = dc->realize; + dc->realize = amd_xgbe_realize; + dc->desc = "VFIO AMD XGBE"; + dc->vmsd = &vfio_platform_amd_xgbe_vmstate; +} + +static const TypeInfo vfio_amd_xgbe_dev_info = { + .name = TYPE_VFIO_AMD_XGBE, + .parent = TYPE_VFIO_PLATFORM, + .instance_size = sizeof(VFIOAmdXgbeDevice), + .class_init = vfio_amd_xgbe_class_init, + .class_size = sizeof(VFIOAmdXgbeDeviceClass), +}; + +static void register_amd_xgbe_dev_type(void) +{ + type_register_static(&vfio_amd_xgbe_dev_info); +} + +type_init(register_amd_xgbe_dev_type) diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index 49f3d2d239..20b505f4ec 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -1207,7 +1207,7 @@ static int vfio_msix_early_setup(VFIOPCIDevice *vdev) } if (pread(fd, &ctrl, sizeof(ctrl), - vdev->config_offset + pos + PCI_CAP_FLAGS) != sizeof(ctrl)) { + vdev->config_offset + pos + PCI_MSIX_FLAGS) != sizeof(ctrl)) { return -errno; } @@ -1505,10 +1505,11 @@ static void vfio_unmap_bars(VFIOPCIDevice *vdev) */ static uint8_t vfio_std_cap_max_size(PCIDevice *pdev, uint8_t pos) { - uint8_t tmp, next = 0xff; + uint8_t tmp; + uint16_t next = PCI_CONFIG_SPACE_SIZE; for (tmp = pdev->config[PCI_CAPABILITY_LIST]; tmp; - tmp = pdev->config[tmp + 1]) { + tmp = pdev->config[tmp + PCI_CAP_LIST_NEXT]) { if (tmp > pos && tmp < next) { next = tmp; } @@ -1697,7 +1698,7 @@ static int vfio_add_std_cap(VFIOPCIDevice *vdev, uint8_t pos) int ret; cap_id = pdev->config[pos]; - next = pdev->config[pos + 1]; + next = pdev->config[pos + PCI_CAP_LIST_NEXT]; /* * If it becomes important to configure capabilities to their actual @@ -1711,7 +1712,7 @@ static int vfio_add_std_cap(VFIOPCIDevice *vdev, uint8_t pos) * pci_add_capability always inserts the new capability at the head * of the chain. Therefore to end up with a chain that matches the * physical device, we insert from the end by making this recursive. - * This is also why we pre-caclulate size above as cached config space + * This is also why we pre-calculate size above as cached config space * will be changed as we unwind the stack. */ if (next) { @@ -1727,7 +1728,7 @@ static int vfio_add_std_cap(VFIOPCIDevice *vdev, uint8_t pos) } /* Use emulated next pointer to allow dropping caps */ - pci_set_byte(vdev->emulated_config_bits + pos + 1, 0xff); + pci_set_byte(vdev->emulated_config_bits + pos + PCI_CAP_LIST_NEXT, 0xff); switch (cap_id) { case PCI_CAP_ID_MSI: diff --git a/hw/virtio/Makefile.objs b/hw/virtio/Makefile.objs index 19b224a44d..3e2b175da8 100644 --- a/hw/virtio/Makefile.objs +++ b/hw/virtio/Makefile.objs @@ -2,7 +2,6 @@ common-obj-y += virtio-rng.o common-obj-$(CONFIG_VIRTIO_PCI) += virtio-pci.o common-obj-y += virtio-bus.o common-obj-y += virtio-mmio.o -obj-$(CONFIG_VIRTIO) += dataplane/ obj-y += virtio.o virtio-balloon.o obj-$(CONFIG_LINUX) += vhost.o vhost-backend.o vhost-user.o diff --git a/hw/virtio/dataplane/Makefile.objs b/hw/virtio/dataplane/Makefile.objs deleted file mode 100644 index 753a9cab44..0000000000 --- a/hw/virtio/dataplane/Makefile.objs +++ /dev/null @@ -1 +0,0 @@ -obj-y += vring.o diff --git a/hw/virtio/dataplane/vring.c b/hw/virtio/dataplane/vring.c deleted file mode 100644 index 4308d9f055..0000000000 --- a/hw/virtio/dataplane/vring.c +++ /dev/null @@ -1,549 +0,0 @@ -/* Copyright 2012 Red Hat, Inc. - * Copyright IBM, Corp. 2012 - * - * Based on Linux 2.6.39 vhost code: - * Copyright (C) 2009 Red Hat, Inc. - * Copyright (C) 2006 Rusty Russell IBM Corporation - * - * Author: Michael S. Tsirkin <mst@redhat.com> - * Stefan Hajnoczi <stefanha@redhat.com> - * - * Inspiration, some code, and most witty comments come from - * Documentation/virtual/lguest/lguest.c, by Rusty Russell - * - * This work is licensed under the terms of the GNU GPL, version 2. - */ - -#include "qemu/osdep.h" -#include "trace.h" -#include "hw/hw.h" -#include "exec/memory.h" -#include "exec/address-spaces.h" -#include "hw/virtio/virtio-access.h" -#include "hw/virtio/dataplane/vring.h" -#include "hw/virtio/dataplane/vring-accessors.h" -#include "qemu/error-report.h" - -/* vring_map can be coupled with vring_unmap or (if you still have the - * value returned in *mr) memory_region_unref. - * Returns NULL on failure. - * Callers that can handle a partial mapping must supply mapped_len pointer to - * get the actual length mapped. - * Passing mapped_len == NULL requires either a full mapping or a failure. - */ -static void *vring_map(MemoryRegion **mr, hwaddr phys, - hwaddr len, hwaddr *mapped_len, - bool is_write) -{ - MemoryRegionSection section = memory_region_find(get_system_memory(), phys, len); - uint64_t size; - - if (!section.mr) { - goto out; - } - - size = int128_get64(section.size); - assert(size); - - /* Passing mapped_len == NULL requires either a full mapping or a failure. */ - if (!mapped_len && size < len) { - goto out; - } - - if (is_write && section.readonly) { - goto out; - } - if (!memory_region_is_ram(section.mr)) { - goto out; - } - - /* Ignore regions with dirty logging, we cannot mark them dirty */ - if (memory_region_get_dirty_log_mask(section.mr)) { - goto out; - } - - if (mapped_len) { - *mapped_len = MIN(size, len); - } - - *mr = section.mr; - return memory_region_get_ram_ptr(section.mr) + section.offset_within_region; - -out: - memory_region_unref(section.mr); - *mr = NULL; - return NULL; -} - -static void vring_unmap(void *buffer, bool is_write) -{ - ram_addr_t addr; - MemoryRegion *mr; - - mr = qemu_ram_addr_from_host(buffer, &addr); - memory_region_unref(mr); -} - -/* Map the guest's vring to host memory */ -bool vring_setup(Vring *vring, VirtIODevice *vdev, int n) -{ - struct vring *vr = &vring->vr; - hwaddr addr; - hwaddr size; - void *ptr; - - vring->broken = false; - vr->num = virtio_queue_get_num(vdev, n); - - addr = virtio_queue_get_desc_addr(vdev, n); - size = virtio_queue_get_desc_size(vdev, n); - /* Map the descriptor area as read only */ - ptr = vring_map(&vring->mr_desc, addr, size, NULL, false); - if (!ptr) { - error_report("Failed to map 0x%" HWADDR_PRIx " byte for vring desc " - "at 0x%" HWADDR_PRIx, - size, addr); - goto out_err_desc; - } - vr->desc = ptr; - - addr = virtio_queue_get_avail_addr(vdev, n); - size = virtio_queue_get_avail_size(vdev, n); - /* Add the size of the used_event_idx */ - size += sizeof(uint16_t); - /* Map the driver area as read only */ - ptr = vring_map(&vring->mr_avail, addr, size, NULL, false); - if (!ptr) { - error_report("Failed to map 0x%" HWADDR_PRIx " byte for vring avail " - "at 0x%" HWADDR_PRIx, - size, addr); - goto out_err_avail; - } - vr->avail = ptr; - - addr = virtio_queue_get_used_addr(vdev, n); - size = virtio_queue_get_used_size(vdev, n); - /* Add the size of the avail_event_idx */ - size += sizeof(uint16_t); - /* Map the device area as read-write */ - ptr = vring_map(&vring->mr_used, addr, size, NULL, true); - if (!ptr) { - error_report("Failed to map 0x%" HWADDR_PRIx " byte for vring used " - "at 0x%" HWADDR_PRIx, - size, addr); - goto out_err_used; - } - vr->used = ptr; - - vring->last_avail_idx = virtio_queue_get_last_avail_idx(vdev, n); - vring->last_used_idx = vring_get_used_idx(vdev, vring); - vring->signalled_used = 0; - vring->signalled_used_valid = false; - - trace_vring_setup(virtio_queue_get_ring_addr(vdev, n), - vring->vr.desc, vring->vr.avail, vring->vr.used); - return true; - -out_err_used: - memory_region_unref(vring->mr_avail); -out_err_avail: - memory_region_unref(vring->mr_desc); -out_err_desc: - vring->broken = true; - return false; -} - -void vring_teardown(Vring *vring, VirtIODevice *vdev, int n) -{ - virtio_queue_set_last_avail_idx(vdev, n, vring->last_avail_idx); - virtio_queue_invalidate_signalled_used(vdev, n); - - memory_region_unref(vring->mr_desc); - memory_region_unref(vring->mr_avail); - memory_region_unref(vring->mr_used); -} - -/* Disable guest->host notifies */ -void vring_disable_notification(VirtIODevice *vdev, Vring *vring) -{ - if (!virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) { - vring_set_used_flags(vdev, vring, VRING_USED_F_NO_NOTIFY); - } -} - -/* Enable guest->host notifies - * - * Return true if the vring is empty, false if there are more requests. - */ -bool vring_enable_notification(VirtIODevice *vdev, Vring *vring) -{ - if (virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) { - vring_avail_event(&vring->vr) = vring->vr.avail->idx; - } else { - vring_clear_used_flags(vdev, vring, VRING_USED_F_NO_NOTIFY); - } - smp_mb(); /* ensure update is seen before reading avail_idx */ - return !vring_more_avail(vdev, vring); -} - -/* This is stolen from linux/drivers/vhost/vhost.c:vhost_notify() */ -bool vring_should_notify(VirtIODevice *vdev, Vring *vring) -{ - uint16_t old, new; - bool v; - /* Flush out used index updates. This is paired - * with the barrier that the Guest executes when enabling - * interrupts. */ - smp_mb(); - - if (virtio_vdev_has_feature(vdev, VIRTIO_F_NOTIFY_ON_EMPTY) && - unlikely(!vring_more_avail(vdev, vring))) { - return true; - } - - if (!virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) { - return !(vring_get_avail_flags(vdev, vring) & - VRING_AVAIL_F_NO_INTERRUPT); - } - old = vring->signalled_used; - v = vring->signalled_used_valid; - new = vring->signalled_used = vring->last_used_idx; - vring->signalled_used_valid = true; - - if (unlikely(!v)) { - return true; - } - - return vring_need_event(virtio_tswap16(vdev, vring_used_event(&vring->vr)), - new, old); -} - -typedef struct VirtQueueCurrentElement { - unsigned in_num; - unsigned out_num; - hwaddr addr[VIRTQUEUE_MAX_SIZE]; - struct iovec iov[VIRTQUEUE_MAX_SIZE]; -} VirtQueueCurrentElement; - -static int get_desc(Vring *vring, VirtQueueCurrentElement *elem, - struct vring_desc *desc) -{ - unsigned *num; - struct iovec *iov; - hwaddr *addr; - MemoryRegion *mr; - hwaddr len; - - if (desc->flags & VRING_DESC_F_WRITE) { - num = &elem->in_num; - iov = &elem->iov[elem->out_num + *num]; - addr = &elem->addr[elem->out_num + *num]; - } else { - num = &elem->out_num; - iov = &elem->iov[*num]; - addr = &elem->addr[*num]; - - /* If it's an output descriptor, they're all supposed - * to come before any input descriptors. */ - if (unlikely(elem->in_num)) { - error_report("Descriptor has out after in"); - return -EFAULT; - } - } - - while (desc->len) { - /* Stop for now if there are not enough iovecs available. */ - if (*num >= VIRTQUEUE_MAX_SIZE) { - error_report("Invalid SG num: %u", *num); - return -EFAULT; - } - - iov->iov_base = vring_map(&mr, desc->addr, desc->len, &len, - desc->flags & VRING_DESC_F_WRITE); - if (!iov->iov_base) { - error_report("Failed to map descriptor addr %#" PRIx64 " len %u", - (uint64_t)desc->addr, desc->len); - return -EFAULT; - } - - /* The MemoryRegion is looked up again and unref'ed later, leave the - * ref in place. */ - (iov++)->iov_len = len; - *addr++ = desc->addr; - desc->len -= len; - desc->addr += len; - *num += 1; - } - - return 0; -} - -static void copy_in_vring_desc(VirtIODevice *vdev, - const struct vring_desc *guest, - struct vring_desc *host) -{ - host->addr = virtio_ldq_p(vdev, &guest->addr); - host->len = virtio_ldl_p(vdev, &guest->len); - host->flags = virtio_lduw_p(vdev, &guest->flags); - host->next = virtio_lduw_p(vdev, &guest->next); -} - -static bool read_vring_desc(VirtIODevice *vdev, - hwaddr guest, - struct vring_desc *host) -{ - if (address_space_read(&address_space_memory, guest, MEMTXATTRS_UNSPECIFIED, - (uint8_t *)host, sizeof *host)) { - return false; - } - host->addr = virtio_tswap64(vdev, host->addr); - host->len = virtio_tswap32(vdev, host->len); - host->flags = virtio_tswap16(vdev, host->flags); - host->next = virtio_tswap16(vdev, host->next); - return true; -} - -/* This is stolen from linux/drivers/vhost/vhost.c. */ -static int get_indirect(VirtIODevice *vdev, Vring *vring, - VirtQueueCurrentElement *cur_elem, - struct vring_desc *indirect) -{ - struct vring_desc desc; - unsigned int i = 0, count, found = 0; - int ret; - - /* Sanity check */ - if (unlikely(indirect->len % sizeof(desc))) { - error_report("Invalid length in indirect descriptor: " - "len %#x not multiple of %#zx", - indirect->len, sizeof(desc)); - vring->broken = true; - return -EFAULT; - } - - count = indirect->len / sizeof(desc); - /* Buffers are chained via a 16 bit next field, so - * we can have at most 2^16 of these. */ - if (unlikely(count > USHRT_MAX + 1)) { - error_report("Indirect buffer length too big: %d", indirect->len); - vring->broken = true; - return -EFAULT; - } - - do { - /* Translate indirect descriptor */ - if (!read_vring_desc(vdev, indirect->addr + found * sizeof(desc), - &desc)) { - error_report("Failed to read indirect descriptor " - "addr %#" PRIx64 " len %zu", - (uint64_t)indirect->addr + found * sizeof(desc), - sizeof(desc)); - vring->broken = true; - return -EFAULT; - } - - /* Ensure descriptor has been loaded before accessing fields */ - barrier(); /* read_barrier_depends(); */ - - if (unlikely(++found > count)) { - error_report("Loop detected: last one at %u " - "indirect size %u", i, count); - vring->broken = true; - return -EFAULT; - } - - if (unlikely(desc.flags & VRING_DESC_F_INDIRECT)) { - error_report("Nested indirect descriptor"); - vring->broken = true; - return -EFAULT; - } - - ret = get_desc(vring, cur_elem, &desc); - if (ret < 0) { - vring->broken |= (ret == -EFAULT); - return ret; - } - i = desc.next; - } while (desc.flags & VRING_DESC_F_NEXT); - return 0; -} - -static void vring_unmap_element(VirtQueueElement *elem) -{ - int i; - - /* This assumes that the iovecs, if changed, are never moved past - * the end of the valid area. This is true if iovec manipulations - * are done with iov_discard_front and iov_discard_back. - */ - for (i = 0; i < elem->out_num; i++) { - vring_unmap(elem->out_sg[i].iov_base, false); - } - - for (i = 0; i < elem->in_num; i++) { - vring_unmap(elem->in_sg[i].iov_base, true); - } -} - -/* This looks in the virtqueue and for the first available buffer, and converts - * it to an iovec for convenient access. Since descriptors consist of some - * number of output then some number of input descriptors, it's actually two - * iovecs, but we pack them into one and note how many of each there were. - * - * This function returns the descriptor number found, or vq->num (which is - * never a valid descriptor number) if none was found. A negative code is - * returned on error. - * - * Stolen from linux/drivers/vhost/vhost.c. - */ -void *vring_pop(VirtIODevice *vdev, Vring *vring, size_t sz) -{ - struct vring_desc desc; - unsigned int i, head, found = 0, num = vring->vr.num; - uint16_t avail_idx, last_avail_idx; - VirtQueueCurrentElement cur_elem; - VirtQueueElement *elem = NULL; - int ret; - - /* If there was a fatal error then refuse operation */ - if (vring->broken) { - ret = -EFAULT; - goto out; - } - - cur_elem.in_num = cur_elem.out_num = 0; - - /* Check it isn't doing very strange things with descriptor numbers. */ - last_avail_idx = vring->last_avail_idx; - avail_idx = vring_get_avail_idx(vdev, vring); - barrier(); /* load indices now and not again later */ - - if (unlikely((uint16_t)(avail_idx - last_avail_idx) > num)) { - error_report("Guest moved used index from %u to %u", - last_avail_idx, avail_idx); - ret = -EFAULT; - goto out; - } - - /* If there's nothing new since last we looked. */ - if (avail_idx == last_avail_idx) { - ret = -EAGAIN; - goto out; - } - - /* Only get avail ring entries after they have been exposed by guest. */ - smp_rmb(); - - /* Grab the next descriptor number they're advertising, and increment - * the index we've seen. */ - head = vring_get_avail_ring(vdev, vring, last_avail_idx % num); - - /* If their number is silly, that's an error. */ - if (unlikely(head >= num)) { - error_report("Guest says index %u > %u is available", head, num); - ret = -EFAULT; - goto out; - } - - i = head; - do { - if (unlikely(i >= num)) { - error_report("Desc index is %u > %u, head = %u", i, num, head); - ret = -EFAULT; - goto out; - } - if (unlikely(++found > num)) { - error_report("Loop detected: last one at %u vq size %u head %u", - i, num, head); - ret = -EFAULT; - goto out; - } - copy_in_vring_desc(vdev, &vring->vr.desc[i], &desc); - - /* Ensure descriptor is loaded before accessing fields */ - barrier(); - - if (desc.flags & VRING_DESC_F_INDIRECT) { - ret = get_indirect(vdev, vring, &cur_elem, &desc); - if (ret < 0) { - goto out; - } - continue; - } - - ret = get_desc(vring, &cur_elem, &desc); - if (ret < 0) { - goto out; - } - - i = desc.next; - } while (desc.flags & VRING_DESC_F_NEXT); - - /* On success, increment avail index. */ - vring->last_avail_idx++; - if (virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) { - vring_avail_event(&vring->vr) = - virtio_tswap16(vdev, vring->last_avail_idx); - } - - /* Now copy what we have collected and mapped */ - elem = virtqueue_alloc_element(sz, cur_elem.out_num, cur_elem.in_num); - elem->index = head; - for (i = 0; i < cur_elem.out_num; i++) { - elem->out_addr[i] = cur_elem.addr[i]; - elem->out_sg[i] = cur_elem.iov[i]; - } - for (i = 0; i < cur_elem.in_num; i++) { - elem->in_addr[i] = cur_elem.addr[cur_elem.out_num + i]; - elem->in_sg[i] = cur_elem.iov[cur_elem.out_num + i]; - } - - return elem; - -out: - assert(ret < 0); - if (ret == -EFAULT) { - vring->broken = true; - } - - for (i = 0; i < cur_elem.out_num + cur_elem.in_num; i++) { - vring_unmap(cur_elem.iov[i].iov_base, false); - } - - g_free(elem); - return NULL; -} - -/* After we've used one of their buffers, we tell them about it. - * - * Stolen from linux/drivers/vhost/vhost.c. - */ -void vring_push(VirtIODevice *vdev, Vring *vring, VirtQueueElement *elem, - int len) -{ - unsigned int head = elem->index; - uint16_t new; - - vring_unmap_element(elem); - - /* Don't touch vring if a fatal error occurred */ - if (vring->broken) { - return; - } - - /* The virtqueue contains a ring of used buffers. Get a pointer to the - * next entry in that used ring. */ - vring_set_used_ring_id(vdev, vring, vring->last_used_idx % vring->vr.num, - head); - vring_set_used_ring_len(vdev, vring, vring->last_used_idx % vring->vr.num, - len); - - /* Make sure buffer is written before we update index. */ - smp_wmb(); - - new = ++vring->last_used_idx; - vring_set_used_idx(vdev, vring, new); - if (unlikely((int16_t)(new - vring->signalled_used) < (uint16_t)1)) { - vring->signalled_used_valid = false; - } -} diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index 7fde1370e0..7ed3dd9a13 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -611,6 +611,25 @@ static int vhost_user_migration_done(struct vhost_dev *dev, char* mac_addr) return -1; } +static bool vhost_user_can_merge(struct vhost_dev *dev, + uint64_t start1, uint64_t size1, + uint64_t start2, uint64_t size2) +{ + ram_addr_t ram_addr; + int mfd, rfd; + MemoryRegion *mr; + + mr = qemu_ram_addr_from_host((void *)(uintptr_t)start1, &ram_addr); + assert(mr); + mfd = qemu_get_ram_fd(ram_addr); + + mr = qemu_ram_addr_from_host((void *)(uintptr_t)start2, &ram_addr); + assert(mr); + rfd = qemu_get_ram_fd(ram_addr); + + return mfd == rfd; +} + const VhostOps user_ops = { .backend_type = VHOST_BACKEND_TYPE_USER, .vhost_backend_init = vhost_user_init, @@ -633,4 +652,5 @@ const VhostOps user_ops = { .vhost_set_vring_enable = vhost_user_set_vring_enable, .vhost_requires_shm_log = vhost_user_requires_shm_log, .vhost_migration_done = vhost_user_migration_done, + .vhost_backend_can_merge = vhost_user_can_merge, }; diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c index 7dff75547d..392d848819 100644 --- a/hw/virtio/vhost.c +++ b/hw/virtio/vhost.c @@ -260,6 +260,13 @@ static void vhost_dev_assign_memory(struct vhost_dev *dev, continue; } + if (dev->vhost_ops->vhost_backend_can_merge && + !dev->vhost_ops->vhost_backend_can_merge(dev, uaddr, size, + reg->userspace_addr, + reg->memory_size)) { + continue; + } + if (merged) { --to; assert(to >= 0); @@ -749,6 +756,27 @@ static void vhost_log_stop(MemoryListener *listener, /* FIXME: implement */ } +/* The vhost driver natively knows how to handle the vrings of non + * cross-endian legacy devices and modern devices. Only legacy devices + * exposed to a bi-endian guest may require the vhost driver to use a + * specific endianness. + */ +static inline bool vhost_needs_vring_endian(VirtIODevice *vdev) +{ + if (virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1)) { + return false; + } +#ifdef TARGET_IS_BIENDIAN +#ifdef HOST_WORDS_BIGENDIAN + return vdev->device_endian == VIRTIO_DEVICE_ENDIAN_LITTLE; +#else + return vdev->device_endian == VIRTIO_DEVICE_ENDIAN_BIG; +#endif +#else + return false; +#endif +} + static int vhost_virtqueue_set_vring_endian_legacy(struct vhost_dev *dev, bool is_big_endian, int vhost_vq_index) @@ -799,8 +827,7 @@ static int vhost_virtqueue_start(struct vhost_dev *dev, return -errno; } - if (!virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1) && - virtio_legacy_is_cross_endian(vdev)) { + if (vhost_needs_vring_endian(vdev)) { r = vhost_virtqueue_set_vring_endian_legacy(dev, virtio_is_big_endian(vdev), vhost_vq_index); @@ -855,6 +882,14 @@ static int vhost_virtqueue_start(struct vhost_dev *dev, /* Clear and discard previous events if any. */ event_notifier_test_and_clear(&vq->masked_notifier); + /* Init vring in unmasked state, unless guest_notifier_mask + * will do it later. + */ + if (!vdev->use_guest_notifier_mask) { + /* TODO: check and handle errors. */ + vhost_virtqueue_mask(dev, vdev, idx, false); + } + return 0; fail_kick: @@ -896,8 +931,7 @@ static void vhost_virtqueue_stop(struct vhost_dev *dev, /* In the cross-endian case, we need to reset the vring endianness to * native as legacy devices expect so by default. */ - if (!virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1) && - virtio_legacy_is_cross_endian(vdev)) { + if (vhost_needs_vring_endian(vdev)) { r = vhost_virtqueue_set_vring_endian_legacy(dev, !virtio_is_big_endian(vdev), vhost_vq_index); @@ -1148,6 +1182,7 @@ void vhost_virtqueue_mask(struct vhost_dev *hdev, VirtIODevice *vdev, int n, struct vhost_vring_file file; if (mask) { + assert(vdev->use_guest_notifier_mask); file.fd = event_notifier_get_fd(&hdev->vqs[index].masked_notifier); } else { file.fd = event_notifier_get_fd(virtio_queue_get_guest_notifier(vvq)); diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c index a382f43f92..e9c30e9615 100644 --- a/hw/virtio/virtio-balloon.c +++ b/hw/virtio/virtio-balloon.c @@ -305,6 +305,39 @@ static void virtio_balloon_get_config(VirtIODevice *vdev, uint8_t *config_data) memcpy(config_data, &config, sizeof(struct virtio_balloon_config)); } +static int build_dimm_list(Object *obj, void *opaque) +{ + GSList **list = opaque; + + if (object_dynamic_cast(obj, TYPE_PC_DIMM)) { + DeviceState *dev = DEVICE(obj); + if (dev->realized) { /* only realized DIMMs matter */ + *list = g_slist_prepend(*list, dev); + } + } + + object_child_foreach(obj, build_dimm_list, opaque); + return 0; +} + +static ram_addr_t get_current_ram_size(void) +{ + GSList *list = NULL, *item; + ram_addr_t size = ram_size; + + build_dimm_list(qdev_get_machine(), &list); + for (item = list; item; item = g_slist_next(item)) { + Object *obj = OBJECT(item->data); + if (!strcmp(object_get_typename(obj), TYPE_PC_DIMM)) { + size += object_property_get_int(obj, PC_DIMM_SIZE_PROP, + &error_abort); + } + } + g_slist_free(list); + + return size; +} + static void virtio_balloon_set_config(VirtIODevice *vdev, const uint8_t *config_data) { diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c index 5494ff4a49..440776c06c 100644 --- a/hw/virtio/virtio-pci.c +++ b/hw/virtio/virtio-pci.c @@ -806,7 +806,7 @@ static int kvm_virtio_pci_vector_use(VirtIOPCIProxy *proxy, int nvqs) /* If guest supports masking, set up irqfd now. * Otherwise, delay until unmasked in the frontend. */ - if (k->guest_notifier_mask) { + if (vdev->use_guest_notifier_mask && k->guest_notifier_mask) { ret = kvm_virtio_pci_irqfd_use(proxy, queue_no, vector); if (ret < 0) { kvm_virtio_pci_vq_vector_release(proxy, vector); @@ -822,7 +822,7 @@ undo: if (vector >= msix_nr_vectors_allocated(dev)) { continue; } - if (k->guest_notifier_mask) { + if (vdev->use_guest_notifier_mask && k->guest_notifier_mask) { kvm_virtio_pci_irqfd_release(proxy, queue_no, vector); } kvm_virtio_pci_vq_vector_release(proxy, vector); @@ -849,7 +849,7 @@ static void kvm_virtio_pci_vector_release(VirtIOPCIProxy *proxy, int nvqs) /* If guest supports masking, clean up irqfd now. * Otherwise, it was cleaned when masked in the frontend. */ - if (k->guest_notifier_mask) { + if (vdev->use_guest_notifier_mask && k->guest_notifier_mask) { kvm_virtio_pci_irqfd_release(proxy, queue_no, vector); } kvm_virtio_pci_vq_vector_release(proxy, vector); @@ -882,7 +882,7 @@ static int virtio_pci_vq_vector_unmask(VirtIOPCIProxy *proxy, /* If guest supports masking, irqfd is already setup, unmask it. * Otherwise, set it up now. */ - if (k->guest_notifier_mask) { + if (vdev->use_guest_notifier_mask && k->guest_notifier_mask) { k->guest_notifier_mask(vdev, queue_no, false); /* Test after unmasking to avoid losing events. */ if (k->guest_notifier_pending && @@ -905,7 +905,7 @@ static void virtio_pci_vq_vector_mask(VirtIOPCIProxy *proxy, /* If guest supports masking, keep irqfd but mask it. * Otherwise, clean it up now. */ - if (k->guest_notifier_mask) { + if (vdev->use_guest_notifier_mask && k->guest_notifier_mask) { k->guest_notifier_mask(vdev, queue_no, true); } else { kvm_virtio_pci_irqfd_release(proxy, queue_no, vector); @@ -1022,7 +1022,9 @@ static int virtio_pci_set_guest_notifier(DeviceState *d, int n, bool assign, event_notifier_cleanup(notifier); } - if (!msix_enabled(&proxy->pci_dev) && vdc->guest_notifier_mask) { + if (!msix_enabled(&proxy->pci_dev) && + vdev->use_guest_notifier_mask && + vdc->guest_notifier_mask) { vdc->guest_notifier_mask(vdev, n, !assign); } diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c index 90f25451d0..08275a9848 100644 --- a/hw/virtio/virtio.c +++ b/hw/virtio/virtio.c @@ -1162,7 +1162,7 @@ void virtio_irq(VirtQueue *vq) virtio_notify_vector(vq->vdev, vq->vector); } -static bool vring_notify(VirtIODevice *vdev, VirtQueue *vq) +bool virtio_should_notify(VirtIODevice *vdev, VirtQueue *vq) { uint16_t old, new; bool v; @@ -1187,7 +1187,7 @@ static bool vring_notify(VirtIODevice *vdev, VirtQueue *vq) void virtio_notify(VirtIODevice *vdev, VirtQueue *vq) { - if (!vring_notify(vdev, vq)) { + if (!virtio_should_notify(vdev, vq)) { return; } @@ -1677,6 +1677,7 @@ 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(); + vdev->use_guest_notifier_mask = true; } hwaddr virtio_queue_get_desc_addr(VirtIODevice *vdev, int n) @@ -1785,6 +1786,22 @@ static void virtio_queue_host_notifier_read(EventNotifier *n) } } +void virtio_queue_aio_set_host_notifier_handler(VirtQueue *vq, AioContext *ctx, + bool assign, bool set_handler) +{ + if (assign && set_handler) { + aio_set_event_notifier(ctx, &vq->host_notifier, true, + virtio_queue_host_notifier_read); + } else { + aio_set_event_notifier(ctx, &vq->host_notifier, true, NULL); + } + if (!assign) { + /* Test and clear notifier before after disabling event, + * in case poll callback didn't have time to run. */ + virtio_queue_host_notifier_read(&vq->host_notifier); + } +} + void virtio_queue_set_host_notifier_fd_handler(VirtQueue *vq, bool assign, bool set_handler) { |