diff options
109 files changed, 5893 insertions, 2331 deletions
diff --git a/.travis.yml b/.travis.yml index 93fd0164a0..87d9fa971c 100644 --- a/.travis.yml +++ b/.travis.yml @@ -175,12 +175,14 @@ matrix: # Python builds - env: - CONFIG="--target-list=x86_64-softmmu" + language: python python: - - "3.0" + - "3.4" - env: - CONFIG="--target-list=x86_64-softmmu" + language: python python: - "3.6" diff --git a/block/sheepdog.c b/block/sheepdog.c index 90ab43baa4..ed14f7afbe 100644 --- a/block/sheepdog.c +++ b/block/sheepdog.c @@ -1224,7 +1224,7 @@ static int find_vdi_name(BDRVSheepdogState *s, const char *filename, SheepdogVdiReq hdr; SheepdogVdiRsp *rsp = (SheepdogVdiRsp *)&hdr; unsigned int wlen, rlen = 0; - char buf[SD_MAX_VDI_LEN + SD_MAX_VDI_TAG_LEN]; + char buf[SD_MAX_VDI_LEN + SD_MAX_VDI_TAG_LEN] QEMU_NONSTRING; fd = connect_to_sdog(s, errp); if (fd < 0) { @@ -1797,6 +1797,9 @@ if ! $python -c 'import sys; sys.exit(sys.version_info < (2,7))'; then "Use --python=/path/to/python to specify a supported Python." fi +# Preserve python version since some functionality is dependent on it +python_version=$($python -V 2>&1 | sed -e 's/Python\ //') + # Suppress writing compiled files python="$python -B" @@ -5889,8 +5892,12 @@ if test "$cpu" = "ppc64" -a "$targetos" != "Darwin" ; then roms="$roms spapr-rtas" fi +# Only build s390-ccw bios if we're on s390x and the compiler has -march=z900 if test "$cpu" = "s390x" ; then - roms="$roms s390-ccw" + write_c_skeleton + if compile_prog "-march=z900" ""; then + roms="$roms s390-ccw" + fi fi # Probe for the need for relocating the user-only binary. @@ -6010,7 +6017,7 @@ echo "LDFLAGS $LDFLAGS" echo "QEMU_LDFLAGS $QEMU_LDFLAGS" echo "make $make" echo "install $install" -echo "python $python" +echo "python $python ($python_version)" if test "$slirp" = "yes" ; then echo "smbd $smbd" fi @@ -6959,6 +6966,7 @@ echo "INSTALL_DATA=$install -c -m 0644" >> $config_host_mak echo "INSTALL_PROG=$install -c -m 0755" >> $config_host_mak echo "INSTALL_LIB=$install -c -m 0644" >> $config_host_mak echo "PYTHON=$python" >> $config_host_mak +echo "PYTHON_VERSION=$python_version" >> $config_host_mak echo "CC=$cc" >> $config_host_mak if $iasl -h > /dev/null 2>&1; then echo "IASL=$iasl" >> $config_host_mak diff --git a/default-configs/virtio.mak b/default-configs/virtio.mak index 1304849018..ecb4420e74 100644 --- a/default-configs/virtio.mak +++ b/default-configs/virtio.mak @@ -1,7 +1,7 @@ CONFIG_VHOST_USER_SCSI=$(call land,$(CONFIG_VHOST_USER),$(CONFIG_LINUX)) CONFIG_VHOST_USER_BLK=$(call land,$(CONFIG_VHOST_USER),$(CONFIG_LINUX)) CONFIG_VIRTIO=y -CONFIG_VIRTIO_9P=y +CONFIG_VIRTIO_9P=$(CONFIG_VIRTFS) CONFIG_VIRTIO_BALLOON=y CONFIG_VIRTIO_BLK=y CONFIG_VIRTIO_CRYPTO=y @@ -12,3 +12,4 @@ CONFIG_VIRTIO_RNG=y CONFIG_SCSI=y CONFIG_VIRTIO_SCSI=y CONFIG_VIRTIO_SERIAL=y +CONFIG_VIRTIO_INPUT_HOST=$(CONFIG_LINUX) diff --git a/docs/devel/migration.rst b/docs/devel/migration.rst index e7658ab050..220059679a 100644 --- a/docs/devel/migration.rst +++ b/docs/devel/migration.rst @@ -419,8 +419,13 @@ The functions to do that are inside a vmstate definition, and are called: This function is called before we save the state of one device. -Example: You can look at hpet.c, that uses the three function to -massage the state that is transferred. +- ``int (*post_save)(void *opaque);`` + + This function is called after we save the state of one device + (even upon failure, unless the call to pre_save returned an error). + +Example: You can look at hpet.c, that uses the first three functions +to massage the state that is transferred. The ``VMSTATE_WITH_TMP`` macro may be useful when the migration data doesn't match the stored device data well; it allows an diff --git a/docs/specs/ivshmem-spec.txt b/docs/specs/ivshmem-spec.txt index a1f5499796..042f7eae22 100644 --- a/docs/specs/ivshmem-spec.txt +++ b/docs/specs/ivshmem-spec.txt @@ -17,12 +17,16 @@ get interrupted by its peers. There are two basic configurations: -- Just shared memory: -device ivshmem-plain,memdev=HMB,... +- Just shared memory: + + -device ivshmem-plain,memdev=HMB,... This uses host memory backend HMB. It should have option "share" set. -- Shared memory plus interrupts: -device ivshmem,chardev=CHR,vectors=N,... +- Shared memory plus interrupts: + + -device ivshmem-doorbell,chardev=CHR,vectors=N,... An ivshmem server must already be running on the host. The device connects to the server's UNIX domain socket via character device diff --git a/docs/specs/tpm.txt b/docs/specs/tpm.txt index 1af82bba86..5d8c26b1ad 100644 --- a/docs/specs/tpm.txt +++ b/docs/specs/tpm.txt @@ -34,6 +34,25 @@ The CRB interface makes a memory mapped IO region in the area 0xfed40000 - QEMU files related to TPM CRB interface: - hw/tpm/tpm_crb.c += fw_cfg interface = + +The bios/firmware may read the "etc/tpm/config" fw_cfg entry for +configuring the guest appropriately. + +The entry of 6 bytes has the following content, in little-endian: + + #define TPM_VERSION_UNSPEC 0 + #define TPM_VERSION_1_2 1 + #define TPM_VERSION_2_0 2 + + #define TPM_PPI_VERSION_NONE 0 + #define TPM_PPI_VERSION_1_30 1 + + struct FwCfgTPMConfig { + uint32_t tpmppi_address; /* PPI memory location */ + uint8_t tpm_version; /* TPM version */ + uint8_t tpmppi_version; /* PPI version */ + }; = ACPI Interface = @@ -57,6 +76,91 @@ URL: https://trustedcomputinggroup.org/tcg-acpi-specification/ +== ACPI PPI Interface == + +QEMU supports the Physical Presence Interface (PPI) for TPM 1.2 and TPM 2. This +interface requires ACPI and firmware support. The specification can be found at +the following URL: + +https://trustedcomputinggroup.org/resource/tcg-physical-presence-interface-specification/ + +PPI enables a system administrator (root) to request a modification to the +TPM upon reboot. The PPI specification defines the operation requests and the +actions the firmware has to take. The system administrator passes the operation +request number to the firmware through an ACPI interface which writes this +number to a memory location that the firmware knows. Upon reboot, the firmware +finds the number and sends commands to the the TPM. The firmware writes the TPM +result code and the operation request number to a memory location that ACPI can +read from and pass the result on to the administrator. + +The PPI specification defines a set of mandatory and optional operations for +the firmware to implement. The ACPI interface also allows an administrator to +list the supported operations. In QEMU the ACPI code is generated by QEMU, yet +the firmware needs to implement support on a per-operations basis, and +different firmwares may support a different subset. Therefore, QEMU introduces +the virtual memory device for PPI where the firmware can indicate which +operations it supports and ACPI can enable the ones that are supported and +disable all others. This interface lies in main memory and has the following +layout: + + +----------+--------+--------+-------------------------------------------+ + | Field | Length | Offset | Description | + +----------+--------+--------+-------------------------------------------+ + | func | 0x100 | 0x000 | Firmware sets values for each supported | + | | | | operation. See defined values below. | + +----------+--------+--------+-------------------------------------------+ + | ppin | 0x1 | 0x100 | SMI interrupt to use. Set by firmware. | + | | | | Not supported. | + +----------+--------+--------+-------------------------------------------+ + | ppip | 0x4 | 0x101 | ACPI function index to pass to SMM code. | + | | | | Set by ACPI. Not supported. | + +----------+--------+--------+-------------------------------------------+ + | pprp | 0x4 | 0x105 | Result of last executed operation. Set by | + | | | | firmware. See function index 5 for values.| + +----------+--------+--------+-------------------------------------------+ + | pprq | 0x4 | 0x109 | Operation request number to execute. See | + | | | | 'Physical Presence Interface Operation | + | | | | Summary' tables in specs. Set by ACPI. | + +----------+--------+--------+-------------------------------------------+ + | pprm | 0x4 | 0x10d | Operation request optional parameter. | + | | | | Values depend on operation. Set by ACPI. | + +----------+--------+--------+-------------------------------------------+ + | lppr | 0x4 | 0x111 | Last executed operation request number. | + | | | | Copied from pprq field by firmware. | + +----------+--------+--------+-------------------------------------------+ + | fret | 0x4 | 0x115 | Result code from SMM function. | + | | | | Not supported. | + +----------+--------+--------+-------------------------------------------+ + | res1 | 0x40 | 0x119 | Reserved for future use | + +----------+--------+--------+-------------------------------------------+ + | next_step| 0x1 | 0x159 | Operation to execute after reboot by | + | | | | firmware. Used by firmware. | + +----------+--------+--------+-------------------------------------------+ + | movv | 0x1 | 0x15a | Memory overwrite variable | + +----------+--------+--------+-------------------------------------------+ + + The following values are supported for the 'func' field. They correspond + to the values used by ACPI function index 8. + + +----------+-------------------------------------------------------------+ + | value | Description | + +----------+-------------------------------------------------------------+ + | 0 | Operation is not implemented. | + +----------+-------------------------------------------------------------+ + | 1 | Operation is only accessible through firmware. | + +----------+-------------------------------------------------------------+ + | 2 | Operation is blocked for OS by firmware configuration. | + +----------+-------------------------------------------------------------+ + | 3 | Operation is allowed and physically present user required. | + +----------+-------------------------------------------------------------+ + | 4 | Operation is allowed and physically present user is not | + | | required. | + +----------+-------------------------------------------------------------+ + +The location of the table is given by the fw_cfg tpmppi_address field. +The PPI memory region size is 0x400 (TPM_PPI_ADDR_SIZE) to leave +enough room for future updates. + QEMU files related to TPM ACPI tables: - hw/i386/acpi-build.c diff --git a/hw/acpi/Makefile.objs b/hw/acpi/Makefile.objs index 11c35bcb44..2d46e3789a 100644 --- a/hw/acpi/Makefile.objs +++ b/hw/acpi/Makefile.objs @@ -11,6 +11,7 @@ common-obj-$(call lnot,$(CONFIG_ACPI_X86)) += acpi-stub.o common-obj-y += acpi_interface.o common-obj-y += bios-linker-loader.o common-obj-y += aml-build.o +common-obj-$(CONFIG_TPM) += tpm.o common-obj-$(CONFIG_IPMI) += ipmi.o common-obj-$(call lnot,$(CONFIG_IPMI)) += ipmi-stub.o diff --git a/hw/acpi/core.c b/hw/acpi/core.c index d6f0709691..47877c0ec1 100644 --- a/hw/acpi/core.c +++ b/hw/acpi/core.c @@ -35,14 +35,18 @@ struct acpi_table_header { uint16_t _length; /* our length, not actual part of the hdr */ /* allows easier parsing for fw_cfg clients */ - char sig[4]; /* ACPI signature (4 ASCII characters) */ + char sig[4] + QEMU_NONSTRING; /* ACPI signature (4 ASCII characters) */ uint32_t length; /* Length of table, in bytes, including header */ uint8_t revision; /* ACPI Specification minor version # */ uint8_t checksum; /* To make sum of entire table == 0 */ - char oem_id[6]; /* OEM identification */ - char oem_table_id[8]; /* OEM table identification */ + char oem_id[6] + QEMU_NONSTRING; /* OEM identification */ + char oem_table_id[8] + QEMU_NONSTRING; /* OEM table identification */ uint32_t oem_revision; /* OEM revision number */ - char asl_compiler_id[4]; /* ASL compiler vendor ID */ + char asl_compiler_id[4] + QEMU_NONSTRING; /* ASL compiler vendor ID */ uint32_t asl_compiler_revision; /* ASL compiler revision number */ } QEMU_PACKED; diff --git a/hw/acpi/memory_hotplug.c b/hw/acpi/memory_hotplug.c index 8c7c1013f3..921cad2c5e 100644 --- a/hw/acpi/memory_hotplug.c +++ b/hw/acpi/memory_hotplug.c @@ -686,15 +686,15 @@ void build_memory_hotplug_aml(Aml *table, uint32_t nr_mem, method = aml_method("_OST", 3, AML_NOTSERIALIZED); s = MEMORY_SLOT_OST_METHOD; - aml_append(method, aml_return(aml_call4( - s, aml_name("_UID"), aml_arg(0), aml_arg(1), aml_arg(2) - ))); + aml_append(method, + aml_call4(s, aml_name("_UID"), aml_arg(0), + aml_arg(1), aml_arg(2))); aml_append(dev, method); method = aml_method("_EJ0", 1, AML_NOTSERIALIZED); s = MEMORY_SLOT_EJECT_METHOD; - aml_append(method, aml_return(aml_call2( - s, aml_name("_UID"), aml_arg(0)))); + aml_append(method, + aml_call2(s, aml_name("_UID"), aml_arg(0))); aml_append(dev, method); aml_append(dev_container, dev); diff --git a/hw/acpi/tpm.c b/hw/acpi/tpm.c new file mode 100644 index 0000000000..b96459e45b --- /dev/null +++ b/hw/acpi/tpm.c @@ -0,0 +1,459 @@ +/* Support for generating ACPI TPM tables + * + * Copyright (C) 2018 IBM, Corp. + * Copyright (C) 2018 Red Hat Inc + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + + * You should have received a copy of the GNU General Public License along + * with this program; if not, see <http://www.gnu.org/licenses/>. + */ +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "hw/acpi/tpm.h" + +void tpm_build_ppi_acpi(TPMIf *tpm, Aml *dev) +{ + Aml *method, *field, *ifctx, *ifctx2, *ifctx3, *func_mask, + *not_implemented, *pak, *tpm2, *tpm3, *pprm, *pprq, *zero, *one; + + if (!object_property_get_bool(OBJECT(tpm), "ppi", &error_abort)) { + return; + } + + zero = aml_int(0); + one = aml_int(1); + func_mask = aml_int(TPM_PPI_FUNC_MASK); + not_implemented = aml_int(TPM_PPI_FUNC_NOT_IMPLEMENTED); + + /* + * TPP2 is for the registers that ACPI code used to pass + * the PPI code and parameter (PPRQ, PPRM) to the firmware. + */ + aml_append(dev, + aml_operation_region("TPP2", AML_SYSTEM_MEMORY, + aml_int(TPM_PPI_ADDR_BASE + 0x100), + 0x5A)); + field = aml_field("TPP2", AML_ANY_ACC, AML_NOLOCK, AML_PRESERVE); + aml_append(field, aml_named_field("PPIN", 8)); + aml_append(field, aml_named_field("PPIP", 32)); + aml_append(field, aml_named_field("PPRP", 32)); + aml_append(field, aml_named_field("PPRQ", 32)); + aml_append(field, aml_named_field("PPRM", 32)); + aml_append(field, aml_named_field("LPPR", 32)); + aml_append(dev, field); + pprq = aml_name("PPRQ"); + pprm = aml_name("PPRM"); + + aml_append(dev, + aml_operation_region( + "TPP3", AML_SYSTEM_MEMORY, + aml_int(TPM_PPI_ADDR_BASE + + 0x15a /* movv, docs/specs/tpm.txt */), + 0x1)); + field = aml_field("TPP3", AML_BYTE_ACC, AML_NOLOCK, AML_PRESERVE); + aml_append(field, aml_named_field("MOVV", 8)); + aml_append(dev, field); + + /* + * DerefOf in Windows is broken with SYSTEM_MEMORY. Use a dynamic + * operation region inside of a method for getting FUNC[op]. + */ + method = aml_method("TPFN", 1, AML_SERIALIZED); + { + Aml *op = aml_arg(0); + ifctx = aml_if(aml_lgreater_equal(op, aml_int(0x100))); + { + aml_append(ifctx, aml_return(zero)); + } + aml_append(method, ifctx); + + aml_append(method, + aml_operation_region("TPP1", AML_SYSTEM_MEMORY, + aml_add(aml_int(TPM_PPI_ADDR_BASE), op, NULL), 0x1)); + field = aml_field("TPP1", AML_BYTE_ACC, AML_NOLOCK, AML_PRESERVE); + aml_append(field, aml_named_field("TPPF", 8)); + aml_append(method, field); + aml_append(method, aml_return(aml_name("TPPF"))); + } + aml_append(dev, method); + + /* + * Use global TPM2 & TPM3 variables to workaround Windows ACPI bug + * when returning packages. + */ + pak = aml_package(2); + aml_append(pak, zero); + aml_append(pak, zero); + aml_append(dev, aml_name_decl("TPM2", pak)); + tpm2 = aml_name("TPM2"); + + pak = aml_package(3); + aml_append(pak, zero); + aml_append(pak, zero); + aml_append(pak, zero); + aml_append(dev, aml_name_decl("TPM3", pak)); + tpm3 = aml_name("TPM3"); + + method = aml_method("_DSM", 4, AML_SERIALIZED); + { + uint8_t zerobyte[1] = { 0 }; + Aml *function, *arguments, *rev, *op, *op_arg, *op_flags, *uuid; + + uuid = aml_arg(0); + rev = aml_arg(1); + function = aml_arg(2); + arguments = aml_arg(3); + op = aml_local(0); + op_flags = aml_local(1); + + /* Physical Presence Interface */ + ifctx = aml_if( + aml_equal(uuid, + aml_touuid("3DDDFAA6-361B-4EB4-A424-8D10089D1653"))); + { + /* standard DSM query function */ + ifctx2 = aml_if(aml_equal(function, zero)); + { + uint8_t byte_list[2] = { 0xff, 0x01 }; /* functions 1-8 */ + + aml_append(ifctx2, + aml_return(aml_buffer(sizeof(byte_list), + byte_list))); + } + aml_append(ifctx, ifctx2); + + /* + * PPI 1.0: 2.1.1 Get Physical Presence Interface Version + * + * Arg 2 (Integer): Function Index = 1 + * Arg 3 (Package): Arguments = Empty Package + * Returns: Type: String + */ + ifctx2 = aml_if(aml_equal(function, one)); + { + aml_append(ifctx2, aml_return(aml_string("1.3"))); + } + aml_append(ifctx, ifctx2); + + /* + * PPI 1.0: 2.1.3 Submit TPM Operation Request to Pre-OS Environment + * + * Arg 2 (Integer): Function Index = 2 + * Arg 3 (Package): Arguments = Package: Type: Integer + * Operation Value of the Request + * Returns: Type: Integer + * 0: Success + * 1: Operation Value of the Request Not Supported + * 2: General Failure + */ + ifctx2 = aml_if(aml_equal(function, aml_int(2))); + { + /* get opcode */ + aml_append(ifctx2, + aml_store(aml_derefof(aml_index(arguments, + zero)), op)); + + /* get opcode flags */ + aml_append(ifctx2, + aml_store(aml_call1("TPFN", op), op_flags)); + + /* if func[opcode] & TPM_PPI_FUNC_NOT_IMPLEMENTED */ + ifctx3 = aml_if( + aml_equal( + aml_and(op_flags, func_mask, NULL), + not_implemented)); + { + /* 1: Operation Value of the Request Not Supported */ + aml_append(ifctx3, aml_return(one)); + } + aml_append(ifctx2, ifctx3); + + aml_append(ifctx2, aml_store(op, pprq)); + aml_append(ifctx2, aml_store(zero, pprm)); + /* 0: success */ + aml_append(ifctx2, aml_return(zero)); + } + aml_append(ifctx, ifctx2); + + /* + * PPI 1.0: 2.1.4 Get Pending TPM Operation Requested By the OS + * + * Arg 2 (Integer): Function Index = 3 + * Arg 3 (Package): Arguments = Empty Package + * Returns: Type: Package of Integers + * Integer 1: Function Return code + * 0: Success + * 1: General Failure + * Integer 2: Pending operation requested by the OS + * 0: None + * >0: Operation Value of the Pending Request + * Integer 3: Optional argument to pending operation + * requested by the OS + * 0: None + * >0: Argument Value of the Pending Request + */ + ifctx2 = aml_if(aml_equal(function, aml_int(3))); + { + /* + * Revision ID of 1, no integer parameter beyond + * parameter two are expected + */ + ifctx3 = aml_if(aml_equal(rev, one)); + { + /* TPM2[1] = PPRQ */ + aml_append(ifctx3, + aml_store(pprq, aml_index(tpm2, one))); + aml_append(ifctx3, aml_return(tpm2)); + } + aml_append(ifctx2, ifctx3); + + /* + * A return value of {0, 23, 1} indicates that + * operation 23 with argument 1 is pending. + */ + ifctx3 = aml_if(aml_equal(rev, aml_int(2))); + { + /* TPM3[1] = PPRQ */ + aml_append(ifctx3, + aml_store(pprq, aml_index(tpm3, one))); + /* TPM3[2] = PPRM */ + aml_append(ifctx3, + aml_store(pprm, aml_index(tpm3, aml_int(2)))); + aml_append(ifctx3, aml_return(tpm3)); + } + aml_append(ifctx2, ifctx3); + } + aml_append(ifctx, ifctx2); + + /* + * PPI 1.0: 2.1.5 Get Platform-Specific Action to Transition to + * Pre-OS Environment + * + * Arg 2 (Integer): Function Index = 4 + * Arg 3 (Package): Arguments = Empty Package + * Returns: Type: Integer + * 0: None + * 1: Shutdown + * 2: Reboot + * 3: OS Vendor-specific + */ + ifctx2 = aml_if(aml_equal(function, aml_int(4))); + { + /* reboot */ + aml_append(ifctx2, aml_return(aml_int(2))); + } + aml_append(ifctx, ifctx2); + + /* + * PPI 1.0: 2.1.6 Return TPM Operation Response to OS Environment + * + * Arg 2 (Integer): Function Index = 5 + * Arg 3 (Package): Arguments = Empty Package + * Returns: Type: Package of Integer + * Integer 1: Function Return code + * 0: Success + * 1: General Failure + * Integer 2: Most recent operation request + * 0: None + * >0: Operation Value of the most recent request + * Integer 3: Response to the most recent operation request + * 0: Success + * 0x00000001..0x00000FFF: Corresponding TPM + * error code + * 0xFFFFFFF0: User Abort or timeout of dialog + * 0xFFFFFFF1: firmware Failure + */ + ifctx2 = aml_if(aml_equal(function, aml_int(5))); + { + /* TPM3[1] = LPPR */ + aml_append(ifctx2, + aml_store(aml_name("LPPR"), + aml_index(tpm3, one))); + /* TPM3[2] = PPRP */ + aml_append(ifctx2, + aml_store(aml_name("PPRP"), + aml_index(tpm3, aml_int(2)))); + aml_append(ifctx2, aml_return(tpm3)); + } + aml_append(ifctx, ifctx2); + + /* + * PPI 1.0: 2.1.7 Submit preferred user language + * + * Arg 2 (Integer): Function Index = 6 + * Arg 3 (Package): Arguments = String Package + * Preferred language code + * Returns: Type: Integer + * Function Return Code + * 3: Not implemented + */ + ifctx2 = aml_if(aml_equal(function, aml_int(6))); + { + /* 3 = not implemented */ + aml_append(ifctx2, aml_return(aml_int(3))); + } + aml_append(ifctx, ifctx2); + + /* + * PPI 1.1: 2.1.7 Submit TPM Operation Request to + * Pre-OS Environment 2 + * + * Arg 2 (Integer): Function Index = 7 + * Arg 3 (Package): Arguments = Package: Type: Integer + * Integer 1: Operation Value of the Request + * Integer 2: Argument for Operation (optional) + * Returns: Type: Integer + * 0: Success + * 1: Not Implemented + * 2: General Failure + * 3: Operation blocked by current firmware settings + */ + ifctx2 = aml_if(aml_equal(function, aml_int(7))); + { + /* get opcode */ + aml_append(ifctx2, aml_store(aml_derefof(aml_index(arguments, + zero)), + op)); + + /* get opcode flags */ + aml_append(ifctx2, aml_store(aml_call1("TPFN", op), + op_flags)); + /* if func[opcode] & TPM_PPI_FUNC_NOT_IMPLEMENTED */ + ifctx3 = aml_if( + aml_equal( + aml_and(op_flags, func_mask, NULL), + not_implemented)); + { + /* 1: not implemented */ + aml_append(ifctx3, aml_return(one)); + } + aml_append(ifctx2, ifctx3); + + /* if func[opcode] & TPM_PPI_FUNC_BLOCKED */ + ifctx3 = aml_if( + aml_equal( + aml_and(op_flags, func_mask, NULL), + aml_int(TPM_PPI_FUNC_BLOCKED))); + { + /* 3: blocked by firmware */ + aml_append(ifctx3, aml_return(aml_int(3))); + } + aml_append(ifctx2, ifctx3); + + /* revision to integer */ + ifctx3 = aml_if(aml_equal(rev, one)); + { + /* revision 1 */ + /* PPRQ = op */ + aml_append(ifctx3, aml_store(op, pprq)); + /* no argument, PPRM = 0 */ + aml_append(ifctx3, aml_store(zero, pprm)); + } + aml_append(ifctx2, ifctx3); + + ifctx3 = aml_if(aml_equal(rev, aml_int(2))); + { + /* revision 2 */ + /* PPRQ = op */ + op_arg = aml_derefof(aml_index(arguments, one)); + aml_append(ifctx3, aml_store(op, pprq)); + /* PPRM = arg3[1] */ + aml_append(ifctx3, aml_store(op_arg, pprm)); + } + aml_append(ifctx2, ifctx3); + /* 0: success */ + aml_append(ifctx2, aml_return(zero)); + } + aml_append(ifctx, ifctx2); + + /* + * PPI 1.1: 2.1.8 Get User Confirmation Status for Operation + * + * Arg 2 (Integer): Function Index = 8 + * Arg 3 (Package): Arguments = Package: Type: Integer + * Operation Value that may need user confirmation + * Returns: Type: Integer + * 0: Not implemented + * 1: Firmware only + * 2: Blocked for OS by firmware configuration + * 3: Allowed and physically present user required + * 4: Allowed and physically present user not required + */ + ifctx2 = aml_if(aml_equal(function, aml_int(8))); + { + /* get opcode */ + aml_append(ifctx2, + aml_store(aml_derefof(aml_index(arguments, + zero)), + op)); + + /* get opcode flags */ + aml_append(ifctx2, aml_store(aml_call1("TPFN", op), + op_flags)); + /* return confirmation status code */ + aml_append(ifctx2, + aml_return( + aml_and(op_flags, func_mask, NULL))); + } + aml_append(ifctx, ifctx2); + + aml_append(ifctx, aml_return(aml_buffer(1, zerobyte))); + } + aml_append(method, ifctx); + + /* + * "TCG Platform Reset Attack Mitigation Specification 1.00", + * Chapter 6 "ACPI _DSM Function" + */ + ifctx = aml_if( + aml_equal(uuid, + aml_touuid("376054ED-CC13-4675-901C-4756D7F2D45D"))); + { + /* standard DSM query function */ + ifctx2 = aml_if(aml_equal(function, zero)); + { + uint8_t byte_list[1] = { 0x03 }; /* functions 1-2 supported */ + + aml_append(ifctx2, + aml_return(aml_buffer(sizeof(byte_list), + byte_list))); + } + aml_append(ifctx, ifctx2); + + /* + * TCG Platform Reset Attack Mitigation Specification 1.0 Ch.6 + * + * Arg 2 (Integer): Function Index = 1 + * Arg 3 (Package): Arguments = Package: Type: Integer + * Operation Value of the Request + * Returns: Type: Integer + * 0: Success + * 1: General Failure + */ + ifctx2 = aml_if(aml_equal(function, one)); + { + aml_append(ifctx2, + aml_store(aml_derefof(aml_index(arguments, zero)), + op)); + { + aml_append(ifctx2, aml_store(op, aml_name("MOVV"))); + + /* 0: success */ + aml_append(ifctx2, aml_return(zero)); + } + } + aml_append(ifctx, ifctx2); + } + aml_append(method, ifctx); + } + aml_append(dev, method); +} diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index 95fad6f0ce..04b62c714d 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -418,6 +418,7 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) smmu->mapping_count = cpu_to_le32(1); smmu->mapping_offset = cpu_to_le32(sizeof(*smmu)); smmu->base_address = cpu_to_le64(vms->memmap[VIRT_SMMU].base); + smmu->flags = cpu_to_le32(ACPI_IORT_SMMU_V3_COHACC_OVERRIDE); smmu->event_gsiv = cpu_to_le32(irq); smmu->pri_gsiv = cpu_to_le32(irq + 1); smmu->gerr_gsiv = cpu_to_le32(irq + 2); diff --git a/hw/block/vhost-user-blk.c b/hw/block/vhost-user-blk.c index 1451940845..c3af28fad4 100644 --- a/hw/block/vhost-user-blk.c +++ b/hw/block/vhost-user-blk.c @@ -250,6 +250,7 @@ static void vhost_user_blk_device_realize(DeviceState *dev, Error **errp) VirtIODevice *vdev = VIRTIO_DEVICE(dev); VHostUserBlk *s = VHOST_USER_BLK(vdev); VhostUserState *user; + struct vhost_virtqueue *vqs = NULL; int i, ret; if (!s->chardev.chr) { @@ -288,6 +289,7 @@ static void vhost_user_blk_device_realize(DeviceState *dev, Error **errp) s->dev.vqs = g_new(struct vhost_virtqueue, s->dev.nvqs); s->dev.vq_index = 0; s->dev.backend_features = 0; + vqs = s->dev.vqs; vhost_dev_set_config_notifier(&s->dev, &blk_ops); @@ -314,7 +316,7 @@ static void vhost_user_blk_device_realize(DeviceState *dev, Error **errp) vhost_err: vhost_dev_cleanup(&s->dev); virtio_err: - g_free(s->dev.vqs); + g_free(vqs); virtio_cleanup(vdev); vhost_user_cleanup(user); @@ -326,10 +328,11 @@ static void vhost_user_blk_device_unrealize(DeviceState *dev, Error **errp) { VirtIODevice *vdev = VIRTIO_DEVICE(dev); VHostUserBlk *s = VHOST_USER_BLK(dev); + struct vhost_virtqueue *vqs = s->dev.vqs; vhost_user_blk_set_status(vdev, 0); vhost_dev_cleanup(&s->dev); - g_free(s->dev.vqs); + g_free(vqs); virtio_cleanup(vdev); if (s->vhost_user) { diff --git a/hw/block/xen-block.c b/hw/block/xen-block.c index be28b63442..a636487b3e 100644 --- a/hw/block/xen-block.c +++ b/hw/block/xen-block.c @@ -215,7 +215,7 @@ static void xen_block_realize(XenDevice *xendev, Error **errp) xen_device_backend_printf(xendev, "sector-size", "%u", conf->logical_block_size); - xen_device_backend_printf(xendev, "sectors", "%lu", + xen_device_backend_printf(xendev, "sectors", "%"PRIi64, blk_getlength(conf->blk) / conf->logical_block_size); diff --git a/hw/char/stm32f2xx_usart.c b/hw/char/stm32f2xx_usart.c index f3363a2952..10392c70e2 100644 --- a/hw/char/stm32f2xx_usart.c +++ b/hw/char/stm32f2xx_usart.c @@ -53,14 +53,13 @@ static void stm32f2xx_usart_receive(void *opaque, const uint8_t *buf, int size) { STM32F2XXUsartState *s = opaque; - s->usart_dr = *buf; - if (!(s->usart_cr1 & USART_CR1_UE && s->usart_cr1 & USART_CR1_RE)) { /* USART not enabled - drop the chars */ DB_PRINT("Dropping the chars\n"); return; } + s->usart_dr = *buf; s->usart_sr |= USART_SR_RXNE; if (s->usart_cr1 & USART_CR1_RXNEIE) { diff --git a/hw/core/machine.c b/hw/core/machine.c index 95dc7c3913..2629515363 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -28,6 +28,8 @@ GlobalProperty hw_compat_3_1[] = { { "pcie-root-port", "x-width", "1" }, { "memory-backend-file", "x-use-canonical-path-for-ramblock-id", "true" }, { "memory-backend-memfd", "x-use-canonical-path-for-ramblock-id", "true" }, + { "tpm-crb", "ppi", "false" }, + { "tpm-tis", "ppi", "false" }, }; const size_t hw_compat_3_1_len = G_N_ELEMENTS(hw_compat_3_1); @@ -91,8 +93,9 @@ const size_t hw_compat_2_7_len = G_N_ELEMENTS(hw_compat_2_7); GlobalProperty hw_compat_2_6[] = { { "virtio-mmio", "format_transport_address", "off" }, - { "virtio-pci", "disable-modern", "on" }, - { "virtio-pci", "disable-legacy", "off" }, + /* Optional because not all virtio-pci devices support legacy mode */ + { "virtio-pci", "disable-modern", "on", .optional = true }, + { "virtio-pci", "disable-legacy", "off", .optional = true }, }; const size_t hw_compat_2_6_len = G_N_ELEMENTS(hw_compat_2_6); diff --git a/hw/display/virtio-gpu-pci.c b/hw/display/virtio-gpu-pci.c index faf76a8bc4..bdcd33c925 100644 --- a/hw/display/virtio-gpu-pci.c +++ b/hw/display/virtio-gpu-pci.c @@ -19,6 +19,20 @@ #include "hw/virtio/virtio-pci.h" #include "hw/virtio/virtio-gpu.h" +typedef struct VirtIOGPUPCI VirtIOGPUPCI; + +/* + * virtio-gpu-pci: This extends VirtioPCIProxy. + */ +#define TYPE_VIRTIO_GPU_PCI "virtio-gpu-pci" +#define VIRTIO_GPU_PCI(obj) \ + OBJECT_CHECK(VirtIOGPUPCI, (obj), TYPE_VIRTIO_GPU_PCI) + +struct VirtIOGPUPCI { + VirtIOPCIProxy parent_obj; + VirtIOGPU vdev; +}; + static Property virtio_gpu_pci_properties[] = { DEFINE_VIRTIO_GPU_PCI_PROPERTIES(VirtIOPCIProxy), DEFINE_PROP_END_OF_LIST(), diff --git a/hw/display/virtio-vga.c b/hw/display/virtio-vga.c index 8db4d916f2..1e48009b74 100644 --- a/hw/display/virtio-vga.c +++ b/hw/display/virtio-vga.c @@ -3,6 +3,7 @@ #include "hw/pci/pci.h" #include "vga_int.h" #include "hw/virtio/virtio-pci.h" +#include "hw/virtio/virtio-gpu.h" #include "qapi/error.h" /* diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c index 14f757fc36..2e21a31f82 100644 --- a/hw/i386/acpi-build.c +++ b/hw/i386/acpi-build.c @@ -119,6 +119,12 @@ typedef struct AcpiBuildPciBusHotplugState { bool pcihp_bridge_en; } AcpiBuildPciBusHotplugState; +typedef struct FwCfgTPMConfig { + uint32_t tpmppi_address; + uint8_t tpm_version; + uint8_t tpmppi_version; +} QEMU_PACKED FwCfgTPMConfig; + static void init_common_fadt_data(Object *o, AcpiFadtData *data) { uint32_t io = object_property_get_uint(o, ACPI_PM_PROP_PM_IO_BASE, NULL); @@ -1796,6 +1802,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, uint32_t nr_mem = machine->ram_slots; int root_bus_limit = 0xFF; PCIBus *bus = NULL; + TPMIf *tpm = tpm_find(); int i; dsdt = init_aml_allocator(); @@ -2133,7 +2140,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, /* Scan all PCI buses. Generate tables to support hotplug. */ build_append_pci_bus_devices(scope, bus, pm->pcihp_bridge_en); - if (TPM_IS_TIS(tpm_find())) { + if (TPM_IS_TIS(tpm)) { dev = aml_device("ISA.TPM"); aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0C31"))); aml_append(dev, aml_name_decl("_STA", aml_int(0xF))); @@ -2147,6 +2154,9 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, */ /* aml_append(crs, aml_irq_no_flags(TPM_TIS_IRQ)); */ aml_append(dev, aml_name_decl("_CRS", crs)); + + tpm_build_ppi_acpi(tpm, dev); + aml_append(scope, dev); } @@ -2154,7 +2164,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, } } - if (TPM_IS_CRB(tpm_find())) { + if (TPM_IS_CRB(tpm)) { dev = aml_device("TPM"); aml_append(dev, aml_name_decl("_HID", aml_string("MSFT0101"))); crs = aml_resource_template(); @@ -2166,6 +2176,8 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, aml_append(method, aml_return(aml_int(0x0f))); aml_append(dev, method); + tpm_build_ppi_acpi(tpm, dev); + aml_append(sb_scope, dev); } @@ -2847,6 +2859,8 @@ void acpi_setup(void) AcpiBuildTables tables; AcpiBuildState *build_state; Object *vmgenid_dev; + TPMIf *tpm; + static FwCfgTPMConfig tpm_config; if (!pcms->fw_cfg) { ACPI_BUILD_DPRINTF("No fw cfg. Bailing out.\n"); @@ -2881,6 +2895,17 @@ void acpi_setup(void) fw_cfg_add_file(pcms->fw_cfg, ACPI_BUILD_TPMLOG_FILE, tables.tcpalog->data, acpi_data_len(tables.tcpalog)); + tpm = tpm_find(); + if (tpm && object_property_get_bool(OBJECT(tpm), "ppi", &error_abort)) { + tpm_config = (FwCfgTPMConfig) { + .tpmppi_address = cpu_to_le32(TPM_PPI_ADDR_BASE), + .tpm_version = tpm_get_version(tpm), + .tpmppi_version = TPM_PPI_VERSION_1_30 + }; + fw_cfg_add_file(pcms->fw_cfg, "etc/tpm/config", + &tpm_config, sizeof tpm_config); + } + vmgenid_dev = find_vmgenid_dev(); if (vmgenid_dev) { vmgenid_add_fw_cfg(VMGENID(vmgenid_dev), pcms->fw_cfg, diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c index 5088e2f492..63c84e3827 100644 --- a/hw/i386/pc_piix.c +++ b/hw/i386/pc_piix.c @@ -715,7 +715,6 @@ static void pc_i440fx_1_2_machine_options(MachineClass *m) PC_CPU_MODEL_IDS("1.2.0") { "nec-usb-xhci", "msi", "off" }, { "nec-usb-xhci", "msix", "off" }, - { "ivshmem", "use64", "0" }, { "qxl", "revision", "3" }, { "qxl-vga", "revision", "3" }, { "VGA", "mmio", "off" }, diff --git a/hw/misc/edu.c b/hw/misc/edu.c index cdcf550dd7..ceaf688bfb 100644 --- a/hw/misc/edu.c +++ b/hw/misc/edu.c @@ -377,6 +377,7 @@ static void pci_edu_uninit(PCIDevice *pdev) qemu_mutex_destroy(&edu->thr_mutex); timer_del(&edu->dma_timer); + msi_uninit(pdev); } static void edu_obj_uint64(Object *obj, Visitor *v, const char *name, diff --git a/hw/misc/ivshmem.c b/hw/misc/ivshmem.c index 8213659602..c7b6bbc974 100644 --- a/hw/misc/ivshmem.c +++ b/hw/misc/ivshmem.c @@ -112,13 +112,6 @@ typedef struct IVShmemState { /* migration stuff */ OnOffAuto master; Error *migration_blocker; - - /* legacy cruft */ - char *role; - char *shmobj; - char *sizearg; - size_t legacy_size; - uint32_t not_legacy_32bit; } IVShmemState; /* registers for the Inter-VM shared memory device */ @@ -529,17 +522,6 @@ static void process_msg_shmem(IVShmemState *s, int fd, Error **errp) size = buf.st_size; - /* Legacy cruft */ - if (s->legacy_size != SIZE_MAX) { - if (size < s->legacy_size) { - error_setg(errp, "server sent only %zd bytes of shared memory", - (size_t)buf.st_size); - close(fd); - return; - } - size = s->legacy_size; - } - /* mmap the region and map into the BAR2 */ memory_region_init_ram_from_fd(&s->server_bar2, OBJECT(s), "ivshmem.bar2", size, true, fd, &local_err); @@ -882,8 +864,6 @@ static void ivshmem_common_realize(PCIDevice *dev, Error **errp) IVShmemState *s = IVSHMEM_COMMON(dev); Error *err = NULL; uint8_t *pci_conf; - uint8_t attr = PCI_BASE_ADDRESS_SPACE_MEMORY | - PCI_BASE_ADDRESS_MEM_PREFETCH; Error *local_err = NULL; /* IRQFD requires MSI */ @@ -903,10 +883,6 @@ static void ivshmem_common_realize(PCIDevice *dev, Error **errp) pci_register_bar(dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY, &s->ivshmem_mmio); - if (s->not_legacy_32bit) { - attr |= PCI_BASE_ADDRESS_MEM_TYPE_64; - } - if (s->hostmem != NULL) { IVSHMEM_DPRINTF("using hostmem\n"); @@ -964,7 +940,11 @@ static void ivshmem_common_realize(PCIDevice *dev, Error **errp) } vmstate_register_ram(s->ivshmem_bar2, DEVICE(s)); - pci_register_bar(PCI_DEVICE(s), 2, attr, s->ivshmem_bar2); + pci_register_bar(PCI_DEVICE(s), 2, + PCI_BASE_ADDRESS_SPACE_MEMORY | + PCI_BASE_ADDRESS_MEM_PREFETCH | + PCI_BASE_ADDRESS_MEM_TYPE_64, + s->ivshmem_bar2); } static void ivshmem_exit(PCIDevice *dev) @@ -1084,13 +1064,6 @@ static Property ivshmem_plain_properties[] = { DEFINE_PROP_END_OF_LIST(), }; -static void ivshmem_plain_init(Object *obj) -{ - IVShmemState *s = IVSHMEM_PLAIN(obj); - - s->not_legacy_32bit = 1; -} - static void ivshmem_plain_realize(PCIDevice *dev, Error **errp) { IVShmemState *s = IVSHMEM_COMMON(dev); @@ -1122,7 +1095,6 @@ static const TypeInfo ivshmem_plain_info = { .name = TYPE_IVSHMEM_PLAIN, .parent = TYPE_IVSHMEM_COMMON, .instance_size = sizeof(IVShmemState), - .instance_init = ivshmem_plain_init, .class_init = ivshmem_plain_class_init, }; @@ -1155,8 +1127,6 @@ static void ivshmem_doorbell_init(Object *obj) IVShmemState *s = IVSHMEM_DOORBELL(obj); s->features |= (1 << IVSHMEM_MSI); - s->legacy_size = SIZE_MAX; /* whatever the server sends */ - s->not_legacy_32bit = 1; } static void ivshmem_doorbell_realize(PCIDevice *dev, Error **errp) @@ -1189,181 +1159,11 @@ static const TypeInfo ivshmem_doorbell_info = { .class_init = ivshmem_doorbell_class_init, }; -static int ivshmem_load_old(QEMUFile *f, void *opaque, int version_id) -{ - IVShmemState *s = opaque; - PCIDevice *pdev = PCI_DEVICE(s); - int ret; - - IVSHMEM_DPRINTF("ivshmem_load_old\n"); - - if (version_id != 0) { - return -EINVAL; - } - - ret = ivshmem_pre_load(s); - if (ret) { - return ret; - } - - ret = pci_device_load(pdev, f); - if (ret) { - return ret; - } - - if (ivshmem_has_feature(s, IVSHMEM_MSI)) { - msix_load(pdev, f); - ivshmem_msix_vector_use(s); - } else { - s->intrstatus = qemu_get_be32(f); - s->intrmask = qemu_get_be32(f); - } - - return 0; -} - -static bool test_msix(void *opaque, int version_id) -{ - IVShmemState *s = opaque; - - return ivshmem_has_feature(s, IVSHMEM_MSI); -} - -static bool test_no_msix(void *opaque, int version_id) -{ - return !test_msix(opaque, version_id); -} - -static const VMStateDescription ivshmem_vmsd = { - .name = "ivshmem", - .version_id = 1, - .minimum_version_id = 1, - .pre_load = ivshmem_pre_load, - .post_load = ivshmem_post_load, - .fields = (VMStateField[]) { - VMSTATE_PCI_DEVICE(parent_obj, IVShmemState), - - VMSTATE_MSIX_TEST(parent_obj, IVShmemState, test_msix), - VMSTATE_UINT32_TEST(intrstatus, IVShmemState, test_no_msix), - VMSTATE_UINT32_TEST(intrmask, IVShmemState, test_no_msix), - - VMSTATE_END_OF_LIST() - }, - .load_state_old = ivshmem_load_old, - .minimum_version_id_old = 0 -}; - -static Property ivshmem_properties[] = { - DEFINE_PROP_CHR("chardev", IVShmemState, server_chr), - DEFINE_PROP_STRING("size", IVShmemState, sizearg), - DEFINE_PROP_UINT32("vectors", IVShmemState, vectors, 1), - DEFINE_PROP_BIT("ioeventfd", IVShmemState, features, IVSHMEM_IOEVENTFD, - false), - DEFINE_PROP_BIT("msi", IVShmemState, features, IVSHMEM_MSI, true), - DEFINE_PROP_STRING("shm", IVShmemState, shmobj), - DEFINE_PROP_STRING("role", IVShmemState, role), - DEFINE_PROP_UINT32("use64", IVShmemState, not_legacy_32bit, 1), - DEFINE_PROP_END_OF_LIST(), -}; - -static void desugar_shm(IVShmemState *s) -{ - Object *obj; - char *path; - - obj = object_new("memory-backend-file"); - path = g_strdup_printf("/dev/shm/%s", s->shmobj); - object_property_set_str(obj, path, "mem-path", &error_abort); - g_free(path); - object_property_set_int(obj, s->legacy_size, "size", &error_abort); - object_property_set_bool(obj, true, "share", &error_abort); - object_property_add_child(OBJECT(s), "internal-shm-backend", obj, - &error_abort); - object_unref(obj); - user_creatable_complete(USER_CREATABLE(obj), &error_abort); - s->hostmem = MEMORY_BACKEND(obj); -} - -static void ivshmem_realize(PCIDevice *dev, Error **errp) -{ - IVShmemState *s = IVSHMEM_COMMON(dev); - - if (!qtest_enabled()) { - warn_report("ivshmem is deprecated, please use ivshmem-plain" - " or ivshmem-doorbell instead"); - } - - if (qemu_chr_fe_backend_connected(&s->server_chr) + !!s->shmobj != 1) { - error_setg(errp, "You must specify either 'shm' or 'chardev'"); - return; - } - - if (s->sizearg == NULL) { - s->legacy_size = 4 * MiB; /* 4 MB default */ - } else { - int ret; - uint64_t size; - - ret = qemu_strtosz_MiB(s->sizearg, NULL, &size); - if (ret < 0 || (size_t)size != size || !is_power_of_2(size)) { - error_setg(errp, "Invalid size %s", s->sizearg); - return; - } - s->legacy_size = size; - } - - /* check that role is reasonable */ - if (s->role) { - if (strncmp(s->role, "peer", 5) == 0) { - s->master = ON_OFF_AUTO_OFF; - } else if (strncmp(s->role, "master", 7) == 0) { - s->master = ON_OFF_AUTO_ON; - } else { - error_setg(errp, "'role' must be 'peer' or 'master'"); - return; - } - } else { - s->master = ON_OFF_AUTO_AUTO; - } - - if (s->shmobj) { - desugar_shm(s); - } - - /* - * Note: we don't use INTx with IVSHMEM_MSI at all, so this is a - * bald-faced lie then. But it's a backwards compatible lie. - */ - pci_config_set_interrupt_pin(dev->config, 1); - - ivshmem_common_realize(dev, errp); -} - -static void ivshmem_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - PCIDeviceClass *k = PCI_DEVICE_CLASS(klass); - - k->realize = ivshmem_realize; - k->revision = 0; - dc->desc = "Inter-VM shared memory (legacy)"; - dc->props = ivshmem_properties; - dc->vmsd = &ivshmem_vmsd; -} - -static const TypeInfo ivshmem_info = { - .name = TYPE_IVSHMEM, - .parent = TYPE_IVSHMEM_COMMON, - .instance_size = sizeof(IVShmemState), - .class_init = ivshmem_class_init, -}; - static void ivshmem_register_types(void) { type_register_static(&ivshmem_common_info); type_register_static(&ivshmem_plain_info); type_register_static(&ivshmem_doorbell_info); - type_register_static(&ivshmem_info); } type_init(ivshmem_register_types) diff --git a/hw/net/ftgmac100.c b/hw/net/ftgmac100.c index 909c1182ee..790430346b 100644 --- a/hw/net/ftgmac100.c +++ b/hw/net/ftgmac100.c @@ -90,6 +90,18 @@ #define FTGMAC100_PHYDATA_MIIRDATA(x) (((x) >> 16) & 0xffff) /* + * PHY control register - New MDC/MDIO interface + */ +#define FTGMAC100_PHYCR_NEW_DATA(x) (((x) >> 16) & 0xffff) +#define FTGMAC100_PHYCR_NEW_FIRE (1 << 15) +#define FTGMAC100_PHYCR_NEW_ST_22 (1 << 12) +#define FTGMAC100_PHYCR_NEW_OP(x) (((x) >> 10) & 3) +#define FTGMAC100_PHYCR_NEW_OP_WRITE 0x1 +#define FTGMAC100_PHYCR_NEW_OP_READ 0x2 +#define FTGMAC100_PHYCR_NEW_DEV(x) (((x) >> 5) & 0x1f) +#define FTGMAC100_PHYCR_NEW_REG(x) ((x) & 0x1f) + +/* * Feature Register */ #define FTGMAC100_REVR_NEW_MDIO_INTERFACE (1 << 31) @@ -269,9 +281,9 @@ static void phy_reset(FTGMAC100State *s) s->phy_int = 0; } -static uint32_t do_phy_read(FTGMAC100State *s, int reg) +static uint16_t do_phy_read(FTGMAC100State *s, uint8_t reg) { - uint32_t val; + uint16_t val; switch (reg) { case MII_BMCR: /* Basic Control */ @@ -336,7 +348,7 @@ static uint32_t do_phy_read(FTGMAC100State *s, int reg) MII_BMCR_FD | MII_BMCR_CTST) #define MII_ANAR_MASK 0x2d7f -static void do_phy_write(FTGMAC100State *s, int reg, uint32_t val) +static void do_phy_write(FTGMAC100State *s, uint8_t reg, uint16_t val) { switch (reg) { case MII_BMCR: /* Basic Control */ @@ -373,6 +385,55 @@ static void do_phy_write(FTGMAC100State *s, int reg, uint32_t val) } } +static void do_phy_new_ctl(FTGMAC100State *s) +{ + uint8_t reg; + uint16_t data; + + if (!(s->phycr & FTGMAC100_PHYCR_NEW_ST_22)) { + qemu_log_mask(LOG_UNIMP, "%s: unsupported ST code\n", __func__); + return; + } + + /* Nothing to do */ + if (!(s->phycr & FTGMAC100_PHYCR_NEW_FIRE)) { + return; + } + + reg = FTGMAC100_PHYCR_NEW_REG(s->phycr); + data = FTGMAC100_PHYCR_NEW_DATA(s->phycr); + + switch (FTGMAC100_PHYCR_NEW_OP(s->phycr)) { + case FTGMAC100_PHYCR_NEW_OP_WRITE: + do_phy_write(s, reg, data); + break; + case FTGMAC100_PHYCR_NEW_OP_READ: + s->phydata = do_phy_read(s, reg) & 0xffff; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid OP code %08x\n", + __func__, s->phycr); + } + + s->phycr &= ~FTGMAC100_PHYCR_NEW_FIRE; +} + +static void do_phy_ctl(FTGMAC100State *s) +{ + uint8_t reg = FTGMAC100_PHYCR_REG(s->phycr); + + if (s->phycr & FTGMAC100_PHYCR_MIIWR) { + do_phy_write(s, reg, s->phydata & 0xffff); + s->phycr &= ~FTGMAC100_PHYCR_MIIWR; + } else if (s->phycr & FTGMAC100_PHYCR_MIIRD) { + s->phydata = do_phy_read(s, reg) << 16; + s->phycr &= ~FTGMAC100_PHYCR_MIIRD; + } else { + qemu_log_mask(LOG_GUEST_ERROR, "%s: no OP code %08x\n", + __func__, s->phycr); + } +} + static int ftgmac100_read_bd(FTGMAC100Desc *bd, dma_addr_t addr) { if (dma_memory_read(&address_space_memory, addr, bd, sizeof(*bd))) { @@ -628,7 +689,6 @@ static void ftgmac100_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { FTGMAC100State *s = FTGMAC100(opaque); - int reg; switch (addr & 0xff) { case FTGMAC100_ISR: /* Interrupt status */ @@ -711,14 +771,11 @@ static void ftgmac100_write(void *opaque, hwaddr addr, break; case FTGMAC100_PHYCR: /* PHY Device control */ - reg = FTGMAC100_PHYCR_REG(value); s->phycr = value; - if (value & FTGMAC100_PHYCR_MIIWR) { - do_phy_write(s, reg, s->phydata & 0xffff); - s->phycr &= ~FTGMAC100_PHYCR_MIIWR; + if (s->revr & FTGMAC100_REVR_NEW_MDIO_INTERFACE) { + do_phy_new_ctl(s); } else { - s->phydata = do_phy_read(s, reg) << 16; - s->phycr &= ~FTGMAC100_PHYCR_MIIRD; + do_phy_ctl(s); } break; case FTGMAC100_PHYDATA: @@ -728,8 +785,7 @@ static void ftgmac100_write(void *opaque, hwaddr addr, s->dblac = value; break; case FTGMAC100_REVR: /* Feature Register */ - /* TODO: Only Old MDIO interface is supported */ - s->revr = value & ~FTGMAC100_REVR_NEW_MDIO_INTERFACE; + s->revr = value; break; case FTGMAC100_FEAR1: /* Feature Register 1 */ s->fear1 = value; diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index e37fc34839..3f319ef723 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -41,6 +41,47 @@ #define VIRTIO_NET_RX_QUEUE_MIN_SIZE VIRTIO_NET_RX_QUEUE_DEFAULT_SIZE #define VIRTIO_NET_TX_QUEUE_MIN_SIZE VIRTIO_NET_TX_QUEUE_DEFAULT_SIZE +#define VIRTIO_NET_IP4_ADDR_SIZE 8 /* ipv4 saddr + daddr */ + +#define VIRTIO_NET_TCP_FLAG 0x3F +#define VIRTIO_NET_TCP_HDR_LENGTH 0xF000 + +/* IPv4 max payload, 16 bits in the header */ +#define VIRTIO_NET_MAX_IP4_PAYLOAD (65535 - sizeof(struct ip_header)) +#define VIRTIO_NET_MAX_TCP_PAYLOAD 65535 + +/* header length value in ip header without option */ +#define VIRTIO_NET_IP4_HEADER_LENGTH 5 + +#define VIRTIO_NET_IP6_ADDR_SIZE 32 /* ipv6 saddr + daddr */ +#define VIRTIO_NET_MAX_IP6_PAYLOAD VIRTIO_NET_MAX_TCP_PAYLOAD + +/* Purge coalesced packets timer interval, This value affects the performance + a lot, and should be tuned carefully, '300000'(300us) is the recommended + value to pass the WHQL test, '50000' can gain 2x netperf throughput with + tso/gso/gro 'off'. */ +#define VIRTIO_NET_RSC_DEFAULT_INTERVAL 300000 + +/* temporary until standard header include it */ +#if !defined(VIRTIO_NET_HDR_F_RSC_INFO) + +#define VIRTIO_NET_HDR_F_RSC_INFO 4 /* rsc_ext data in csum_ fields */ +#define VIRTIO_NET_F_RSC_EXT 61 + +static inline __virtio16 *virtio_net_rsc_ext_num_packets( + struct virtio_net_hdr *hdr) +{ + return &hdr->csum_start; +} + +static inline __virtio16 *virtio_net_rsc_ext_num_dupacks( + struct virtio_net_hdr *hdr) +{ + return &hdr->csum_offset; +} + +#endif + /* * Calculate the number of bytes up to and including the given 'field' of * 'container'. @@ -628,6 +669,7 @@ static uint64_t virtio_net_get_features(VirtIODevice *vdev, uint64_t features, if (!get_vhost_net(nc->peer)) { return features; } + features = vhost_net_get_features(get_vhost_net(nc->peer), features); vdev->backend_features = features; @@ -701,6 +743,11 @@ static void virtio_net_set_features(VirtIODevice *vdev, uint64_t features) virtio_has_feature(features, VIRTIO_F_VERSION_1)); + n->rsc4_enabled = virtio_has_feature(features, VIRTIO_NET_F_RSC_EXT) && + virtio_has_feature(features, VIRTIO_NET_F_GUEST_TSO4); + n->rsc6_enabled = virtio_has_feature(features, VIRTIO_NET_F_RSC_EXT) && + virtio_has_feature(features, VIRTIO_NET_F_GUEST_TSO6); + if (n->has_vnet_hdr) { n->curr_guest_offloads = virtio_net_guest_offloads_by_features(features); @@ -781,6 +828,12 @@ static int virtio_net_handle_offloads(VirtIONet *n, uint8_t cmd, return VIRTIO_NET_ERR; } + n->rsc4_enabled = virtio_has_feature(offloads, VIRTIO_NET_F_RSC_EXT) && + virtio_has_feature(offloads, VIRTIO_NET_F_GUEST_TSO4); + n->rsc6_enabled = virtio_has_feature(offloads, VIRTIO_NET_F_RSC_EXT) && + virtio_has_feature(offloads, VIRTIO_NET_F_GUEST_TSO6); + virtio_clear_feature(&offloads, VIRTIO_NET_F_RSC_EXT); + supported_offloads = virtio_net_supported_guest_offloads(n); if (offloads & ~supported_offloads) { return VIRTIO_NET_ERR; @@ -1292,7 +1345,7 @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf, return size; } -static ssize_t virtio_net_receive(NetClientState *nc, const uint8_t *buf, +static ssize_t virtio_net_do_receive(NetClientState *nc, const uint8_t *buf, size_t size) { ssize_t r; @@ -1303,6 +1356,612 @@ static ssize_t virtio_net_receive(NetClientState *nc, const uint8_t *buf, return r; } +static void virtio_net_rsc_extract_unit4(VirtioNetRscChain *chain, + const uint8_t *buf, + VirtioNetRscUnit *unit) +{ + uint16_t ip_hdrlen; + struct ip_header *ip; + + ip = (struct ip_header *)(buf + chain->n->guest_hdr_len + + sizeof(struct eth_header)); + unit->ip = (void *)ip; + ip_hdrlen = (ip->ip_ver_len & 0xF) << 2; + unit->ip_plen = &ip->ip_len; + unit->tcp = (struct tcp_header *)(((uint8_t *)unit->ip) + ip_hdrlen); + unit->tcp_hdrlen = (htons(unit->tcp->th_offset_flags) & 0xF000) >> 10; + unit->payload = htons(*unit->ip_plen) - ip_hdrlen - unit->tcp_hdrlen; +} + +static void virtio_net_rsc_extract_unit6(VirtioNetRscChain *chain, + const uint8_t *buf, + VirtioNetRscUnit *unit) +{ + struct ip6_header *ip6; + + ip6 = (struct ip6_header *)(buf + chain->n->guest_hdr_len + + sizeof(struct eth_header)); + unit->ip = ip6; + unit->ip_plen = &(ip6->ip6_ctlun.ip6_un1.ip6_un1_plen); + unit->tcp = (struct tcp_header *)(((uint8_t *)unit->ip)\ + + sizeof(struct ip6_header)); + unit->tcp_hdrlen = (htons(unit->tcp->th_offset_flags) & 0xF000) >> 10; + + /* There is a difference between payload lenght in ipv4 and v6, + ip header is excluded in ipv6 */ + unit->payload = htons(*unit->ip_plen) - unit->tcp_hdrlen; +} + +static size_t virtio_net_rsc_drain_seg(VirtioNetRscChain *chain, + VirtioNetRscSeg *seg) +{ + int ret; + struct virtio_net_hdr *h; + + h = (struct virtio_net_hdr *)seg->buf; + h->flags = 0; + h->gso_type = VIRTIO_NET_HDR_GSO_NONE; + + if (seg->is_coalesced) { + *virtio_net_rsc_ext_num_packets(h) = seg->packets; + *virtio_net_rsc_ext_num_dupacks(h) = seg->dup_ack; + h->flags = VIRTIO_NET_HDR_F_RSC_INFO; + if (chain->proto == ETH_P_IP) { + h->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; + } else { + h->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; + } + } + + ret = virtio_net_do_receive(seg->nc, seg->buf, seg->size); + QTAILQ_REMOVE(&chain->buffers, seg, next); + g_free(seg->buf); + g_free(seg); + + return ret; +} + +static void virtio_net_rsc_purge(void *opq) +{ + VirtioNetRscSeg *seg, *rn; + VirtioNetRscChain *chain = (VirtioNetRscChain *)opq; + + QTAILQ_FOREACH_SAFE(seg, &chain->buffers, next, rn) { + if (virtio_net_rsc_drain_seg(chain, seg) == 0) { + chain->stat.purge_failed++; + continue; + } + } + + chain->stat.timer++; + if (!QTAILQ_EMPTY(&chain->buffers)) { + timer_mod(chain->drain_timer, + qemu_clock_get_ns(QEMU_CLOCK_HOST) + chain->n->rsc_timeout); + } +} + +static void virtio_net_rsc_cleanup(VirtIONet *n) +{ + VirtioNetRscChain *chain, *rn_chain; + VirtioNetRscSeg *seg, *rn_seg; + + QTAILQ_FOREACH_SAFE(chain, &n->rsc_chains, next, rn_chain) { + QTAILQ_FOREACH_SAFE(seg, &chain->buffers, next, rn_seg) { + QTAILQ_REMOVE(&chain->buffers, seg, next); + g_free(seg->buf); + g_free(seg); + } + + timer_del(chain->drain_timer); + timer_free(chain->drain_timer); + QTAILQ_REMOVE(&n->rsc_chains, chain, next); + g_free(chain); + } +} + +static void virtio_net_rsc_cache_buf(VirtioNetRscChain *chain, + NetClientState *nc, + const uint8_t *buf, size_t size) +{ + uint16_t hdr_len; + VirtioNetRscSeg *seg; + + hdr_len = chain->n->guest_hdr_len; + seg = g_malloc(sizeof(VirtioNetRscSeg)); + seg->buf = g_malloc(hdr_len + sizeof(struct eth_header) + + sizeof(struct ip6_header) + VIRTIO_NET_MAX_TCP_PAYLOAD); + memcpy(seg->buf, buf, size); + seg->size = size; + seg->packets = 1; + seg->dup_ack = 0; + seg->is_coalesced = 0; + seg->nc = nc; + + QTAILQ_INSERT_TAIL(&chain->buffers, seg, next); + chain->stat.cache++; + + switch (chain->proto) { + case ETH_P_IP: + virtio_net_rsc_extract_unit4(chain, seg->buf, &seg->unit); + break; + case ETH_P_IPV6: + virtio_net_rsc_extract_unit6(chain, seg->buf, &seg->unit); + break; + default: + g_assert_not_reached(); + } +} + +static int32_t virtio_net_rsc_handle_ack(VirtioNetRscChain *chain, + VirtioNetRscSeg *seg, + const uint8_t *buf, + struct tcp_header *n_tcp, + struct tcp_header *o_tcp) +{ + uint32_t nack, oack; + uint16_t nwin, owin; + + nack = htonl(n_tcp->th_ack); + nwin = htons(n_tcp->th_win); + oack = htonl(o_tcp->th_ack); + owin = htons(o_tcp->th_win); + + if ((nack - oack) >= VIRTIO_NET_MAX_TCP_PAYLOAD) { + chain->stat.ack_out_of_win++; + return RSC_FINAL; + } else if (nack == oack) { + /* duplicated ack or window probe */ + if (nwin == owin) { + /* duplicated ack, add dup ack count due to whql test up to 1 */ + chain->stat.dup_ack++; + return RSC_FINAL; + } else { + /* Coalesce window update */ + o_tcp->th_win = n_tcp->th_win; + chain->stat.win_update++; + return RSC_COALESCE; + } + } else { + /* pure ack, go to 'C', finalize*/ + chain->stat.pure_ack++; + return RSC_FINAL; + } +} + +static int32_t virtio_net_rsc_coalesce_data(VirtioNetRscChain *chain, + VirtioNetRscSeg *seg, + const uint8_t *buf, + VirtioNetRscUnit *n_unit) +{ + void *data; + uint16_t o_ip_len; + uint32_t nseq, oseq; + VirtioNetRscUnit *o_unit; + + o_unit = &seg->unit; + o_ip_len = htons(*o_unit->ip_plen); + nseq = htonl(n_unit->tcp->th_seq); + oseq = htonl(o_unit->tcp->th_seq); + + /* out of order or retransmitted. */ + if ((nseq - oseq) > VIRTIO_NET_MAX_TCP_PAYLOAD) { + chain->stat.data_out_of_win++; + return RSC_FINAL; + } + + data = ((uint8_t *)n_unit->tcp) + n_unit->tcp_hdrlen; + if (nseq == oseq) { + if ((o_unit->payload == 0) && n_unit->payload) { + /* From no payload to payload, normal case, not a dup ack or etc */ + chain->stat.data_after_pure_ack++; + goto coalesce; + } else { + return virtio_net_rsc_handle_ack(chain, seg, buf, + n_unit->tcp, o_unit->tcp); + } + } else if ((nseq - oseq) != o_unit->payload) { + /* Not a consistent packet, out of order */ + chain->stat.data_out_of_order++; + return RSC_FINAL; + } else { +coalesce: + if ((o_ip_len + n_unit->payload) > chain->max_payload) { + chain->stat.over_size++; + return RSC_FINAL; + } + + /* Here comes the right data, the payload length in v4/v6 is different, + so use the field value to update and record the new data len */ + o_unit->payload += n_unit->payload; /* update new data len */ + + /* update field in ip header */ + *o_unit->ip_plen = htons(o_ip_len + n_unit->payload); + + /* Bring 'PUSH' big, the whql test guide says 'PUSH' can be coalesced + for windows guest, while this may change the behavior for linux + guest (only if it uses RSC feature). */ + o_unit->tcp->th_offset_flags = n_unit->tcp->th_offset_flags; + + o_unit->tcp->th_ack = n_unit->tcp->th_ack; + o_unit->tcp->th_win = n_unit->tcp->th_win; + + memmove(seg->buf + seg->size, data, n_unit->payload); + seg->size += n_unit->payload; + seg->packets++; + chain->stat.coalesced++; + return RSC_COALESCE; + } +} + +static int32_t virtio_net_rsc_coalesce4(VirtioNetRscChain *chain, + VirtioNetRscSeg *seg, + const uint8_t *buf, size_t size, + VirtioNetRscUnit *unit) +{ + struct ip_header *ip1, *ip2; + + ip1 = (struct ip_header *)(unit->ip); + ip2 = (struct ip_header *)(seg->unit.ip); + if ((ip1->ip_src ^ ip2->ip_src) || (ip1->ip_dst ^ ip2->ip_dst) + || (unit->tcp->th_sport ^ seg->unit.tcp->th_sport) + || (unit->tcp->th_dport ^ seg->unit.tcp->th_dport)) { + chain->stat.no_match++; + return RSC_NO_MATCH; + } + + return virtio_net_rsc_coalesce_data(chain, seg, buf, unit); +} + +static int32_t virtio_net_rsc_coalesce6(VirtioNetRscChain *chain, + VirtioNetRscSeg *seg, + const uint8_t *buf, size_t size, + VirtioNetRscUnit *unit) +{ + struct ip6_header *ip1, *ip2; + + ip1 = (struct ip6_header *)(unit->ip); + ip2 = (struct ip6_header *)(seg->unit.ip); + if (memcmp(&ip1->ip6_src, &ip2->ip6_src, sizeof(struct in6_address)) + || memcmp(&ip1->ip6_dst, &ip2->ip6_dst, sizeof(struct in6_address)) + || (unit->tcp->th_sport ^ seg->unit.tcp->th_sport) + || (unit->tcp->th_dport ^ seg->unit.tcp->th_dport)) { + chain->stat.no_match++; + return RSC_NO_MATCH; + } + + return virtio_net_rsc_coalesce_data(chain, seg, buf, unit); +} + +/* Packets with 'SYN' should bypass, other flag should be sent after drain + * to prevent out of order */ +static int virtio_net_rsc_tcp_ctrl_check(VirtioNetRscChain *chain, + struct tcp_header *tcp) +{ + uint16_t tcp_hdr; + uint16_t tcp_flag; + + tcp_flag = htons(tcp->th_offset_flags); + tcp_hdr = (tcp_flag & VIRTIO_NET_TCP_HDR_LENGTH) >> 10; + tcp_flag &= VIRTIO_NET_TCP_FLAG; + tcp_flag = htons(tcp->th_offset_flags) & 0x3F; + if (tcp_flag & TH_SYN) { + chain->stat.tcp_syn++; + return RSC_BYPASS; + } + + if (tcp_flag & (TH_FIN | TH_URG | TH_RST | TH_ECE | TH_CWR)) { + chain->stat.tcp_ctrl_drain++; + return RSC_FINAL; + } + + if (tcp_hdr > sizeof(struct tcp_header)) { + chain->stat.tcp_all_opt++; + return RSC_FINAL; + } + + return RSC_CANDIDATE; +} + +static size_t virtio_net_rsc_do_coalesce(VirtioNetRscChain *chain, + NetClientState *nc, + const uint8_t *buf, size_t size, + VirtioNetRscUnit *unit) +{ + int ret; + VirtioNetRscSeg *seg, *nseg; + + if (QTAILQ_EMPTY(&chain->buffers)) { + chain->stat.empty_cache++; + virtio_net_rsc_cache_buf(chain, nc, buf, size); + timer_mod(chain->drain_timer, + qemu_clock_get_ns(QEMU_CLOCK_HOST) + chain->n->rsc_timeout); + return size; + } + + QTAILQ_FOREACH_SAFE(seg, &chain->buffers, next, nseg) { + if (chain->proto == ETH_P_IP) { + ret = virtio_net_rsc_coalesce4(chain, seg, buf, size, unit); + } else { + ret = virtio_net_rsc_coalesce6(chain, seg, buf, size, unit); + } + + if (ret == RSC_FINAL) { + if (virtio_net_rsc_drain_seg(chain, seg) == 0) { + /* Send failed */ + chain->stat.final_failed++; + return 0; + } + + /* Send current packet */ + return virtio_net_do_receive(nc, buf, size); + } else if (ret == RSC_NO_MATCH) { + continue; + } else { + /* Coalesced, mark coalesced flag to tell calc cksum for ipv4 */ + seg->is_coalesced = 1; + return size; + } + } + + chain->stat.no_match_cache++; + virtio_net_rsc_cache_buf(chain, nc, buf, size); + return size; +} + +/* Drain a connection data, this is to avoid out of order segments */ +static size_t virtio_net_rsc_drain_flow(VirtioNetRscChain *chain, + NetClientState *nc, + const uint8_t *buf, size_t size, + uint16_t ip_start, uint16_t ip_size, + uint16_t tcp_port) +{ + VirtioNetRscSeg *seg, *nseg; + uint32_t ppair1, ppair2; + + ppair1 = *(uint32_t *)(buf + tcp_port); + QTAILQ_FOREACH_SAFE(seg, &chain->buffers, next, nseg) { + ppair2 = *(uint32_t *)(seg->buf + tcp_port); + if (memcmp(buf + ip_start, seg->buf + ip_start, ip_size) + || (ppair1 != ppair2)) { + continue; + } + if (virtio_net_rsc_drain_seg(chain, seg) == 0) { + chain->stat.drain_failed++; + } + + break; + } + + return virtio_net_do_receive(nc, buf, size); +} + +static int32_t virtio_net_rsc_sanity_check4(VirtioNetRscChain *chain, + struct ip_header *ip, + const uint8_t *buf, size_t size) +{ + uint16_t ip_len; + + /* Not an ipv4 packet */ + if (((ip->ip_ver_len & 0xF0) >> 4) != IP_HEADER_VERSION_4) { + chain->stat.ip_option++; + return RSC_BYPASS; + } + + /* Don't handle packets with ip option */ + if ((ip->ip_ver_len & 0xF) != VIRTIO_NET_IP4_HEADER_LENGTH) { + chain->stat.ip_option++; + return RSC_BYPASS; + } + + if (ip->ip_p != IPPROTO_TCP) { + chain->stat.bypass_not_tcp++; + return RSC_BYPASS; + } + + /* Don't handle packets with ip fragment */ + if (!(htons(ip->ip_off) & IP_DF)) { + chain->stat.ip_frag++; + return RSC_BYPASS; + } + + /* Don't handle packets with ecn flag */ + if (IPTOS_ECN(ip->ip_tos)) { + chain->stat.ip_ecn++; + return RSC_BYPASS; + } + + ip_len = htons(ip->ip_len); + if (ip_len < (sizeof(struct ip_header) + sizeof(struct tcp_header)) + || ip_len > (size - chain->n->guest_hdr_len - + sizeof(struct eth_header))) { + chain->stat.ip_hacked++; + return RSC_BYPASS; + } + + return RSC_CANDIDATE; +} + +static size_t virtio_net_rsc_receive4(VirtioNetRscChain *chain, + NetClientState *nc, + const uint8_t *buf, size_t size) +{ + int32_t ret; + uint16_t hdr_len; + VirtioNetRscUnit unit; + + hdr_len = ((VirtIONet *)(chain->n))->guest_hdr_len; + + if (size < (hdr_len + sizeof(struct eth_header) + sizeof(struct ip_header) + + sizeof(struct tcp_header))) { + chain->stat.bypass_not_tcp++; + return virtio_net_do_receive(nc, buf, size); + } + + virtio_net_rsc_extract_unit4(chain, buf, &unit); + if (virtio_net_rsc_sanity_check4(chain, unit.ip, buf, size) + != RSC_CANDIDATE) { + return virtio_net_do_receive(nc, buf, size); + } + + ret = virtio_net_rsc_tcp_ctrl_check(chain, unit.tcp); + if (ret == RSC_BYPASS) { + return virtio_net_do_receive(nc, buf, size); + } else if (ret == RSC_FINAL) { + return virtio_net_rsc_drain_flow(chain, nc, buf, size, + ((hdr_len + sizeof(struct eth_header)) + 12), + VIRTIO_NET_IP4_ADDR_SIZE, + hdr_len + sizeof(struct eth_header) + sizeof(struct ip_header)); + } + + return virtio_net_rsc_do_coalesce(chain, nc, buf, size, &unit); +} + +static int32_t virtio_net_rsc_sanity_check6(VirtioNetRscChain *chain, + struct ip6_header *ip6, + const uint8_t *buf, size_t size) +{ + uint16_t ip_len; + + if (((ip6->ip6_ctlun.ip6_un1.ip6_un1_flow & 0xF0) >> 4) + != IP_HEADER_VERSION_6) { + return RSC_BYPASS; + } + + /* Both option and protocol is checked in this */ + if (ip6->ip6_ctlun.ip6_un1.ip6_un1_nxt != IPPROTO_TCP) { + chain->stat.bypass_not_tcp++; + return RSC_BYPASS; + } + + ip_len = htons(ip6->ip6_ctlun.ip6_un1.ip6_un1_plen); + if (ip_len < sizeof(struct tcp_header) || + ip_len > (size - chain->n->guest_hdr_len - sizeof(struct eth_header) + - sizeof(struct ip6_header))) { + chain->stat.ip_hacked++; + return RSC_BYPASS; + } + + /* Don't handle packets with ecn flag */ + if (IP6_ECN(ip6->ip6_ctlun.ip6_un3.ip6_un3_ecn)) { + chain->stat.ip_ecn++; + return RSC_BYPASS; + } + + return RSC_CANDIDATE; +} + +static size_t virtio_net_rsc_receive6(void *opq, NetClientState *nc, + const uint8_t *buf, size_t size) +{ + int32_t ret; + uint16_t hdr_len; + VirtioNetRscChain *chain; + VirtioNetRscUnit unit; + + chain = (VirtioNetRscChain *)opq; + hdr_len = ((VirtIONet *)(chain->n))->guest_hdr_len; + + if (size < (hdr_len + sizeof(struct eth_header) + sizeof(struct ip6_header) + + sizeof(tcp_header))) { + return virtio_net_do_receive(nc, buf, size); + } + + virtio_net_rsc_extract_unit6(chain, buf, &unit); + if (RSC_CANDIDATE != virtio_net_rsc_sanity_check6(chain, + unit.ip, buf, size)) { + return virtio_net_do_receive(nc, buf, size); + } + + ret = virtio_net_rsc_tcp_ctrl_check(chain, unit.tcp); + if (ret == RSC_BYPASS) { + return virtio_net_do_receive(nc, buf, size); + } else if (ret == RSC_FINAL) { + return virtio_net_rsc_drain_flow(chain, nc, buf, size, + ((hdr_len + sizeof(struct eth_header)) + 8), + VIRTIO_NET_IP6_ADDR_SIZE, + hdr_len + sizeof(struct eth_header) + + sizeof(struct ip6_header)); + } + + return virtio_net_rsc_do_coalesce(chain, nc, buf, size, &unit); +} + +static VirtioNetRscChain *virtio_net_rsc_lookup_chain(VirtIONet *n, + NetClientState *nc, + uint16_t proto) +{ + VirtioNetRscChain *chain; + + if ((proto != (uint16_t)ETH_P_IP) && (proto != (uint16_t)ETH_P_IPV6)) { + return NULL; + } + + QTAILQ_FOREACH(chain, &n->rsc_chains, next) { + if (chain->proto == proto) { + return chain; + } + } + + chain = g_malloc(sizeof(*chain)); + chain->n = n; + chain->proto = proto; + if (proto == (uint16_t)ETH_P_IP) { + chain->max_payload = VIRTIO_NET_MAX_IP4_PAYLOAD; + chain->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; + } else { + chain->max_payload = VIRTIO_NET_MAX_IP6_PAYLOAD; + chain->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; + } + chain->drain_timer = timer_new_ns(QEMU_CLOCK_HOST, + virtio_net_rsc_purge, chain); + memset(&chain->stat, 0, sizeof(chain->stat)); + + QTAILQ_INIT(&chain->buffers); + QTAILQ_INSERT_TAIL(&n->rsc_chains, chain, next); + + return chain; +} + +static ssize_t virtio_net_rsc_receive(NetClientState *nc, + const uint8_t *buf, + size_t size) +{ + uint16_t proto; + VirtioNetRscChain *chain; + struct eth_header *eth; + VirtIONet *n; + + n = qemu_get_nic_opaque(nc); + if (size < (n->host_hdr_len + sizeof(struct eth_header))) { + return virtio_net_do_receive(nc, buf, size); + } + + eth = (struct eth_header *)(buf + n->guest_hdr_len); + proto = htons(eth->h_proto); + + chain = virtio_net_rsc_lookup_chain(n, nc, proto); + if (chain) { + chain->stat.received++; + if (proto == (uint16_t)ETH_P_IP && n->rsc4_enabled) { + return virtio_net_rsc_receive4(chain, nc, buf, size); + } else if (proto == (uint16_t)ETH_P_IPV6 && n->rsc6_enabled) { + return virtio_net_rsc_receive6(chain, nc, buf, size); + } + } + return virtio_net_do_receive(nc, buf, size); +} + +static ssize_t virtio_net_receive(NetClientState *nc, const uint8_t *buf, + size_t size) +{ + VirtIONet *n = qemu_get_nic_opaque(nc); + if ((n->rsc4_enabled || n->rsc6_enabled)) { + return virtio_net_rsc_receive(nc, buf, size); + } else { + return virtio_net_do_receive(nc, buf, size); + } +} + static int32_t virtio_net_flush_tx(VirtIONetQueue *q); static void virtio_net_tx_complete(NetClientState *nc, ssize_t len) @@ -2075,6 +2734,7 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp) nc = qemu_get_queue(n->nic); nc->rxfilter_notify_enabled = 1; + QTAILQ_INIT(&n->rsc_chains); n->qdev = dev; } @@ -2104,6 +2764,7 @@ static void virtio_net_device_unrealize(DeviceState *dev, Error **errp) timer_free(n->announce_timer); g_free(n->vqs); qemu_del_nic(n->nic); + virtio_net_rsc_cleanup(n); virtio_cleanup(vdev); } @@ -2184,6 +2845,10 @@ static Property virtio_net_properties[] = { DEFINE_PROP_BIT64("ctrl_guest_offloads", VirtIONet, host_features, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS, true), DEFINE_PROP_BIT64("mq", VirtIONet, host_features, VIRTIO_NET_F_MQ, false), + DEFINE_PROP_BIT64("guest_rsc_ext", VirtIONet, host_features, + VIRTIO_NET_F_RSC_EXT, false), + DEFINE_PROP_UINT32("rsc_interval", VirtIONet, rsc_timeout, + VIRTIO_NET_RSC_DEFAULT_INTERVAL), DEFINE_NIC_PROPERTIES(VirtIONet, nic_conf), DEFINE_PROP_UINT32("x-txtimer", VirtIONet, net_conf.txtimer, TX_TIMER_INTERVAL), diff --git a/hw/pci/msix.c b/hw/pci/msix.c index c7bdbeda9e..4e336416a7 100644 --- a/hw/pci/msix.c +++ b/hw/pci/msix.c @@ -345,7 +345,7 @@ int msix_init_exclusive_bar(PCIDevice *dev, unsigned short nentries, char *name; uint32_t bar_size = 4096; uint32_t bar_pba_offset = bar_size / 2; - uint32_t bar_pba_size = (nentries / 8 + 1) * 8; + uint32_t bar_pba_size = QEMU_ALIGN_UP(nentries, 64) / 8; /* * Migration compatibility dictates that this remains a 4k diff --git a/hw/pci/pcie.c b/hw/pci/pcie.c index 2d3d8a047b..230478faab 100644 --- a/hw/pci/pcie.c +++ b/hw/pci/pcie.c @@ -391,10 +391,10 @@ static void pcie_cap_slot_event(PCIDevice *dev, PCIExpressHotPlugEvent event) } static void pcie_cap_slot_plug_common(PCIDevice *hotplug_dev, DeviceState *dev, - uint8_t **exp_cap, Error **errp) + Error **errp) { - *exp_cap = hotplug_dev->config + hotplug_dev->exp.exp_cap; - uint16_t sltsta = pci_get_word(*exp_cap + PCI_EXP_SLTSTA); + uint8_t *exp_cap = hotplug_dev->config + hotplug_dev->exp.exp_cap; + uint16_t sltsta = pci_get_word(exp_cap + PCI_EXP_SLTSTA); PCIE_DEV_PRINTF(PCI_DEVICE(dev), "hotplug state: 0x%x\n", sltsta); if (sltsta & PCI_EXP_SLTSTA_EIS) { @@ -405,14 +405,19 @@ static void pcie_cap_slot_plug_common(PCIDevice *hotplug_dev, DeviceState *dev, } } +void pcie_cap_slot_pre_plug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, + Error **errp) +{ + pcie_cap_slot_plug_common(PCI_DEVICE(hotplug_dev), dev, errp); +} + void pcie_cap_slot_plug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { - uint8_t *exp_cap; + PCIDevice *hotplug_pdev = PCI_DEVICE(hotplug_dev); + uint8_t *exp_cap = hotplug_pdev->config + hotplug_pdev->exp.exp_cap; PCIDevice *pci_dev = PCI_DEVICE(dev); - pcie_cap_slot_plug_common(PCI_DEVICE(hotplug_dev), dev, &exp_cap, errp); - /* Don't send event when device is enabled during qemu machine creation: * it is present on boot, no hotplug event is necessary. We do send an * event when the device is disabled later. */ @@ -458,11 +463,15 @@ static void pcie_unplug_device(PCIBus *bus, PCIDevice *dev, void *opaque) void pcie_cap_slot_unplug_request_cb(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { - uint8_t *exp_cap; + Error *local_err = NULL; PCIDevice *pci_dev = PCI_DEVICE(dev); PCIBus *bus = pci_get_bus(pci_dev); - pcie_cap_slot_plug_common(PCI_DEVICE(hotplug_dev), dev, &exp_cap, errp); + pcie_cap_slot_plug_common(PCI_DEVICE(hotplug_dev), dev, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } /* In case user cancel the operation of multi-function hot-add, * remove the function that is unexposed to guest individually, diff --git a/hw/pci/pcie_port.c b/hw/pci/pcie_port.c index bc07abc31b..a30291ef54 100644 --- a/hw/pci/pcie_port.c +++ b/hw/pci/pcie_port.c @@ -154,6 +154,7 @@ static void pcie_slot_class_init(ObjectClass *oc, void *data) HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(oc); dc->props = pcie_slot_props; + hc->pre_plug = pcie_cap_slot_pre_plug_cb; hc->plug = pcie_cap_slot_plug_cb; hc->unplug = pcie_cap_slot_unplug_cb; hc->unplug_request = pcie_cap_slot_unplug_request_cb; diff --git a/hw/s390x/s390-pci-bus.c b/hw/s390x/s390-pci-bus.c index 15759b6514..f017c1ded0 100644 --- a/hw/s390x/s390-pci-bus.c +++ b/hw/s390x/s390-pci-bus.c @@ -660,7 +660,7 @@ void s390_pci_iommu_enable(S390PCIIOMMU *iommu) char *name = g_strdup_printf("iommu-s390-%04x", iommu->pbdev->uid); memory_region_init_iommu(&iommu->iommu_mr, sizeof(iommu->iommu_mr), TYPE_S390_IOMMU_MEMORY_REGION, OBJECT(&iommu->mr), - name, iommu->pal + 1); + name, iommu->pal - iommu->pba + 1); iommu->enabled = true; memory_region_add_subregion(&iommu->mr, 0, MEMORY_REGION(&iommu->iommu_mr)); g_free(name); @@ -818,28 +818,43 @@ static bool s390_pci_alloc_idx(S390pciState *s, S390PCIBusDevice *pbdev) } pbdev->idx = idx; - s->next_idx = (idx + 1) & FH_MASK_INDEX; - return true; } +static void s390_pcihost_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev, + Error **errp) +{ + S390pciState *s = S390_PCI_HOST_BRIDGE(hotplug_dev); + + if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) { + PCIDevice *pdev = PCI_DEVICE(dev); + + if (pdev->cap_present & QEMU_PCI_CAP_MULTIFUNCTION) { + error_setg(errp, "multifunction not supported in s390"); + return; + } + } else if (object_dynamic_cast(OBJECT(dev), TYPE_S390_PCI_DEVICE)) { + S390PCIBusDevice *pbdev = S390_PCI_DEVICE(dev); + + if (!s390_pci_alloc_idx(s, pbdev)) { + error_setg(errp, "no slot for plugging zpci device"); + return; + } + } +} + static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { + S390pciState *s = S390_PCI_HOST_BRIDGE(hotplug_dev); PCIDevice *pdev = NULL; S390PCIBusDevice *pbdev = NULL; - S390pciState *s = s390_get_phb(); if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_BRIDGE)) { BusState *bus; PCIBridge *pb = PCI_BRIDGE(dev); PCIDevice *pdev = PCI_DEVICE(dev); - if (pdev->cap_present & QEMU_PCI_CAP_MULTIFUNCTION) { - error_setg(errp, "multifunction not supported in s390"); - return; - } - pci_bridge_map_irq(pb, dev->id, s390_pci_map_irq); pci_setup_iommu(&pb->sec_bus, s390_pci_dma_iommu, s); @@ -859,11 +874,6 @@ static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev, } else if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) { pdev = PCI_DEVICE(dev); - if (pdev->cap_present & QEMU_PCI_CAP_MULTIFUNCTION) { - error_setg(errp, "multifunction not supported in s390"); - return; - } - if (!dev->id) { /* In the case the PCI device does not define an id */ /* we generate one based on the PCI address */ @@ -899,19 +909,19 @@ static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev, } if (dev->hotplugged) { - s390_pci_generate_plug_event(HP_EVENT_RESERVED_TO_STANDBY, + s390_pci_generate_plug_event(HP_EVENT_TO_CONFIGURED , pbdev->fh, pbdev->fid); } } else if (object_dynamic_cast(OBJECT(dev), TYPE_S390_PCI_DEVICE)) { pbdev = S390_PCI_DEVICE(dev); - if (!s390_pci_alloc_idx(s, pbdev)) { - error_setg(errp, "no slot for plugging zpci device"); - return; - } + /* the allocated idx is actually getting used */ + s->next_idx = (pbdev->idx + 1) & FH_MASK_INDEX; pbdev->fh = pbdev->idx; QTAILQ_INSERT_TAIL(&s->zpci_devs, pbdev, link); g_hash_table_insert(s->zpci_table, &pbdev->idx, pbdev); + } else { + g_assert_not_reached(); } } @@ -935,11 +945,11 @@ static void s390_pcihost_timer_cb(void *opaque) static void s390_pcihost_unplug(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { + S390pciState *s = S390_PCI_HOST_BRIDGE(hotplug_dev); PCIDevice *pci_dev = NULL; PCIBus *bus; int32_t devfn; S390PCIBusDevice *pbdev = NULL; - S390pciState *s = s390_get_phb(); if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_BRIDGE)) { error_setg(errp, "PCI bridge hot unplug currently not supported"); @@ -956,6 +966,8 @@ static void s390_pcihost_unplug(HotplugHandler *hotplug_dev, DeviceState *dev, } else if (object_dynamic_cast(OBJECT(dev), TYPE_S390_PCI_DEVICE)) { pbdev = S390_PCI_DEVICE(dev); pci_dev = pbdev->pdev; + } else { + g_assert_not_reached(); } switch (pbdev->state) { @@ -964,6 +976,9 @@ static void s390_pcihost_unplug(HotplugHandler *hotplug_dev, DeviceState *dev, case ZPCI_FS_STANDBY: break; default: + if (pbdev->release_timer) { + return; + } s390_pci_generate_plug_event(HP_EVENT_DECONFIGURE_REQUEST, pbdev->fh, pbdev->fid); pbdev->release_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, @@ -974,7 +989,7 @@ static void s390_pcihost_unplug(HotplugHandler *hotplug_dev, DeviceState *dev, return; } - if (pbdev->release_timer && timer_pending(pbdev->release_timer)) { + if (pbdev->release_timer) { timer_del(pbdev->release_timer); timer_free(pbdev->release_timer); pbdev->release_timer = NULL; @@ -985,6 +1000,7 @@ static void s390_pcihost_unplug(HotplugHandler *hotplug_dev, DeviceState *dev, bus = pci_get_bus(pci_dev); devfn = pci_dev->devfn; object_unparent(OBJECT(pci_dev)); + fmb_timer_free(pbdev); s390_pci_msix_free(pbdev); s390_pci_iommu_free(s, bus, devfn); pbdev->pdev = NULL; @@ -1041,6 +1057,7 @@ static void s390_pcihost_class_init(ObjectClass *klass, void *data) dc->reset = s390_pcihost_reset; dc->realize = s390_pcihost_realize; + hc->pre_plug = s390_pcihost_pre_plug; hc->plug = s390_pcihost_plug; hc->unplug = s390_pcihost_unplug; msi_nonbroken = true; @@ -1132,6 +1149,7 @@ static void s390_pci_device_realize(DeviceState *dev, Error **errp) } zpci->state = ZPCI_FS_RESERVED; + zpci->fmb.format = ZPCI_FMB_FORMAT; } static void s390_pci_device_reset(DeviceState *dev) @@ -1156,7 +1174,7 @@ static void s390_pci_device_reset(DeviceState *dev) pci_dereg_ioat(pbdev->iommu); } - pbdev->fmb_addr = 0; + fmb_timer_free(pbdev); } static void s390_pci_get_fid(Object *obj, Visitor *v, const char *name, diff --git a/hw/s390x/s390-pci-bus.h b/hw/s390x/s390-pci-bus.h index f47a0f2da5..dadad1f758 100644 --- a/hw/s390x/s390-pci-bus.h +++ b/hw/s390x/s390-pci-bus.h @@ -285,6 +285,33 @@ typedef struct S390PCIIOMMUTable { S390PCIIOMMU *iommu[PCI_SLOT_MAX]; } S390PCIIOMMUTable; +/* Function Measurement Block */ +#define DEFAULT_MUI 4000 +#define UPDATE_U_BIT 0x1ULL +#define FMBK_MASK 0xfULL + +typedef struct ZpciFmbFmt0 { + uint64_t dma_rbytes; + uint64_t dma_wbytes; +} ZpciFmbFmt0; + +#define ZPCI_FMB_CNT_LD 0 +#define ZPCI_FMB_CNT_ST 1 +#define ZPCI_FMB_CNT_STB 2 +#define ZPCI_FMB_CNT_RPCIT 3 +#define ZPCI_FMB_CNT_MAX 4 + +#define ZPCI_FMB_FORMAT 0 + +typedef struct ZpciFmb { + uint32_t format; + uint32_t sample; + uint64_t last_update; + uint64_t counter[ZPCI_FMB_CNT_MAX]; + ZpciFmbFmt0 fmt0; +} ZpciFmb; +QEMU_BUILD_BUG_MSG(offsetof(ZpciFmb, fmt0) != 48, "padding in ZpciFmb"); + struct S390PCIBusDevice { DeviceState qdev; PCIDevice *pdev; @@ -296,6 +323,8 @@ struct S390PCIBusDevice { uint32_t fid; bool fid_defined; uint64_t fmb_addr; + ZpciFmb fmb; + QEMUTimer *fmb_timer; uint8_t isc; uint16_t noi; uint16_t maxstbl; diff --git a/hw/s390x/s390-pci-inst.c b/hw/s390x/s390-pci-inst.c index 7b61367ee3..be2896232d 100644 --- a/hw/s390x/s390-pci-inst.c +++ b/hw/s390x/s390-pci-inst.c @@ -19,6 +19,7 @@ #include "exec/memory-internal.h" #include "qemu/error-report.h" #include "sysemu/hw_accel.h" +#include "hw/s390x/tod.h" #ifndef DEBUG_S390PCI_INST #define DEBUG_S390PCI_INST 0 @@ -293,7 +294,7 @@ int clp_service_call(S390CPU *cpu, uint8_t r2, uintptr_t ra) resgrp->fr = 1; stq_p(&resgrp->dasm, 0); stq_p(&resgrp->msia, ZPCI_MSI_ADDR); - stw_p(&resgrp->mui, 0); + stw_p(&resgrp->mui, DEFAULT_MUI); stw_p(&resgrp->i, 128); stw_p(&resgrp->maxstbl, 128); resgrp->version = 0; @@ -456,6 +457,8 @@ int pcilg_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra) return 0; } + pbdev->fmb.counter[ZPCI_FMB_CNT_LD]++; + env->regs[r1] = data; setcc(cpu, ZPCI_PCI_LS_OK); return 0; @@ -561,6 +564,8 @@ int pcistg_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra) return 0; } + pbdev->fmb.counter[ZPCI_FMB_CNT_ST]++; + setcc(cpu, ZPCI_PCI_LS_OK); return 0; } @@ -681,6 +686,7 @@ err: s390_set_status_code(env, r1, ZPCI_PCI_ST_FUNC_IN_ERR); s390_pci_generate_error_event(error, pbdev->fh, pbdev->fid, start, 0); } else { + pbdev->fmb.counter[ZPCI_FMB_CNT_RPCIT]++; setcc(cpu, ZPCI_PCI_LS_OK); } return 0; @@ -783,6 +789,8 @@ int pcistb_service_call(S390CPU *cpu, uint8_t r1, uint8_t r3, uint64_t gaddr, } } + pbdev->fmb.counter[ZPCI_FMB_CNT_STB]++; + setcc(cpu, ZPCI_PCI_LS_OK); return 0; @@ -889,6 +897,99 @@ void pci_dereg_ioat(S390PCIIOMMU *iommu) iommu->g_iota = 0; } +void fmb_timer_free(S390PCIBusDevice *pbdev) +{ + if (pbdev->fmb_timer) { + timer_del(pbdev->fmb_timer); + timer_free(pbdev->fmb_timer); + pbdev->fmb_timer = NULL; + } + pbdev->fmb_addr = 0; + memset(&pbdev->fmb, 0, sizeof(ZpciFmb)); +} + +static int fmb_do_update(S390PCIBusDevice *pbdev, int offset, uint64_t val, + int len) +{ + MemTxResult ret; + uint64_t dst = pbdev->fmb_addr + offset; + + switch (len) { + case 8: + address_space_stq_be(&address_space_memory, dst, val, + MEMTXATTRS_UNSPECIFIED, + &ret); + break; + case 4: + address_space_stl_be(&address_space_memory, dst, val, + MEMTXATTRS_UNSPECIFIED, + &ret); + break; + case 2: + address_space_stw_be(&address_space_memory, dst, val, + MEMTXATTRS_UNSPECIFIED, + &ret); + break; + case 1: + address_space_stb(&address_space_memory, dst, val, + MEMTXATTRS_UNSPECIFIED, + &ret); + break; + default: + ret = MEMTX_ERROR; + break; + } + if (ret != MEMTX_OK) { + s390_pci_generate_error_event(ERR_EVENT_FMBA, pbdev->fh, pbdev->fid, + pbdev->fmb_addr, 0); + fmb_timer_free(pbdev); + } + + return ret; +} + +static void fmb_update(void *opaque) +{ + S390PCIBusDevice *pbdev = opaque; + int64_t t = qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL); + int i; + + /* Update U bit */ + pbdev->fmb.last_update *= 2; + pbdev->fmb.last_update |= UPDATE_U_BIT; + if (fmb_do_update(pbdev, offsetof(ZpciFmb, last_update), + pbdev->fmb.last_update, + sizeof(pbdev->fmb.last_update))) { + return; + } + + /* Update FMB sample count */ + if (fmb_do_update(pbdev, offsetof(ZpciFmb, sample), + pbdev->fmb.sample++, + sizeof(pbdev->fmb.sample))) { + return; + } + + /* Update FMB counters */ + for (i = 0; i < ZPCI_FMB_CNT_MAX; i++) { + if (fmb_do_update(pbdev, offsetof(ZpciFmb, counter[i]), + pbdev->fmb.counter[i], + sizeof(pbdev->fmb.counter[0]))) { + return; + } + } + + /* Clear U bit and update the time */ + pbdev->fmb.last_update = time2tod(qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL)); + pbdev->fmb.last_update *= 2; + if (fmb_do_update(pbdev, offsetof(ZpciFmb, last_update), + pbdev->fmb.last_update, + sizeof(pbdev->fmb.last_update))) { + return; + } + timer_mod(pbdev->fmb_timer, t + DEFAULT_MUI); +} + int mpcifc_service_call(S390CPU *cpu, uint8_t r1, uint64_t fiba, uint8_t ar, uintptr_t ra) { @@ -1018,9 +1119,35 @@ int mpcifc_service_call(S390CPU *cpu, uint8_t r1, uint64_t fiba, uint8_t ar, s390_set_status_code(env, r1, ZPCI_MOD_ST_SEQUENCE); } break; - case ZPCI_MOD_FC_SET_MEASURE: - pbdev->fmb_addr = ldq_p(&fib.fmb_addr); + case ZPCI_MOD_FC_SET_MEASURE: { + uint64_t fmb_addr = ldq_p(&fib.fmb_addr); + + if (fmb_addr & FMBK_MASK) { + cc = ZPCI_PCI_LS_ERR; + s390_pci_generate_error_event(ERR_EVENT_FMBPRO, pbdev->fh, + pbdev->fid, fmb_addr, 0); + fmb_timer_free(pbdev); + break; + } + + if (!fmb_addr) { + /* Stop updating FMB. */ + fmb_timer_free(pbdev); + break; + } + + if (!pbdev->fmb_timer) { + pbdev->fmb_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL, + fmb_update, pbdev); + } else if (timer_pending(pbdev->fmb_timer)) { + /* Remove pending timer to update FMB address. */ + timer_del(pbdev->fmb_timer); + } + pbdev->fmb_addr = fmb_addr; + timer_mod(pbdev->fmb_timer, + qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + DEFAULT_MUI); break; + } default: s390_program_interrupt(&cpu->env, PGM_OPERAND, 6, ra); cc = ZPCI_PCI_LS_ERR; diff --git a/hw/s390x/s390-pci-inst.h b/hw/s390x/s390-pci-inst.h index 91c3d61f2a..fa3bf8b5aa 100644 --- a/hw/s390x/s390-pci-inst.h +++ b/hw/s390x/s390-pci-inst.h @@ -303,6 +303,7 @@ int mpcifc_service_call(S390CPU *cpu, uint8_t r1, uint64_t fiba, uint8_t ar, uintptr_t ra); int stpcifc_service_call(S390CPU *cpu, uint8_t r1, uint64_t fiba, uint8_t ar, uintptr_t ra); +void fmb_timer_free(S390PCIBusDevice *pbdev); #define ZPCI_IO_BAR_MIN 0 #define ZPCI_IO_BAR_MAX 5 diff --git a/hw/scsi/vhost-scsi.c b/hw/scsi/vhost-scsi.c index 7f21b4f9d6..61e2e57da9 100644 --- a/hw/scsi/vhost-scsi.c +++ b/hw/scsi/vhost-scsi.c @@ -215,6 +215,7 @@ static void vhost_scsi_unrealize(DeviceState *dev, Error **errp) { VirtIODevice *vdev = VIRTIO_DEVICE(dev); VHostSCSICommon *vsc = VHOST_SCSI_COMMON(dev); + struct vhost_virtqueue *vqs = vsc->dev.vqs; migrate_del_blocker(vsc->migration_blocker); error_free(vsc->migration_blocker); @@ -223,7 +224,7 @@ static void vhost_scsi_unrealize(DeviceState *dev, Error **errp) vhost_scsi_set_status(vdev, 0); vhost_dev_cleanup(&vsc->dev); - g_free(vsc->dev.vqs); + g_free(vqs); virtio_scsi_common_unrealize(dev, errp); } diff --git a/hw/scsi/vhost-user-scsi.c b/hw/scsi/vhost-user-scsi.c index 2e1ba4a87b..6728878a52 100644 --- a/hw/scsi/vhost-user-scsi.c +++ b/hw/scsi/vhost-user-scsi.c @@ -121,12 +121,13 @@ static void vhost_user_scsi_unrealize(DeviceState *dev, Error **errp) VirtIODevice *vdev = VIRTIO_DEVICE(dev); VHostUserSCSI *s = VHOST_USER_SCSI(dev); VHostSCSICommon *vsc = VHOST_SCSI_COMMON(s); + struct vhost_virtqueue *vqs = vsc->dev.vqs; /* This will stop the vhost backend. */ vhost_user_scsi_set_status(vdev, 0); vhost_dev_cleanup(&vsc->dev); - g_free(vsc->dev.vqs); + g_free(vqs); virtio_scsi_common_unrealize(dev, errp); diff --git a/hw/tpm/Makefile.objs b/hw/tpm/Makefile.objs index 1dc9f8bf2c..700c878622 100644 --- a/hw/tpm/Makefile.objs +++ b/hw/tpm/Makefile.objs @@ -1,4 +1,5 @@ common-obj-y += tpm_util.o +obj-y += tpm_ppi.o common-obj-$(CONFIG_TPM_TIS) += tpm_tis.o common-obj-$(CONFIG_TPM_CRB) += tpm_crb.o common-obj-$(CONFIG_TPM_PASSTHROUGH) += tpm_passthrough.o diff --git a/hw/tpm/tpm_crb.c b/hw/tpm/tpm_crb.c index a92dd50437..3087acc4ab 100644 --- a/hw/tpm/tpm_crb.c +++ b/hw/tpm/tpm_crb.c @@ -29,6 +29,7 @@ #include "sysemu/reset.h" #include "tpm_int.h" #include "tpm_util.h" +#include "tpm_ppi.h" #include "trace.h" typedef struct CRBState { @@ -41,6 +42,9 @@ typedef struct CRBState { MemoryRegion cmdmem; size_t be_buffer_size; + + bool ppi_enabled; + TPMPPI ppi; } CRBState; #define CRB(obj) OBJECT_CHECK(CRBState, (obj), TYPE_TPM_CRB) @@ -221,6 +225,7 @@ static const VMStateDescription vmstate_tpm_crb = { static Property tpm_crb_properties[] = { DEFINE_PROP_TPMBE("tpmdev", CRBState, tpmbe), + DEFINE_PROP_BOOL("ppi", CRBState, ppi_enabled, true), DEFINE_PROP_END_OF_LIST(), }; @@ -228,6 +233,9 @@ static void tpm_crb_reset(void *dev) { CRBState *s = CRB(dev); + if (s->ppi_enabled) { + tpm_ppi_reset(&s->ppi); + } tpm_backend_reset(s->tpmbe); memset(s->regs, 0, sizeof(s->regs)); @@ -291,6 +299,11 @@ static void tpm_crb_realize(DeviceState *dev, Error **errp) memory_region_add_subregion(get_system_memory(), TPM_CRB_ADDR_BASE + sizeof(s->regs), &s->cmdmem); + if (s->ppi_enabled) { + tpm_ppi_init(&s->ppi, get_system_memory(), + TPM_PPI_ADDR_BASE, OBJECT(s)); + } + qemu_register_reset(tpm_crb_reset, dev); } diff --git a/hw/tpm/tpm_ppi.c b/hw/tpm/tpm_ppi.c new file mode 100644 index 0000000000..cd8205f212 --- /dev/null +++ b/hw/tpm/tpm_ppi.c @@ -0,0 +1,53 @@ +/* + * tpm_ppi.c - TPM Physical Presence Interface + * + * Copyright (C) 2018 IBM Corporation + * + * Authors: + * Stefan Berger <stefanb@us.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 "qemu/osdep.h" + +#include "qapi/error.h" +#include "cpu.h" +#include "sysemu/memory_mapping.h" +#include "sysemu/reset.h" +#include "migration/vmstate.h" +#include "tpm_ppi.h" +#include "trace.h" + +void tpm_ppi_reset(TPMPPI *tpmppi) +{ + if (tpmppi->buf[0x15a /* movv, docs/specs/tpm.txt */] & 0x1) { + GuestPhysBlockList guest_phys_blocks; + GuestPhysBlock *block; + + guest_phys_blocks_init(&guest_phys_blocks); + guest_phys_blocks_append(&guest_phys_blocks); + QTAILQ_FOREACH(block, &guest_phys_blocks.head, next) { + trace_tpm_ppi_memset(block->host_addr, + block->target_end - block->target_start); + memset(block->host_addr, 0, + block->target_end - block->target_start); + memory_region_set_dirty(block->mr, 0, + block->target_end - block->target_start); + } + guest_phys_blocks_free(&guest_phys_blocks); + } +} + +void tpm_ppi_init(TPMPPI *tpmppi, struct MemoryRegion *m, + hwaddr addr, Object *obj) +{ + tpmppi->buf = g_malloc0(HOST_PAGE_ALIGN(TPM_PPI_ADDR_SIZE)); + memory_region_init_ram_device_ptr(&tpmppi->ram, obj, "tpm-ppi", + TPM_PPI_ADDR_SIZE, tpmppi->buf); + vmstate_register_ram(&tpmppi->ram, DEVICE(obj)); + + memory_region_add_subregion(m, addr, &tpmppi->ram); +} diff --git a/hw/tpm/tpm_ppi.h b/hw/tpm/tpm_ppi.h new file mode 100644 index 0000000000..d33ef27de6 --- /dev/null +++ b/hw/tpm/tpm_ppi.h @@ -0,0 +1,46 @@ +/* + * TPM Physical Presence Interface + * + * Copyright (C) 2018 IBM Corporation + * + * Authors: + * Stefan Berger <stefanb@us.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. + */ +#ifndef TPM_TPM_PPI_H +#define TPM_TPM_PPI_H + +#include "hw/acpi/tpm.h" +#include "exec/address-spaces.h" + +typedef struct TPMPPI { + MemoryRegion ram; + uint8_t *buf; +} TPMPPI; + +/** + * tpm_ppi_init: + * @tpmppi: a TPMPPI + * @m: the address-space / MemoryRegion to use + * @addr: the address of the PPI region + * @obj: the owner object + * + * Register the TPM PPI memory region at @addr on the given address + * space for the object @obj. + **/ +void tpm_ppi_init(TPMPPI *tpmppi, struct MemoryRegion *m, + hwaddr addr, Object *obj); + +/** + * tpm_ppi_reset: + * @tpmppi: a TPMPPI + * + * Function to call on machine reset. It will check if the "Memory + * overwrite" variable is set, and perform a memory clear on volatile + * memory if requested. + **/ +void tpm_ppi_reset(TPMPPI *tpmppi); + +#endif /* TPM_TPM_PPI_H */ diff --git a/hw/tpm/tpm_tis.c b/hw/tpm/tpm_tis.c index 2563d7501f..fd6bb9b59a 100644 --- a/hw/tpm/tpm_tis.c +++ b/hw/tpm/tpm_tis.c @@ -31,6 +31,7 @@ #include "sysemu/tpm_backend.h" #include "tpm_int.h" #include "tpm_util.h" +#include "tpm_ppi.h" #include "trace.h" #define TPM_TIS_NUM_LOCALITIES 5 /* per spec */ @@ -81,6 +82,9 @@ typedef struct TPMState { TPMVersion be_tpm_version; size_t be_buffer_size; + + bool ppi_enabled; + TPMPPI ppi; } TPMState; #define TPM(obj) OBJECT_CHECK(TPMState, (obj), TYPE_TPM_TIS) @@ -868,6 +872,9 @@ static void tpm_tis_reset(DeviceState *dev) s->be_buffer_size = MIN(tpm_backend_get_buffer_size(s->be_driver), TPM_TIS_BUFFER_MAX); + if (s->ppi_enabled) { + tpm_ppi_reset(&s->ppi); + } tpm_backend_reset(s->be_driver); s->active_locty = TPM_TIS_NO_LOCALITY; @@ -954,6 +961,7 @@ static const VMStateDescription vmstate_tpm_tis = { static Property tpm_tis_properties[] = { DEFINE_PROP_UINT32("irq", TPMState, irq_num, TPM_TIS_IRQ), DEFINE_PROP_TPMBE("tpmdev", TPMState, be_driver), + DEFINE_PROP_BOOL("ppi", TPMState, ppi_enabled, true), DEFINE_PROP_END_OF_LIST(), }; @@ -980,6 +988,11 @@ static void tpm_tis_realizefn(DeviceState *dev, Error **errp) memory_region_add_subregion(isa_address_space(ISA_DEVICE(dev)), TPM_TIS_ADDR_BASE, &s->mmio); + + if (s->ppi_enabled) { + tpm_ppi_init(&s->ppi, isa_address_space(ISA_DEVICE(dev)), + TPM_PPI_ADDR_BASE, OBJECT(s)); + } } static void tpm_tis_initfn(Object *obj) diff --git a/hw/tpm/trace-events b/hw/tpm/trace-events index 25bee0cecf..920d32ad55 100644 --- a/hw/tpm/trace-events +++ b/hw/tpm/trace-events @@ -51,3 +51,6 @@ tpm_tis_mmio_write_init_abort(void) "Initiating abort" tpm_tis_mmio_write_lowering_irq(void) "Lowering IRQ" tpm_tis_mmio_write_data2send(uint32_t value, unsigned size) "Data to send to TPM: 0x%08x (size=%d)" tpm_tis_pre_save(uint8_t locty, uint32_t rw_offset) "locty: %d, rw_offset = %u" + +# hw/tpm/tpm_ppi.c +tpm_ppi_memset(uint8_t *ptr, size_t size) "memset: %p %zu" diff --git a/hw/virtio/Makefile.objs b/hw/virtio/Makefile.objs index 1b2799cfd8..ea7913d532 100644 --- a/hw/virtio/Makefile.objs +++ b/hw/virtio/Makefile.objs @@ -11,6 +11,21 @@ obj-$(call land,$(CONFIG_VIRTIO_CRYPTO),$(CONFIG_VIRTIO_PCI)) += virtio-crypto-p obj-$(CONFIG_LINUX) += vhost.o vhost-backend.o vhost-user.o obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock.o +ifeq ($(CONFIG_PCI),y) +obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock-pci.o +obj-$(CONFIG_VHOST_USER_BLK) += vhost-user-blk-pci.o +obj-$(CONFIG_VHOST_USER_SCSI) += vhost-user-scsi-pci.o +obj-$(CONFIG_VHOST_SCSI) += vhost-scsi-pci.o +obj-$(CONFIG_VIRTIO_INPUT_HOST) += virtio-input-host-pci.o +obj-$(CONFIG_VIRTIO_INPUT) += virtio-input-pci.o +obj-$(CONFIG_VIRTIO_RNG) += virtio-rng-pci.o +obj-$(CONFIG_VIRTIO_BALLOON) += virtio-balloon-pci.o +obj-$(CONFIG_VIRTIO_9P) += virtio-9p-pci.o +obj-$(CONFIG_VIRTIO_SCSI) += virtio-scsi-pci.o +obj-$(CONFIG_VIRTIO_BLK) += virtio-blk-pci.o +obj-$(CONFIG_VIRTIO_NET) += virtio-net-pci.o +obj-$(CONFIG_VIRTIO_SERIAL) += virtio-serial-pci.o +endif endif common-obj-$(call lnot,$(call land,$(CONFIG_VIRTIO),$(CONFIG_LINUX))) += vhost-stub.o diff --git a/hw/virtio/vhost-scsi-pci.c b/hw/virtio/vhost-scsi-pci.c new file mode 100644 index 0000000000..523f7cb3ce --- /dev/null +++ b/hw/virtio/vhost-scsi-pci.c @@ -0,0 +1,97 @@ +/* + * Vhost scsi PCI bindings + * + * Copyright IBM, Corp. 2011 + * + * Authors: + * Stefan Hajnoczi <stefanha@linux.vnet.ibm.com> + * + * Changes for QEMU mainline + tcm_vhost kernel upstream: + * Nicholas Bellinger <nab@risingtidesystems.com> + * + * This work is licensed under the terms of the GNU LGPL, version 2 or later. + * See the COPYING.LIB file in the top-level directory. + * + */ + +#include "qemu/osdep.h" + +#include "standard-headers/linux/virtio_pci.h" +#include "hw/virtio/vhost-scsi.h" +#include "qapi/error.h" +#include "virtio-pci.h" + +typedef struct VHostSCSIPCI VHostSCSIPCI; + +/* + * vhost-scsi-pci: This extends VirtioPCIProxy. + */ +#define TYPE_VHOST_SCSI_PCI "vhost-scsi-pci-base" +#define VHOST_SCSI_PCI(obj) \ + OBJECT_CHECK(VHostSCSIPCI, (obj), TYPE_VHOST_SCSI_PCI) + +struct VHostSCSIPCI { + VirtIOPCIProxy parent_obj; + VHostSCSI vdev; +}; + +static Property vhost_scsi_pci_properties[] = { + DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, + DEV_NVECTORS_UNSPECIFIED), + DEFINE_PROP_END_OF_LIST(), +}; + +static void vhost_scsi_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) +{ + VHostSCSIPCI *dev = VHOST_SCSI_PCI(vpci_dev); + DeviceState *vdev = DEVICE(&dev->vdev); + VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(vdev); + + if (vpci_dev->nvectors == DEV_NVECTORS_UNSPECIFIED) { + vpci_dev->nvectors = vs->conf.num_queues + 3; + } + + qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); + object_property_set_bool(OBJECT(vdev), true, "realized", errp); +} + +static void vhost_scsi_pci_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); + PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); + k->realize = vhost_scsi_pci_realize; + set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); + dc->props = vhost_scsi_pci_properties; + pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; + pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_SCSI; + pcidev_k->revision = 0x00; + pcidev_k->class_id = PCI_CLASS_STORAGE_SCSI; +} + +static void vhost_scsi_pci_instance_init(Object *obj) +{ + VHostSCSIPCI *dev = VHOST_SCSI_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VHOST_SCSI); + object_property_add_alias(obj, "bootindex", OBJECT(&dev->vdev), + "bootindex", &error_abort); +} + +static const VirtioPCIDeviceTypeInfo vhost_scsi_pci_info = { + .base_name = TYPE_VHOST_SCSI_PCI, + .generic_name = "vhost-scsi-pci", + .transitional_name = "vhost-scsi-pci-transitional", + .non_transitional_name = "vhost-scsi-pci-non-transitional", + .instance_size = sizeof(VHostSCSIPCI), + .instance_init = vhost_scsi_pci_instance_init, + .class_init = vhost_scsi_pci_class_init, +}; + +static void vhost_scsi_pci_register(void) +{ + virtio_pci_types_register(&vhost_scsi_pci_info); +} + +type_init(vhost_scsi_pci_register) diff --git a/hw/virtio/vhost-user-blk-pci.c b/hw/virtio/vhost-user-blk-pci.c new file mode 100644 index 0000000000..ca66c217a7 --- /dev/null +++ b/hw/virtio/vhost-user-blk-pci.c @@ -0,0 +1,103 @@ +/* + * Vhost user blk PCI Bindings + * + * Copyright(C) 2017 Intel Corporation. + * + * Authors: + * Changpeng Liu <changpeng.liu@intel.com> + * + * Largely based on the "vhost-user-scsi.c" and "vhost-scsi.c" implemented by: + * Felipe Franciosi <felipe@nutanix.com> + * Stefan Hajnoczi <stefanha@linux.vnet.ibm.com> + * Nicholas Bellinger <nab@risingtidesystems.com> + * + * This work is licensed under the terms of the GNU LGPL, version 2 or later. + * See the COPYING.LIB file in the top-level directory. + * + */ + +#include "qemu/osdep.h" + +#include "standard-headers/linux/virtio_pci.h" +#include "hw/virtio/virtio.h" +#include "hw/virtio/vhost-user-blk.h" +#include "hw/pci/pci.h" +#include "qapi/error.h" +#include "qemu/error-report.h" +#include "virtio-pci.h" + +typedef struct VHostUserBlkPCI VHostUserBlkPCI; + +/* + * vhost-user-blk-pci: This extends VirtioPCIProxy. + */ +#define TYPE_VHOST_USER_BLK_PCI "vhost-user-blk-pci-base" +#define VHOST_USER_BLK_PCI(obj) \ + OBJECT_CHECK(VHostUserBlkPCI, (obj), TYPE_VHOST_USER_BLK_PCI) + +struct VHostUserBlkPCI { + VirtIOPCIProxy parent_obj; + VHostUserBlk vdev; +}; + +static Property vhost_user_blk_pci_properties[] = { + DEFINE_PROP_UINT32("class", VirtIOPCIProxy, class_code, 0), + DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, + DEV_NVECTORS_UNSPECIFIED), + DEFINE_PROP_END_OF_LIST(), +}; + +static void vhost_user_blk_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) +{ + VHostUserBlkPCI *dev = VHOST_USER_BLK_PCI(vpci_dev); + DeviceState *vdev = DEVICE(&dev->vdev); + + if (vpci_dev->nvectors == DEV_NVECTORS_UNSPECIFIED) { + vpci_dev->nvectors = dev->vdev.num_queues + 1; + } + + qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); + object_property_set_bool(OBJECT(vdev), true, "realized", errp); +} + +static void vhost_user_blk_pci_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); + PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); + + set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); + dc->props = vhost_user_blk_pci_properties; + k->realize = vhost_user_blk_pci_realize; + pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; + pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_BLOCK; + pcidev_k->revision = VIRTIO_PCI_ABI_VERSION; + pcidev_k->class_id = PCI_CLASS_STORAGE_SCSI; +} + +static void vhost_user_blk_pci_instance_init(Object *obj) +{ + VHostUserBlkPCI *dev = VHOST_USER_BLK_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VHOST_USER_BLK); + object_property_add_alias(obj, "bootindex", OBJECT(&dev->vdev), + "bootindex", &error_abort); +} + +static const VirtioPCIDeviceTypeInfo vhost_user_blk_pci_info = { + .base_name = TYPE_VHOST_USER_BLK_PCI, + .generic_name = "vhost-user-blk-pci", + .transitional_name = "vhost-user-blk-pci-transitional", + .non_transitional_name = "vhost-user-blk-pci-non-transitional", + .instance_size = sizeof(VHostUserBlkPCI), + .instance_init = vhost_user_blk_pci_instance_init, + .class_init = vhost_user_blk_pci_class_init, +}; + +static void vhost_user_blk_pci_register(void) +{ + virtio_pci_types_register(&vhost_user_blk_pci_info); +} + +type_init(vhost_user_blk_pci_register) diff --git a/hw/virtio/vhost-user-scsi-pci.c b/hw/virtio/vhost-user-scsi-pci.c new file mode 100644 index 0000000000..46f7193cc7 --- /dev/null +++ b/hw/virtio/vhost-user-scsi-pci.c @@ -0,0 +1,103 @@ +/* + * Vhost user scsi PCI Bindings + * + * Copyright (c) 2016 Nutanix Inc. All rights reserved. + * + * Author: + * Felipe Franciosi <felipe@nutanix.com> + * + * This work is largely based on the "vhost-scsi" implementation by: + * Stefan Hajnoczi <stefanha@linux.vnet.ibm.com> + * Nicholas Bellinger <nab@risingtidesystems.com> + * + * This work is licensed under the terms of the GNU LGPL, version 2 or later. + * See the COPYING.LIB file in the top-level directory. + * + */ + +#include "qemu/osdep.h" + +#include "standard-headers/linux/virtio_pci.h" +#include "hw/virtio/vhost-user-scsi.h" +#include "hw/virtio/virtio.h" +#include "hw/virtio/virtio-scsi.h" +#include "hw/pci/pci.h" +#include "qapi/error.h" +#include "qemu/error-report.h" +#include "hw/pci/msi.h" +#include "hw/pci/msix.h" +#include "hw/loader.h" +#include "sysemu/kvm.h" +#include "virtio-pci.h" + +typedef struct VHostUserSCSIPCI VHostUserSCSIPCI; + +#define TYPE_VHOST_USER_SCSI_PCI "vhost-user-scsi-pci-base" +#define VHOST_USER_SCSI_PCI(obj) \ + OBJECT_CHECK(VHostUserSCSIPCI, (obj), TYPE_VHOST_USER_SCSI_PCI) + +struct VHostUserSCSIPCI { + VirtIOPCIProxy parent_obj; + VHostUserSCSI vdev; +}; + +static Property vhost_user_scsi_pci_properties[] = { + DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, + DEV_NVECTORS_UNSPECIFIED), + DEFINE_PROP_END_OF_LIST(), +}; + +static void vhost_user_scsi_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) +{ + VHostUserSCSIPCI *dev = VHOST_USER_SCSI_PCI(vpci_dev); + DeviceState *vdev = DEVICE(&dev->vdev); + VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(vdev); + + if (vpci_dev->nvectors == DEV_NVECTORS_UNSPECIFIED) { + vpci_dev->nvectors = vs->conf.num_queues + 3; + } + + qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); + object_property_set_bool(OBJECT(vdev), true, "realized", errp); +} + +static void vhost_user_scsi_pci_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); + PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); + k->realize = vhost_user_scsi_pci_realize; + set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); + dc->props = vhost_user_scsi_pci_properties; + pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; + pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_SCSI; + pcidev_k->revision = 0x00; + pcidev_k->class_id = PCI_CLASS_STORAGE_SCSI; +} + +static void vhost_user_scsi_pci_instance_init(Object *obj) +{ + VHostUserSCSIPCI *dev = VHOST_USER_SCSI_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VHOST_USER_SCSI); + object_property_add_alias(obj, "bootindex", OBJECT(&dev->vdev), + "bootindex", &error_abort); +} + +static const VirtioPCIDeviceTypeInfo vhost_user_scsi_pci_info = { + .base_name = TYPE_VHOST_USER_SCSI_PCI, + .generic_name = "vhost-user-scsi-pci", + .transitional_name = "vhost-user-scsi-pci-transitional", + .non_transitional_name = "vhost-user-scsi-pci-non-transitional", + .instance_size = sizeof(VHostUserSCSIPCI), + .instance_init = vhost_user_scsi_pci_instance_init, + .class_init = vhost_user_scsi_pci_class_init, +}; + +static void vhost_user_scsi_pci_register(void) +{ + virtio_pci_types_register(&vhost_user_scsi_pci_info); +} + +type_init(vhost_user_scsi_pci_register) diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index e09bed0e4a..564a31d12c 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -207,7 +207,7 @@ struct vhost_user { static bool ioeventfd_enabled(void) { - return kvm_enabled() && kvm_eventfds_enabled(); + return !kvm_enabled() || kvm_eventfds_enabled(); } static int vhost_user_read(struct vhost_dev *dev, VhostUserMsg *msg) diff --git a/hw/virtio/vhost-vsock-pci.c b/hw/virtio/vhost-vsock-pci.c new file mode 100644 index 0000000000..6f43ca35fb --- /dev/null +++ b/hw/virtio/vhost-vsock-pci.c @@ -0,0 +1,86 @@ +/* + * Vhost vsock PCI Bindings + * + * Copyright 2015 Red Hat, Inc. + * + * Authors: + * Stefan Hajnoczi <stefanha@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * (at your option) any later version. See the COPYING file in the + * top-level directory. + */ + +#include "qemu/osdep.h" + +#include "virtio-pci.h" +#include "hw/virtio/vhost-vsock.h" + +typedef struct VHostVSockPCI VHostVSockPCI; + +/* + * vhost-vsock-pci: This extends VirtioPCIProxy. + */ +#define TYPE_VHOST_VSOCK_PCI "vhost-vsock-pci-base" +#define VHOST_VSOCK_PCI(obj) \ + OBJECT_CHECK(VHostVSockPCI, (obj), TYPE_VHOST_VSOCK_PCI) + +struct VHostVSockPCI { + VirtIOPCIProxy parent_obj; + VHostVSock vdev; +}; + +/* vhost-vsock-pci */ + +static Property vhost_vsock_pci_properties[] = { + DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 3), + DEFINE_PROP_END_OF_LIST(), +}; + +static void vhost_vsock_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) +{ + VHostVSockPCI *dev = VHOST_VSOCK_PCI(vpci_dev); + DeviceState *vdev = DEVICE(&dev->vdev); + + qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); + object_property_set_bool(OBJECT(vdev), true, "realized", errp); +} + +static void vhost_vsock_pci_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); + PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); + k->realize = vhost_vsock_pci_realize; + set_bit(DEVICE_CATEGORY_MISC, dc->categories); + dc->props = vhost_vsock_pci_properties; + pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; + pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_VSOCK; + pcidev_k->revision = 0x00; + pcidev_k->class_id = PCI_CLASS_COMMUNICATION_OTHER; +} + +static void vhost_vsock_pci_instance_init(Object *obj) +{ + VHostVSockPCI *dev = VHOST_VSOCK_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VHOST_VSOCK); +} + +static const VirtioPCIDeviceTypeInfo vhost_vsock_pci_info = { + .base_name = TYPE_VHOST_VSOCK_PCI, + .generic_name = "vhost-vsock-pci", + .transitional_name = "vhost-vsock-pci-transitional", + .non_transitional_name = "vhost-vsock-pci-non-transitional", + .instance_size = sizeof(VHostVSockPCI), + .instance_init = vhost_vsock_pci_instance_init, + .class_init = vhost_vsock_pci_class_init, +}; + +static void virtio_pci_vhost_register(void) +{ + virtio_pci_types_register(&vhost_vsock_pci_info); +} + +type_init(virtio_pci_vhost_register) diff --git a/hw/virtio/virtio-9p-pci.c b/hw/virtio/virtio-9p-pci.c new file mode 100644 index 0000000000..7bf1130966 --- /dev/null +++ b/hw/virtio/virtio-9p-pci.c @@ -0,0 +1,88 @@ +/* + * Virtio 9p PCI Bindings + * + * Copyright IBM, Corp. 2010 + * + * Authors: + * Anthony Liguori <aliguori@us.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Contributions after 2012-01-13 are licensed under the terms of the + * GNU GPL, version 2 or (at your option) any later version. + */ + +#include "qemu/osdep.h" + +#include "virtio-pci.h" +#include "hw/9pfs/virtio-9p.h" + +/* + * virtio-9p-pci: This extends VirtioPCIProxy. + */ + +#define TYPE_VIRTIO_9P_PCI "virtio-9p-pci-base" +#define VIRTIO_9P_PCI(obj) \ + OBJECT_CHECK(V9fsPCIState, (obj), TYPE_VIRTIO_9P_PCI) + +typedef struct V9fsPCIState { + VirtIOPCIProxy parent_obj; + V9fsVirtioState vdev; +} V9fsPCIState; + +static void virtio_9p_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) +{ + V9fsPCIState *dev = VIRTIO_9P_PCI(vpci_dev); + DeviceState *vdev = DEVICE(&dev->vdev); + + qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); + object_property_set_bool(OBJECT(vdev), true, "realized", errp); +} + +static Property virtio_9p_pci_properties[] = { + DEFINE_PROP_BIT("ioeventfd", VirtIOPCIProxy, flags, + VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT, true), + DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 2), + DEFINE_PROP_END_OF_LIST(), +}; + +static void virtio_9p_pci_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); + VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); + + k->realize = virtio_9p_pci_realize; + pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; + pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_9P; + pcidev_k->revision = VIRTIO_PCI_ABI_VERSION; + pcidev_k->class_id = 0x2; + set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); + dc->props = virtio_9p_pci_properties; +} + +static void virtio_9p_pci_instance_init(Object *obj) +{ + V9fsPCIState *dev = VIRTIO_9P_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VIRTIO_9P); +} + +static const VirtioPCIDeviceTypeInfo virtio_9p_pci_info = { + .base_name = TYPE_VIRTIO_9P_PCI, + .generic_name = "virtio-9p-pci", + .transitional_name = "virtio-9p-pci-transitional", + .non_transitional_name = "virtio-9p-pci-non-transitional", + .instance_size = sizeof(V9fsPCIState), + .instance_init = virtio_9p_pci_instance_init, + .class_init = virtio_9p_pci_class_init, +}; + +static void virtio_9p_pci_register(void) +{ + virtio_pci_types_register(&virtio_9p_pci_info); +} + +type_init(virtio_9p_pci_register) diff --git a/hw/virtio/virtio-balloon-pci.c b/hw/virtio/virtio-balloon-pci.c new file mode 100644 index 0000000000..2a213bbb38 --- /dev/null +++ b/hw/virtio/virtio-balloon-pci.c @@ -0,0 +1,95 @@ +/* + * Virtio balloon PCI Bindings + * + * Copyright IBM, Corp. 2007 + * Copyright (c) 2009 CodeSourcery + * + * Authors: + * Anthony Liguori <aliguori@us.ibm.com> + * Paul Brook <paul@codesourcery.com> + * + * Contributions after 2012-01-13 are licensed under the terms of the + * GNU GPL, version 2 or (at your option) any later version. + */ + +#include "qemu/osdep.h" + +#include "virtio-pci.h" +#include "hw/virtio/virtio-balloon.h" +#include "qapi/error.h" + +typedef struct VirtIOBalloonPCI VirtIOBalloonPCI; + +/* + * virtio-balloon-pci: This extends VirtioPCIProxy. + */ +#define TYPE_VIRTIO_BALLOON_PCI "virtio-balloon-pci-base" +#define VIRTIO_BALLOON_PCI(obj) \ + OBJECT_CHECK(VirtIOBalloonPCI, (obj), TYPE_VIRTIO_BALLOON_PCI) + +struct VirtIOBalloonPCI { + VirtIOPCIProxy parent_obj; + VirtIOBalloon vdev; +}; +static Property virtio_balloon_pci_properties[] = { + DEFINE_PROP_UINT32("class", VirtIOPCIProxy, class_code, 0), + DEFINE_PROP_END_OF_LIST(), +}; + +static void virtio_balloon_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) +{ + VirtIOBalloonPCI *dev = VIRTIO_BALLOON_PCI(vpci_dev); + DeviceState *vdev = DEVICE(&dev->vdev); + + if (vpci_dev->class_code != PCI_CLASS_OTHERS && + vpci_dev->class_code != PCI_CLASS_MEMORY_RAM) { /* qemu < 1.1 */ + vpci_dev->class_code = PCI_CLASS_OTHERS; + } + + qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); + object_property_set_bool(OBJECT(vdev), true, "realized", errp); +} + +static void virtio_balloon_pci_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); + PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); + k->realize = virtio_balloon_pci_realize; + set_bit(DEVICE_CATEGORY_MISC, dc->categories); + dc->props = virtio_balloon_pci_properties; + pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; + pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_BALLOON; + pcidev_k->revision = VIRTIO_PCI_ABI_VERSION; + pcidev_k->class_id = PCI_CLASS_OTHERS; +} + +static void virtio_balloon_pci_instance_init(Object *obj) +{ + VirtIOBalloonPCI *dev = VIRTIO_BALLOON_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VIRTIO_BALLOON); + object_property_add_alias(obj, "guest-stats", OBJECT(&dev->vdev), + "guest-stats", &error_abort); + object_property_add_alias(obj, "guest-stats-polling-interval", + OBJECT(&dev->vdev), + "guest-stats-polling-interval", &error_abort); +} + +static const VirtioPCIDeviceTypeInfo virtio_balloon_pci_info = { + .base_name = TYPE_VIRTIO_BALLOON_PCI, + .generic_name = "virtio-balloon-pci", + .transitional_name = "virtio-balloon-pci-transitional", + .non_transitional_name = "virtio-balloon-pci-non-transitional", + .instance_size = sizeof(VirtIOBalloonPCI), + .instance_init = virtio_balloon_pci_instance_init, + .class_init = virtio_balloon_pci_class_init, +}; + +static void virtio_balloon_pci_register(void) +{ + virtio_pci_types_register(&virtio_balloon_pci_info); +} + +type_init(virtio_balloon_pci_register) diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c index 1728e4f83a..a12677d4d5 100644 --- a/hw/virtio/virtio-balloon.c +++ b/hw/virtio/virtio-balloon.c @@ -311,7 +311,7 @@ out: static void virtio_balloon_get_config(VirtIODevice *vdev, uint8_t *config_data) { VirtIOBalloon *dev = VIRTIO_BALLOON(vdev); - struct virtio_balloon_config config; + struct virtio_balloon_config config = {}; config.num_pages = cpu_to_le32(dev->num_pages); config.actual = cpu_to_le32(dev->actual); diff --git a/hw/virtio/virtio-blk-pci.c b/hw/virtio/virtio-blk-pci.c new file mode 100644 index 0000000000..60c9185c39 --- /dev/null +++ b/hw/virtio/virtio-blk-pci.c @@ -0,0 +1,100 @@ +/* + * Virtio blk PCI Bindings + * + * Copyright IBM, Corp. 2007 + * Copyright (c) 2009 CodeSourcery + * + * Authors: + * Anthony Liguori <aliguori@us.ibm.com> + * Paul Brook <paul@codesourcery.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Contributions after 2012-01-13 are licensed under the terms of the + * GNU GPL, version 2 or (at your option) any later version. + */ + +#include "qemu/osdep.h" + +#include "hw/virtio/virtio-blk.h" +#include "virtio-pci.h" +#include "qapi/error.h" + +typedef struct VirtIOBlkPCI VirtIOBlkPCI; + +/* + * virtio-blk-pci: This extends VirtioPCIProxy. + */ +#define TYPE_VIRTIO_BLK_PCI "virtio-blk-pci-base" +#define VIRTIO_BLK_PCI(obj) \ + OBJECT_CHECK(VirtIOBlkPCI, (obj), TYPE_VIRTIO_BLK_PCI) + +struct VirtIOBlkPCI { + VirtIOPCIProxy parent_obj; + VirtIOBlock vdev; +}; + +static Property virtio_blk_pci_properties[] = { + DEFINE_PROP_UINT32("class", VirtIOPCIProxy, class_code, 0), + DEFINE_PROP_BIT("ioeventfd", VirtIOPCIProxy, flags, + VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT, true), + DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, + DEV_NVECTORS_UNSPECIFIED), + DEFINE_PROP_END_OF_LIST(), +}; + +static void virtio_blk_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) +{ + VirtIOBlkPCI *dev = VIRTIO_BLK_PCI(vpci_dev); + DeviceState *vdev = DEVICE(&dev->vdev); + + if (vpci_dev->nvectors == DEV_NVECTORS_UNSPECIFIED) { + vpci_dev->nvectors = dev->vdev.conf.num_queues + 1; + } + + qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); + object_property_set_bool(OBJECT(vdev), true, "realized", errp); +} + +static void virtio_blk_pci_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); + PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); + + set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); + dc->props = virtio_blk_pci_properties; + k->realize = virtio_blk_pci_realize; + pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; + pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_BLOCK; + pcidev_k->revision = VIRTIO_PCI_ABI_VERSION; + pcidev_k->class_id = PCI_CLASS_STORAGE_SCSI; +} + +static void virtio_blk_pci_instance_init(Object *obj) +{ + VirtIOBlkPCI *dev = VIRTIO_BLK_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VIRTIO_BLK); + object_property_add_alias(obj, "bootindex", OBJECT(&dev->vdev), + "bootindex", &error_abort); +} + +static const VirtioPCIDeviceTypeInfo virtio_blk_pci_info = { + .base_name = TYPE_VIRTIO_BLK_PCI, + .generic_name = "virtio-blk-pci", + .transitional_name = "virtio-blk-pci-transitional", + .non_transitional_name = "virtio-blk-pci-non-transitional", + .instance_size = sizeof(VirtIOBlkPCI), + .instance_init = virtio_blk_pci_instance_init, + .class_init = virtio_blk_pci_class_init, +}; + +static void virtio_blk_pci_register(void) +{ + virtio_pci_types_register(&virtio_blk_pci_info); +} + +type_init(virtio_blk_pci_register) diff --git a/hw/virtio/virtio-crypto-pci.c b/hw/virtio/virtio-crypto-pci.c index 8cc3fa3ef7..90a6e0dc2e 100644 --- a/hw/virtio/virtio-crypto-pci.c +++ b/hw/virtio/virtio-crypto-pci.c @@ -19,6 +19,20 @@ #include "hw/virtio/virtio-crypto.h" #include "qapi/error.h" +typedef struct VirtIOCryptoPCI VirtIOCryptoPCI; + +/* + * virtio-crypto-pci: This extends VirtioPCIProxy. + */ +#define TYPE_VIRTIO_CRYPTO_PCI "virtio-crypto-pci" +#define VIRTIO_CRYPTO_PCI(obj) \ + OBJECT_CHECK(VirtIOCryptoPCI, (obj), TYPE_VIRTIO_CRYPTO_PCI) + +struct VirtIOCryptoPCI { + VirtIOPCIProxy parent_obj; + VirtIOCrypto vdev; +}; + static Property virtio_crypto_pci_properties[] = { DEFINE_PROP_BIT("ioeventfd", VirtIOPCIProxy, flags, VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT, true), diff --git a/hw/virtio/virtio-input-host-pci.c b/hw/virtio/virtio-input-host-pci.c new file mode 100644 index 0000000000..725a51ad30 --- /dev/null +++ b/hw/virtio/virtio-input-host-pci.c @@ -0,0 +1,48 @@ +/* + * Virtio input host PCI Bindings + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * (at your option) any later version. See the COPYING file in the + * top-level directory. + */ + +#include "qemu/osdep.h" + +#include "virtio-pci.h" +#include "hw/virtio/virtio-input.h" + +typedef struct VirtIOInputHostPCI VirtIOInputHostPCI; + +#define TYPE_VIRTIO_INPUT_HOST_PCI "virtio-input-host-pci-base" +#define VIRTIO_INPUT_HOST_PCI(obj) \ + OBJECT_CHECK(VirtIOInputHostPCI, (obj), TYPE_VIRTIO_INPUT_HOST_PCI) + +struct VirtIOInputHostPCI { + VirtIOPCIProxy parent_obj; + VirtIOInputHost vdev; +}; + +static void virtio_host_initfn(Object *obj) +{ + VirtIOInputHostPCI *dev = VIRTIO_INPUT_HOST_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VIRTIO_INPUT_HOST); +} + +static const VirtioPCIDeviceTypeInfo virtio_input_host_pci_info = { + .base_name = TYPE_VIRTIO_INPUT_HOST_PCI, + .generic_name = "virtio-input-host-pci", + .transitional_name = "virtio-input-host-pci-transitional", + .non_transitional_name = "virtio-input-host-pci-non-transitional", + .parent = TYPE_VIRTIO_INPUT_PCI, + .instance_size = sizeof(VirtIOInputHostPCI), + .instance_init = virtio_host_initfn, +}; + +static void virtio_input_host_pci_register(void) +{ + virtio_pci_types_register(&virtio_input_host_pci_info); +} + +type_init(virtio_input_host_pci_register) diff --git a/hw/virtio/virtio-input-pci.c b/hw/virtio/virtio-input-pci.c new file mode 100644 index 0000000000..2c1397842b --- /dev/null +++ b/hw/virtio/virtio-input-pci.c @@ -0,0 +1,157 @@ +/* + * Virtio input PCI Bindings + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * (at your option) any later version. See the COPYING file in the + * top-level directory. + */ + +#include "qemu/osdep.h" + +#include "virtio-pci.h" +#include "hw/virtio/virtio-input.h" + +typedef struct VirtIOInputPCI VirtIOInputPCI; +typedef struct VirtIOInputHIDPCI VirtIOInputHIDPCI; + +/* + * virtio-input-pci: This extends VirtioPCIProxy. + */ +#define VIRTIO_INPUT_PCI(obj) \ + OBJECT_CHECK(VirtIOInputPCI, (obj), TYPE_VIRTIO_INPUT_PCI) + +struct VirtIOInputPCI { + VirtIOPCIProxy parent_obj; + VirtIOInput vdev; +}; + +#define TYPE_VIRTIO_INPUT_HID_PCI "virtio-input-hid-pci" +#define TYPE_VIRTIO_KEYBOARD_PCI "virtio-keyboard-pci" +#define TYPE_VIRTIO_MOUSE_PCI "virtio-mouse-pci" +#define TYPE_VIRTIO_TABLET_PCI "virtio-tablet-pci" +#define VIRTIO_INPUT_HID_PCI(obj) \ + OBJECT_CHECK(VirtIOInputHIDPCI, (obj), TYPE_VIRTIO_INPUT_HID_PCI) + +struct VirtIOInputHIDPCI { + VirtIOPCIProxy parent_obj; + VirtIOInputHID vdev; +}; + +static Property virtio_input_pci_properties[] = { + DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 2), + DEFINE_PROP_END_OF_LIST(), +}; + +static void virtio_input_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) +{ + VirtIOInputPCI *vinput = VIRTIO_INPUT_PCI(vpci_dev); + DeviceState *vdev = DEVICE(&vinput->vdev); + + qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); + virtio_pci_force_virtio_1(vpci_dev); + object_property_set_bool(OBJECT(vdev), true, "realized", errp); +} + +static void virtio_input_pci_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); + PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); + + dc->props = virtio_input_pci_properties; + k->realize = virtio_input_pci_realize; + set_bit(DEVICE_CATEGORY_INPUT, dc->categories); + + pcidev_k->class_id = PCI_CLASS_INPUT_OTHER; +} + +static void virtio_input_hid_kbd_pci_class_init(ObjectClass *klass, void *data) +{ + PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); + + pcidev_k->class_id = PCI_CLASS_INPUT_KEYBOARD; +} + +static void virtio_input_hid_mouse_pci_class_init(ObjectClass *klass, + void *data) +{ + PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); + + pcidev_k->class_id = PCI_CLASS_INPUT_MOUSE; +} + +static void virtio_keyboard_initfn(Object *obj) +{ + VirtIOInputHIDPCI *dev = VIRTIO_INPUT_HID_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VIRTIO_KEYBOARD); +} + +static void virtio_mouse_initfn(Object *obj) +{ + VirtIOInputHIDPCI *dev = VIRTIO_INPUT_HID_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VIRTIO_MOUSE); +} + +static void virtio_tablet_initfn(Object *obj) +{ + VirtIOInputHIDPCI *dev = VIRTIO_INPUT_HID_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VIRTIO_TABLET); +} + +static const TypeInfo virtio_input_pci_info = { + .name = TYPE_VIRTIO_INPUT_PCI, + .parent = TYPE_VIRTIO_PCI, + .instance_size = sizeof(VirtIOInputPCI), + .class_init = virtio_input_pci_class_init, + .abstract = true, +}; + +static const TypeInfo virtio_input_hid_pci_info = { + .name = TYPE_VIRTIO_INPUT_HID_PCI, + .parent = TYPE_VIRTIO_INPUT_PCI, + .instance_size = sizeof(VirtIOInputHIDPCI), + .abstract = true, +}; + +static const VirtioPCIDeviceTypeInfo virtio_keyboard_pci_info = { + .generic_name = TYPE_VIRTIO_KEYBOARD_PCI, + .parent = TYPE_VIRTIO_INPUT_HID_PCI, + .class_init = virtio_input_hid_kbd_pci_class_init, + .instance_size = sizeof(VirtIOInputHIDPCI), + .instance_init = virtio_keyboard_initfn, +}; + +static const VirtioPCIDeviceTypeInfo virtio_mouse_pci_info = { + .generic_name = TYPE_VIRTIO_MOUSE_PCI, + .parent = TYPE_VIRTIO_INPUT_HID_PCI, + .class_init = virtio_input_hid_mouse_pci_class_init, + .instance_size = sizeof(VirtIOInputHIDPCI), + .instance_init = virtio_mouse_initfn, +}; + +static const VirtioPCIDeviceTypeInfo virtio_tablet_pci_info = { + .generic_name = TYPE_VIRTIO_TABLET_PCI, + .parent = TYPE_VIRTIO_INPUT_HID_PCI, + .instance_size = sizeof(VirtIOInputHIDPCI), + .instance_init = virtio_tablet_initfn, +}; + +static void virtio_pci_input_register(void) +{ + /* Base types: */ + type_register_static(&virtio_input_pci_info); + type_register_static(&virtio_input_hid_pci_info); + + /* Implementations: */ + virtio_pci_types_register(&virtio_keyboard_pci_info); + virtio_pci_types_register(&virtio_mouse_pci_info); + virtio_pci_types_register(&virtio_tablet_pci_info); +} + +type_init(virtio_pci_input_register) diff --git a/hw/virtio/virtio-net-pci.c b/hw/virtio/virtio-net-pci.c new file mode 100644 index 0000000000..db07ab9e21 --- /dev/null +++ b/hw/virtio/virtio-net-pci.c @@ -0,0 +1,98 @@ +/* + * Virtio net PCI Bindings + * + * Copyright IBM, Corp. 2007 + * Copyright (c) 2009 CodeSourcery + * + * Authors: + * Anthony Liguori <aliguori@us.ibm.com> + * Paul Brook <paul@codesourcery.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Contributions after 2012-01-13 are licensed under the terms of the + * GNU GPL, version 2 or (at your option) any later version. + */ + +#include "qemu/osdep.h" + +#include "hw/virtio/virtio-net.h" +#include "virtio-pci.h" +#include "qapi/error.h" + +typedef struct VirtIONetPCI VirtIONetPCI; + +/* + * virtio-net-pci: This extends VirtioPCIProxy. + */ +#define TYPE_VIRTIO_NET_PCI "virtio-net-pci-base" +#define VIRTIO_NET_PCI(obj) \ + OBJECT_CHECK(VirtIONetPCI, (obj), TYPE_VIRTIO_NET_PCI) + +struct VirtIONetPCI { + VirtIOPCIProxy parent_obj; + VirtIONet vdev; +}; + +static Property virtio_net_properties[] = { + DEFINE_PROP_BIT("ioeventfd", VirtIOPCIProxy, flags, + VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT, true), + DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 3), + DEFINE_PROP_END_OF_LIST(), +}; + +static void virtio_net_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) +{ + DeviceState *qdev = DEVICE(vpci_dev); + VirtIONetPCI *dev = VIRTIO_NET_PCI(vpci_dev); + DeviceState *vdev = DEVICE(&dev->vdev); + + virtio_net_set_netclient_name(&dev->vdev, qdev->id, + object_get_typename(OBJECT(qdev))); + qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); + object_property_set_bool(OBJECT(vdev), true, "realized", errp); +} + +static void virtio_net_pci_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + PCIDeviceClass *k = PCI_DEVICE_CLASS(klass); + VirtioPCIClass *vpciklass = VIRTIO_PCI_CLASS(klass); + + k->romfile = "efi-virtio.rom"; + k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; + k->device_id = PCI_DEVICE_ID_VIRTIO_NET; + k->revision = VIRTIO_PCI_ABI_VERSION; + k->class_id = PCI_CLASS_NETWORK_ETHERNET; + set_bit(DEVICE_CATEGORY_NETWORK, dc->categories); + dc->props = virtio_net_properties; + vpciklass->realize = virtio_net_pci_realize; +} + +static void virtio_net_pci_instance_init(Object *obj) +{ + VirtIONetPCI *dev = VIRTIO_NET_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VIRTIO_NET); + object_property_add_alias(obj, "bootindex", OBJECT(&dev->vdev), + "bootindex", &error_abort); +} + +static const VirtioPCIDeviceTypeInfo virtio_net_pci_info = { + .base_name = TYPE_VIRTIO_NET_PCI, + .generic_name = "virtio-net-pci", + .transitional_name = "virtio-net-pci-transitional", + .non_transitional_name = "virtio-net-pci-non-transitional", + .instance_size = sizeof(VirtIONetPCI), + .instance_init = virtio_net_pci_instance_init, + .class_init = virtio_net_pci_class_init, +}; + +static void virtio_net_pci_register(void) +{ + virtio_pci_types_register(&virtio_net_pci_info); +} + +type_init(virtio_net_pci_register) diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c index d05066deb8..b282109343 100644 --- a/hw/virtio/virtio-pci.c +++ b/hw/virtio/virtio-pci.c @@ -19,12 +19,6 @@ #include "standard-headers/linux/virtio_pci.h" #include "hw/virtio/virtio.h" -#include "hw/virtio/virtio-blk.h" -#include "hw/virtio/virtio-net.h" -#include "hw/virtio/virtio-serial.h" -#include "hw/virtio/virtio-scsi.h" -#include "hw/virtio/virtio-balloon.h" -#include "hw/virtio/virtio-input.h" #include "hw/pci/pci.h" #include "qapi/error.h" #include "qemu/error-report.h" @@ -1079,57 +1073,6 @@ static void virtio_pci_vmstate_change(DeviceState *d, bool running) } } -#ifdef CONFIG_VIRTFS -static void virtio_9p_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) -{ - V9fsPCIState *dev = VIRTIO_9P_PCI(vpci_dev); - DeviceState *vdev = DEVICE(&dev->vdev); - - qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); - object_property_set_bool(OBJECT(vdev), true, "realized", errp); -} - -static Property virtio_9p_pci_properties[] = { - DEFINE_PROP_BIT("ioeventfd", VirtIOPCIProxy, flags, - VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT, true), - DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 2), - DEFINE_PROP_END_OF_LIST(), -}; - -static void virtio_9p_pci_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); - VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); - - k->realize = virtio_9p_pci_realize; - pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; - pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_9P; - pcidev_k->revision = VIRTIO_PCI_ABI_VERSION; - pcidev_k->class_id = 0x2; - set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); - dc->props = virtio_9p_pci_properties; -} - -static void virtio_9p_pci_instance_init(Object *obj) -{ - V9fsPCIState *dev = VIRTIO_9P_PCI(obj); - - virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), - TYPE_VIRTIO_9P); -} - -static const VirtioPCIDeviceTypeInfo virtio_9p_pci_info = { - .base_name = TYPE_VIRTIO_9P_PCI, - .generic_name = "virtio-9p-pci", - .transitional_name = "virtio-9p-pci-transitional", - .non_transitional_name = "virtio-9p-pci-non-transitional", - .instance_size = sizeof(V9fsPCIState), - .instance_init = virtio_9p_pci_instance_init, - .class_init = virtio_9p_pci_class_init, -}; -#endif /* CONFIG_VIRTFS */ - /* * virtio-pci: This is the PCIDevice which has a virtio-pci-bus. */ @@ -2055,728 +1998,6 @@ void virtio_pci_types_register(const VirtioPCIDeviceTypeInfo *t) } } -/* virtio-blk-pci */ - -static Property virtio_blk_pci_properties[] = { - DEFINE_PROP_UINT32("class", VirtIOPCIProxy, class_code, 0), - DEFINE_PROP_BIT("ioeventfd", VirtIOPCIProxy, flags, - VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT, true), - DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, - DEV_NVECTORS_UNSPECIFIED), - DEFINE_PROP_END_OF_LIST(), -}; - -static void virtio_blk_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) -{ - VirtIOBlkPCI *dev = VIRTIO_BLK_PCI(vpci_dev); - DeviceState *vdev = DEVICE(&dev->vdev); - - if (vpci_dev->nvectors == DEV_NVECTORS_UNSPECIFIED) { - vpci_dev->nvectors = dev->vdev.conf.num_queues + 1; - } - - qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); - object_property_set_bool(OBJECT(vdev), true, "realized", errp); -} - -static void virtio_blk_pci_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); - PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); - - set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); - dc->props = virtio_blk_pci_properties; - k->realize = virtio_blk_pci_realize; - pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; - pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_BLOCK; - pcidev_k->revision = VIRTIO_PCI_ABI_VERSION; - pcidev_k->class_id = PCI_CLASS_STORAGE_SCSI; -} - -static void virtio_blk_pci_instance_init(Object *obj) -{ - VirtIOBlkPCI *dev = VIRTIO_BLK_PCI(obj); - - virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), - TYPE_VIRTIO_BLK); - object_property_add_alias(obj, "bootindex", OBJECT(&dev->vdev), - "bootindex", &error_abort); -} - -static const VirtioPCIDeviceTypeInfo virtio_blk_pci_info = { - .base_name = TYPE_VIRTIO_BLK_PCI, - .generic_name = "virtio-blk-pci", - .transitional_name = "virtio-blk-pci-transitional", - .non_transitional_name = "virtio-blk-pci-non-transitional", - .instance_size = sizeof(VirtIOBlkPCI), - .instance_init = virtio_blk_pci_instance_init, - .class_init = virtio_blk_pci_class_init, -}; - -#if defined(CONFIG_VHOST_USER) && defined(CONFIG_LINUX) -/* vhost-user-blk */ - -static Property vhost_user_blk_pci_properties[] = { - DEFINE_PROP_UINT32("class", VirtIOPCIProxy, class_code, 0), - DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, - DEV_NVECTORS_UNSPECIFIED), - DEFINE_PROP_END_OF_LIST(), -}; - -static void vhost_user_blk_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) -{ - VHostUserBlkPCI *dev = VHOST_USER_BLK_PCI(vpci_dev); - DeviceState *vdev = DEVICE(&dev->vdev); - - if (vpci_dev->nvectors == DEV_NVECTORS_UNSPECIFIED) { - vpci_dev->nvectors = dev->vdev.num_queues + 1; - } - - qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); - object_property_set_bool(OBJECT(vdev), true, "realized", errp); -} - -static void vhost_user_blk_pci_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); - PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); - - set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); - dc->props = vhost_user_blk_pci_properties; - k->realize = vhost_user_blk_pci_realize; - pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; - pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_BLOCK; - pcidev_k->revision = VIRTIO_PCI_ABI_VERSION; - pcidev_k->class_id = PCI_CLASS_STORAGE_SCSI; -} - -static void vhost_user_blk_pci_instance_init(Object *obj) -{ - VHostUserBlkPCI *dev = VHOST_USER_BLK_PCI(obj); - - virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), - TYPE_VHOST_USER_BLK); - object_property_add_alias(obj, "bootindex", OBJECT(&dev->vdev), - "bootindex", &error_abort); -} - -static const VirtioPCIDeviceTypeInfo vhost_user_blk_pci_info = { - .base_name = TYPE_VHOST_USER_BLK_PCI, - .generic_name = "vhost-user-blk-pci", - .transitional_name = "vhost-user-blk-pci-transitional", - .non_transitional_name = "vhost-user-blk-pci-non-transitional", - .instance_size = sizeof(VHostUserBlkPCI), - .instance_init = vhost_user_blk_pci_instance_init, - .class_init = vhost_user_blk_pci_class_init, -}; -#endif - -/* virtio-scsi-pci */ - -static Property virtio_scsi_pci_properties[] = { - DEFINE_PROP_BIT("ioeventfd", VirtIOPCIProxy, flags, - VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT, true), - DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, - DEV_NVECTORS_UNSPECIFIED), - DEFINE_PROP_END_OF_LIST(), -}; - -static void virtio_scsi_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) -{ - VirtIOSCSIPCI *dev = VIRTIO_SCSI_PCI(vpci_dev); - DeviceState *vdev = DEVICE(&dev->vdev); - VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(vdev); - DeviceState *proxy = DEVICE(vpci_dev); - char *bus_name; - - if (vpci_dev->nvectors == DEV_NVECTORS_UNSPECIFIED) { - vpci_dev->nvectors = vs->conf.num_queues + 3; - } - - /* - * For command line compatibility, this sets the virtio-scsi-device bus - * name as before. - */ - if (proxy->id) { - bus_name = g_strdup_printf("%s.0", proxy->id); - virtio_device_set_child_bus_name(VIRTIO_DEVICE(vdev), bus_name); - g_free(bus_name); - } - - qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); - object_property_set_bool(OBJECT(vdev), true, "realized", errp); -} - -static void virtio_scsi_pci_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); - PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); - - k->realize = virtio_scsi_pci_realize; - set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); - dc->props = virtio_scsi_pci_properties; - pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; - pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_SCSI; - pcidev_k->revision = 0x00; - pcidev_k->class_id = PCI_CLASS_STORAGE_SCSI; -} - -static void virtio_scsi_pci_instance_init(Object *obj) -{ - VirtIOSCSIPCI *dev = VIRTIO_SCSI_PCI(obj); - - virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), - TYPE_VIRTIO_SCSI); -} - -static const VirtioPCIDeviceTypeInfo virtio_scsi_pci_info = { - .base_name = TYPE_VIRTIO_SCSI_PCI, - .generic_name = "virtio-scsi-pci", - .transitional_name = "virtio-scsi-pci-transitional", - .non_transitional_name = "virtio-scsi-pci-non-transitional", - .instance_size = sizeof(VirtIOSCSIPCI), - .instance_init = virtio_scsi_pci_instance_init, - .class_init = virtio_scsi_pci_class_init, -}; - -/* vhost-scsi-pci */ - -#ifdef CONFIG_VHOST_SCSI -static Property vhost_scsi_pci_properties[] = { - DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, - DEV_NVECTORS_UNSPECIFIED), - DEFINE_PROP_END_OF_LIST(), -}; - -static void vhost_scsi_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) -{ - VHostSCSIPCI *dev = VHOST_SCSI_PCI(vpci_dev); - DeviceState *vdev = DEVICE(&dev->vdev); - VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(vdev); - - if (vpci_dev->nvectors == DEV_NVECTORS_UNSPECIFIED) { - vpci_dev->nvectors = vs->conf.num_queues + 3; - } - - qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); - object_property_set_bool(OBJECT(vdev), true, "realized", errp); -} - -static void vhost_scsi_pci_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); - PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); - k->realize = vhost_scsi_pci_realize; - set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); - dc->props = vhost_scsi_pci_properties; - pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; - pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_SCSI; - pcidev_k->revision = 0x00; - pcidev_k->class_id = PCI_CLASS_STORAGE_SCSI; -} - -static void vhost_scsi_pci_instance_init(Object *obj) -{ - VHostSCSIPCI *dev = VHOST_SCSI_PCI(obj); - - virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), - TYPE_VHOST_SCSI); - object_property_add_alias(obj, "bootindex", OBJECT(&dev->vdev), - "bootindex", &error_abort); -} - -static const VirtioPCIDeviceTypeInfo vhost_scsi_pci_info = { - .base_name = TYPE_VHOST_SCSI_PCI, - .generic_name = "vhost-scsi-pci", - .transitional_name = "vhost-scsi-pci-transitional", - .non_transitional_name = "vhost-scsi-pci-non-transitional", - .instance_size = sizeof(VHostSCSIPCI), - .instance_init = vhost_scsi_pci_instance_init, - .class_init = vhost_scsi_pci_class_init, -}; -#endif - -#if defined(CONFIG_VHOST_USER) && defined(CONFIG_LINUX) -/* vhost-user-scsi-pci */ -static Property vhost_user_scsi_pci_properties[] = { - DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, - DEV_NVECTORS_UNSPECIFIED), - DEFINE_PROP_END_OF_LIST(), -}; - -static void vhost_user_scsi_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) -{ - VHostUserSCSIPCI *dev = VHOST_USER_SCSI_PCI(vpci_dev); - DeviceState *vdev = DEVICE(&dev->vdev); - VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(vdev); - - if (vpci_dev->nvectors == DEV_NVECTORS_UNSPECIFIED) { - vpci_dev->nvectors = vs->conf.num_queues + 3; - } - - qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); - object_property_set_bool(OBJECT(vdev), true, "realized", errp); -} - -static void vhost_user_scsi_pci_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); - PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); - k->realize = vhost_user_scsi_pci_realize; - set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); - dc->props = vhost_user_scsi_pci_properties; - pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; - pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_SCSI; - pcidev_k->revision = 0x00; - pcidev_k->class_id = PCI_CLASS_STORAGE_SCSI; -} - -static void vhost_user_scsi_pci_instance_init(Object *obj) -{ - VHostUserSCSIPCI *dev = VHOST_USER_SCSI_PCI(obj); - - virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), - TYPE_VHOST_USER_SCSI); - object_property_add_alias(obj, "bootindex", OBJECT(&dev->vdev), - "bootindex", &error_abort); -} - -static const VirtioPCIDeviceTypeInfo vhost_user_scsi_pci_info = { - .base_name = TYPE_VHOST_USER_SCSI_PCI, - .generic_name = "vhost-user-scsi-pci", - .transitional_name = "vhost-user-scsi-pci-transitional", - .non_transitional_name = "vhost-user-scsi-pci-non-transitional", - .instance_size = sizeof(VHostUserSCSIPCI), - .instance_init = vhost_user_scsi_pci_instance_init, - .class_init = vhost_user_scsi_pci_class_init, -}; -#endif - -/* vhost-vsock-pci */ - -#ifdef CONFIG_VHOST_VSOCK -static Property vhost_vsock_pci_properties[] = { - DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 3), - DEFINE_PROP_END_OF_LIST(), -}; - -static void vhost_vsock_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) -{ - VHostVSockPCI *dev = VHOST_VSOCK_PCI(vpci_dev); - DeviceState *vdev = DEVICE(&dev->vdev); - - qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); - object_property_set_bool(OBJECT(vdev), true, "realized", errp); -} - -static void vhost_vsock_pci_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); - PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); - k->realize = vhost_vsock_pci_realize; - set_bit(DEVICE_CATEGORY_MISC, dc->categories); - dc->props = vhost_vsock_pci_properties; - pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; - pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_VSOCK; - pcidev_k->revision = 0x00; - pcidev_k->class_id = PCI_CLASS_COMMUNICATION_OTHER; -} - -static void vhost_vsock_pci_instance_init(Object *obj) -{ - VHostVSockPCI *dev = VHOST_VSOCK_PCI(obj); - - virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), - TYPE_VHOST_VSOCK); -} - -static const VirtioPCIDeviceTypeInfo vhost_vsock_pci_info = { - .base_name = TYPE_VHOST_VSOCK_PCI, - .generic_name = "vhost-vsock-pci", - .transitional_name = "vhost-vsock-pci-transitional", - .non_transitional_name = "vhost-vsock-pci-non-transitional", - .instance_size = sizeof(VHostVSockPCI), - .instance_init = vhost_vsock_pci_instance_init, - .class_init = vhost_vsock_pci_class_init, -}; -#endif - -/* virtio-balloon-pci */ - -static Property virtio_balloon_pci_properties[] = { - DEFINE_PROP_UINT32("class", VirtIOPCIProxy, class_code, 0), - DEFINE_PROP_END_OF_LIST(), -}; - -static void virtio_balloon_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) -{ - VirtIOBalloonPCI *dev = VIRTIO_BALLOON_PCI(vpci_dev); - DeviceState *vdev = DEVICE(&dev->vdev); - - if (vpci_dev->class_code != PCI_CLASS_OTHERS && - vpci_dev->class_code != PCI_CLASS_MEMORY_RAM) { /* qemu < 1.1 */ - vpci_dev->class_code = PCI_CLASS_OTHERS; - } - - qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); - object_property_set_bool(OBJECT(vdev), true, "realized", errp); -} - -static void virtio_balloon_pci_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); - PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); - k->realize = virtio_balloon_pci_realize; - set_bit(DEVICE_CATEGORY_MISC, dc->categories); - dc->props = virtio_balloon_pci_properties; - pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; - pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_BALLOON; - pcidev_k->revision = VIRTIO_PCI_ABI_VERSION; - pcidev_k->class_id = PCI_CLASS_OTHERS; -} - -static void virtio_balloon_pci_instance_init(Object *obj) -{ - VirtIOBalloonPCI *dev = VIRTIO_BALLOON_PCI(obj); - - virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), - TYPE_VIRTIO_BALLOON); - object_property_add_alias(obj, "guest-stats", OBJECT(&dev->vdev), - "guest-stats", &error_abort); - object_property_add_alias(obj, "guest-stats-polling-interval", - OBJECT(&dev->vdev), - "guest-stats-polling-interval", &error_abort); -} - -static const VirtioPCIDeviceTypeInfo virtio_balloon_pci_info = { - .base_name = TYPE_VIRTIO_BALLOON_PCI, - .generic_name = "virtio-balloon-pci", - .transitional_name = "virtio-balloon-pci-transitional", - .non_transitional_name = "virtio-balloon-pci-non-transitional", - .instance_size = sizeof(VirtIOBalloonPCI), - .instance_init = virtio_balloon_pci_instance_init, - .class_init = virtio_balloon_pci_class_init, -}; - -/* virtio-serial-pci */ - -static void virtio_serial_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) -{ - VirtIOSerialPCI *dev = VIRTIO_SERIAL_PCI(vpci_dev); - DeviceState *vdev = DEVICE(&dev->vdev); - DeviceState *proxy = DEVICE(vpci_dev); - char *bus_name; - - if (vpci_dev->class_code != PCI_CLASS_COMMUNICATION_OTHER && - vpci_dev->class_code != PCI_CLASS_DISPLAY_OTHER && /* qemu 0.10 */ - vpci_dev->class_code != PCI_CLASS_OTHERS) { /* qemu-kvm */ - vpci_dev->class_code = PCI_CLASS_COMMUNICATION_OTHER; - } - - /* backwards-compatibility with machines that were created with - DEV_NVECTORS_UNSPECIFIED */ - if (vpci_dev->nvectors == DEV_NVECTORS_UNSPECIFIED) { - vpci_dev->nvectors = dev->vdev.serial.max_virtserial_ports + 1; - } - - /* - * For command line compatibility, this sets the virtio-serial-device bus - * name as before. - */ - if (proxy->id) { - bus_name = g_strdup_printf("%s.0", proxy->id); - virtio_device_set_child_bus_name(VIRTIO_DEVICE(vdev), bus_name); - g_free(bus_name); - } - - qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); - object_property_set_bool(OBJECT(vdev), true, "realized", errp); -} - -static Property virtio_serial_pci_properties[] = { - DEFINE_PROP_BIT("ioeventfd", VirtIOPCIProxy, flags, - VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT, true), - DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 2), - DEFINE_PROP_UINT32("class", VirtIOPCIProxy, class_code, 0), - DEFINE_PROP_END_OF_LIST(), -}; - -static void virtio_serial_pci_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); - PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); - k->realize = virtio_serial_pci_realize; - set_bit(DEVICE_CATEGORY_INPUT, dc->categories); - dc->props = virtio_serial_pci_properties; - pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; - pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_CONSOLE; - pcidev_k->revision = VIRTIO_PCI_ABI_VERSION; - pcidev_k->class_id = PCI_CLASS_COMMUNICATION_OTHER; -} - -static void virtio_serial_pci_instance_init(Object *obj) -{ - VirtIOSerialPCI *dev = VIRTIO_SERIAL_PCI(obj); - - virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), - TYPE_VIRTIO_SERIAL); -} - -static const VirtioPCIDeviceTypeInfo virtio_serial_pci_info = { - .base_name = TYPE_VIRTIO_SERIAL_PCI, - .generic_name = "virtio-serial-pci", - .transitional_name = "virtio-serial-pci-transitional", - .non_transitional_name = "virtio-serial-pci-non-transitional", - .instance_size = sizeof(VirtIOSerialPCI), - .instance_init = virtio_serial_pci_instance_init, - .class_init = virtio_serial_pci_class_init, -}; - -/* virtio-net-pci */ - -static Property virtio_net_properties[] = { - DEFINE_PROP_BIT("ioeventfd", VirtIOPCIProxy, flags, - VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT, true), - DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 3), - DEFINE_PROP_END_OF_LIST(), -}; - -static void virtio_net_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) -{ - DeviceState *qdev = DEVICE(vpci_dev); - VirtIONetPCI *dev = VIRTIO_NET_PCI(vpci_dev); - DeviceState *vdev = DEVICE(&dev->vdev); - - virtio_net_set_netclient_name(&dev->vdev, qdev->id, - object_get_typename(OBJECT(qdev))); - qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); - object_property_set_bool(OBJECT(vdev), true, "realized", errp); -} - -static void virtio_net_pci_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - PCIDeviceClass *k = PCI_DEVICE_CLASS(klass); - VirtioPCIClass *vpciklass = VIRTIO_PCI_CLASS(klass); - - k->romfile = "efi-virtio.rom"; - k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; - k->device_id = PCI_DEVICE_ID_VIRTIO_NET; - k->revision = VIRTIO_PCI_ABI_VERSION; - k->class_id = PCI_CLASS_NETWORK_ETHERNET; - set_bit(DEVICE_CATEGORY_NETWORK, dc->categories); - dc->props = virtio_net_properties; - vpciklass->realize = virtio_net_pci_realize; -} - -static void virtio_net_pci_instance_init(Object *obj) -{ - VirtIONetPCI *dev = VIRTIO_NET_PCI(obj); - - virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), - TYPE_VIRTIO_NET); - object_property_add_alias(obj, "bootindex", OBJECT(&dev->vdev), - "bootindex", &error_abort); -} - -static const VirtioPCIDeviceTypeInfo virtio_net_pci_info = { - .base_name = TYPE_VIRTIO_NET_PCI, - .generic_name = "virtio-net-pci", - .transitional_name = "virtio-net-pci-transitional", - .non_transitional_name = "virtio-net-pci-non-transitional", - .instance_size = sizeof(VirtIONetPCI), - .instance_init = virtio_net_pci_instance_init, - .class_init = virtio_net_pci_class_init, -}; - -/* virtio-rng-pci */ - -static void virtio_rng_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) -{ - VirtIORngPCI *vrng = VIRTIO_RNG_PCI(vpci_dev); - DeviceState *vdev = DEVICE(&vrng->vdev); - Error *err = NULL; - - qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); - object_property_set_bool(OBJECT(vdev), true, "realized", &err); - if (err) { - error_propagate(errp, err); - return; - } - - object_property_set_link(OBJECT(vrng), - OBJECT(vrng->vdev.conf.rng), "rng", - NULL); -} - -static void virtio_rng_pci_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); - PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); - - k->realize = virtio_rng_pci_realize; - set_bit(DEVICE_CATEGORY_MISC, dc->categories); - - pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; - pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_RNG; - pcidev_k->revision = VIRTIO_PCI_ABI_VERSION; - pcidev_k->class_id = PCI_CLASS_OTHERS; -} - -static void virtio_rng_initfn(Object *obj) -{ - VirtIORngPCI *dev = VIRTIO_RNG_PCI(obj); - - virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), - TYPE_VIRTIO_RNG); -} - -static const VirtioPCIDeviceTypeInfo virtio_rng_pci_info = { - .base_name = TYPE_VIRTIO_RNG_PCI, - .generic_name = "virtio-rng-pci", - .transitional_name = "virtio-rng-pci-transitional", - .non_transitional_name = "virtio-rng-pci-non-transitional", - .instance_size = sizeof(VirtIORngPCI), - .instance_init = virtio_rng_initfn, - .class_init = virtio_rng_pci_class_init, -}; - -/* virtio-input-pci */ - -static Property virtio_input_pci_properties[] = { - DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 2), - DEFINE_PROP_END_OF_LIST(), -}; - -static void virtio_input_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) -{ - VirtIOInputPCI *vinput = VIRTIO_INPUT_PCI(vpci_dev); - DeviceState *vdev = DEVICE(&vinput->vdev); - - qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); - virtio_pci_force_virtio_1(vpci_dev); - object_property_set_bool(OBJECT(vdev), true, "realized", errp); -} - -static void virtio_input_pci_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); - PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); - - dc->props = virtio_input_pci_properties; - k->realize = virtio_input_pci_realize; - set_bit(DEVICE_CATEGORY_INPUT, dc->categories); - - pcidev_k->class_id = PCI_CLASS_INPUT_OTHER; -} - -static void virtio_input_hid_kbd_pci_class_init(ObjectClass *klass, void *data) -{ - PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); - - pcidev_k->class_id = PCI_CLASS_INPUT_KEYBOARD; -} - -static void virtio_input_hid_mouse_pci_class_init(ObjectClass *klass, - void *data) -{ - PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); - - pcidev_k->class_id = PCI_CLASS_INPUT_MOUSE; -} - -static void virtio_keyboard_initfn(Object *obj) -{ - VirtIOInputHIDPCI *dev = VIRTIO_INPUT_HID_PCI(obj); - - virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), - TYPE_VIRTIO_KEYBOARD); -} - -static void virtio_mouse_initfn(Object *obj) -{ - VirtIOInputHIDPCI *dev = VIRTIO_INPUT_HID_PCI(obj); - - virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), - TYPE_VIRTIO_MOUSE); -} - -static void virtio_tablet_initfn(Object *obj) -{ - VirtIOInputHIDPCI *dev = VIRTIO_INPUT_HID_PCI(obj); - - virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), - TYPE_VIRTIO_TABLET); -} - -static const TypeInfo virtio_input_pci_info = { - .name = TYPE_VIRTIO_INPUT_PCI, - .parent = TYPE_VIRTIO_PCI, - .instance_size = sizeof(VirtIOInputPCI), - .class_init = virtio_input_pci_class_init, - .abstract = true, -}; - -static const TypeInfo virtio_input_hid_pci_info = { - .name = TYPE_VIRTIO_INPUT_HID_PCI, - .parent = TYPE_VIRTIO_INPUT_PCI, - .instance_size = sizeof(VirtIOInputHIDPCI), - .abstract = true, -}; - -static const VirtioPCIDeviceTypeInfo virtio_keyboard_pci_info = { - .generic_name = TYPE_VIRTIO_KEYBOARD_PCI, - .parent = TYPE_VIRTIO_INPUT_HID_PCI, - .class_init = virtio_input_hid_kbd_pci_class_init, - .instance_size = sizeof(VirtIOInputHIDPCI), - .instance_init = virtio_keyboard_initfn, -}; - -static const VirtioPCIDeviceTypeInfo virtio_mouse_pci_info = { - .generic_name = TYPE_VIRTIO_MOUSE_PCI, - .parent = TYPE_VIRTIO_INPUT_HID_PCI, - .class_init = virtio_input_hid_mouse_pci_class_init, - .instance_size = sizeof(VirtIOInputHIDPCI), - .instance_init = virtio_mouse_initfn, -}; - -static const VirtioPCIDeviceTypeInfo virtio_tablet_pci_info = { - .generic_name = TYPE_VIRTIO_TABLET_PCI, - .parent = TYPE_VIRTIO_INPUT_HID_PCI, - .instance_size = sizeof(VirtIOInputHIDPCI), - .instance_init = virtio_tablet_initfn, -}; - -#ifdef CONFIG_LINUX -static void virtio_host_initfn(Object *obj) -{ - VirtIOInputHostPCI *dev = VIRTIO_INPUT_HOST_PCI(obj); - - virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), - TYPE_VIRTIO_INPUT_HOST); -} - -static const VirtioPCIDeviceTypeInfo virtio_host_pci_info = { - .base_name = TYPE_VIRTIO_INPUT_HOST_PCI, - .generic_name = "virtio-input-host-pci", - .transitional_name = "virtio-input-host-pci-transitional", - .non_transitional_name = "virtio-input-host-pci-non-transitional", - .parent = TYPE_VIRTIO_INPUT_PCI, - .instance_size = sizeof(VirtIOInputHostPCI), - .instance_init = virtio_host_initfn, -}; -#endif - /* virtio-pci-bus */ static void virtio_pci_bus_new(VirtioBusState *bus, size_t bus_size, @@ -2827,37 +2048,7 @@ static void virtio_pci_register_types(void) /* Base types: */ type_register_static(&virtio_pci_bus_info); type_register_static(&virtio_pci_info); - type_register_static(&virtio_input_pci_info); - type_register_static(&virtio_input_hid_pci_info); - - /* Implementations: */ - virtio_pci_types_register(&virtio_rng_pci_info); - virtio_pci_types_register(&virtio_keyboard_pci_info); - virtio_pci_types_register(&virtio_mouse_pci_info); - virtio_pci_types_register(&virtio_tablet_pci_info); -#ifdef CONFIG_LINUX - virtio_pci_types_register(&virtio_host_pci_info); -#endif -#ifdef CONFIG_VIRTFS - virtio_pci_types_register(&virtio_9p_pci_info); -#endif - virtio_pci_types_register(&virtio_blk_pci_info); -#if defined(CONFIG_VHOST_USER) && defined(CONFIG_LINUX) - virtio_pci_types_register(&vhost_user_blk_pci_info); -#endif - virtio_pci_types_register(&virtio_scsi_pci_info); - virtio_pci_types_register(&virtio_balloon_pci_info); - virtio_pci_types_register(&virtio_serial_pci_info); - virtio_pci_types_register(&virtio_net_pci_info); -#ifdef CONFIG_VHOST_SCSI - virtio_pci_types_register(&vhost_scsi_pci_info); -#endif -#if defined(CONFIG_VHOST_USER) && defined(CONFIG_LINUX) - virtio_pci_types_register(&vhost_user_scsi_pci_info); -#endif -#ifdef CONFIG_VHOST_VSOCK - virtio_pci_types_register(&vhost_vsock_pci_info); -#endif } type_init(virtio_pci_register_types) + diff --git a/hw/virtio/virtio-pci.h b/hw/virtio/virtio-pci.h index 29b4216107..bd223a6e3b 100644 --- a/hw/virtio/virtio-pci.h +++ b/hw/virtio/virtio-pci.h @@ -16,47 +16,9 @@ #define QEMU_VIRTIO_PCI_H #include "hw/pci/msi.h" -#include "hw/virtio/virtio-blk.h" -#include "hw/virtio/virtio-net.h" -#include "hw/virtio/virtio-rng.h" -#include "hw/virtio/virtio-serial.h" -#include "hw/virtio/virtio-scsi.h" -#include "hw/virtio/virtio-balloon.h" #include "hw/virtio/virtio-bus.h" -#include "hw/virtio/virtio-input.h" -#include "hw/virtio/virtio-gpu.h" -#include "hw/virtio/virtio-crypto.h" -#include "hw/virtio/vhost-user-scsi.h" -#if defined(CONFIG_VHOST_USER) && defined(CONFIG_LINUX) -#include "hw/virtio/vhost-user-blk.h" -#endif - -#ifdef CONFIG_VIRTFS -#include "hw/9pfs/virtio-9p.h" -#endif -#ifdef CONFIG_VHOST_SCSI -#include "hw/virtio/vhost-scsi.h" -#endif -#ifdef CONFIG_VHOST_VSOCK -#include "hw/virtio/vhost-vsock.h" -#endif typedef struct VirtIOPCIProxy VirtIOPCIProxy; -typedef struct VirtIOBlkPCI VirtIOBlkPCI; -typedef struct VirtIOSCSIPCI VirtIOSCSIPCI; -typedef struct VirtIOBalloonPCI VirtIOBalloonPCI; -typedef struct VirtIOSerialPCI VirtIOSerialPCI; -typedef struct VirtIONetPCI VirtIONetPCI; -typedef struct VHostSCSIPCI VHostSCSIPCI; -typedef struct VHostUserSCSIPCI VHostUserSCSIPCI; -typedef struct VHostUserBlkPCI VHostUserBlkPCI; -typedef struct VirtIORngPCI VirtIORngPCI; -typedef struct VirtIOInputPCI VirtIOInputPCI; -typedef struct VirtIOInputHIDPCI VirtIOInputHIDPCI; -typedef struct VirtIOInputHostPCI VirtIOInputHostPCI; -typedef struct VirtIOGPUPCI VirtIOGPUPCI; -typedef struct VHostVSockPCI VHostVSockPCI; -typedef struct VirtIOCryptoPCI VirtIOCryptoPCI; /* virtio-pci-bus */ @@ -214,205 +176,9 @@ static inline void virtio_pci_disable_modern(VirtIOPCIProxy *proxy) } /* - * virtio-scsi-pci: This extends VirtioPCIProxy. - */ -#define TYPE_VIRTIO_SCSI_PCI "virtio-scsi-pci-base" -#define VIRTIO_SCSI_PCI(obj) \ - OBJECT_CHECK(VirtIOSCSIPCI, (obj), TYPE_VIRTIO_SCSI_PCI) - -struct VirtIOSCSIPCI { - VirtIOPCIProxy parent_obj; - VirtIOSCSI vdev; -}; - -#ifdef CONFIG_VHOST_SCSI -/* - * vhost-scsi-pci: This extends VirtioPCIProxy. - */ -#define TYPE_VHOST_SCSI_PCI "vhost-scsi-pci-base" -#define VHOST_SCSI_PCI(obj) \ - OBJECT_CHECK(VHostSCSIPCI, (obj), TYPE_VHOST_SCSI_PCI) - -struct VHostSCSIPCI { - VirtIOPCIProxy parent_obj; - VHostSCSI vdev; -}; -#endif - -#define TYPE_VHOST_USER_SCSI_PCI "vhost-user-scsi-pci-base" -#define VHOST_USER_SCSI_PCI(obj) \ - OBJECT_CHECK(VHostUserSCSIPCI, (obj), TYPE_VHOST_USER_SCSI_PCI) - -struct VHostUserSCSIPCI { - VirtIOPCIProxy parent_obj; - VHostUserSCSI vdev; -}; - -#if defined(CONFIG_VHOST_USER) && defined(CONFIG_LINUX) -/* - * vhost-user-blk-pci: This extends VirtioPCIProxy. - */ -#define TYPE_VHOST_USER_BLK_PCI "vhost-user-blk-pci-base" -#define VHOST_USER_BLK_PCI(obj) \ - OBJECT_CHECK(VHostUserBlkPCI, (obj), TYPE_VHOST_USER_BLK_PCI) - -struct VHostUserBlkPCI { - VirtIOPCIProxy parent_obj; - VHostUserBlk vdev; -}; -#endif - -/* - * virtio-blk-pci: This extends VirtioPCIProxy. - */ -#define TYPE_VIRTIO_BLK_PCI "virtio-blk-pci-base" -#define VIRTIO_BLK_PCI(obj) \ - OBJECT_CHECK(VirtIOBlkPCI, (obj), TYPE_VIRTIO_BLK_PCI) - -struct VirtIOBlkPCI { - VirtIOPCIProxy parent_obj; - VirtIOBlock vdev; -}; - -/* - * virtio-balloon-pci: This extends VirtioPCIProxy. - */ -#define TYPE_VIRTIO_BALLOON_PCI "virtio-balloon-pci-base" -#define VIRTIO_BALLOON_PCI(obj) \ - OBJECT_CHECK(VirtIOBalloonPCI, (obj), TYPE_VIRTIO_BALLOON_PCI) - -struct VirtIOBalloonPCI { - VirtIOPCIProxy parent_obj; - VirtIOBalloon vdev; -}; - -/* - * virtio-serial-pci: This extends VirtioPCIProxy. - */ -#define TYPE_VIRTIO_SERIAL_PCI "virtio-serial-pci-base" -#define VIRTIO_SERIAL_PCI(obj) \ - OBJECT_CHECK(VirtIOSerialPCI, (obj), TYPE_VIRTIO_SERIAL_PCI) - -struct VirtIOSerialPCI { - VirtIOPCIProxy parent_obj; - VirtIOSerial vdev; -}; - -/* - * virtio-net-pci: This extends VirtioPCIProxy. - */ -#define TYPE_VIRTIO_NET_PCI "virtio-net-pci-base" -#define VIRTIO_NET_PCI(obj) \ - OBJECT_CHECK(VirtIONetPCI, (obj), TYPE_VIRTIO_NET_PCI) - -struct VirtIONetPCI { - VirtIOPCIProxy parent_obj; - VirtIONet vdev; -}; - -/* - * virtio-9p-pci: This extends VirtioPCIProxy. - */ - -#ifdef CONFIG_VIRTFS - -#define TYPE_VIRTIO_9P_PCI "virtio-9p-pci-base" -#define VIRTIO_9P_PCI(obj) \ - OBJECT_CHECK(V9fsPCIState, (obj), TYPE_VIRTIO_9P_PCI) - -typedef struct V9fsPCIState { - VirtIOPCIProxy parent_obj; - V9fsVirtioState vdev; -} V9fsPCIState; - -#endif - -/* - * virtio-rng-pci: This extends VirtioPCIProxy. - */ -#define TYPE_VIRTIO_RNG_PCI "virtio-rng-pci-base" -#define VIRTIO_RNG_PCI(obj) \ - OBJECT_CHECK(VirtIORngPCI, (obj), TYPE_VIRTIO_RNG_PCI) - -struct VirtIORngPCI { - VirtIOPCIProxy parent_obj; - VirtIORNG vdev; -}; - -/* * virtio-input-pci: This extends VirtioPCIProxy. */ #define TYPE_VIRTIO_INPUT_PCI "virtio-input-pci" -#define VIRTIO_INPUT_PCI(obj) \ - OBJECT_CHECK(VirtIOInputPCI, (obj), TYPE_VIRTIO_INPUT_PCI) - -struct VirtIOInputPCI { - VirtIOPCIProxy parent_obj; - VirtIOInput vdev; -}; - -#define TYPE_VIRTIO_INPUT_HID_PCI "virtio-input-hid-pci" -#define TYPE_VIRTIO_KEYBOARD_PCI "virtio-keyboard-pci" -#define TYPE_VIRTIO_MOUSE_PCI "virtio-mouse-pci" -#define TYPE_VIRTIO_TABLET_PCI "virtio-tablet-pci" -#define VIRTIO_INPUT_HID_PCI(obj) \ - OBJECT_CHECK(VirtIOInputHIDPCI, (obj), TYPE_VIRTIO_INPUT_HID_PCI) - -struct VirtIOInputHIDPCI { - VirtIOPCIProxy parent_obj; - VirtIOInputHID vdev; -}; - -#ifdef CONFIG_LINUX - -#define TYPE_VIRTIO_INPUT_HOST_PCI "virtio-input-host-pci-base" -#define VIRTIO_INPUT_HOST_PCI(obj) \ - OBJECT_CHECK(VirtIOInputHostPCI, (obj), TYPE_VIRTIO_INPUT_HOST_PCI) - -struct VirtIOInputHostPCI { - VirtIOPCIProxy parent_obj; - VirtIOInputHost vdev; -}; - -#endif - -/* - * virtio-gpu-pci: This extends VirtioPCIProxy. - */ -#define TYPE_VIRTIO_GPU_PCI "virtio-gpu-pci" -#define VIRTIO_GPU_PCI(obj) \ - OBJECT_CHECK(VirtIOGPUPCI, (obj), TYPE_VIRTIO_GPU_PCI) - -struct VirtIOGPUPCI { - VirtIOPCIProxy parent_obj; - VirtIOGPU vdev; -}; - -#ifdef CONFIG_VHOST_VSOCK -/* - * vhost-vsock-pci: This extends VirtioPCIProxy. - */ -#define TYPE_VHOST_VSOCK_PCI "vhost-vsock-pci-base" -#define VHOST_VSOCK_PCI(obj) \ - OBJECT_CHECK(VHostVSockPCI, (obj), TYPE_VHOST_VSOCK_PCI) - -struct VHostVSockPCI { - VirtIOPCIProxy parent_obj; - VHostVSock vdev; -}; -#endif - -/* - * virtio-crypto-pci: This extends VirtioPCIProxy. - */ -#define TYPE_VIRTIO_CRYPTO_PCI "virtio-crypto-pci" -#define VIRTIO_CRYPTO_PCI(obj) \ - OBJECT_CHECK(VirtIOCryptoPCI, (obj), TYPE_VIRTIO_CRYPTO_PCI) - -struct VirtIOCryptoPCI { - VirtIOPCIProxy parent_obj; - VirtIOCrypto vdev; -}; /* Virtio ABI version, if we increment this, we break the guest driver. */ #define VIRTIO_PCI_ABI_VERSION 0 diff --git a/hw/virtio/virtio-rng-pci.c b/hw/virtio/virtio-rng-pci.c new file mode 100644 index 0000000000..6cc6374289 --- /dev/null +++ b/hw/virtio/virtio-rng-pci.c @@ -0,0 +1,88 @@ +/* + * Virtio rng PCI Bindings + * + * Copyright 2012 Red Hat, Inc. + * Copyright 2012 Amit Shah <amit.shah@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * (at your option) any later version. See the COPYING file in the + * top-level directory. + */ + +#include "qemu/osdep.h" + +#include "virtio-pci.h" +#include "hw/virtio/virtio-rng.h" +#include "qapi/error.h" + +typedef struct VirtIORngPCI VirtIORngPCI; + +/* + * virtio-rng-pci: This extends VirtioPCIProxy. + */ +#define TYPE_VIRTIO_RNG_PCI "virtio-rng-pci-base" +#define VIRTIO_RNG_PCI(obj) \ + OBJECT_CHECK(VirtIORngPCI, (obj), TYPE_VIRTIO_RNG_PCI) + +struct VirtIORngPCI { + VirtIOPCIProxy parent_obj; + VirtIORNG vdev; +}; + +static void virtio_rng_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) +{ + VirtIORngPCI *vrng = VIRTIO_RNG_PCI(vpci_dev); + DeviceState *vdev = DEVICE(&vrng->vdev); + Error *err = NULL; + + qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); + object_property_set_bool(OBJECT(vdev), true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + + object_property_set_link(OBJECT(vrng), + OBJECT(vrng->vdev.conf.rng), "rng", + NULL); +} + +static void virtio_rng_pci_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); + PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); + + k->realize = virtio_rng_pci_realize; + set_bit(DEVICE_CATEGORY_MISC, dc->categories); + + pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; + pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_RNG; + pcidev_k->revision = VIRTIO_PCI_ABI_VERSION; + pcidev_k->class_id = PCI_CLASS_OTHERS; +} + +static void virtio_rng_initfn(Object *obj) +{ + VirtIORngPCI *dev = VIRTIO_RNG_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VIRTIO_RNG); +} + +static const VirtioPCIDeviceTypeInfo virtio_rng_pci_info = { + .base_name = TYPE_VIRTIO_RNG_PCI, + .generic_name = "virtio-rng-pci", + .transitional_name = "virtio-rng-pci-transitional", + .non_transitional_name = "virtio-rng-pci-non-transitional", + .instance_size = sizeof(VirtIORngPCI), + .instance_init = virtio_rng_initfn, + .class_init = virtio_rng_pci_class_init, +}; + +static void virtio_rng_pci_register(void) +{ + virtio_pci_types_register(&virtio_rng_pci_info); +} + +type_init(virtio_rng_pci_register) diff --git a/hw/virtio/virtio-scsi-pci.c b/hw/virtio/virtio-scsi-pci.c new file mode 100644 index 0000000000..2830849729 --- /dev/null +++ b/hw/virtio/virtio-scsi-pci.c @@ -0,0 +1,107 @@ +/* + * Virtio scsi PCI Bindings + * + * Copyright IBM, Corp. 2007 + * Copyright (c) 2009 CodeSourcery + * + * Authors: + * Anthony Liguori <aliguori@us.ibm.com> + * Paul Brook <paul@codesourcery.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * (at your option) any later version. See the COPYING file in the + * top-level directory. + */ + +#include "qemu/osdep.h" + +#include "hw/virtio/virtio-scsi.h" +#include "virtio-pci.h" + +typedef struct VirtIOSCSIPCI VirtIOSCSIPCI; + +/* + * virtio-scsi-pci: This extends VirtioPCIProxy. + */ +#define TYPE_VIRTIO_SCSI_PCI "virtio-scsi-pci-base" +#define VIRTIO_SCSI_PCI(obj) \ + OBJECT_CHECK(VirtIOSCSIPCI, (obj), TYPE_VIRTIO_SCSI_PCI) + +struct VirtIOSCSIPCI { + VirtIOPCIProxy parent_obj; + VirtIOSCSI vdev; +}; + +static Property virtio_scsi_pci_properties[] = { + DEFINE_PROP_BIT("ioeventfd", VirtIOPCIProxy, flags, + VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT, true), + DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, + DEV_NVECTORS_UNSPECIFIED), + DEFINE_PROP_END_OF_LIST(), +}; + +static void virtio_scsi_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) +{ + VirtIOSCSIPCI *dev = VIRTIO_SCSI_PCI(vpci_dev); + DeviceState *vdev = DEVICE(&dev->vdev); + VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(vdev); + DeviceState *proxy = DEVICE(vpci_dev); + char *bus_name; + + if (vpci_dev->nvectors == DEV_NVECTORS_UNSPECIFIED) { + vpci_dev->nvectors = vs->conf.num_queues + 3; + } + + /* + * For command line compatibility, this sets the virtio-scsi-device bus + * name as before. + */ + if (proxy->id) { + bus_name = g_strdup_printf("%s.0", proxy->id); + virtio_device_set_child_bus_name(VIRTIO_DEVICE(vdev), bus_name); + g_free(bus_name); + } + + qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); + object_property_set_bool(OBJECT(vdev), true, "realized", errp); +} + +static void virtio_scsi_pci_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); + PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); + + k->realize = virtio_scsi_pci_realize; + set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); + dc->props = virtio_scsi_pci_properties; + pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; + pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_SCSI; + pcidev_k->revision = 0x00; + pcidev_k->class_id = PCI_CLASS_STORAGE_SCSI; +} + +static void virtio_scsi_pci_instance_init(Object *obj) +{ + VirtIOSCSIPCI *dev = VIRTIO_SCSI_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VIRTIO_SCSI); +} + +static const VirtioPCIDeviceTypeInfo virtio_scsi_pci_info = { + .base_name = TYPE_VIRTIO_SCSI_PCI, + .generic_name = "virtio-scsi-pci", + .transitional_name = "virtio-scsi-pci-transitional", + .non_transitional_name = "virtio-scsi-pci-non-transitional", + .instance_size = sizeof(VirtIOSCSIPCI), + .instance_init = virtio_scsi_pci_instance_init, + .class_init = virtio_scsi_pci_class_init, +}; + +static void virtio_scsi_pci_register(void) +{ + virtio_pci_types_register(&virtio_scsi_pci_info); +} + +type_init(virtio_scsi_pci_register) diff --git a/hw/virtio/virtio-serial-pci.c b/hw/virtio/virtio-serial-pci.c new file mode 100644 index 0000000000..971b2eb8d8 --- /dev/null +++ b/hw/virtio/virtio-serial-pci.c @@ -0,0 +1,115 @@ +/* + * Virtio serial PCI Bindings + * + * Copyright IBM, Corp. 2007 + * Copyright (c) 2009 CodeSourcery + * + * Authors: + * Anthony Liguori <aliguori@us.ibm.com> + * Paul Brook <paul@codesourcery.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Contributions after 2012-01-13 are licensed under the terms of the + * GNU GPL, version 2 or (at your option) any later version. + */ + +#include "qemu/osdep.h" + +#include "hw/virtio/virtio-serial.h" +#include "virtio-pci.h" + +typedef struct VirtIOSerialPCI VirtIOSerialPCI; + +/* + * virtio-serial-pci: This extends VirtioPCIProxy. + */ +#define TYPE_VIRTIO_SERIAL_PCI "virtio-serial-pci-base" +#define VIRTIO_SERIAL_PCI(obj) \ + OBJECT_CHECK(VirtIOSerialPCI, (obj), TYPE_VIRTIO_SERIAL_PCI) + +struct VirtIOSerialPCI { + VirtIOPCIProxy parent_obj; + VirtIOSerial vdev; +}; + +static void virtio_serial_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) +{ + VirtIOSerialPCI *dev = VIRTIO_SERIAL_PCI(vpci_dev); + DeviceState *vdev = DEVICE(&dev->vdev); + DeviceState *proxy = DEVICE(vpci_dev); + char *bus_name; + + if (vpci_dev->class_code != PCI_CLASS_COMMUNICATION_OTHER && + vpci_dev->class_code != PCI_CLASS_DISPLAY_OTHER && /* qemu 0.10 */ + vpci_dev->class_code != PCI_CLASS_OTHERS) { /* qemu-kvm */ + vpci_dev->class_code = PCI_CLASS_COMMUNICATION_OTHER; + } + + /* backwards-compatibility with machines that were created with + DEV_NVECTORS_UNSPECIFIED */ + if (vpci_dev->nvectors == DEV_NVECTORS_UNSPECIFIED) { + vpci_dev->nvectors = dev->vdev.serial.max_virtserial_ports + 1; + } + + /* + * For command line compatibility, this sets the virtio-serial-device bus + * name as before. + */ + if (proxy->id) { + bus_name = g_strdup_printf("%s.0", proxy->id); + virtio_device_set_child_bus_name(VIRTIO_DEVICE(vdev), bus_name); + g_free(bus_name); + } + + qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); + object_property_set_bool(OBJECT(vdev), true, "realized", errp); +} + +static Property virtio_serial_pci_properties[] = { + DEFINE_PROP_BIT("ioeventfd", VirtIOPCIProxy, flags, + VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT, true), + DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 2), + DEFINE_PROP_UINT32("class", VirtIOPCIProxy, class_code, 0), + DEFINE_PROP_END_OF_LIST(), +}; + +static void virtio_serial_pci_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); + PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); + k->realize = virtio_serial_pci_realize; + set_bit(DEVICE_CATEGORY_INPUT, dc->categories); + dc->props = virtio_serial_pci_properties; + pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; + pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_CONSOLE; + pcidev_k->revision = VIRTIO_PCI_ABI_VERSION; + pcidev_k->class_id = PCI_CLASS_COMMUNICATION_OTHER; +} + +static void virtio_serial_pci_instance_init(Object *obj) +{ + VirtIOSerialPCI *dev = VIRTIO_SERIAL_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VIRTIO_SERIAL); +} + +static const VirtioPCIDeviceTypeInfo virtio_serial_pci_info = { + .base_name = TYPE_VIRTIO_SERIAL_PCI, + .generic_name = "virtio-serial-pci", + .transitional_name = "virtio-serial-pci-transitional", + .non_transitional_name = "virtio-serial-pci-non-transitional", + .instance_size = sizeof(VirtIOSerialPCI), + .instance_init = virtio_serial_pci_instance_init, + .class_init = virtio_serial_pci_class_init, +}; + +static void virtio_serial_pci_register(void) +{ + virtio_pci_types_register(&virtio_serial_pci_info); +} + +type_init(virtio_serial_pci_register) diff --git a/include/hw/acpi/acpi-defs.h b/include/hw/acpi/acpi-defs.h index 5021cb9e79..f9aa4bd398 100644 --- a/include/hw/acpi/acpi-defs.h +++ b/include/hw/acpi/acpi-defs.h @@ -41,8 +41,8 @@ enum { }; typedef struct AcpiRsdpData { - uint8_t oem_id[6]; /* OEM identification */ - uint8_t revision; /* Must be 0 for 1.0, 2 for 2.0 */ + uint8_t oem_id[6] QEMU_NONSTRING; /* OEM identification */ + uint8_t revision; /* Must be 0 for 1.0, 2 for 2.0 */ unsigned *rsdt_tbl_offset; unsigned *xsdt_tbl_offset; @@ -57,10 +57,13 @@ typedef struct AcpiRsdpData { uint32_t length; /* Length of table, in bytes, including header */ \ uint8_t revision; /* ACPI Specification minor version # */ \ uint8_t checksum; /* To make sum of entire table == 0 */ \ - uint8_t oem_id [6]; /* OEM identification */ \ - uint8_t oem_table_id [8]; /* OEM table identification */ \ + uint8_t oem_id[6] \ + QEMU_NONSTRING; /* OEM identification */ \ + uint8_t oem_table_id[8] \ + QEMU_NONSTRING; /* OEM table identification */ \ uint32_t oem_revision; /* OEM revision number */ \ - uint8_t asl_compiler_id [4]; /* ASL compiler vendor ID */ \ + uint8_t asl_compiler_id[4] \ + QEMU_NONSTRING; /* ASL compiler vendor ID */ \ uint32_t asl_compiler_revision; /* ASL compiler revision number */ @@ -623,6 +626,8 @@ struct AcpiIortItsGroup { } QEMU_PACKED; typedef struct AcpiIortItsGroup AcpiIortItsGroup; +#define ACPI_IORT_SMMU_V3_COHACC_OVERRIDE 1 + struct AcpiIortSmmu3 { ACPI_IORT_NODE_HEADER_DEF uint64_t base_address; diff --git a/include/hw/acpi/tpm.h b/include/hw/acpi/tpm.h index 3580ffd50c..1a2a57a21f 100644 --- a/include/hw/acpi/tpm.h +++ b/include/hw/acpi/tpm.h @@ -18,6 +18,8 @@ #include "qemu/units.h" #include "hw/registerfields.h" +#include "hw/acpi/aml-build.h" +#include "sysemu/tpm.h" #define TPM_TIS_ADDR_BASE 0xFED40000 #define TPM_TIS_ADDR_SIZE 0x5000 @@ -188,4 +190,23 @@ REG32(CRB_DATA_BUFFER, 0x80) #define TPM2_START_METHOD_MMIO 6 #define TPM2_START_METHOD_CRB 7 +/* + * Physical Presence Interface + */ +#define TPM_PPI_ADDR_SIZE 0x400 +#define TPM_PPI_ADDR_BASE 0xFED45000 + +#define TPM_PPI_VERSION_NONE 0 +#define TPM_PPI_VERSION_1_30 1 + +/* whether function is blocked by BIOS settings; bits 0, 1, 2 */ +#define TPM_PPI_FUNC_NOT_IMPLEMENTED (0 << 0) +#define TPM_PPI_FUNC_BIOS_ONLY (1 << 0) +#define TPM_PPI_FUNC_BLOCKED (2 << 0) +#define TPM_PPI_FUNC_ALLOWED_USR_REQ (3 << 0) +#define TPM_PPI_FUNC_ALLOWED_USR_NOT_REQ (4 << 0) +#define TPM_PPI_FUNC_MASK (7 << 0) + +void tpm_build_ppi_acpi(TPMIf *tpm, Aml *dev); + #endif /* HW_ACPI_TPM_H */ diff --git a/include/hw/pci/pcie.h b/include/hw/pci/pcie.h index cd318646a2..5b82a0d244 100644 --- a/include/hw/pci/pcie.h +++ b/include/hw/pci/pcie.h @@ -132,6 +132,8 @@ void pcie_ari_init(PCIDevice *dev, uint16_t offset, uint16_t nextfn); void pcie_dev_ser_num_init(PCIDevice *dev, uint16_t offset, uint64_t ser_num); void pcie_ats_init(PCIDevice *dev, uint16_t offset); +void pcie_cap_slot_pre_plug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, + Error **errp); void pcie_cap_slot_plug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp); void pcie_cap_slot_unplug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h index 9614f76ae6..0a84c42756 100644 --- a/include/hw/qdev-core.h +++ b/include/hw/qdev-core.h @@ -250,6 +250,8 @@ struct PropertyInfo { /** * GlobalProperty: * @used: Set to true if property was used when initializing a device. + * @optional: If set to true, GlobalProperty will be skipped without errors + * if the property doesn't exist. * * An error is fatal for non-hotplugged devices, when the global is applied. */ @@ -258,6 +260,7 @@ typedef struct GlobalProperty { const char *property; const char *value; bool used; + bool optional; } GlobalProperty; static inline void diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h index 4d7f3c82ca..c7ec1a755f 100644 --- a/include/hw/virtio/virtio-net.h +++ b/include/hw/virtio/virtio-net.h @@ -44,6 +44,83 @@ typedef struct virtio_net_conf uint8_t duplex; } virtio_net_conf; +/* Coalesced packets type & status */ +typedef enum { + RSC_COALESCE, /* Data been coalesced */ + RSC_FINAL, /* Will terminate current connection */ + RSC_NO_MATCH, /* No matched in the buffer pool */ + RSC_BYPASS, /* Packet to be bypass, not tcp, tcp ctrl, etc */ + RSC_CANDIDATE /* Data want to be coalesced */ +} CoalesceStatus; + +typedef struct VirtioNetRscStat { + uint32_t received; + uint32_t coalesced; + uint32_t over_size; + uint32_t cache; + uint32_t empty_cache; + uint32_t no_match_cache; + uint32_t win_update; + uint32_t no_match; + uint32_t tcp_syn; + uint32_t tcp_ctrl_drain; + uint32_t dup_ack; + uint32_t dup_ack1; + uint32_t dup_ack2; + uint32_t pure_ack; + uint32_t ack_out_of_win; + uint32_t data_out_of_win; + uint32_t data_out_of_order; + uint32_t data_after_pure_ack; + uint32_t bypass_not_tcp; + uint32_t tcp_option; + uint32_t tcp_all_opt; + uint32_t ip_frag; + uint32_t ip_ecn; + uint32_t ip_hacked; + uint32_t ip_option; + uint32_t purge_failed; + uint32_t drain_failed; + uint32_t final_failed; + int64_t timer; +} VirtioNetRscStat; + +/* Rsc unit general info used to checking if can coalescing */ +typedef struct VirtioNetRscUnit { + void *ip; /* ip header */ + uint16_t *ip_plen; /* data len pointer in ip header field */ + struct tcp_header *tcp; /* tcp header */ + uint16_t tcp_hdrlen; /* tcp header len */ + uint16_t payload; /* pure payload without virtio/eth/ip/tcp */ +} VirtioNetRscUnit; + +/* Coalesced segmant */ +typedef struct VirtioNetRscSeg { + QTAILQ_ENTRY(VirtioNetRscSeg) next; + void *buf; + size_t size; + uint16_t packets; + uint16_t dup_ack; + bool is_coalesced; /* need recal ipv4 header checksum, mark here */ + VirtioNetRscUnit unit; + NetClientState *nc; +} VirtioNetRscSeg; + +struct VirtIONet; +typedef struct VirtIONet VirtIONet; + +/* Chain is divided by protocol(ipv4/v6) and NetClientInfo */ +typedef struct VirtioNetRscChain { + QTAILQ_ENTRY(VirtioNetRscChain) next; + VirtIONet *n; /* VirtIONet */ + uint16_t proto; + uint8_t gso_type; + uint16_t max_payload; + QEMUTimer *drain_timer; + QTAILQ_HEAD(, VirtioNetRscSeg) buffers; + VirtioNetRscStat stat; +} VirtioNetRscChain; + /* Maximum packet size we can receive from tap device: header + 64k */ #define VIRTIO_NET_MAX_BUFSIZE (sizeof(struct virtio_net_hdr) + (64 * KiB)) @@ -66,12 +143,18 @@ typedef struct VirtIONet { VirtIONetQueue *vqs; VirtQueue *ctrl_vq; NICState *nic; + /* RSC Chains - temporary storage of coalesced data, + all these data are lost in case of migration */ + QTAILQ_HEAD(, VirtioNetRscChain) rsc_chains; uint32_t tx_timeout; int32_t tx_burst; uint32_t has_vnet_hdr; size_t host_hdr_len; size_t guest_hdr_len; uint64_t host_features; + uint32_t rsc_timeout; + uint8_t rsc4_enabled; + uint8_t rsc6_enabled; uint8_t has_ufo; uint32_t mergeable_rx_bufs; uint8_t promisc; diff --git a/include/migration/vmstate.h b/include/migration/vmstate.h index 61bef3ef5c..067b126cf1 100644 --- a/include/migration/vmstate.h +++ b/include/migration/vmstate.h @@ -185,6 +185,7 @@ struct VMStateDescription { int (*pre_load)(void *opaque); int (*post_load)(void *opaque, int version_id); int (*pre_save)(void *opaque); + int (*post_save)(void *opaque); bool (*needed)(void *opaque); const VMStateField *fields; const VMStateDescription **subsections; diff --git a/include/net/eth.h b/include/net/eth.h index e6dc8a7ba0..7f45c678e7 100644 --- a/include/net/eth.h +++ b/include/net/eth.h @@ -177,6 +177,8 @@ struct tcp_hdr { #define TH_PUSH 0x08 #define TH_ACK 0x10 #define TH_URG 0x20 +#define TH_ECE 0x40 +#define TH_CWR 0x80 u_short th_win; /* window */ u_short th_sum; /* checksum */ u_short th_urp; /* urgent pointer */ diff --git a/include/qemu/compiler.h b/include/qemu/compiler.h index 261842beae..2d8f507c73 100644 --- a/include/qemu/compiler.h +++ b/include/qemu/compiler.h @@ -151,6 +151,21 @@ # define QEMU_ERROR(X) #endif +/* + * The nonstring variable attribute specifies that an object or member + * declaration with type array of char or pointer to char is intended + * to store character arrays that do not necessarily contain a terminating + * NUL character. This is useful in detecting uses of such arrays or pointers + * with functions that expect NUL-terminated strings, and to avoid warnings + * when such an array or pointer is used as an argument to a bounded string + * manipulation function such as strncpy. + */ +#if __has_attribute(nonstring) +# define QEMU_NONSTRING __attribute__((nonstring)) +#else +# define QEMU_NONSTRING +#endif + /* Implement C11 _Generic via GCC builtins. Example: * * QEMU_GENERIC(x, (float, sinf), (long double, sinl), sin) (x) diff --git a/migration/global_state.c b/migration/global_state.c index 8e8ab5c51e..2c8c447239 100644 --- a/migration/global_state.c +++ b/migration/global_state.c @@ -42,6 +42,7 @@ int global_state_store(void) void global_state_store_running(void) { const char *state = RunState_str(RUN_STATE_RUNNING); + assert(strlen(state) < sizeof(global_state.runstate)); strncpy((char *)global_state.runstate, state, sizeof(global_state.runstate)); } @@ -88,6 +89,17 @@ static int global_state_post_load(void *opaque, int version_id) s->received = true; trace_migrate_global_state_post_load(runstate); + if (strnlen((char *)s->runstate, + sizeof(s->runstate)) == sizeof(s->runstate)) { + /* + * This condition should never happen during migration, because + * all runstate names are shorter than 100 bytes (the size of + * s->runstate). However, a malicious stream could overflow + * the qapi_enum_parse() call, so we force the last character + * to a NUL byte. + */ + s->runstate[sizeof(s->runstate) - 1] = '\0'; + } r = qapi_enum_parse(&RunState_lookup, runstate, -1, &local_err); if (r == -1) { @@ -106,7 +118,8 @@ static int global_state_pre_save(void *opaque) GlobalState *s = opaque; trace_migrate_global_state_pre_save((char *)s->runstate); - s->size = strlen((char *)s->runstate) + 1; + s->size = strnlen((char *)s->runstate, sizeof(s->runstate)) + 1; + assert(s->size <= sizeof(s->runstate)); return 0; } diff --git a/migration/vmstate.c b/migration/vmstate.c index 80b59009aa..e2bbb7b5f7 100644 --- a/migration/vmstate.c +++ b/migration/vmstate.c @@ -390,6 +390,9 @@ int vmstate_save_state_v(QEMUFile *f, const VMStateDescription *vmsd, if (ret) { error_report("Save of field %s/%s failed", vmsd->name, field->name); + if (vmsd->post_save) { + vmsd->post_save(opaque); + } return ret; } @@ -415,7 +418,15 @@ int vmstate_save_state_v(QEMUFile *f, const VMStateDescription *vmsd, json_end_array(vmdesc); } - return vmstate_subsection_save(f, vmsd, opaque, vmdesc); + ret = vmstate_subsection_save(f, vmsd, opaque, vmdesc); + + if (vmsd->post_save) { + int ps_ret = vmsd->post_save(opaque); + if (!ret) { + ret = ps_ret; + } + } + return ret; } static const VMStateDescription * diff --git a/pc-bios/s390-ccw/start.S b/pc-bios/s390-ccw/start.S index eb8d024dbb..5c22cb0849 100644 --- a/pc-bios/s390-ccw/start.S +++ b/pc-bios/s390-ccw/start.S @@ -59,9 +59,9 @@ disabled_wait: .globl consume_sclp_int consume_sclp_int: /* enable service interrupts in cr0 */ - stctg 0,0,0(15) - oi 6(15), 0x2 - lctlg 0,0,0(15) + stctg %c0,%c0,0(%r15) + oi 6(%r15),0x2 + lctlg %c0,%c0,0(%r15) /* prepare external call handler */ larl %r1, external_new_code stg %r1, 0x1b8 @@ -73,10 +73,10 @@ consume_sclp_int: external_new_code: /* disable service interrupts in cr0 */ - stctg 0,0,0(15) - ni 6(15), 0xfd - lctlg 0,0,0(15) - br 14 + stctg %c0,%c0,0(%r15) + ni 6(%r15),0xfd + lctlg %c0,%c0,0(%r15) + br %r14 .align 8 disabled_wait_psw: diff --git a/qemu-deprecated.texi b/qemu-deprecated.texi index 81de5fc019..219206a836 100644 --- a/qemu-deprecated.texi +++ b/qemu-deprecated.texi @@ -126,11 +126,6 @@ documentation of ``query-hotpluggable-cpus'' for additional details. @section System emulator devices -@subsection ivshmem (since 2.6.0) - -The ``ivshmem'' device type is replaced by either the ``ivshmem-plain'' -or ``ivshmem-doorbell`` device types. - @subsection bluetooth (since 3.1) The bluetooth subsystem is unmaintained since many years and likely bitrotten diff --git a/qom/object.c b/qom/object.c index 4e5226ca12..b8c732063b 100644 --- a/qom/object.c +++ b/qom/object.c @@ -385,6 +385,9 @@ void object_apply_global_props(Object *obj, const GPtrArray *props, Error **errp if (object_dynamic_cast(obj, p->driver) == NULL) { continue; } + if (p->optional && !object_property_find(obj, p->property, NULL)) { + continue; + } p->used = true; object_property_parse(obj, p->value, p->property, &err); if (err != NULL) { diff --git a/scripts/analyse-locks-simpletrace.py b/scripts/analyse-locks-simpletrace.py index 30090bdfff..7d9b574300 100755 --- a/scripts/analyse-locks-simpletrace.py +++ b/scripts/analyse-locks-simpletrace.py @@ -7,7 +7,6 @@ # from __future__ import print_function -import os import simpletrace import argparse import numpy as np diff --git a/scripts/analyze-migration.py b/scripts/analyze-migration.py index 5c2010c917..e527eb168e 100755 --- a/scripts/analyze-migration.py +++ b/scripts/analyze-migration.py @@ -23,7 +23,6 @@ import json import os import argparse import collections -import pprint def mkdir_p(path): try: diff --git a/scripts/device-crash-test b/scripts/device-crash-test index e93a7c0c84..483dafb2fc 100755 --- a/scripts/device-crash-test +++ b/scripts/device-crash-test @@ -26,7 +26,6 @@ check for crashes and unexpected errors. from __future__ import print_function import sys -import os import glob import logging import traceback @@ -83,7 +82,6 @@ ERROR_WHITELIST = [ {'device':'isa-ipmi-bt', 'expected':True}, # IPMI device requires a bmc attribute to be set {'device':'isa-ipmi-kcs', 'expected':True}, # IPMI device requires a bmc attribute to be set {'device':'isa-parallel', 'expected':True}, # Can't create serial device, empty char device - {'device':'ivshmem', 'expected':True}, # You must specify either 'shm' or 'chardev' {'device':'ivshmem-doorbell', 'expected':True}, # You must specify a 'chardev' {'device':'ivshmem-plain', 'expected':True}, # You must specify a 'memdev' {'device':'loader', 'expected':True}, # please include valid arguments @@ -182,21 +180,6 @@ ERROR_WHITELIST = [ # other exitcode=1 failures not listed above will just generate INFO messages: {'exitcode':1, 'loglevel':logging.INFO}, - # KNOWN CRASHES: - # Known crashes will generate error messages, but won't be fatal. - # Those entries must be removed once we fix the crashes. - {'exitcode':-6, 'log':r"Device 'serial0' is in use", 'loglevel':logging.ERROR}, - {'exitcode':-6, 'log':r"qemu_net_client_setup: Assertion `!peer->peer' failed", 'loglevel':logging.ERROR}, - {'exitcode':-6, 'log':r'RAMBlock "[\w.-]+" already registered', 'loglevel':logging.ERROR}, - {'exitcode':-6, 'log':r"find_ram_offset: Assertion `size != 0' failed.", 'loglevel':logging.ERROR}, - {'exitcode':-6, 'log':r"add_cpreg_to_hashtable: code should not be reached", 'loglevel':logging.ERROR}, - {'exitcode':-6, 'log':r"qemu_alloc_display: Assertion `surface->image != NULL' failed", 'loglevel':logging.ERROR}, - {'exitcode':-6, 'log':r"Unexpected error in error_set_from_qdev_prop_error", 'loglevel':logging.ERROR}, - {'exitcode':-6, 'log':r"Object .* is not an instance of type spapr-machine", 'loglevel':logging.ERROR}, - {'exitcode':-6, 'log':r"Object .* is not an instance of type generic-pc-machine", 'loglevel':logging.ERROR}, - {'exitcode':-6, 'log':r"Object .* is not an instance of type e500-ccsr", 'loglevel':logging.ERROR}, - {'exitcode':-6, 'log':r"vmstate_register_with_alias_id: Assertion `!se->compat \|\| se->instance_id == 0' failed", 'loglevel':logging.ERROR}, - # everything else (including SIGABRT and SIGSEGV) will be a fatal error: {'exitcode':None, 'fatal':True, 'loglevel':logging.FATAL}, ] diff --git a/scripts/qemu.py b/scripts/qemu.py index 6e3b0e6771..0a5e02eb56 100644 --- a/scripts/qemu.py +++ b/scripts/qemu.py @@ -351,7 +351,7 @@ class QEMUMachine(object): command = ' '.join(self._qemu_full_args) else: command = '' - LOG.warn(msg, exitcode, command) + LOG.warn(msg, -exitcode, command) self._launched = False diff --git a/scripts/replay-dump.py b/scripts/replay-dump.py index 5ae77c8a92..ee7fda2638 100755 --- a/scripts/replay-dump.py +++ b/scripts/replay-dump.py @@ -3,7 +3,7 @@ # # Dump the contents of a recorded execution stream # -# Copyright (c) 2017 Alex Bennée <alex.bennee@linaro.org> +# Copyright (c) 2017 Alex Bennée <alex.bennee@linaro.org> # # This library is free software; you can redistribute it and/or # modify it under the terms of the GNU Lesser General Public diff --git a/scripts/simpletrace.py b/scripts/simpletrace.py index 4ad34f90cd..45485b864b 100755 --- a/scripts/simpletrace.py +++ b/scripts/simpletrace.py @@ -11,7 +11,6 @@ from __future__ import print_function import struct -import re import inspect from tracetool import read_events, Event from tracetool.backend.simple import is_string diff --git a/scripts/tracetool.py b/scripts/tracetool.py index fe2b0771f2..3beaa66bd8 100755 --- a/scripts/tracetool.py +++ b/scripts/tracetool.py @@ -15,8 +15,6 @@ __email__ = "stefanha@linux.vnet.ibm.com" import sys import getopt -import os.path -import re from tracetool import error_write, out import tracetool.backend diff --git a/scripts/tracetool/format/simpletrace_stap.py b/scripts/tracetool/format/simpletrace_stap.py index e7e44842ca..57b04061cf 100644 --- a/scripts/tracetool/format/simpletrace_stap.py +++ b/scripts/tracetool/format/simpletrace_stap.py @@ -14,7 +14,7 @@ __email__ = "stefanha@redhat.com" from tracetool import out -from tracetool.backend.dtrace import binary, probeprefix +from tracetool.backend.dtrace import probeprefix from tracetool.backend.simple import is_string from tracetool.format.stap import stap_escape diff --git a/stubs/tpm.c b/stubs/tpm.c index 80939cd3db..66c99d667d 100644 --- a/stubs/tpm.c +++ b/stubs/tpm.c @@ -8,6 +8,7 @@ #include "qemu/osdep.h" #include "qapi/qapi-commands-tpm.h" #include "sysemu/tpm.h" +#include "hw/acpi/tpm.h" void tpm_init(void) { @@ -31,3 +32,7 @@ TpmModelList *qmp_query_tpm_models(Error **errp) { return NULL; } + +void tpm_build_ppi_acpi(TPMIf *tpm, Aml *dev) +{ +} diff --git a/target/arm/Makefile.objs b/target/arm/Makefile.objs index 11c7baf8a3..1a4fc06448 100644 --- a/target/arm/Makefile.objs +++ b/target/arm/Makefile.objs @@ -8,6 +8,7 @@ obj-y += translate.o op_helper.o helper.o cpu.o obj-y += neon_helper.o iwmmxt_helper.o vec_helper.o obj-y += gdbstub.o obj-$(TARGET_AARCH64) += cpu64.o translate-a64.o helper-a64.o gdbstub64.o +obj-$(TARGET_AARCH64) += pauth_helper.o obj-y += crypto_helper.o obj-$(CONFIG_SOFTMMU) += arm-powerctl.o diff --git a/target/arm/cpu.c b/target/arm/cpu.c index 4c4e9e169e..7e1f3dd637 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -162,6 +162,9 @@ static void arm_cpu_reset(CPUState *s) env->pstate = PSTATE_MODE_EL0t; /* Userspace expects access to DC ZVA, CTL_EL0 and the cache ops */ env->cp15.sctlr_el[1] |= SCTLR_UCT | SCTLR_UCI | SCTLR_DZE; + /* Enable all PAC instructions */ + env->cp15.hcr_el2 |= HCR_API; + env->cp15.scr_el3 |= SCR_API; /* and to the FP/Neon instructions */ env->cp15.cpacr_el1 = deposit64(env->cp15.cpacr_el1, 20, 2, 3); /* and to the SVE instructions */ @@ -1034,7 +1037,19 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) if (!cpu->has_pmu) { unset_feature(env, ARM_FEATURE_PMU); + } + if (arm_feature(env, ARM_FEATURE_PMU)) { + cpu->pmceid0 = get_pmceid(&cpu->env, 0); + cpu->pmceid1 = get_pmceid(&cpu->env, 1); + + if (!kvm_enabled()) { + arm_register_pre_el_change_hook(cpu, &pmu_pre_el_change, 0); + arm_register_el_change_hook(cpu, &pmu_post_el_change, 0); + } + } else { cpu->id_aa64dfr0 &= ~0xf00; + cpu->pmceid0 = 0; + cpu->pmceid1 = 0; } if (!arm_feature(env, ARM_FEATURE_EL2)) { @@ -1679,8 +1694,6 @@ static void cortex_a7_initfn(Object *obj) cpu->id_pfr0 = 0x00001131; cpu->id_pfr1 = 0x00011011; cpu->id_dfr0 = 0x02010555; - cpu->pmceid0 = 0x00000000; - cpu->pmceid1 = 0x00000000; cpu->id_afr0 = 0x00000000; cpu->id_mmfr0 = 0x10101105; cpu->id_mmfr1 = 0x40000000; @@ -1726,8 +1739,6 @@ static void cortex_a15_initfn(Object *obj) cpu->id_pfr0 = 0x00001131; cpu->id_pfr1 = 0x00011011; cpu->id_dfr0 = 0x02010555; - cpu->pmceid0 = 0x0000000; - cpu->pmceid1 = 0x00000000; cpu->id_afr0 = 0x00000000; cpu->id_mmfr0 = 0x10201105; cpu->id_mmfr1 = 0x20000000; diff --git a/target/arm/cpu.h b/target/arm/cpu.h index 6f606eb97b..ff81db420d 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -201,11 +201,16 @@ typedef struct ARMVectorReg { uint64_t d[2 * ARM_MAX_VQ] QEMU_ALIGNED(16); } ARMVectorReg; -/* In AArch32 mode, predicate registers do not exist at all. */ #ifdef TARGET_AARCH64 +/* In AArch32 mode, predicate registers do not exist at all. */ typedef struct ARMPredicateReg { uint64_t p[2 * ARM_MAX_VQ / 8] QEMU_ALIGNED(16); } ARMPredicateReg; + +/* In AArch32 mode, PAC keys do not exist at all. */ +typedef struct ARMPACKey { + uint64_t lo, hi; +} ARMPACKey; #endif @@ -468,10 +473,23 @@ typedef struct CPUARMState { uint64_t oslsr_el1; /* OS Lock Status */ uint64_t mdcr_el2; uint64_t mdcr_el3; - /* If the counter is enabled, this stores the last time the counter - * was reset. Otherwise it stores the counter value + /* Stores the architectural value of the counter *the last time it was + * updated* by pmccntr_op_start. Accesses should always be surrounded + * by pmccntr_op_start/pmccntr_op_finish to guarantee the latest + * architecturally-correct value is being read/set. */ uint64_t c15_ccnt; + /* Stores the delta between the architectural value and the underlying + * cycle count during normal operation. It is used to update c15_ccnt + * to be the correct architectural value before accesses. During + * accesses, c15_ccnt_delta contains the underlying count being used + * for the access, after which it reverts to the delta value in + * pmccntr_op_finish. + */ + uint64_t c15_ccnt_delta; + uint64_t c14_pmevcntr[31]; + uint64_t c14_pmevcntr_delta[31]; + uint64_t c14_pmevtyper[31]; uint64_t pmccfiltr_el0; /* Performance Monitor Filter Register */ uint64_t vpidr_el2; /* Virtualization Processor ID Register */ uint64_t vmpidr_el2; /* Virtualization Multiprocessor ID Register */ @@ -605,6 +623,14 @@ typedef struct CPUARMState { uint32_t cregs[16]; } iwmmxt; +#ifdef TARGET_AARCH64 + ARMPACKey apia_key; + ARMPACKey apib_key; + ARMPACKey apda_key; + ARMPACKey apdb_key; + ARMPACKey apga_key; +#endif + #if defined(CONFIG_USER_ONLY) /* For usermode syscall translation. */ int eabi; @@ -829,8 +855,8 @@ struct ARMCPU { uint32_t id_pfr0; uint32_t id_pfr1; uint32_t id_dfr0; - uint32_t pmceid0; - uint32_t pmceid1; + uint64_t pmceid0; + uint64_t pmceid1; uint32_t id_afr0; uint32_t id_mmfr0; uint32_t id_mmfr1; @@ -958,15 +984,42 @@ int cpu_arm_signal_handler(int host_signum, void *pinfo, void *puc); /** - * pmccntr_sync + * pmccntr_op_start/finish + * @env: CPUARMState + * + * Convert the counter in the PMCCNTR between its delta form (the typical mode + * when it's enabled) and the guest-visible value. These two calls must always + * surround any action which might affect the counter. + */ +void pmccntr_op_start(CPUARMState *env); +void pmccntr_op_finish(CPUARMState *env); + +/** + * pmu_op_start/finish + * @env: CPUARMState + * + * Convert all PMU counters between their delta form (the typical mode when + * they are enabled) and the guest-visible values. These two calls must + * surround any action which might affect the counters. + */ +void pmu_op_start(CPUARMState *env); +void pmu_op_finish(CPUARMState *env); + +/** + * Functions to register as EL change hooks for PMU mode filtering + */ +void pmu_pre_el_change(ARMCPU *cpu, void *ignored); +void pmu_post_el_change(ARMCPU *cpu, void *ignored); + +/* + * get_pmceid * @env: CPUARMState + * @which: which PMCEID register to return (0 or 1) * - * Synchronises the counter in the PMCCNTR. This must always be called twice, - * once before any action that might affect the timer and again afterwards. - * The function is used to swap the state of the register if required. - * This only happens when not in user mode (!CONFIG_USER_ONLY) + * Return the PMCEID[01]_EL0 register values corresponding to the counters + * which are supported given the current configuration */ -void pmccntr_sync(CPUARMState *env); +uint64_t get_pmceid(CPUARMState *env, unsigned which); /* SCTLR bit meanings. Several bits have been reused in newer * versions of the architecture; in that case we define constants @@ -978,12 +1031,15 @@ void pmccntr_sync(CPUARMState *env); #define SCTLR_A (1U << 1) #define SCTLR_C (1U << 2) #define SCTLR_W (1U << 3) /* up to v6; RAO in v7 */ -#define SCTLR_SA (1U << 3) +#define SCTLR_nTLSMD_32 (1U << 3) /* v8.2-LSMAOC, AArch32 only */ +#define SCTLR_SA (1U << 3) /* AArch64 only */ #define SCTLR_P (1U << 4) /* up to v5; RAO in v6 and v7 */ +#define SCTLR_LSMAOE_32 (1U << 4) /* v8.2-LSMAOC, AArch32 only */ #define SCTLR_SA0 (1U << 4) /* v8 onward, AArch64 only */ #define SCTLR_D (1U << 5) /* up to v5; RAO in v6 */ #define SCTLR_CP15BEN (1U << 5) /* v7 onward */ #define SCTLR_L (1U << 6) /* up to v5; RAO in v6 and v7; RAZ in v8 */ +#define SCTLR_nAA (1U << 6) /* when v8.4-LSE is implemented */ #define SCTLR_B (1U << 7) /* up to v6; RAZ in v7 */ #define SCTLR_ITD (1U << 7) /* v8 onward */ #define SCTLR_S (1U << 8) /* up to v6; RAZ in v7 */ @@ -991,35 +1047,53 @@ void pmccntr_sync(CPUARMState *env); #define SCTLR_R (1U << 9) /* up to v6; RAZ in v7 */ #define SCTLR_UMA (1U << 9) /* v8 onward, AArch64 only */ #define SCTLR_F (1U << 10) /* up to v6 */ -#define SCTLR_SW (1U << 10) /* v7 onward */ -#define SCTLR_Z (1U << 11) +#define SCTLR_SW (1U << 10) /* v7, RES0 in v8 */ +#define SCTLR_Z (1U << 11) /* in v7, RES1 in v8 */ +#define SCTLR_EOS (1U << 11) /* v8.5-ExS */ #define SCTLR_I (1U << 12) -#define SCTLR_V (1U << 13) +#define SCTLR_V (1U << 13) /* AArch32 only */ +#define SCTLR_EnDB (1U << 13) /* v8.3, AArch64 only */ #define SCTLR_RR (1U << 14) /* up to v7 */ #define SCTLR_DZE (1U << 14) /* v8 onward, AArch64 only */ #define SCTLR_L4 (1U << 15) /* up to v6; RAZ in v7 */ #define SCTLR_UCT (1U << 15) /* v8 onward, AArch64 only */ #define SCTLR_DT (1U << 16) /* up to ??, RAO in v6 and v7 */ #define SCTLR_nTWI (1U << 16) /* v8 onward */ -#define SCTLR_HA (1U << 17) +#define SCTLR_HA (1U << 17) /* up to v7, RES0 in v8 */ #define SCTLR_BR (1U << 17) /* PMSA only */ #define SCTLR_IT (1U << 18) /* up to ??, RAO in v6 and v7 */ #define SCTLR_nTWE (1U << 18) /* v8 onward */ #define SCTLR_WXN (1U << 19) #define SCTLR_ST (1U << 20) /* up to ??, RAZ in v6 */ -#define SCTLR_UWXN (1U << 20) /* v7 onward */ -#define SCTLR_FI (1U << 21) -#define SCTLR_U (1U << 22) +#define SCTLR_UWXN (1U << 20) /* v7 onward, AArch32 only */ +#define SCTLR_FI (1U << 21) /* up to v7, v8 RES0 */ +#define SCTLR_IESB (1U << 21) /* v8.2-IESB, AArch64 only */ +#define SCTLR_U (1U << 22) /* up to v6, RAO in v7 */ +#define SCTLR_EIS (1U << 22) /* v8.5-ExS */ #define SCTLR_XP (1U << 23) /* up to v6; v7 onward RAO */ +#define SCTLR_SPAN (1U << 23) /* v8.1-PAN */ #define SCTLR_VE (1U << 24) /* up to v7 */ #define SCTLR_E0E (1U << 24) /* v8 onward, AArch64 only */ #define SCTLR_EE (1U << 25) #define SCTLR_L2 (1U << 26) /* up to v6, RAZ in v7 */ #define SCTLR_UCI (1U << 26) /* v8 onward, AArch64 only */ -#define SCTLR_NMFI (1U << 27) -#define SCTLR_TRE (1U << 28) -#define SCTLR_AFE (1U << 29) -#define SCTLR_TE (1U << 30) +#define SCTLR_NMFI (1U << 27) /* up to v7, RAZ in v7VE and v8 */ +#define SCTLR_EnDA (1U << 27) /* v8.3, AArch64 only */ +#define SCTLR_TRE (1U << 28) /* AArch32 only */ +#define SCTLR_nTLSMD_64 (1U << 28) /* v8.2-LSMAOC, AArch64 only */ +#define SCTLR_AFE (1U << 29) /* AArch32 only */ +#define SCTLR_LSMAOE_64 (1U << 29) /* v8.2-LSMAOC, AArch64 only */ +#define SCTLR_TE (1U << 30) /* AArch32 only */ +#define SCTLR_EnIB (1U << 30) /* v8.3, AArch64 only */ +#define SCTLR_EnIA (1U << 31) /* v8.3, AArch64 only */ +#define SCTLR_BT0 (1ULL << 35) /* v8.5-BTI */ +#define SCTLR_BT1 (1ULL << 36) /* v8.5-BTI */ +#define SCTLR_ITFSB (1ULL << 37) /* v8.5-MemTag */ +#define SCTLR_TCF0 (3ULL << 38) /* v8.5-MemTag */ +#define SCTLR_TCF (3ULL << 40) /* v8.5-MemTag */ +#define SCTLR_ATA0 (1ULL << 42) /* v8.5-MemTag */ +#define SCTLR_ATA (1ULL << 43) /* v8.5-MemTag */ +#define SCTLR_DSSBS (1ULL << 44) /* v8.5 */ #define CPTR_TCPAC (1U << 31) #define CPTR_TTA (1U << 20) @@ -1029,7 +1103,8 @@ void pmccntr_sync(CPUARMState *env); #define MDCR_EPMAD (1U << 21) #define MDCR_EDAD (1U << 20) -#define MDCR_SPME (1U << 17) +#define MDCR_SPME (1U << 17) /* MDCR_EL3 */ +#define MDCR_HPMD (1U << 17) /* MDCR_EL2 */ #define MDCR_SDD (1U << 16) #define MDCR_SPD (3U << 14) #define MDCR_TDRA (1U << 11) @@ -1039,6 +1114,7 @@ void pmccntr_sync(CPUARMState *env); #define MDCR_HPME (1U << 7) #define MDCR_TPM (1U << 6) #define MDCR_TPMCR (1U << 5) +#define MDCR_HPMN (0x1fU) /* Not all of the MDCR_EL3 bits are present in the 32-bit SDCR */ #define SDCR_VALID_MASK (MDCR_EPMAD | MDCR_EDAD | MDCR_SPME | MDCR_SPD) @@ -1618,6 +1694,15 @@ FIELD(ID_AA64MMFR1, PAN, 20, 4) FIELD(ID_AA64MMFR1, SPECSEI, 24, 4) FIELD(ID_AA64MMFR1, XNX, 28, 4) +FIELD(ID_DFR0, COPDBG, 0, 4) +FIELD(ID_DFR0, COPSDBG, 4, 4) +FIELD(ID_DFR0, MMAPDBG, 8, 4) +FIELD(ID_DFR0, COPTRC, 12, 4) +FIELD(ID_DFR0, MMAPTRC, 16, 4) +FIELD(ID_DFR0, MPROFDBG, 20, 4) +FIELD(ID_DFR0, PERFMON, 24, 4) +FIELD(ID_DFR0, TRACEFILT, 28, 4) + QEMU_BUILD_BUG_ON(ARRAY_SIZE(((ARMCPU *)0)->ccsidr) <= R_V7M_CSSELR_INDEX_MASK); /* If adding a feature bit which corresponds to a Linux ELF @@ -2707,54 +2792,23 @@ static inline int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx) } /* Return the MMU index for a v7M CPU in the specified security and - * privilege state + * privilege state. */ -static inline ARMMMUIdx arm_v7m_mmu_idx_for_secstate_and_priv(CPUARMState *env, - bool secstate, - bool priv) -{ - ARMMMUIdx mmu_idx = ARM_MMU_IDX_M; - - if (priv) { - mmu_idx |= ARM_MMU_IDX_M_PRIV; - } - - if (armv7m_nvic_neg_prio_requested(env->nvic, secstate)) { - mmu_idx |= ARM_MMU_IDX_M_NEGPRI; - } - - if (secstate) { - mmu_idx |= ARM_MMU_IDX_M_S; - } - - return mmu_idx; -} +ARMMMUIdx arm_v7m_mmu_idx_for_secstate_and_priv(CPUARMState *env, + bool secstate, bool priv); /* Return the MMU index for a v7M CPU in the specified security state */ -static inline ARMMMUIdx arm_v7m_mmu_idx_for_secstate(CPUARMState *env, - bool secstate) -{ - bool priv = arm_current_el(env) != 0; - - return arm_v7m_mmu_idx_for_secstate_and_priv(env, secstate, priv); -} - -/* Determine the current mmu_idx to use for normal loads/stores */ -static inline int cpu_mmu_index(CPUARMState *env, bool ifetch) -{ - int el = arm_current_el(env); +ARMMMUIdx arm_v7m_mmu_idx_for_secstate(CPUARMState *env, bool secstate); - if (arm_feature(env, ARM_FEATURE_M)) { - ARMMMUIdx mmu_idx = arm_v7m_mmu_idx_for_secstate(env, env->v7m.secure); - - return arm_to_core_mmu_idx(mmu_idx); - } - - if (el < 2 && arm_is_secure_below_el3(env)) { - return arm_to_core_mmu_idx(ARMMMUIdx_S1SE0 + el); - } - return el; -} +/** + * cpu_mmu_index: + * @env: The cpu environment + * @ifetch: True for code access, false for data access. + * + * Return the core mmu index for the current translation regime. + * This function is used by generic TCG code paths. + */ +int cpu_mmu_index(CPUARMState *env, bool ifetch); /* Indexes used when registering address spaces with cpu_address_space_init */ typedef enum ARMASIdx { @@ -2976,10 +3030,10 @@ FIELD(TBFLAG_A32, HANDLER, 21, 1) FIELD(TBFLAG_A32, STACKCHECK, 22, 1) /* Bit usage when in AArch64 state */ -FIELD(TBFLAG_A64, TBI0, 0, 1) -FIELD(TBFLAG_A64, TBI1, 1, 1) +FIELD(TBFLAG_A64, TBII, 0, 2) FIELD(TBFLAG_A64, SVEEXC_EL, 2, 2) FIELD(TBFLAG_A64, ZCR_LEN, 4, 4) +FIELD(TBFLAG_A64, PAUTH_ACTIVE, 8, 1) static inline bool bswap_code(bool sctlr_b) { @@ -3012,41 +3066,6 @@ static inline bool arm_cpu_bswap_data(CPUARMState *env) } #endif -#ifndef CONFIG_USER_ONLY -/** - * arm_regime_tbi0: - * @env: CPUARMState - * @mmu_idx: MMU index indicating required translation regime - * - * Extracts the TBI0 value from the appropriate TCR for the current EL - * - * Returns: the TBI0 value. - */ -uint32_t arm_regime_tbi0(CPUARMState *env, ARMMMUIdx mmu_idx); - -/** - * arm_regime_tbi1: - * @env: CPUARMState - * @mmu_idx: MMU index indicating required translation regime - * - * Extracts the TBI1 value from the appropriate TCR for the current EL - * - * Returns: the TBI1 value. - */ -uint32_t arm_regime_tbi1(CPUARMState *env, ARMMMUIdx mmu_idx); -#else -/* We can't handle tagged addresses properly in user-only mode */ -static inline uint32_t arm_regime_tbi0(CPUARMState *env, ARMMMUIdx mmu_idx) -{ - return 0; -} - -static inline uint32_t arm_regime_tbi1(CPUARMState *env, ARMMMUIdx mmu_idx) -{ - return 0; -} -#endif - void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, target_ulong *cs_base, uint32_t *flags); @@ -3264,6 +3283,21 @@ static inline bool isar_feature_aa64_fcma(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, FCMA) != 0; } +static inline bool isar_feature_aa64_pauth(const ARMISARegisters *id) +{ + /* + * Note that while QEMU will only implement the architected algorithm + * QARMA, and thus APA+GPA, the host cpu for kvm may use implementation + * defined algorithms, and thus API+GPI, and this predicate controls + * migration of the 128-bit keys. + */ + return (id->id_aa64isar1 & + (FIELD_DP64(0, ID_AA64ISAR1, APA, 0xf) | + FIELD_DP64(0, ID_AA64ISAR1, API, 0xf) | + FIELD_DP64(0, ID_AA64ISAR1, GPA, 0xf) | + FIELD_DP64(0, ID_AA64ISAR1, GPI, 0xf))) != 0; +} + static inline bool isar_feature_aa64_fp16(const ARMISARegisters *id) { /* We always set the AdvSIMD and FP fields identically wrt FP16. */ diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index 4b544a1c58..e9bc461c36 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -138,8 +138,6 @@ static void aarch64_a57_initfn(Object *obj) cpu->isar.id_isar6 = 0; cpu->isar.id_aa64pfr0 = 0x00002222; cpu->id_aa64dfr0 = 0x10305106; - cpu->pmceid0 = 0x00000000; - cpu->pmceid1 = 0x00000000; cpu->isar.id_aa64isar0 = 0x00011120; cpu->isar.id_aa64mmfr0 = 0x00001124; cpu->dbgdidr = 0x3516d000; @@ -246,8 +244,6 @@ static void aarch64_a72_initfn(Object *obj) cpu->isar.id_isar5 = 0x00011121; cpu->isar.id_aa64pfr0 = 0x00002222; cpu->id_aa64dfr0 = 0x10305106; - cpu->pmceid0 = 0x00000000; - cpu->pmceid1 = 0x00000000; cpu->isar.id_aa64isar0 = 0x00011120; cpu->isar.id_aa64mmfr0 = 0x00001124; cpu->dbgdidr = 0x3516d000; @@ -285,6 +281,38 @@ static void cpu_max_set_sve_vq(Object *obj, Visitor *v, const char *name, error_propagate(errp, err); } +#ifdef CONFIG_USER_ONLY +static void cpu_max_get_packey(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + ARMCPU *cpu = ARM_CPU(obj); + const uint64_t *bit = opaque; + bool enabled = (cpu->env.cp15.sctlr_el[1] & *bit) != 0; + + visit_type_bool(v, name, &enabled, errp); +} + +static void cpu_max_set_packey(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + ARMCPU *cpu = ARM_CPU(obj); + Error *err = NULL; + const uint64_t *bit = opaque; + bool enabled; + + visit_type_bool(v, name, &enabled, errp); + + if (!err) { + if (enabled) { + cpu->env.cp15.sctlr_el[1] |= *bit; + } else { + cpu->env.cp15.sctlr_el[1] &= ~*bit; + } + } + error_propagate(errp, err); +} +#endif + /* -cpu max: if KVM is enabled, like -cpu host (best possible with this host); * otherwise, a CPU with as many features enabled as our emulation supports. * The version of '-cpu max' for qemu-system-arm is defined in cpu.c; @@ -316,6 +344,10 @@ static void aarch64_max_initfn(Object *obj) t = cpu->isar.id_aa64isar1; t = FIELD_DP64(t, ID_AA64ISAR1, FCMA, 1); + t = FIELD_DP64(t, ID_AA64ISAR1, APA, 1); /* PAuth, architected only */ + t = FIELD_DP64(t, ID_AA64ISAR1, API, 0); + t = FIELD_DP64(t, ID_AA64ISAR1, GPA, 1); + t = FIELD_DP64(t, ID_AA64ISAR1, GPI, 0); cpu->isar.id_aa64isar1 = t; t = cpu->isar.id_aa64pfr0; @@ -356,6 +388,34 @@ static void aarch64_max_initfn(Object *obj) */ cpu->ctr = 0x80038003; /* 32 byte I and D cacheline size, VIPT icache */ cpu->dcz_blocksize = 7; /* 512 bytes */ + + /* + * Note that Linux will enable enable all of the keys at once. + * But doing it this way will allow experimentation beyond that. + */ + { + static const uint64_t apia_bit = SCTLR_EnIA; + static const uint64_t apib_bit = SCTLR_EnIB; + static const uint64_t apda_bit = SCTLR_EnDA; + static const uint64_t apdb_bit = SCTLR_EnDB; + + object_property_add(obj, "apia", "bool", cpu_max_get_packey, + cpu_max_set_packey, NULL, + (void *)&apia_bit, &error_fatal); + object_property_add(obj, "apib", "bool", cpu_max_get_packey, + cpu_max_set_packey, NULL, + (void *)&apib_bit, &error_fatal); + object_property_add(obj, "apda", "bool", cpu_max_get_packey, + cpu_max_set_packey, NULL, + (void *)&apda_bit, &error_fatal); + object_property_add(obj, "apdb", "bool", cpu_max_get_packey, + cpu_max_set_packey, NULL, + (void *)&apdb_bit, &error_fatal); + + /* Enable all PAC keys by default. */ + cpu->env.cp15.sctlr_el[1] |= SCTLR_EnIA | SCTLR_EnIB; + cpu->env.cp15.sctlr_el[1] |= SCTLR_EnDA | SCTLR_EnDB; + } #endif cpu->sve_max_vq = ARM_MAX_VQ; diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index 61799d20e1..101fa6d3ea 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -887,6 +887,161 @@ uint32_t HELPER(advsimd_f16touinth)(uint32_t a, void *fpstp) return float16_to_uint16(a, fpst); } +static int el_from_spsr(uint32_t spsr) +{ + /* Return the exception level that this SPSR is requesting a return to, + * or -1 if it is invalid (an illegal return) + */ + if (spsr & PSTATE_nRW) { + switch (spsr & CPSR_M) { + case ARM_CPU_MODE_USR: + return 0; + case ARM_CPU_MODE_HYP: + return 2; + case ARM_CPU_MODE_FIQ: + case ARM_CPU_MODE_IRQ: + case ARM_CPU_MODE_SVC: + case ARM_CPU_MODE_ABT: + case ARM_CPU_MODE_UND: + case ARM_CPU_MODE_SYS: + return 1; + case ARM_CPU_MODE_MON: + /* Returning to Mon from AArch64 is never possible, + * so this is an illegal return. + */ + default: + return -1; + } + } else { + if (extract32(spsr, 1, 1)) { + /* Return with reserved M[1] bit set */ + return -1; + } + if (extract32(spsr, 0, 4) == 1) { + /* return to EL0 with M[0] bit set */ + return -1; + } + return extract32(spsr, 2, 2); + } +} + +void HELPER(exception_return)(CPUARMState *env, uint64_t new_pc) +{ + int cur_el = arm_current_el(env); + unsigned int spsr_idx = aarch64_banked_spsr_index(cur_el); + uint32_t spsr = env->banked_spsr[spsr_idx]; + int new_el; + bool return_to_aa64 = (spsr & PSTATE_nRW) == 0; + + aarch64_save_sp(env, cur_el); + + arm_clear_exclusive(env); + + /* We must squash the PSTATE.SS bit to zero unless both of the + * following hold: + * 1. debug exceptions are currently disabled + * 2. singlestep will be active in the EL we return to + * We check 1 here and 2 after we've done the pstate/cpsr write() to + * transition to the EL we're going to. + */ + if (arm_generate_debug_exceptions(env)) { + spsr &= ~PSTATE_SS; + } + + new_el = el_from_spsr(spsr); + if (new_el == -1) { + goto illegal_return; + } + if (new_el > cur_el + || (new_el == 2 && !arm_feature(env, ARM_FEATURE_EL2))) { + /* Disallow return to an EL which is unimplemented or higher + * than the current one. + */ + goto illegal_return; + } + + if (new_el != 0 && arm_el_is_aa64(env, new_el) != return_to_aa64) { + /* Return to an EL which is configured for a different register width */ + goto illegal_return; + } + + if (new_el == 2 && arm_is_secure_below_el3(env)) { + /* Return to the non-existent secure-EL2 */ + goto illegal_return; + } + + if (new_el == 1 && (arm_hcr_el2_eff(env) & HCR_TGE)) { + goto illegal_return; + } + + qemu_mutex_lock_iothread(); + arm_call_pre_el_change_hook(arm_env_get_cpu(env)); + qemu_mutex_unlock_iothread(); + + if (!return_to_aa64) { + env->aarch64 = 0; + /* We do a raw CPSR write because aarch64_sync_64_to_32() + * will sort the register banks out for us, and we've already + * caught all the bad-mode cases in el_from_spsr(). + */ + cpsr_write(env, spsr, ~0, CPSRWriteRaw); + if (!arm_singlestep_active(env)) { + env->uncached_cpsr &= ~PSTATE_SS; + } + aarch64_sync_64_to_32(env); + + if (spsr & CPSR_T) { + env->regs[15] = new_pc & ~0x1; + } else { + env->regs[15] = new_pc & ~0x3; + } + qemu_log_mask(CPU_LOG_INT, "Exception return from AArch64 EL%d to " + "AArch32 EL%d PC 0x%" PRIx32 "\n", + cur_el, new_el, env->regs[15]); + } else { + env->aarch64 = 1; + pstate_write(env, spsr); + if (!arm_singlestep_active(env)) { + env->pstate &= ~PSTATE_SS; + } + aarch64_restore_sp(env, new_el); + env->pc = new_pc; + qemu_log_mask(CPU_LOG_INT, "Exception return from AArch64 EL%d to " + "AArch64 EL%d PC 0x%" PRIx64 "\n", + cur_el, new_el, env->pc); + } + /* + * Note that cur_el can never be 0. If new_el is 0, then + * el0_a64 is return_to_aa64, else el0_a64 is ignored. + */ + aarch64_sve_change_el(env, cur_el, new_el, return_to_aa64); + + qemu_mutex_lock_iothread(); + arm_call_el_change_hook(arm_env_get_cpu(env)); + qemu_mutex_unlock_iothread(); + + return; + +illegal_return: + /* Illegal return events of various kinds have architecturally + * mandated behaviour: + * restore NZCV and DAIF from SPSR_ELx + * set PSTATE.IL + * restore PC from ELR_ELx + * no change to exception level, execution state or stack pointer + */ + env->pstate |= PSTATE_IL; + env->pc = new_pc; + spsr &= PSTATE_NZCV | PSTATE_DAIF; + spsr |= pstate_read(env) & ~(PSTATE_NZCV | PSTATE_DAIF); + pstate_write(env, spsr); + if (!arm_singlestep_active(env)) { + env->pstate &= ~PSTATE_SS; + } + qemu_log_mask(LOG_GUEST_ERROR, "Illegal exception return at EL%d: " + "resuming execution at 0x%" PRIx64 "\n", cur_el, env->pc); +} + /* * Square Root and Reciprocal square root */ diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h index 9d3a907049..aff8d6c9f3 100644 --- a/target/arm/helper-a64.h +++ b/target/arm/helper-a64.h @@ -85,3 +85,17 @@ DEF_HELPER_2(advsimd_rinth, f16, f16, ptr) DEF_HELPER_2(advsimd_f16tosinth, i32, f16, ptr) DEF_HELPER_2(advsimd_f16touinth, i32, f16, ptr) DEF_HELPER_2(sqrt_f16, f16, f16, ptr) + +DEF_HELPER_2(exception_return, void, env, i64) + +DEF_HELPER_FLAGS_3(pacia, TCG_CALL_NO_WG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(pacib, TCG_CALL_NO_WG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(pacda, TCG_CALL_NO_WG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(pacdb, TCG_CALL_NO_WG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(pacga, TCG_CALL_NO_WG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(autia, TCG_CALL_NO_WG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(autib, TCG_CALL_NO_WG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(autda, TCG_CALL_NO_WG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(autdb, TCG_CALL_NO_WG, i64, env, i64, i64) +DEF_HELPER_FLAGS_2(xpaci, TCG_CALL_NO_RWG_SE, i64, env, i64) +DEF_HELPER_FLAGS_2(xpacd, TCG_CALL_NO_RWG_SE, i64, env, i64) diff --git a/target/arm/helper.c b/target/arm/helper.c index f00c141ef9..92666e5208 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -15,6 +15,7 @@ #include "arm_ldst.h" #include <zlib.h> /* For crc32 */ #include "exec/semihost.h" +#include "sysemu/cpus.h" #include "sysemu/kvm.h" #include "fpu/softfloat.h" #include "qemu/range.h" @@ -976,10 +977,29 @@ static const ARMCPRegInfo v6_cp_reginfo[] = { /* Definitions for the PMU registers */ #define PMCRN_MASK 0xf800 #define PMCRN_SHIFT 11 +#define PMCRDP 0x10 #define PMCRD 0x8 #define PMCRC 0x4 +#define PMCRP 0x2 #define PMCRE 0x1 +#define PMXEVTYPER_P 0x80000000 +#define PMXEVTYPER_U 0x40000000 +#define PMXEVTYPER_NSK 0x20000000 +#define PMXEVTYPER_NSU 0x10000000 +#define PMXEVTYPER_NSH 0x08000000 +#define PMXEVTYPER_M 0x04000000 +#define PMXEVTYPER_MT 0x02000000 +#define PMXEVTYPER_EVTCOUNT 0x0000ffff +#define PMXEVTYPER_MASK (PMXEVTYPER_P | PMXEVTYPER_U | PMXEVTYPER_NSK | \ + PMXEVTYPER_NSU | PMXEVTYPER_NSH | \ + PMXEVTYPER_M | PMXEVTYPER_MT | \ + PMXEVTYPER_EVTCOUNT) + +#define PMCCFILTR 0xf8000000 +#define PMCCFILTR_M PMXEVTYPER_M +#define PMCCFILTR_EL0 (PMCCFILTR | PMCCFILTR_M) + static inline uint32_t pmu_num_counters(CPUARMState *env) { return (env->cp15.c9_pmcr & PMCRN_MASK) >> PMCRN_SHIFT; @@ -991,6 +1011,128 @@ static inline uint64_t pmu_counter_mask(CPUARMState *env) return (1 << 31) | ((1 << pmu_num_counters(env)) - 1); } +typedef struct pm_event { + uint16_t number; /* PMEVTYPER.evtCount is 16 bits wide */ + /* If the event is supported on this CPU (used to generate PMCEID[01]) */ + bool (*supported)(CPUARMState *); + /* + * Retrieve the current count of the underlying event. The programmed + * counters hold a difference from the return value from this function + */ + uint64_t (*get_count)(CPUARMState *); +} pm_event; + +static bool event_always_supported(CPUARMState *env) +{ + return true; +} + +static uint64_t swinc_get_count(CPUARMState *env) +{ + /* + * SW_INCR events are written directly to the pmevcntr's by writes to + * PMSWINC, so there is no underlying count maintained by the PMU itself + */ + return 0; +} + +/* + * Return the underlying cycle count for the PMU cycle counters. If we're in + * usermode, simply return 0. + */ +static uint64_t cycles_get_count(CPUARMState *env) +{ +#ifndef CONFIG_USER_ONLY + return muldiv64(qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL), + ARM_CPU_FREQ, NANOSECONDS_PER_SECOND); +#else + return cpu_get_host_ticks(); +#endif +} + +#ifndef CONFIG_USER_ONLY +static bool instructions_supported(CPUARMState *env) +{ + return use_icount == 1 /* Precise instruction counting */; +} + +static uint64_t instructions_get_count(CPUARMState *env) +{ + return (uint64_t)cpu_get_icount_raw(); +} +#endif + +static const pm_event pm_events[] = { + { .number = 0x000, /* SW_INCR */ + .supported = event_always_supported, + .get_count = swinc_get_count, + }, +#ifndef CONFIG_USER_ONLY + { .number = 0x008, /* INST_RETIRED, Instruction architecturally executed */ + .supported = instructions_supported, + .get_count = instructions_get_count, + }, + { .number = 0x011, /* CPU_CYCLES, Cycle */ + .supported = event_always_supported, + .get_count = cycles_get_count, + } +#endif +}; + +/* + * Note: Before increasing MAX_EVENT_ID beyond 0x3f into the 0x40xx range of + * events (i.e. the statistical profiling extension), this implementation + * should first be updated to something sparse instead of the current + * supported_event_map[] array. + */ +#define MAX_EVENT_ID 0x11 +#define UNSUPPORTED_EVENT UINT16_MAX +static uint16_t supported_event_map[MAX_EVENT_ID + 1]; + +/* + * Called upon initialization to build PMCEID0_EL0 or PMCEID1_EL0 (indicated by + * 'which'). We also use it to build a map of ARM event numbers to indices in + * our pm_events array. + * + * Note: Events in the 0x40XX range are not currently supported. + */ +uint64_t get_pmceid(CPUARMState *env, unsigned which) +{ + uint64_t pmceid = 0; + unsigned int i; + + assert(which <= 1); + + for (i = 0; i < ARRAY_SIZE(supported_event_map); i++) { + supported_event_map[i] = UNSUPPORTED_EVENT; + } + + for (i = 0; i < ARRAY_SIZE(pm_events); i++) { + const pm_event *cnt = &pm_events[i]; + assert(cnt->number <= MAX_EVENT_ID); + /* We do not currently support events in the 0x40xx range */ + assert(cnt->number <= 0x3f); + + if ((cnt->number & 0x20) == (which << 6) && + cnt->supported(env)) { + pmceid |= (1 << (cnt->number & 0x1f)); + supported_event_map[cnt->number] = i; + } + } + return pmceid; +} + +/* + * Check at runtime whether a PMU event is supported for the current machine + */ +static bool event_supported(uint16_t number) +{ + if (number > MAX_EVENT_ID) { + return false; + } + return supported_event_map[number] != UNSUPPORTED_EVENT; +} + static CPAccessResult pmreg_access(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) { @@ -1044,8 +1186,6 @@ static CPAccessResult pmreg_access_swinc(CPUARMState *env, return pmreg_access(env, ri, isread); } -#ifndef CONFIG_USER_ONLY - static CPAccessResult pmreg_access_selr(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) @@ -1075,68 +1215,222 @@ static CPAccessResult pmreg_access_ccntr(CPUARMState *env, return pmreg_access(env, ri, isread); } -static inline bool arm_ccnt_enabled(CPUARMState *env) +/* Returns true if the counter (pass 31 for PMCCNTR) should count events using + * the current EL, security state, and register configuration. + */ +static bool pmu_counter_enabled(CPUARMState *env, uint8_t counter) { - /* This does not support checking PMCCFILTR_EL0 register */ + uint64_t filter; + bool e, p, u, nsk, nsu, nsh, m; + bool enabled, prohibited, filtered; + bool secure = arm_is_secure(env); + int el = arm_current_el(env); + uint8_t hpmn = env->cp15.mdcr_el2 & MDCR_HPMN; - if (!(env->cp15.c9_pmcr & PMCRE) || !(env->cp15.c9_pmcnten & (1 << 31))) { - return false; + if (!arm_feature(env, ARM_FEATURE_EL2) || + (counter < hpmn || counter == 31)) { + e = env->cp15.c9_pmcr & PMCRE; + } else { + e = env->cp15.mdcr_el2 & MDCR_HPME; } + enabled = e && (env->cp15.c9_pmcnten & (1 << counter)); - return true; + if (!secure) { + if (el == 2 && (counter < hpmn || counter == 31)) { + prohibited = env->cp15.mdcr_el2 & MDCR_HPMD; + } else { + prohibited = false; + } + } else { + prohibited = arm_feature(env, ARM_FEATURE_EL3) && + (env->cp15.mdcr_el3 & MDCR_SPME); + } + + if (prohibited && counter == 31) { + prohibited = env->cp15.c9_pmcr & PMCRDP; + } + + if (counter == 31) { + filter = env->cp15.pmccfiltr_el0; + } else { + filter = env->cp15.c14_pmevtyper[counter]; + } + + p = filter & PMXEVTYPER_P; + u = filter & PMXEVTYPER_U; + nsk = arm_feature(env, ARM_FEATURE_EL3) && (filter & PMXEVTYPER_NSK); + nsu = arm_feature(env, ARM_FEATURE_EL3) && (filter & PMXEVTYPER_NSU); + nsh = arm_feature(env, ARM_FEATURE_EL2) && (filter & PMXEVTYPER_NSH); + m = arm_el_is_aa64(env, 1) && + arm_feature(env, ARM_FEATURE_EL3) && (filter & PMXEVTYPER_M); + + if (el == 0) { + filtered = secure ? u : u != nsu; + } else if (el == 1) { + filtered = secure ? p : p != nsk; + } else if (el == 2) { + filtered = !nsh; + } else { /* EL3 */ + filtered = m != p; + } + + if (counter != 31) { + /* + * If not checking PMCCNTR, ensure the counter is setup to an event we + * support + */ + uint16_t event = filter & PMXEVTYPER_EVTCOUNT; + if (!event_supported(event)) { + return false; + } + } + + return enabled && !prohibited && !filtered; +} + +/* + * Ensure c15_ccnt is the guest-visible count so that operations such as + * enabling/disabling the counter or filtering, modifying the count itself, + * etc. can be done logically. This is essentially a no-op if the counter is + * not enabled at the time of the call. + */ +void pmccntr_op_start(CPUARMState *env) +{ + uint64_t cycles = cycles_get_count(env); + + if (pmu_counter_enabled(env, 31)) { + uint64_t eff_cycles = cycles; + if (env->cp15.c9_pmcr & PMCRD) { + /* Increment once every 64 processor clock cycles */ + eff_cycles /= 64; + } + + env->cp15.c15_ccnt = eff_cycles - env->cp15.c15_ccnt_delta; + } + env->cp15.c15_ccnt_delta = cycles; } -void pmccntr_sync(CPUARMState *env) +/* + * If PMCCNTR is enabled, recalculate the delta between the clock and the + * guest-visible count. A call to pmccntr_op_finish should follow every call to + * pmccntr_op_start. + */ +void pmccntr_op_finish(CPUARMState *env) { - uint64_t temp_ticks; + if (pmu_counter_enabled(env, 31)) { + uint64_t prev_cycles = env->cp15.c15_ccnt_delta; + + if (env->cp15.c9_pmcr & PMCRD) { + /* Increment once every 64 processor clock cycles */ + prev_cycles /= 64; + } + + env->cp15.c15_ccnt_delta = prev_cycles - env->cp15.c15_ccnt; + } +} + +static void pmevcntr_op_start(CPUARMState *env, uint8_t counter) +{ + + uint16_t event = env->cp15.c14_pmevtyper[counter] & PMXEVTYPER_EVTCOUNT; + uint64_t count = 0; + if (event_supported(event)) { + uint16_t event_idx = supported_event_map[event]; + count = pm_events[event_idx].get_count(env); + } + + if (pmu_counter_enabled(env, counter)) { + env->cp15.c14_pmevcntr[counter] = + count - env->cp15.c14_pmevcntr_delta[counter]; + } + env->cp15.c14_pmevcntr_delta[counter] = count; +} - temp_ticks = muldiv64(qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL), - ARM_CPU_FREQ, NANOSECONDS_PER_SECOND); +static void pmevcntr_op_finish(CPUARMState *env, uint8_t counter) +{ + if (pmu_counter_enabled(env, counter)) { + env->cp15.c14_pmevcntr_delta[counter] -= + env->cp15.c14_pmevcntr[counter]; + } +} - if (env->cp15.c9_pmcr & PMCRD) { - /* Increment once every 64 processor clock cycles */ - temp_ticks /= 64; +void pmu_op_start(CPUARMState *env) +{ + unsigned int i; + pmccntr_op_start(env); + for (i = 0; i < pmu_num_counters(env); i++) { + pmevcntr_op_start(env, i); } +} - if (arm_ccnt_enabled(env)) { - env->cp15.c15_ccnt = temp_ticks - env->cp15.c15_ccnt; +void pmu_op_finish(CPUARMState *env) +{ + unsigned int i; + pmccntr_op_finish(env); + for (i = 0; i < pmu_num_counters(env); i++) { + pmevcntr_op_finish(env, i); } } +void pmu_pre_el_change(ARMCPU *cpu, void *ignored) +{ + pmu_op_start(&cpu->env); +} + +void pmu_post_el_change(ARMCPU *cpu, void *ignored) +{ + pmu_op_finish(&cpu->env); +} + static void pmcr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { - pmccntr_sync(env); + pmu_op_start(env); if (value & PMCRC) { /* The counter has been reset */ env->cp15.c15_ccnt = 0; } + if (value & PMCRP) { + unsigned int i; + for (i = 0; i < pmu_num_counters(env); i++) { + env->cp15.c14_pmevcntr[i] = 0; + } + } + /* only the DP, X, D and E bits are writable */ env->cp15.c9_pmcr &= ~0x39; env->cp15.c9_pmcr |= (value & 0x39); - pmccntr_sync(env); + pmu_op_finish(env); } -static uint64_t pmccntr_read(CPUARMState *env, const ARMCPRegInfo *ri) +static void pmswinc_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { - uint64_t total_ticks; - - if (!arm_ccnt_enabled(env)) { - /* Counter is disabled, do not change value */ - return env->cp15.c15_ccnt; + unsigned int i; + for (i = 0; i < pmu_num_counters(env); i++) { + /* Increment a counter's count iff: */ + if ((value & (1 << i)) && /* counter's bit is set */ + /* counter is enabled and not filtered */ + pmu_counter_enabled(env, i) && + /* counter is SW_INCR */ + (env->cp15.c14_pmevtyper[i] & PMXEVTYPER_EVTCOUNT) == 0x0) { + pmevcntr_op_start(env, i); + env->cp15.c14_pmevcntr[i]++; + pmevcntr_op_finish(env, i); + } } +} - total_ticks = muldiv64(qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL), - ARM_CPU_FREQ, NANOSECONDS_PER_SECOND); - - if (env->cp15.c9_pmcr & PMCRD) { - /* Increment once every 64 processor clock cycles */ - total_ticks /= 64; - } - return total_ticks - env->cp15.c15_ccnt; +static uint64_t pmccntr_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + uint64_t ret; + pmccntr_op_start(env); + ret = env->cp15.c15_ccnt; + pmccntr_op_finish(env); + return ret; } static void pmselr_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -1153,22 +1447,9 @@ static void pmselr_write(CPUARMState *env, const ARMCPRegInfo *ri, static void pmccntr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { - uint64_t total_ticks; - - if (!arm_ccnt_enabled(env)) { - /* Counter is disabled, set the absolute value */ - env->cp15.c15_ccnt = value; - return; - } - - total_ticks = muldiv64(qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL), - ARM_CPU_FREQ, NANOSECONDS_PER_SECOND); - - if (env->cp15.c9_pmcr & PMCRD) { - /* Increment once every 64 processor clock cycles */ - total_ticks /= 64; - } - env->cp15.c15_ccnt = total_ticks - value; + pmccntr_op_start(env); + env->cp15.c15_ccnt = value; + pmccntr_op_finish(env); } static void pmccntr_write32(CPUARMState *env, const ARMCPRegInfo *ri, @@ -1179,20 +1460,28 @@ static void pmccntr_write32(CPUARMState *env, const ARMCPRegInfo *ri, pmccntr_write(env, ri, deposit64(cur_val, 0, 32, value)); } -#else /* CONFIG_USER_ONLY */ - -void pmccntr_sync(CPUARMState *env) +static void pmccfiltr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { + pmccntr_op_start(env); + env->cp15.pmccfiltr_el0 = value & PMCCFILTR_EL0; + pmccntr_op_finish(env); } -#endif - -static void pmccfiltr_write(CPUARMState *env, const ARMCPRegInfo *ri, +static void pmccfiltr_write_a32(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { - pmccntr_sync(env); - env->cp15.pmccfiltr_el0 = value & 0xfc000000; - pmccntr_sync(env); + pmccntr_op_start(env); + /* M is not accessible from AArch32 */ + env->cp15.pmccfiltr_el0 = (env->cp15.pmccfiltr_el0 & PMCCFILTR_M) | + (value & PMCCFILTR); + pmccntr_op_finish(env); +} + +static uint64_t pmccfiltr_read_a32(CPUARMState *env, const ARMCPRegInfo *ri) +{ + /* M is not visible in AArch32 */ + return env->cp15.pmccfiltr_el0 & PMCCFILTR; } static void pmcntenset_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -1216,30 +1505,181 @@ static void pmovsr_write(CPUARMState *env, const ARMCPRegInfo *ri, env->cp15.c9_pmovsr &= ~value; } -static void pmxevtyper_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void pmovsset_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { + value &= pmu_counter_mask(env); + env->cp15.c9_pmovsr |= value; +} + +static void pmevtyper_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value, const uint8_t counter) +{ + if (counter == 31) { + pmccfiltr_write(env, ri, value); + } else if (counter < pmu_num_counters(env)) { + pmevcntr_op_start(env, counter); + + /* + * If this counter's event type is changing, store the current + * underlying count for the new type in c14_pmevcntr_delta[counter] so + * pmevcntr_op_finish has the correct baseline when it converts back to + * a delta. + */ + uint16_t old_event = env->cp15.c14_pmevtyper[counter] & + PMXEVTYPER_EVTCOUNT; + uint16_t new_event = value & PMXEVTYPER_EVTCOUNT; + if (old_event != new_event) { + uint64_t count = 0; + if (event_supported(new_event)) { + uint16_t event_idx = supported_event_map[new_event]; + count = pm_events[event_idx].get_count(env); + } + env->cp15.c14_pmevcntr_delta[counter] = count; + } + + env->cp15.c14_pmevtyper[counter] = value & PMXEVTYPER_MASK; + pmevcntr_op_finish(env, counter); + } /* Attempts to access PMXEVTYPER are CONSTRAINED UNPREDICTABLE when * PMSELR value is equal to or greater than the number of implemented * counters, but not equal to 0x1f. We opt to behave as a RAZ/WI. */ - if (env->cp15.c9_pmselr == 0x1f) { - pmccfiltr_write(env, ri, value); +} + +static uint64_t pmevtyper_read(CPUARMState *env, const ARMCPRegInfo *ri, + const uint8_t counter) +{ + if (counter == 31) { + return env->cp15.pmccfiltr_el0; + } else if (counter < pmu_num_counters(env)) { + return env->cp15.c14_pmevtyper[counter]; + } else { + /* + * We opt to behave as a RAZ/WI when attempts to access PMXEVTYPER + * are CONSTRAINED UNPREDICTABLE. See comments in pmevtyper_write(). + */ + return 0; } } +static void pmevtyper_writefn(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + uint8_t counter = ((ri->crm & 3) << 3) | (ri->opc2 & 7); + pmevtyper_write(env, ri, value, counter); +} + +static void pmevtyper_rawwrite(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + uint8_t counter = ((ri->crm & 3) << 3) | (ri->opc2 & 7); + env->cp15.c14_pmevtyper[counter] = value; + + /* + * pmevtyper_rawwrite is called between a pair of pmu_op_start and + * pmu_op_finish calls when loading saved state for a migration. Because + * we're potentially updating the type of event here, the value written to + * c14_pmevcntr_delta by the preceeding pmu_op_start call may be for a + * different counter type. Therefore, we need to set this value to the + * current count for the counter type we're writing so that pmu_op_finish + * has the correct count for its calculation. + */ + uint16_t event = value & PMXEVTYPER_EVTCOUNT; + if (event_supported(event)) { + uint16_t event_idx = supported_event_map[event]; + env->cp15.c14_pmevcntr_delta[counter] = + pm_events[event_idx].get_count(env); + } +} + +static uint64_t pmevtyper_readfn(CPUARMState *env, const ARMCPRegInfo *ri) +{ + uint8_t counter = ((ri->crm & 3) << 3) | (ri->opc2 & 7); + return pmevtyper_read(env, ri, counter); +} + +static void pmxevtyper_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + pmevtyper_write(env, ri, value, env->cp15.c9_pmselr & 31); +} + static uint64_t pmxevtyper_read(CPUARMState *env, const ARMCPRegInfo *ri) { - /* We opt to behave as a RAZ/WI when attempts to access PMXEVTYPER - * are CONSTRAINED UNPREDICTABLE. See comments in pmxevtyper_write(). + return pmevtyper_read(env, ri, env->cp15.c9_pmselr & 31); +} + +static void pmevcntr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value, uint8_t counter) +{ + if (counter < pmu_num_counters(env)) { + pmevcntr_op_start(env, counter); + env->cp15.c14_pmevcntr[counter] = value; + pmevcntr_op_finish(env, counter); + } + /* + * We opt to behave as a RAZ/WI when attempts to access PM[X]EVCNTR + * are CONSTRAINED UNPREDICTABLE. */ - if (env->cp15.c9_pmselr == 0x1f) { - return env->cp15.pmccfiltr_el0; +} + +static uint64_t pmevcntr_read(CPUARMState *env, const ARMCPRegInfo *ri, + uint8_t counter) +{ + if (counter < pmu_num_counters(env)) { + uint64_t ret; + pmevcntr_op_start(env, counter); + ret = env->cp15.c14_pmevcntr[counter]; + pmevcntr_op_finish(env, counter); + return ret; } else { + /* We opt to behave as a RAZ/WI when attempts to access PM[X]EVCNTR + * are CONSTRAINED UNPREDICTABLE. */ return 0; } } +static void pmevcntr_writefn(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + uint8_t counter = ((ri->crm & 3) << 3) | (ri->opc2 & 7); + pmevcntr_write(env, ri, value, counter); +} + +static uint64_t pmevcntr_readfn(CPUARMState *env, const ARMCPRegInfo *ri) +{ + uint8_t counter = ((ri->crm & 3) << 3) | (ri->opc2 & 7); + return pmevcntr_read(env, ri, counter); +} + +static void pmevcntr_rawwrite(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + uint8_t counter = ((ri->crm & 3) << 3) | (ri->opc2 & 7); + assert(counter < pmu_num_counters(env)); + env->cp15.c14_pmevcntr[counter] = value; + pmevcntr_write(env, ri, value, counter); +} + +static uint64_t pmevcntr_rawread(CPUARMState *env, const ARMCPRegInfo *ri) +{ + uint8_t counter = ((ri->crm & 3) << 3) | (ri->opc2 & 7); + assert(counter < pmu_num_counters(env)); + return env->cp15.c14_pmevcntr[counter]; +} + +static void pmxevcntr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + pmevcntr_write(env, ri, value, env->cp15.c9_pmselr & 31); +} + +static uint64_t pmxevcntr_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + return pmevcntr_read(env, ri, env->cp15.c9_pmselr & 31); +} + static void pmuserenr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -1368,7 +1808,7 @@ static const ARMCPRegInfo v7_cp_reginfo[] = { .access = PL1_W, .type = ARM_CP_NOP }, /* Performance monitors are implementation defined in v7, * but with an ARM recommended set of registers, which we - * follow (although we don't actually implement any counters) + * follow. * * Performance registers fall into three categories: * (a) always UNDEF in PL0, RW in PL1 (PMINTENSET, PMINTENCLR) @@ -1413,10 +1853,13 @@ static const ARMCPRegInfo v7_cp_reginfo[] = { .fieldoffset = offsetof(CPUARMState, cp15.c9_pmovsr), .writefn = pmovsr_write, .raw_writefn = raw_write }, - /* Unimplemented so WI. */ { .name = "PMSWINC", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 4, - .access = PL0_W, .accessfn = pmreg_access_swinc, .type = ARM_CP_NOP }, -#ifndef CONFIG_USER_ONLY + .access = PL0_W, .accessfn = pmreg_access_swinc, .type = ARM_CP_NO_RAW, + .writefn = pmswinc_write }, + { .name = "PMSWINC_EL0", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 12, .opc2 = 4, + .access = PL0_W, .accessfn = pmreg_access_swinc, .type = ARM_CP_NO_RAW, + .writefn = pmswinc_write }, { .name = "PMSELR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 5, .access = PL0_RW, .type = ARM_CP_ALIAS, .fieldoffset = offsetoflow32(CPUARMState, cp15.c9_pmselr), @@ -1435,26 +1878,39 @@ static const ARMCPRegInfo v7_cp_reginfo[] = { .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 13, .opc2 = 0, .access = PL0_RW, .accessfn = pmreg_access_ccntr, .type = ARM_CP_IO, - .readfn = pmccntr_read, .writefn = pmccntr_write, }, -#endif + .fieldoffset = offsetof(CPUARMState, cp15.c15_ccnt), + .readfn = pmccntr_read, .writefn = pmccntr_write, + .raw_readfn = raw_read, .raw_writefn = raw_write, }, + { .name = "PMCCFILTR", .cp = 15, .opc1 = 0, .crn = 14, .crm = 15, .opc2 = 7, + .writefn = pmccfiltr_write_a32, .readfn = pmccfiltr_read_a32, + .access = PL0_RW, .accessfn = pmreg_access, + .type = ARM_CP_ALIAS | ARM_CP_IO, + .resetvalue = 0, }, { .name = "PMCCFILTR_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 15, .opc2 = 7, - .writefn = pmccfiltr_write, + .writefn = pmccfiltr_write, .raw_writefn = raw_write, .access = PL0_RW, .accessfn = pmreg_access, .type = ARM_CP_IO, .fieldoffset = offsetof(CPUARMState, cp15.pmccfiltr_el0), .resetvalue = 0, }, { .name = "PMXEVTYPER", .cp = 15, .crn = 9, .crm = 13, .opc1 = 0, .opc2 = 1, - .access = PL0_RW, .type = ARM_CP_NO_RAW, .accessfn = pmreg_access, + .access = PL0_RW, .type = ARM_CP_NO_RAW | ARM_CP_IO, + .accessfn = pmreg_access, .writefn = pmxevtyper_write, .readfn = pmxevtyper_read }, { .name = "PMXEVTYPER_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 13, .opc2 = 1, - .access = PL0_RW, .type = ARM_CP_NO_RAW, .accessfn = pmreg_access, + .access = PL0_RW, .type = ARM_CP_NO_RAW | ARM_CP_IO, + .accessfn = pmreg_access, .writefn = pmxevtyper_write, .readfn = pmxevtyper_read }, - /* Unimplemented, RAZ/WI. */ { .name = "PMXEVCNTR", .cp = 15, .crn = 9, .crm = 13, .opc1 = 0, .opc2 = 2, - .access = PL0_RW, .type = ARM_CP_CONST, .resetvalue = 0, - .accessfn = pmreg_access_xevcntr }, + .access = PL0_RW, .type = ARM_CP_NO_RAW | ARM_CP_IO, + .accessfn = pmreg_access_xevcntr, + .writefn = pmxevcntr_write, .readfn = pmxevcntr_read }, + { .name = "PMXEVCNTR_EL0", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 13, .opc2 = 2, + .access = PL0_RW, .type = ARM_CP_NO_RAW | ARM_CP_IO, + .accessfn = pmreg_access_xevcntr, + .writefn = pmxevcntr_write, .readfn = pmxevcntr_read }, { .name = "PMUSERENR", .cp = 15, .crn = 9, .crm = 14, .opc1 = 0, .opc2 = 0, .access = PL0_R | PL1_RW, .accessfn = access_tpm, .fieldoffset = offsetoflow32(CPUARMState, cp15.c9_pmuserenr), @@ -1585,6 +2041,24 @@ static const ARMCPRegInfo v7mp_cp_reginfo[] = { REGINFO_SENTINEL }; +static const ARMCPRegInfo pmovsset_cp_reginfo[] = { + /* PMOVSSET is not implemented in v7 before v7ve */ + { .name = "PMOVSSET", .cp = 15, .opc1 = 0, .crn = 9, .crm = 14, .opc2 = 3, + .access = PL0_RW, .accessfn = pmreg_access, + .type = ARM_CP_ALIAS, + .fieldoffset = offsetoflow32(CPUARMState, cp15.c9_pmovsr), + .writefn = pmovsset_write, + .raw_writefn = raw_write }, + { .name = "PMOVSSET_EL0", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 14, .opc2 = 3, + .access = PL0_RW, .accessfn = pmreg_access, + .type = ARM_CP_ALIAS, + .fieldoffset = offsetof(CPUARMState, cp15.c9_pmovsr), + .writefn = pmovsset_write, + .raw_writefn = raw_write }, + REGINFO_SENTINEL +}; + static void teecr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -4284,7 +4758,7 @@ static const ARMCPRegInfo el2_cp_reginfo[] = { #endif /* The only field of MDCR_EL2 that has a defined architectural reset value * is MDCR_EL2.HPMN which should reset to the value of PMCR_EL0.N; but we - * don't impelment any PMU event counters, so using zero as a reset + * don't implement any PMU event counters, so using zero as a reset * value for MDCR_EL2 is okay */ { .name = "MDCR_EL2", .state = ARM_CP_STATE_BOTH, @@ -5061,6 +5535,70 @@ static CPAccessResult access_lor_other(CPUARMState *env, return access_lor_ns(env); } +#ifdef TARGET_AARCH64 +static CPAccessResult access_pauth(CPUARMState *env, const ARMCPRegInfo *ri, + bool isread) +{ + int el = arm_current_el(env); + + if (el < 2 && + arm_feature(env, ARM_FEATURE_EL2) && + !(arm_hcr_el2_eff(env) & HCR_APK)) { + return CP_ACCESS_TRAP_EL2; + } + if (el < 3 && + arm_feature(env, ARM_FEATURE_EL3) && + !(env->cp15.scr_el3 & SCR_APK)) { + return CP_ACCESS_TRAP_EL3; + } + return CP_ACCESS_OK; +} + +static const ARMCPRegInfo pauth_reginfo[] = { + { .name = "APDAKEYLO_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 2, .opc2 = 0, + .access = PL1_RW, .accessfn = access_pauth, + .fieldoffset = offsetof(CPUARMState, apda_key.lo) }, + { .name = "APDAKEYHI_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 2, .opc2 = 1, + .access = PL1_RW, .accessfn = access_pauth, + .fieldoffset = offsetof(CPUARMState, apda_key.hi) }, + { .name = "APDBKEYLO_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 2, .opc2 = 2, + .access = PL1_RW, .accessfn = access_pauth, + .fieldoffset = offsetof(CPUARMState, apdb_key.lo) }, + { .name = "APDBKEYHI_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 2, .opc2 = 3, + .access = PL1_RW, .accessfn = access_pauth, + .fieldoffset = offsetof(CPUARMState, apdb_key.hi) }, + { .name = "APGAKEYLO_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 3, .opc2 = 0, + .access = PL1_RW, .accessfn = access_pauth, + .fieldoffset = offsetof(CPUARMState, apga_key.lo) }, + { .name = "APGAKEYHI_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 3, .opc2 = 1, + .access = PL1_RW, .accessfn = access_pauth, + .fieldoffset = offsetof(CPUARMState, apga_key.hi) }, + { .name = "APIAKEYLO_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 1, .opc2 = 0, + .access = PL1_RW, .accessfn = access_pauth, + .fieldoffset = offsetof(CPUARMState, apia_key.lo) }, + { .name = "APIAKEYHI_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 1, .opc2 = 1, + .access = PL1_RW, .accessfn = access_pauth, + .fieldoffset = offsetof(CPUARMState, apia_key.hi) }, + { .name = "APIBKEYLO_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 1, .opc2 = 2, + .access = PL1_RW, .accessfn = access_pauth, + .fieldoffset = offsetof(CPUARMState, apib_key.lo) }, + { .name = "APIBKEYHI_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 1, .opc2 = 3, + .access = PL1_RW, .accessfn = access_pauth, + .fieldoffset = offsetof(CPUARMState, apib_key.hi) }, + REGINFO_SENTINEL +}; +#endif + void register_cp_regs_for_features(ARMCPU *cpu) { /* Register all the coprocessor registers based on feature bits */ @@ -5163,12 +5701,15 @@ void register_cp_regs_for_features(ARMCPU *cpu) !arm_feature(env, ARM_FEATURE_PMSA)) { define_arm_cp_regs(cpu, v7mp_cp_reginfo); } + if (arm_feature(env, ARM_FEATURE_V7VE)) { + define_arm_cp_regs(cpu, pmovsset_cp_reginfo); + } if (arm_feature(env, ARM_FEATURE_V7)) { /* v7 performance monitor control register: same implementor - * field as main ID register, and we implement only the cycle - * count register. + * field as main ID register, and we implement four counters in + * addition to the cycle count register. */ -#ifndef CONFIG_USER_ONLY + unsigned int i, pmcrn = 4; ARMCPRegInfo pmcr = { .name = "PMCR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 0, .access = PL0_RW, @@ -5183,12 +5724,48 @@ void register_cp_regs_for_features(ARMCPU *cpu) .access = PL0_RW, .accessfn = pmreg_access, .type = ARM_CP_IO, .fieldoffset = offsetof(CPUARMState, cp15.c9_pmcr), - .resetvalue = cpu->midr & 0xff000000, + .resetvalue = (cpu->midr & 0xff000000) | (pmcrn << PMCRN_SHIFT), .writefn = pmcr_write, .raw_writefn = raw_write, }; define_one_arm_cp_reg(cpu, &pmcr); define_one_arm_cp_reg(cpu, &pmcr64); -#endif + for (i = 0; i < pmcrn; i++) { + char *pmevcntr_name = g_strdup_printf("PMEVCNTR%d", i); + char *pmevcntr_el0_name = g_strdup_printf("PMEVCNTR%d_EL0", i); + char *pmevtyper_name = g_strdup_printf("PMEVTYPER%d", i); + char *pmevtyper_el0_name = g_strdup_printf("PMEVTYPER%d_EL0", i); + ARMCPRegInfo pmev_regs[] = { + { .name = pmevcntr_name, .cp = 15, .crn = 15, + .crm = 8 | (3 & (i >> 3)), .opc1 = 0, .opc2 = i & 7, + .access = PL0_RW, .type = ARM_CP_IO | ARM_CP_ALIAS, + .readfn = pmevcntr_readfn, .writefn = pmevcntr_writefn, + .accessfn = pmreg_access }, + { .name = pmevcntr_el0_name, .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 3, .crn = 15, .crm = 8 | (3 & (i >> 3)), + .opc2 = i & 7, .access = PL0_RW, .accessfn = pmreg_access, + .type = ARM_CP_IO, + .readfn = pmevcntr_readfn, .writefn = pmevcntr_writefn, + .raw_readfn = pmevcntr_rawread, + .raw_writefn = pmevcntr_rawwrite }, + { .name = pmevtyper_name, .cp = 15, .crn = 15, + .crm = 12 | (3 & (i >> 3)), .opc1 = 0, .opc2 = i & 7, + .access = PL0_RW, .type = ARM_CP_IO | ARM_CP_ALIAS, + .readfn = pmevtyper_readfn, .writefn = pmevtyper_writefn, + .accessfn = pmreg_access }, + { .name = pmevtyper_el0_name, .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 3, .crn = 15, .crm = 12 | (3 & (i >> 3)), + .opc2 = i & 7, .access = PL0_RW, .accessfn = pmreg_access, + .type = ARM_CP_IO, + .readfn = pmevtyper_readfn, .writefn = pmevtyper_writefn, + .raw_writefn = pmevtyper_rawwrite }, + REGINFO_SENTINEL + }; + define_arm_cp_regs(cpu, pmev_regs); + g_free(pmevcntr_name); + g_free(pmevcntr_el0_name); + g_free(pmevtyper_name); + g_free(pmevtyper_el0_name); + } ARMCPRegInfo clidr = { .name = "CLIDR", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .crn = 0, .crm = 0, .opc1 = 1, .opc2 = 1, @@ -5200,6 +5777,21 @@ void register_cp_regs_for_features(ARMCPU *cpu) } else { define_arm_cp_regs(cpu, not_v7_cp_reginfo); } + if (FIELD_EX32(cpu->id_dfr0, ID_DFR0, PERFMON) >= 4 && + FIELD_EX32(cpu->id_dfr0, ID_DFR0, PERFMON) != 0xf) { + ARMCPRegInfo v81_pmu_regs[] = { + { .name = "PMCEID2", .state = ARM_CP_STATE_AA32, + .cp = 15, .opc1 = 0, .crn = 9, .crm = 14, .opc2 = 4, + .access = PL0_R, .accessfn = pmreg_access, .type = ARM_CP_CONST, + .resetvalue = extract64(cpu->pmceid0, 32, 32) }, + { .name = "PMCEID3", .state = ARM_CP_STATE_AA32, + .cp = 15, .opc1 = 0, .crn = 9, .crm = 14, .opc2 = 5, + .access = PL0_R, .accessfn = pmreg_access, .type = ARM_CP_CONST, + .resetvalue = extract64(cpu->pmceid1, 32, 32) }, + REGINFO_SENTINEL + }; + define_arm_cp_regs(cpu, v81_pmu_regs); + } if (arm_feature(env, ARM_FEATURE_V8)) { /* AArch64 ID registers, which all have impdef reset values. * Note that within the ID register ranges the unused slots @@ -5376,7 +5968,7 @@ void register_cp_regs_for_features(ARMCPU *cpu) { .name = "PMCEID0", .state = ARM_CP_STATE_AA32, .cp = 15, .opc1 = 0, .crn = 9, .crm = 12, .opc2 = 6, .access = PL0_R, .accessfn = pmreg_access, .type = ARM_CP_CONST, - .resetvalue = cpu->pmceid0 }, + .resetvalue = extract64(cpu->pmceid0, 0, 32) }, { .name = "PMCEID0_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 12, .opc2 = 6, .access = PL0_R, .accessfn = pmreg_access, .type = ARM_CP_CONST, @@ -5384,7 +5976,7 @@ void register_cp_regs_for_features(ARMCPU *cpu) { .name = "PMCEID1", .state = ARM_CP_STATE_AA32, .cp = 15, .opc1 = 0, .crn = 9, .crm = 12, .opc2 = 7, .access = PL0_R, .accessfn = pmreg_access, .type = ARM_CP_CONST, - .resetvalue = cpu->pmceid1 }, + .resetvalue = extract64(cpu->pmceid1, 0, 32) }, { .name = "PMCEID1_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 12, .opc2 = 7, .access = PL0_R, .accessfn = pmreg_access, .type = ARM_CP_CONST, @@ -5845,6 +6437,12 @@ void register_cp_regs_for_features(ARMCPU *cpu) define_one_arm_cp_reg(cpu, &zcr_el3_reginfo); } } + +#ifdef TARGET_AARCH64 + if (cpu_isar_feature(aa64_pauth, cpu)) { + define_arm_cp_regs(cpu, pauth_reginfo); + } +#endif } void arm_cpu_register_gdb_regs_for_features(ARMCPU *cpu) @@ -6297,7 +6895,7 @@ static int bad_mode_switch(CPUARMState *env, int mode, CPSRWriteType write_type) return 0; case ARM_CPU_MODE_HYP: return !arm_feature(env, ARM_FEATURE_EL2) - || arm_current_el(env) < 2 || arm_is_secure(env); + || arm_current_el(env) < 2 || arm_is_secure_below_el3(env); case ARM_CPU_MODE_MON: return arm_current_el(env) < 3; default: @@ -7117,7 +7715,7 @@ static bool v7m_push_callee_stack(ARMCPU *cpu, uint32_t lr, bool dotailchain, limit = env->v7m.msplim[M_REG_S]; } } else { - mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false)); + mmu_idx = arm_mmu_idx(env); frame_sp_p = &env->regs[13]; limit = v7m_sp_limit(env); } @@ -7298,7 +7896,7 @@ static bool v7m_push_stack(ARMCPU *cpu) CPUARMState *env = &cpu->env; uint32_t xpsr = xpsr_read(env); uint32_t frameptr = env->regs[13]; - ARMMMUIdx mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false)); + ARMMMUIdx mmu_idx = arm_mmu_idx(env); /* Align stack pointer if the guest wants that */ if ((frameptr & 4) && @@ -8957,48 +9555,6 @@ static inline ARMMMUIdx stage_1_mmu_idx(ARMMMUIdx mmu_idx) return mmu_idx; } -/* Returns TBI0 value for current regime el */ -uint32_t arm_regime_tbi0(CPUARMState *env, ARMMMUIdx mmu_idx) -{ - TCR *tcr; - uint32_t el; - - /* For EL0 and EL1, TBI is controlled by stage 1's TCR, so convert - * a stage 1+2 mmu index into the appropriate stage 1 mmu index. - */ - mmu_idx = stage_1_mmu_idx(mmu_idx); - - tcr = regime_tcr(env, mmu_idx); - el = regime_el(env, mmu_idx); - - if (el > 1) { - return extract64(tcr->raw_tcr, 20, 1); - } else { - return extract64(tcr->raw_tcr, 37, 1); - } -} - -/* Returns TBI1 value for current regime el */ -uint32_t arm_regime_tbi1(CPUARMState *env, ARMMMUIdx mmu_idx) -{ - TCR *tcr; - uint32_t el; - - /* For EL0 and EL1, TBI is controlled by stage 1's TCR, so convert - * a stage 1+2 mmu index into the appropriate stage 1 mmu index. - */ - mmu_idx = stage_1_mmu_idx(mmu_idx); - - tcr = regime_tcr(env, mmu_idx); - el = regime_el(env, mmu_idx); - - if (el > 1) { - return 0; - } else { - return extract64(tcr->raw_tcr, 38, 1); - } -} - /* Return the TTBR associated with this translation regime */ static inline uint64_t regime_ttbr(CPUARMState *env, ARMMMUIdx mmu_idx, int ttbrn) @@ -9744,6 +10300,138 @@ static uint8_t convert_stage2_attrs(CPUARMState *env, uint8_t s2attrs) return (hiattr << 6) | (hihint << 4) | (loattr << 2) | lohint; } +ARMVAParameters aa64_va_parameters_both(CPUARMState *env, uint64_t va, + ARMMMUIdx mmu_idx) +{ + uint64_t tcr = regime_tcr(env, mmu_idx)->raw_tcr; + uint32_t el = regime_el(env, mmu_idx); + bool tbi, tbid, epd, hpd, using16k, using64k; + int select, tsz; + + /* + * Bit 55 is always between the two regions, and is canonical for + * determining if address tagging is enabled. + */ + select = extract64(va, 55, 1); + + if (el > 1) { + tsz = extract32(tcr, 0, 6); + using64k = extract32(tcr, 14, 1); + using16k = extract32(tcr, 15, 1); + if (mmu_idx == ARMMMUIdx_S2NS) { + /* VTCR_EL2 */ + tbi = tbid = hpd = false; + } else { + tbi = extract32(tcr, 20, 1); + hpd = extract32(tcr, 24, 1); + tbid = extract32(tcr, 29, 1); + } + epd = false; + } else if (!select) { + tsz = extract32(tcr, 0, 6); + epd = extract32(tcr, 7, 1); + using64k = extract32(tcr, 14, 1); + using16k = extract32(tcr, 15, 1); + tbi = extract64(tcr, 37, 1); + hpd = extract64(tcr, 41, 1); + tbid = extract64(tcr, 51, 1); + } else { + int tg = extract32(tcr, 30, 2); + using16k = tg == 1; + using64k = tg == 3; + tsz = extract32(tcr, 16, 6); + epd = extract32(tcr, 23, 1); + tbi = extract64(tcr, 38, 1); + hpd = extract64(tcr, 42, 1); + tbid = extract64(tcr, 52, 1); + } + tsz = MIN(tsz, 39); /* TODO: ARMv8.4-TTST */ + tsz = MAX(tsz, 16); /* TODO: ARMv8.2-LVA */ + + return (ARMVAParameters) { + .tsz = tsz, + .select = select, + .tbi = tbi, + .tbid = tbid, + .epd = epd, + .hpd = hpd, + .using16k = using16k, + .using64k = using64k, + }; +} + +ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, + ARMMMUIdx mmu_idx, bool data) +{ + ARMVAParameters ret = aa64_va_parameters_both(env, va, mmu_idx); + + /* Present TBI as a composite with TBID. */ + ret.tbi &= (data || !ret.tbid); + return ret; +} + +static ARMVAParameters aa32_va_parameters(CPUARMState *env, uint32_t va, + ARMMMUIdx mmu_idx) +{ + uint64_t tcr = regime_tcr(env, mmu_idx)->raw_tcr; + uint32_t el = regime_el(env, mmu_idx); + int select, tsz; + bool epd, hpd; + + if (mmu_idx == ARMMMUIdx_S2NS) { + /* VTCR */ + bool sext = extract32(tcr, 4, 1); + bool sign = extract32(tcr, 3, 1); + + /* + * If the sign-extend bit is not the same as t0sz[3], the result + * is unpredictable. Flag this as a guest error. + */ + if (sign != sext) { + qemu_log_mask(LOG_GUEST_ERROR, + "AArch32: VTCR.S / VTCR.T0SZ[3] mismatch\n"); + } + tsz = sextract32(tcr, 0, 4) + 8; + select = 0; + hpd = false; + epd = false; + } else if (el == 2) { + /* HTCR */ + tsz = extract32(tcr, 0, 3); + select = 0; + hpd = extract64(tcr, 24, 1); + epd = false; + } else { + int t0sz = extract32(tcr, 0, 3); + int t1sz = extract32(tcr, 16, 3); + + if (t1sz == 0) { + select = va > (0xffffffffu >> t0sz); + } else { + /* Note that we will detect errors later. */ + select = va >= ~(0xffffffffu >> t1sz); + } + if (!select) { + tsz = t0sz; + epd = extract32(tcr, 7, 1); + hpd = extract64(tcr, 41, 1); + } else { + tsz = t1sz; + epd = extract32(tcr, 23, 1); + hpd = extract64(tcr, 42, 1); + } + /* For aarch32, hpd0 is not enabled without t2e as well. */ + hpd &= extract32(tcr, 6, 1); + } + + return (ARMVAParameters) { + .tsz = tsz, + .select = select, + .epd = epd, + .hpd = hpd, + }; +} + static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, MMUAccessType access_type, ARMMMUIdx mmu_idx, hwaddr *phys_ptr, MemTxAttrs *txattrs, int *prot, @@ -9755,26 +10443,20 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, /* Read an LPAE long-descriptor translation table. */ ARMFaultType fault_type = ARMFault_Translation; uint32_t level; - uint32_t epd = 0; - int32_t t0sz, t1sz; - uint32_t tg; + ARMVAParameters param; uint64_t ttbr; - int ttbr_select; hwaddr descaddr, indexmask, indexmask_grainsize; uint32_t tableattrs; - target_ulong page_size; + target_ulong page_size, top_bits; uint32_t attrs; - int32_t stride = 9; - int32_t addrsize; - int inputsize; - int32_t tbi = 0; + int32_t stride; + int addrsize, inputsize; TCR *tcr = regime_tcr(env, mmu_idx); int ap, ns, xn, pxn; uint32_t el = regime_el(env, mmu_idx); - bool ttbr1_valid = true; + bool ttbr1_valid; uint64_t descaddrmask; bool aarch64 = arm_el_is_aa64(env, el); - bool hpd = false; /* TODO: * This code does not handle the different format TCR for VTCR_EL2. @@ -9783,91 +10465,44 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, * support for those page table walks. */ if (aarch64) { + param = aa64_va_parameters(env, address, mmu_idx, + access_type != MMU_INST_FETCH); level = 0; - addrsize = 64; - if (el > 1) { - if (mmu_idx != ARMMMUIdx_S2NS) { - tbi = extract64(tcr->raw_tcr, 20, 1); - } - } else { - if (extract64(address, 55, 1)) { - tbi = extract64(tcr->raw_tcr, 38, 1); - } else { - tbi = extract64(tcr->raw_tcr, 37, 1); - } - } - tbi *= 8; - /* If we are in 64-bit EL2 or EL3 then there is no TTBR1, so mark it * invalid. */ - if (el > 1) { - ttbr1_valid = false; - } + ttbr1_valid = (el < 2); + addrsize = 64 - 8 * param.tbi; + inputsize = 64 - param.tsz; } else { + param = aa32_va_parameters(env, address, mmu_idx); level = 1; - addrsize = 32; /* There is no TTBR1 for EL2 */ - if (el == 2) { - ttbr1_valid = false; - } + ttbr1_valid = (el != 2); + addrsize = (mmu_idx == ARMMMUIdx_S2NS ? 40 : 32); + inputsize = addrsize - param.tsz; } - /* Determine whether this address is in the region controlled by - * TTBR0 or TTBR1 (or if it is in neither region and should fault). - * This is a Non-secure PL0/1 stage 1 translation, so controlled by - * TTBCR/TTBR0/TTBR1 in accordance with ARM ARM DDI0406C table B-32: + /* + * We determined the region when collecting the parameters, but we + * have not yet validated that the address is valid for the region. + * Extract the top bits and verify that they all match select. */ - if (aarch64) { - /* AArch64 translation. */ - t0sz = extract32(tcr->raw_tcr, 0, 6); - t0sz = MIN(t0sz, 39); - t0sz = MAX(t0sz, 16); - } else if (mmu_idx != ARMMMUIdx_S2NS) { - /* AArch32 stage 1 translation. */ - t0sz = extract32(tcr->raw_tcr, 0, 3); - } else { - /* AArch32 stage 2 translation. */ - bool sext = extract32(tcr->raw_tcr, 4, 1); - bool sign = extract32(tcr->raw_tcr, 3, 1); - /* Address size is 40-bit for a stage 2 translation, - * and t0sz can be negative (from -8 to 7), - * so we need to adjust it to use the TTBR selecting logic below. - */ - addrsize = 40; - t0sz = sextract32(tcr->raw_tcr, 0, 4) + 8; - - /* If the sign-extend bit is not the same as t0sz[3], the result - * is unpredictable. Flag this as a guest error. */ - if (sign != sext) { - qemu_log_mask(LOG_GUEST_ERROR, - "AArch32: VTCR.S / VTCR.T0SZ[3] mismatch\n"); - } - } - t1sz = extract32(tcr->raw_tcr, 16, 6); - if (aarch64) { - t1sz = MIN(t1sz, 39); - t1sz = MAX(t1sz, 16); - } - if (t0sz && !extract64(address, addrsize - t0sz, t0sz - tbi)) { - /* there is a ttbr0 region and we are in it (high bits all zero) */ - ttbr_select = 0; - } else if (ttbr1_valid && t1sz && - !extract64(~address, addrsize - t1sz, t1sz - tbi)) { - /* there is a ttbr1 region and we are in it (high bits all one) */ - ttbr_select = 1; - } else if (!t0sz) { - /* ttbr0 region is "everything not in the ttbr1 region" */ - ttbr_select = 0; - } else if (!t1sz && ttbr1_valid) { - /* ttbr1 region is "everything not in the ttbr0 region" */ - ttbr_select = 1; - } else { - /* in the gap between the two regions, this is a Translation fault */ + top_bits = sextract64(address, inputsize, addrsize - inputsize); + if (-top_bits != param.select || (param.select && !ttbr1_valid)) { + /* In the gap between the two regions, this is a Translation fault */ fault_type = ARMFault_Translation; goto do_fault; } + if (param.using64k) { + stride = 13; + } else if (param.using16k) { + stride = 11; + } else { + stride = 9; + } + /* Note that QEMU ignores shareability and cacheability attributes, * so we don't need to do anything with the SH, ORGN, IRGN fields * in the TTBCR. Similarly, TTBCR:A1 selects whether we get the @@ -9875,56 +10510,13 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, * implement any ASID-like capability so we can ignore it (instead * we will always flush the TLB any time the ASID is changed). */ - if (ttbr_select == 0) { - ttbr = regime_ttbr(env, mmu_idx, 0); - if (el < 2) { - epd = extract32(tcr->raw_tcr, 7, 1); - } - inputsize = addrsize - t0sz; - - tg = extract32(tcr->raw_tcr, 14, 2); - if (tg == 1) { /* 64KB pages */ - stride = 13; - } - if (tg == 2) { /* 16KB pages */ - stride = 11; - } - if (aarch64 && el > 1) { - hpd = extract64(tcr->raw_tcr, 24, 1); - } else { - hpd = extract64(tcr->raw_tcr, 41, 1); - } - if (!aarch64) { - /* For aarch32, hpd0 is not enabled without t2e as well. */ - hpd &= extract64(tcr->raw_tcr, 6, 1); - } - } else { - /* We should only be here if TTBR1 is valid */ - assert(ttbr1_valid); - - ttbr = regime_ttbr(env, mmu_idx, 1); - epd = extract32(tcr->raw_tcr, 23, 1); - inputsize = addrsize - t1sz; - - tg = extract32(tcr->raw_tcr, 30, 2); - if (tg == 3) { /* 64KB pages */ - stride = 13; - } - if (tg == 1) { /* 16KB pages */ - stride = 11; - } - hpd = extract64(tcr->raw_tcr, 42, 1); - if (!aarch64) { - /* For aarch32, hpd1 is not enabled without t2e as well. */ - hpd &= extract64(tcr->raw_tcr, 6, 1); - } - } + ttbr = regime_ttbr(env, mmu_idx, param.select); /* Here we should have set up all the parameters for the translation: * inputsize, ttbr, epd, stride, tbi */ - if (epd) { + if (param.epd) { /* Translation table walk disabled => Translation fault on TLB miss * Note: This is always 0 on 64-bit EL2 and EL3. */ @@ -10037,7 +10629,7 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, } /* Merge in attributes from table descriptors */ attrs |= nstable << 3; /* NS */ - if (hpd) { + if (param.hpd) { /* HPD disables all the table attributes except NSTable. */ break; } @@ -11073,7 +11665,7 @@ hwaddr arm_cpu_get_phys_page_attrs_debug(CPUState *cs, vaddr addr, int prot; bool ret; ARMMMUFaultInfo fi = {}; - ARMMMUIdx mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false)); + ARMMMUIdx mmu_idx = arm_mmu_idx(env); *attrs = (MemTxAttrs) {}; @@ -12949,10 +13541,66 @@ int fp_exception_el(CPUARMState *env, int cur_el) return 0; } +ARMMMUIdx arm_v7m_mmu_idx_for_secstate_and_priv(CPUARMState *env, + bool secstate, bool priv) +{ + ARMMMUIdx mmu_idx = ARM_MMU_IDX_M; + + if (priv) { + mmu_idx |= ARM_MMU_IDX_M_PRIV; + } + + if (armv7m_nvic_neg_prio_requested(env->nvic, secstate)) { + mmu_idx |= ARM_MMU_IDX_M_NEGPRI; + } + + if (secstate) { + mmu_idx |= ARM_MMU_IDX_M_S; + } + + return mmu_idx; +} + +/* Return the MMU index for a v7M CPU in the specified security state */ +ARMMMUIdx arm_v7m_mmu_idx_for_secstate(CPUARMState *env, bool secstate) +{ + bool priv = arm_current_el(env) != 0; + + return arm_v7m_mmu_idx_for_secstate_and_priv(env, secstate, priv); +} + +ARMMMUIdx arm_mmu_idx(CPUARMState *env) +{ + int el; + + if (arm_feature(env, ARM_FEATURE_M)) { + return arm_v7m_mmu_idx_for_secstate(env, env->v7m.secure); + } + + el = arm_current_el(env); + if (el < 2 && arm_is_secure_below_el3(env)) { + return ARMMMUIdx_S1SE0 + el; + } else { + return ARMMMUIdx_S12NSE0 + el; + } +} + +int cpu_mmu_index(CPUARMState *env, bool ifetch) +{ + return arm_to_core_mmu_idx(arm_mmu_idx(env)); +} + +#ifndef CONFIG_USER_ONLY +ARMMMUIdx arm_stage1_mmu_idx(CPUARMState *env) +{ + return stage_1_mmu_idx(arm_mmu_idx(env)); +} +#endif + void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, target_ulong *cs_base, uint32_t *pflags) { - ARMMMUIdx mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false)); + ARMMMUIdx mmu_idx = arm_mmu_idx(env); int current_el = arm_current_el(env); int fp_el = fp_exception_el(env, current_el); uint32_t flags = 0; @@ -12962,11 +13610,30 @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, *pc = env->pc; flags = FIELD_DP32(flags, TBFLAG_ANY, AARCH64_STATE, 1); - /* Get control bits for tagged addresses */ - flags = FIELD_DP32(flags, TBFLAG_A64, TBI0, - arm_regime_tbi0(env, mmu_idx)); - flags = FIELD_DP32(flags, TBFLAG_A64, TBI1, - arm_regime_tbi1(env, mmu_idx)); + +#ifndef CONFIG_USER_ONLY + /* + * Get control bits for tagged addresses. Note that the + * translator only uses this for instruction addresses. + */ + { + ARMMMUIdx stage1 = stage_1_mmu_idx(mmu_idx); + ARMVAParameters p0 = aa64_va_parameters_both(env, 0, stage1); + int tbii, tbid; + + /* FIXME: ARMv8.1-VHE S2 translation regime. */ + if (regime_el(env, stage1) < 2) { + ARMVAParameters p1 = aa64_va_parameters_both(env, -1, stage1); + tbid = (p1.tbi << 1) | p0.tbi; + tbii = tbid & ~((p1.tbid << 1) | p0.tbid); + } else { + tbid = p0.tbi; + tbii = tbid & !p0.tbid; + } + + flags = FIELD_DP32(flags, TBFLAG_A64, TBII, tbii); + } +#endif if (cpu_isar_feature(aa64_sve, cpu)) { int sve_el = sve_exception_el(env, current_el); @@ -12983,6 +13650,25 @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, flags = FIELD_DP32(flags, TBFLAG_A64, SVEEXC_EL, sve_el); flags = FIELD_DP32(flags, TBFLAG_A64, ZCR_LEN, zcr_len); } + + if (cpu_isar_feature(aa64_pauth, cpu)) { + /* + * In order to save space in flags, we record only whether + * pauth is "inactive", meaning all insns are implemented as + * a nop, or "active" when some action must be performed. + * The decision of which action to take is left to a helper. + */ + uint64_t sctlr; + if (current_el == 0) { + /* FIXME: ARMv8.1-VHE S2 translation regime. */ + sctlr = env->cp15.sctlr_el[1]; + } else { + sctlr = env->cp15.sctlr_el[current_el]; + } + if (sctlr & (SCTLR_EnIA | SCTLR_EnIB | SCTLR_EnDA | SCTLR_EnDB)) { + flags = FIELD_DP32(flags, TBFLAG_A64, PAUTH_ACTIVE, 1); + } + } } else { *pc = env->regs[15]; flags = FIELD_DP32(flags, TBFLAG_A32, THUMB, env->thumb); diff --git a/target/arm/helper.h b/target/arm/helper.h index 8c9590091b..53a38188c6 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -79,7 +79,6 @@ DEF_HELPER_2(get_cp_reg64, i64, env, ptr) DEF_HELPER_3(msr_i_pstate, void, env, i32, i32) DEF_HELPER_1(clear_pstate_ss, void, env) -DEF_HELPER_1(exception_return, void, env) DEF_HELPER_2(get_r13_banked, i32, env, i32) DEF_HELPER_3(set_r13_banked, void, env, i32, i32) diff --git a/target/arm/internals.h b/target/arm/internals.h index 78e026d6e9..a6fd4582b2 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -104,6 +104,13 @@ void QEMU_NORETURN raise_exception(CPUARMState *env, uint32_t excp, uint32_t syndrome, uint32_t target_el); /* + * Similarly, but also use unwinding to restore cpu state. + */ +void QEMU_NORETURN raise_exception_ra(CPUARMState *env, uint32_t excp, + uint32_t syndrome, uint32_t target_el, + uintptr_t ra); + +/* * For AArch64, map a given EL to an index in the banked_spsr array. * Note that this mapping and the AArch32 mapping defined in bank_number() * must agree such that the AArch64<->AArch32 SPSRs have the architecturally @@ -259,6 +266,7 @@ enum arm_exception_class { EC_CP14DTTRAP = 0x06, EC_ADVSIMDFPACCESSTRAP = 0x07, EC_FPIDTRAP = 0x08, + EC_PACTRAP = 0x09, EC_CP14RRTTRAP = 0x0c, EC_ILLEGALSTATE = 0x0e, EC_AA32_SVC = 0x11, @@ -426,6 +434,11 @@ static inline uint32_t syn_sve_access_trap(void) return EC_SVEACCESSTRAP << ARM_EL_EC_SHIFT; } +static inline uint32_t syn_pactrap(void) +{ + return EC_PACTRAP << ARM_EL_EC_SHIFT; +} + static inline uint32_t syn_insn_abort(int same_el, int ea, int s1ptw, int fsc) { return (EC_INSNABORT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT) @@ -906,4 +919,68 @@ void arm_cpu_update_virq(ARMCPU *cpu); */ void arm_cpu_update_vfiq(ARMCPU *cpu); +/** + * arm_mmu_idx: + * @env: The cpu environment + * + * Return the full ARMMMUIdx for the current translation regime. + */ +ARMMMUIdx arm_mmu_idx(CPUARMState *env); + +/** + * arm_stage1_mmu_idx: + * @env: The cpu environment + * + * Return the ARMMMUIdx for the stage1 traversal for the current regime. + */ +#ifdef CONFIG_USER_ONLY +static inline ARMMMUIdx arm_stage1_mmu_idx(CPUARMState *env) +{ + return ARMMMUIdx_S1NSE0; +} +#else +ARMMMUIdx arm_stage1_mmu_idx(CPUARMState *env); +#endif + +/* + * Parameters of a given virtual address, as extracted from the + * translation control register (TCR) for a given regime. + */ +typedef struct ARMVAParameters { + unsigned tsz : 8; + unsigned select : 1; + bool tbi : 1; + bool tbid : 1; + bool epd : 1; + bool hpd : 1; + bool using16k : 1; + bool using64k : 1; +} ARMVAParameters; + +#ifdef CONFIG_USER_ONLY +static inline ARMVAParameters aa64_va_parameters_both(CPUARMState *env, + uint64_t va, + ARMMMUIdx mmu_idx) +{ + return (ARMVAParameters) { + /* 48-bit address space */ + .tsz = 16, + /* We can't handle tagged addresses properly in user-only mode */ + .tbi = false, + }; +} + +static inline ARMVAParameters aa64_va_parameters(CPUARMState *env, + uint64_t va, + ARMMMUIdx mmu_idx, bool data) +{ + return aa64_va_parameters_both(env, va, mmu_idx); +} +#else +ARMVAParameters aa64_va_parameters_both(CPUARMState *env, uint64_t va, + ARMMMUIdx mmu_idx); +ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, + ARMMMUIdx mmu_idx, bool data); +#endif + #endif diff --git a/target/arm/machine.c b/target/arm/machine.c index 7a22ebc209..b292549614 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -620,6 +620,10 @@ static int cpu_pre_save(void *opaque) { ARMCPU *cpu = opaque; + if (!kvm_enabled()) { + pmu_op_start(&cpu->env); + } + if (kvm_enabled()) { if (!write_kvmstate_to_list(cpu)) { /* This should never fail */ @@ -641,6 +645,17 @@ static int cpu_pre_save(void *opaque) return 0; } +static int cpu_post_save(void *opaque) +{ + ARMCPU *cpu = opaque; + + if (!kvm_enabled()) { + pmu_op_finish(&cpu->env); + } + + return 0; +} + static int cpu_pre_load(void *opaque) { ARMCPU *cpu = opaque; @@ -653,6 +668,10 @@ static int cpu_pre_load(void *opaque) */ env->irq_line_state = UINT32_MAX; + if (!kvm_enabled()) { + pmu_op_start(&cpu->env); + } + return 0; } @@ -721,6 +740,10 @@ static int cpu_post_load(void *opaque, int version_id) hw_breakpoint_update_all(cpu); hw_watchpoint_update_all(cpu); + if (!kvm_enabled()) { + pmu_op_finish(&cpu->env); + } + return 0; } @@ -729,6 +752,7 @@ const VMStateDescription vmstate_arm_cpu = { .version_id = 22, .minimum_version_id = 22, .pre_save = cpu_pre_save, + .post_save = cpu_post_save, .pre_load = cpu_pre_load, .post_load = cpu_post_load, .fields = (VMStateField[]) { diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index ef72361a36..c998eadfaa 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -28,8 +28,8 @@ #define SIGNBIT (uint32_t)0x80000000 #define SIGNBIT64 ((uint64_t)1 << 63) -void raise_exception(CPUARMState *env, uint32_t excp, - uint32_t syndrome, uint32_t target_el) +static CPUState *do_raise_exception(CPUARMState *env, uint32_t excp, + uint32_t syndrome, uint32_t target_el) { CPUState *cs = CPU(arm_env_get_cpu(env)); @@ -50,9 +50,24 @@ void raise_exception(CPUARMState *env, uint32_t excp, cs->exception_index = excp; env->exception.syndrome = syndrome; env->exception.target_el = target_el; + + return cs; +} + +void raise_exception(CPUARMState *env, uint32_t excp, + uint32_t syndrome, uint32_t target_el) +{ + CPUState *cs = do_raise_exception(env, excp, syndrome, target_el); cpu_loop_exit(cs); } +void raise_exception_ra(CPUARMState *env, uint32_t excp, uint32_t syndrome, + uint32_t target_el, uintptr_t ra) +{ + CPUState *cs = do_raise_exception(env, excp, syndrome, target_el); + cpu_loop_exit_restore(cs, ra); +} + static int exception_target_el(CPUARMState *env) { int target_el = MAX(1, arm_current_el(env)); @@ -1014,161 +1029,6 @@ void HELPER(pre_smc)(CPUARMState *env, uint32_t syndrome) } } -static int el_from_spsr(uint32_t spsr) -{ - /* Return the exception level that this SPSR is requesting a return to, - * or -1 if it is invalid (an illegal return) - */ - if (spsr & PSTATE_nRW) { - switch (spsr & CPSR_M) { - case ARM_CPU_MODE_USR: - return 0; - case ARM_CPU_MODE_HYP: - return 2; - case ARM_CPU_MODE_FIQ: - case ARM_CPU_MODE_IRQ: - case ARM_CPU_MODE_SVC: - case ARM_CPU_MODE_ABT: - case ARM_CPU_MODE_UND: - case ARM_CPU_MODE_SYS: - return 1; - case ARM_CPU_MODE_MON: - /* Returning to Mon from AArch64 is never possible, - * so this is an illegal return. - */ - default: - return -1; - } - } else { - if (extract32(spsr, 1, 1)) { - /* Return with reserved M[1] bit set */ - return -1; - } - if (extract32(spsr, 0, 4) == 1) { - /* return to EL0 with M[0] bit set */ - return -1; - } - return extract32(spsr, 2, 2); - } -} - -void HELPER(exception_return)(CPUARMState *env) -{ - int cur_el = arm_current_el(env); - unsigned int spsr_idx = aarch64_banked_spsr_index(cur_el); - uint32_t spsr = env->banked_spsr[spsr_idx]; - int new_el; - bool return_to_aa64 = (spsr & PSTATE_nRW) == 0; - - aarch64_save_sp(env, cur_el); - - arm_clear_exclusive(env); - - /* We must squash the PSTATE.SS bit to zero unless both of the - * following hold: - * 1. debug exceptions are currently disabled - * 2. singlestep will be active in the EL we return to - * We check 1 here and 2 after we've done the pstate/cpsr write() to - * transition to the EL we're going to. - */ - if (arm_generate_debug_exceptions(env)) { - spsr &= ~PSTATE_SS; - } - - new_el = el_from_spsr(spsr); - if (new_el == -1) { - goto illegal_return; - } - if (new_el > cur_el - || (new_el == 2 && !arm_feature(env, ARM_FEATURE_EL2))) { - /* Disallow return to an EL which is unimplemented or higher - * than the current one. - */ - goto illegal_return; - } - - if (new_el != 0 && arm_el_is_aa64(env, new_el) != return_to_aa64) { - /* Return to an EL which is configured for a different register width */ - goto illegal_return; - } - - if (new_el == 2 && arm_is_secure_below_el3(env)) { - /* Return to the non-existent secure-EL2 */ - goto illegal_return; - } - - if (new_el == 1 && (arm_hcr_el2_eff(env) & HCR_TGE)) { - goto illegal_return; - } - - qemu_mutex_lock_iothread(); - arm_call_pre_el_change_hook(arm_env_get_cpu(env)); - qemu_mutex_unlock_iothread(); - - if (!return_to_aa64) { - env->aarch64 = 0; - /* We do a raw CPSR write because aarch64_sync_64_to_32() - * will sort the register banks out for us, and we've already - * caught all the bad-mode cases in el_from_spsr(). - */ - cpsr_write(env, spsr, ~0, CPSRWriteRaw); - if (!arm_singlestep_active(env)) { - env->uncached_cpsr &= ~PSTATE_SS; - } - aarch64_sync_64_to_32(env); - - if (spsr & CPSR_T) { - env->regs[15] = env->elr_el[cur_el] & ~0x1; - } else { - env->regs[15] = env->elr_el[cur_el] & ~0x3; - } - qemu_log_mask(CPU_LOG_INT, "Exception return from AArch64 EL%d to " - "AArch32 EL%d PC 0x%" PRIx32 "\n", - cur_el, new_el, env->regs[15]); - } else { - env->aarch64 = 1; - pstate_write(env, spsr); - if (!arm_singlestep_active(env)) { - env->pstate &= ~PSTATE_SS; - } - aarch64_restore_sp(env, new_el); - env->pc = env->elr_el[cur_el]; - qemu_log_mask(CPU_LOG_INT, "Exception return from AArch64 EL%d to " - "AArch64 EL%d PC 0x%" PRIx64 "\n", - cur_el, new_el, env->pc); - } - /* - * Note that cur_el can never be 0. If new_el is 0, then - * el0_a64 is return_to_aa64, else el0_a64 is ignored. - */ - aarch64_sve_change_el(env, cur_el, new_el, return_to_aa64); - - qemu_mutex_lock_iothread(); - arm_call_el_change_hook(arm_env_get_cpu(env)); - qemu_mutex_unlock_iothread(); - - return; - -illegal_return: - /* Illegal return events of various kinds have architecturally - * mandated behaviour: - * restore NZCV and DAIF from SPSR_ELx - * set PSTATE.IL - * restore PC from ELR_ELx - * no change to exception level, execution state or stack pointer - */ - env->pstate |= PSTATE_IL; - env->pc = env->elr_el[cur_el]; - spsr &= PSTATE_NZCV | PSTATE_DAIF; - spsr |= pstate_read(env) & ~(PSTATE_NZCV | PSTATE_DAIF); - pstate_write(env, spsr); - if (!arm_singlestep_active(env)) { - env->pstate &= ~PSTATE_SS; - } - qemu_log_mask(LOG_GUEST_ERROR, "Illegal exception return at EL%d: " - "resuming execution at 0x%" PRIx64 "\n", cur_el, env->pc); -} - /* Return true if the linked breakpoint entry lbn passes its checks */ static bool linked_bp_matches(ARMCPU *cpu, int lbn) { diff --git a/target/arm/pauth_helper.c b/target/arm/pauth_helper.c new file mode 100644 index 0000000000..d750f96edf --- /dev/null +++ b/target/arm/pauth_helper.c @@ -0,0 +1,497 @@ +/* + * ARM v8.3-PAuth Operations + * + * Copyright (c) 2019 Linaro, Ltd. + * + * 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/>. + */ + +#include "qemu/osdep.h" +#include "cpu.h" +#include "internals.h" +#include "exec/exec-all.h" +#include "exec/cpu_ldst.h" +#include "exec/helper-proto.h" +#include "tcg/tcg-gvec-desc.h" + + +static uint64_t pac_cell_shuffle(uint64_t i) +{ + uint64_t o = 0; + + o |= extract64(i, 52, 4); + o |= extract64(i, 24, 4) << 4; + o |= extract64(i, 44, 4) << 8; + o |= extract64(i, 0, 4) << 12; + + o |= extract64(i, 28, 4) << 16; + o |= extract64(i, 48, 4) << 20; + o |= extract64(i, 4, 4) << 24; + o |= extract64(i, 40, 4) << 28; + + o |= extract64(i, 32, 4) << 32; + o |= extract64(i, 12, 4) << 36; + o |= extract64(i, 56, 4) << 40; + o |= extract64(i, 20, 4) << 44; + + o |= extract64(i, 8, 4) << 48; + o |= extract64(i, 36, 4) << 52; + o |= extract64(i, 16, 4) << 56; + o |= extract64(i, 60, 4) << 60; + + return o; +} + +static uint64_t pac_cell_inv_shuffle(uint64_t i) +{ + uint64_t o = 0; + + o |= extract64(i, 12, 4); + o |= extract64(i, 24, 4) << 4; + o |= extract64(i, 48, 4) << 8; + o |= extract64(i, 36, 4) << 12; + + o |= extract64(i, 56, 4) << 16; + o |= extract64(i, 44, 4) << 20; + o |= extract64(i, 4, 4) << 24; + o |= extract64(i, 16, 4) << 28; + + o |= i & MAKE_64BIT_MASK(32, 4); + o |= extract64(i, 52, 4) << 36; + o |= extract64(i, 28, 4) << 40; + o |= extract64(i, 8, 4) << 44; + + o |= extract64(i, 20, 4) << 48; + o |= extract64(i, 0, 4) << 52; + o |= extract64(i, 40, 4) << 56; + o |= i & MAKE_64BIT_MASK(60, 4); + + return o; +} + +static uint64_t pac_sub(uint64_t i) +{ + static const uint8_t sub[16] = { + 0xb, 0x6, 0x8, 0xf, 0xc, 0x0, 0x9, 0xe, + 0x3, 0x7, 0x4, 0x5, 0xd, 0x2, 0x1, 0xa, + }; + uint64_t o = 0; + int b; + + for (b = 0; b < 64; b += 16) { + o |= (uint64_t)sub[(i >> b) & 0xf] << b; + } + return o; +} + +static uint64_t pac_inv_sub(uint64_t i) +{ + static const uint8_t inv_sub[16] = { + 0x5, 0xe, 0xd, 0x8, 0xa, 0xb, 0x1, 0x9, + 0x2, 0x6, 0xf, 0x0, 0x4, 0xc, 0x7, 0x3, + }; + uint64_t o = 0; + int b; + + for (b = 0; b < 64; b += 16) { + o |= (uint64_t)inv_sub[(i >> b) & 0xf] << b; + } + return o; +} + +static int rot_cell(int cell, int n) +{ + /* 4-bit rotate left by n. */ + cell |= cell << 4; + return extract32(cell, 4 - n, 4); +} + +static uint64_t pac_mult(uint64_t i) +{ + uint64_t o = 0; + int b; + + for (b = 0; b < 4 * 4; b += 4) { + int i0, i4, i8, ic, t0, t1, t2, t3; + + i0 = extract64(i, b, 4); + i4 = extract64(i, b + 4 * 4, 4); + i8 = extract64(i, b + 8 * 4, 4); + ic = extract64(i, b + 12 * 4, 4); + + t0 = rot_cell(i8, 1) ^ rot_cell(i4, 2) ^ rot_cell(i0, 1); + t1 = rot_cell(ic, 1) ^ rot_cell(i4, 1) ^ rot_cell(i0, 2); + t2 = rot_cell(ic, 2) ^ rot_cell(i8, 1) ^ rot_cell(i0, 1); + t3 = rot_cell(ic, 1) ^ rot_cell(i8, 2) ^ rot_cell(i4, 1); + + o |= (uint64_t)t3 << b; + o |= (uint64_t)t2 << (b + 4 * 4); + o |= (uint64_t)t1 << (b + 8 * 4); + o |= (uint64_t)t0 << (b + 12 * 4); + } + return o; +} + +static uint64_t tweak_cell_rot(uint64_t cell) +{ + return (cell >> 1) | (((cell ^ (cell >> 1)) & 1) << 3); +} + +static uint64_t tweak_shuffle(uint64_t i) +{ + uint64_t o = 0; + + o |= extract64(i, 16, 4) << 0; + o |= extract64(i, 20, 4) << 4; + o |= tweak_cell_rot(extract64(i, 24, 4)) << 8; + o |= extract64(i, 28, 4) << 12; + + o |= tweak_cell_rot(extract64(i, 44, 4)) << 16; + o |= extract64(i, 8, 4) << 20; + o |= extract64(i, 12, 4) << 24; + o |= tweak_cell_rot(extract64(i, 32, 4)) << 28; + + o |= extract64(i, 48, 4) << 32; + o |= extract64(i, 52, 4) << 36; + o |= extract64(i, 56, 4) << 40; + o |= tweak_cell_rot(extract64(i, 60, 4)) << 44; + + o |= tweak_cell_rot(extract64(i, 0, 4)) << 48; + o |= extract64(i, 4, 4) << 52; + o |= tweak_cell_rot(extract64(i, 40, 4)) << 56; + o |= tweak_cell_rot(extract64(i, 36, 4)) << 60; + + return o; +} + +static uint64_t tweak_cell_inv_rot(uint64_t cell) +{ + return ((cell << 1) & 0xf) | ((cell & 1) ^ (cell >> 3)); +} + +static uint64_t tweak_inv_shuffle(uint64_t i) +{ + uint64_t o = 0; + + o |= tweak_cell_inv_rot(extract64(i, 48, 4)); + o |= extract64(i, 52, 4) << 4; + o |= extract64(i, 20, 4) << 8; + o |= extract64(i, 24, 4) << 12; + + o |= extract64(i, 0, 4) << 16; + o |= extract64(i, 4, 4) << 20; + o |= tweak_cell_inv_rot(extract64(i, 8, 4)) << 24; + o |= extract64(i, 12, 4) << 28; + + o |= tweak_cell_inv_rot(extract64(i, 28, 4)) << 32; + o |= tweak_cell_inv_rot(extract64(i, 60, 4)) << 36; + o |= tweak_cell_inv_rot(extract64(i, 56, 4)) << 40; + o |= tweak_cell_inv_rot(extract64(i, 16, 4)) << 44; + + o |= extract64(i, 32, 4) << 48; + o |= extract64(i, 36, 4) << 52; + o |= extract64(i, 40, 4) << 56; + o |= tweak_cell_inv_rot(extract64(i, 44, 4)) << 60; + + return o; +} + +static uint64_t pauth_computepac(uint64_t data, uint64_t modifier, + ARMPACKey key) +{ + static const uint64_t RC[5] = { + 0x0000000000000000ull, + 0x13198A2E03707344ull, + 0xA4093822299F31D0ull, + 0x082EFA98EC4E6C89ull, + 0x452821E638D01377ull, + }; + const uint64_t alpha = 0xC0AC29B7C97C50DDull; + /* + * Note that in the ARM pseudocode, key0 contains bits <127:64> + * and key1 contains bits <63:0> of the 128-bit key. + */ + uint64_t key0 = key.hi, key1 = key.lo; + uint64_t workingval, runningmod, roundkey, modk0; + int i; + + modk0 = (key0 << 63) | ((key0 >> 1) ^ (key0 >> 63)); + runningmod = modifier; + workingval = data ^ key0; + + for (i = 0; i <= 4; ++i) { + roundkey = key1 ^ runningmod; + workingval ^= roundkey; + workingval ^= RC[i]; + if (i > 0) { + workingval = pac_cell_shuffle(workingval); + workingval = pac_mult(workingval); + } + workingval = pac_sub(workingval); + runningmod = tweak_shuffle(runningmod); + } + roundkey = modk0 ^ runningmod; + workingval ^= roundkey; + workingval = pac_cell_shuffle(workingval); + workingval = pac_mult(workingval); + workingval = pac_sub(workingval); + workingval = pac_cell_shuffle(workingval); + workingval = pac_mult(workingval); + workingval ^= key1; + workingval = pac_cell_inv_shuffle(workingval); + workingval = pac_inv_sub(workingval); + workingval = pac_mult(workingval); + workingval = pac_cell_inv_shuffle(workingval); + workingval ^= key0; + workingval ^= runningmod; + for (i = 0; i <= 4; ++i) { + workingval = pac_inv_sub(workingval); + if (i < 4) { + workingval = pac_mult(workingval); + workingval = pac_cell_inv_shuffle(workingval); + } + runningmod = tweak_inv_shuffle(runningmod); + roundkey = key1 ^ runningmod; + workingval ^= RC[4 - i]; + workingval ^= roundkey; + workingval ^= alpha; + } + workingval ^= modk0; + + return workingval; +} + +static uint64_t pauth_addpac(CPUARMState *env, uint64_t ptr, uint64_t modifier, + ARMPACKey *key, bool data) +{ + ARMMMUIdx mmu_idx = arm_stage1_mmu_idx(env); + ARMVAParameters param = aa64_va_parameters(env, ptr, mmu_idx, data); + uint64_t pac, ext_ptr, ext, test; + int bot_bit, top_bit; + + /* If tagged pointers are in use, use ptr<55>, otherwise ptr<63>. */ + if (param.tbi) { + ext = sextract64(ptr, 55, 1); + } else { + ext = sextract64(ptr, 63, 1); + } + + /* Build a pointer with known good extension bits. */ + top_bit = 64 - 8 * param.tbi; + bot_bit = 64 - param.tsz; + ext_ptr = deposit64(ptr, bot_bit, top_bit - bot_bit, ext); + + pac = pauth_computepac(ext_ptr, modifier, *key); + + /* + * Check if the ptr has good extension bits and corrupt the + * pointer authentication code if not. + */ + test = sextract64(ptr, bot_bit, top_bit - bot_bit); + if (test != 0 && test != -1) { + pac ^= MAKE_64BIT_MASK(top_bit - 1, 1); + } + + /* + * Preserve the determination between upper and lower at bit 55, + * and insert pointer authentication code. + */ + if (param.tbi) { + ptr &= ~MAKE_64BIT_MASK(bot_bit, 55 - bot_bit + 1); + pac &= MAKE_64BIT_MASK(bot_bit, 54 - bot_bit + 1); + } else { + ptr &= MAKE_64BIT_MASK(0, bot_bit); + pac &= ~(MAKE_64BIT_MASK(55, 1) | MAKE_64BIT_MASK(0, bot_bit)); + } + ext &= MAKE_64BIT_MASK(55, 1); + return pac | ext | ptr; +} + +static uint64_t pauth_original_ptr(uint64_t ptr, ARMVAParameters param) +{ + uint64_t extfield = -param.select; + int bot_pac_bit = 64 - param.tsz; + int top_pac_bit = 64 - 8 * param.tbi; + + return deposit64(ptr, bot_pac_bit, top_pac_bit - bot_pac_bit, extfield); +} + +static uint64_t pauth_auth(CPUARMState *env, uint64_t ptr, uint64_t modifier, + ARMPACKey *key, bool data, int keynumber) +{ + ARMMMUIdx mmu_idx = arm_stage1_mmu_idx(env); + ARMVAParameters param = aa64_va_parameters(env, ptr, mmu_idx, data); + int bot_bit, top_bit; + uint64_t pac, orig_ptr, test; + + orig_ptr = pauth_original_ptr(ptr, param); + pac = pauth_computepac(orig_ptr, modifier, *key); + bot_bit = 64 - param.tsz; + top_bit = 64 - 8 * param.tbi; + + test = (pac ^ ptr) & ~MAKE_64BIT_MASK(55, 1); + if (unlikely(extract64(test, bot_bit, top_bit - bot_bit))) { + int error_code = (keynumber << 1) | (keynumber ^ 1); + if (param.tbi) { + return deposit64(ptr, 53, 2, error_code); + } else { + return deposit64(ptr, 61, 2, error_code); + } + } + return orig_ptr; +} + +static uint64_t pauth_strip(CPUARMState *env, uint64_t ptr, bool data) +{ + ARMMMUIdx mmu_idx = arm_stage1_mmu_idx(env); + ARMVAParameters param = aa64_va_parameters(env, ptr, mmu_idx, data); + + return pauth_original_ptr(ptr, param); +} + +static void QEMU_NORETURN pauth_trap(CPUARMState *env, int target_el, + uintptr_t ra) +{ + raise_exception_ra(env, EXCP_UDEF, syn_pactrap(), target_el, ra); +} + +static void pauth_check_trap(CPUARMState *env, int el, uintptr_t ra) +{ + if (el < 2 && arm_feature(env, ARM_FEATURE_EL2)) { + uint64_t hcr = arm_hcr_el2_eff(env); + bool trap = !(hcr & HCR_API); + /* FIXME: ARMv8.1-VHE: trap only applies to EL1&0 regime. */ + /* FIXME: ARMv8.3-NV: HCR_NV trap takes precedence for ERETA[AB]. */ + if (trap) { + pauth_trap(env, 2, ra); + } + } + if (el < 3 && arm_feature(env, ARM_FEATURE_EL3)) { + if (!(env->cp15.scr_el3 & SCR_API)) { + pauth_trap(env, 3, ra); + } + } +} + +static bool pauth_key_enabled(CPUARMState *env, int el, uint32_t bit) +{ + uint32_t sctlr; + if (el == 0) { + /* FIXME: ARMv8.1-VHE S2 translation regime. */ + sctlr = env->cp15.sctlr_el[1]; + } else { + sctlr = env->cp15.sctlr_el[el]; + } + return (sctlr & bit) != 0; +} + +uint64_t HELPER(pacia)(CPUARMState *env, uint64_t x, uint64_t y) +{ + int el = arm_current_el(env); + if (!pauth_key_enabled(env, el, SCTLR_EnIA)) { + return x; + } + pauth_check_trap(env, el, GETPC()); + return pauth_addpac(env, x, y, &env->apia_key, false); +} + +uint64_t HELPER(pacib)(CPUARMState *env, uint64_t x, uint64_t y) +{ + int el = arm_current_el(env); + if (!pauth_key_enabled(env, el, SCTLR_EnIB)) { + return x; + } + pauth_check_trap(env, el, GETPC()); + return pauth_addpac(env, x, y, &env->apib_key, false); +} + +uint64_t HELPER(pacda)(CPUARMState *env, uint64_t x, uint64_t y) +{ + int el = arm_current_el(env); + if (!pauth_key_enabled(env, el, SCTLR_EnDA)) { + return x; + } + pauth_check_trap(env, el, GETPC()); + return pauth_addpac(env, x, y, &env->apda_key, true); +} + +uint64_t HELPER(pacdb)(CPUARMState *env, uint64_t x, uint64_t y) +{ + int el = arm_current_el(env); + if (!pauth_key_enabled(env, el, SCTLR_EnDB)) { + return x; + } + pauth_check_trap(env, el, GETPC()); + return pauth_addpac(env, x, y, &env->apdb_key, true); +} + +uint64_t HELPER(pacga)(CPUARMState *env, uint64_t x, uint64_t y) +{ + uint64_t pac; + + pauth_check_trap(env, arm_current_el(env), GETPC()); + pac = pauth_computepac(x, y, env->apga_key); + + return pac & 0xffffffff00000000ull; +} + +uint64_t HELPER(autia)(CPUARMState *env, uint64_t x, uint64_t y) +{ + int el = arm_current_el(env); + if (!pauth_key_enabled(env, el, SCTLR_EnIA)) { + return x; + } + pauth_check_trap(env, el, GETPC()); + return pauth_auth(env, x, y, &env->apia_key, false, 0); +} + +uint64_t HELPER(autib)(CPUARMState *env, uint64_t x, uint64_t y) +{ + int el = arm_current_el(env); + if (!pauth_key_enabled(env, el, SCTLR_EnIB)) { + return x; + } + pauth_check_trap(env, el, GETPC()); + return pauth_auth(env, x, y, &env->apib_key, false, 1); +} + +uint64_t HELPER(autda)(CPUARMState *env, uint64_t x, uint64_t y) +{ + int el = arm_current_el(env); + if (!pauth_key_enabled(env, el, SCTLR_EnDA)) { + return x; + } + pauth_check_trap(env, el, GETPC()); + return pauth_auth(env, x, y, &env->apda_key, true, 0); +} + +uint64_t HELPER(autdb)(CPUARMState *env, uint64_t x, uint64_t y) +{ + int el = arm_current_el(env); + if (!pauth_key_enabled(env, el, SCTLR_EnDB)) { + return x; + } + pauth_check_trap(env, el, GETPC()); + return pauth_auth(env, x, y, &env->apdb_key, true, 1); +} + +uint64_t HELPER(xpaci)(CPUARMState *env, uint64_t a) +{ + return pauth_strip(env, a, false); +} + +uint64_t HELPER(xpacd)(CPUARMState *env, uint64_t a) +{ + return pauth_strip(env, a, true); +} diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index b7b6ab6371..4d28a27c3b 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -261,7 +261,7 @@ void gen_a64_set_pc_im(uint64_t val) /* Load the PC from a generic TCG variable. * * If address tagging is enabled via the TCR TBI bits, then loading - * an address into the PC will clear out any tag in the it: + * an address into the PC will clear out any tag in it: * + for EL2 and EL3 there is only one TBI bit, and if it is set * then the address is zero-extended, clearing bits [63:56] * + for EL0 and EL1, TBI0 controls addresses with bit 55 == 0 @@ -276,56 +276,38 @@ void gen_a64_set_pc_im(uint64_t val) */ static void gen_a64_set_pc(DisasContext *s, TCGv_i64 src) { + /* Note that TBII is TBI1:TBI0. */ + int tbi = s->tbii; if (s->current_el <= 1) { - /* Test if NEITHER or BOTH TBI values are set. If so, no need to - * examine bit 55 of address, can just generate code. - * If mixed, then test via generated code - */ - if (s->tbi0 && s->tbi1) { - TCGv_i64 tmp_reg = tcg_temp_new_i64(); - /* Both bits set, sign extension from bit 55 into [63:56] will - * cover both cases - */ - tcg_gen_shli_i64(tmp_reg, src, 8); - tcg_gen_sari_i64(cpu_pc, tmp_reg, 8); - tcg_temp_free_i64(tmp_reg); - } else if (!s->tbi0 && !s->tbi1) { - /* Neither bit set, just load it as-is */ - tcg_gen_mov_i64(cpu_pc, src); - } else { - TCGv_i64 tcg_tmpval = tcg_temp_new_i64(); - TCGv_i64 tcg_bit55 = tcg_temp_new_i64(); - TCGv_i64 tcg_zero = tcg_const_i64(0); - - tcg_gen_andi_i64(tcg_bit55, src, (1ull << 55)); - - if (s->tbi0) { - /* tbi0==1, tbi1==0, so 0-fill upper byte if bit 55 = 0 */ - tcg_gen_andi_i64(tcg_tmpval, src, - 0x00FFFFFFFFFFFFFFull); - tcg_gen_movcond_i64(TCG_COND_EQ, cpu_pc, tcg_bit55, tcg_zero, - tcg_tmpval, src); - } else { - /* tbi0==0, tbi1==1, so 1-fill upper byte if bit 55 = 1 */ - tcg_gen_ori_i64(tcg_tmpval, src, - 0xFF00000000000000ull); - tcg_gen_movcond_i64(TCG_COND_NE, cpu_pc, tcg_bit55, tcg_zero, - tcg_tmpval, src); + if (tbi != 0) { + /* Sign-extend from bit 55. */ + tcg_gen_sextract_i64(cpu_pc, src, 0, 56); + + if (tbi != 3) { + TCGv_i64 tcg_zero = tcg_const_i64(0); + + /* + * The two TBI bits differ. + * If tbi0, then !tbi1: only use the extension if positive. + * if !tbi0, then tbi1: only use the extension if negative. + */ + tcg_gen_movcond_i64(tbi == 1 ? TCG_COND_GE : TCG_COND_LT, + cpu_pc, cpu_pc, tcg_zero, cpu_pc, src); + tcg_temp_free_i64(tcg_zero); } - tcg_temp_free_i64(tcg_zero); - tcg_temp_free_i64(tcg_bit55); - tcg_temp_free_i64(tcg_tmpval); + return; } - } else { /* EL > 1 */ - if (s->tbi0) { + } else { + if (tbi != 0) { /* Force tag byte to all zero */ - tcg_gen_andi_i64(cpu_pc, src, 0x00FFFFFFFFFFFFFFull); - } else { - /* Load unmodified address */ - tcg_gen_mov_i64(cpu_pc, src); + tcg_gen_extract_i64(cpu_pc, src, 0, 56); + return; } } + + /* Load unmodified address */ + tcg_gen_mov_i64(cpu_pc, src); } typedef struct DisasCompare64 { @@ -1471,33 +1453,102 @@ static void handle_hint(DisasContext *s, uint32_t insn, } switch (selector) { - case 0: /* NOP */ - return; - case 3: /* WFI */ + case 0b00000: /* NOP */ + break; + case 0b00011: /* WFI */ s->base.is_jmp = DISAS_WFI; - return; + break; + case 0b00001: /* YIELD */ /* When running in MTTCG we don't generate jumps to the yield and * WFE helpers as it won't affect the scheduling of other vCPUs. * If we wanted to more completely model WFE/SEV so we don't busy * spin unnecessarily we would need to do something more involved. */ - case 1: /* YIELD */ if (!(tb_cflags(s->base.tb) & CF_PARALLEL)) { s->base.is_jmp = DISAS_YIELD; } - return; - case 2: /* WFE */ + break; + case 0b00010: /* WFE */ if (!(tb_cflags(s->base.tb) & CF_PARALLEL)) { s->base.is_jmp = DISAS_WFE; } - return; - case 4: /* SEV */ - case 5: /* SEVL */ + break; + case 0b00100: /* SEV */ + case 0b00101: /* SEVL */ /* we treat all as NOP at least for now */ - return; + break; + case 0b00111: /* XPACLRI */ + if (s->pauth_active) { + gen_helper_xpaci(cpu_X[30], cpu_env, cpu_X[30]); + } + break; + case 0b01000: /* PACIA1716 */ + if (s->pauth_active) { + gen_helper_pacia(cpu_X[17], cpu_env, cpu_X[17], cpu_X[16]); + } + break; + case 0b01010: /* PACIB1716 */ + if (s->pauth_active) { + gen_helper_pacib(cpu_X[17], cpu_env, cpu_X[17], cpu_X[16]); + } + break; + case 0b01100: /* AUTIA1716 */ + if (s->pauth_active) { + gen_helper_autia(cpu_X[17], cpu_env, cpu_X[17], cpu_X[16]); + } + break; + case 0b01110: /* AUTIB1716 */ + if (s->pauth_active) { + gen_helper_autib(cpu_X[17], cpu_env, cpu_X[17], cpu_X[16]); + } + break; + case 0b11000: /* PACIAZ */ + if (s->pauth_active) { + gen_helper_pacia(cpu_X[30], cpu_env, cpu_X[30], + new_tmp_a64_zero(s)); + } + break; + case 0b11001: /* PACIASP */ + if (s->pauth_active) { + gen_helper_pacia(cpu_X[30], cpu_env, cpu_X[30], cpu_X[31]); + } + break; + case 0b11010: /* PACIBZ */ + if (s->pauth_active) { + gen_helper_pacib(cpu_X[30], cpu_env, cpu_X[30], + new_tmp_a64_zero(s)); + } + break; + case 0b11011: /* PACIBSP */ + if (s->pauth_active) { + gen_helper_pacib(cpu_X[30], cpu_env, cpu_X[30], cpu_X[31]); + } + break; + case 0b11100: /* AUTIAZ */ + if (s->pauth_active) { + gen_helper_autia(cpu_X[30], cpu_env, cpu_X[30], + new_tmp_a64_zero(s)); + } + break; + case 0b11101: /* AUTIASP */ + if (s->pauth_active) { + gen_helper_autia(cpu_X[30], cpu_env, cpu_X[30], cpu_X[31]); + } + break; + case 0b11110: /* AUTIBZ */ + if (s->pauth_active) { + gen_helper_autib(cpu_X[30], cpu_env, cpu_X[30], + new_tmp_a64_zero(s)); + } + break; + case 0b11111: /* AUTIBSP */ + if (s->pauth_active) { + gen_helper_autib(cpu_X[30], cpu_env, cpu_X[30], cpu_X[31]); + } + break; default: /* default specified as NOP equivalent */ - return; + break; } } @@ -1912,6 +1963,8 @@ static void disas_exc(DisasContext *s, uint32_t insn) static void disas_uncond_b_reg(DisasContext *s, uint32_t insn) { unsigned int opc, op2, op3, rn, op4; + TCGv_i64 dst; + TCGv_i64 modifier; opc = extract32(insn, 21, 4); op2 = extract32(insn, 16, 5); @@ -1919,44 +1972,152 @@ static void disas_uncond_b_reg(DisasContext *s, uint32_t insn) rn = extract32(insn, 5, 5); op4 = extract32(insn, 0, 5); - if (op4 != 0x0 || op3 != 0x0 || op2 != 0x1f) { - unallocated_encoding(s); - return; + if (op2 != 0x1f) { + goto do_unallocated; } switch (opc) { case 0: /* BR */ case 1: /* BLR */ case 2: /* RET */ - gen_a64_set_pc(s, cpu_reg(s, rn)); + switch (op3) { + case 0: + /* BR, BLR, RET */ + if (op4 != 0) { + goto do_unallocated; + } + dst = cpu_reg(s, rn); + break; + + case 2: + case 3: + if (!dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + if (opc == 2) { + /* RETAA, RETAB */ + if (rn != 0x1f || op4 != 0x1f) { + goto do_unallocated; + } + rn = 30; + modifier = cpu_X[31]; + } else { + /* BRAAZ, BRABZ, BLRAAZ, BLRABZ */ + if (op4 != 0x1f) { + goto do_unallocated; + } + modifier = new_tmp_a64_zero(s); + } + if (s->pauth_active) { + dst = new_tmp_a64(s); + if (op3 == 2) { + gen_helper_autia(dst, cpu_env, cpu_reg(s, rn), modifier); + } else { + gen_helper_autib(dst, cpu_env, cpu_reg(s, rn), modifier); + } + } else { + dst = cpu_reg(s, rn); + } + break; + + default: + goto do_unallocated; + } + + gen_a64_set_pc(s, dst); /* BLR also needs to load return address */ if (opc == 1) { tcg_gen_movi_i64(cpu_reg(s, 30), s->pc); } break; + + case 8: /* BRAA */ + case 9: /* BLRAA */ + if (!dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + if (op3 != 2 || op3 != 3) { + goto do_unallocated; + } + if (s->pauth_active) { + dst = new_tmp_a64(s); + modifier = cpu_reg_sp(s, op4); + if (op3 == 2) { + gen_helper_autia(dst, cpu_env, cpu_reg(s, rn), modifier); + } else { + gen_helper_autib(dst, cpu_env, cpu_reg(s, rn), modifier); + } + } else { + dst = cpu_reg(s, rn); + } + gen_a64_set_pc(s, dst); + /* BLRAA also needs to load return address */ + if (opc == 9) { + tcg_gen_movi_i64(cpu_reg(s, 30), s->pc); + } + break; + case 4: /* ERET */ if (s->current_el == 0) { - unallocated_encoding(s); - return; + goto do_unallocated; + } + switch (op3) { + case 0: /* ERET */ + if (op4 != 0) { + goto do_unallocated; + } + dst = tcg_temp_new_i64(); + tcg_gen_ld_i64(dst, cpu_env, + offsetof(CPUARMState, elr_el[s->current_el])); + break; + + case 2: /* ERETAA */ + case 3: /* ERETAB */ + if (!dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + if (rn != 0x1f || op4 != 0x1f) { + goto do_unallocated; + } + dst = tcg_temp_new_i64(); + tcg_gen_ld_i64(dst, cpu_env, + offsetof(CPUARMState, elr_el[s->current_el])); + if (s->pauth_active) { + modifier = cpu_X[31]; + if (op3 == 2) { + gen_helper_autia(dst, cpu_env, dst, modifier); + } else { + gen_helper_autib(dst, cpu_env, dst, modifier); + } + } + break; + + default: + goto do_unallocated; } if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { gen_io_start(); } - gen_helper_exception_return(cpu_env); + + gen_helper_exception_return(cpu_env, dst); + tcg_temp_free_i64(dst); if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { gen_io_end(); } /* Must exit loop to check un-masked IRQs */ s->base.is_jmp = DISAS_EXIT; return; + case 5: /* DRPS */ - if (rn != 0x1f) { - unallocated_encoding(s); + if (op3 != 0 || op4 != 0 || rn != 0x1f) { + goto do_unallocated; } else { unsupported_encoding(s, insn); } return; + default: + do_unallocated: unallocated_encoding(s); return; } @@ -2967,6 +3128,64 @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn, s->be_data | size | MO_ALIGN); } +/* + * PAC memory operations + * + * 31 30 27 26 24 22 21 12 11 10 5 0 + * +------+-------+---+-----+-----+---+--------+---+---+----+-----+ + * | size | 1 1 1 | V | 0 0 | M S | 1 | imm9 | W | 1 | Rn | Rt | + * +------+-------+---+-----+-----+---+--------+---+---+----+-----+ + * + * Rt: the result register + * Rn: base address or SP + * V: vector flag (always 0 as of v8.3) + * M: clear for key DA, set for key DB + * W: pre-indexing flag + * S: sign for imm9. + */ +static void disas_ldst_pac(DisasContext *s, uint32_t insn, + int size, int rt, bool is_vector) +{ + int rn = extract32(insn, 5, 5); + bool is_wback = extract32(insn, 11, 1); + bool use_key_a = !extract32(insn, 23, 1); + int offset; + TCGv_i64 tcg_addr, tcg_rt; + + if (size != 3 || is_vector || !dc_isar_feature(aa64_pauth, s)) { + unallocated_encoding(s); + return; + } + + if (rn == 31) { + gen_check_sp_alignment(s); + } + tcg_addr = read_cpu_reg_sp(s, rn, 1); + + if (s->pauth_active) { + if (use_key_a) { + gen_helper_autda(tcg_addr, cpu_env, tcg_addr, cpu_X[31]); + } else { + gen_helper_autdb(tcg_addr, cpu_env, tcg_addr, cpu_X[31]); + } + } + + /* Form the 10-bit signed, scaled offset. */ + offset = (extract32(insn, 22, 1) << 9) | extract32(insn, 12, 9); + offset = sextract32(offset << size, 0, 10 + size); + tcg_gen_addi_i64(tcg_addr, tcg_addr, offset); + + tcg_rt = cpu_reg(s, rt); + + do_gpr_ld(s, tcg_rt, tcg_addr, size, /* is_signed */ false, + /* extend */ false, /* iss_valid */ !is_wback, + /* iss_srt */ rt, /* iss_sf */ true, /* iss_ar */ false); + + if (is_wback) { + tcg_gen_mov_i64(cpu_reg_sp(s, rn), tcg_addr); + } +} + /* Load/store register (all forms) */ static void disas_ldst_reg(DisasContext *s, uint32_t insn) { @@ -2992,6 +3211,9 @@ static void disas_ldst_reg(DisasContext *s, uint32_t insn) case 2: disas_ldst_reg_roffset(s, insn, opc, size, rt, is_vector); return; + default: + disas_ldst_pac(s, insn, size, rt, is_vector); + return; } break; case 1: @@ -4494,38 +4716,197 @@ static void handle_rev16(DisasContext *s, unsigned int sf, */ static void disas_data_proc_1src(DisasContext *s, uint32_t insn) { - unsigned int sf, opcode, rn, rd; + unsigned int sf, opcode, opcode2, rn, rd; + TCGv_i64 tcg_rd; - if (extract32(insn, 29, 1) || extract32(insn, 16, 5)) { + if (extract32(insn, 29, 1)) { unallocated_encoding(s); return; } sf = extract32(insn, 31, 1); opcode = extract32(insn, 10, 6); + opcode2 = extract32(insn, 16, 5); rn = extract32(insn, 5, 5); rd = extract32(insn, 0, 5); - switch (opcode) { - case 0: /* RBIT */ +#define MAP(SF, O2, O1) ((SF) | (O1 << 1) | (O2 << 7)) + + switch (MAP(sf, opcode2, opcode)) { + case MAP(0, 0x00, 0x00): /* RBIT */ + case MAP(1, 0x00, 0x00): handle_rbit(s, sf, rn, rd); break; - case 1: /* REV16 */ + case MAP(0, 0x00, 0x01): /* REV16 */ + case MAP(1, 0x00, 0x01): handle_rev16(s, sf, rn, rd); break; - case 2: /* REV32 */ + case MAP(0, 0x00, 0x02): /* REV/REV32 */ + case MAP(1, 0x00, 0x02): handle_rev32(s, sf, rn, rd); break; - case 3: /* REV64 */ + case MAP(1, 0x00, 0x03): /* REV64 */ handle_rev64(s, sf, rn, rd); break; - case 4: /* CLZ */ + case MAP(0, 0x00, 0x04): /* CLZ */ + case MAP(1, 0x00, 0x04): handle_clz(s, sf, rn, rd); break; - case 5: /* CLS */ + case MAP(0, 0x00, 0x05): /* CLS */ + case MAP(1, 0x00, 0x05): handle_cls(s, sf, rn, rd); break; + case MAP(1, 0x01, 0x00): /* PACIA */ + if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_pacia(tcg_rd, cpu_env, tcg_rd, cpu_reg_sp(s, rn)); + } else if (!dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + break; + case MAP(1, 0x01, 0x01): /* PACIB */ + if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_pacib(tcg_rd, cpu_env, tcg_rd, cpu_reg_sp(s, rn)); + } else if (!dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + break; + case MAP(1, 0x01, 0x02): /* PACDA */ + if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_pacda(tcg_rd, cpu_env, tcg_rd, cpu_reg_sp(s, rn)); + } else if (!dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + break; + case MAP(1, 0x01, 0x03): /* PACDB */ + if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_pacdb(tcg_rd, cpu_env, tcg_rd, cpu_reg_sp(s, rn)); + } else if (!dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + break; + case MAP(1, 0x01, 0x04): /* AUTIA */ + if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_autia(tcg_rd, cpu_env, tcg_rd, cpu_reg_sp(s, rn)); + } else if (!dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + break; + case MAP(1, 0x01, 0x05): /* AUTIB */ + if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_autib(tcg_rd, cpu_env, tcg_rd, cpu_reg_sp(s, rn)); + } else if (!dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + break; + case MAP(1, 0x01, 0x06): /* AUTDA */ + if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_autda(tcg_rd, cpu_env, tcg_rd, cpu_reg_sp(s, rn)); + } else if (!dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + break; + case MAP(1, 0x01, 0x07): /* AUTDB */ + if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_autdb(tcg_rd, cpu_env, tcg_rd, cpu_reg_sp(s, rn)); + } else if (!dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + break; + case MAP(1, 0x01, 0x08): /* PACIZA */ + if (!dc_isar_feature(aa64_pauth, s) || rn != 31) { + goto do_unallocated; + } else if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_pacia(tcg_rd, cpu_env, tcg_rd, new_tmp_a64_zero(s)); + } + break; + case MAP(1, 0x01, 0x09): /* PACIZB */ + if (!dc_isar_feature(aa64_pauth, s) || rn != 31) { + goto do_unallocated; + } else if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_pacib(tcg_rd, cpu_env, tcg_rd, new_tmp_a64_zero(s)); + } + break; + case MAP(1, 0x01, 0x0a): /* PACDZA */ + if (!dc_isar_feature(aa64_pauth, s) || rn != 31) { + goto do_unallocated; + } else if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_pacda(tcg_rd, cpu_env, tcg_rd, new_tmp_a64_zero(s)); + } + break; + case MAP(1, 0x01, 0x0b): /* PACDZB */ + if (!dc_isar_feature(aa64_pauth, s) || rn != 31) { + goto do_unallocated; + } else if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_pacdb(tcg_rd, cpu_env, tcg_rd, new_tmp_a64_zero(s)); + } + break; + case MAP(1, 0x01, 0x0c): /* AUTIZA */ + if (!dc_isar_feature(aa64_pauth, s) || rn != 31) { + goto do_unallocated; + } else if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_autia(tcg_rd, cpu_env, tcg_rd, new_tmp_a64_zero(s)); + } + break; + case MAP(1, 0x01, 0x0d): /* AUTIZB */ + if (!dc_isar_feature(aa64_pauth, s) || rn != 31) { + goto do_unallocated; + } else if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_autib(tcg_rd, cpu_env, tcg_rd, new_tmp_a64_zero(s)); + } + break; + case MAP(1, 0x01, 0x0e): /* AUTDZA */ + if (!dc_isar_feature(aa64_pauth, s) || rn != 31) { + goto do_unallocated; + } else if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_autda(tcg_rd, cpu_env, tcg_rd, new_tmp_a64_zero(s)); + } + break; + case MAP(1, 0x01, 0x0f): /* AUTDZB */ + if (!dc_isar_feature(aa64_pauth, s) || rn != 31) { + goto do_unallocated; + } else if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_autdb(tcg_rd, cpu_env, tcg_rd, new_tmp_a64_zero(s)); + } + break; + case MAP(1, 0x01, 0x10): /* XPACI */ + if (!dc_isar_feature(aa64_pauth, s) || rn != 31) { + goto do_unallocated; + } else if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_xpaci(tcg_rd, cpu_env, tcg_rd); + } + break; + case MAP(1, 0x01, 0x11): /* XPACD */ + if (!dc_isar_feature(aa64_pauth, s) || rn != 31) { + goto do_unallocated; + } else if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_xpacd(tcg_rd, cpu_env, tcg_rd); + } + break; + default: + do_unallocated: + unallocated_encoding(s); + break; } + +#undef MAP } static void handle_div(DisasContext *s, bool is_signed, unsigned int sf, @@ -4656,6 +5037,13 @@ static void disas_data_proc_2src(DisasContext *s, uint32_t insn) case 11: /* RORV */ handle_shift_reg(s, A64_SHIFT_TYPE_ROR, sf, rm, rn, rd); break; + case 12: /* PACGA */ + if (sf == 0 || !dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + gen_helper_pacga(cpu_reg(s, rd), cpu_env, + cpu_reg(s, rn), cpu_reg_sp(s, rm)); + break; case 16: case 17: case 18: @@ -4671,6 +5059,7 @@ static void disas_data_proc_2src(DisasContext *s, uint32_t insn) break; } default: + do_unallocated: unallocated_encoding(s); break; } @@ -13400,8 +13789,7 @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, dc->condexec_cond = 0; core_mmu_idx = FIELD_EX32(tb_flags, TBFLAG_ANY, MMUIDX); dc->mmu_idx = core_to_arm_mmu_idx(env, core_mmu_idx); - dc->tbi0 = FIELD_EX32(tb_flags, TBFLAG_A64, TBI0); - dc->tbi1 = FIELD_EX32(tb_flags, TBFLAG_A64, TBI1); + dc->tbii = FIELD_EX32(tb_flags, TBFLAG_A64, TBII); dc->current_el = arm_mmu_idx_to_el(dc->mmu_idx); #if !defined(CONFIG_USER_ONLY) dc->user = (dc->current_el == 0); @@ -13409,6 +13797,7 @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, dc->fp_excp_el = FIELD_EX32(tb_flags, TBFLAG_ANY, FPEXC_EL); dc->sve_excp_el = FIELD_EX32(tb_flags, TBFLAG_A64, SVEEXC_EL); dc->sve_len = (FIELD_EX32(tb_flags, TBFLAG_A64, ZCR_LEN) + 1) * 16; + dc->pauth_active = FIELD_EX32(tb_flags, TBFLAG_A64, PAUTH_ACTIVE); dc->vec_len = 0; dc->vec_stride = 0; dc->cp_regs = arm_cpu->cp_regs; diff --git a/target/arm/translate.h b/target/arm/translate.h index 1550aa8bc7..bb37d35741 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -26,8 +26,7 @@ typedef struct DisasContext { int user; #endif ARMMMUIdx mmu_idx; /* MMU index to use for normal loads/stores */ - bool tbi0; /* TBI0 for EL0/1 or TBI for EL2/3 */ - bool tbi1; /* TBI1 for EL0/1, not used for EL2/3 */ + uint8_t tbii; /* TBI1|TBI0 for EL0/1 or TBI for EL2/3 */ bool ns; /* Use non-secure CPREG bank on access */ int fp_excp_el; /* FP exception EL or 0 if enabled */ int sve_excp_el; /* SVE exception EL or 0 if enabled */ @@ -68,6 +67,8 @@ typedef struct DisasContext { bool is_ldex; /* True if a single-step exception will be taken to the current EL */ bool ss_same_el; + /* True if v8.3-PAuth is active. */ + bool pauth_active; /* Bottom two bits of XScale c15_cpar coprocessor access control reg */ int c15_cpar; /* TCG op of the current insn_start. */ diff --git a/target/s390x/diag.c b/target/s390x/diag.c index acb0f3d4af..aafa740f61 100644 --- a/target/s390x/diag.c +++ b/target/s390x/diag.c @@ -130,7 +130,7 @@ out: } return; default: - hw_error("Unhandled diag308 subcode %" PRIx64, subcode); + s390_program_interrupt(env, PGM_SPECIFICATION, ILEN_AUTO, ra); break; } } diff --git a/tests/Makefile.include b/tests/Makefile.include index f403a6571d..5e6b2c7058 100644 --- a/tests/Makefile.include +++ b/tests/Makefile.include @@ -3,7 +3,8 @@ check-help: @echo "Regression testing targets:" @echo - @echo " $(MAKE) check Run all tests" + @echo " $(MAKE) check Run unit, qapi-schema, qtest and decodetree" + @echo @echo " $(MAKE) check-qtest-TARGET Run qtest tests for given target" @echo " $(MAKE) check-qtest Run qtest tests" @echo " $(MAKE) check-unit Run qobject tests" @@ -12,12 +13,13 @@ check-help: @echo " $(MAKE) check-block Run block tests" @echo " $(MAKE) check-tcg Run TCG tests" @echo " $(MAKE) check-acceptance Run all acceptance (functional) tests" + @echo @echo " $(MAKE) check-report.html Generates an HTML test report" @echo " $(MAKE) check-venv Creates a Python venv for tests" - @echo " $(MAKE) check-clean Clean the tests" + @echo " $(MAKE) check-clean Clean the tests and related data" @echo @echo "Please note that HTML reports do not regenerate if the unit tests" - @echo "has not changed." + @echo "have not changed." @echo @echo "The variable SPEED can be set to control the gtester speed setting." @echo "Default options are -k and (for $(MAKE) V=1) --verbose; they can be" @@ -107,7 +109,7 @@ check-unit-y += tests/test-crypto-secret$(EXESUF) check-unit-$(CONFIG_GNUTLS) += tests/test-crypto-tlscredsx509$(EXESUF) check-unit-$(CONFIG_GNUTLS) += tests/test-crypto-tlssession$(EXESUF) ifneq (,$(findstring qemu-ga,$(TOOLS))) -check-unit-$(CONFIG_LINUX) += tests/test-qga$(EXESUF) +check-unit-$(land,$(CONFIG_LINUX),$(CONFIG_VIRTIO_SERIAL)) += tests/test-qga$(EXESUF) endif check-unit-y += tests/test-timed-average$(EXESUF) check-unit-y += tests/test-util-sockets$(EXESUF) @@ -143,17 +145,17 @@ check-qtest-generic-y += tests/cdrom-test$(EXESUF) check-qtest-ipack-y += tests/ipoctal232-test$(EXESUF) -check-qtest-virtioserial-y += tests/virtio-console-test$(EXESUF) +check-qtest-virtioserial-$(CONFIG_VIRTIO_SERIAL) += tests/virtio-console-test$(EXESUF) -check-qtest-virtio-y += tests/virtio-net-test$(EXESUF) -check-qtest-virtio-y += tests/virtio-balloon-test$(EXESUF) -check-qtest-virtio-y += tests/virtio-blk-test$(EXESUF) -check-qtest-virtio-y += tests/virtio-rng-test$(EXESUF) -check-qtest-virtio-y += tests/virtio-scsi-test$(EXESUF) +check-qtest-virtio-$(CONFIG_VIRTIO_NET) += tests/virtio-net-test$(EXESUF) +check-qtest-virtio-$(CONFIG_VIRTIO_BALLOON) += tests/virtio-balloon-test$(EXESUF) +check-qtest-virtio-$(CONFIG_VIRTIO_BLK) += tests/virtio-blk-test$(EXESUF) +check-qtest-virtio-$(CONFIG_VIRTIO_RNG) += tests/virtio-rng-test$(EXESUF) +check-qtest-virtio-$(CONFIG_VIRTIO_SCSI) += tests/virtio-scsi-test$(EXESUF) ifeq ($(CONFIG_VIRTIO)$(CONFIG_VIRTFS)$(CONFIG_PCI),yyy) -check-qtest-virtio-y += tests/virtio-9p-test$(EXESUF) +check-qtest-virtio-$(CONFIG_VIRTIO_9P) += tests/virtio-9p-test$(EXESUF) endif -check-qtest-virtio-y += tests/virtio-serial-test$(EXESUF) +check-qtest-virtio-$(CONFIG_VIRTIO_SERIAL) += tests/virtio-serial-test$(EXESUF) check-qtest-virtio-y += $(check-qtest-virtioserial-y) check-qtest-pci-y += tests/e1000-test$(EXESUF) @@ -184,7 +186,8 @@ check-qtest-i386-$(CONFIG_SGA) += tests/boot-serial-test$(EXESUF) check-qtest-i386-$(CONFIG_SLIRP) += tests/pxe-test$(EXESUF) check-qtest-i386-y += tests/rtc-test$(EXESUF) check-qtest-i386-y += tests/ipmi-kcs-test$(EXESUF) -check-qtest-i386-y += tests/ipmi-bt-test$(EXESUF) +# Disabled temporarily as it fails intermittently especially under NetBSD VM +# check-qtest-i386-y += tests/ipmi-bt-test$(EXESUF) check-qtest-i386-y += tests/i440fx-test$(EXESUF) check-qtest-i386-y += tests/fw_cfg-test$(EXESUF) check-qtest-i386-y += tests/drive_del-test$(EXESUF) @@ -284,7 +287,7 @@ check-qtest-arm-y += tests/pca9552-test$(EXESUF) check-qtest-arm-y += tests/ds1338-test$(EXESUF) check-qtest-arm-y += tests/microbit-test$(EXESUF) check-qtest-arm-y += tests/m25p80-test$(EXESUF) -check-qtest-arm-y += tests/virtio-blk-test$(EXESUF) +check-qtest-arm-$(CONFIG_VIRTIO_BLK) += tests/virtio-blk-test$(EXESUF) check-qtest-arm-y += tests/test-arm-mptimer$(EXESUF) check-qtest-arm-y += tests/boot-serial-test$(EXESUF) check-qtest-arm-$(CONFIG_SDHCI) += tests/sdhci-test$(EXESUF) @@ -958,8 +961,7 @@ TESTS_RESULTS_DIR=$(BUILD_DIR)/tests/results # information please refer to "avocado --help". AVOCADO_SHOW=none -PYTHON3 = $(shell $(PYTHON) -c 'import sys; print(1 if sys.version_info >= (3, 0) else 0)') -ifeq ($(PYTHON3), 1) +ifneq ($(findstring v2,"v$(PYTHON_VERSION)"),v2) $(TESTS_VENV_DIR): $(TESTS_VENV_REQ) $(call quiet-command, \ $(PYTHON) -m venv --system-site-packages $@, \ diff --git a/tests/acceptance/linux_initrd.py b/tests/acceptance/linux_initrd.py new file mode 100644 index 0000000000..737355c2ef --- /dev/null +++ b/tests/acceptance/linux_initrd.py @@ -0,0 +1,48 @@ +# Linux initrd acceptance test. +# +# Copyright (c) 2018 Red Hat, Inc. +# +# Author: +# Wainer dos Santos Moschetta <wainersm@redhat.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. + +import tempfile +from avocado.utils.process import run + +from avocado_qemu import Test + + +class LinuxInitrd(Test): + """ + Checks QEMU evaluates correctly the initrd file passed as -initrd option. + + :avocado: enable + :avocado: tags=x86_64 + """ + + timeout = 60 + + def test_with_2gib_file_should_exit_error_msg(self): + """ + Pretends to boot QEMU with an initrd file with size of 2GiB + and expect it exits with error message. + """ + kernel_url = ('https://mirrors.kernel.org/fedora/releases/28/' + 'Everything/x86_64/os/images/pxeboot/vmlinuz') + kernel_hash = '238e083e114c48200f80d889f7e32eeb2793e02a' + kernel_path = self.fetch_asset(kernel_url, asset_hash=kernel_hash) + max_size = 2 * (1024 ** 3) - 1 + + with tempfile.NamedTemporaryFile() as initrd: + initrd.seek(max_size) + initrd.write(b'\0') + initrd.flush() + cmd = "%s -kernel %s -initrd %s" % (self.qemu_bin, kernel_path, + initrd.name) + res = run(cmd, ignore_status=True) + self.assertEqual(res.exit_status, 1) + expected_msg = r'.*initrd is too large.*max: \d+, need %s.*' % ( + max_size + 1) + self.assertRegex(res.stderr_text, expected_msg) diff --git a/tests/acpi-utils.c b/tests/acpi-utils.c index 17abcc43a4..cc33b460ab 100644 --- a/tests/acpi-utils.c +++ b/tests/acpi-utils.c @@ -51,14 +51,6 @@ uint32_t acpi_find_rsdp_address(QTestState *qts) return off; } -uint32_t acpi_get_rsdt_address(uint8_t *rsdp_table) -{ - uint32_t rsdt_physical_address; - - memcpy(&rsdt_physical_address, &rsdp_table[16 /* RsdtAddress offset */], 4); - return le32_to_cpu(rsdt_physical_address); -} - uint64_t acpi_get_xsdt_address(uint8_t *rsdp_table) { uint64_t xsdt_physical_address; @@ -92,3 +84,30 @@ void acpi_parse_rsdp_table(QTestState *qts, uint32_t addr, uint8_t *rsdp_table) ACPI_ASSERT_CMP64(*((uint64_t *)(rsdp_table)), "RSD PTR "); } + +/** acpi_fetch_table + * load ACPI table at @addr_ptr offset pointer into buffer and return it in + * @aml, its length in @aml_len and check that signature/checksum matches + * actual one. + */ +void acpi_fetch_table(QTestState *qts, uint8_t **aml, uint32_t *aml_len, + const uint8_t *addr_ptr, const char *sig, + bool verify_checksum) +{ + uint32_t addr, len; + + memcpy(&addr, addr_ptr , sizeof(addr)); + addr = le32_to_cpu(addr); + qtest_memread(qts, addr + 4, &len, 4); /* Length of ACPI table */ + *aml_len = le32_to_cpu(len); + *aml = g_malloc0(*aml_len); + /* get whole table */ + qtest_memread(qts, addr, *aml, *aml_len); + + if (sig) { + ACPI_ASSERT_CMP(**aml, sig); + } + if (verify_checksum) { + g_assert(!acpi_calc_checksum(*aml, *aml_len)); + } +} diff --git a/tests/acpi-utils.h b/tests/acpi-utils.h index c5b0e12aa2..ef388bbf12 100644 --- a/tests/acpi-utils.h +++ b/tests/acpi-utils.h @@ -13,14 +13,12 @@ #ifndef TEST_ACPI_UTILS_H #define TEST_ACPI_UTILS_H -#include "hw/acpi/acpi-defs.h" #include "libqtest.h" /* DSDT and SSDTs format */ typedef struct { - AcpiTableHeader header; - gchar *aml; /* aml bytecode from guest */ - gsize aml_len; + uint8_t *aml; /* aml bytecode from guest */ + uint32_t aml_len; gchar *aml_file; gchar *asl; /* asl code generated from aml */ gsize asl_len; @@ -28,36 +26,6 @@ typedef struct { bool tmp_files_retain; /* do not delete the temp asl/aml */ } AcpiSdtTable; -#define ACPI_READ_FIELD(qts, field, addr) \ - do { \ - qtest_memread(qts, addr, &field, sizeof(field)); \ - addr += sizeof(field); \ - } while (0) - -#define ACPI_READ_ARRAY_PTR(qts, arr, length, addr) \ - do { \ - int idx; \ - for (idx = 0; idx < length; ++idx) { \ - ACPI_READ_FIELD(qts, arr[idx], addr); \ - } \ - } while (0) - -#define ACPI_READ_ARRAY(qts, arr, addr) \ - ACPI_READ_ARRAY_PTR(qts, arr, sizeof(arr) / sizeof(arr[0]), addr) - -#define ACPI_READ_TABLE_HEADER(qts, table, addr) \ - do { \ - ACPI_READ_FIELD(qts, (table)->signature, addr); \ - ACPI_READ_FIELD(qts, (table)->length, addr); \ - ACPI_READ_FIELD(qts, (table)->revision, addr); \ - ACPI_READ_FIELD(qts, (table)->checksum, addr); \ - ACPI_READ_ARRAY(qts, (table)->oem_id, addr); \ - ACPI_READ_ARRAY(qts, (table)->oem_table_id, addr); \ - ACPI_READ_FIELD(qts, (table)->oem_revision, addr); \ - ACPI_READ_ARRAY(qts, (table)->asl_compiler_id, addr); \ - ACPI_READ_FIELD(qts, (table)->asl_compiler_revision, addr); \ - } while (0) - #define ACPI_ASSERT_CMP(actual, expected) do { \ char ACPI_ASSERT_CMP_str[5] = {}; \ memcpy(ACPI_ASSERT_CMP_str, &actual, 4); \ @@ -71,11 +39,17 @@ typedef struct { } while (0) +#define ACPI_FOREACH_RSDT_ENTRY(table, table_len, entry_ptr, entry_size) \ + for (entry_ptr = table + 36 /* 1st Entry */; \ + entry_ptr < table + table_len; \ + entry_ptr += entry_size) uint8_t acpi_calc_checksum(const uint8_t *data, int len); uint32_t acpi_find_rsdp_address(QTestState *qts); -uint32_t acpi_get_rsdt_address(uint8_t *rsdp_table); uint64_t acpi_get_xsdt_address(uint8_t *rsdp_table); void acpi_parse_rsdp_table(QTestState *qts, uint32_t addr, uint8_t *rsdp_table); +void acpi_fetch_table(QTestState *qts, uint8_t **aml, uint32_t *aml_len, + const uint8_t *addr_ptr, const char *sig, + bool verify_checksum); #endif /* TEST_ACPI_UTILS_H */ diff --git a/tests/bios-tables-test.c b/tests/bios-tables-test.c index d455b2abfc..a506dcbb29 100644 --- a/tests/bios-tables-test.c +++ b/tests/bios-tables-test.c @@ -28,12 +28,6 @@ typedef struct { const char *variant; uint32_t rsdp_addr; uint8_t rsdp_table[36 /* ACPI 2.0+ RSDP size */]; - AcpiRsdtDescriptorRev1 rsdt_table; - uint32_t dsdt_addr; - uint32_t facs_addr; - AcpiFacsDescriptorRev1 facs_table; - uint32_t *rsdt_tables_addr; - int rsdt_tables_nr; GArray *tables; uint32_t smbios_ep_addr; struct smbios_21_entry_point smbios_ep_table; @@ -50,28 +44,34 @@ static const char *iasl = stringify(CONFIG_IASL); static const char *iasl; #endif +static bool compare_signature(const AcpiSdtTable *sdt, const char *signature) +{ + return !memcmp(sdt->aml, signature, 4); +} + +static void cleanup_table_descriptor(AcpiSdtTable *table) +{ + g_free(table->aml); + if (table->aml_file && + !table->tmp_files_retain && + g_strstr_len(table->aml_file, -1, "aml-")) { + unlink(table->aml_file); + } + g_free(table->aml_file); + g_free(table->asl); + if (table->asl_file && + !table->tmp_files_retain) { + unlink(table->asl_file); + } + g_free(table->asl_file); +} + static void free_test_data(test_data *data) { - AcpiSdtTable *temp; int i; - g_free(data->rsdt_tables_addr); - for (i = 0; i < data->tables->len; ++i) { - temp = &g_array_index(data->tables, AcpiSdtTable, i); - g_free(temp->aml); - if (temp->aml_file && - !temp->tmp_files_retain && - g_strstr_len(temp->aml_file, -1, "aml-")) { - unlink(temp->aml_file); - } - g_free(temp->aml_file); - g_free(temp->asl); - if (temp->asl_file && - !temp->tmp_files_retain) { - unlink(temp->asl_file); - } - g_free(temp->asl_file); + cleanup_table_descriptor(&g_array_index(data->tables, AcpiSdtTable, i)); } g_array_free(data->tables, true); @@ -109,154 +109,53 @@ static void test_acpi_rsdp_table(test_data *data) static void test_acpi_rsdt_table(test_data *data) { - AcpiRsdtDescriptorRev1 *rsdt_table = &data->rsdt_table; - uint32_t addr = acpi_get_rsdt_address(data->rsdp_table); - uint32_t *tables; - int tables_nr; - uint8_t checksum; - uint32_t rsdt_table_length; - - /* read the header */ - ACPI_READ_TABLE_HEADER(data->qts, rsdt_table, addr); - ACPI_ASSERT_CMP(rsdt_table->signature, "RSDT"); - - rsdt_table_length = le32_to_cpu(rsdt_table->length); - - /* compute the table entries in rsdt */ - tables_nr = (rsdt_table_length - sizeof(AcpiRsdtDescriptorRev1)) / - sizeof(uint32_t); - g_assert(tables_nr > 0); + AcpiSdtTable rsdt = {}; + uint8_t *ent; - /* get the addresses of the tables pointed by rsdt */ - tables = g_new0(uint32_t, tables_nr); - ACPI_READ_ARRAY_PTR(data->qts, tables, tables_nr, addr); + /* read RSDT table */ + acpi_fetch_table(data->qts, &rsdt.aml, &rsdt.aml_len, + &data->rsdp_table[16 /* RsdtAddress */], "RSDT", true); - checksum = acpi_calc_checksum((uint8_t *)rsdt_table, rsdt_table_length) + - acpi_calc_checksum((uint8_t *)tables, - tables_nr * sizeof(uint32_t)); - g_assert(!checksum); + /* Load all tables and add to test list directly RSDT referenced tables */ + ACPI_FOREACH_RSDT_ENTRY(rsdt.aml, rsdt.aml_len, ent, 4 /* Entry size */) { + AcpiSdtTable ssdt_table = {}; - /* SSDT tables after FADT */ - data->rsdt_tables_addr = tables; - data->rsdt_tables_nr = tables_nr; -} - -static void fadt_fetch_facs_and_dsdt_ptrs(test_data *data) -{ - uint32_t addr; - AcpiTableHeader hdr; - - /* FADT table comes first */ - addr = le32_to_cpu(data->rsdt_tables_addr[0]); - ACPI_READ_TABLE_HEADER(data->qts, &hdr, addr); - ACPI_ASSERT_CMP(hdr.signature, "FACP"); - - ACPI_READ_FIELD(data->qts, data->facs_addr, addr); - ACPI_READ_FIELD(data->qts, data->dsdt_addr, addr); -} - -static void sanitize_fadt_ptrs(test_data *data) -{ - /* fixup pointers in FADT */ - int i; - - for (i = 0; i < data->tables->len; i++) { - AcpiSdtTable *sdt = &g_array_index(data->tables, AcpiSdtTable, i); - - if (memcmp(&sdt->header.signature, "FACP", 4)) { - continue; - } - - /* check original FADT checksum before sanitizing table */ - g_assert(!(uint8_t)( - acpi_calc_checksum((uint8_t *)sdt, sizeof(AcpiTableHeader)) + - acpi_calc_checksum((uint8_t *)sdt->aml, sdt->aml_len) - )); - - /* sdt->aml field offset := spec offset - header size */ - memset(sdt->aml + 0, 0, 4); /* sanitize FIRMWARE_CTRL(36) ptr */ - memset(sdt->aml + 4, 0, 4); /* sanitize DSDT(40) ptr */ - if (sdt->header.revision >= 3) { - memset(sdt->aml + 96, 0, 8); /* sanitize X_FIRMWARE_CTRL(132) ptr */ - memset(sdt->aml + 104, 0, 8); /* sanitize X_DSDT(140) ptr */ - } - - /* update checksum */ - sdt->header.checksum = 0; - sdt->header.checksum -= - acpi_calc_checksum((uint8_t *)sdt, sizeof(AcpiTableHeader)) + - acpi_calc_checksum((uint8_t *)sdt->aml, sdt->aml_len); - break; + acpi_fetch_table(data->qts, &ssdt_table.aml, &ssdt_table.aml_len, ent, + NULL, true); + /* Add table to ASL test tables list */ + g_array_append_val(data->tables, ssdt_table); } + cleanup_table_descriptor(&rsdt); } -static void test_acpi_facs_table(test_data *data) -{ - AcpiFacsDescriptorRev1 *facs_table = &data->facs_table; - uint32_t addr = le32_to_cpu(data->facs_addr); - - ACPI_READ_FIELD(data->qts, facs_table->signature, addr); - ACPI_READ_FIELD(data->qts, facs_table->length, addr); - ACPI_READ_FIELD(data->qts, facs_table->hardware_signature, addr); - ACPI_READ_FIELD(data->qts, facs_table->firmware_waking_vector, addr); - ACPI_READ_FIELD(data->qts, facs_table->global_lock, addr); - ACPI_READ_FIELD(data->qts, facs_table->flags, addr); - ACPI_READ_ARRAY(data->qts, facs_table->resverved3, addr); - - ACPI_ASSERT_CMP(facs_table->signature, "FACS"); -} - -/** fetch_table - * load ACPI table at @addr into table descriptor @sdt_table - * and check that header checksum matches actual one. - */ -static void fetch_table(QTestState *qts, AcpiSdtTable *sdt_table, uint32_t addr) -{ - uint8_t checksum; - - memset(sdt_table, 0, sizeof(*sdt_table)); - ACPI_READ_TABLE_HEADER(qts, &sdt_table->header, addr); - - sdt_table->aml_len = le32_to_cpu(sdt_table->header.length) - - sizeof(AcpiTableHeader); - sdt_table->aml = g_malloc0(sdt_table->aml_len); - ACPI_READ_ARRAY_PTR(qts, sdt_table->aml, sdt_table->aml_len, addr); - - checksum = acpi_calc_checksum((uint8_t *)sdt_table, - sizeof(AcpiTableHeader)) + - acpi_calc_checksum((uint8_t *)sdt_table->aml, - sdt_table->aml_len); - g_assert(!checksum); -} - -static void test_acpi_dsdt_table(test_data *data) +static void test_acpi_fadt_table(test_data *data) { - AcpiSdtTable dsdt_table; - uint32_t addr = le32_to_cpu(data->dsdt_addr); + /* FADT table is 1st */ + AcpiSdtTable table = g_array_index(data->tables, typeof(table), 0); + uint8_t *fadt_aml = table.aml; + uint32_t fadt_len = table.aml_len; - fetch_table(data->qts, &dsdt_table, addr); - ACPI_ASSERT_CMP(dsdt_table.header.signature, "DSDT"); - - /* Since DSDT isn't in RSDT, add DSDT to ASL test tables list manually */ - g_array_append_val(data->tables, dsdt_table); -} - -/* Load all tables and add to test list directly RSDT referenced tables */ -static void fetch_rsdt_referenced_tables(test_data *data) -{ - int tables_nr = data->rsdt_tables_nr; - int i; + g_assert(compare_signature(&table, "FACP")); - for (i = 0; i < tables_nr; i++) { - AcpiSdtTable ssdt_table; - uint32_t addr; + /* Since DSDT/FACS isn't in RSDT, add them to ASL test list manually */ + acpi_fetch_table(data->qts, &table.aml, &table.aml_len, + fadt_aml + 36 /* FIRMWARE_CTRL */, "FACS", false); + g_array_append_val(data->tables, table); - addr = le32_to_cpu(data->rsdt_tables_addr[i]); - fetch_table(data->qts, &ssdt_table, addr); + acpi_fetch_table(data->qts, &table.aml, &table.aml_len, + fadt_aml + 40 /* DSDT */, "DSDT", true); + g_array_append_val(data->tables, table); - /* Add table to ASL test tables list */ - g_array_append_val(data->tables, ssdt_table); + memset(fadt_aml + 36, 0, 4); /* sanitize FIRMWARE_CTRL ptr */ + memset(fadt_aml + 40, 0, 4); /* sanitize DSDT ptr */ + if (fadt_aml[8 /* FADT Major Version */] >= 3) { + memset(fadt_aml + 132, 0, 8); /* sanitize X_FIRMWARE_CTRL ptr */ + memset(fadt_aml + 140, 0, 8); /* sanitize X_DSDT ptr */ } + + /* update checksum */ + fadt_aml[9 /* Checksum */] = 0; + fadt_aml[9 /* Checksum */] -= acpi_calc_checksum(fadt_aml, fadt_len); } static void dump_aml_files(test_data *data, bool rebuild) @@ -275,7 +174,7 @@ static void dump_aml_files(test_data *data, bool rebuild) if (rebuild) { aml_file = g_strdup_printf("%s/%s/%.4s%s", data_dir, data->machine, - (gchar *)&sdt->header.signature, ext); + sdt->aml, ext); fd = g_open(aml_file, O_WRONLY|O_TRUNC|O_CREAT, S_IRUSR|S_IWUSR|S_IRGRP|S_IWGRP|S_IROTH); } else { @@ -284,8 +183,6 @@ static void dump_aml_files(test_data *data, bool rebuild) } g_assert(fd >= 0); - ret = qemu_write_full(fd, sdt, sizeof(AcpiTableHeader)); - g_assert(ret == sizeof(AcpiTableHeader)); ret = qemu_write_full(fd, sdt->aml, sdt->aml_len); g_assert(ret == sdt->aml_len); @@ -295,11 +192,6 @@ static void dump_aml_files(test_data *data, bool rebuild) } } -static bool compare_signature(AcpiSdtTable *sdt, const char *signature) -{ - return !memcmp(&sdt->header.signature, signature, 4); -} - static bool load_asl(GArray *sdts, AcpiSdtTable *sdt) { AcpiSdtTable *temp; @@ -382,6 +274,7 @@ static GArray *load_expected_aml(test_data *data) AcpiSdtTable *sdt; GError *error = NULL; gboolean ret; + gsize aml_len; GArray *exp_tables = g_array_new(false, true, sizeof(AcpiSdtTable)); if (getenv("V")) { @@ -395,11 +288,10 @@ static GArray *load_expected_aml(test_data *data) sdt = &g_array_index(data->tables, AcpiSdtTable, i); memset(&exp_sdt, 0, sizeof(exp_sdt)); - exp_sdt.header.signature = sdt->header.signature; try_again: aml_file = g_strdup_printf("%s/%s/%.4s%s", data_dir, data->machine, - (gchar *)&sdt->header.signature, ext); + sdt->aml, ext); if (getenv("V")) { fprintf(stderr, "Looking for expected file '%s'\n", aml_file); } @@ -415,8 +307,9 @@ try_again: if (getenv("V")) { fprintf(stderr, "Using expected file '%s'\n", aml_file); } - ret = g_file_get_contents(aml_file, &exp_sdt.aml, - &exp_sdt.aml_len, &error); + ret = g_file_get_contents(aml_file, (gchar **)&exp_sdt.aml, + &aml_len, &error); + exp_sdt.aml_len = aml_len; g_assert(ret); g_assert_no_error(error); g_assert(exp_sdt.aml); @@ -459,14 +352,12 @@ static void test_acpi_asl(test_data *data) fprintf(stderr, "Warning! iasl couldn't parse the expected aml\n"); } else { - uint32_t signature = cpu_to_le32(exp_sdt->header.signature); sdt->tmp_files_retain = true; exp_sdt->tmp_files_retain = true; fprintf(stderr, "acpi-test: Warning! %.4s mismatch. " "Actual [asl:%s, aml:%s], Expected [asl:%s, aml:%s].\n", - (gchar *)&signature, - sdt->asl_file, sdt->aml_file, + exp_sdt->aml, sdt->asl_file, sdt->aml_file, exp_sdt->asl_file, exp_sdt->aml_file); if (getenv("V")) { const char *diff_cmd = getenv("DIFF"); @@ -498,32 +389,19 @@ static bool smbios_ep_table_ok(test_data *data) struct smbios_21_entry_point *ep_table = &data->smbios_ep_table; uint32_t addr = data->smbios_ep_addr; - ACPI_READ_ARRAY(data->qts, ep_table->anchor_string, addr); + qtest_memread(data->qts, addr, ep_table, sizeof(*ep_table)); if (memcmp(ep_table->anchor_string, "_SM_", 4)) { return false; } - ACPI_READ_FIELD(data->qts, ep_table->checksum, addr); - ACPI_READ_FIELD(data->qts, ep_table->length, addr); - ACPI_READ_FIELD(data->qts, ep_table->smbios_major_version, addr); - ACPI_READ_FIELD(data->qts, ep_table->smbios_minor_version, addr); - ACPI_READ_FIELD(data->qts, ep_table->max_structure_size, addr); - ACPI_READ_FIELD(data->qts, ep_table->entry_point_revision, addr); - ACPI_READ_ARRAY(data->qts, ep_table->formatted_area, addr); - ACPI_READ_ARRAY(data->qts, ep_table->intermediate_anchor_string, addr); if (memcmp(ep_table->intermediate_anchor_string, "_DMI_", 5)) { return false; } - ACPI_READ_FIELD(data->qts, ep_table->intermediate_checksum, addr); - ACPI_READ_FIELD(data->qts, ep_table->structure_table_length, addr); if (ep_table->structure_table_length == 0) { return false; } - ACPI_READ_FIELD(data->qts, ep_table->structure_table_address, addr); - ACPI_READ_FIELD(data->qts, ep_table->number_of_structures, addr); if (ep_table->number_of_structures == 0) { return false; } - ACPI_READ_FIELD(data->qts, ep_table->smbios_bcd_revision, addr); if (acpi_calc_checksum((uint8_t *)ep_table, sizeof *ep_table) || acpi_calc_checksum((uint8_t *)ep_table + 0x10, sizeof *ep_table - 0x10)) { @@ -644,12 +522,7 @@ static void test_acpi_one(const char *params, test_data *data) test_acpi_rsdp_address(data); test_acpi_rsdp_table(data); test_acpi_rsdt_table(data); - fadt_fetch_facs_and_dsdt_ptrs(data); - test_acpi_facs_table(data); - test_acpi_dsdt_table(data); - fetch_rsdt_referenced_tables(data); - - sanitize_fadt_ptrs(data); + test_acpi_fadt_table(data); if (iasl) { if (getenv(ACPI_REBUILD_EXPECTED_AML)) { diff --git a/tests/data/acpi/pc/DSDT.dimmpxm b/tests/data/acpi/pc/DSDT.dimmpxm Binary files differindex f6ec911b11..ad2800de67 100644 --- a/tests/data/acpi/pc/DSDT.dimmpxm +++ b/tests/data/acpi/pc/DSDT.dimmpxm diff --git a/tests/data/acpi/pc/DSDT.memhp b/tests/data/acpi/pc/DSDT.memhp Binary files differindex e31ef50296..9e75ac96e1 100644 --- a/tests/data/acpi/pc/DSDT.memhp +++ b/tests/data/acpi/pc/DSDT.memhp diff --git a/tests/data/acpi/q35/DSDT.dimmpxm b/tests/data/acpi/q35/DSDT.dimmpxm Binary files differindex 3837792dec..7177116a21 100644 --- a/tests/data/acpi/q35/DSDT.dimmpxm +++ b/tests/data/acpi/q35/DSDT.dimmpxm diff --git a/tests/data/acpi/q35/DSDT.memhp b/tests/data/acpi/q35/DSDT.memhp Binary files differindex 8fba0baf79..0235461391 100644 --- a/tests/data/acpi/q35/DSDT.memhp +++ b/tests/data/acpi/q35/DSDT.memhp diff --git a/tests/data/acpi/q35/DSDT.mmio64 b/tests/data/acpi/q35/DSDT.mmio64 Binary files differindex a058ff2ee3..f60ee77fb4 100644 --- a/tests/data/acpi/q35/DSDT.mmio64 +++ b/tests/data/acpi/q35/DSDT.mmio64 diff --git a/tests/ivshmem-test.c b/tests/ivshmem-test.c index fe5eb304b1..4911b69317 100644 --- a/tests/ivshmem-test.c +++ b/tests/ivshmem-test.c @@ -291,20 +291,20 @@ static void *server_thread(void *data) return NULL; } -static void setup_vm_with_server(IVState *s, int nvectors, bool msi) +static void setup_vm_with_server(IVState *s, int nvectors) { - char *cmd = g_strdup_printf("-chardev socket,id=chr0,path=%s,nowait " - "-device ivshmem%s,chardev=chr0,vectors=%d", - tmpserver, - msi ? "-doorbell" : ",size=1M,msi=off", - nvectors); + char *cmd; - setup_vm_cmd(s, cmd, msi); + cmd = g_strdup_printf("-chardev socket,id=chr0,path=%s,nowait " + "-device ivshmem-doorbell,chardev=chr0,vectors=%d", + tmpserver, nvectors); + + setup_vm_cmd(s, cmd, true); g_free(cmd); } -static void test_ivshmem_server(bool msi) +static void test_ivshmem_server(void) { IVState state1, state2, *s1, *s2; ServerThread thread; @@ -327,9 +327,9 @@ static void test_ivshmem_server(bool msi) thread.thread = g_thread_new("ivshmem-server", server_thread, &thread); g_assert(thread.thread != NULL); - setup_vm_with_server(&state1, nvectors, msi); + setup_vm_with_server(&state1, nvectors); s1 = &state1; - setup_vm_with_server(&state2, nvectors, msi); + setup_vm_with_server(&state2, nvectors); s2 = &state2; /* check got different VM ids */ @@ -340,38 +340,28 @@ static void test_ivshmem_server(bool msi) g_assert_cmpint(vm1, !=, vm2); /* check number of MSI-X vectors */ - if (msi) { - ret = qpci_msix_table_size(s1->dev); - g_assert_cmpuint(ret, ==, nvectors); - } + ret = qpci_msix_table_size(s1->dev); + g_assert_cmpuint(ret, ==, nvectors); /* TODO test behavior before MSI-X is enabled */ /* ping vm2 -> vm1 on vector 0 */ - if (msi) { - ret = qpci_msix_pending(s1->dev, 0); - g_assert_cmpuint(ret, ==, 0); - } else { - g_assert_cmpuint(in_reg(s1, INTRSTATUS), ==, 0); - } + ret = qpci_msix_pending(s1->dev, 0); + g_assert_cmpuint(ret, ==, 0); out_reg(s2, DOORBELL, vm1 << 16); do { g_usleep(10000); - ret = msi ? qpci_msix_pending(s1->dev, 0) : in_reg(s1, INTRSTATUS); + ret = qpci_msix_pending(s1->dev, 0); } while (ret == 0 && g_get_monotonic_time() < end_time); g_assert_cmpuint(ret, !=, 0); /* ping vm1 -> vm2 on vector 1 */ - if (msi) { - ret = qpci_msix_pending(s2->dev, 1); - g_assert_cmpuint(ret, ==, 0); - } else { - g_assert_cmpuint(in_reg(s2, INTRSTATUS), ==, 0); - } + ret = qpci_msix_pending(s2->dev, 1); + g_assert_cmpuint(ret, ==, 0); out_reg(s1, DOORBELL, vm2 << 16 | 1); do { g_usleep(10000); - ret = msi ? qpci_msix_pending(s2->dev, 1) : in_reg(s2, INTRSTATUS); + ret = qpci_msix_pending(s2->dev, 1); } while (ret == 0 && g_get_monotonic_time() < end_time); g_assert_cmpuint(ret, !=, 0); @@ -389,27 +379,17 @@ static void test_ivshmem_server(bool msi) close(thread.pipe[0]); } -static void test_ivshmem_server_msi(void) -{ - test_ivshmem_server(true); -} - -static void test_ivshmem_server_irq(void) -{ - test_ivshmem_server(false); -} - #define PCI_SLOT_HP 0x06 static void test_ivshmem_hotplug(void) { const char *arch = qtest_get_arch(); - qtest_start(""); + qtest_start("-object memory-backend-ram,size=1M,id=mb1"); - qtest_qmp_device_add("ivshmem", - "iv1", "{'addr': %s, 'shm': %s, 'size': '1M'}", - stringify(PCI_SLOT_HP), tmpshm); + qtest_qmp_device_add("ivshmem-plain", "iv1", + "{'addr': %s, 'memdev': 'mb1'}", + stringify(PCI_SLOT_HP)); if (strcmp(arch, "ppc64") != 0) { qpci_unplug_acpi_device_test("iv1", PCI_SLOT_HP); } @@ -509,8 +489,7 @@ int main(int argc, char **argv) if (g_test_slow()) { qtest_add_func("/ivshmem/pair", test_ivshmem_pair); if (strcmp(arch, "ppc64") != 0) { - qtest_add_func("/ivshmem/server-msi", test_ivshmem_server_msi); - qtest_add_func("/ivshmem/server-irq", test_ivshmem_server_irq); + qtest_add_func("/ivshmem/server", test_ivshmem_server); } } diff --git a/tests/vhost-user-test.c b/tests/vhost-user-test.c index 54982f68e7..84e50d84e7 100644 --- a/tests/vhost-user-test.c +++ b/tests/vhost-user-test.c @@ -309,7 +309,7 @@ static void chr_read(void *opaque, const uint8_t *buf, int size) CharBackend *chr = &s->chr; VhostUserMsg msg; uint8_t *p = (uint8_t *) &msg; - int fd; + int fd = -1; if (s->test_fail) { qemu_chr_fe_disconnect(chr); diff --git a/tests/vmgenid-test.c b/tests/vmgenid-test.c index 1c1d435bbd..52cdd83ec0 100644 --- a/tests/vmgenid-test.c +++ b/tests/vmgenid-test.c @@ -23,26 +23,13 @@ */ #define RSDP_ADDR_INVALID 0x100000 /* RSDP must be below this address */ -typedef struct { - AcpiTableHeader header; - gchar name_op; - gchar vgia[4]; - gchar val_op; - uint32_t vgia_val; -} QEMU_PACKED VgidTable; - static uint32_t acpi_find_vgia(QTestState *qts) { uint32_t rsdp_offset; uint32_t guid_offset = 0; uint8_t rsdp_table[36 /* ACPI 2.0+ RSDP size */]; - uint32_t rsdt, rsdt_table_length; - AcpiRsdtDescriptorRev1 rsdt_table; - size_t tables_nr; - uint32_t *tables; - AcpiTableHeader ssdt_table; - VgidTable vgid_table; - int i; + uint32_t rsdt_len, table_length; + uint8_t *rsdt, *ent; /* Wait for guest firmware to finish and start the payload. */ boot_sector_test(qts); @@ -52,48 +39,37 @@ static uint32_t acpi_find_vgia(QTestState *qts) g_assert_cmphex(rsdp_offset, <, RSDP_ADDR_INVALID); - acpi_parse_rsdp_table(qts, rsdp_offset, rsdp_table); - - rsdt = acpi_get_rsdt_address(rsdp_table); - g_assert(rsdt); - /* read the header */ - ACPI_READ_TABLE_HEADER(qts, &rsdt_table, rsdt); - ACPI_ASSERT_CMP(rsdt_table.signature, "RSDT"); - rsdt_table_length = le32_to_cpu(rsdt_table.length); - - /* compute the table entries in rsdt */ - g_assert_cmpint(rsdt_table_length, >, sizeof(AcpiRsdtDescriptorRev1)); - tables_nr = (rsdt_table_length - sizeof(AcpiRsdtDescriptorRev1)) / - sizeof(uint32_t); + acpi_parse_rsdp_table(qts, rsdp_offset, rsdp_table); + acpi_fetch_table(qts, &rsdt, &rsdt_len, &rsdp_table[16 /* RsdtAddress */], + "RSDT", true); - /* get the addresses of the tables pointed by rsdt */ - tables = g_new0(uint32_t, tables_nr); - ACPI_READ_ARRAY_PTR(qts, tables, tables_nr, rsdt); + ACPI_FOREACH_RSDT_ENTRY(rsdt, rsdt_len, ent, 4 /* Entry size */) { + uint8_t *table_aml; - for (i = 0; i < tables_nr; i++) { - uint32_t addr = le32_to_cpu(tables[i]); - ACPI_READ_TABLE_HEADER(qts, &ssdt_table, addr); - if (!strncmp((char *)ssdt_table.oem_table_id, "VMGENID", 7)) { + acpi_fetch_table(qts, &table_aml, &table_length, ent, NULL, true); + if (!memcmp(table_aml + 16 /* OEM Table ID */, "VMGENID", 7)) { + uint32_t vgia_val; + uint8_t *aml = &table_aml[36 /* AML byte-code start */]; /* the first entry in the table should be VGIA * That's all we need */ - ACPI_READ_FIELD(qts, vgid_table.name_op, addr); - g_assert(vgid_table.name_op == 0x08); /* name */ - ACPI_READ_ARRAY(qts, vgid_table.vgia, addr); - g_assert(memcmp(vgid_table.vgia, "VGIA", 4) == 0); - ACPI_READ_FIELD(qts, vgid_table.val_op, addr); - g_assert(vgid_table.val_op == 0x0C); /* dword */ - ACPI_READ_FIELD(qts, vgid_table.vgia_val, addr); + g_assert(aml[0 /* name_op*/] == 0x08); + g_assert(memcmp(&aml[1 /* name */], "VGIA", 4) == 0); + g_assert(aml[5 /* value op */] == 0x0C /* dword */); + memcpy(&vgia_val, &aml[6 /* value */], 4); + /* The GUID is written at a fixed offset into the fw_cfg file * in order to implement the "OVMF SDT Header probe suppressor" * see docs/specs/vmgenid.txt for more details */ - guid_offset = le32_to_cpu(vgid_table.vgia_val) + VMGENID_GUID_OFFSET; + guid_offset = le32_to_cpu(vgia_val) + VMGENID_GUID_OFFSET; + g_free(table_aml); break; } + g_free(table_aml); } - g_free(tables); + g_free(rsdt); return guid_offset; } diff --git a/util/oslib-posix.c b/util/oslib-posix.c index c1bee2a581..4ce1ba9ca4 100644 --- a/util/oslib-posix.c +++ b/util/oslib-posix.c @@ -233,14 +233,18 @@ void qemu_set_block(int fd) { int f; f = fcntl(fd, F_GETFL); - fcntl(fd, F_SETFL, f & ~O_NONBLOCK); + assert(f != -1); + f = fcntl(fd, F_SETFL, f & ~O_NONBLOCK); + assert(f != -1); } void qemu_set_nonblock(int fd) { int f; f = fcntl(fd, F_GETFL); - fcntl(fd, F_SETFL, f | O_NONBLOCK); + assert(f != -1); + f = fcntl(fd, F_SETFL, f | O_NONBLOCK); + assert(f != -1); } int socket_set_fast_reuse(int fd) |