diff options
Diffstat (limited to 'hw')
47 files changed, 2754 insertions, 417 deletions
diff --git a/hw/alpha/dp264.c b/hw/alpha/dp264.c index 9fe7e8b5cb..f86e7bb830 100644 --- a/hw/alpha/dp264.c +++ b/hw/alpha/dp264.c @@ -55,7 +55,7 @@ static void clipper_init(MachineState *machine) ISABus *isa_bus; qemu_irq rtc_irq; long size, i; - const char *palcode_filename; + char *palcode_filename; uint64_t palcode_entry, palcode_low, palcode_high; uint64_t kernel_entry, kernel_low, kernel_high; @@ -101,8 +101,8 @@ static void clipper_init(MachineState *machine) /* Load PALcode. Given that this is not "real" cpu palcode, but one explicitly written for the emulation, we might as well load it directly from and ELF image. */ - palcode_filename = (bios_name ? bios_name : "palcode-clipper"); - palcode_filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, palcode_filename); + palcode_filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, + bios_name ? bios_name : "palcode-clipper"); if (palcode_filename == NULL) { hw_error("no palcode provided\n"); exit(1); @@ -114,6 +114,7 @@ static void clipper_init(MachineState *machine) hw_error("could not load palcode '%s'\n", palcode_filename); exit(1); } + g_free(palcode_filename); /* Start all cpus at the PALcode RESET entry point. */ for (i = 0; i < smp_cpus; ++i) { diff --git a/hw/alpha/typhoon.c b/hw/alpha/typhoon.c index 7df842dff7..421162e1d4 100644 --- a/hw/alpha/typhoon.c +++ b/hw/alpha/typhoon.c @@ -841,7 +841,7 @@ PCIBus *typhoon_init(ram_addr_t ram_size, ISABus **isa_bus, } } - *p_rtc_irq = *qemu_allocate_irqs(typhoon_set_timer_irq, s, 1); + *p_rtc_irq = qemu_allocate_irq(typhoon_set_timer_irq, s, 0); /* Main memory region, 0x00.0000.0000. Real hardware supports 32GB, but the address space hole reserved at this point is 8TB. */ @@ -918,11 +918,11 @@ PCIBus *typhoon_init(ram_addr_t ram_size, ISABus **isa_bus, /* Init the ISA bus. */ /* ??? Technically there should be a cy82c693ub pci-isa bridge. */ { - qemu_irq isa_pci_irq, *isa_irqs; + qemu_irq *isa_irqs; *isa_bus = isa_bus_new(NULL, get_system_memory(), &s->pchip.reg_io); - isa_pci_irq = *qemu_allocate_irqs(typhoon_set_isa_irq, s, 1); - isa_irqs = i8259_init(*isa_bus, isa_pci_irq); + isa_irqs = i8259_init(*isa_bus, + qemu_allocate_irq(typhoon_set_isa_irq, s, 0)); isa_bus_irqs(*isa_bus, isa_irqs); } diff --git a/hw/arm/Makefile.objs b/hw/arm/Makefile.objs index 4b09caf594..cf346c1d0a 100644 --- a/hw/arm/Makefile.objs +++ b/hw/arm/Makefile.objs @@ -5,6 +5,7 @@ obj-y += omap_sx1.o palm.o realview.o spitz.o stellaris.o obj-y += tosa.o versatilepb.o vexpress.o virt.o xilinx_zynq.o z2.o obj-$(CONFIG_ACPI) += virt-acpi-build.o obj-y += netduino2.o +obj-y += sysbus-fdt.o obj-y += armv7m.o exynos4210.o pxa2xx.o pxa2xx_gpio.o pxa2xx_pic.o obj-$(CONFIG_DIGIC) += digic.o diff --git a/hw/arm/boot.c b/hw/arm/boot.c index fa6950352c..d036624948 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -557,7 +557,7 @@ static void load_image_to_fw_cfg(FWCfgState *fw_cfg, uint16_t size_key, fw_cfg_add_bytes(fw_cfg, data_key, data, size); } -void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) +static void arm_load_kernel_notify(Notifier *notifier, void *data) { CPUState *cs; int kernel_size; @@ -568,6 +568,11 @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) hwaddr entry, kernel_load_offset; int big_endian; static const ARMInsnFixup *primary_loader; + ArmLoadKernelNotifier *n = DO_UPCAST(ArmLoadKernelNotifier, + notifier, notifier); + ARMCPU *cpu = n->cpu; + struct arm_boot_info *info = + container_of(n, struct arm_boot_info, load_kernel_notifier); /* CPU objects (unlike devices) are not automatically reset on system * reset, so we must always register a handler to do so. If we're @@ -775,3 +780,10 @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) ARM_CPU(cs)->env.boot_info = info; } } + +void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) +{ + info->load_kernel_notifier.cpu = cpu; + info->load_kernel_notifier.notifier.notify = arm_load_kernel_notify; + qemu_add_machine_init_done_notifier(&info->load_kernel_notifier.notifier); +} diff --git a/hw/arm/nseries.c b/hw/arm/nseries.c index d243159664..a659e8525d 100644 --- a/hw/arm/nseries.c +++ b/hw/arm/nseries.c @@ -133,9 +133,8 @@ static void n800_mmc_cs_cb(void *opaque, int line, int level) static void n8x0_gpio_setup(struct n800_s *s) { - qemu_irq *mmc_cs = qemu_allocate_irqs(n800_mmc_cs_cb, s->mpu->mmc, 1); - qdev_connect_gpio_out(s->mpu->gpio, N8X0_MMC_CS_GPIO, mmc_cs[0]); - + qdev_connect_gpio_out(s->mpu->gpio, N8X0_MMC_CS_GPIO, + qemu_allocate_irq(n800_mmc_cs_cb, s->mpu->mmc, 0)); qemu_irq_lower(qdev_get_gpio_in(s->mpu->gpio, N800_BAT_COVER_GPIO)); } diff --git a/hw/arm/omap_sx1.c b/hw/arm/omap_sx1.c index 671e02c4ed..4b0f7f9c42 100644 --- a/hw/arm/omap_sx1.c +++ b/hw/arm/omap_sx1.c @@ -103,7 +103,6 @@ static void sx1_init(MachineState *machine, const int version) struct omap_mpu_state_s *mpu; MemoryRegion *address_space = get_system_memory(); MemoryRegion *flash = g_new(MemoryRegion, 1); - MemoryRegion *flash_1 = g_new(MemoryRegion, 1); MemoryRegion *cs = g_new(MemoryRegion, 4); static uint32_t cs0val = 0x00213090; static uint32_t cs1val = 0x00215070; @@ -165,6 +164,7 @@ static void sx1_init(MachineState *machine, const int version) if ((version == 1) && (dinfo = drive_get(IF_PFLASH, 0, fl_idx)) != NULL) { + MemoryRegion *flash_1 = g_new(MemoryRegion, 1); memory_region_init_ram(flash_1, NULL, "omap_sx1.flash1-0", flash1_size, &error_abort); vmstate_register_ram_global(flash_1); diff --git a/hw/arm/sysbus-fdt.c b/hw/arm/sysbus-fdt.c new file mode 100644 index 0000000000..3038b94b4a --- /dev/null +++ b/hw/arm/sysbus-fdt.c @@ -0,0 +1,174 @@ +/* + * ARM Platform Bus device tree generation helpers + * + * Copyright (c) 2014 Linaro Limited + * + * Authors: + * Alex Graf <agraf@suse.de> + * Eric Auger <eric.auger@linaro.org> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2 or later, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + * + */ + +#include "hw/arm/sysbus-fdt.h" +#include "qemu/error-report.h" +#include "sysemu/device_tree.h" +#include "hw/platform-bus.h" +#include "sysemu/sysemu.h" + +/* + * internal struct that contains the information to create dynamic + * sysbus device node + */ +typedef struct PlatformBusFDTData { + void *fdt; /* device tree handle */ + int irq_start; /* index of the first IRQ usable by platform bus devices */ + const char *pbus_node_name; /* name of the platform bus node */ + PlatformBusDevice *pbus; +} PlatformBusFDTData; + +/* + * struct used when calling the machine init done notifier + * that constructs the fdt nodes of platform bus devices + */ +typedef struct PlatformBusFDTNotifierParams { + Notifier notifier; + ARMPlatformBusFDTParams *fdt_params; +} PlatformBusFDTNotifierParams; + +/* struct that associates a device type name and a node creation function */ +typedef struct NodeCreationPair { + const char *typename; + int (*add_fdt_node_fn)(SysBusDevice *sbdev, void *opaque); +} NodeCreationPair; + +/* list of supported dynamic sysbus devices */ +static const NodeCreationPair add_fdt_node_functions[] = { + {"", NULL}, /* last element */ +}; + +/** + * add_fdt_node - add the device tree node of a dynamic sysbus device + * + * @sbdev: handle to the sysbus device + * @opaque: handle to the PlatformBusFDTData + * + * Checks the sysbus type belongs to the list of device types that + * are dynamically instantiable and if so call the node creation + * function. + */ +static int add_fdt_node(SysBusDevice *sbdev, void *opaque) +{ + int i, ret; + + for (i = 0; i < ARRAY_SIZE(add_fdt_node_functions); i++) { + if (!strcmp(object_get_typename(OBJECT(sbdev)), + add_fdt_node_functions[i].typename)) { + ret = add_fdt_node_functions[i].add_fdt_node_fn(sbdev, opaque); + assert(!ret); + return 0; + } + } + error_report("Device %s can not be dynamically instantiated", + qdev_fw_name(DEVICE(sbdev))); + exit(1); +} + +/** + * add_all_platform_bus_fdt_nodes - create all the platform bus nodes + * + * builds the parent platform bus node and all the nodes of dynamic + * sysbus devices attached to it. + */ +static void add_all_platform_bus_fdt_nodes(ARMPlatformBusFDTParams *fdt_params) +{ + const char platcomp[] = "qemu,platform\0simple-bus"; + PlatformBusDevice *pbus; + DeviceState *dev; + gchar *node; + uint64_t addr, size; + int irq_start, dtb_size; + struct arm_boot_info *info = fdt_params->binfo; + const ARMPlatformBusSystemParams *params = fdt_params->system_params; + const char *intc = fdt_params->intc; + void *fdt = info->get_dtb(info, &dtb_size); + + /* + * If the user provided a dtb, we assume the dynamic sysbus nodes + * already are integrated there. This corresponds to a use case where + * the dynamic sysbus nodes are complex and their generation is not yet + * supported. In that case the user can take charge of the guest dt + * while qemu takes charge of the qom stuff. + */ + if (info->dtb_filename) { + return; + } + + assert(fdt); + + node = g_strdup_printf("/platform@%"PRIx64, params->platform_bus_base); + addr = params->platform_bus_base; + size = params->platform_bus_size; + irq_start = params->platform_bus_first_irq; + + /* Create a /platform node that we can put all devices into */ + qemu_fdt_add_subnode(fdt, node); + qemu_fdt_setprop(fdt, node, "compatible", platcomp, sizeof(platcomp)); + + /* Our platform bus region is less than 32bits, so 1 cell is enough for + * address and size + */ + qemu_fdt_setprop_cells(fdt, node, "#size-cells", 1); + qemu_fdt_setprop_cells(fdt, node, "#address-cells", 1); + qemu_fdt_setprop_cells(fdt, node, "ranges", 0, addr >> 32, addr, size); + + qemu_fdt_setprop_phandle(fdt, node, "interrupt-parent", intc); + + dev = qdev_find_recursive(sysbus_get_default(), TYPE_PLATFORM_BUS_DEVICE); + pbus = PLATFORM_BUS_DEVICE(dev); + + /* We can only create dt nodes for dynamic devices when they're ready */ + assert(pbus->done_gathering); + + PlatformBusFDTData data = { + .fdt = fdt, + .irq_start = irq_start, + .pbus_node_name = node, + .pbus = pbus, + }; + + /* Loop through all dynamic sysbus devices and create their node */ + foreach_dynamic_sysbus_device(add_fdt_node, &data); + + g_free(node); +} + +static void platform_bus_fdt_notify(Notifier *notifier, void *data) +{ + PlatformBusFDTNotifierParams *p = DO_UPCAST(PlatformBusFDTNotifierParams, + notifier, notifier); + + add_all_platform_bus_fdt_nodes(p->fdt_params); + g_free(p->fdt_params); + g_free(p); +} + +void arm_register_platform_bus_fdt_creator(ARMPlatformBusFDTParams *fdt_params) +{ + PlatformBusFDTNotifierParams *p = g_new(PlatformBusFDTNotifierParams, 1); + + p->fdt_params = fdt_params; + p->notifier.notify = platform_bus_fdt_notify; + qemu_add_machine_init_done_notifier(&p->notifier); +} diff --git a/hw/arm/virt.c b/hw/arm/virt.c index 05db8cb2f7..0a75cc83ee 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -45,9 +45,11 @@ #include "qemu/error-report.h" #include "hw/pci-host/gpex.h" #include "hw/arm/virt-acpi-build.h" +#include "hw/arm/sysbus-fdt.h" +#include "hw/platform-bus.h" /* Number of external interrupt lines to configure the GIC with */ -#define NUM_IRQS 128 +#define NUM_IRQS 256 #define GIC_FDT_IRQ_TYPE_SPI 0 #define GIC_FDT_IRQ_TYPE_PPI 1 @@ -60,6 +62,10 @@ #define GIC_FDT_IRQ_PPI_CPU_START 8 #define GIC_FDT_IRQ_PPI_CPU_WIDTH 8 +#define PLATFORM_BUS_NUM_IRQS 64 + +static ARMPlatformBusSystemParams platform_bus_params; + typedef struct VirtBoardInfo { struct arm_boot_info bootinfo; const char *cpu_model; @@ -69,6 +75,8 @@ typedef struct VirtBoardInfo { void *fdt; int fdt_size; uint32_t clock_phandle; + uint32_t gic_phandle; + uint32_t v2m_phandle; } VirtBoardInfo; typedef struct { @@ -103,20 +111,22 @@ typedef struct { */ static const MemMapEntry a15memmap[] = { /* Space up to 0x8000000 is reserved for a boot ROM */ - [VIRT_FLASH] = { 0, 0x08000000 }, - [VIRT_CPUPERIPHS] = { 0x08000000, 0x00020000 }, + [VIRT_FLASH] = { 0, 0x08000000 }, + [VIRT_CPUPERIPHS] = { 0x08000000, 0x00020000 }, /* GIC distributor and CPU interfaces sit inside the CPU peripheral space */ - [VIRT_GIC_DIST] = { 0x08000000, 0x00010000 }, - [VIRT_GIC_CPU] = { 0x08010000, 0x00010000 }, - [VIRT_UART] = { 0x09000000, 0x00001000 }, - [VIRT_RTC] = { 0x09010000, 0x00001000 }, - [VIRT_FW_CFG] = { 0x09020000, 0x0000000a }, - [VIRT_MMIO] = { 0x0a000000, 0x00000200 }, + [VIRT_GIC_DIST] = { 0x08000000, 0x00010000 }, + [VIRT_GIC_CPU] = { 0x08010000, 0x00010000 }, + [VIRT_GIC_V2M] = { 0x08020000, 0x00001000 }, + [VIRT_UART] = { 0x09000000, 0x00001000 }, + [VIRT_RTC] = { 0x09010000, 0x00001000 }, + [VIRT_FW_CFG] = { 0x09020000, 0x0000000a }, + [VIRT_MMIO] = { 0x0a000000, 0x00000200 }, /* ...repeating for a total of NUM_VIRTIO_TRANSPORTS, each of that size */ - [VIRT_PCIE_MMIO] = { 0x10000000, 0x2eff0000 }, - [VIRT_PCIE_PIO] = { 0x3eff0000, 0x00010000 }, - [VIRT_PCIE_ECAM] = { 0x3f000000, 0x01000000 }, - [VIRT_MEM] = { 0x40000000, 30ULL * 1024 * 1024 * 1024 }, + [VIRT_PLATFORM_BUS] = { 0x0c000000, 0x02000000 }, + [VIRT_PCIE_MMIO] = { 0x10000000, 0x2eff0000 }, + [VIRT_PCIE_PIO] = { 0x3eff0000, 0x00010000 }, + [VIRT_PCIE_ECAM] = { 0x3f000000, 0x01000000 }, + [VIRT_MEM] = { 0x40000000, 30ULL * 1024 * 1024 * 1024 }, }; static const int a15irqmap[] = { @@ -124,6 +134,8 @@ static const int a15irqmap[] = { [VIRT_RTC] = 2, [VIRT_PCIE] = 3, /* ... to 6 */ [VIRT_MMIO] = 16, /* ...to 16 + NUM_VIRTIO_TRANSPORTS - 1 */ + [VIRT_GIC_V2M] = 48, /* ...to 48 + NUM_GICV2M_SPIS - 1 */ + [VIRT_PLATFORM_BUS] = 112, /* ...to 112 + PLATFORM_BUS_NUM_IRQS -1 */ }; static VirtBoardInfo machines[] = { @@ -299,12 +311,23 @@ static void fdt_add_cpu_nodes(const VirtBoardInfo *vbi) } } -static uint32_t fdt_add_gic_node(const VirtBoardInfo *vbi) +static void fdt_add_v2m_gic_node(VirtBoardInfo *vbi) { - uint32_t gic_phandle; + vbi->v2m_phandle = qemu_fdt_alloc_phandle(vbi->fdt); + qemu_fdt_add_subnode(vbi->fdt, "/intc/v2m"); + qemu_fdt_setprop_string(vbi->fdt, "/intc/v2m", "compatible", + "arm,gic-v2m-frame"); + qemu_fdt_setprop(vbi->fdt, "/intc/v2m", "msi-controller", NULL, 0); + qemu_fdt_setprop_sized_cells(vbi->fdt, "/intc/v2m", "reg", + 2, vbi->memmap[VIRT_GIC_V2M].base, + 2, vbi->memmap[VIRT_GIC_V2M].size); + qemu_fdt_setprop_cell(vbi->fdt, "/intc/v2m", "phandle", vbi->v2m_phandle); +} - gic_phandle = qemu_fdt_alloc_phandle(vbi->fdt); - qemu_fdt_setprop_cell(vbi->fdt, "/", "interrupt-parent", gic_phandle); +static void fdt_add_gic_node(VirtBoardInfo *vbi) +{ + vbi->gic_phandle = qemu_fdt_alloc_phandle(vbi->fdt); + qemu_fdt_setprop_cell(vbi->fdt, "/", "interrupt-parent", vbi->gic_phandle); qemu_fdt_add_subnode(vbi->fdt, "/intc"); /* 'cortex-a15-gic' means 'GIC v2' */ @@ -317,12 +340,32 @@ static uint32_t fdt_add_gic_node(const VirtBoardInfo *vbi) 2, vbi->memmap[VIRT_GIC_DIST].size, 2, vbi->memmap[VIRT_GIC_CPU].base, 2, vbi->memmap[VIRT_GIC_CPU].size); - qemu_fdt_setprop_cell(vbi->fdt, "/intc", "phandle", gic_phandle); + qemu_fdt_setprop_cell(vbi->fdt, "/intc", "#address-cells", 0x2); + qemu_fdt_setprop_cell(vbi->fdt, "/intc", "#size-cells", 0x2); + qemu_fdt_setprop(vbi->fdt, "/intc", "ranges", NULL, 0); + qemu_fdt_setprop_cell(vbi->fdt, "/intc", "phandle", vbi->gic_phandle); +} + +static void create_v2m(VirtBoardInfo *vbi, qemu_irq *pic) +{ + int i; + int irq = vbi->irqmap[VIRT_GIC_V2M]; + DeviceState *dev; - return gic_phandle; + dev = qdev_create(NULL, "arm-gicv2m"); + sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, vbi->memmap[VIRT_GIC_V2M].base); + qdev_prop_set_uint32(dev, "base-spi", irq); + qdev_prop_set_uint32(dev, "num-spi", NUM_GICV2M_SPIS); + qdev_init_nofail(dev); + + for (i = 0; i < NUM_GICV2M_SPIS; i++) { + sysbus_connect_irq(SYS_BUS_DEVICE(dev), i, pic[irq + i]); + } + + fdt_add_v2m_gic_node(vbi); } -static uint32_t create_gic(const VirtBoardInfo *vbi, qemu_irq *pic) +static void create_gic(VirtBoardInfo *vbi, qemu_irq *pic) { /* We create a standalone GIC v2 */ DeviceState *gicdev; @@ -371,7 +414,9 @@ static uint32_t create_gic(const VirtBoardInfo *vbi, qemu_irq *pic) pic[i] = qdev_get_gpio_in(gicdev, i); } - return fdt_add_gic_node(vbi); + fdt_add_gic_node(vbi); + + create_v2m(vbi, pic); } static void create_uart(const VirtBoardInfo *vbi, qemu_irq *pic) @@ -587,7 +632,7 @@ static void create_pcie_irq_map(const VirtBoardInfo *vbi, uint32_t gic_phandle, int first_irq, const char *nodename) { int devfn, pin; - uint32_t full_irq_map[4 * 4 * 8] = { 0 }; + uint32_t full_irq_map[4 * 4 * 10] = { 0 }; uint32_t *irq_map = full_irq_map; for (devfn = 0; devfn <= 0x18; devfn += 0x8) { @@ -600,13 +645,13 @@ static void create_pcie_irq_map(const VirtBoardInfo *vbi, uint32_t gic_phandle, uint32_t map[] = { devfn << 8, 0, 0, /* devfn */ pin + 1, /* PCI pin */ - gic_phandle, irq_type, irq_nr, irq_level }; /* GIC irq */ + gic_phandle, 0, 0, irq_type, irq_nr, irq_level }; /* GIC irq */ /* Convert map to big endian */ - for (i = 0; i < 8; i++) { + for (i = 0; i < 10; i++) { irq_map[i] = cpu_to_be32(map[i]); } - irq_map += 8; + irq_map += 10; } } @@ -618,8 +663,7 @@ static void create_pcie_irq_map(const VirtBoardInfo *vbi, uint32_t gic_phandle, 0x7 /* PCI irq */); } -static void create_pcie(const VirtBoardInfo *vbi, qemu_irq *pic, - uint32_t gic_phandle) +static void create_pcie(const VirtBoardInfo *vbi, qemu_irq *pic) { hwaddr base_mmio = vbi->memmap[VIRT_PCIE_MMIO].base; hwaddr size_mmio = vbi->memmap[VIRT_PCIE_MMIO].size; @@ -676,6 +720,8 @@ static void create_pcie(const VirtBoardInfo *vbi, qemu_irq *pic, qemu_fdt_setprop_cells(vbi->fdt, nodename, "bus-range", 0, nr_pcie_buses - 1); + qemu_fdt_setprop_cells(vbi->fdt, nodename, "msi-parent", vbi->v2m_phandle); + qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "reg", 2, base_ecam, 2, size_ecam); qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "ranges", @@ -685,11 +731,52 @@ static void create_pcie(const VirtBoardInfo *vbi, qemu_irq *pic, 2, base_mmio, 2, size_mmio); qemu_fdt_setprop_cell(vbi->fdt, nodename, "#interrupt-cells", 1); - create_pcie_irq_map(vbi, gic_phandle, irq, nodename); + create_pcie_irq_map(vbi, vbi->gic_phandle, irq, nodename); g_free(nodename); } +static void create_platform_bus(VirtBoardInfo *vbi, qemu_irq *pic) +{ + DeviceState *dev; + SysBusDevice *s; + int i; + ARMPlatformBusFDTParams *fdt_params = g_new(ARMPlatformBusFDTParams, 1); + MemoryRegion *sysmem = get_system_memory(); + + platform_bus_params.platform_bus_base = vbi->memmap[VIRT_PLATFORM_BUS].base; + platform_bus_params.platform_bus_size = vbi->memmap[VIRT_PLATFORM_BUS].size; + platform_bus_params.platform_bus_first_irq = vbi->irqmap[VIRT_PLATFORM_BUS]; + platform_bus_params.platform_bus_num_irqs = PLATFORM_BUS_NUM_IRQS; + + fdt_params->system_params = &platform_bus_params; + fdt_params->binfo = &vbi->bootinfo; + fdt_params->intc = "/intc"; + /* + * register a machine init done notifier that creates the device tree + * nodes of the platform bus and its children dynamic sysbus devices + */ + arm_register_platform_bus_fdt_creator(fdt_params); + + dev = qdev_create(NULL, TYPE_PLATFORM_BUS_DEVICE); + dev->id = TYPE_PLATFORM_BUS_DEVICE; + qdev_prop_set_uint32(dev, "num_irqs", + platform_bus_params.platform_bus_num_irqs); + qdev_prop_set_uint32(dev, "mmio_size", + platform_bus_params.platform_bus_size); + qdev_init_nofail(dev); + s = SYS_BUS_DEVICE(dev); + + for (i = 0; i < platform_bus_params.platform_bus_num_irqs; i++) { + int irqn = platform_bus_params.platform_bus_first_irq + i; + sysbus_connect_irq(s, i, pic[irqn]); + } + + memory_region_add_subregion(sysmem, + platform_bus_params.platform_bus_base, + sysbus_mmio_get_region(s, 0)); +} + static void *machvirt_dtb(const struct arm_boot_info *binfo, int *fdt_size) { const VirtBoardInfo *board = (const VirtBoardInfo *)binfo; @@ -717,7 +804,6 @@ static void machvirt_init(MachineState *machine) VirtBoardInfo *vbi; VirtGuestInfoState *guest_info_state = g_malloc0(sizeof *guest_info_state); VirtGuestInfo *guest_info = &guest_info_state->info; - uint32_t gic_phandle; char **cpustr; if (!cpu_model) { @@ -794,13 +880,13 @@ static void machvirt_init(MachineState *machine) create_flash(vbi); - gic_phandle = create_gic(vbi, pic); + create_gic(vbi, pic); create_uart(vbi, pic); create_rtc(vbi, pic); - create_pcie(vbi, pic, gic_phandle); + create_pcie(vbi, pic); /* Create mmio transports, so the user can create virtio backends * (which will be automatically plugged in to the transports). If @@ -828,6 +914,14 @@ static void machvirt_init(MachineState *machine) vbi->bootinfo.get_dtb = machvirt_dtb; vbi->bootinfo.firmware_loaded = bios_name || drive_get(IF_PFLASH, 0, 0); arm_load_kernel(ARM_CPU(first_cpu), &vbi->bootinfo); + + /* + * arm_load_kernel machine init done notifier registration must + * happen before the platform_bus_create call. In this latter, + * another notifier is registered which adds platform bus nodes. + * Notifiers are executed in registration reverse order. + */ + create_platform_bus(vbi, pic); } static bool virt_get_secure(Object *obj, Error **errp) @@ -866,6 +960,7 @@ static void virt_class_init(ObjectClass *oc, void *data) mc->desc = "ARM Virtual Machine", mc->init = machvirt_init; mc->max_cpus = 8; + mc->has_dynamic_sysbus = true; } static const TypeInfo machvirt_info = { diff --git a/hw/core/machine.c b/hw/core/machine.c index 25c45e6f9d..ac4654e9dd 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -294,6 +294,14 @@ static void machine_init_notify(Notifier *notifier, void *data) foreach_dynamic_sysbus_device(error_on_sysbus_device, NULL); } +static void machine_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + + /* Default 128 MB as guest ram size */ + mc->default_ram_size = 128 * M_BYTE; +} + static void machine_initfn(Object *obj) { MachineState *ms = MACHINE(obj); @@ -463,6 +471,7 @@ static const TypeInfo machine_info = { .parent = TYPE_OBJECT, .abstract = true, .class_size = sizeof(MachineClass), + .class_init = machine_class_init, .instance_size = sizeof(MachineState), .instance_init = machine_initfn, .instance_finalize = machine_finalize, diff --git a/hw/display/tc6393xb.c b/hw/display/tc6393xb.c index 66b7ade8da..f5f3f3e69d 100644 --- a/hw/display/tc6393xb.c +++ b/hw/display/tc6393xb.c @@ -571,7 +571,7 @@ TC6393xbState *tc6393xb_init(MemoryRegion *sysmem, uint32_t base, qemu_irq irq) s->irq = irq; s->gpio_in = qemu_allocate_irqs(tc6393xb_gpio_set, s, TC6393XB_GPIOS); - s->l3v = *qemu_allocate_irqs(tc6393xb_l3v, s, 1); + s->l3v = qemu_allocate_irq(tc6393xb_l3v, s, 0); s->blanked = 1; s->sub_irqs = qemu_allocate_irqs(tc6393xb_sub_irq, s, TC6393XB_NR_IRQS); diff --git a/hw/gpio/pl061.c b/hw/gpio/pl061.c index bd03e99975..4ba730b476 100644 --- a/hw/gpio/pl061.c +++ b/hw/gpio/pl061.c @@ -173,7 +173,7 @@ static uint64_t pl061_read(void *opaque, hwaddr offset, case 0x414: /* Raw interrupt status */ return s->istate; case 0x418: /* Masked interrupt status */ - return s->istate | s->im; + return s->istate & s->im; case 0x420: /* Alternate function select */ return s->afsel; case 0x500: /* 2mA drive */ diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c index db32fd1526..5593e41f84 100644 --- a/hw/i386/acpi-build.c +++ b/hw/i386/acpi-build.c @@ -615,6 +615,7 @@ static void build_append_pci_bus_devices(Aml *parent_scope, PCIBus *bus, } } aml_append(parent_scope, method); + qobject_decref(bsel); } /* diff --git a/hw/i386/pc.c b/hw/i386/pc.c index a93972fb41..2baff4a660 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -1007,7 +1007,6 @@ static X86CPU *pc_new_cpu(const char *cpu_model, int64_t apic_id, } qdev_set_parent_bus(DEVICE(cpu), qdev_get_child_bus(icc_bridge, "icc")); - object_unref(OBJECT(cpu)); object_property_set_int(OBJECT(cpu), apic_id, "apic-id", &local_err); object_property_set_bool(OBJECT(cpu), true, "realized", &local_err); @@ -1026,7 +1025,9 @@ static const char *current_cpu_model; void pc_hot_add_cpu(const int64_t id, Error **errp) { DeviceState *icc_bridge; + X86CPU *cpu; int64_t apic_id = x86_cpu_apic_id_from_index(id); + Error *local_err = NULL; if (id < 0) { error_setg(errp, "Invalid CPU id: %" PRIi64, id); @@ -1054,7 +1055,12 @@ void pc_hot_add_cpu(const int64_t id, Error **errp) icc_bridge = DEVICE(object_resolve_path_type("icc-bridge", TYPE_ICC_BRIDGE, NULL)); - pc_new_cpu(current_cpu_model, apic_id, icc_bridge, errp); + cpu = pc_new_cpu(current_cpu_model, apic_id, icc_bridge, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } + object_unref(OBJECT(cpu)); } void pc_cpus_init(const char *cpu_model, DeviceState *icc_bridge) @@ -1088,6 +1094,7 @@ void pc_cpus_init(const char *cpu_model, DeviceState *icc_bridge) error_report_err(error); exit(1); } + object_unref(OBJECT(cpu)); } /* map APIC MMIO area if CPU has APIC */ @@ -1365,9 +1372,9 @@ FWCfgState *pc_memory_init(MachineState *machine, return fw_cfg; } -qemu_irq *pc_allocate_cpu_irq(void) +qemu_irq pc_allocate_cpu_irq(void) { - return qemu_allocate_irqs(pic_irq_request, NULL, 1); + return qemu_allocate_irq(pic_irq_request, NULL, 0); } DeviceState *pc_vga_init(ISABus *isa_bus, PCIBus *pci_bus) diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c index 0688f0c52f..5253e6d4fa 100644 --- a/hw/i386/pc_piix.c +++ b/hw/i386/pc_piix.c @@ -86,10 +86,9 @@ static void pc_init1(MachineState *machine) ISABus *isa_bus; PCII440FXState *i440fx_state; int piix3_devfn = -1; - qemu_irq *cpu_irq; qemu_irq *gsi; qemu_irq *i8259; - qemu_irq *smi_irq; + qemu_irq smi_irq; GSIState *gsi_state; DriveInfo *hd[MAX_IDE_BUS * MAX_IDE_DEVS]; BusState *idebus[MAX_IDE_BUS]; @@ -219,13 +218,13 @@ static void pc_init1(MachineState *machine) } else if (xen_enabled()) { i8259 = xen_interrupt_controller_init(); } else { - cpu_irq = pc_allocate_cpu_irq(); - i8259 = i8259_init(isa_bus, cpu_irq[0]); + i8259 = i8259_init(isa_bus, pc_allocate_cpu_irq()); } for (i = 0; i < ISA_NUM_IRQS; i++) { gsi_state->i8259_irq[i] = i8259[i]; } + g_free(i8259); if (pci_enabled) { ioapic_init_gsi(gsi_state, "i440fx"); } @@ -283,10 +282,10 @@ static void pc_init1(MachineState *machine) DeviceState *piix4_pm; I2CBus *smbus; - smi_irq = qemu_allocate_irqs(pc_acpi_smi_interrupt, first_cpu, 1); + smi_irq = qemu_allocate_irq(pc_acpi_smi_interrupt, first_cpu, 0); /* TODO: Populate SPD eeprom data. */ smbus = piix4_pm_init(pci_bus, piix3_devfn + 3, 0xb100, - gsi[9], *smi_irq, + gsi[9], smi_irq, kvm_enabled(), &piix4_pm); smbus_eeprom_init(smbus, 8, NULL, 0); diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c index 66220b352b..110dfb78a8 100644 --- a/hw/i386/pc_q35.c +++ b/hw/i386/pc_q35.c @@ -79,7 +79,6 @@ static void pc_q35_init(MachineState *machine) GSIState *gsi_state; ISABus *isa_bus; int pci_enabled = 1; - qemu_irq *cpu_irq; qemu_irq *gsi; qemu_irq *i8259; int i; @@ -230,8 +229,7 @@ static void pc_q35_init(MachineState *machine) } else if (xen_enabled()) { i8259 = xen_interrupt_controller_init(); } else { - cpu_irq = pc_allocate_cpu_irq(); - i8259 = i8259_init(isa_bus, cpu_irq[0]); + i8259 = i8259_init(isa_bus, pc_allocate_cpu_irq()); } for (i = 0; i < ISA_NUM_IRQS; i++) { diff --git a/hw/ide/pci.c b/hw/ide/pci.c index 1b3d1c12ad..4b5e32dcbe 100644 --- a/hw/ide/pci.c +++ b/hw/ide/pci.c @@ -452,8 +452,6 @@ static const struct IDEDMAOps bmdma_ops = { void bmdma_init(IDEBus *bus, BMDMAState *bm, PCIIDEState *d) { - qemu_irq *irq; - if (bus->dma == &bm->dma) { return; } @@ -461,8 +459,7 @@ void bmdma_init(IDEBus *bus, BMDMAState *bm, PCIIDEState *d) bm->dma.ops = &bmdma_ops; bus->dma = &bm->dma; bm->irq = bus->irq; - irq = qemu_allocate_irqs(bmdma_irq, bm, 1); - bus->irq = *irq; + bus->irq = qemu_allocate_irq(bmdma_irq, bm, 0); bm->pci_dev = d; } diff --git a/hw/intc/Makefile.objs b/hw/intc/Makefile.objs index 843864a3ef..092d8a80ac 100644 --- a/hw/intc/Makefile.objs +++ b/hw/intc/Makefile.objs @@ -11,6 +11,7 @@ common-obj-$(CONFIG_SLAVIO) += slavio_intctl.o common-obj-$(CONFIG_IOAPIC) += ioapic_common.o common-obj-$(CONFIG_ARM_GIC) += arm_gic_common.o common-obj-$(CONFIG_ARM_GIC) += arm_gic.o +common-obj-$(CONFIG_ARM_GIC) += arm_gicv2m.o common-obj-$(CONFIG_OPENPIC) += openpic.o obj-$(CONFIG_APIC) += apic.o apic_common.o diff --git a/hw/intc/apic.c b/hw/intc/apic.c index 0f97b47925..77b639cce8 100644 --- a/hw/intc/apic.c +++ b/hw/intc/apic.c @@ -370,13 +370,14 @@ static int apic_irq_pending(APICCommonState *s) static void apic_update_irq(APICCommonState *s) { CPUState *cpu; + DeviceState *dev = (DeviceState *)s; cpu = CPU(s->cpu); if (!qemu_cpu_is_self(cpu)) { cpu_interrupt(cpu, CPU_INTERRUPT_POLL); } else if (apic_irq_pending(s) > 0) { cpu_interrupt(cpu, CPU_INTERRUPT_HARD); - } else if (!apic_accept_pic_intr(&s->busdev.qdev) || !pic_get_output(isa_pic)) { + } else if (!apic_accept_pic_intr(dev) || !pic_get_output(isa_pic)) { cpu_reset_interrupt(cpu, CPU_INTERRUPT_HARD); } } @@ -549,10 +550,12 @@ static void apic_deliver(DeviceState *dev, uint8_t dest, uint8_t dest_mode, static bool apic_check_pic(APICCommonState *s) { - if (!apic_accept_pic_intr(&s->busdev.qdev) || !pic_get_output(isa_pic)) { + DeviceState *dev = (DeviceState *)s; + + if (!apic_accept_pic_intr(dev) || !pic_get_output(isa_pic)) { return false; } - apic_deliver_pic_intr(&s->busdev.qdev, 1); + apic_deliver_pic_intr(dev, 1); return true; } diff --git a/hw/intc/arm_gicv2m.c b/hw/intc/arm_gicv2m.c new file mode 100644 index 0000000000..43d1976c49 --- /dev/null +++ b/hw/intc/arm_gicv2m.c @@ -0,0 +1,192 @@ +/* + * GICv2m extension for MSI/MSI-x support with a GICv2-based system + * + * Copyright (C) 2015 Linaro, All rights reserved. + * + * Author: Christoffer Dall <christoffer.dall@linaro.org> + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ + +/* This file implements an emulated GICv2m widget as described in the ARM + * Server Base System Architecture (SBSA) specification Version 2.2 + * (ARM-DEN-0029 v2.2) pages 35-39 without any optional implementation defined + * identification registers and with a single non-secure MSI register frame. + */ + +#include "hw/sysbus.h" +#include "hw/pci/msi.h" + +#define TYPE_ARM_GICV2M "arm-gicv2m" +#define ARM_GICV2M(obj) OBJECT_CHECK(ARMGICv2mState, (obj), TYPE_ARM_GICV2M) + +#define GICV2M_NUM_SPI_MAX 128 + +#define V2M_MSI_TYPER 0x008 +#define V2M_MSI_SETSPI_NS 0x040 +#define V2M_MSI_IIDR 0xFCC +#define V2M_IIDR0 0xFD0 +#define V2M_IIDR11 0xFFC + +#define PRODUCT_ID_QEMU 0x51 /* ASCII code Q */ + +typedef struct ARMGICv2mState { + SysBusDevice parent_obj; + + MemoryRegion iomem; + qemu_irq spi[GICV2M_NUM_SPI_MAX]; + + uint32_t base_spi; + uint32_t num_spi; +} ARMGICv2mState; + +static void gicv2m_set_irq(void *opaque, int irq) +{ + ARMGICv2mState *s = (ARMGICv2mState *)opaque; + + qemu_irq_pulse(s->spi[irq]); +} + +static uint64_t gicv2m_read(void *opaque, hwaddr offset, + unsigned size) +{ + ARMGICv2mState *s = (ARMGICv2mState *)opaque; + uint32_t val; + + if (size != 4) { + qemu_log_mask(LOG_GUEST_ERROR, "gicv2m_read: bad size %u\n", size); + return 0; + } + + switch (offset) { + case V2M_MSI_TYPER: + val = (s->base_spi + 32) << 16; + val |= s->num_spi; + return val; + case V2M_MSI_IIDR: + /* We don't have any valid implementor so we leave that field as zero + * and we return 0 in the arch revision as per the spec. + */ + return (PRODUCT_ID_QEMU << 20); + case V2M_IIDR0 ... V2M_IIDR11: + /* We do not implement any optional identification registers and the + * mandatory MSI_PIDR2 register reads as 0x0, so we capture all + * implementation defined registers here. + */ + return 0; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "gicv2m_read: Bad offset %x\n", (int)offset); + return 0; + } +} + +static void gicv2m_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + ARMGICv2mState *s = (ARMGICv2mState *)opaque; + + if (size != 2 && size != 4) { + qemu_log_mask(LOG_GUEST_ERROR, "gicv2m_write: bad size %u\n", size); + return; + } + + switch (offset) { + case V2M_MSI_SETSPI_NS: { + int spi; + + spi = (value & 0x3ff) - (s->base_spi + 32); + if (spi >= 0 && spi < s->num_spi) { + gicv2m_set_irq(s, spi); + } + return; + } + default: + qemu_log_mask(LOG_GUEST_ERROR, + "gicv2m_write: Bad offset %x\n", (int)offset); + } +} + +static const MemoryRegionOps gicv2m_ops = { + .read = gicv2m_read, + .write = gicv2m_write, + .endianness = DEVICE_LITTLE_ENDIAN, +}; + +static void gicv2m_realize(DeviceState *dev, Error **errp) +{ + ARMGICv2mState *s = ARM_GICV2M(dev); + int i; + + if (s->num_spi > GICV2M_NUM_SPI_MAX) { + error_setg(errp, + "requested %u SPIs exceeds GICv2m frame maximum %d", + s->num_spi, GICV2M_NUM_SPI_MAX); + return; + } + + if (s->base_spi + 32 > 1020 - s->num_spi) { + error_setg(errp, + "requested base SPI %u+%u exceeds max. number 1020", + s->base_spi + 32, s->num_spi); + return; + } + + for (i = 0; i < s->num_spi; i++) { + sysbus_init_irq(SYS_BUS_DEVICE(dev), &s->spi[i]); + } + + msi_supported = true; + kvm_gsi_direct_mapping = true; + kvm_msi_via_irqfd_allowed = kvm_irqfds_enabled(); +} + +static void gicv2m_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + ARMGICv2mState *s = ARM_GICV2M(obj); + + memory_region_init_io(&s->iomem, OBJECT(s), &gicv2m_ops, s, + "gicv2m", 0x1000); + sysbus_init_mmio(sbd, &s->iomem); +} + +static Property gicv2m_properties[] = { + DEFINE_PROP_UINT32("base-spi", ARMGICv2mState, base_spi, 0), + DEFINE_PROP_UINT32("num-spi", ARMGICv2mState, num_spi, 64), + DEFINE_PROP_END_OF_LIST(), +}; + +static void gicv2m_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->props = gicv2m_properties; + dc->realize = gicv2m_realize; +} + +static const TypeInfo gicv2m_info = { + .name = TYPE_ARM_GICV2M, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(ARMGICv2mState), + .instance_init = gicv2m_init, + .class_init = gicv2m_class_init, +}; + +static void gicv2m_register_types(void) +{ + type_register_static(&gicv2m_info); +} + +type_init(gicv2m_register_types) diff --git a/hw/intc/exynos4210_gic.c b/hw/intc/exynos4210_gic.c index 0590d5dfb8..b2a4950bc3 100644 --- a/hw/intc/exynos4210_gic.c +++ b/hw/intc/exynos4210_gic.c @@ -213,9 +213,6 @@ void exynos4210_init_board_irqs(Exynos4210Irq *s) uint32_t grp, bit, irq_id, n; for (n = 0; n < EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ; n++) { - s->board_irqs[n] = qemu_irq_split(s->int_combiner_irq[n], - s->ext_combiner_irq[n]); - irq_id = 0; if (n == EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 4) || n == EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 4)) { @@ -230,8 +227,10 @@ void exynos4210_init_board_irqs(Exynos4210Irq *s) if (irq_id) { s->board_irqs[n] = qemu_irq_split(s->int_combiner_irq[n], s->ext_gic_irq[irq_id-32]); + } else { + s->board_irqs[n] = qemu_irq_split(s->int_combiner_irq[n], + s->ext_combiner_irq[n]); } - } for (; n < EXYNOS4210_MAX_INT_COMBINER_IN_IRQ; n++) { /* these IDs are passed to Internal Combiner and External GIC */ diff --git a/hw/isa/i82378.c b/hw/isa/i82378.c index 9da9dfc4da..fcf97d86ac 100644 --- a/hw/isa/i82378.c +++ b/hw/isa/i82378.c @@ -65,7 +65,6 @@ static void i82378_realize(PCIDevice *pci, Error **errp) uint8_t *pci_conf; ISABus *isabus; ISADevice *isa; - qemu_irq *out0_irq; pci_conf = pci->config; pci_set_word(pci_conf + PCI_COMMAND, @@ -88,11 +87,9 @@ static void i82378_realize(PCIDevice *pci, Error **errp) All devices accept byte access only, except timer */ - /* Workaround the fact that i8259 is not qdev'ified... */ - out0_irq = qemu_allocate_irqs(i82378_request_out0_irq, s, 1); - /* 2 82C59 (irq) */ - s->i8259 = i8259_init(isabus, *out0_irq); + s->i8259 = i8259_init(isabus, + qemu_allocate_irq(i82378_request_out0_irq, s, 0)); isa_bus_irqs(isabus, s->i8259); /* 1 82C54 (pit) */ diff --git a/hw/isa/lpc_ich9.c b/hw/isa/lpc_ich9.c index bc9afc60ab..18718d772e 100644 --- a/hw/isa/lpc_ich9.c +++ b/hw/isa/lpc_ich9.c @@ -360,11 +360,8 @@ static void ich9_set_sci(void *opaque, int irq_num, int level) void ich9_lpc_pm_init(PCIDevice *lpc_pci) { ICH9LPCState *lpc = ICH9_LPC_DEVICE(lpc_pci); - qemu_irq *sci_irq; - - sci_irq = qemu_allocate_irqs(ich9_set_sci, lpc, 1); - ich9_pm_init(lpc_pci, &lpc->pm, sci_irq[0]); + ich9_pm_init(lpc_pci, &lpc->pm, qemu_allocate_irq(ich9_set_sci, lpc, 0)); ich9_lpc_reset(&lpc->d.qdev); } diff --git a/hw/lm32/lm32_boards.c b/hw/lm32/lm32_boards.c index 14d0efcdd9..70f48d3b1d 100644 --- a/hw/lm32/lm32_boards.c +++ b/hw/lm32/lm32_boards.c @@ -78,7 +78,7 @@ static void lm32_evr_init(MachineState *machine) DriveInfo *dinfo; MemoryRegion *address_space_mem = get_system_memory(); MemoryRegion *phys_ram = g_new(MemoryRegion, 1); - qemu_irq *cpu_irq, irq[32]; + qemu_irq irq[32]; ResetInfo *reset_info; int i; @@ -123,8 +123,7 @@ static void lm32_evr_init(MachineState *machine) 1, 2, 0x01, 0x7e, 0x43, 0x00, 0x555, 0x2aa, 1); /* create irq lines */ - cpu_irq = qemu_allocate_irqs(cpu_irq_handler, cpu, 1); - env->pic_state = lm32_pic_init(*cpu_irq); + env->pic_state = lm32_pic_init(qemu_allocate_irq(cpu_irq_handler, cpu, 0)); for (i = 0; i < 32; i++) { irq[i] = qdev_get_gpio_in(env->pic_state, i); } @@ -173,7 +172,7 @@ static void lm32_uclinux_init(MachineState *machine) DriveInfo *dinfo; MemoryRegion *address_space_mem = get_system_memory(); MemoryRegion *phys_ram = g_new(MemoryRegion, 1); - qemu_irq *cpu_irq, irq[32]; + qemu_irq irq[32]; HWSetup *hw; ResetInfo *reset_info; int i; @@ -225,8 +224,7 @@ static void lm32_uclinux_init(MachineState *machine) 1, 2, 0x01, 0x7e, 0x43, 0x00, 0x555, 0x2aa, 1); /* create irq lines */ - cpu_irq = qemu_allocate_irqs(cpu_irq_handler, env, 1); - env->pic_state = lm32_pic_init(*cpu_irq); + env->pic_state = lm32_pic_init(qemu_allocate_irq(cpu_irq_handler, env, 0)); for (i = 0; i < 32; i++) { irq[i] = qdev_get_gpio_in(env->pic_state, i); } diff --git a/hw/lm32/milkymist.c b/hw/lm32/milkymist.c index e0cec7dc41..e755f5b24f 100644 --- a/hw/lm32/milkymist.c +++ b/hw/lm32/milkymist.c @@ -86,7 +86,7 @@ milkymist_init(MachineState *machine) DriveInfo *dinfo; MemoryRegion *address_space_mem = get_system_memory(); MemoryRegion *phys_sdram = g_new(MemoryRegion, 1); - qemu_irq irq[32], *cpu_irq; + qemu_irq irq[32]; int i; char *bios_filename; ResetInfo *reset_info; @@ -130,8 +130,7 @@ milkymist_init(MachineState *machine) 2, 0x00, 0x89, 0x00, 0x1d, 1); /* create irq lines */ - cpu_irq = qemu_allocate_irqs(cpu_irq_handler, cpu, 1); - env->pic_state = lm32_pic_init(*cpu_irq); + env->pic_state = lm32_pic_init(qemu_allocate_irq(cpu_irq_handler, cpu, 0)); for (i = 0; i < 32; i++) { irq[i] = qdev_get_gpio_in(env->pic_state, i); } diff --git a/hw/misc/macio/macio.c b/hw/misc/macio/macio.c index 063ad80412..e9037b0c39 100644 --- a/hw/misc/macio/macio.c +++ b/hw/misc/macio/macio.c @@ -126,17 +126,18 @@ static void macio_bar_setup(MacIOState *macio_state) } } -static int macio_common_initfn(PCIDevice *d) +static void macio_common_realize(PCIDevice *d, Error **errp) { MacIOState *s = MACIO(d); SysBusDevice *sysbus_dev; - int ret; + Error *err = NULL; d->config[0x3d] = 0x01; // interrupt on pin 1 - ret = qdev_init(DEVICE(&s->cuda)); - if (ret < 0) { - return ret; + object_property_set_bool(OBJECT(&s->cuda), true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; } sysbus_dev = SYS_BUS_DEVICE(&s->cuda); memory_region_add_subregion(&s->bar, 0x16000, @@ -144,12 +145,11 @@ static int macio_common_initfn(PCIDevice *d) macio_bar_setup(s); pci_register_bar(d, 0, PCI_BASE_ADDRESS_SPACE_MEMORY, &s->bar); - - return 0; } -static int macio_initfn_ide(MacIOState *s, MACIOIDEState *ide, qemu_irq irq0, - qemu_irq irq1, int dmaid) +static void macio_realize_ide(MacIOState *s, MACIOIDEState *ide, + qemu_irq irq0, qemu_irq irq1, int dmaid, + Error **errp) { SysBusDevice *sysbus_dev; @@ -157,27 +157,31 @@ static int macio_initfn_ide(MacIOState *s, MACIOIDEState *ide, qemu_irq irq0, sysbus_connect_irq(sysbus_dev, 0, irq0); sysbus_connect_irq(sysbus_dev, 1, irq1); macio_ide_register_dma(ide, s->dbdma, dmaid); - return qdev_init(DEVICE(ide)); + object_property_set_bool(OBJECT(ide), true, "realized", errp); } -static int macio_oldworld_initfn(PCIDevice *d) +static void macio_oldworld_realize(PCIDevice *d, Error **errp) { MacIOState *s = MACIO(d); OldWorldMacIOState *os = OLDWORLD_MACIO(d); + Error *err = NULL; SysBusDevice *sysbus_dev; int i; int cur_irq = 0; - int ret = macio_common_initfn(d); - if (ret < 0) { - return ret; + + macio_common_realize(d, &err); + if (err) { + error_propagate(errp, err); + return; } sysbus_dev = SYS_BUS_DEVICE(&s->cuda); sysbus_connect_irq(sysbus_dev, 0, os->irqs[cur_irq++]); - ret = qdev_init(DEVICE(&os->nvram)); - if (ret < 0) { - return ret; + object_property_set_bool(OBJECT(&os->nvram), true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; } sysbus_dev = SYS_BUS_DEVICE(&os->nvram); memory_region_add_subregion(&s->bar, 0x60000, @@ -194,13 +198,12 @@ static int macio_oldworld_initfn(PCIDevice *d) qemu_irq irq0 = os->irqs[cur_irq++]; qemu_irq irq1 = os->irqs[cur_irq++]; - ret = macio_initfn_ide(s, &os->ide[i], irq0, irq1, 0x16 + (i * 4)); - if (ret < 0) { - return ret; + macio_realize_ide(s, &os->ide[i], irq0, irq1, 0x16 + (i * 4), &err); + if (err) { + error_propagate(errp, err); + return; } } - - return 0; } static void macio_init_ide(MacIOState *s, MACIOIDEState *ide, size_t ide_size, @@ -268,17 +271,20 @@ static const MemoryRegionOps timer_ops = { .endianness = DEVICE_LITTLE_ENDIAN, }; -static int macio_newworld_initfn(PCIDevice *d) +static void macio_newworld_realize(PCIDevice *d, Error **errp) { MacIOState *s = MACIO(d); NewWorldMacIOState *ns = NEWWORLD_MACIO(d); + Error *err = NULL; SysBusDevice *sysbus_dev; MemoryRegion *timer_memory = NULL; int i; int cur_irq = 0; - int ret = macio_common_initfn(d); - if (ret < 0) { - return ret; + + macio_common_realize(d, &err); + if (err) { + error_propagate(errp, err); + return; } sysbus_dev = SYS_BUS_DEVICE(&s->cuda); @@ -294,9 +300,10 @@ static int macio_newworld_initfn(PCIDevice *d) qemu_irq irq0 = ns->irqs[cur_irq++]; qemu_irq irq1 = ns->irqs[cur_irq++]; - ret = macio_initfn_ide(s, &ns->ide[i], irq0, irq1, 0x16 + (i * 4)); - if (ret < 0) { - return ret; + macio_realize_ide(s, &ns->ide[i], irq0, irq1, 0x16 + (i * 4), &err); + if (err) { + error_propagate(errp, err); + return; } } @@ -305,8 +312,6 @@ static int macio_newworld_initfn(PCIDevice *d) memory_region_init_io(timer_memory, OBJECT(s), &timer_ops, NULL, "timer", 0x1000); memory_region_add_subregion(&s->bar, 0x15000, timer_memory); - - return 0; } static void macio_newworld_init(Object *obj) @@ -352,7 +357,7 @@ static void macio_oldworld_class_init(ObjectClass *oc, void *data) PCIDeviceClass *pdc = PCI_DEVICE_CLASS(oc); DeviceClass *dc = DEVICE_CLASS(oc); - pdc->init = macio_oldworld_initfn; + pdc->realize = macio_oldworld_realize; pdc->device_id = PCI_DEVICE_ID_APPLE_343S1201; dc->vmsd = &vmstate_macio_oldworld; } @@ -372,7 +377,7 @@ static void macio_newworld_class_init(ObjectClass *oc, void *data) PCIDeviceClass *pdc = PCI_DEVICE_CLASS(oc); DeviceClass *dc = DEVICE_CLASS(oc); - pdc->init = macio_newworld_initfn; + pdc->realize = macio_newworld_realize; pdc->device_id = PCI_DEVICE_ID_APPLE_UNI_N_KEYL; dc->vmsd = &vmstate_macio_newworld; } diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index dafe91421b..494a346cf6 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -155,7 +155,7 @@ #define GEM_NWCFG_BCAST_REJ 0x00000020 /* Reject broadcast packets */ #define GEM_NWCFG_PROMISC 0x00000010 /* Accept all packets */ -#define GEM_DMACFG_RBUFSZ_M 0x007F0000 /* DMA RX Buffer Size mask */ +#define GEM_DMACFG_RBUFSZ_M 0x00FF0000 /* DMA RX Buffer Size mask */ #define GEM_DMACFG_RBUFSZ_S 16 /* DMA RX Buffer Size shift */ #define GEM_DMACFG_RBUFSZ_MUL 64 /* DMA RX Buffer Size multiplier */ #define GEM_DMACFG_TXCSUM_OFFL 0x00000800 /* Transmit checksum offload */ diff --git a/hw/pci/msi.c b/hw/pci/msi.c index c111dbaff6..f9c0484420 100644 --- a/hw/pci/msi.c +++ b/hw/pci/msi.c @@ -21,10 +21,6 @@ #include "hw/pci/msi.h" #include "qemu/range.h" -/* Eventually those constants should go to Linux pci_regs.h */ -#define PCI_MSI_PENDING_32 0x10 -#define PCI_MSI_PENDING_64 0x14 - /* PCI_MSI_ADDRESS_LO */ #define PCI_MSI_ADDRESS_LO_MASK (~0x3) diff --git a/hw/pci/pci-stub.c b/hw/pci/pci-stub.c index 5e564c3a87..f8f237e823 100644 --- a/hw/pci/pci-stub.c +++ b/hw/pci/pci-stub.c @@ -29,19 +29,7 @@ PciInfoList *qmp_query_pci(Error **errp) return NULL; } -static void pci_error_message(Monitor *mon) +void hmp_pcie_aer_inject_error(Monitor *mon, const QDict *qdict) { monitor_printf(mon, "PCI devices not supported\n"); } - -int hmp_pcie_aer_inject_error(Monitor *mon, - const QDict *qdict, QObject **ret_data) -{ - pci_error_message(mon); - return -ENOSYS; -} - -void pcie_aer_inject_error_print(Monitor *mon, const QObject *data) -{ - pci_error_message(mon); -} diff --git a/hw/pci/pci.c b/hw/pci/pci.c index 4989408ece..750f3dacea 100644 --- a/hw/pci/pci.c +++ b/hw/pci/pci.c @@ -147,7 +147,7 @@ static uint16_t pci_default_sub_device_id = PCI_SUBDEVICE_ID_QEMU; static QLIST_HEAD(, PCIHostState) pci_host_bridges; -static int pci_bar(PCIDevice *d, int reg) +int pci_bar(PCIDevice *d, int reg) { uint8_t type; diff --git a/hw/pci/pcie_aer.c b/hw/pci/pcie_aer.c index b48c09cd11..c8dea8ed9c 100644 --- a/hw/pci/pcie_aer.c +++ b/hw/pci/pcie_aer.c @@ -815,21 +815,6 @@ const VMStateDescription vmstate_pcie_aer_log = { } }; -void pcie_aer_inject_error_print(Monitor *mon, const QObject *data) -{ - QDict *qdict; - int devfn; - assert(qobject_type(data) == QTYPE_QDICT); - qdict = qobject_to_qdict(data); - - devfn = (int)qdict_get_int(qdict, "devfn"); - monitor_printf(mon, "OK id: %s root bus: %s, bus: %x devfn: %x.%x\n", - qdict_get_str(qdict, "id"), - qdict_get_str(qdict, "root_bus"), - (int) qdict_get_int(qdict, "bus"), - PCI_SLOT(devfn), PCI_FUNC(devfn)); -} - typedef struct PCIEAERErrorName { const char *name; uint32_t val; @@ -962,8 +947,8 @@ static int pcie_aer_parse_error_string(const char *error_name, return -EINVAL; } -int hmp_pcie_aer_inject_error(Monitor *mon, - const QDict *qdict, QObject **ret_data) +static int do_pcie_aer_inject_error(Monitor *mon, + const QDict *qdict, QObject **ret_data) { const char *id = qdict_get_str(qdict, "id"); const char *error_name; @@ -1035,3 +1020,23 @@ int hmp_pcie_aer_inject_error(Monitor *mon, return 0; } + +void hmp_pcie_aer_inject_error(Monitor *mon, const QDict *qdict) +{ + QObject *data; + int devfn; + + if (do_pcie_aer_inject_error(mon, qdict, &data) < 0) { + return; + } + + assert(qobject_type(data) == QTYPE_QDICT); + qdict = qobject_to_qdict(data); + + devfn = (int)qdict_get_int(qdict, "devfn"); + monitor_printf(mon, "OK id: %s root bus: %s, bus: %x devfn: %x.%x\n", + qdict_get_str(qdict, "id"), + qdict_get_str(qdict, "root_bus"), + (int) qdict_get_int(qdict, "bus"), + PCI_SLOT(devfn), PCI_FUNC(devfn)); +} diff --git a/hw/ppc/Makefile.objs b/hw/ppc/Makefile.objs index 437955d1d5..c8ab06e7f3 100644 --- a/hw/ppc/Makefile.objs +++ b/hw/ppc/Makefile.objs @@ -3,7 +3,7 @@ obj-y += ppc.o ppc_booke.o # IBM pSeries (sPAPR) obj-$(CONFIG_PSERIES) += spapr.o spapr_vio.o spapr_events.o obj-$(CONFIG_PSERIES) += spapr_hcall.o spapr_iommu.o spapr_rtas.o -obj-$(CONFIG_PSERIES) += spapr_pci.o spapr_rtc.o +obj-$(CONFIG_PSERIES) += spapr_pci.o spapr_rtc.o spapr_drc.o ifeq ($(CONFIG_PCI)$(CONFIG_PSERIES)$(CONFIG_LINUX), yyy) obj-y += spapr_pci_vfio.o endif diff --git a/hw/ppc/e500.c b/hw/ppc/e500.c index c10e1b57b6..d300846c3d 100644 --- a/hw/ppc/e500.c +++ b/hw/ppc/e500.c @@ -1030,6 +1030,7 @@ void ppce500_init(MachineState *machine, PPCE500Params *params) exit(1); } } + g_free(filename); /* Reserve space for dtb */ dt_base = (loadaddr + bios_size + DTC_LOAD_PAD) & ~DTC_PAD_MASK; diff --git a/hw/ppc/prep.c b/hw/ppc/prep.c index 7f52662d76..998ee2d16b 100644 --- a/hw/ppc/prep.c +++ b/hw/ppc/prep.c @@ -528,7 +528,6 @@ static void ppc_prep_init(MachineState *machine) PCIDevice *pci; ISABus *isa_bus; ISADevice *isa; - qemu_irq *cpu_exit_irq; int ppc_boot_device; DriveInfo *hd[MAX_IDE_BUS * MAX_IDE_DEVS]; @@ -625,11 +624,11 @@ static void ppc_prep_init(MachineState *machine) /* PCI -> ISA bridge */ pci = pci_create_simple(pci_bus, PCI_DEVFN(1, 0), "i82378"); - cpu_exit_irq = qemu_allocate_irqs(cpu_request_exit, NULL, 1); cpu = POWERPC_CPU(first_cpu); qdev_connect_gpio_out(&pci->qdev, 0, cpu->env.irq_inputs[PPC6xx_INPUT_INT]); - qdev_connect_gpio_out(&pci->qdev, 1, *cpu_exit_irq); + qdev_connect_gpio_out(&pci->qdev, 1, + qemu_allocate_irq(cpu_request_exit, NULL, 0)); sysbus_connect_irq(&pcihost->busdev, 0, qdev_get_gpio_in(&pci->qdev, 9)); sysbus_connect_irq(&pcihost->busdev, 1, qdev_get_gpio_in(&pci->qdev, 11)); sysbus_connect_irq(&pcihost->busdev, 2, qdev_get_gpio_in(&pci->qdev, 9)); diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index a15fa3c965..f174e5a0f3 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -533,6 +533,8 @@ static void *spapr_create_fdt_skel(hwaddr initrd_base, refpoints, sizeof(refpoints)))); _FDT((fdt_property_cell(fdt, "rtas-error-log-max", RTAS_ERROR_LOG_MAX))); + _FDT((fdt_property_cell(fdt, "rtas-event-scan-rate", + RTAS_EVENT_SCAN_RATE))); /* * According to PAPR, rtas ibm,os-term does not guarantee a return @@ -794,8 +796,8 @@ static void spapr_finalize_fdt(sPAPREnvironment *spapr, _FDT((fdt_pack(fdt))); if (fdt_totalsize(fdt) > FDT_MAX_SIZE) { - hw_error("FDT too big ! 0x%x bytes (max is 0x%x)\n", - fdt_totalsize(fdt), FDT_MAX_SIZE); + error_report("FDT too big ! 0x%x bytes (max is 0x%x)", + fdt_totalsize(fdt), FDT_MAX_SIZE); exit(1); } @@ -899,7 +901,7 @@ static int spapr_check_htab_fd(sPAPREnvironment *spapr) spapr->htab_fd = kvmppc_get_htab_fd(false); if (spapr->htab_fd < 0) { error_report("Unable to open fd for reading hash table from KVM: " - "%s", strerror(errno)); + "%s", strerror(errno)); rc = -1; } spapr->htab_fd_stale = false; @@ -1419,7 +1421,7 @@ static void ppc_spapr_init(MachineState *machine) rma_alloc_size = kvmppc_alloc_rma(&rma); if (rma_alloc_size == -1) { - hw_error("qemu: Unable to create RMA\n"); + error_report("Unable to create RMA"); exit(1); } @@ -1504,6 +1506,11 @@ static void ppc_spapr_init(MachineState *machine) qemu_register_reset(spapr_cpu_reset, cpu); } + if (kvm_enabled()) { + /* Enable H_LOGICAL_CI_* so SLOF can talk to in-kernel devices */ + kvmppc_enable_logical_ci_hcalls(); + } + /* allocate RAM */ spapr->ram_limit = ram_size; memory_region_allocate_system_memory(ram, NULL, "ppc_spapr.ram", @@ -1520,18 +1527,18 @@ static void ppc_spapr_init(MachineState *machine) filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, "spapr-rtas.bin"); if (!filename) { - hw_error("Could not find LPAR rtas '%s'\n", "spapr-rtas.bin"); + error_report("Could not find LPAR rtas '%s'", "spapr-rtas.bin"); exit(1); } spapr->rtas_size = get_image_size(filename); spapr->rtas_blob = g_malloc(spapr->rtas_size); if (load_image_size(filename, spapr->rtas_blob, spapr->rtas_size) < 0) { - hw_error("qemu: could not load LPAR rtas '%s'\n", filename); + error_report("Could not load LPAR rtas '%s'", filename); exit(1); } if (spapr->rtas_size > RTAS_MAX_SIZE) { - hw_error("RTAS too big ! 0x%zx bytes (max is 0x%x)\n", - (size_t)spapr->rtas_size, RTAS_MAX_SIZE); + error_report("RTAS too big ! 0x%zx bytes (max is 0x%x)", + (size_t)spapr->rtas_size, RTAS_MAX_SIZE); exit(1); } g_free(filename); @@ -1641,12 +1648,12 @@ static void ppc_spapr_init(MachineState *machine) } filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, bios_name); if (!filename) { - hw_error("Could not find LPAR rtas '%s'\n", bios_name); + error_report("Could not find LPAR firmware '%s'", bios_name); exit(1); } fw_size = load_image_targphys(filename, 0, FW_MAX_SIZE); - if (fw_size < 0) { - hw_error("qemu: could not load LPAR rtas '%s'\n", filename); + if (fw_size <= 0) { + error_report("Could not load LPAR firmware '%s'", filename); exit(1); } g_free(filename); @@ -1660,9 +1667,14 @@ static void ppc_spapr_init(MachineState *machine) /* Prepare the device tree */ spapr->fdt_skel = spapr_create_fdt_skel(initrd_base, initrd_size, kernel_size, kernel_le, - kernel_cmdline, spapr->epow_irq); + kernel_cmdline, + spapr->check_exception_irq); assert(spapr->fdt_skel != NULL); + /* used by RTAS */ + QTAILQ_INIT(&spapr->ccs_list); + qemu_register_reset(spapr_ccs_reset_hook, spapr); + qemu_register_boot_set(spapr_boot_set, spapr); } @@ -1794,6 +1806,7 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data) mc->max_cpus = MAX_CPUS; mc->no_parallel = 1; mc->default_boot_order = ""; + mc->default_ram_size = 512 * M_BYTE; mc->kvm_type = spapr_kvm_type; mc->has_dynamic_sysbus = true; @@ -1816,7 +1829,12 @@ static const TypeInfo spapr_machine_info = { }; #define SPAPR_COMPAT_2_3 \ - HW_COMPAT_2_3 + HW_COMPAT_2_3 \ + {\ + .driver = "spapr-pci-host-bridge",\ + .property = "dynamic-reconfiguration",\ + .value = "off",\ + }, #define SPAPR_COMPAT_2_2 \ SPAPR_COMPAT_2_3 \ @@ -1905,10 +1923,15 @@ static const TypeInfo spapr_machine_2_2_info = { static void spapr_machine_2_3_class_init(ObjectClass *oc, void *data) { + static GlobalProperty compat_props[] = { + SPAPR_COMPAT_2_3 + { /* end of list */ } + }; MachineClass *mc = MACHINE_CLASS(oc); mc->name = "pseries-2.3"; mc->desc = "pSeries Logical Partition (PAPR compliant) v2.3"; + mc->compat_props = compat_props; } static const TypeInfo spapr_machine_2_3_info = { diff --git a/hw/ppc/spapr_drc.c b/hw/ppc/spapr_drc.c new file mode 100644 index 0000000000..ef985381cb --- /dev/null +++ b/hw/ppc/spapr_drc.c @@ -0,0 +1,744 @@ +/* + * QEMU SPAPR Dynamic Reconfiguration Connector Implementation + * + * Copyright IBM Corp. 2014 + * + * Authors: + * Michael Roth <mdroth@linux.vnet.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "hw/ppc/spapr_drc.h" +#include "qom/object.h" +#include "hw/qdev.h" +#include "qapi/visitor.h" +#include "qemu/error-report.h" + +/* #define DEBUG_SPAPR_DRC */ + +#ifdef DEBUG_SPAPR_DRC +#define DPRINTF(fmt, ...) \ + do { fprintf(stderr, fmt, ## __VA_ARGS__); } while (0) +#define DPRINTFN(fmt, ...) \ + do { DPRINTF(fmt, ## __VA_ARGS__); fprintf(stderr, "\n"); } while (0) +#else +#define DPRINTF(fmt, ...) \ + do { } while (0) +#define DPRINTFN(fmt, ...) \ + do { } while (0) +#endif + +#define DRC_CONTAINER_PATH "/dr-connector" +#define DRC_INDEX_TYPE_SHIFT 28 +#define DRC_INDEX_ID_MASK (~(~0 << DRC_INDEX_TYPE_SHIFT)) + +static sPAPRDRConnectorTypeShift get_type_shift(sPAPRDRConnectorType type) +{ + uint32_t shift = 0; + + /* make sure this isn't SPAPR_DR_CONNECTOR_TYPE_ANY, or some + * other wonky value. + */ + g_assert(is_power_of_2(type)); + + while (type != (1 << shift)) { + shift++; + } + return shift; +} + +static uint32_t get_index(sPAPRDRConnector *drc) +{ + /* no set format for a drc index: it only needs to be globally + * unique. this is how we encode the DRC type on bare-metal + * however, so might as well do that here + */ + return (get_type_shift(drc->type) << DRC_INDEX_TYPE_SHIFT) | + (drc->id & DRC_INDEX_ID_MASK); +} + +static int set_isolation_state(sPAPRDRConnector *drc, + sPAPRDRIsolationState state) +{ + sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); + + DPRINTFN("drc: %x, set_isolation_state: %x", get_index(drc), state); + + drc->isolation_state = state; + + if (drc->isolation_state == SPAPR_DR_ISOLATION_STATE_ISOLATED) { + /* if we're awaiting release, but still in an unconfigured state, + * it's likely the guest is still in the process of configuring + * the device and is transitioning the devices to an ISOLATED + * state as a part of that process. so we only complete the + * removal when this transition happens for a device in a + * configured state, as suggested by the state diagram from + * PAPR+ 2.7, 13.4 + */ + if (drc->awaiting_release) { + if (drc->configured) { + DPRINTFN("finalizing device removal"); + drck->detach(drc, DEVICE(drc->dev), drc->detach_cb, + drc->detach_cb_opaque, NULL); + } else { + DPRINTFN("deferring device removal on unconfigured device\n"); + } + } + drc->configured = false; + } + + return 0; +} + +static int set_indicator_state(sPAPRDRConnector *drc, + sPAPRDRIndicatorState state) +{ + DPRINTFN("drc: %x, set_indicator_state: %x", get_index(drc), state); + drc->indicator_state = state; + return 0; +} + +static int set_allocation_state(sPAPRDRConnector *drc, + sPAPRDRAllocationState state) +{ + sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); + + DPRINTFN("drc: %x, set_allocation_state: %x", get_index(drc), state); + + if (drc->type != SPAPR_DR_CONNECTOR_TYPE_PCI) { + drc->allocation_state = state; + if (drc->awaiting_release && + drc->allocation_state == SPAPR_DR_ALLOCATION_STATE_UNUSABLE) { + DPRINTFN("finalizing device removal"); + drck->detach(drc, DEVICE(drc->dev), drc->detach_cb, + drc->detach_cb_opaque, NULL); + } + } + return 0; +} + +static uint32_t get_type(sPAPRDRConnector *drc) +{ + return drc->type; +} + +static const char *get_name(sPAPRDRConnector *drc) +{ + return drc->name; +} + +static const void *get_fdt(sPAPRDRConnector *drc, int *fdt_start_offset) +{ + if (fdt_start_offset) { + *fdt_start_offset = drc->fdt_start_offset; + } + return drc->fdt; +} + +static void set_configured(sPAPRDRConnector *drc) +{ + DPRINTFN("drc: %x, set_configured", get_index(drc)); + + if (drc->isolation_state != SPAPR_DR_ISOLATION_STATE_UNISOLATED) { + /* guest should be not configuring an isolated device */ + DPRINTFN("drc: %x, set_configured: skipping isolated device", + get_index(drc)); + return; + } + drc->configured = true; +} + +/* + * dr-entity-sense sensor value + * returned via get-sensor-state RTAS calls + * as expected by state diagram in PAPR+ 2.7, 13.4 + * based on the current allocation/indicator/power states + * for the DR connector. + */ +static sPAPRDREntitySense entity_sense(sPAPRDRConnector *drc) +{ + sPAPRDREntitySense state; + + if (drc->dev) { + if (drc->type != SPAPR_DR_CONNECTOR_TYPE_PCI && + drc->allocation_state == SPAPR_DR_ALLOCATION_STATE_UNUSABLE) { + /* for logical DR, we return a state of UNUSABLE + * iff the allocation state UNUSABLE. + * Otherwise, report the state as USABLE/PRESENT, + * as we would for PCI. + */ + state = SPAPR_DR_ENTITY_SENSE_UNUSABLE; + } else { + /* this assumes all PCI devices are assigned to + * a 'live insertion' power domain, where QEMU + * manages power state automatically as opposed + * to the guest. present, non-PCI resources are + * unaffected by power state. + */ + state = SPAPR_DR_ENTITY_SENSE_PRESENT; + } + } else { + if (drc->type == SPAPR_DR_CONNECTOR_TYPE_PCI) { + /* PCI devices, and only PCI devices, use EMPTY + * in cases where we'd otherwise use UNUSABLE + */ + state = SPAPR_DR_ENTITY_SENSE_EMPTY; + } else { + state = SPAPR_DR_ENTITY_SENSE_UNUSABLE; + } + } + + DPRINTFN("drc: %x, entity_sense: %x", get_index(drc), state); + return state; +} + +static void prop_get_index(Object *obj, Visitor *v, void *opaque, + const char *name, Error **errp) +{ + sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(obj); + sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); + uint32_t value = (uint32_t)drck->get_index(drc); + visit_type_uint32(v, &value, name, errp); +} + +static void prop_get_type(Object *obj, Visitor *v, void *opaque, + const char *name, Error **errp) +{ + sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(obj); + sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); + uint32_t value = (uint32_t)drck->get_type(drc); + visit_type_uint32(v, &value, name, errp); +} + +static char *prop_get_name(Object *obj, Error **errp) +{ + sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(obj); + sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); + return g_strdup(drck->get_name(drc)); +} + +static void prop_get_entity_sense(Object *obj, Visitor *v, void *opaque, + const char *name, Error **errp) +{ + sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(obj); + sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); + uint32_t value = (uint32_t)drck->entity_sense(drc); + visit_type_uint32(v, &value, name, errp); +} + +static void prop_get_fdt(Object *obj, Visitor *v, void *opaque, + const char *name, Error **errp) +{ + sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(obj); + int fdt_offset_next, fdt_offset, fdt_depth; + void *fdt; + + if (!drc->fdt) { + return; + } + + fdt = drc->fdt; + fdt_offset = drc->fdt_start_offset; + fdt_depth = 0; + + do { + const char *name = NULL; + const struct fdt_property *prop = NULL; + int prop_len = 0, name_len = 0; + uint32_t tag; + + tag = fdt_next_tag(fdt, fdt_offset, &fdt_offset_next); + switch (tag) { + case FDT_BEGIN_NODE: + fdt_depth++; + name = fdt_get_name(fdt, fdt_offset, &name_len); + visit_start_struct(v, NULL, NULL, name, 0, NULL); + break; + case FDT_END_NODE: + /* shouldn't ever see an FDT_END_NODE before FDT_BEGIN_NODE */ + g_assert(fdt_depth > 0); + visit_end_struct(v, NULL); + fdt_depth--; + break; + case FDT_PROP: { + int i; + prop = fdt_get_property_by_offset(fdt, fdt_offset, &prop_len); + name = fdt_string(fdt, fdt32_to_cpu(prop->nameoff)); + visit_start_list(v, name, NULL); + for (i = 0; i < prop_len; i++) { + visit_type_uint8(v, (uint8_t *)&prop->data[i], NULL, NULL); + + } + visit_end_list(v, NULL); + break; + } + default: + error_setg(&error_abort, "device FDT in unexpected state: %d", tag); + } + fdt_offset = fdt_offset_next; + } while (fdt_depth != 0); +} + +static void attach(sPAPRDRConnector *drc, DeviceState *d, void *fdt, + int fdt_start_offset, bool coldplug, Error **errp) +{ + DPRINTFN("drc: %x, attach", get_index(drc)); + + if (drc->isolation_state != SPAPR_DR_ISOLATION_STATE_ISOLATED) { + error_setg(errp, "an attached device is still awaiting release"); + return; + } + if (drc->type == SPAPR_DR_CONNECTOR_TYPE_PCI) { + g_assert(drc->allocation_state == SPAPR_DR_ALLOCATION_STATE_USABLE); + } + g_assert(fdt || coldplug); + + /* NOTE: setting initial isolation state to UNISOLATED means we can't + * detach unless guest has a userspace/kernel that moves this state + * back to ISOLATED in response to an unplug event, or this is done + * manually by the admin prior. if we force things while the guest + * may be accessing the device, we can easily crash the guest, so we + * we defer completion of removal in such cases to the reset() hook. + */ + if (drc->type == SPAPR_DR_CONNECTOR_TYPE_PCI) { + drc->isolation_state = SPAPR_DR_ISOLATION_STATE_UNISOLATED; + } + drc->indicator_state = SPAPR_DR_INDICATOR_STATE_ACTIVE; + + drc->dev = d; + drc->fdt = fdt; + drc->fdt_start_offset = fdt_start_offset; + drc->configured = false; + + object_property_add_link(OBJECT(drc), "device", + object_get_typename(OBJECT(drc->dev)), + (Object **)(&drc->dev), + NULL, 0, NULL); +} + +static void detach(sPAPRDRConnector *drc, DeviceState *d, + spapr_drc_detach_cb *detach_cb, + void *detach_cb_opaque, Error **errp) +{ + DPRINTFN("drc: %x, detach", get_index(drc)); + + drc->detach_cb = detach_cb; + drc->detach_cb_opaque = detach_cb_opaque; + + if (drc->isolation_state != SPAPR_DR_ISOLATION_STATE_ISOLATED) { + DPRINTFN("awaiting transition to isolated state before removal"); + drc->awaiting_release = true; + return; + } + + if (drc->type != SPAPR_DR_CONNECTOR_TYPE_PCI && + drc->allocation_state != SPAPR_DR_ALLOCATION_STATE_UNUSABLE) { + DPRINTFN("awaiting transition to unusable state before removal"); + drc->awaiting_release = true; + return; + } + + drc->indicator_state = SPAPR_DR_INDICATOR_STATE_INACTIVE; + + if (drc->detach_cb) { + drc->detach_cb(drc->dev, drc->detach_cb_opaque); + } + + drc->awaiting_release = false; + g_free(drc->fdt); + drc->fdt = NULL; + drc->fdt_start_offset = 0; + object_property_del(OBJECT(drc), "device", NULL); + drc->dev = NULL; + drc->detach_cb = NULL; + drc->detach_cb_opaque = NULL; +} + +static bool release_pending(sPAPRDRConnector *drc) +{ + return drc->awaiting_release; +} + +static void reset(DeviceState *d) +{ + sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(d); + sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); + + DPRINTFN("drc reset: %x", drck->get_index(drc)); + /* immediately upon reset we can safely assume DRCs whose devices + * are pending removal can be safely removed, and that they will + * subsequently be left in an ISOLATED state. move the DRC to this + * state in these cases (which will in turn complete any pending + * device removals) + */ + if (drc->awaiting_release) { + drck->set_isolation_state(drc, SPAPR_DR_ISOLATION_STATE_ISOLATED); + /* generally this should also finalize the removal, but if the device + * hasn't yet been configured we normally defer removal under the + * assumption that this transition is taking place as part of device + * configuration. so check if we're still waiting after this, and + * force removal if we are + */ + if (drc->awaiting_release) { + drck->detach(drc, DEVICE(drc->dev), drc->detach_cb, + drc->detach_cb_opaque, NULL); + } + + /* non-PCI devices may be awaiting a transition to UNUSABLE */ + if (drc->type != SPAPR_DR_CONNECTOR_TYPE_PCI && + drc->awaiting_release) { + drck->set_allocation_state(drc, SPAPR_DR_ALLOCATION_STATE_UNUSABLE); + } + } +} + +static void realize(DeviceState *d, Error **errp) +{ + sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(d); + sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); + Object *root_container; + char link_name[256]; + gchar *child_name; + Error *err = NULL; + + DPRINTFN("drc realize: %x", drck->get_index(drc)); + /* NOTE: we do this as part of realize/unrealize due to the fact + * that the guest will communicate with the DRC via RTAS calls + * referencing the global DRC index. By unlinking the DRC + * from DRC_CONTAINER_PATH/<drc_index> we effectively make it + * inaccessible by the guest, since lookups rely on this path + * existing in the composition tree + */ + root_container = container_get(object_get_root(), DRC_CONTAINER_PATH); + snprintf(link_name, sizeof(link_name), "%x", drck->get_index(drc)); + child_name = object_get_canonical_path_component(OBJECT(drc)); + DPRINTFN("drc child name: %s", child_name); + object_property_add_alias(root_container, link_name, + drc->owner, child_name, &err); + if (err) { + error_report("%s", error_get_pretty(err)); + error_free(err); + object_unref(OBJECT(drc)); + } + DPRINTFN("drc realize complete"); +} + +static void unrealize(DeviceState *d, Error **errp) +{ + sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(d); + sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); + Object *root_container; + char name[256]; + Error *err = NULL; + + DPRINTFN("drc unrealize: %x", drck->get_index(drc)); + root_container = container_get(object_get_root(), DRC_CONTAINER_PATH); + snprintf(name, sizeof(name), "%x", drck->get_index(drc)); + object_property_del(root_container, name, &err); + if (err) { + error_report("%s", error_get_pretty(err)); + error_free(err); + object_unref(OBJECT(drc)); + } +} + +sPAPRDRConnector *spapr_dr_connector_new(Object *owner, + sPAPRDRConnectorType type, + uint32_t id) +{ + sPAPRDRConnector *drc = + SPAPR_DR_CONNECTOR(object_new(TYPE_SPAPR_DR_CONNECTOR)); + + g_assert(type); + + drc->type = type; + drc->id = id; + drc->owner = owner; + object_property_add_child(owner, "dr-connector[*]", OBJECT(drc), NULL); + object_property_set_bool(OBJECT(drc), true, "realized", NULL); + + /* human-readable name for a DRC to encode into the DT + * description. this is mainly only used within a guest in place + * of the unique DRC index. + * + * in the case of VIO/PCI devices, it corresponds to a + * "location code" that maps a logical device/function (DRC index) + * to a physical (or virtual in the case of VIO) location in the + * system by chaining together the "location label" for each + * encapsulating component. + * + * since this is more to do with diagnosing physical hardware + * issues than guest compatibility, we choose location codes/DRC + * names that adhere to the documented format, but avoid encoding + * the entire topology information into the label/code, instead + * just using the location codes based on the labels for the + * endpoints (VIO/PCI adaptor connectors), which is basically + * just "C" followed by an integer ID. + * + * DRC names as documented by PAPR+ v2.7, 13.5.2.4 + * location codes as documented by PAPR+ v2.7, 12.3.1.5 + */ + switch (drc->type) { + case SPAPR_DR_CONNECTOR_TYPE_CPU: + drc->name = g_strdup_printf("CPU %d", id); + break; + case SPAPR_DR_CONNECTOR_TYPE_PHB: + drc->name = g_strdup_printf("PHB %d", id); + break; + case SPAPR_DR_CONNECTOR_TYPE_VIO: + case SPAPR_DR_CONNECTOR_TYPE_PCI: + drc->name = g_strdup_printf("C%d", id); + break; + case SPAPR_DR_CONNECTOR_TYPE_LMB: + drc->name = g_strdup_printf("LMB %d", id); + break; + default: + g_assert(false); + } + + /* PCI slot always start in a USABLE state, and stay there */ + if (drc->type == SPAPR_DR_CONNECTOR_TYPE_PCI) { + drc->allocation_state = SPAPR_DR_ALLOCATION_STATE_USABLE; + } + + return drc; +} + +static void spapr_dr_connector_instance_init(Object *obj) +{ + sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(obj); + + object_property_add_uint32_ptr(obj, "isolation-state", + &drc->isolation_state, NULL); + object_property_add_uint32_ptr(obj, "indicator-state", + &drc->indicator_state, NULL); + object_property_add_uint32_ptr(obj, "allocation-state", + &drc->allocation_state, NULL); + object_property_add_uint32_ptr(obj, "id", &drc->id, NULL); + object_property_add(obj, "index", "uint32", prop_get_index, + NULL, NULL, NULL, NULL); + object_property_add(obj, "connector_type", "uint32", prop_get_type, + NULL, NULL, NULL, NULL); + object_property_add_str(obj, "name", prop_get_name, NULL, NULL); + object_property_add(obj, "entity-sense", "uint32", prop_get_entity_sense, + NULL, NULL, NULL, NULL); + object_property_add(obj, "fdt", "struct", prop_get_fdt, + NULL, NULL, NULL, NULL); +} + +static void spapr_dr_connector_class_init(ObjectClass *k, void *data) +{ + DeviceClass *dk = DEVICE_CLASS(k); + sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_CLASS(k); + + dk->reset = reset; + dk->realize = realize; + dk->unrealize = unrealize; + drck->set_isolation_state = set_isolation_state; + drck->set_indicator_state = set_indicator_state; + drck->set_allocation_state = set_allocation_state; + drck->get_index = get_index; + drck->get_type = get_type; + drck->get_name = get_name; + drck->get_fdt = get_fdt; + drck->set_configured = set_configured; + drck->entity_sense = entity_sense; + drck->attach = attach; + drck->detach = detach; + drck->release_pending = release_pending; +} + +static const TypeInfo spapr_dr_connector_info = { + .name = TYPE_SPAPR_DR_CONNECTOR, + .parent = TYPE_DEVICE, + .instance_size = sizeof(sPAPRDRConnector), + .instance_init = spapr_dr_connector_instance_init, + .class_size = sizeof(sPAPRDRConnectorClass), + .class_init = spapr_dr_connector_class_init, +}; + +static void spapr_drc_register_types(void) +{ + type_register_static(&spapr_dr_connector_info); +} + +type_init(spapr_drc_register_types) + +/* helper functions for external users */ + +sPAPRDRConnector *spapr_dr_connector_by_index(uint32_t index) +{ + Object *obj; + char name[256]; + + snprintf(name, sizeof(name), "%s/%x", DRC_CONTAINER_PATH, index); + obj = object_resolve_path(name, NULL); + + return !obj ? NULL : SPAPR_DR_CONNECTOR(obj); +} + +sPAPRDRConnector *spapr_dr_connector_by_id(sPAPRDRConnectorType type, + uint32_t id) +{ + return spapr_dr_connector_by_index( + (get_type_shift(type) << DRC_INDEX_TYPE_SHIFT) | + (id & DRC_INDEX_ID_MASK)); +} + +/* generate a string the describes the DRC to encode into the + * device tree. + * + * as documented by PAPR+ v2.7, 13.5.2.6 and C.6.1 + */ +static const char *spapr_drc_get_type_str(sPAPRDRConnectorType type) +{ + switch (type) { + case SPAPR_DR_CONNECTOR_TYPE_CPU: + return "CPU"; + case SPAPR_DR_CONNECTOR_TYPE_PHB: + return "PHB"; + case SPAPR_DR_CONNECTOR_TYPE_VIO: + return "SLOT"; + case SPAPR_DR_CONNECTOR_TYPE_PCI: + return "28"; + case SPAPR_DR_CONNECTOR_TYPE_LMB: + return "MEM"; + default: + g_assert(false); + } + + return NULL; +} + +/** + * spapr_drc_populate_dt + * + * @fdt: libfdt device tree + * @path: path in the DT to generate properties + * @owner: parent Object/DeviceState for which to generate DRC + * descriptions for + * @drc_type_mask: mask of sPAPRDRConnectorType values corresponding + * to the types of DRCs to generate entries for + * + * generate OF properties to describe DRC topology/indices to guests + * + * as documented in PAPR+ v2.1, 13.5.2 + */ +int spapr_drc_populate_dt(void *fdt, int fdt_offset, Object *owner, + uint32_t drc_type_mask) +{ + Object *root_container; + ObjectProperty *prop; + uint32_t drc_count = 0; + GArray *drc_indexes, *drc_power_domains; + GString *drc_names, *drc_types; + int ret; + + /* the first entry of each properties is a 32-bit integer encoding + * the number of elements in the array. we won't know this until + * we complete the iteration through all the matching DRCs, but + * reserve the space now and set the offsets accordingly so we + * can fill them in later. + */ + drc_indexes = g_array_new(false, true, sizeof(uint32_t)); + drc_indexes = g_array_set_size(drc_indexes, 1); + drc_power_domains = g_array_new(false, true, sizeof(uint32_t)); + drc_power_domains = g_array_set_size(drc_power_domains, 1); + drc_names = g_string_set_size(g_string_new(NULL), sizeof(uint32_t)); + drc_types = g_string_set_size(g_string_new(NULL), sizeof(uint32_t)); + + /* aliases for all DRConnector objects will be rooted in QOM + * composition tree at DRC_CONTAINER_PATH + */ + root_container = container_get(object_get_root(), DRC_CONTAINER_PATH); + + QTAILQ_FOREACH(prop, &root_container->properties, node) { + Object *obj; + sPAPRDRConnector *drc; + sPAPRDRConnectorClass *drck; + uint32_t drc_index, drc_power_domain; + + if (!strstart(prop->type, "link<", NULL)) { + continue; + } + + obj = object_property_get_link(root_container, prop->name, NULL); + drc = SPAPR_DR_CONNECTOR(obj); + drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); + + if (owner && (drc->owner != owner)) { + continue; + } + + if ((drc->type & drc_type_mask) == 0) { + continue; + } + + drc_count++; + + /* ibm,drc-indexes */ + drc_index = cpu_to_be32(drck->get_index(drc)); + g_array_append_val(drc_indexes, drc_index); + + /* ibm,drc-power-domains */ + drc_power_domain = cpu_to_be32(-1); + g_array_append_val(drc_power_domains, drc_power_domain); + + /* ibm,drc-names */ + drc_names = g_string_append(drc_names, drck->get_name(drc)); + drc_names = g_string_insert_len(drc_names, -1, "\0", 1); + + /* ibm,drc-types */ + drc_types = g_string_append(drc_types, + spapr_drc_get_type_str(drc->type)); + drc_types = g_string_insert_len(drc_types, -1, "\0", 1); + } + + /* now write the drc count into the space we reserved at the + * beginning of the arrays previously + */ + *(uint32_t *)drc_indexes->data = cpu_to_be32(drc_count); + *(uint32_t *)drc_power_domains->data = cpu_to_be32(drc_count); + *(uint32_t *)drc_names->str = cpu_to_be32(drc_count); + *(uint32_t *)drc_types->str = cpu_to_be32(drc_count); + + ret = fdt_setprop(fdt, fdt_offset, "ibm,drc-indexes", + drc_indexes->data, + drc_indexes->len * sizeof(uint32_t)); + if (ret) { + fprintf(stderr, "Couldn't create ibm,drc-indexes property\n"); + goto out; + } + + ret = fdt_setprop(fdt, fdt_offset, "ibm,drc-power-domains", + drc_power_domains->data, + drc_power_domains->len * sizeof(uint32_t)); + if (ret) { + fprintf(stderr, "Couldn't finalize ibm,drc-power-domains property\n"); + goto out; + } + + ret = fdt_setprop(fdt, fdt_offset, "ibm,drc-names", + drc_names->str, drc_names->len); + if (ret) { + fprintf(stderr, "Couldn't finalize ibm,drc-names property\n"); + goto out; + } + + ret = fdt_setprop(fdt, fdt_offset, "ibm,drc-types", + drc_types->str, drc_types->len); + if (ret) { + fprintf(stderr, "Couldn't finalize ibm,drc-types property\n"); + goto out; + } + +out: + g_array_free(drc_indexes, true); + g_array_free(drc_power_domains, true); + g_string_free(drc_names, true); + g_string_free(drc_types, true); + + return ret; +} diff --git a/hw/ppc/spapr_events.c b/hw/ppc/spapr_events.c index 283e96bca1..fda9e3590a 100644 --- a/hw/ppc/spapr_events.c +++ b/hw/ppc/spapr_events.c @@ -32,6 +32,9 @@ #include "hw/ppc/spapr.h" #include "hw/ppc/spapr_vio.h" +#include "hw/pci/pci.h" +#include "hw/pci-host/spapr.h" +#include "hw/ppc/spapr_drc.h" #include <libfdt.h> @@ -77,6 +80,7 @@ struct rtas_error_log { #define RTAS_LOG_TYPE_ECC_UNCORR 0x00000009 #define RTAS_LOG_TYPE_ECC_CORR 0x0000000a #define RTAS_LOG_TYPE_EPOW 0x00000040 +#define RTAS_LOG_TYPE_HOTPLUG 0x000000e5 uint32_t extended_length; } QEMU_PACKED; @@ -166,6 +170,38 @@ struct epow_log_full { struct rtas_event_log_v6_epow epow; } QEMU_PACKED; +struct rtas_event_log_v6_hp { +#define RTAS_LOG_V6_SECTION_ID_HOTPLUG 0x4850 /* HP */ + struct rtas_event_log_v6_section_header hdr; + uint8_t hotplug_type; +#define RTAS_LOG_V6_HP_TYPE_CPU 1 +#define RTAS_LOG_V6_HP_TYPE_MEMORY 2 +#define RTAS_LOG_V6_HP_TYPE_SLOT 3 +#define RTAS_LOG_V6_HP_TYPE_PHB 4 +#define RTAS_LOG_V6_HP_TYPE_PCI 5 + uint8_t hotplug_action; +#define RTAS_LOG_V6_HP_ACTION_ADD 1 +#define RTAS_LOG_V6_HP_ACTION_REMOVE 2 + uint8_t hotplug_identifier; +#define RTAS_LOG_V6_HP_ID_DRC_NAME 1 +#define RTAS_LOG_V6_HP_ID_DRC_INDEX 2 +#define RTAS_LOG_V6_HP_ID_DRC_COUNT 3 + uint8_t reserved; + union { + uint32_t index; + uint32_t count; + char name[1]; + } drc; +} QEMU_PACKED; + +struct hp_log_full { + struct rtas_error_log hdr; + struct rtas_event_log_v6 v6hdr; + struct rtas_event_log_v6_maina maina; + struct rtas_event_log_v6_mainb mainb; + struct rtas_event_log_v6_hp hp; +} QEMU_PACKED; + #define EVENT_MASK_INTERNAL_ERRORS 0x80000000 #define EVENT_MASK_EPOW 0x40000000 #define EVENT_MASK_HOTPLUG 0x10000000 @@ -181,67 +217,105 @@ struct epow_log_full { } \ } while (0) -void spapr_events_fdt_skel(void *fdt, uint32_t epow_irq) +void spapr_events_fdt_skel(void *fdt, uint32_t check_exception_irq) { - uint32_t epow_irq_ranges[] = {cpu_to_be32(epow_irq), cpu_to_be32(1)}; - uint32_t epow_interrupts[] = {cpu_to_be32(epow_irq), 0}; + uint32_t irq_ranges[] = {cpu_to_be32(check_exception_irq), cpu_to_be32(1)}; + uint32_t interrupts[] = {cpu_to_be32(check_exception_irq), 0}; _FDT((fdt_begin_node(fdt, "event-sources"))); _FDT((fdt_property(fdt, "interrupt-controller", NULL, 0))); _FDT((fdt_property_cell(fdt, "#interrupt-cells", 2))); _FDT((fdt_property(fdt, "interrupt-ranges", - epow_irq_ranges, sizeof(epow_irq_ranges)))); + irq_ranges, sizeof(irq_ranges)))); _FDT((fdt_begin_node(fdt, "epow-events"))); - _FDT((fdt_property(fdt, "interrupts", - epow_interrupts, sizeof(epow_interrupts)))); + _FDT((fdt_property(fdt, "interrupts", interrupts, sizeof(interrupts)))); _FDT((fdt_end_node(fdt))); _FDT((fdt_end_node(fdt))); } -static struct epow_log_full *pending_epow; -static uint32_t next_plid; +static void rtas_event_log_queue(int log_type, void *data, bool exception) +{ + sPAPREventLogEntry *entry = g_new(sPAPREventLogEntry, 1); -static void spapr_powerdown_req(Notifier *n, void *opaque) + g_assert(data); + entry->log_type = log_type; + entry->exception = exception; + entry->data = data; + QTAILQ_INSERT_TAIL(&spapr->pending_events, entry, next); +} + +static sPAPREventLogEntry *rtas_event_log_dequeue(uint32_t event_mask, + bool exception) { - sPAPREnvironment *spapr = container_of(n, sPAPREnvironment, epow_notifier); - struct rtas_error_log *hdr; - struct rtas_event_log_v6 *v6hdr; - struct rtas_event_log_v6_maina *maina; - struct rtas_event_log_v6_mainb *mainb; - struct rtas_event_log_v6_epow *epow; - struct tm tm; - int year; + sPAPREventLogEntry *entry = NULL; - if (pending_epow) { - /* For now, we just throw away earlier events if two come - * along before any are consumed. This is sufficient for our - * powerdown messages, but we'll need more if we do more - * general error/event logging */ - g_free(pending_epow); + /* we only queue EPOW events atm. */ + if ((event_mask & EVENT_MASK_EPOW) == 0) { + return NULL; } - pending_epow = g_malloc0(sizeof(*pending_epow)); - hdr = &pending_epow->hdr; - v6hdr = &pending_epow->v6hdr; - maina = &pending_epow->maina; - mainb = &pending_epow->mainb; - epow = &pending_epow->epow; - hdr->summary = cpu_to_be32(RTAS_LOG_VERSION_6 - | RTAS_LOG_SEVERITY_EVENT - | RTAS_LOG_DISPOSITION_NOT_RECOVERED - | RTAS_LOG_OPTIONAL_PART_PRESENT - | RTAS_LOG_TYPE_EPOW); - hdr->extended_length = cpu_to_be32(sizeof(*pending_epow) - - sizeof(pending_epow->hdr)); + QTAILQ_FOREACH(entry, &spapr->pending_events, next) { + if (entry->exception != exception) { + continue; + } + + /* EPOW and hotplug events are surfaced in the same manner */ + if (entry->log_type == RTAS_LOG_TYPE_EPOW || + entry->log_type == RTAS_LOG_TYPE_HOTPLUG) { + break; + } + } + + if (entry) { + QTAILQ_REMOVE(&spapr->pending_events, entry, next); + } + return entry; +} + +static bool rtas_event_log_contains(uint32_t event_mask, bool exception) +{ + sPAPREventLogEntry *entry = NULL; + + /* we only queue EPOW events atm. */ + if ((event_mask & EVENT_MASK_EPOW) == 0) { + return false; + } + + QTAILQ_FOREACH(entry, &spapr->pending_events, next) { + if (entry->exception != exception) { + continue; + } + + /* EPOW and hotplug events are surfaced in the same manner */ + if (entry->log_type == RTAS_LOG_TYPE_EPOW || + entry->log_type == RTAS_LOG_TYPE_HOTPLUG) { + return true; + } + } + + return false; +} + +static uint32_t next_plid; + +static void spapr_init_v6hdr(struct rtas_event_log_v6 *v6hdr) +{ v6hdr->b0 = RTAS_LOG_V6_B0_VALID | RTAS_LOG_V6_B0_NEW_LOG | RTAS_LOG_V6_B0_BIGENDIAN; v6hdr->b2 = RTAS_LOG_V6_B2_POWERPC_FORMAT | RTAS_LOG_V6_B2_LOG_FORMAT_PLATFORM_EVENT; v6hdr->company = cpu_to_be32(RTAS_LOG_V6_COMPANY_IBM); +} + +static void spapr_init_maina(struct rtas_event_log_v6_maina *maina, + int section_count) +{ + struct tm tm; + int year; maina->hdr.section_id = cpu_to_be16(RTAS_LOG_V6_SECTION_ID_MAINA); maina->hdr.section_length = cpu_to_be16(sizeof(*maina)); @@ -256,8 +330,37 @@ static void spapr_powerdown_req(Notifier *n, void *opaque) | (to_bcd(tm.tm_min) << 16) | (to_bcd(tm.tm_sec) << 8)); maina->creator_id = 'H'; /* Hypervisor */ - maina->section_count = 3; /* Main-A, Main-B and EPOW */ + maina->section_count = section_count; maina->plid = next_plid++; +} + +static void spapr_powerdown_req(Notifier *n, void *opaque) +{ + sPAPREnvironment *spapr = container_of(n, sPAPREnvironment, epow_notifier); + struct rtas_error_log *hdr; + struct rtas_event_log_v6 *v6hdr; + struct rtas_event_log_v6_maina *maina; + struct rtas_event_log_v6_mainb *mainb; + struct rtas_event_log_v6_epow *epow; + struct epow_log_full *new_epow; + + new_epow = g_malloc0(sizeof(*new_epow)); + hdr = &new_epow->hdr; + v6hdr = &new_epow->v6hdr; + maina = &new_epow->maina; + mainb = &new_epow->mainb; + epow = &new_epow->epow; + + hdr->summary = cpu_to_be32(RTAS_LOG_VERSION_6 + | RTAS_LOG_SEVERITY_EVENT + | RTAS_LOG_DISPOSITION_NOT_RECOVERED + | RTAS_LOG_OPTIONAL_PART_PRESENT + | RTAS_LOG_TYPE_EPOW); + hdr->extended_length = cpu_to_be32(sizeof(*new_epow) + - sizeof(new_epow->hdr)); + + spapr_init_v6hdr(v6hdr); + spapr_init_maina(maina, 3 /* Main-A, Main-B and EPOW */); mainb->hdr.section_id = cpu_to_be16(RTAS_LOG_V6_SECTION_ID_MAINB); mainb->hdr.section_length = cpu_to_be16(sizeof(*mainb)); @@ -274,7 +377,80 @@ static void spapr_powerdown_req(Notifier *n, void *opaque) epow->event_modifier = RTAS_LOG_V6_EPOW_MODIFIER_NORMAL; epow->extended_modifier = RTAS_LOG_V6_EPOW_XMODIFIER_PARTITION_SPECIFIC; - qemu_irq_pulse(xics_get_qirq(spapr->icp, spapr->epow_irq)); + rtas_event_log_queue(RTAS_LOG_TYPE_EPOW, new_epow, true); + + qemu_irq_pulse(xics_get_qirq(spapr->icp, spapr->check_exception_irq)); +} + +static void spapr_hotplug_req_event(sPAPRDRConnector *drc, uint8_t hp_action) +{ + struct hp_log_full *new_hp; + struct rtas_error_log *hdr; + struct rtas_event_log_v6 *v6hdr; + struct rtas_event_log_v6_maina *maina; + struct rtas_event_log_v6_mainb *mainb; + struct rtas_event_log_v6_hp *hp; + sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); + sPAPRDRConnectorType drc_type = drck->get_type(drc); + + new_hp = g_malloc0(sizeof(struct hp_log_full)); + hdr = &new_hp->hdr; + v6hdr = &new_hp->v6hdr; + maina = &new_hp->maina; + mainb = &new_hp->mainb; + hp = &new_hp->hp; + + hdr->summary = cpu_to_be32(RTAS_LOG_VERSION_6 + | RTAS_LOG_SEVERITY_EVENT + | RTAS_LOG_DISPOSITION_NOT_RECOVERED + | RTAS_LOG_OPTIONAL_PART_PRESENT + | RTAS_LOG_INITIATOR_HOTPLUG + | RTAS_LOG_TYPE_HOTPLUG); + hdr->extended_length = cpu_to_be32(sizeof(*new_hp) + - sizeof(new_hp->hdr)); + + spapr_init_v6hdr(v6hdr); + spapr_init_maina(maina, 3 /* Main-A, Main-B, HP */); + + mainb->hdr.section_id = cpu_to_be16(RTAS_LOG_V6_SECTION_ID_MAINB); + mainb->hdr.section_length = cpu_to_be16(sizeof(*mainb)); + mainb->subsystem_id = 0x80; /* External environment */ + mainb->event_severity = 0x00; /* Informational / non-error */ + mainb->event_subtype = 0x00; /* Normal shutdown */ + + hp->hdr.section_id = cpu_to_be16(RTAS_LOG_V6_SECTION_ID_HOTPLUG); + hp->hdr.section_length = cpu_to_be16(sizeof(*hp)); + hp->hdr.section_version = 1; /* includes extended modifier */ + hp->hotplug_action = hp_action; + + + switch (drc_type) { + case SPAPR_DR_CONNECTOR_TYPE_PCI: + hp->drc.index = cpu_to_be32(drck->get_index(drc)); + hp->hotplug_identifier = RTAS_LOG_V6_HP_ID_DRC_INDEX; + hp->hotplug_type = RTAS_LOG_V6_HP_TYPE_PCI; + break; + default: + /* we shouldn't be signaling hotplug events for resources + * that don't support them + */ + g_assert(false); + return; + } + + rtas_event_log_queue(RTAS_LOG_TYPE_HOTPLUG, new_hp, true); + + qemu_irq_pulse(xics_get_qirq(spapr->icp, spapr->check_exception_irq)); +} + +void spapr_hotplug_req_add_event(sPAPRDRConnector *drc) +{ + spapr_hotplug_req_event(drc, RTAS_LOG_V6_HP_ACTION_ADD); +} + +void spapr_hotplug_req_remove_event(sPAPRDRConnector *drc) +{ + spapr_hotplug_req_event(drc, RTAS_LOG_V6_HP_ACTION_REMOVE); } static void check_exception(PowerPCCPU *cpu, sPAPREnvironment *spapr, @@ -282,8 +458,10 @@ static void check_exception(PowerPCCPU *cpu, sPAPREnvironment *spapr, target_ulong args, uint32_t nret, target_ulong rets) { - uint32_t mask, buf, len; + uint32_t mask, buf, len, event_len; uint64_t xinfo; + sPAPREventLogEntry *event; + struct rtas_error_log *hdr; if ((nargs < 6) || (nargs > 7) || nret != 1) { rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); @@ -298,25 +476,85 @@ static void check_exception(PowerPCCPU *cpu, sPAPREnvironment *spapr, xinfo |= (uint64_t)rtas_ld(args, 6) << 32; } - if ((mask & EVENT_MASK_EPOW) && pending_epow) { - if (sizeof(*pending_epow) < len) { - len = sizeof(*pending_epow); - } + event = rtas_event_log_dequeue(mask, true); + if (!event) { + goto out_no_events; + } + + hdr = event->data; + event_len = be32_to_cpu(hdr->extended_length) + sizeof(*hdr); + + if (event_len < len) { + len = event_len; + } + + cpu_physical_memory_write(buf, event->data, len); + rtas_st(rets, 0, RTAS_OUT_SUCCESS); + g_free(event->data); + g_free(event); + + /* according to PAPR+, the IRQ must be left asserted, or re-asserted, if + * there are still pending events to be fetched via check-exception. We + * do the latter here, since our code relies on edge-triggered + * interrupts. + */ + if (rtas_event_log_contains(mask, true)) { + qemu_irq_pulse(xics_get_qirq(spapr->icp, spapr->check_exception_irq)); + } - cpu_physical_memory_write(buf, pending_epow, len); - g_free(pending_epow); - pending_epow = NULL; - rtas_st(rets, 0, RTAS_OUT_SUCCESS); - } else { - rtas_st(rets, 0, RTAS_OUT_NO_ERRORS_FOUND); + return; + +out_no_events: + rtas_st(rets, 0, RTAS_OUT_NO_ERRORS_FOUND); +} + +static void event_scan(PowerPCCPU *cpu, sPAPREnvironment *spapr, + uint32_t token, uint32_t nargs, + target_ulong args, + uint32_t nret, target_ulong rets) +{ + uint32_t mask, buf, len, event_len; + sPAPREventLogEntry *event; + struct rtas_error_log *hdr; + + if (nargs != 4 || nret != 1) { + rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); + return; } + + mask = rtas_ld(args, 0); + buf = rtas_ld(args, 2); + len = rtas_ld(args, 3); + + event = rtas_event_log_dequeue(mask, false); + if (!event) { + goto out_no_events; + } + + hdr = event->data; + event_len = be32_to_cpu(hdr->extended_length) + sizeof(*hdr); + + if (event_len < len) { + len = event_len; + } + + cpu_physical_memory_write(buf, event->data, len); + rtas_st(rets, 0, RTAS_OUT_SUCCESS); + g_free(event->data); + g_free(event); + return; + +out_no_events: + rtas_st(rets, 0, RTAS_OUT_NO_ERRORS_FOUND); } void spapr_events_init(sPAPREnvironment *spapr) { - spapr->epow_irq = xics_alloc(spapr->icp, 0, 0, false); + QTAILQ_INIT(&spapr->pending_events); + spapr->check_exception_irq = xics_alloc(spapr->icp, 0, 0, false); spapr->epow_notifier.notify = spapr_powerdown_req; qemu_register_powerdown_notifier(&spapr->epow_notifier); spapr_rtas_register(RTAS_CHECK_EXCEPTION, "check-exception", check_exception); + spapr_rtas_register(RTAS_EVENT_SCAN, "event-scan", event_scan); } diff --git a/hw/ppc/spapr_iommu.c b/hw/ppc/spapr_iommu.c index f3990fdc32..8cd9dba9ac 100644 --- a/hw/ppc/spapr_iommu.c +++ b/hw/ppc/spapr_iommu.c @@ -41,7 +41,7 @@ enum sPAPRTCEAccess { static QLIST_HEAD(spapr_tce_tables, sPAPRTCETable) spapr_tce_tables; -static sPAPRTCETable *spapr_tce_find_by_liobn(uint32_t liobn) +sPAPRTCETable *spapr_tce_find_by_liobn(target_ulong liobn) { sPAPRTCETable *tcet; @@ -52,7 +52,7 @@ static sPAPRTCETable *spapr_tce_find_by_liobn(uint32_t liobn) } QLIST_FOREACH(tcet, &spapr_tce_tables, list) { - if (tcet->liobn == liobn) { + if (tcet->liobn == (uint32_t)liobn) { return tcet; } } @@ -126,11 +126,11 @@ static MemoryRegionIOMMUOps spapr_iommu_ops = { static int spapr_tce_table_realize(DeviceState *dev) { sPAPRTCETable *tcet = SPAPR_TCE_TABLE(dev); + uint64_t window_size = (uint64_t)tcet->nb_table << tcet->page_shift; - if (kvm_enabled()) { + if (kvm_enabled() && !(window_size >> 32)) { tcet->table = kvmppc_create_spapr_tce(tcet->liobn, - tcet->nb_table << - tcet->page_shift, + window_size, &tcet->fd, tcet->vfio_accel); } @@ -161,6 +161,7 @@ sPAPRTCETable *spapr_tce_new_table(DeviceState *owner, uint32_t liobn, bool vfio_accel) { sPAPRTCETable *tcet; + char tmp[64]; if (spapr_tce_find_by_liobn(liobn)) { fprintf(stderr, "Attempted to create TCE table with duplicate" @@ -179,7 +180,8 @@ sPAPRTCETable *spapr_tce_new_table(DeviceState *owner, uint32_t liobn, tcet->nb_table = nb_table; tcet->vfio_accel = vfio_accel; - object_property_add_child(OBJECT(owner), "tce-table", OBJECT(tcet), NULL); + snprintf(tmp, sizeof(tmp), "tce-table-%x", liobn); + object_property_add_child(OBJECT(owner), tmp, OBJECT(tcet), NULL); object_property_set_bool(OBJECT(tcet), true, "realized", NULL); @@ -247,7 +249,7 @@ static target_ulong h_put_tce_indirect(PowerPCCPU *cpu, target_ulong ioba1 = ioba; target_ulong tce_list = args[2]; target_ulong npages = args[3]; - target_ulong ret = H_PARAMETER; + target_ulong ret = H_PARAMETER, tce = 0; sPAPRTCETable *tcet = spapr_tce_find_by_liobn(liobn); CPUState *cs = CPU(cpu); hwaddr page_mask, page_size; @@ -267,7 +269,7 @@ static target_ulong h_put_tce_indirect(PowerPCCPU *cpu, for (i = 0; i < npages; ++i, ioba += page_size) { target_ulong off = (tce_list & ~SPAPR_TCE_RW) + i * sizeof(target_ulong); - target_ulong tce = ldq_phys(cs->as, off); + tce = ldq_be_phys(cs->as, off); ret = put_tce_emu(tcet, ioba, tce); if (ret) { @@ -277,11 +279,11 @@ static target_ulong h_put_tce_indirect(PowerPCCPU *cpu, /* Trace last successful or the first problematic entry */ i = i ? (i - 1) : 0; - trace_spapr_iommu_indirect(liobn, ioba1, tce_list, i, - ldq_phys(cs->as, - tce_list + i * sizeof(target_ulong)), - ret); - + if (SPAPR_IS_PCI_LIOBN(liobn)) { + trace_spapr_iommu_pci_indirect(liobn, ioba1, tce_list, i, tce, ret); + } else { + trace_spapr_iommu_indirect(liobn, ioba1, tce_list, i, tce, ret); + } return ret; } @@ -315,7 +317,11 @@ static target_ulong h_stuff_tce(PowerPCCPU *cpu, sPAPREnvironment *spapr, break; } } - trace_spapr_iommu_stuff(liobn, ioba, tce_value, npages, ret); + if (SPAPR_IS_PCI_LIOBN(liobn)) { + trace_spapr_iommu_pci_stuff(liobn, ioba, tce_value, npages, ret); + } else { + trace_spapr_iommu_stuff(liobn, ioba, tce_value, npages, ret); + } return ret; } @@ -336,7 +342,11 @@ static target_ulong h_put_tce(PowerPCCPU *cpu, sPAPREnvironment *spapr, ret = put_tce_emu(tcet, ioba, tce); } - trace_spapr_iommu_put(liobn, ioba, tce, ret); + if (SPAPR_IS_PCI_LIOBN(liobn)) { + trace_spapr_iommu_pci_put(liobn, ioba, tce, ret); + } else { + trace_spapr_iommu_put(liobn, ioba, tce, ret); + } return ret; } @@ -376,7 +386,11 @@ static target_ulong h_get_tce(PowerPCCPU *cpu, sPAPREnvironment *spapr, args[0] = tce; } } - trace_spapr_iommu_get(liobn, ioba, ret, tce); + if (SPAPR_IS_PCI_LIOBN(liobn)) { + trace_spapr_iommu_pci_get(liobn, ioba, ret, tce); + } else { + trace_spapr_iommu_get(liobn, ioba, ret, tce); + } return ret; } diff --git a/hw/ppc/spapr_pci.c b/hw/ppc/spapr_pci.c index 05f4faca6e..4df3a33db4 100644 --- a/hw/ppc/spapr_pci.c +++ b/hw/ppc/spapr_pci.c @@ -33,8 +33,11 @@ #include <libfdt.h> #include "trace.h" #include "qemu/error-report.h" +#include "qapi/qmp/qerror.h" #include "hw/pci/pci_bus.h" +#include "hw/ppc/spapr_drc.h" +#include "sysemu/device_tree.h" /* Copied from the kernel arch/powerpc/platforms/pseries/msi.c */ #define RTAS_QUERY_FN 0 @@ -47,7 +50,15 @@ #define RTAS_TYPE_MSI 1 #define RTAS_TYPE_MSIX 2 -static sPAPRPHBState *find_phb(sPAPREnvironment *spapr, uint64_t buid) +#define _FDT(exp) \ + do { \ + int ret = (exp); \ + if (ret < 0) { \ + return ret; \ + } \ + } while (0) + +sPAPRPHBState *spapr_pci_find_phb(sPAPREnvironment *spapr, uint64_t buid) { sPAPRPHBState *sphb; @@ -61,10 +72,10 @@ static sPAPRPHBState *find_phb(sPAPREnvironment *spapr, uint64_t buid) return NULL; } -static PCIDevice *find_dev(sPAPREnvironment *spapr, uint64_t buid, - uint32_t config_addr) +PCIDevice *spapr_pci_find_dev(sPAPREnvironment *spapr, uint64_t buid, + uint32_t config_addr) { - sPAPRPHBState *sphb = find_phb(spapr, buid); + sPAPRPHBState *sphb = spapr_pci_find_phb(spapr, buid); PCIHostState *phb = PCI_HOST_BRIDGE(sphb); int bus_num = (config_addr >> 16) & 0xFF; int devfn = (config_addr >> 8) & 0xFF; @@ -95,7 +106,7 @@ static void finish_read_pci_config(sPAPREnvironment *spapr, uint64_t buid, return; } - pci_dev = find_dev(spapr, buid, addr); + pci_dev = spapr_pci_find_dev(spapr, buid, addr); addr = rtas_pci_cfgaddr(addr); if (!pci_dev || (addr % size) || (addr >= pci_config_size(pci_dev))) { @@ -162,7 +173,7 @@ static void finish_write_pci_config(sPAPREnvironment *spapr, uint64_t buid, return; } - pci_dev = find_dev(spapr, buid, addr); + pci_dev = spapr_pci_find_dev(spapr, buid, addr); addr = rtas_pci_cfgaddr(addr); if (!pci_dev || (addr % size) || (addr >= pci_config_size(pci_dev))) { @@ -280,9 +291,9 @@ static void rtas_ibm_change_msi(PowerPCCPU *cpu, sPAPREnvironment *spapr, } /* Fins sPAPRPHBState */ - phb = find_phb(spapr, buid); + phb = spapr_pci_find_phb(spapr, buid); if (phb) { - pdev = find_dev(spapr, buid, config_addr); + pdev = spapr_pci_find_dev(spapr, buid, config_addr); } if (!phb || !pdev) { rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); @@ -381,9 +392,9 @@ static void rtas_ibm_query_interrupt_source_number(PowerPCCPU *cpu, spapr_pci_msi *msi; /* Find sPAPRPHBState */ - phb = find_phb(spapr, buid); + phb = spapr_pci_find_phb(spapr, buid); if (phb) { - pdev = find_dev(spapr, buid, config_addr); + pdev = spapr_pci_find_dev(spapr, buid, config_addr); } if (!phb || !pdev) { rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); @@ -426,7 +437,7 @@ static void rtas_ibm_set_eeh_option(PowerPCCPU *cpu, addr = rtas_ld(args, 0); option = rtas_ld(args, 3); - sphb = find_phb(spapr, buid); + sphb = spapr_pci_find_phb(spapr, buid); if (!sphb) { goto param_error_exit; } @@ -461,7 +472,7 @@ static void rtas_ibm_get_config_addr_info2(PowerPCCPU *cpu, } buid = ((uint64_t)rtas_ld(args, 1) << 32) | rtas_ld(args, 2); - sphb = find_phb(spapr, buid); + sphb = spapr_pci_find_phb(spapr, buid); if (!sphb) { goto param_error_exit; } @@ -479,7 +490,7 @@ static void rtas_ibm_get_config_addr_info2(PowerPCCPU *cpu, switch (option) { case RTAS_GET_PE_ADDR: addr = rtas_ld(args, 0); - pdev = find_dev(spapr, buid, addr); + pdev = spapr_pci_find_dev(spapr, buid, addr); if (!pdev) { goto param_error_exit; } @@ -516,7 +527,7 @@ static void rtas_ibm_read_slot_reset_state2(PowerPCCPU *cpu, } buid = ((uint64_t)rtas_ld(args, 1) << 32) | rtas_ld(args, 2); - sphb = find_phb(spapr, buid); + sphb = spapr_pci_find_phb(spapr, buid); if (!sphb) { goto param_error_exit; } @@ -562,7 +573,7 @@ static void rtas_ibm_set_slot_reset(PowerPCCPU *cpu, buid = ((uint64_t)rtas_ld(args, 1) << 32) | rtas_ld(args, 2); option = rtas_ld(args, 3); - sphb = find_phb(spapr, buid); + sphb = spapr_pci_find_phb(spapr, buid); if (!sphb) { goto param_error_exit; } @@ -596,7 +607,7 @@ static void rtas_ibm_configure_pe(PowerPCCPU *cpu, } buid = ((uint64_t)rtas_ld(args, 1) << 32) | rtas_ld(args, 2); - sphb = find_phb(spapr, buid); + sphb = spapr_pci_find_phb(spapr, buid); if (!sphb) { goto param_error_exit; } @@ -631,7 +642,7 @@ static void rtas_ibm_slot_error_detail(PowerPCCPU *cpu, } buid = ((uint64_t)rtas_ld(args, 1) << 32) | rtas_ld(args, 2); - sphb = find_phb(spapr, buid); + sphb = spapr_pci_find_phb(spapr, buid); if (!sphb) { goto param_error_exit; } @@ -731,6 +742,372 @@ static AddressSpace *spapr_pci_dma_iommu(PCIBus *bus, void *opaque, int devfn) return &phb->iommu_as; } +/* Macros to operate with address in OF binding to PCI */ +#define b_x(x, p, l) (((x) & ((1<<(l))-1)) << (p)) +#define b_n(x) b_x((x), 31, 1) /* 0 if relocatable */ +#define b_p(x) b_x((x), 30, 1) /* 1 if prefetchable */ +#define b_t(x) b_x((x), 29, 1) /* 1 if the address is aliased */ +#define b_ss(x) b_x((x), 24, 2) /* the space code */ +#define b_bbbbbbbb(x) b_x((x), 16, 8) /* bus number */ +#define b_ddddd(x) b_x((x), 11, 5) /* device number */ +#define b_fff(x) b_x((x), 8, 3) /* function number */ +#define b_rrrrrrrr(x) b_x((x), 0, 8) /* register number */ + +/* for 'reg'/'assigned-addresses' OF properties */ +#define RESOURCE_CELLS_SIZE 2 +#define RESOURCE_CELLS_ADDRESS 3 + +typedef struct ResourceFields { + uint32_t phys_hi; + uint32_t phys_mid; + uint32_t phys_lo; + uint32_t size_hi; + uint32_t size_lo; +} QEMU_PACKED ResourceFields; + +typedef struct ResourceProps { + ResourceFields reg[8]; + ResourceFields assigned[7]; + uint32_t reg_len; + uint32_t assigned_len; +} ResourceProps; + +/* fill in the 'reg'/'assigned-resources' OF properties for + * a PCI device. 'reg' describes resource requirements for a + * device's IO/MEM regions, 'assigned-addresses' describes the + * actual resource assignments. + * + * the properties are arrays of ('phys-addr', 'size') pairs describing + * the addressable regions of the PCI device, where 'phys-addr' is a + * RESOURCE_CELLS_ADDRESS-tuple of 32-bit integers corresponding to + * (phys.hi, phys.mid, phys.lo), and 'size' is a + * RESOURCE_CELLS_SIZE-tuple corresponding to (size.hi, size.lo). + * + * phys.hi = 0xYYXXXXZZ, where: + * 0xYY = npt000ss + * ||| | + * ||| +-- space code: 1 if IO region, 2 if MEM region + * ||+------ for non-relocatable IO: 1 if aliased + * || for relocatable IO: 1 if below 64KB + * || for MEM: 1 if below 1MB + * |+------- 1 if region is prefetchable + * +-------- 1 if region is non-relocatable + * 0xXXXX = bbbbbbbb dddddfff, encoding bus, slot, and function + * bits respectively + * 0xZZ = rrrrrrrr, the register number of the BAR corresponding + * to the region + * + * phys.mid and phys.lo correspond respectively to the hi/lo portions + * of the actual address of the region. + * + * how the phys-addr/size values are used differ slightly between + * 'reg' and 'assigned-addresses' properties. namely, 'reg' has + * an additional description for the config space region of the + * device, and in the case of QEMU has n=0 and phys.mid=phys.lo=0 + * to describe the region as relocatable, with an address-mapping + * that corresponds directly to the PHB's address space for the + * resource. 'assigned-addresses' always has n=1 set with an absolute + * address assigned for the resource. in general, 'assigned-addresses' + * won't be populated, since addresses for PCI devices are generally + * unmapped initially and left to the guest to assign. + * + * note also that addresses defined in these properties are, at least + * for PAPR guests, relative to the PHBs IO/MEM windows, and + * correspond directly to the addresses in the BARs. + * + * in accordance with PCI Bus Binding to Open Firmware, + * IEEE Std 1275-1994, section 4.1.1, as implemented by PAPR+ v2.7, + * Appendix C. + */ +static void populate_resource_props(PCIDevice *d, ResourceProps *rp) +{ + int bus_num = pci_bus_num(PCI_BUS(qdev_get_parent_bus(DEVICE(d)))); + uint32_t dev_id = (b_bbbbbbbb(bus_num) | + b_ddddd(PCI_SLOT(d->devfn)) | + b_fff(PCI_FUNC(d->devfn))); + ResourceFields *reg, *assigned; + int i, reg_idx = 0, assigned_idx = 0; + + /* config space region */ + reg = &rp->reg[reg_idx++]; + reg->phys_hi = cpu_to_be32(dev_id); + reg->phys_mid = 0; + reg->phys_lo = 0; + reg->size_hi = 0; + reg->size_lo = 0; + + for (i = 0; i < PCI_NUM_REGIONS; i++) { + if (!d->io_regions[i].size) { + continue; + } + + reg = &rp->reg[reg_idx++]; + + reg->phys_hi = cpu_to_be32(dev_id | b_rrrrrrrr(pci_bar(d, i))); + if (d->io_regions[i].type & PCI_BASE_ADDRESS_SPACE_IO) { + reg->phys_hi |= cpu_to_be32(b_ss(1)); + } else { + reg->phys_hi |= cpu_to_be32(b_ss(2)); + } + reg->phys_mid = 0; + reg->phys_lo = 0; + reg->size_hi = cpu_to_be32(d->io_regions[i].size >> 32); + reg->size_lo = cpu_to_be32(d->io_regions[i].size); + + if (d->io_regions[i].addr == PCI_BAR_UNMAPPED) { + continue; + } + + assigned = &rp->assigned[assigned_idx++]; + assigned->phys_hi = cpu_to_be32(reg->phys_hi | b_n(1)); + assigned->phys_mid = cpu_to_be32(d->io_regions[i].addr >> 32); + assigned->phys_lo = cpu_to_be32(d->io_regions[i].addr); + assigned->size_hi = reg->size_hi; + assigned->size_lo = reg->size_lo; + } + + rp->reg_len = reg_idx * sizeof(ResourceFields); + rp->assigned_len = assigned_idx * sizeof(ResourceFields); +} + +static int spapr_populate_pci_child_dt(PCIDevice *dev, void *fdt, int offset, + int phb_index, int drc_index, + const char *drc_name) +{ + ResourceProps rp; + bool is_bridge = false; + int pci_status; + + if (pci_default_read_config(dev, PCI_HEADER_TYPE, 1) == + PCI_HEADER_TYPE_BRIDGE) { + is_bridge = true; + } + + /* in accordance with PAPR+ v2.7 13.6.3, Table 181 */ + _FDT(fdt_setprop_cell(fdt, offset, "vendor-id", + pci_default_read_config(dev, PCI_VENDOR_ID, 2))); + _FDT(fdt_setprop_cell(fdt, offset, "device-id", + pci_default_read_config(dev, PCI_DEVICE_ID, 2))); + _FDT(fdt_setprop_cell(fdt, offset, "revision-id", + pci_default_read_config(dev, PCI_REVISION_ID, 1))); + _FDT(fdt_setprop_cell(fdt, offset, "class-code", + pci_default_read_config(dev, PCI_CLASS_DEVICE, 2) + << 8)); + if (pci_default_read_config(dev, PCI_INTERRUPT_PIN, 1)) { + _FDT(fdt_setprop_cell(fdt, offset, "interrupts", + pci_default_read_config(dev, PCI_INTERRUPT_PIN, 1))); + } + + if (!is_bridge) { + _FDT(fdt_setprop_cell(fdt, offset, "min-grant", + pci_default_read_config(dev, PCI_MIN_GNT, 1))); + _FDT(fdt_setprop_cell(fdt, offset, "max-latency", + pci_default_read_config(dev, PCI_MAX_LAT, 1))); + } + + if (pci_default_read_config(dev, PCI_SUBSYSTEM_ID, 2)) { + _FDT(fdt_setprop_cell(fdt, offset, "subsystem-id", + pci_default_read_config(dev, PCI_SUBSYSTEM_ID, 2))); + } + + if (pci_default_read_config(dev, PCI_SUBSYSTEM_VENDOR_ID, 2)) { + _FDT(fdt_setprop_cell(fdt, offset, "subsystem-vendor-id", + pci_default_read_config(dev, PCI_SUBSYSTEM_VENDOR_ID, 2))); + } + + _FDT(fdt_setprop_cell(fdt, offset, "cache-line-size", + pci_default_read_config(dev, PCI_CACHE_LINE_SIZE, 1))); + + /* the following fdt cells are masked off the pci status register */ + pci_status = pci_default_read_config(dev, PCI_STATUS, 2); + _FDT(fdt_setprop_cell(fdt, offset, "devsel-speed", + PCI_STATUS_DEVSEL_MASK & pci_status)); + + if (pci_status & PCI_STATUS_FAST_BACK) { + _FDT(fdt_setprop(fdt, offset, "fast-back-to-back", NULL, 0)); + } + if (pci_status & PCI_STATUS_66MHZ) { + _FDT(fdt_setprop(fdt, offset, "66mhz-capable", NULL, 0)); + } + if (pci_status & PCI_STATUS_UDF) { + _FDT(fdt_setprop(fdt, offset, "udf-supported", NULL, 0)); + } + + /* NOTE: this is normally generated by firmware via path/unit name, + * but in our case we must set it manually since it does not get + * processed by OF beforehand + */ + _FDT(fdt_setprop_string(fdt, offset, "name", "pci")); + _FDT(fdt_setprop(fdt, offset, "ibm,loc-code", drc_name, strlen(drc_name))); + _FDT(fdt_setprop_cell(fdt, offset, "ibm,my-drc-index", drc_index)); + + _FDT(fdt_setprop_cell(fdt, offset, "#address-cells", + RESOURCE_CELLS_ADDRESS)); + _FDT(fdt_setprop_cell(fdt, offset, "#size-cells", + RESOURCE_CELLS_SIZE)); + _FDT(fdt_setprop_cell(fdt, offset, "ibm,req#msi-x", + RESOURCE_CELLS_SIZE)); + + populate_resource_props(dev, &rp); + _FDT(fdt_setprop(fdt, offset, "reg", (uint8_t *)rp.reg, rp.reg_len)); + _FDT(fdt_setprop(fdt, offset, "assigned-addresses", + (uint8_t *)rp.assigned, rp.assigned_len)); + + return 0; +} + +/* create OF node for pci device and required OF DT properties */ +static void *spapr_create_pci_child_dt(sPAPRPHBState *phb, PCIDevice *dev, + int drc_index, const char *drc_name, + int *dt_offset) +{ + void *fdt; + int offset, ret, fdt_size; + int slot = PCI_SLOT(dev->devfn); + int func = PCI_FUNC(dev->devfn); + char nodename[512]; + + fdt = create_device_tree(&fdt_size); + if (func != 0) { + sprintf(nodename, "pci@%d,%d", slot, func); + } else { + sprintf(nodename, "pci@%d", slot); + } + offset = fdt_add_subnode(fdt, 0, nodename); + ret = spapr_populate_pci_child_dt(dev, fdt, offset, phb->index, drc_index, + drc_name); + g_assert(!ret); + + *dt_offset = offset; + return fdt; +} + +static void spapr_phb_add_pci_device(sPAPRDRConnector *drc, + sPAPRPHBState *phb, + PCIDevice *pdev, + Error **errp) +{ + sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); + DeviceState *dev = DEVICE(pdev); + int drc_index = drck->get_index(drc); + const char *drc_name = drck->get_name(drc); + void *fdt = NULL; + int fdt_start_offset = 0; + + /* boot-time devices get their device tree node created by SLOF, but for + * hotplugged devices we need QEMU to generate it so the guest can fetch + * it via RTAS + */ + if (dev->hotplugged) { + fdt = spapr_create_pci_child_dt(phb, pdev, drc_index, drc_name, + &fdt_start_offset); + } + + drck->attach(drc, DEVICE(pdev), + fdt, fdt_start_offset, !dev->hotplugged, errp); + if (*errp) { + g_free(fdt); + } +} + +static void spapr_phb_remove_pci_device_cb(DeviceState *dev, void *opaque) +{ + /* some version guests do not wait for completion of a device + * cleanup (generally done asynchronously by the kernel) before + * signaling to QEMU that the device is safe, but instead sleep + * for some 'safe' period of time. unfortunately on a busy host + * this sleep isn't guaranteed to be long enough, resulting in + * bad things like IRQ lines being left asserted during final + * device removal. to deal with this we call reset just prior + * to finalizing the device, which will put the device back into + * an 'idle' state, as the device cleanup code expects. + */ + pci_device_reset(PCI_DEVICE(dev)); + object_unparent(OBJECT(dev)); +} + +static void spapr_phb_remove_pci_device(sPAPRDRConnector *drc, + sPAPRPHBState *phb, + PCIDevice *pdev, + Error **errp) +{ + sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); + + drck->detach(drc, DEVICE(pdev), spapr_phb_remove_pci_device_cb, phb, errp); +} + +static sPAPRDRConnector *spapr_phb_get_pci_drc(sPAPRPHBState *phb, + PCIDevice *pdev) +{ + uint32_t busnr = pci_bus_num(PCI_BUS(qdev_get_parent_bus(DEVICE(pdev)))); + return spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_PCI, + (phb->index << 16) | + (busnr << 8) | + pdev->devfn); +} + +static void spapr_phb_hot_plug_child(HotplugHandler *plug_handler, + DeviceState *plugged_dev, Error **errp) +{ + sPAPRPHBState *phb = SPAPR_PCI_HOST_BRIDGE(DEVICE(plug_handler)); + PCIDevice *pdev = PCI_DEVICE(plugged_dev); + sPAPRDRConnector *drc = spapr_phb_get_pci_drc(phb, pdev); + Error *local_err = NULL; + + /* if DR is disabled we don't need to do anything in the case of + * hotplug or coldplug callbacks + */ + if (!phb->dr_enabled) { + /* if this is a hotplug operation initiated by the user + * we need to let them know it's not enabled + */ + if (plugged_dev->hotplugged) { + error_set(errp, QERR_BUS_NO_HOTPLUG, + object_get_typename(OBJECT(phb))); + } + return; + } + + g_assert(drc); + + spapr_phb_add_pci_device(drc, phb, pdev, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } + if (plugged_dev->hotplugged) { + spapr_hotplug_req_add_event(drc); + } +} + +static void spapr_phb_hot_unplug_child(HotplugHandler *plug_handler, + DeviceState *plugged_dev, Error **errp) +{ + sPAPRPHBState *phb = SPAPR_PCI_HOST_BRIDGE(DEVICE(plug_handler)); + PCIDevice *pdev = PCI_DEVICE(plugged_dev); + sPAPRDRConnectorClass *drck; + sPAPRDRConnector *drc = spapr_phb_get_pci_drc(phb, pdev); + Error *local_err = NULL; + + if (!phb->dr_enabled) { + error_set(errp, QERR_BUS_NO_HOTPLUG, + object_get_typename(OBJECT(phb))); + return; + } + + g_assert(drc); + + drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); + if (!drck->release_pending(drc)) { + spapr_phb_remove_pci_device(drc, phb, pdev, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } + spapr_hotplug_req_remove_event(drc); + } +} + static void spapr_phb_realize(DeviceState *dev, Error **errp) { SysBusDevice *s = SYS_BUS_DEVICE(dev); @@ -742,12 +1119,12 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp) PCIBus *bus; uint64_t msi_window_size = 4096; - if (sphb->index != -1) { + if (sphb->index != (uint32_t)-1) { hwaddr windows_base; - if ((sphb->buid != -1) || (sphb->dma_liobn != -1) - || (sphb->mem_win_addr != -1) - || (sphb->io_win_addr != -1)) { + if ((sphb->buid != (uint64_t)-1) || (sphb->dma_liobn != (uint32_t)-1) + || (sphb->mem_win_addr != (hwaddr)-1) + || (sphb->io_win_addr != (hwaddr)-1)) { error_setg(errp, "Either \"index\" or other parameters must" " be specified for PAPR PHB, not both"); return; @@ -760,7 +1137,7 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp) } sphb->buid = SPAPR_PCI_BASE_BUID + sphb->index; - sphb->dma_liobn = SPAPR_PCI_BASE_LIOBN + sphb->index; + sphb->dma_liobn = SPAPR_PCI_LIOBN(sphb->index, 0); windows_base = SPAPR_PCI_WINDOW_BASE + sphb->index * SPAPR_PCI_WINDOW_SPACING; @@ -768,27 +1145,27 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp) sphb->io_win_addr = windows_base + SPAPR_PCI_IO_WIN_OFF; } - if (sphb->buid == -1) { + if (sphb->buid == (uint64_t)-1) { error_setg(errp, "BUID not specified for PHB"); return; } - if (sphb->dma_liobn == -1) { + if (sphb->dma_liobn == (uint32_t)-1) { error_setg(errp, "LIOBN not specified for PHB"); return; } - if (sphb->mem_win_addr == -1) { + if (sphb->mem_win_addr == (hwaddr)-1) { error_setg(errp, "Memory window address not specified for PHB"); return; } - if (sphb->io_win_addr == -1) { + if (sphb->io_win_addr == (hwaddr)-1) { error_setg(errp, "IO window address not specified for PHB"); return; } - if (find_phb(spapr, sphb->buid)) { + if (spapr_pci_find_phb(spapr, sphb->buid)) { error_setg(errp, "PCI host bridges must have unique BUIDs"); return; } @@ -824,6 +1201,7 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp) &sphb->memspace, &sphb->iospace, PCI_DEVFN(0, 0), PCI_NUM_PINS, TYPE_PCI_BUS); phb->bus = bus; + qbus_set_hotplug_handler(BUS(phb->bus), DEVICE(sphb), NULL); /* * Initialize PHB address space. @@ -880,6 +1258,15 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp) sphb->lsi_table[i].irq = irq; } + /* allocate connectors for child PCI devices */ + if (sphb->dr_enabled) { + for (i = 0; i < PCI_SLOT_MAX * 8; i++) { + spapr_dr_connector_new(OBJECT(phb), + SPAPR_DR_CONNECTOR_TYPE_PCI, + (sphb->index << 16) | i); + } + } + if (!info->finish_realize) { error_setg(errp, "finish_realize not defined"); return; @@ -893,11 +1280,11 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp) static void spapr_phb_finish_realize(sPAPRPHBState *sphb, Error **errp) { sPAPRTCETable *tcet; + uint32_t nb_table; + nb_table = SPAPR_PCI_DMA32_SIZE >> SPAPR_TCE_PAGE_SHIFT; tcet = spapr_tce_new_table(DEVICE(sphb), sphb->dma_liobn, - 0, - SPAPR_TCE_PAGE_SHIFT, - 0x40000000 >> SPAPR_TCE_PAGE_SHIFT, false); + 0, SPAPR_TCE_PAGE_SHIFT, nb_table, false); if (!tcet) { error_setg(errp, "Unable to create TCE table for %s", sphb->dtbusname); @@ -936,6 +1323,8 @@ static Property spapr_phb_properties[] = { DEFINE_PROP_UINT64("io_win_addr", sPAPRPHBState, io_win_addr, -1), DEFINE_PROP_UINT64("io_win_size", sPAPRPHBState, io_win_size, SPAPR_PCI_IO_WIN_SIZE), + DEFINE_PROP_BOOL("dynamic-reconfiguration", sPAPRPHBState, dr_enabled, + true), DEFINE_PROP_END_OF_LIST(), }; @@ -1049,6 +1438,7 @@ static void spapr_phb_class_init(ObjectClass *klass, void *data) PCIHostBridgeClass *hc = PCI_HOST_BRIDGE_CLASS(klass); DeviceClass *dc = DEVICE_CLASS(klass); sPAPRPHBClass *spc = SPAPR_PCI_HOST_BRIDGE_CLASS(klass); + HotplugHandlerClass *hp = HOTPLUG_HANDLER_CLASS(klass); hc->root_bus_path = spapr_phb_root_bus_path; dc->realize = spapr_phb_realize; @@ -1058,6 +1448,8 @@ static void spapr_phb_class_init(ObjectClass *klass, void *data) set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories); dc->cannot_instantiate_with_device_add_yet = false; spc->finish_realize = spapr_phb_finish_realize; + hp->plug = spapr_phb_hot_plug_child; + hp->unplug = spapr_phb_hot_unplug_child; } static const TypeInfo spapr_phb_info = { @@ -1066,6 +1458,10 @@ static const TypeInfo spapr_phb_info = { .instance_size = sizeof(sPAPRPHBState), .class_init = spapr_phb_class_init, .class_size = sizeof(sPAPRPHBClass), + .interfaces = (InterfaceInfo[]) { + { TYPE_HOTPLUG_HANDLER }, + { } + } }; PCIHostState *spapr_create_phb(sPAPREnvironment *spapr, int index) @@ -1079,45 +1475,11 @@ PCIHostState *spapr_create_phb(sPAPREnvironment *spapr, int index) return PCI_HOST_BRIDGE(dev); } -/* Macros to operate with address in OF binding to PCI */ -#define b_x(x, p, l) (((x) & ((1<<(l))-1)) << (p)) -#define b_n(x) b_x((x), 31, 1) /* 0 if relocatable */ -#define b_p(x) b_x((x), 30, 1) /* 1 if prefetchable */ -#define b_t(x) b_x((x), 29, 1) /* 1 if the address is aliased */ -#define b_ss(x) b_x((x), 24, 2) /* the space code */ -#define b_bbbbbbbb(x) b_x((x), 16, 8) /* bus number */ -#define b_ddddd(x) b_x((x), 11, 5) /* device number */ -#define b_fff(x) b_x((x), 8, 3) /* function number */ -#define b_rrrrrrrr(x) b_x((x), 0, 8) /* register number */ - -typedef struct sPAPRTCEDT { - void *fdt; - int node_off; -} sPAPRTCEDT; - -static int spapr_phb_children_dt(Object *child, void *opaque) -{ - sPAPRTCEDT *p = opaque; - sPAPRTCETable *tcet; - - tcet = (sPAPRTCETable *) object_dynamic_cast(child, TYPE_SPAPR_TCE_TABLE); - if (!tcet) { - return 0; - } - - spapr_dma_dt(p->fdt, p->node_off, "ibm,dma-window", - tcet->liobn, tcet->bus_offset, - tcet->nb_table << tcet->page_shift); - /* Stop after the first window */ - - return 1; -} - int spapr_populate_pci_dt(sPAPRPHBState *phb, uint32_t xics_phandle, void *fdt) { - int bus_off, i, j; + int bus_off, i, j, ret; char nodename[256]; uint32_t bus_range[] = { cpu_to_be32(0), cpu_to_be32(0xff) }; const uint64_t mmiosize = memory_region_size(&phb->memwindow); @@ -1151,6 +1513,7 @@ int spapr_populate_pci_dt(sPAPRPHBState *phb, uint32_t interrupt_map_mask[] = { cpu_to_be32(b_ddddd(-1)|b_fff(0)), 0x0, 0x0, cpu_to_be32(-1)}; uint32_t interrupt_map[PCI_SLOT_MAX * PCI_NUM_PINS][7]; + sPAPRTCETable *tcet; /* Start populating the FDT */ sprintf(nodename, "pci@%" PRIx64, phb->buid); @@ -1159,14 +1522,6 @@ int spapr_populate_pci_dt(sPAPRPHBState *phb, return bus_off; } -#define _FDT(exp) \ - do { \ - int ret = (exp); \ - if (ret < 0) { \ - return ret; \ - } \ - } while (0) - /* Write PHB properties */ _FDT(fdt_setprop_string(fdt, bus_off, "device_type", "pci")); _FDT(fdt_setprop_string(fdt, bus_off, "compatible", "IBM,Logical_PHB")); @@ -1203,8 +1558,16 @@ int spapr_populate_pci_dt(sPAPRPHBState *phb, _FDT(fdt_setprop(fdt, bus_off, "interrupt-map", &interrupt_map, sizeof(interrupt_map))); - object_child_foreach(OBJECT(phb), spapr_phb_children_dt, - &((sPAPRTCEDT){ .fdt = fdt, .node_off = bus_off })); + tcet = spapr_tce_find_by_liobn(SPAPR_PCI_LIOBN(phb->index, 0)); + spapr_dma_dt(fdt, bus_off, "ibm,dma-window", + tcet->liobn, tcet->bus_offset, + tcet->nb_table << tcet->page_shift); + + ret = spapr_drc_populate_dt(fdt, bus_off, OBJECT(phb), + SPAPR_DR_CONNECTOR_TYPE_PCI); + if (ret) { + return ret; + } return 0; } diff --git a/hw/ppc/spapr_rtas.c b/hw/ppc/spapr_rtas.c index 0f1ae55828..fa28d43f81 100644 --- a/hw/ppc/spapr_rtas.c +++ b/hw/ppc/spapr_rtas.c @@ -35,6 +35,55 @@ #include "qapi-event.h" #include <libfdt.h> +#include "hw/ppc/spapr_drc.h" + +/* #define DEBUG_SPAPR */ + +#ifdef DEBUG_SPAPR +#define DPRINTF(fmt, ...) \ + do { fprintf(stderr, fmt, ## __VA_ARGS__); } while (0) +#else +#define DPRINTF(fmt, ...) \ + do { } while (0) +#endif + +static sPAPRConfigureConnectorState *spapr_ccs_find(sPAPREnvironment *spapr, + uint32_t drc_index) +{ + sPAPRConfigureConnectorState *ccs = NULL; + + QTAILQ_FOREACH(ccs, &spapr->ccs_list, next) { + if (ccs->drc_index == drc_index) { + break; + } + } + + return ccs; +} + +static void spapr_ccs_add(sPAPREnvironment *spapr, + sPAPRConfigureConnectorState *ccs) +{ + g_assert(!spapr_ccs_find(spapr, ccs->drc_index)); + QTAILQ_INSERT_HEAD(&spapr->ccs_list, ccs, next); +} + +static void spapr_ccs_remove(sPAPREnvironment *spapr, + sPAPRConfigureConnectorState *ccs) +{ + QTAILQ_REMOVE(&spapr->ccs_list, ccs, next); + g_free(ccs); +} + +void spapr_ccs_reset_hook(void *opaque) +{ + sPAPREnvironment *spapr = opaque; + sPAPRConfigureConnectorState *ccs, *ccs_tmp; + + QTAILQ_FOREACH_SAFE(ccs, &spapr->ccs_list, next, ccs_tmp) { + spapr_ccs_remove(spapr, ccs); + } +} static void rtas_display_character(PowerPCCPU *cpu, sPAPREnvironment *spapr, uint32_t token, uint32_t nargs, @@ -245,6 +294,308 @@ static void rtas_ibm_os_term(PowerPCCPU *cpu, rtas_st(rets, 0, ret); } +static void rtas_set_power_level(PowerPCCPU *cpu, sPAPREnvironment *spapr, + uint32_t token, uint32_t nargs, + target_ulong args, uint32_t nret, + target_ulong rets) +{ + int32_t power_domain; + + if (nargs != 2 || nret != 2) { + rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); + return; + } + + /* we currently only use a single, "live insert" powerdomain for + * hotplugged/dlpar'd resources, so the power is always live/full (100) + */ + power_domain = rtas_ld(args, 0); + if (power_domain != -1) { + rtas_st(rets, 0, RTAS_OUT_NOT_SUPPORTED); + return; + } + + rtas_st(rets, 0, RTAS_OUT_SUCCESS); + rtas_st(rets, 1, 100); +} + +static void rtas_get_power_level(PowerPCCPU *cpu, sPAPREnvironment *spapr, + uint32_t token, uint32_t nargs, + target_ulong args, uint32_t nret, + target_ulong rets) +{ + int32_t power_domain; + + if (nargs != 1 || nret != 2) { + rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); + return; + } + + /* we currently only use a single, "live insert" powerdomain for + * hotplugged/dlpar'd resources, so the power is always live/full (100) + */ + power_domain = rtas_ld(args, 0); + if (power_domain != -1) { + rtas_st(rets, 0, RTAS_OUT_NOT_SUPPORTED); + return; + } + + rtas_st(rets, 0, RTAS_OUT_SUCCESS); + rtas_st(rets, 1, 100); +} + +static bool sensor_type_is_dr(uint32_t sensor_type) +{ + switch (sensor_type) { + case RTAS_SENSOR_TYPE_ISOLATION_STATE: + case RTAS_SENSOR_TYPE_DR: + case RTAS_SENSOR_TYPE_ALLOCATION_STATE: + return true; + } + + return false; +} + +static void rtas_set_indicator(PowerPCCPU *cpu, sPAPREnvironment *spapr, + uint32_t token, uint32_t nargs, + target_ulong args, uint32_t nret, + target_ulong rets) +{ + uint32_t sensor_type; + uint32_t sensor_index; + uint32_t sensor_state; + sPAPRDRConnector *drc; + sPAPRDRConnectorClass *drck; + + if (nargs != 3 || nret != 1) { + rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); + return; + } + + sensor_type = rtas_ld(args, 0); + sensor_index = rtas_ld(args, 1); + sensor_state = rtas_ld(args, 2); + + if (!sensor_type_is_dr(sensor_type)) { + goto out_unimplemented; + } + + /* if this is a DR sensor we can assume sensor_index == drc_index */ + drc = spapr_dr_connector_by_index(sensor_index); + if (!drc) { + DPRINTF("rtas_set_indicator: invalid sensor/DRC index: %xh\n", + sensor_index); + rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); + return; + } + drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); + + switch (sensor_type) { + case RTAS_SENSOR_TYPE_ISOLATION_STATE: + /* if the guest is configuring a device attached to this + * DRC, we should reset the configuration state at this + * point since it may no longer be reliable (guest released + * device and needs to start over, or unplug occurred so + * the FDT is no longer valid) + */ + if (sensor_state == SPAPR_DR_ISOLATION_STATE_ISOLATED) { + sPAPRConfigureConnectorState *ccs = spapr_ccs_find(spapr, + sensor_index); + if (ccs) { + spapr_ccs_remove(spapr, ccs); + } + } + drck->set_isolation_state(drc, sensor_state); + break; + case RTAS_SENSOR_TYPE_DR: + drck->set_indicator_state(drc, sensor_state); + break; + case RTAS_SENSOR_TYPE_ALLOCATION_STATE: + drck->set_allocation_state(drc, sensor_state); + break; + default: + goto out_unimplemented; + } + + rtas_st(rets, 0, RTAS_OUT_SUCCESS); + return; + +out_unimplemented: + /* currently only DR-related sensors are implemented */ + DPRINTF("rtas_set_indicator: sensor/indicator not implemented: %d\n", + sensor_type); + rtas_st(rets, 0, RTAS_OUT_NOT_SUPPORTED); +} + +static void rtas_get_sensor_state(PowerPCCPU *cpu, sPAPREnvironment *spapr, + uint32_t token, uint32_t nargs, + target_ulong args, uint32_t nret, + target_ulong rets) +{ + uint32_t sensor_type; + uint32_t sensor_index; + sPAPRDRConnector *drc; + sPAPRDRConnectorClass *drck; + uint32_t entity_sense; + + if (nargs != 2 || nret != 2) { + rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); + return; + } + + sensor_type = rtas_ld(args, 0); + sensor_index = rtas_ld(args, 1); + + if (sensor_type != RTAS_SENSOR_TYPE_ENTITY_SENSE) { + /* currently only DR-related sensors are implemented */ + DPRINTF("rtas_get_sensor_state: sensor/indicator not implemented: %d\n", + sensor_type); + rtas_st(rets, 0, RTAS_OUT_NOT_SUPPORTED); + return; + } + + drc = spapr_dr_connector_by_index(sensor_index); + if (!drc) { + DPRINTF("rtas_get_sensor_state: invalid sensor/DRC index: %xh\n", + sensor_index); + rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); + return; + } + drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); + entity_sense = drck->entity_sense(drc); + + rtas_st(rets, 0, RTAS_OUT_SUCCESS); + rtas_st(rets, 1, entity_sense); +} + +/* configure-connector work area offsets, int32_t units for field + * indexes, bytes for field offset/len values. + * + * as documented by PAPR+ v2.7, 13.5.3.5 + */ +#define CC_IDX_NODE_NAME_OFFSET 2 +#define CC_IDX_PROP_NAME_OFFSET 2 +#define CC_IDX_PROP_LEN 3 +#define CC_IDX_PROP_DATA_OFFSET 4 +#define CC_VAL_DATA_OFFSET ((CC_IDX_PROP_DATA_OFFSET + 1) * 4) +#define CC_WA_LEN 4096 + +static void rtas_ibm_configure_connector(PowerPCCPU *cpu, + sPAPREnvironment *spapr, + uint32_t token, uint32_t nargs, + target_ulong args, uint32_t nret, + target_ulong rets) +{ + uint64_t wa_addr; + uint64_t wa_offset; + uint32_t drc_index; + sPAPRDRConnector *drc; + sPAPRDRConnectorClass *drck; + sPAPRConfigureConnectorState *ccs; + sPAPRDRCCResponse resp = SPAPR_DR_CC_RESPONSE_CONTINUE; + int rc; + const void *fdt; + + if (nargs != 2 || nret != 1) { + rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); + return; + } + + wa_addr = ((uint64_t)rtas_ld(args, 1) << 32) | rtas_ld(args, 0); + + drc_index = rtas_ld(wa_addr, 0); + drc = spapr_dr_connector_by_index(drc_index); + if (!drc) { + DPRINTF("rtas_ibm_configure_connector: invalid DRC index: %xh\n", + drc_index); + rc = RTAS_OUT_PARAM_ERROR; + goto out; + } + + drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); + fdt = drck->get_fdt(drc, NULL); + + ccs = spapr_ccs_find(spapr, drc_index); + if (!ccs) { + ccs = g_new0(sPAPRConfigureConnectorState, 1); + (void)drck->get_fdt(drc, &ccs->fdt_offset); + ccs->drc_index = drc_index; + spapr_ccs_add(spapr, ccs); + } + + do { + uint32_t tag; + const char *name; + const struct fdt_property *prop; + int fdt_offset_next, prop_len; + + tag = fdt_next_tag(fdt, ccs->fdt_offset, &fdt_offset_next); + + switch (tag) { + case FDT_BEGIN_NODE: + ccs->fdt_depth++; + name = fdt_get_name(fdt, ccs->fdt_offset, NULL); + + /* provide the name of the next OF node */ + wa_offset = CC_VAL_DATA_OFFSET; + rtas_st(wa_addr, CC_IDX_NODE_NAME_OFFSET, wa_offset); + rtas_st_buffer_direct(wa_addr + wa_offset, CC_WA_LEN - wa_offset, + (uint8_t *)name, strlen(name) + 1); + resp = SPAPR_DR_CC_RESPONSE_NEXT_CHILD; + break; + case FDT_END_NODE: + ccs->fdt_depth--; + if (ccs->fdt_depth == 0) { + /* done sending the device tree, don't need to track + * the state anymore + */ + drck->set_configured(drc); + spapr_ccs_remove(spapr, ccs); + ccs = NULL; + resp = SPAPR_DR_CC_RESPONSE_SUCCESS; + } else { + resp = SPAPR_DR_CC_RESPONSE_PREV_PARENT; + } + break; + case FDT_PROP: + prop = fdt_get_property_by_offset(fdt, ccs->fdt_offset, + &prop_len); + name = fdt_string(fdt, fdt32_to_cpu(prop->nameoff)); + + /* provide the name of the next OF property */ + wa_offset = CC_VAL_DATA_OFFSET; + rtas_st(wa_addr, CC_IDX_PROP_NAME_OFFSET, wa_offset); + rtas_st_buffer_direct(wa_addr + wa_offset, CC_WA_LEN - wa_offset, + (uint8_t *)name, strlen(name) + 1); + + /* provide the length and value of the OF property. data gets + * placed immediately after NULL terminator of the OF property's + * name string + */ + wa_offset += strlen(name) + 1, + rtas_st(wa_addr, CC_IDX_PROP_LEN, prop_len); + rtas_st(wa_addr, CC_IDX_PROP_DATA_OFFSET, wa_offset); + rtas_st_buffer_direct(wa_addr + wa_offset, CC_WA_LEN - wa_offset, + (uint8_t *)((struct fdt_property *)prop)->data, + prop_len); + resp = SPAPR_DR_CC_RESPONSE_NEXT_PROPERTY; + break; + case FDT_END: + resp = SPAPR_DR_CC_RESPONSE_ERROR; + default: + /* keep seeking for an actionable tag */ + break; + } + if (ccs) { + ccs->fdt_offset = fdt_offset_next; + } + } while (resp == SPAPR_DR_CC_RESPONSE_CONTINUE); + + rc = resp; +out: + rtas_st(rets, 0, rc); +} + static struct rtas_call { const char *name; spapr_rtas_fn fn; @@ -370,6 +721,16 @@ static void core_rtas_register_types(void) rtas_ibm_set_system_parameter); spapr_rtas_register(RTAS_IBM_OS_TERM, "ibm,os-term", rtas_ibm_os_term); + spapr_rtas_register(RTAS_SET_POWER_LEVEL, "set-power-level", + rtas_set_power_level); + spapr_rtas_register(RTAS_GET_POWER_LEVEL, "get-power-level", + rtas_get_power_level); + spapr_rtas_register(RTAS_SET_INDICATOR, "set-indicator", + rtas_set_indicator); + spapr_rtas_register(RTAS_GET_SENSOR_STATE, "get-sensor-state", + rtas_get_sensor_state); + spapr_rtas_register(RTAS_IBM_CONFIGURE_CONNECTOR, "ibm,configure-connector", + rtas_ibm_configure_connector); } type_init(core_rtas_register_types) diff --git a/hw/ppc/spapr_vio.c b/hw/ppc/spapr_vio.c index 1360b97ab0..174033dd41 100644 --- a/hw/ppc/spapr_vio.c +++ b/hw/ppc/spapr_vio.c @@ -469,7 +469,7 @@ static void spapr_vio_busdev_realize(DeviceState *qdev, Error **errp) } if (pc->rtce_window_size) { - uint32_t liobn = SPAPR_VIO_BASE_LIOBN | dev->reg; + uint32_t liobn = SPAPR_VIO_LIOBN(dev->reg); memory_region_init(&dev->mrroot, OBJECT(dev), "iommu-spapr-root", ram_size); diff --git a/hw/sparc/sun4m.c b/hw/sparc/sun4m.c index a69bf2da45..8a3599c403 100644 --- a/hw/sparc/sun4m.c +++ b/hw/sparc/sun4m.c @@ -897,7 +897,6 @@ static void sun4m_hw_init(const struct sun4m_hwdef *hwdef, espdma_irq, ledma_irq; qemu_irq esp_reset, dma_enable; qemu_irq fdc_tc; - qemu_irq *cpu_halt; unsigned long kernel_size; DriveInfo *fd[MAX_FD]; FWCfgState *fw_cfg; @@ -1024,9 +1023,8 @@ static void sun4m_hw_init(const struct sun4m_hwdef *hwdef, escc_init(hwdef->serial_base, slavio_irq[15], slavio_irq[15], serial_hds[0], serial_hds[1], ESCC_CLOCK, 1); - cpu_halt = qemu_allocate_irqs(cpu_halt_signal, NULL, 1); if (hwdef->apc_base) { - apc_init(hwdef->apc_base, cpu_halt[0]); + apc_init(hwdef->apc_base, qemu_allocate_irq(cpu_halt_signal, NULL, 0)); } if (hwdef->fd_base) { @@ -1036,7 +1034,7 @@ static void sun4m_hw_init(const struct sun4m_hwdef *hwdef, sun4m_fdctrl_init(slavio_irq[22], hwdef->fd_base, fd, &fdc_tc); } else { - fdc_tc = *qemu_allocate_irqs(dummy_fdc_tc, NULL, 1); + fdc_tc = qemu_allocate_irq(dummy_fdc_tc, NULL, 0); } slavio_misc_init(hwdef->slavio_base, hwdef->aux1_base, hwdef->aux2_base, diff --git a/hw/timer/arm_timer.c b/hw/timer/arm_timer.c index 145291016b..d53f39ad62 100644 --- a/hw/timer/arm_timer.c +++ b/hw/timer/arm_timer.c @@ -280,14 +280,12 @@ static int sp804_init(SysBusDevice *sbd) { DeviceState *dev = DEVICE(sbd); SP804State *s = SP804(dev); - qemu_irq *qi; - qi = qemu_allocate_irqs(sp804_set_irq, s, 2); sysbus_init_irq(sbd, &s->irq); s->timer[0] = arm_timer_init(s->freq0); s->timer[1] = arm_timer_init(s->freq1); - s->timer[0]->irq = qi[0]; - s->timer[1]->irq = qi[1]; + s->timer[0]->irq = qemu_allocate_irq(sp804_set_irq, s, 0); + s->timer[1]->irq = qemu_allocate_irq(sp804_set_irq, s, 1); memory_region_init_io(&s->iomem, OBJECT(s), &sp804_ops, s, "sp804", 0x1000); sysbus_init_mmio(sbd, &s->iomem); diff --git a/hw/unicore32/puv3.c b/hw/unicore32/puv3.c index cc9a21a712..703e29d6d3 100644 --- a/hw/unicore32/puv3.c +++ b/hw/unicore32/puv3.c @@ -40,15 +40,15 @@ static void puv3_intc_cpu_handler(void *opaque, int irq, int level) static void puv3_soc_init(CPUUniCore32State *env) { - qemu_irq *cpu_intc, irqs[PUV3_IRQS_NR]; + qemu_irq cpu_intc, irqs[PUV3_IRQS_NR]; DeviceState *dev; MemoryRegion *i8042 = g_new(MemoryRegion, 1); int i; /* Initialize interrupt controller */ - cpu_intc = qemu_allocate_irqs(puv3_intc_cpu_handler, - uc32_env_get_cpu(env), 1); - dev = sysbus_create_simple("puv3_intc", PUV3_INTC_BASE, *cpu_intc); + cpu_intc = qemu_allocate_irq(puv3_intc_cpu_handler, + uc32_env_get_cpu(env), 0); + dev = sysbus_create_simple("puv3_intc", PUV3_INTC_BASE, cpu_intc); for (i = 0; i < PUV3_IRQS_NR; i++) { irqs[i] = qdev_get_gpio_in(dev, i); } diff --git a/hw/xen/xen_pt.c b/hw/xen/xen_pt.c index d095c081cc..9afcda8e21 100644 --- a/hw/xen/xen_pt.c +++ b/hw/xen/xen_pt.c @@ -234,11 +234,12 @@ static void xen_pt_pci_write_config(PCIDevice *d, uint32_t addr, int index = 0; XenPTRegGroup *reg_grp_entry = NULL; int rc = 0; - uint32_t read_val = 0; + uint32_t read_val = 0, wb_mask; int emul_len = 0; XenPTReg *reg_entry = NULL; uint32_t find_addr = addr; XenPTRegInfo *reg = NULL; + bool wp_flag = false; if (xen_pt_pci_config_access_check(d, addr, len)) { return; @@ -271,10 +272,17 @@ static void xen_pt_pci_write_config(PCIDevice *d, uint32_t addr, if (rc < 0) { XEN_PT_ERR(d, "pci_read_block failed. return value: %d.\n", rc); memset(&read_val, 0xff, len); + wb_mask = 0; + } else { + wb_mask = 0xFFFFFFFF >> ((4 - len) << 3); } /* pass directly to the real device for passthrough type register group */ if (reg_grp_entry == NULL) { + if (!s->permissive) { + wb_mask = 0; + wp_flag = true; + } goto out; } @@ -295,9 +303,17 @@ static void xen_pt_pci_write_config(PCIDevice *d, uint32_t addr, uint32_t real_offset = reg_grp_entry->base_offset + reg->offset; uint32_t valid_mask = 0xFFFFFFFF >> ((4 - emul_len) << 3); uint8_t *ptr_val = NULL; + uint32_t wp_mask = reg->emu_mask | reg->ro_mask; valid_mask <<= (find_addr - real_offset) << 3; ptr_val = (uint8_t *)&val + (real_offset & 3); + if (!s->permissive) { + wp_mask |= reg->res_mask; + } + if (wp_mask == (0xFFFFFFFF >> ((4 - reg->size) << 3))) { + wb_mask &= ~((wp_mask >> ((find_addr - real_offset) << 3)) + << ((len - emul_len) << 3)); + } /* do emulation based on register size */ switch (reg->size) { @@ -339,6 +355,16 @@ static void xen_pt_pci_write_config(PCIDevice *d, uint32_t addr, } else { /* nothing to do with passthrough type register, * continue to find next byte */ + if (!s->permissive) { + wb_mask &= ~(0xff << ((len - emul_len) << 3)); + /* Unused BARs will make it here, but we don't want to issue + * warnings for writes to them (bogus writes get dealt with + * above). + */ + if (index < 0) { + wp_flag = true; + } + } emul_len--; find_addr++; } @@ -350,10 +376,26 @@ static void xen_pt_pci_write_config(PCIDevice *d, uint32_t addr, memory_region_transaction_commit(); out: - if (!(reg && reg->no_wb)) { + if (wp_flag && !s->permissive_warned) { + s->permissive_warned = true; + xen_pt_log(d, "Write-back to unknown field 0x%02x (partially) inhibited (0x%0*x)\n", + addr, len * 2, wb_mask); + xen_pt_log(d, "If the device doesn't work, try enabling permissive mode\n"); + xen_pt_log(d, "(unsafe) and if it helps report the problem to xen-devel\n"); + } + for (index = 0; wb_mask; index += len) { /* unknown regs are passed through */ - rc = xen_host_pci_set_block(&s->real_device, addr, - (uint8_t *)&val, len); + while (!(wb_mask & 0xff)) { + index++; + wb_mask >>= 8; + } + len = 0; + do { + len++; + wb_mask >>= 8; + } while (wb_mask & 0xff); + rc = xen_host_pci_set_block(&s->real_device, addr + index, + (uint8_t *)&val + index, len); if (rc < 0) { XEN_PT_ERR(d, "pci_write_block failed. return value: %d.\n", rc); @@ -807,6 +849,7 @@ static void xen_pt_unregister_device(PCIDevice *d) static Property xen_pci_passthrough_properties[] = { DEFINE_PROP_PCI_HOST_DEVADDR("hostaddr", XenPCIPassthroughState, hostaddr), + DEFINE_PROP_BOOL("permissive", XenPCIPassthroughState, permissive, false), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/xen/xen_pt.h b/hw/xen/xen_pt.h index 942dc60cc7..4bba559763 100644 --- a/hw/xen/xen_pt.h +++ b/hw/xen/xen_pt.h @@ -101,12 +101,12 @@ struct XenPTRegInfo { uint32_t offset; uint32_t size; uint32_t init_val; + /* reg reserved field mask (ON:reserved, OFF:defined) */ + uint32_t res_mask; /* reg read only field mask (ON:RO/ROS, OFF:other) */ uint32_t ro_mask; /* reg emulate field mask (ON:emu, OFF:passthrough) */ uint32_t emu_mask; - /* no write back allowed */ - uint32_t no_wb; xen_pt_conf_reg_init init; /* read/write function pointer * for double_word/word/byte size */ @@ -177,6 +177,7 @@ typedef struct XenPTMSIXEntry { uint32_t data; uint32_t vector_ctrl; bool updated; /* indicate whether MSI ADDR or DATA is updated */ + bool warned; /* avoid issuing (bogus) warning more than once */ } XenPTMSIXEntry; typedef struct XenPTMSIX { uint32_t ctrl_offset; @@ -196,6 +197,8 @@ struct XenPCIPassthroughState { PCIHostDeviceAddress hostaddr; bool is_virtfn; + bool permissive; + bool permissive_warned; XenHostPCIDevice real_device; XenPTRegion bases[PCI_NUM_REGIONS]; /* Access regions */ QLIST_HEAD(, XenPTRegGroup) reg_grps; diff --git a/hw/xen/xen_pt_config_init.c b/hw/xen/xen_pt_config_init.c index 95a51dbbb1..f3cf069b60 100644 --- a/hw/xen/xen_pt_config_init.c +++ b/hw/xen/xen_pt_config_init.c @@ -95,6 +95,18 @@ XenPTReg *xen_pt_find_reg(XenPTRegGroup *reg_grp, uint32_t address) return NULL; } +static uint32_t get_throughable_mask(const XenPCIPassthroughState *s, + const XenPTRegInfo *reg, + uint32_t valid_mask) +{ + uint32_t throughable_mask = ~(reg->emu_mask | reg->ro_mask); + + if (!s->permissive) { + throughable_mask &= ~reg->res_mask; + } + + return throughable_mask & valid_mask; +} /**************** * general register functions @@ -157,14 +169,13 @@ static int xen_pt_byte_reg_write(XenPCIPassthroughState *s, XenPTReg *cfg_entry, { XenPTRegInfo *reg = cfg_entry->reg; uint8_t writable_mask = 0; - uint8_t throughable_mask = 0; + uint8_t throughable_mask = get_throughable_mask(s, reg, valid_mask); /* modify emulate register */ writable_mask = reg->emu_mask & ~reg->ro_mask & valid_mask; cfg_entry->data = XEN_PT_MERGE_VALUE(*val, cfg_entry->data, writable_mask); /* create value for writing to I/O device register */ - throughable_mask = ~reg->emu_mask & valid_mask; *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask); return 0; @@ -175,14 +186,13 @@ static int xen_pt_word_reg_write(XenPCIPassthroughState *s, XenPTReg *cfg_entry, { XenPTRegInfo *reg = cfg_entry->reg; uint16_t writable_mask = 0; - uint16_t throughable_mask = 0; + uint16_t throughable_mask = get_throughable_mask(s, reg, valid_mask); /* modify emulate register */ writable_mask = reg->emu_mask & ~reg->ro_mask & valid_mask; cfg_entry->data = XEN_PT_MERGE_VALUE(*val, cfg_entry->data, writable_mask); /* create value for writing to I/O device register */ - throughable_mask = ~reg->emu_mask & valid_mask; *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask); return 0; @@ -193,14 +203,13 @@ static int xen_pt_long_reg_write(XenPCIPassthroughState *s, XenPTReg *cfg_entry, { XenPTRegInfo *reg = cfg_entry->reg; uint32_t writable_mask = 0; - uint32_t throughable_mask = 0; + uint32_t throughable_mask = get_throughable_mask(s, reg, valid_mask); /* modify emulate register */ writable_mask = reg->emu_mask & ~reg->ro_mask & valid_mask; cfg_entry->data = XEN_PT_MERGE_VALUE(*val, cfg_entry->data, writable_mask); /* create value for writing to I/O device register */ - throughable_mask = ~reg->emu_mask & valid_mask; *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask); return 0; @@ -292,15 +301,13 @@ static int xen_pt_cmd_reg_write(XenPCIPassthroughState *s, XenPTReg *cfg_entry, { XenPTRegInfo *reg = cfg_entry->reg; uint16_t writable_mask = 0; - uint16_t throughable_mask = 0; + uint16_t throughable_mask = get_throughable_mask(s, reg, valid_mask); /* modify emulate register */ writable_mask = ~reg->ro_mask & valid_mask; cfg_entry->data = XEN_PT_MERGE_VALUE(*val, cfg_entry->data, writable_mask); /* create value for writing to I/O device register */ - throughable_mask = ~reg->emu_mask & valid_mask; - if (*val & PCI_COMMAND_INTX_DISABLE) { throughable_mask |= PCI_COMMAND_INTX_DISABLE; } else { @@ -454,7 +461,6 @@ static int xen_pt_bar_reg_write(XenPCIPassthroughState *s, XenPTReg *cfg_entry, PCIDevice *d = &s->dev; const PCIIORegion *r; uint32_t writable_mask = 0; - uint32_t throughable_mask = 0; uint32_t bar_emu_mask = 0; uint32_t bar_ro_mask = 0; uint32_t r_size = 0; @@ -511,8 +517,7 @@ static int xen_pt_bar_reg_write(XenPCIPassthroughState *s, XenPTReg *cfg_entry, } /* create value for writing to I/O device register */ - throughable_mask = ~bar_emu_mask & valid_mask; - *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask); + *val = XEN_PT_MERGE_VALUE(*val, dev_value, 0); return 0; } @@ -526,9 +531,8 @@ static int xen_pt_exp_rom_bar_reg_write(XenPCIPassthroughState *s, XenPTRegion *base = NULL; PCIDevice *d = (PCIDevice *)&s->dev; uint32_t writable_mask = 0; - uint32_t throughable_mask = 0; + uint32_t throughable_mask = get_throughable_mask(s, reg, valid_mask); pcibus_t r_size = 0; - uint32_t bar_emu_mask = 0; uint32_t bar_ro_mask = 0; r_size = d->io_regions[PCI_ROM_SLOT].size; @@ -537,7 +541,6 @@ static int xen_pt_exp_rom_bar_reg_write(XenPCIPassthroughState *s, r_size = xen_pt_get_emul_size(base->bar_flag, r_size); /* set emulate mask and read-only mask */ - bar_emu_mask = reg->emu_mask; bar_ro_mask = (reg->ro_mask | (r_size - 1)) & ~PCI_ROM_ADDRESS_ENABLE; /* modify emulate register */ @@ -545,7 +548,6 @@ static int xen_pt_exp_rom_bar_reg_write(XenPCIPassthroughState *s, cfg_entry->data = XEN_PT_MERGE_VALUE(*val, cfg_entry->data, writable_mask); /* create value for writing to I/O device register */ - throughable_mask = ~bar_emu_mask & valid_mask; *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask); return 0; @@ -580,7 +582,7 @@ static XenPTRegInfo xen_pt_emu_reg_header0[] = { .offset = PCI_COMMAND, .size = 2, .init_val = 0x0000, - .ro_mask = 0xF880, + .res_mask = 0xF880, .emu_mask = 0x0743, .init = xen_pt_common_reg_init, .u.w.read = xen_pt_word_reg_read, @@ -605,7 +607,8 @@ static XenPTRegInfo xen_pt_emu_reg_header0[] = { .offset = PCI_STATUS, .size = 2, .init_val = 0x0000, - .ro_mask = 0x06FF, + .res_mask = 0x0007, + .ro_mask = 0x06F8, .emu_mask = 0x0010, .init = xen_pt_status_reg_init, .u.w.read = xen_pt_word_reg_read, @@ -755,6 +758,15 @@ static XenPTRegInfo xen_pt_emu_reg_vpd[] = { .u.b.write = xen_pt_byte_reg_write, }, { + .offset = PCI_VPD_ADDR, + .size = 2, + .ro_mask = 0x0003, + .emu_mask = 0x0003, + .init = xen_pt_common_reg_init, + .u.w.read = xen_pt_word_reg_read, + .u.w.write = xen_pt_word_reg_write, + }, + { .size = 0, }, }; @@ -873,7 +885,7 @@ static XenPTRegInfo xen_pt_emu_reg_pcie[] = { .offset = PCI_EXP_DEVCAP, .size = 4, .init_val = 0x00000000, - .ro_mask = 0x1FFCFFFF, + .ro_mask = 0xFFFFFFFF, .emu_mask = 0x10000000, .init = xen_pt_common_reg_init, .u.dw.read = xen_pt_long_reg_read, @@ -890,6 +902,16 @@ static XenPTRegInfo xen_pt_emu_reg_pcie[] = { .u.w.read = xen_pt_word_reg_read, .u.w.write = xen_pt_word_reg_write, }, + /* Device Status reg */ + { + .offset = PCI_EXP_DEVSTA, + .size = 2, + .res_mask = 0xFFC0, + .ro_mask = 0x0030, + .init = xen_pt_common_reg_init, + .u.w.read = xen_pt_word_reg_read, + .u.w.write = xen_pt_word_reg_write, + }, /* Link Control reg */ { .offset = PCI_EXP_LNKCTL, @@ -901,6 +923,15 @@ static XenPTRegInfo xen_pt_emu_reg_pcie[] = { .u.w.read = xen_pt_word_reg_read, .u.w.write = xen_pt_word_reg_write, }, + /* Link Status reg */ + { + .offset = PCI_EXP_LNKSTA, + .size = 2, + .ro_mask = 0x3FFF, + .init = xen_pt_common_reg_init, + .u.w.read = xen_pt_word_reg_read, + .u.w.write = xen_pt_word_reg_write, + }, /* Device Control 2 reg */ { .offset = 0x28, @@ -933,39 +964,22 @@ static XenPTRegInfo xen_pt_emu_reg_pcie[] = { * Power Management Capability */ -/* read Power Management Control/Status register */ -static int xen_pt_pmcsr_reg_read(XenPCIPassthroughState *s, XenPTReg *cfg_entry, - uint16_t *value, uint16_t valid_mask) -{ - XenPTRegInfo *reg = cfg_entry->reg; - uint16_t valid_emu_mask = reg->emu_mask; - - valid_emu_mask |= PCI_PM_CTRL_STATE_MASK | PCI_PM_CTRL_NO_SOFT_RESET; - - valid_emu_mask = valid_emu_mask & valid_mask; - *value = XEN_PT_MERGE_VALUE(*value, cfg_entry->data, ~valid_emu_mask); - - return 0; -} /* write Power Management Control/Status register */ static int xen_pt_pmcsr_reg_write(XenPCIPassthroughState *s, XenPTReg *cfg_entry, uint16_t *val, uint16_t dev_value, uint16_t valid_mask) { XenPTRegInfo *reg = cfg_entry->reg; - uint16_t emu_mask = reg->emu_mask; uint16_t writable_mask = 0; - uint16_t throughable_mask = 0; - - emu_mask |= PCI_PM_CTRL_STATE_MASK | PCI_PM_CTRL_NO_SOFT_RESET; + uint16_t throughable_mask = get_throughable_mask(s, reg, valid_mask); /* modify emulate register */ - writable_mask = emu_mask & ~reg->ro_mask & valid_mask; + writable_mask = reg->emu_mask & ~reg->ro_mask & valid_mask; cfg_entry->data = XEN_PT_MERGE_VALUE(*val, cfg_entry->data, writable_mask); /* create value for writing to I/O device register */ - throughable_mask = ~emu_mask & valid_mask; - *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask); + *val = XEN_PT_MERGE_VALUE(*val, dev_value & ~PCI_PM_CTRL_PME_STATUS, + throughable_mask); return 0; } @@ -999,10 +1013,11 @@ static XenPTRegInfo xen_pt_emu_reg_pm[] = { .offset = PCI_PM_CTRL, .size = 2, .init_val = 0x0008, - .ro_mask = 0xE1FC, - .emu_mask = 0x8100, + .res_mask = 0x00F0, + .ro_mask = 0xE10C, + .emu_mask = 0x810B, .init = xen_pt_common_reg_init, - .u.w.read = xen_pt_pmcsr_reg_read, + .u.w.read = xen_pt_word_reg_read, .u.w.write = xen_pt_pmcsr_reg_write, }, { @@ -1016,13 +1031,9 @@ static XenPTRegInfo xen_pt_emu_reg_pm[] = { */ /* Helper */ -static bool xen_pt_msgdata_check_type(uint32_t offset, uint16_t flags) -{ - /* check the offset whether matches the type or not */ - bool is_32 = (offset == PCI_MSI_DATA_32) && !(flags & PCI_MSI_FLAGS_64BIT); - bool is_64 = (offset == PCI_MSI_DATA_64) && (flags & PCI_MSI_FLAGS_64BIT); - return is_32 || is_64; -} +#define xen_pt_msi_check_type(offset, flags, what) \ + ((offset) == ((flags) & PCI_MSI_FLAGS_64BIT ? \ + PCI_MSI_##what##_64 : PCI_MSI_##what##_32)) /* Message Control register */ static int xen_pt_msgctrl_reg_init(XenPCIPassthroughState *s, @@ -1056,8 +1067,7 @@ static int xen_pt_msgctrl_reg_write(XenPCIPassthroughState *s, XenPTRegInfo *reg = cfg_entry->reg; XenPTMSI *msi = s->msi; uint16_t writable_mask = 0; - uint16_t throughable_mask = 0; - uint16_t raw_val; + uint16_t throughable_mask = get_throughable_mask(s, reg, valid_mask); /* Currently no support for multi-vector */ if (*val & PCI_MSI_FLAGS_QSIZE) { @@ -1070,12 +1080,10 @@ static int xen_pt_msgctrl_reg_write(XenPCIPassthroughState *s, msi->flags |= cfg_entry->data & ~PCI_MSI_FLAGS_ENABLE; /* create value for writing to I/O device register */ - raw_val = *val; - throughable_mask = ~reg->emu_mask & valid_mask; *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask); /* update MSI */ - if (raw_val & PCI_MSI_FLAGS_ENABLE) { + if (*val & PCI_MSI_FLAGS_ENABLE) { /* setup MSI pirq for the first time */ if (!msi->initialized) { /* Init physical one */ @@ -1103,10 +1111,6 @@ static int xen_pt_msgctrl_reg_write(XenPCIPassthroughState *s, xen_pt_msi_disable(s); } - /* pass through MSI_ENABLE bit */ - *val &= ~PCI_MSI_FLAGS_ENABLE; - *val |= raw_val & PCI_MSI_FLAGS_ENABLE; - return 0; } @@ -1134,7 +1138,45 @@ static int xen_pt_msgdata_reg_init(XenPCIPassthroughState *s, uint32_t offset = reg->offset; /* check the offset whether matches the type or not */ - if (xen_pt_msgdata_check_type(offset, flags)) { + if (xen_pt_msi_check_type(offset, flags, DATA)) { + *data = reg->init_val; + } else { + *data = XEN_PT_INVALID_REG; + } + return 0; +} + +/* this function will be called twice (for 32 bit and 64 bit type) */ +/* initialize Mask register */ +static int xen_pt_mask_reg_init(XenPCIPassthroughState *s, + XenPTRegInfo *reg, uint32_t real_offset, + uint32_t *data) +{ + uint32_t flags = s->msi->flags; + + /* check the offset whether matches the type or not */ + if (!(flags & PCI_MSI_FLAGS_MASKBIT)) { + *data = XEN_PT_INVALID_REG; + } else if (xen_pt_msi_check_type(reg->offset, flags, MASK)) { + *data = reg->init_val; + } else { + *data = XEN_PT_INVALID_REG; + } + return 0; +} + +/* this function will be called twice (for 32 bit and 64 bit type) */ +/* initialize Pending register */ +static int xen_pt_pending_reg_init(XenPCIPassthroughState *s, + XenPTRegInfo *reg, uint32_t real_offset, + uint32_t *data) +{ + uint32_t flags = s->msi->flags; + + /* check the offset whether matches the type or not */ + if (!(flags & PCI_MSI_FLAGS_MASKBIT)) { + *data = XEN_PT_INVALID_REG; + } else if (xen_pt_msi_check_type(reg->offset, flags, PENDING)) { *data = reg->init_val; } else { *data = XEN_PT_INVALID_REG; @@ -1149,7 +1191,6 @@ static int xen_pt_msgaddr32_reg_write(XenPCIPassthroughState *s, { XenPTRegInfo *reg = cfg_entry->reg; uint32_t writable_mask = 0; - uint32_t throughable_mask = 0; uint32_t old_addr = cfg_entry->data; /* modify emulate register */ @@ -1158,8 +1199,7 @@ static int xen_pt_msgaddr32_reg_write(XenPCIPassthroughState *s, s->msi->addr_lo = cfg_entry->data; /* create value for writing to I/O device register */ - throughable_mask = ~reg->emu_mask & valid_mask; - *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask); + *val = XEN_PT_MERGE_VALUE(*val, dev_value, 0); /* update MSI */ if (cfg_entry->data != old_addr) { @@ -1177,7 +1217,6 @@ static int xen_pt_msgaddr64_reg_write(XenPCIPassthroughState *s, { XenPTRegInfo *reg = cfg_entry->reg; uint32_t writable_mask = 0; - uint32_t throughable_mask = 0; uint32_t old_addr = cfg_entry->data; /* check whether the type is 64 bit or not */ @@ -1194,8 +1233,7 @@ static int xen_pt_msgaddr64_reg_write(XenPCIPassthroughState *s, s->msi->addr_hi = cfg_entry->data; /* create value for writing to I/O device register */ - throughable_mask = ~reg->emu_mask & valid_mask; - *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask); + *val = XEN_PT_MERGE_VALUE(*val, dev_value, 0); /* update MSI */ if (cfg_entry->data != old_addr) { @@ -1217,12 +1255,11 @@ static int xen_pt_msgdata_reg_write(XenPCIPassthroughState *s, XenPTRegInfo *reg = cfg_entry->reg; XenPTMSI *msi = s->msi; uint16_t writable_mask = 0; - uint16_t throughable_mask = 0; uint16_t old_data = cfg_entry->data; uint32_t offset = reg->offset; /* check the offset whether matches the type or not */ - if (!xen_pt_msgdata_check_type(offset, msi->flags)) { + if (!xen_pt_msi_check_type(offset, msi->flags, DATA)) { /* exit I/O emulator */ XEN_PT_ERR(&s->dev, "the offset does not match the 32/64 bit type!\n"); return -1; @@ -1235,8 +1272,7 @@ static int xen_pt_msgdata_reg_write(XenPCIPassthroughState *s, msi->data = cfg_entry->data; /* create value for writing to I/O device register */ - throughable_mask = ~reg->emu_mask & valid_mask; - *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask); + *val = XEN_PT_MERGE_VALUE(*val, dev_value, 0); /* update MSI */ if (cfg_entry->data != old_data) { @@ -1266,8 +1302,9 @@ static XenPTRegInfo xen_pt_emu_reg_msi[] = { .offset = PCI_MSI_FLAGS, .size = 2, .init_val = 0x0000, - .ro_mask = 0xFF8E, - .emu_mask = 0x007F, + .res_mask = 0xFE00, + .ro_mask = 0x018E, + .emu_mask = 0x017E, .init = xen_pt_msgctrl_reg_init, .u.w.read = xen_pt_word_reg_read, .u.w.write = xen_pt_msgctrl_reg_write, @@ -1279,7 +1316,6 @@ static XenPTRegInfo xen_pt_emu_reg_msi[] = { .init_val = 0x00000000, .ro_mask = 0x00000003, .emu_mask = 0xFFFFFFFF, - .no_wb = 1, .init = xen_pt_common_reg_init, .u.dw.read = xen_pt_long_reg_read, .u.dw.write = xen_pt_msgaddr32_reg_write, @@ -1291,7 +1327,6 @@ static XenPTRegInfo xen_pt_emu_reg_msi[] = { .init_val = 0x00000000, .ro_mask = 0x00000000, .emu_mask = 0xFFFFFFFF, - .no_wb = 1, .init = xen_pt_msgaddr64_reg_init, .u.dw.read = xen_pt_long_reg_read, .u.dw.write = xen_pt_msgaddr64_reg_write, @@ -1303,7 +1338,6 @@ static XenPTRegInfo xen_pt_emu_reg_msi[] = { .init_val = 0x0000, .ro_mask = 0x0000, .emu_mask = 0xFFFF, - .no_wb = 1, .init = xen_pt_msgdata_reg_init, .u.w.read = xen_pt_word_reg_read, .u.w.write = xen_pt_msgdata_reg_write, @@ -1315,11 +1349,54 @@ static XenPTRegInfo xen_pt_emu_reg_msi[] = { .init_val = 0x0000, .ro_mask = 0x0000, .emu_mask = 0xFFFF, - .no_wb = 1, .init = xen_pt_msgdata_reg_init, .u.w.read = xen_pt_word_reg_read, .u.w.write = xen_pt_msgdata_reg_write, }, + /* Mask reg (if PCI_MSI_FLAGS_MASKBIT set, for 32-bit devices) */ + { + .offset = PCI_MSI_MASK_32, + .size = 4, + .init_val = 0x00000000, + .ro_mask = 0xFFFFFFFF, + .emu_mask = 0xFFFFFFFF, + .init = xen_pt_mask_reg_init, + .u.dw.read = xen_pt_long_reg_read, + .u.dw.write = xen_pt_long_reg_write, + }, + /* Mask reg (if PCI_MSI_FLAGS_MASKBIT set, for 64-bit devices) */ + { + .offset = PCI_MSI_MASK_64, + .size = 4, + .init_val = 0x00000000, + .ro_mask = 0xFFFFFFFF, + .emu_mask = 0xFFFFFFFF, + .init = xen_pt_mask_reg_init, + .u.dw.read = xen_pt_long_reg_read, + .u.dw.write = xen_pt_long_reg_write, + }, + /* Pending reg (if PCI_MSI_FLAGS_MASKBIT set, for 32-bit devices) */ + { + .offset = PCI_MSI_MASK_32 + 4, + .size = 4, + .init_val = 0x00000000, + .ro_mask = 0xFFFFFFFF, + .emu_mask = 0x00000000, + .init = xen_pt_pending_reg_init, + .u.dw.read = xen_pt_long_reg_read, + .u.dw.write = xen_pt_long_reg_write, + }, + /* Pending reg (if PCI_MSI_FLAGS_MASKBIT set, for 64-bit devices) */ + { + .offset = PCI_MSI_MASK_64 + 4, + .size = 4, + .init_val = 0x00000000, + .ro_mask = 0xFFFFFFFF, + .emu_mask = 0x00000000, + .init = xen_pt_pending_reg_init, + .u.dw.read = xen_pt_long_reg_read, + .u.dw.write = xen_pt_long_reg_write, + }, { .size = 0, }, @@ -1358,7 +1435,7 @@ static int xen_pt_msixctrl_reg_write(XenPCIPassthroughState *s, { XenPTRegInfo *reg = cfg_entry->reg; uint16_t writable_mask = 0; - uint16_t throughable_mask = 0; + uint16_t throughable_mask = get_throughable_mask(s, reg, valid_mask); int debug_msix_enabled_old; /* modify emulate register */ @@ -1366,7 +1443,6 @@ static int xen_pt_msixctrl_reg_write(XenPCIPassthroughState *s, cfg_entry->data = XEN_PT_MERGE_VALUE(*val, cfg_entry->data, writable_mask); /* create value for writing to I/O device register */ - throughable_mask = ~reg->emu_mask & valid_mask; *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask); /* update MSI-X */ @@ -1405,7 +1481,8 @@ static XenPTRegInfo xen_pt_emu_reg_msix[] = { .offset = PCI_MSI_FLAGS, .size = 2, .init_val = 0x0000, - .ro_mask = 0x3FFF, + .res_mask = 0x3800, + .ro_mask = 0x07FF, .emu_mask = 0x0000, .init = xen_pt_msixctrl_reg_init, .u.w.read = xen_pt_word_reg_read, diff --git a/hw/xen/xen_pt_msi.c b/hw/xen/xen_pt_msi.c index 9ed9321c9f..68db6233dc 100644 --- a/hw/xen/xen_pt_msi.c +++ b/hw/xen/xen_pt_msi.c @@ -434,11 +434,10 @@ static void pci_msix_write(void *opaque, hwaddr addr, XenPCIPassthroughState *s = opaque; XenPTMSIX *msix = s->msix; XenPTMSIXEntry *entry; - int entry_nr, offset; + unsigned int entry_nr, offset; entry_nr = addr / PCI_MSIX_ENTRY_SIZE; - if (entry_nr < 0 || entry_nr >= msix->total_entries) { - XEN_PT_ERR(&s->dev, "asked MSI-X entry '%i' invalid!\n", entry_nr); + if (entry_nr >= msix->total_entries) { return; } entry = &msix->msix_entry[entry_nr]; @@ -460,8 +459,11 @@ static void pci_msix_write(void *opaque, hwaddr addr, + PCI_MSIX_ENTRY_VECTOR_CTRL; if (msix->enabled && !(*vec_ctrl & PCI_MSIX_ENTRY_CTRL_MASKBIT)) { - XEN_PT_ERR(&s->dev, "Can't update msix entry %d since MSI-X is" - " already enabled.\n", entry_nr); + if (!entry->warned) { + entry->warned = true; + XEN_PT_ERR(&s->dev, "Can't update msix entry %d since MSI-X is" + " already enabled.\n", entry_nr); + } return; } |