diff options
433 files changed, 8522 insertions, 7264 deletions
@@ -16,3 +16,5 @@ In addition, other licenses may also apply. Please see: Documentation/process/license-rules.rst for more details. + +All contributions to the Linux Kernel are subject to this COPYING file. diff --git a/Documentation/arm64/memory.rst b/Documentation/arm64/memory.rst index 02e02175e6f5..cf03b3290800 100644 --- a/Documentation/arm64/memory.rst +++ b/Documentation/arm64/memory.rst @@ -129,7 +129,7 @@ this logic. As a single binary will need to support both 48-bit and 52-bit VA spaces, the VMEMMAP must be sized large enough for 52-bit VAs and -also must be sized large enought to accommodate a fixed PAGE_OFFSET. +also must be sized large enough to accommodate a fixed PAGE_OFFSET. Most code in the kernel should not need to consider the VA_BITS, for code that does need to know the VA size the variables are diff --git a/Documentation/arm64/tagged-address-abi.rst b/Documentation/arm64/tagged-address-abi.rst index d4a85d535bf9..4a9d9c794ee5 100644 --- a/Documentation/arm64/tagged-address-abi.rst +++ b/Documentation/arm64/tagged-address-abi.rst @@ -44,8 +44,15 @@ The AArch64 Tagged Address ABI has two stages of relaxation depending how the user addresses are used by the kernel: 1. User addresses not accessed by the kernel but used for address space - management (e.g. ``mmap()``, ``mprotect()``, ``madvise()``). The use - of valid tagged pointers in this context is always allowed. + management (e.g. ``mprotect()``, ``madvise()``). The use of valid + tagged pointers in this context is allowed with the exception of + ``brk()``, ``mmap()`` and the ``new_address`` argument to + ``mremap()`` as these have the potential to alias with existing + user addresses. + + NOTE: This behaviour changed in v5.6 and so some earlier kernels may + incorrectly accept valid tagged pointers for the ``brk()``, + ``mmap()`` and ``mremap()`` system calls. 2. User addresses accessed by the kernel (e.g. ``write()``). This ABI relaxation is disabled by default and the application thread needs to diff --git a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml index 86ad617d2327..5ff9cf26ca38 100644 --- a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml +++ b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml @@ -43,9 +43,13 @@ properties: - enum: - allwinner,sun8i-h3-tcon-tv - allwinner,sun50i-a64-tcon-tv - - allwinner,sun50i-h6-tcon-tv - const: allwinner,sun8i-a83t-tcon-tv + - items: + - enum: + - allwinner,sun50i-h6-tcon-tv + - const: allwinner,sun8i-r40-tcon-tv + reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml index 9af873b43acd..8453ee340b9f 100644 --- a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml +++ b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml @@ -33,24 +33,40 @@ properties: maxItems: 1 clocks: - minItems: 2 - maxItems: 3 - items: - - description: The CSI interface clock - - description: The CSI ISP clock - - description: The CSI DRAM clock + oneOf: + - items: + - description: The CSI interface clock + - description: The CSI DRAM clock + + - items: + - description: The CSI interface clock + - description: The CSI ISP clock + - description: The CSI DRAM clock clock-names: - minItems: 2 - maxItems: 3 - items: - - const: bus - - const: isp - - const: ram + oneOf: + - items: + - const: bus + - const: ram + + - items: + - const: bus + - const: isp + - const: ram resets: maxItems: 1 + # FIXME: This should be made required eventually once every SoC will + # have the MBUS declared. + interconnects: + maxItems: 1 + + # FIXME: This should be made required eventually once every SoC will + # have the MBUS declared. + interconnect-names: + const: dma-mem + # See ./video-interfaces.txt for details port: type: object diff --git a/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra124-emc.yaml b/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra124-emc.yaml index dd1843489ad1..3e0a8a92d652 100644 --- a/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra124-emc.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/nvidia,tegra124-emc.yaml @@ -347,6 +347,7 @@ examples: interrupts = <GIC_SPI 77 IRQ_TYPE_LEVEL_HIGH>; #iommu-cells = <1>; + #reset-cells = <1>; }; external-memory-controller@7001b000 { @@ -363,20 +364,23 @@ examples: timing-0 { clock-frequency = <12750000>; - nvidia,emc-zcal-cnt-long = <0x00000042>; - nvidia,emc-auto-cal-interval = <0x001fffff>; - nvidia,emc-ctt-term-ctrl = <0x00000802>; - nvidia,emc-cfg = <0x73240000>; - nvidia,emc-cfg-2 = <0x000008c5>; - nvidia,emc-sel-dpd-ctrl = <0x00040128>; - nvidia,emc-bgbias-ctl0 = <0x00000008>; nvidia,emc-auto-cal-config = <0xa1430000>; nvidia,emc-auto-cal-config2 = <0x00000000>; nvidia,emc-auto-cal-config3 = <0x00000000>; - nvidia,emc-mode-reset = <0x80001221>; + nvidia,emc-auto-cal-interval = <0x001fffff>; + nvidia,emc-bgbias-ctl0 = <0x00000008>; + nvidia,emc-cfg = <0x73240000>; + nvidia,emc-cfg-2 = <0x000008c5>; + nvidia,emc-ctt-term-ctrl = <0x00000802>; nvidia,emc-mode-1 = <0x80100003>; nvidia,emc-mode-2 = <0x80200008>; nvidia,emc-mode-4 = <0x00000000>; + nvidia,emc-mode-reset = <0x80001221>; + nvidia,emc-mrs-wait-cnt = <0x000e000e>; + nvidia,emc-sel-dpd-ctrl = <0x00040128>; + nvidia,emc-xm2dqspadctrl2 = <0x0130b118>; + nvidia,emc-zcal-cnt-long = <0x00000042>; + nvidia,emc-zcal-interval = <0x00000000>; nvidia,emc-configuration = < 0x00000000 /* EMC_RC */ diff --git a/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt b/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt index 19f5508a7569..4a9145ef15d6 100644 --- a/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt +++ b/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt @@ -124,7 +124,7 @@ not every application needs SDIO irq, e.g. MMC cards. pinctrl-1 = <&mmc1_idle>; pinctrl-2 = <&mmc1_sleep>; ... - interrupts-extended = <&intc 64 &gpio2 28 GPIO_ACTIVE_LOW>; + interrupts-extended = <&intc 64 &gpio2 28 IRQ_TYPE_LEVEL_LOW>; }; mmc1_idle : pinmux_cirq_pin { diff --git a/Documentation/devicetree/bindings/net/mdio.yaml b/Documentation/devicetree/bindings/net/mdio.yaml index 5d08d2ffd4eb..50c3397a82bc 100644 --- a/Documentation/devicetree/bindings/net/mdio.yaml +++ b/Documentation/devicetree/bindings/net/mdio.yaml @@ -56,7 +56,6 @@ patternProperties: examples: - | davinci_mdio: mdio@5c030000 { - compatible = "ti,davinci_mdio"; reg = <0x5c030000 0x1000>; #address-cells = <1>; #size-cells = <0>; diff --git a/Documentation/driver-api/ipmb.rst b/Documentation/driver-api/ipmb.rst index 3ec3baed84c4..209c49e05116 100644 --- a/Documentation/driver-api/ipmb.rst +++ b/Documentation/driver-api/ipmb.rst @@ -71,9 +71,13 @@ b) Example for device tree:: ipmb@10 { compatible = "ipmb-dev"; reg = <0x10>; + i2c-protocol; }; }; +If xmit of data to be done using raw i2c block vs smbus +then "i2c-protocol" needs to be defined as above. + 2) Manually from Linux:: modprobe ipmb-dev-int diff --git a/Documentation/hwmon/xdpe12284.rst b/Documentation/hwmon/xdpe12284.rst index 6b7ae98cc536..67d1f87808e5 100644 --- a/Documentation/hwmon/xdpe12284.rst +++ b/Documentation/hwmon/xdpe12284.rst @@ -24,6 +24,7 @@ This driver implements support for Infineon Multi-phase XDPE122 family dual loop voltage regulators. The family includes XDPE12284 and XDPE12254 devices. The devices from this family complaint with: + - Intel VR13 and VR13HC rev 1.3, IMVP8 rev 1.2 and IMPVP9 rev 1.3 DC-DC converter specification. - Intel SVID rev 1.9. protocol. diff --git a/Documentation/process/embargoed-hardware-issues.rst b/Documentation/process/embargoed-hardware-issues.rst index 33edae654599..a19d084f9b2c 100644 --- a/Documentation/process/embargoed-hardware-issues.rst +++ b/Documentation/process/embargoed-hardware-issues.rst @@ -244,23 +244,23 @@ disclosure of a particular issue, unless requested by a response team or by an involved disclosed party. The current ambassadors list: ============= ======================================================== - ARM + ARM Grant Likely <grant.likely@arm.com> AMD Tom Lendacky <tom.lendacky@amd.com> IBM Intel Tony Luck <tony.luck@intel.com> Qualcomm Trilok Soni <tsoni@codeaurora.org> - Microsoft Sasha Levin <sashal@kernel.org> + Microsoft James Morris <jamorris@linux.microsoft.com> VMware Xen Andrew Cooper <andrew.cooper3@citrix.com> - Canonical Tyler Hicks <tyhicks@canonical.com> + Canonical John Johansen <john.johansen@canonical.com> Debian Ben Hutchings <ben@decadent.org.uk> Oracle Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Red Hat Josh Poimboeuf <jpoimboe@redhat.com> SUSE Jiri Kosina <jkosina@suse.cz> - Amazon Peter Bowen <pzb@amzn.com> + Amazon Google Kees Cook <keescook@chromium.org> ============= ======================================================== diff --git a/Documentation/translations/zh_CN/process/embargoed-hardware-issues.rst b/Documentation/translations/zh_CN/process/embargoed-hardware-issues.rst index b93f1af68261..88273ebe7823 100644 --- a/Documentation/translations/zh_CN/process/embargoed-hardware-issues.rst +++ b/Documentation/translations/zh_CN/process/embargoed-hardware-issues.rst @@ -183,7 +183,7 @@ CVE分配 VMware Xen Andrew Cooper <andrew.cooper3@citrix.com> - Canonical Tyler Hicks <tyhicks@canonical.com> + Canonical John Johansen <john.johansen@canonical.com> Debian Ben Hutchings <ben@decadent.org.uk> Oracle Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Red Hat Josh Poimboeuf <jpoimboe@redhat.com> diff --git a/Documentation/virtual/guest-halt-polling.txt b/Documentation/virt/guest-halt-polling.rst index b3a2a294532d..b4e747942417 100644 --- a/Documentation/virtual/guest-halt-polling.txt +++ b/Documentation/virt/guest-halt-polling.rst @@ -1,9 +1,11 @@ +================== Guest halt polling ================== The cpuidle_haltpoll driver, with the haltpoll governor, allows the guest vcpus to poll for a specified amount of time before halting. + This provides the following benefits to host side polling: 1) The POLL flag is set while polling is performed, which allows @@ -29,18 +31,21 @@ Module Parameters The haltpoll governor has 5 tunable module parameters: 1) guest_halt_poll_ns: + Maximum amount of time, in nanoseconds, that polling is performed before halting. Default: 200000 2) guest_halt_poll_shrink: + Division factor used to shrink per-cpu guest_halt_poll_ns when wakeup event occurs after the global guest_halt_poll_ns. Default: 2 3) guest_halt_poll_grow: + Multiplication factor used to grow per-cpu guest_halt_poll_ns when event occurs after per-cpu guest_halt_poll_ns but before global guest_halt_poll_ns. @@ -48,6 +53,7 @@ but before global guest_halt_poll_ns. Default: 2 4) guest_halt_poll_grow_start: + The per-cpu guest_halt_poll_ns eventually reaches zero in case of an idle system. This value sets the initial per-cpu guest_halt_poll_ns when growing. This can @@ -66,7 +72,7 @@ high once achieves global guest_halt_poll_ns value). Default: Y -The module parameters can be set from the debugfs files in: +The module parameters can be set from the debugfs files in:: /sys/module/haltpoll/parameters/ @@ -74,5 +80,5 @@ Further Notes ============= - Care should be taken when setting the guest_halt_poll_ns parameter as a -large value has the potential to drive the cpu usage to 100% on a machine which -would be almost entirely idle otherwise. + large value has the potential to drive the cpu usage to 100% on a machine + which would be almost entirely idle otherwise. diff --git a/Documentation/virt/index.rst b/Documentation/virt/index.rst index 062ffb527043..de1ab81df958 100644 --- a/Documentation/virt/index.rst +++ b/Documentation/virt/index.rst @@ -8,7 +8,9 @@ Linux Virtualization Support :maxdepth: 2 kvm/index + uml/user_mode_linux paravirt_ops + guest-halt-polling .. only:: html and subproject diff --git a/Documentation/virt/kvm/api.txt b/Documentation/virt/kvm/api.rst index c6e1ce5d40de..97a72a53fa4b 100644 --- a/Documentation/virt/kvm/api.txt +++ b/Documentation/virt/kvm/api.rst @@ -1,8 +1,11 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=================================================================== The Definitive KVM (Kernel-based Virtual Machine) API Documentation =================================================================== 1. General description ----------------------- +====================== The kvm API is a set of ioctls that are issued to control various aspects of a virtual machine. The ioctls belong to the following classes: @@ -33,7 +36,7 @@ of a virtual machine. The ioctls belong to the following classes: was used to create the VM. 2. File descriptors -------------------- +=================== The kvm API is centered around file descriptors. An initial open("/dev/kvm") obtains a handle to the kvm subsystem; this handle @@ -70,7 +73,7 @@ the VM is shut down. 3. Extensions -------------- +============= As of Linux 2.6.22, the KVM ABI has been stabilized: no backward incompatible change are allowed. However, there is an extension @@ -84,13 +87,14 @@ set of ioctls is available for application use. 4. API description ------------------- +================== This section describes ioctls that can be used to control kvm guests. For each ioctl, the following information is provided along with a description: - Capability: which KVM extension provides this ioctl. Can be 'basic', + Capability: + which KVM extension provides this ioctl. Can be 'basic', which means that is will be provided by any kernel that supports API version 12 (see section 4.1), a KVM_CAP_xyz constant, which means availability needs to be checked with KVM_CHECK_EXTENSION @@ -99,24 +103,29 @@ description: availability: for kernels that don't support the ioctl, the ioctl returns -ENOTTY. - Architectures: which instruction set architectures provide this ioctl. + Architectures: + which instruction set architectures provide this ioctl. x86 includes both i386 and x86_64. - Type: system, vm, or vcpu. + Type: + system, vm, or vcpu. - Parameters: what parameters are accepted by the ioctl. + Parameters: + what parameters are accepted by the ioctl. - Returns: the return value. General error numbers (EBADF, ENOMEM, EINVAL) + Returns: + the return value. General error numbers (EBADF, ENOMEM, EINVAL) are not detailed, but errors with specific meanings are. 4.1 KVM_GET_API_VERSION +----------------------- -Capability: basic -Architectures: all -Type: system ioctl -Parameters: none -Returns: the constant KVM_API_VERSION (=12) +:Capability: basic +:Architectures: all +:Type: system ioctl +:Parameters: none +:Returns: the constant KVM_API_VERSION (=12) This identifies the API version as the stable kvm API. It is not expected that this number will change. However, Linux 2.6.20 and @@ -127,12 +136,13 @@ described as 'basic' will be available. 4.2 KVM_CREATE_VM +----------------- -Capability: basic -Architectures: all -Type: system ioctl -Parameters: machine type identifier (KVM_VM_*) -Returns: a VM fd that can be used to control the new virtual machine. +:Capability: basic +:Architectures: all +:Type: system ioctl +:Parameters: machine type identifier (KVM_VM_*) +:Returns: a VM fd that can be used to control the new virtual machine. The new VM has no virtual cpus and no memory. You probably want to use 0 as machine type. @@ -155,17 +165,17 @@ identifier, where IPA_Bits is the maximum width of any physical address used by the VM. The IPA_Bits is encoded in bits[7-0] of the machine type identifier. -e.g, to configure a guest to use 48bit physical address size : +e.g, to configure a guest to use 48bit physical address size:: vm_fd = ioctl(dev_fd, KVM_CREATE_VM, KVM_VM_TYPE_ARM_IPA_SIZE(48)); -The requested size (IPA_Bits) must be : - 0 - Implies default size, 40bits (for backward compatibility) +The requested size (IPA_Bits) must be: - or - - N - Implies N bits, where N is a positive integer such that, + == ========================================================= + 0 Implies default size, 40bits (for backward compatibility) + N Implies N bits, where N is a positive integer such that, 32 <= N <= Host_IPA_Limit + == ========================================================= Host_IPA_Limit is the maximum possible value for IPA_Bits on the host and is dependent on the CPU capability and the kernel configuration. The limit can @@ -179,21 +189,28 @@ host physical address translations). 4.3 KVM_GET_MSR_INDEX_LIST, KVM_GET_MSR_FEATURE_INDEX_LIST +---------------------------------------------------------- + +:Capability: basic, KVM_CAP_GET_MSR_FEATURES for KVM_GET_MSR_FEATURE_INDEX_LIST +:Architectures: x86 +:Type: system ioctl +:Parameters: struct kvm_msr_list (in/out) +:Returns: 0 on success; -1 on error -Capability: basic, KVM_CAP_GET_MSR_FEATURES for KVM_GET_MSR_FEATURE_INDEX_LIST -Architectures: x86 -Type: system ioctl -Parameters: struct kvm_msr_list (in/out) -Returns: 0 on success; -1 on error Errors: - EFAULT: the msr index list cannot be read from or written to - E2BIG: the msr index list is to be to fit in the array specified by + + ====== ============================================================ + EFAULT the msr index list cannot be read from or written to + E2BIG the msr index list is to be to fit in the array specified by the user. + ====== ============================================================ -struct kvm_msr_list { +:: + + struct kvm_msr_list { __u32 nmsrs; /* number of msrs in entries */ __u32 indices[0]; -}; + }; The user fills in the size of the indices array in nmsrs, and in return kvm adjusts nmsrs to reflect the actual number of msrs and fills in the @@ -214,12 +231,13 @@ otherwise. 4.4 KVM_CHECK_EXTENSION +----------------------- -Capability: basic, KVM_CAP_CHECK_EXTENSION_VM for vm ioctl -Architectures: all -Type: system ioctl, vm ioctl -Parameters: extension identifier (KVM_CAP_*) -Returns: 0 if unsupported; 1 (or some other positive integer) if supported +:Capability: basic, KVM_CAP_CHECK_EXTENSION_VM for vm ioctl +:Architectures: all +:Type: system ioctl, vm ioctl +:Parameters: extension identifier (KVM_CAP_*) +:Returns: 0 if unsupported; 1 (or some other positive integer) if supported The API allows the application to query about extensions to the core kvm API. Userspace passes an extension identifier (an integer) and @@ -232,12 +250,13 @@ It is thus encouraged to use the vm ioctl to query for capabilities (available with KVM_CAP_CHECK_EXTENSION_VM on the vm fd) 4.5 KVM_GET_VCPU_MMAP_SIZE +-------------------------- -Capability: basic -Architectures: all -Type: system ioctl -Parameters: none -Returns: size of vcpu mmap area, in bytes +:Capability: basic +:Architectures: all +:Type: system ioctl +:Parameters: none +:Returns: size of vcpu mmap area, in bytes The KVM_RUN ioctl (cf.) communicates with userspace via a shared memory region. This ioctl returns the size of that region. See the @@ -245,23 +264,25 @@ KVM_RUN documentation for details. 4.6 KVM_SET_MEMORY_REGION +------------------------- -Capability: basic -Architectures: all -Type: vm ioctl -Parameters: struct kvm_memory_region (in) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: all +:Type: vm ioctl +:Parameters: struct kvm_memory_region (in) +:Returns: 0 on success, -1 on error This ioctl is obsolete and has been removed. 4.7 KVM_CREATE_VCPU +------------------- -Capability: basic -Architectures: all -Type: vm ioctl -Parameters: vcpu id (apic id on x86) -Returns: vcpu fd on success, -1 on error +:Capability: basic +:Architectures: all +:Type: vm ioctl +:Parameters: vcpu id (apic id on x86) +:Returns: vcpu fd on success, -1 on error This API adds a vcpu to a virtual machine. No more than max_vcpus may be added. The vcpu id is an integer in the range [0, max_vcpu_id). @@ -302,22 +323,25 @@ cpu's hardware control block. 4.8 KVM_GET_DIRTY_LOG (vm ioctl) +-------------------------------- -Capability: basic -Architectures: all -Type: vm ioctl -Parameters: struct kvm_dirty_log (in/out) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: all +:Type: vm ioctl +:Parameters: struct kvm_dirty_log (in/out) +:Returns: 0 on success, -1 on error -/* for KVM_GET_DIRTY_LOG */ -struct kvm_dirty_log { +:: + + /* for KVM_GET_DIRTY_LOG */ + struct kvm_dirty_log { __u32 slot; __u32 padding; union { void __user *dirty_bitmap; /* one bit per page */ __u64 padding; }; -}; + }; Given a memory slot, return a bitmap containing any pages dirtied since the last call to this ioctl. Bit 0 is the first page in the @@ -334,25 +358,31 @@ KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is enabled. For more information, see the description of the capability. 4.9 KVM_SET_MEMORY_ALIAS +------------------------ -Capability: basic -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_memory_alias (in) -Returns: 0 (success), -1 (error) +:Capability: basic +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_memory_alias (in) +:Returns: 0 (success), -1 (error) This ioctl is obsolete and has been removed. 4.10 KVM_RUN +------------ + +:Capability: basic +:Architectures: all +:Type: vcpu ioctl +:Parameters: none +:Returns: 0 on success, -1 on error -Capability: basic -Architectures: all -Type: vcpu ioctl -Parameters: none -Returns: 0 on success, -1 on error Errors: - EINTR: an unmasked signal is pending + + ===== ============================= + EINTR an unmasked signal is pending + ===== ============================= This ioctl is used to run a guest virtual cpu. While there are no explicit parameters, there is an implicit parameter block that can be @@ -362,42 +392,46 @@ kvm_run' (see below). 4.11 KVM_GET_REGS +----------------- -Capability: basic -Architectures: all except ARM, arm64 -Type: vcpu ioctl -Parameters: struct kvm_regs (out) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: all except ARM, arm64 +:Type: vcpu ioctl +:Parameters: struct kvm_regs (out) +:Returns: 0 on success, -1 on error Reads the general purpose registers from the vcpu. -/* x86 */ -struct kvm_regs { +:: + + /* x86 */ + struct kvm_regs { /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */ __u64 rax, rbx, rcx, rdx; __u64 rsi, rdi, rsp, rbp; __u64 r8, r9, r10, r11; __u64 r12, r13, r14, r15; __u64 rip, rflags; -}; + }; -/* mips */ -struct kvm_regs { + /* mips */ + struct kvm_regs { /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */ __u64 gpr[32]; __u64 hi; __u64 lo; __u64 pc; -}; + }; 4.12 KVM_SET_REGS +----------------- -Capability: basic -Architectures: all except ARM, arm64 -Type: vcpu ioctl -Parameters: struct kvm_regs (in) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: all except ARM, arm64 +:Type: vcpu ioctl +:Parameters: struct kvm_regs (in) +:Returns: 0 on success, -1 on error Writes the general purpose registers into the vcpu. @@ -405,17 +439,20 @@ See KVM_GET_REGS for the data structure. 4.13 KVM_GET_SREGS +------------------ -Capability: basic -Architectures: x86, ppc -Type: vcpu ioctl -Parameters: struct kvm_sregs (out) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: x86, ppc +:Type: vcpu ioctl +:Parameters: struct kvm_sregs (out) +:Returns: 0 on success, -1 on error Reads special registers from the vcpu. -/* x86 */ -struct kvm_sregs { +:: + + /* x86 */ + struct kvm_sregs { struct kvm_segment cs, ds, es, fs, gs, ss; struct kvm_segment tr, ldt; struct kvm_dtable gdt, idt; @@ -423,9 +460,9 @@ struct kvm_sregs { __u64 efer; __u64 apic_base; __u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64]; -}; + }; -/* ppc -- see arch/powerpc/include/uapi/asm/kvm.h */ + /* ppc -- see arch/powerpc/include/uapi/asm/kvm.h */ interrupt_bitmap is a bitmap of pending external interrupts. At most one bit may be set. This interrupt has been acknowledged by the APIC @@ -433,29 +470,33 @@ but not yet injected into the cpu core. 4.14 KVM_SET_SREGS +------------------ -Capability: basic -Architectures: x86, ppc -Type: vcpu ioctl -Parameters: struct kvm_sregs (in) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: x86, ppc +:Type: vcpu ioctl +:Parameters: struct kvm_sregs (in) +:Returns: 0 on success, -1 on error Writes special registers into the vcpu. See KVM_GET_SREGS for the data structures. 4.15 KVM_TRANSLATE +------------------ -Capability: basic -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_translation (in/out) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_translation (in/out) +:Returns: 0 on success, -1 on error Translates a virtual address according to the vcpu's current address translation mode. -struct kvm_translation { +:: + + struct kvm_translation { /* in */ __u64 linear_address; @@ -465,59 +506,68 @@ struct kvm_translation { __u8 writeable; __u8 usermode; __u8 pad[5]; -}; + }; 4.16 KVM_INTERRUPT +------------------ -Capability: basic -Architectures: x86, ppc, mips -Type: vcpu ioctl -Parameters: struct kvm_interrupt (in) -Returns: 0 on success, negative on failure. +:Capability: basic +:Architectures: x86, ppc, mips +:Type: vcpu ioctl +:Parameters: struct kvm_interrupt (in) +:Returns: 0 on success, negative on failure. Queues a hardware interrupt vector to be injected. -/* for KVM_INTERRUPT */ -struct kvm_interrupt { +:: + + /* for KVM_INTERRUPT */ + struct kvm_interrupt { /* in */ __u32 irq; -}; + }; X86: +^^^^ + +:Returns: -Returns: 0 on success, - -EEXIST if an interrupt is already enqueued - -EINVAL the the irq number is invalid - -ENXIO if the PIC is in the kernel - -EFAULT if the pointer is invalid + ========= =================================== + 0 on success, + -EEXIST if an interrupt is already enqueued + -EINVAL the the irq number is invalid + -ENXIO if the PIC is in the kernel + -EFAULT if the pointer is invalid + ========= =================================== Note 'irq' is an interrupt vector, not an interrupt pin or line. This ioctl is useful if the in-kernel PIC is not used. PPC: +^^^^ Queues an external interrupt to be injected. This ioctl is overleaded with 3 different irq values: a) KVM_INTERRUPT_SET - This injects an edge type external interrupt into the guest once it's ready - to receive interrupts. When injected, the interrupt is done. + This injects an edge type external interrupt into the guest once it's ready + to receive interrupts. When injected, the interrupt is done. b) KVM_INTERRUPT_UNSET - This unsets any pending interrupt. + This unsets any pending interrupt. - Only available with KVM_CAP_PPC_UNSET_IRQ. + Only available with KVM_CAP_PPC_UNSET_IRQ. c) KVM_INTERRUPT_SET_LEVEL - This injects a level type external interrupt into the guest context. The - interrupt stays pending until a specific ioctl with KVM_INTERRUPT_UNSET - is triggered. + This injects a level type external interrupt into the guest context. The + interrupt stays pending until a specific ioctl with KVM_INTERRUPT_UNSET + is triggered. - Only available with KVM_CAP_PPC_IRQ_LEVEL. + Only available with KVM_CAP_PPC_IRQ_LEVEL. Note that any value for 'irq' other than the ones stated above is invalid and incurs unexpected behavior. @@ -525,6 +575,7 @@ and incurs unexpected behavior. This is an asynchronous vcpu ioctl and can be invoked from any thread. MIPS: +^^^^^ Queues an external interrupt to be injected into the virtual CPU. A negative interrupt number dequeues the interrupt. @@ -533,24 +584,26 @@ This is an asynchronous vcpu ioctl and can be invoked from any thread. 4.17 KVM_DEBUG_GUEST +-------------------- -Capability: basic -Architectures: none -Type: vcpu ioctl -Parameters: none) -Returns: -1 on error +:Capability: basic +:Architectures: none +:Type: vcpu ioctl +:Parameters: none) +:Returns: -1 on error Support for this has been removed. Use KVM_SET_GUEST_DEBUG instead. 4.18 KVM_GET_MSRS +----------------- -Capability: basic (vcpu), KVM_CAP_GET_MSR_FEATURES (system) -Architectures: x86 -Type: system ioctl, vcpu ioctl -Parameters: struct kvm_msrs (in/out) -Returns: number of msrs successfully returned; - -1 on error +:Capability: basic (vcpu), KVM_CAP_GET_MSR_FEATURES (system) +:Architectures: x86 +:Type: system ioctl, vcpu ioctl +:Parameters: struct kvm_msrs (in/out) +:Returns: number of msrs successfully returned; + -1 on error When used as a system ioctl: Reads the values of MSR-based features that are available for the VM. This @@ -562,18 +615,20 @@ When used as a vcpu ioctl: Reads model-specific registers from the vcpu. Supported msr indices can be obtained using KVM_GET_MSR_INDEX_LIST in a system ioctl. -struct kvm_msrs { +:: + + struct kvm_msrs { __u32 nmsrs; /* number of msrs in entries */ __u32 pad; struct kvm_msr_entry entries[0]; -}; + }; -struct kvm_msr_entry { + struct kvm_msr_entry { __u32 index; __u32 reserved; __u64 data; -}; + }; Application code should set the 'nmsrs' member (which indicates the size of the entries array) and the 'index' member of each array entry. @@ -581,12 +636,13 @@ kvm will fill in the 'data' member. 4.19 KVM_SET_MSRS +----------------- -Capability: basic -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_msrs (in) -Returns: number of msrs successfully set (see below), -1 on error +:Capability: basic +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_msrs (in) +:Returns: number of msrs successfully set (see below), -1 on error Writes model-specific registers to the vcpu. See KVM_GET_MSRS for the data structures. @@ -602,41 +658,44 @@ MSRs that have been set successfully. 4.20 KVM_SET_CPUID +------------------ -Capability: basic -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_cpuid (in) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_cpuid (in) +:Returns: 0 on success, -1 on error Defines the vcpu responses to the cpuid instruction. Applications should use the KVM_SET_CPUID2 ioctl if available. +:: -struct kvm_cpuid_entry { + struct kvm_cpuid_entry { __u32 function; __u32 eax; __u32 ebx; __u32 ecx; __u32 edx; __u32 padding; -}; + }; -/* for KVM_SET_CPUID */ -struct kvm_cpuid { + /* for KVM_SET_CPUID */ + struct kvm_cpuid { __u32 nent; __u32 padding; struct kvm_cpuid_entry entries[0]; -}; + }; 4.21 KVM_SET_SIGNAL_MASK +------------------------ -Capability: basic -Architectures: all -Type: vcpu ioctl -Parameters: struct kvm_signal_mask (in) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: all +:Type: vcpu ioctl +:Parameters: struct kvm_signal_mask (in) +:Returns: 0 on success, -1 on error Defines which signals are blocked during execution of KVM_RUN. This signal mask temporarily overrides the threads signal mask. Any @@ -646,25 +705,30 @@ their traditional behaviour) will cause KVM_RUN to return with -EINTR. Note the signal will only be delivered if not blocked by the original signal mask. -/* for KVM_SET_SIGNAL_MASK */ -struct kvm_signal_mask { +:: + + /* for KVM_SET_SIGNAL_MASK */ + struct kvm_signal_mask { __u32 len; __u8 sigset[0]; -}; + }; 4.22 KVM_GET_FPU +---------------- -Capability: basic -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_fpu (out) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_fpu (out) +:Returns: 0 on success, -1 on error Reads the floating point state from the vcpu. -/* for KVM_GET_FPU and KVM_SET_FPU */ -struct kvm_fpu { +:: + + /* for KVM_GET_FPU and KVM_SET_FPU */ + struct kvm_fpu { __u8 fpr[8][16]; __u16 fcw; __u16 fsw; @@ -676,21 +740,24 @@ struct kvm_fpu { __u8 xmm[16][16]; __u32 mxcsr; __u32 pad2; -}; + }; 4.23 KVM_SET_FPU +---------------- -Capability: basic -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_fpu (in) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_fpu (in) +:Returns: 0 on success, -1 on error Writes the floating point state to the vcpu. -/* for KVM_GET_FPU and KVM_SET_FPU */ -struct kvm_fpu { +:: + + /* for KVM_GET_FPU and KVM_SET_FPU */ + struct kvm_fpu { __u8 fpr[8][16]; __u16 fcw; __u16 fsw; @@ -702,16 +769,17 @@ struct kvm_fpu { __u8 xmm[16][16]; __u32 mxcsr; __u32 pad2; -}; + }; 4.24 KVM_CREATE_IRQCHIP +----------------------- -Capability: KVM_CAP_IRQCHIP, KVM_CAP_S390_IRQCHIP (s390) -Architectures: x86, ARM, arm64, s390 -Type: vm ioctl -Parameters: none -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_IRQCHIP, KVM_CAP_S390_IRQCHIP (s390) +:Architectures: x86, ARM, arm64, s390 +:Type: vm ioctl +:Parameters: none +:Returns: 0 on success, -1 on error Creates an interrupt controller model in the kernel. On x86, creates a virtual ioapic, a virtual PIC (two PICs, nested), and sets up @@ -727,12 +795,13 @@ before KVM_CREATE_IRQCHIP can be used. 4.25 KVM_IRQ_LINE +----------------- -Capability: KVM_CAP_IRQCHIP -Architectures: x86, arm, arm64 -Type: vm ioctl -Parameters: struct kvm_irq_level -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_IRQCHIP +:Architectures: x86, arm, arm64 +:Type: vm ioctl +:Parameters: struct kvm_irq_level +:Returns: 0 on success, -1 on error Sets the level of a GSI input to the interrupt controller model in the kernel. On some architectures it is required that an interrupt controller model has @@ -756,16 +825,20 @@ of course). ARM/arm64 can signal an interrupt either at the CPU level, or at the in-kernel irqchip (GIC), and for in-kernel irqchip can tell the GIC to use PPIs designated for specific cpus. The irq field is interpreted -like this: +like this:: bits: | 31 ... 28 | 27 ... 24 | 23 ... 16 | 15 ... 0 | field: | vcpu2_index | irq_type | vcpu_index | irq_id | The irq_type field has the following values: -- irq_type[0]: out-of-kernel GIC: irq_id 0 is IRQ, irq_id 1 is FIQ -- irq_type[1]: in-kernel GIC: SPI, irq_id between 32 and 1019 (incl.) + +- irq_type[0]: + out-of-kernel GIC: irq_id 0 is IRQ, irq_id 1 is FIQ +- irq_type[1]: + in-kernel GIC: SPI, irq_id between 32 and 1019 (incl.) (the vcpu_index field is ignored) -- irq_type[2]: in-kernel GIC: PPI, irq_id between 16 and 31 (incl.) +- irq_type[2]: + in-kernel GIC: PPI, irq_id between 16 and 31 (incl.) (The irq_id field thus corresponds nicely to the IRQ ID in the ARM GIC specs) @@ -779,27 +852,32 @@ Note that on arm/arm64, the KVM_CAP_IRQCHIP capability only conditions injection of interrupts for the in-kernel irqchip. KVM_IRQ_LINE can always be used for a userspace interrupt controller. -struct kvm_irq_level { +:: + + struct kvm_irq_level { union { __u32 irq; /* GSI */ __s32 status; /* not used for KVM_IRQ_LEVEL */ }; __u32 level; /* 0 or 1 */ -}; + }; 4.26 KVM_GET_IRQCHIP +-------------------- -Capability: KVM_CAP_IRQCHIP -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_irqchip (in/out) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_IRQCHIP +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_irqchip (in/out) +:Returns: 0 on success, -1 on error Reads the state of a kernel interrupt controller created with KVM_CREATE_IRQCHIP into a buffer provided by the caller. -struct kvm_irqchip { +:: + + struct kvm_irqchip { __u32 chip_id; /* 0 = PIC1, 1 = PIC2, 2 = IOAPIC */ __u32 pad; union { @@ -807,21 +885,24 @@ struct kvm_irqchip { struct kvm_pic_state pic; struct kvm_ioapic_state ioapic; } chip; -}; + }; 4.27 KVM_SET_IRQCHIP +-------------------- -Capability: KVM_CAP_IRQCHIP -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_irqchip (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_IRQCHIP +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_irqchip (in) +:Returns: 0 on success, -1 on error Sets the state of a kernel interrupt controller created with KVM_CREATE_IRQCHIP from a buffer provided by the caller. -struct kvm_irqchip { +:: + + struct kvm_irqchip { __u32 chip_id; /* 0 = PIC1, 1 = PIC2, 2 = IOAPIC */ __u32 pad; union { @@ -829,16 +910,17 @@ struct kvm_irqchip { struct kvm_pic_state pic; struct kvm_ioapic_state ioapic; } chip; -}; + }; 4.28 KVM_XEN_HVM_CONFIG +----------------------- -Capability: KVM_CAP_XEN_HVM -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_xen_hvm_config (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_XEN_HVM +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_xen_hvm_config (in) +:Returns: 0 on success, -1 on error Sets the MSR that the Xen HVM guest uses to initialize its hypercall page, and provides the starting address and size of the hypercall @@ -846,7 +928,9 @@ blobs in userspace. When the guest writes the MSR, kvm copies one page of a blob (32- or 64-bit, depending on the vcpu mode) to guest memory. -struct kvm_xen_hvm_config { +:: + + struct kvm_xen_hvm_config { __u32 flags; __u32 msr; __u64 blob_addr_32; @@ -854,16 +938,17 @@ struct kvm_xen_hvm_config { __u8 blob_size_32; __u8 blob_size_64; __u8 pad2[30]; -}; + }; 4.29 KVM_GET_CLOCK +------------------ -Capability: KVM_CAP_ADJUST_CLOCK -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_clock_data (out) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_ADJUST_CLOCK +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_clock_data (out) +:Returns: 0 on success, -1 on error Gets the current timestamp of kvmclock as seen by the current guest. In conjunction with KVM_SET_CLOCK, it is used to ensure monotonicity on scenarios @@ -880,47 +965,56 @@ with KVM_SET_CLOCK. KVM will try to make all VCPUs follow this clock, but the exact value read by each VCPU could differ, because the host TSC is not stable. -struct kvm_clock_data { +:: + + struct kvm_clock_data { __u64 clock; /* kvmclock current value */ __u32 flags; __u32 pad[9]; -}; + }; 4.30 KVM_SET_CLOCK +------------------ -Capability: KVM_CAP_ADJUST_CLOCK -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_clock_data (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_ADJUST_CLOCK +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_clock_data (in) +:Returns: 0 on success, -1 on error Sets the current timestamp of kvmclock to the value specified in its parameter. In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios such as migration. -struct kvm_clock_data { +:: + + struct kvm_clock_data { __u64 clock; /* kvmclock current value */ __u32 flags; __u32 pad[9]; -}; + }; 4.31 KVM_GET_VCPU_EVENTS +------------------------ -Capability: KVM_CAP_VCPU_EVENTS -Extended by: KVM_CAP_INTR_SHADOW -Architectures: x86, arm, arm64 -Type: vcpu ioctl -Parameters: struct kvm_vcpu_event (out) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_VCPU_EVENTS +:Extended by: KVM_CAP_INTR_SHADOW +:Architectures: x86, arm, arm64 +:Type: vcpu ioctl +:Parameters: struct kvm_vcpu_event (out) +:Returns: 0 on success, -1 on error X86: +^^^^ Gets currently pending exceptions, interrupts, and NMIs as well as related states of the vcpu. -struct kvm_vcpu_events { +:: + + struct kvm_vcpu_events { struct { __u8 injected; __u8 nr; @@ -951,7 +1045,7 @@ struct kvm_vcpu_events { __u8 reserved[27]; __u8 exception_has_payload; __u64 exception_payload; -}; + }; The following bits are defined in the flags field: @@ -967,6 +1061,7 @@ The following bits are defined in the flags field: KVM_CAP_EXCEPTION_PAYLOAD is enabled. ARM/ARM64: +^^^^^^^^^^ If the guest accesses a device that is being emulated by the host kernel in such a way that a real device would generate a physical SError, KVM may make @@ -1006,8 +1101,9 @@ It is not possible to read back a pending external abort (injected via KVM_SET_VCPU_EVENTS or otherwise) because such an exception is always delivered directly to the virtual CPU). +:: -struct kvm_vcpu_events { + struct kvm_vcpu_events { struct { __u8 serror_pending; __u8 serror_has_esr; @@ -1017,18 +1113,20 @@ struct kvm_vcpu_events { __u64 serror_esr; } exception; __u32 reserved[12]; -}; + }; 4.32 KVM_SET_VCPU_EVENTS +------------------------ -Capability: KVM_CAP_VCPU_EVENTS -Extended by: KVM_CAP_INTR_SHADOW -Architectures: x86, arm, arm64 -Type: vcpu ioctl -Parameters: struct kvm_vcpu_event (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_VCPU_EVENTS +:Extended by: KVM_CAP_INTR_SHADOW +:Architectures: x86, arm, arm64 +:Type: vcpu ioctl +:Parameters: struct kvm_vcpu_event (in) +:Returns: 0 on success, -1 on error X86: +^^^^ Set pending exceptions, interrupts, and NMIs as well as related states of the vcpu. @@ -1040,9 +1138,11 @@ from the update. These fields are nmi.pending, sipi_vector, smi.smm, smi.pending. Keep the corresponding bits in the flags field cleared to suppress overwriting the current in-kernel state. The bits are: -KVM_VCPUEVENT_VALID_NMI_PENDING - transfer nmi.pending to the kernel -KVM_VCPUEVENT_VALID_SIPI_VECTOR - transfer sipi_vector -KVM_VCPUEVENT_VALID_SMM - transfer the smi sub-struct. +=============================== ================================== +KVM_VCPUEVENT_VALID_NMI_PENDING transfer nmi.pending to the kernel +KVM_VCPUEVENT_VALID_SIPI_VECTOR transfer sipi_vector +KVM_VCPUEVENT_VALID_SMM transfer the smi sub-struct. +=============================== ================================== If KVM_CAP_INTR_SHADOW is available, KVM_VCPUEVENT_VALID_SHADOW can be set in the flags field to signal that interrupt.shadow contains a valid state and @@ -1056,6 +1156,7 @@ exception_has_payload, exception_payload, and exception.pending fields contain a valid state and shall be written into the VCPU. ARM/ARM64: +^^^^^^^^^^ User space may need to inject several types of events to the guest. @@ -1078,31 +1179,35 @@ See KVM_GET_VCPU_EVENTS for the data structure. 4.33 KVM_GET_DEBUGREGS +---------------------- -Capability: KVM_CAP_DEBUGREGS -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_debugregs (out) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_DEBUGREGS +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_debugregs (out) +:Returns: 0 on success, -1 on error Reads debug registers from the vcpu. -struct kvm_debugregs { +:: + + struct kvm_debugregs { __u64 db[4]; __u64 dr6; __u64 dr7; __u64 flags; __u64 reserved[9]; -}; + }; 4.34 KVM_SET_DEBUGREGS +---------------------- -Capability: KVM_CAP_DEBUGREGS -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_debugregs (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_DEBUGREGS +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_debugregs (in) +:Returns: 0 on success, -1 on error Writes debug registers into the vcpu. @@ -1111,24 +1216,27 @@ yet and must be cleared on entry. 4.35 KVM_SET_USER_MEMORY_REGION +------------------------------- + +:Capability: KVM_CAP_USER_MEMORY +:Architectures: all +:Type: vm ioctl +:Parameters: struct kvm_userspace_memory_region (in) +:Returns: 0 on success, -1 on error -Capability: KVM_CAP_USER_MEMORY -Architectures: all -Type: vm ioctl -Parameters: struct kvm_userspace_memory_region (in) -Returns: 0 on success, -1 on error +:: -struct kvm_userspace_memory_region { + struct kvm_userspace_memory_region { __u32 slot; __u32 flags; __u64 guest_phys_addr; __u64 memory_size; /* bytes */ __u64 userspace_addr; /* start of the userspace allocated memory */ -}; + }; -/* for kvm_memory_region::flags */ -#define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0) -#define KVM_MEM_READONLY (1UL << 1) + /* for kvm_memory_region::flags */ + #define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0) + #define KVM_MEM_READONLY (1UL << 1) This ioctl allows the user to create, modify or delete a guest physical memory slot. Bits 0-15 of "slot" specify the slot id and this value @@ -1174,12 +1282,13 @@ allocation and is deprecated. 4.36 KVM_SET_TSS_ADDR +--------------------- -Capability: KVM_CAP_SET_TSS_ADDR -Architectures: x86 -Type: vm ioctl -Parameters: unsigned long tss_address (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_SET_TSS_ADDR +:Architectures: x86 +:Type: vm ioctl +:Parameters: unsigned long tss_address (in) +:Returns: 0 on success, -1 on error This ioctl defines the physical address of a three-page region in the guest physical address space. The region must be within the first 4GB of the @@ -1193,21 +1302,24 @@ documentation when it pops into existence). 4.37 KVM_ENABLE_CAP +------------------- -Capability: KVM_CAP_ENABLE_CAP -Architectures: mips, ppc, s390 -Type: vcpu ioctl -Parameters: struct kvm_enable_cap (in) -Returns: 0 on success; -1 on error +:Capability: KVM_CAP_ENABLE_CAP +:Architectures: mips, ppc, s390 +:Type: vcpu ioctl +:Parameters: struct kvm_enable_cap (in) +:Returns: 0 on success; -1 on error -Capability: KVM_CAP_ENABLE_CAP_VM -Architectures: all -Type: vcpu ioctl -Parameters: struct kvm_enable_cap (in) -Returns: 0 on success; -1 on error +:Capability: KVM_CAP_ENABLE_CAP_VM +:Architectures: all +:Type: vcpu ioctl +:Parameters: struct kvm_enable_cap (in) +:Returns: 0 on success; -1 on error + +.. note:: -+Not all extensions are enabled by default. Using this ioctl the application -can enable an extension, making it available to the guest. + Not all extensions are enabled by default. Using this ioctl the application + can enable an extension, making it available to the guest. On systems that do not support this ioctl, it always fails. On systems that do support it, it only works for extensions that are supported for enablement. @@ -1215,76 +1327,91 @@ do support it, it only works for extensions that are supported for enablement. To check if a capability can be enabled, the KVM_CHECK_EXTENSION ioctl should be used. -struct kvm_enable_cap { +:: + + struct kvm_enable_cap { /* in */ __u32 cap; The capability that is supposed to get enabled. +:: + __u32 flags; A bitfield indicating future enhancements. Has to be 0 for now. +:: + __u64 args[4]; Arguments for enabling a feature. If a feature needs initial values to function properly, this is the place to put them. +:: + __u8 pad[64]; -}; + }; The vcpu ioctl should be used for vcpu-specific capabilities, the vm ioctl for vm-wide capabilities. 4.38 KVM_GET_MP_STATE +--------------------- -Capability: KVM_CAP_MP_STATE -Architectures: x86, s390, arm, arm64 -Type: vcpu ioctl -Parameters: struct kvm_mp_state (out) -Returns: 0 on success; -1 on error +:Capability: KVM_CAP_MP_STATE +:Architectures: x86, s390, arm, arm64 +:Type: vcpu ioctl +:Parameters: struct kvm_mp_state (out) +:Returns: 0 on success; -1 on error + +:: -struct kvm_mp_state { + struct kvm_mp_state { __u32 mp_state; -}; + }; Returns the vcpu's current "multiprocessing state" (though also valid on uniprocessor guests). Possible values are: - - KVM_MP_STATE_RUNNABLE: the vcpu is currently running [x86,arm/arm64] - - KVM_MP_STATE_UNINITIALIZED: the vcpu is an application processor (AP) + ========================== =============================================== + KVM_MP_STATE_RUNNABLE the vcpu is currently running [x86,arm/arm64] + KVM_MP_STATE_UNINITIALIZED the vcpu is an application processor (AP) which has not yet received an INIT signal [x86] - - KVM_MP_STATE_INIT_RECEIVED: the vcpu has received an INIT signal, and is + KVM_MP_STATE_INIT_RECEIVED the vcpu has received an INIT signal, and is now ready for a SIPI [x86] - - KVM_MP_STATE_HALTED: the vcpu has executed a HLT instruction and + KVM_MP_STATE_HALTED the vcpu has executed a HLT instruction and is waiting for an interrupt [x86] - - KVM_MP_STATE_SIPI_RECEIVED: the vcpu has just received a SIPI (vector + KVM_MP_STATE_SIPI_RECEIVED the vcpu has just received a SIPI (vector accessible via KVM_GET_VCPU_EVENTS) [x86] - - KVM_MP_STATE_STOPPED: the vcpu is stopped [s390,arm/arm64] - - KVM_MP_STATE_CHECK_STOP: the vcpu is in a special error state [s390] - - KVM_MP_STATE_OPERATING: the vcpu is operating (running or halted) + KVM_MP_STATE_STOPPED the vcpu is stopped [s390,arm/arm64] + KVM_MP_STATE_CHECK_STOP the vcpu is in a special error state [s390] + KVM_MP_STATE_OPERATING the vcpu is operating (running or halted) [s390] - - KVM_MP_STATE_LOAD: the vcpu is in a special load/startup state + KVM_MP_STATE_LOAD the vcpu is in a special load/startup state [s390] + ========================== =============================================== On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an in-kernel irqchip, the multiprocessing state must be maintained by userspace on these architectures. For arm/arm64: +^^^^^^^^^^^^^^ The only states that are valid are KVM_MP_STATE_STOPPED and KVM_MP_STATE_RUNNABLE which reflect if the vcpu is paused or not. 4.39 KVM_SET_MP_STATE +--------------------- -Capability: KVM_CAP_MP_STATE -Architectures: x86, s390, arm, arm64 -Type: vcpu ioctl -Parameters: struct kvm_mp_state (in) -Returns: 0 on success; -1 on error +:Capability: KVM_CAP_MP_STATE +:Architectures: x86, s390, arm, arm64 +:Type: vcpu ioctl +:Parameters: struct kvm_mp_state (in) +:Returns: 0 on success; -1 on error Sets the vcpu's current "multiprocessing state"; see KVM_GET_MP_STATE for arguments. @@ -1294,17 +1421,19 @@ in-kernel irqchip, the multiprocessing state must be maintained by userspace on these architectures. For arm/arm64: +^^^^^^^^^^^^^^ The only states that are valid are KVM_MP_STATE_STOPPED and KVM_MP_STATE_RUNNABLE which reflect if the vcpu should be paused or not. 4.40 KVM_SET_IDENTITY_MAP_ADDR +------------------------------ -Capability: KVM_CAP_SET_IDENTITY_MAP_ADDR -Architectures: x86 -Type: vm ioctl -Parameters: unsigned long identity (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_SET_IDENTITY_MAP_ADDR +:Architectures: x86 +:Type: vm ioctl +:Parameters: unsigned long identity (in) +:Returns: 0 on success, -1 on error This ioctl defines the physical address of a one-page region in the guest physical address space. The region must be within the first 4GB of the @@ -1322,12 +1451,13 @@ documentation when it pops into existence). Fails if any VCPU has already been created. 4.41 KVM_SET_BOOT_CPU_ID +------------------------ -Capability: KVM_CAP_SET_BOOT_CPU_ID -Architectures: x86 -Type: vm ioctl -Parameters: unsigned long vcpu_id -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_SET_BOOT_CPU_ID +:Architectures: x86 +:Type: vm ioctl +:Parameters: unsigned long vcpu_id +:Returns: 0 on success, -1 on error Define which vcpu is the Bootstrap Processor (BSP). Values are the same as the vcpu id in KVM_CREATE_VCPU. If this ioctl is not called, the default @@ -1335,102 +1465,119 @@ is vcpu 0. 4.42 KVM_GET_XSAVE +------------------ -Capability: KVM_CAP_XSAVE -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_xsave (out) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_XSAVE +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_xsave (out) +:Returns: 0 on success, -1 on error + + +:: -struct kvm_xsave { + struct kvm_xsave { __u32 region[1024]; -}; + }; This ioctl would copy current vcpu's xsave struct to the userspace. 4.43 KVM_SET_XSAVE +------------------ -Capability: KVM_CAP_XSAVE -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_xsave (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_XSAVE +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_xsave (in) +:Returns: 0 on success, -1 on error + +:: -struct kvm_xsave { + + struct kvm_xsave { __u32 region[1024]; -}; + }; This ioctl would copy userspace's xsave struct to the kernel. 4.44 KVM_GET_XCRS +----------------- -Capability: KVM_CAP_XCRS -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_xcrs (out) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_XCRS +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_xcrs (out) +:Returns: 0 on success, -1 on error + +:: -struct kvm_xcr { + struct kvm_xcr { __u32 xcr; __u32 reserved; __u64 value; -}; + }; -struct kvm_xcrs { + struct kvm_xcrs { __u32 nr_xcrs; __u32 flags; struct kvm_xcr xcrs[KVM_MAX_XCRS]; __u64 padding[16]; -}; + }; This ioctl would copy current vcpu's xcrs to the userspace. 4.45 KVM_SET_XCRS +----------------- -Capability: KVM_CAP_XCRS -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_xcrs (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_XCRS +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_xcrs (in) +:Returns: 0 on success, -1 on error + +:: -struct kvm_xcr { + struct kvm_xcr { __u32 xcr; __u32 reserved; __u64 value; -}; + }; -struct kvm_xcrs { + struct kvm_xcrs { __u32 nr_xcrs; __u32 flags; struct kvm_xcr xcrs[KVM_MAX_XCRS]; __u64 padding[16]; -}; + }; This ioctl would set vcpu's xcr to the value userspace specified. 4.46 KVM_GET_SUPPORTED_CPUID +---------------------------- + +:Capability: KVM_CAP_EXT_CPUID +:Architectures: x86 +:Type: system ioctl +:Parameters: struct kvm_cpuid2 (in/out) +:Returns: 0 on success, -1 on error -Capability: KVM_CAP_EXT_CPUID -Architectures: x86 -Type: system ioctl -Parameters: struct kvm_cpuid2 (in/out) -Returns: 0 on success, -1 on error +:: -struct kvm_cpuid2 { + struct kvm_cpuid2 { __u32 nent; __u32 padding; struct kvm_cpuid_entry2 entries[0]; -}; + }; -#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0) -#define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1) -#define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2) + #define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0) + #define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1) + #define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2) -struct kvm_cpuid_entry2 { + struct kvm_cpuid_entry2 { __u32 function; __u32 index; __u32 flags; @@ -1439,7 +1586,7 @@ struct kvm_cpuid_entry2 { __u32 ecx; __u32 edx; __u32 padding[3]; -}; + }; This ioctl returns x86 cpuid features which are supported by both the hardware and kvm in its default configuration. Userspace can use the @@ -1467,10 +1614,16 @@ with unknown or unsupported features masked out. Some features (for example, x2apic), may not be present in the host cpu, but are exposed by kvm if it can emulate them efficiently. The fields in each entry are defined as follows: - function: the eax value used to obtain the entry - index: the ecx value used to obtain the entry (for entries that are + function: + the eax value used to obtain the entry + + index: + the ecx value used to obtain the entry (for entries that are affected by ecx) - flags: an OR of zero or more of the following: + + flags: + an OR of zero or more of the following: + KVM_CPUID_FLAG_SIGNIFCANT_INDEX: if the index field is valid KVM_CPUID_FLAG_STATEFUL_FUNC: @@ -1480,12 +1633,14 @@ emulate them efficiently. The fields in each entry are defined as follows: KVM_CPUID_FLAG_STATE_READ_NEXT: for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is the first entry to be read by a cpu - eax, ebx, ecx, edx: the values returned by the cpuid instruction for + + eax, ebx, ecx, edx: + the values returned by the cpuid instruction for this function/index combination The TSC deadline timer feature (CPUID leaf 1, ecx[24]) is always returned as false, since the feature depends on KVM_CREATE_IRQCHIP for local APIC -support. Instead it is reported via +support. Instead it is reported via:: ioctl(KVM_CHECK_EXTENSION, KVM_CAP_TSC_DEADLINE_TIMER) @@ -1494,18 +1649,21 @@ feature in userspace, then you can enable the feature for KVM_SET_CPUID2. 4.47 KVM_PPC_GET_PVINFO +----------------------- + +:Capability: KVM_CAP_PPC_GET_PVINFO +:Architectures: ppc +:Type: vm ioctl +:Parameters: struct kvm_ppc_pvinfo (out) +:Returns: 0 on success, !0 on error -Capability: KVM_CAP_PPC_GET_PVINFO -Architectures: ppc -Type: vm ioctl -Parameters: struct kvm_ppc_pvinfo (out) -Returns: 0 on success, !0 on error +:: -struct kvm_ppc_pvinfo { + struct kvm_ppc_pvinfo { __u32 flags; __u32 hcall[4]; __u8 pad[108]; -}; + }; This ioctl fetches PV specific information that need to be passed to the guest using the device tree or other means from vm context. @@ -1515,33 +1673,39 @@ The hcall array defines 4 instructions that make up a hypercall. If any additional field gets added to this structure later on, a bit for that additional piece of information will be set in the flags bitmap. -The flags bitmap is defined as: +The flags bitmap is defined as:: /* the host supports the ePAPR idle hcall #define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0) 4.52 KVM_SET_GSI_ROUTING +------------------------ -Capability: KVM_CAP_IRQ_ROUTING -Architectures: x86 s390 arm arm64 -Type: vm ioctl -Parameters: struct kvm_irq_routing (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_IRQ_ROUTING +:Architectures: x86 s390 arm arm64 +:Type: vm ioctl +:Parameters: struct kvm_irq_routing (in) +:Returns: 0 on success, -1 on error Sets the GSI routing table entries, overwriting any previously set entries. On arm/arm64, GSI routing has the following limitation: + - GSI routing does not apply to KVM_IRQ_LINE but only to KVM_IRQFD. -struct kvm_irq_routing { +:: + + struct kvm_irq_routing { __u32 nr; __u32 flags; struct kvm_irq_routing_entry entries[0]; -}; + }; No flags are specified so far, the corresponding field must be set to zero. -struct kvm_irq_routing_entry { +:: + + struct kvm_irq_routing_entry { __u32 gsi; __u32 type; __u32 flags; @@ -1553,15 +1717,16 @@ struct kvm_irq_routing_entry { struct kvm_irq_routing_hv_sint hv_sint; __u32 pad[8]; } u; -}; + }; -/* gsi routing entry types */ -#define KVM_IRQ_ROUTING_IRQCHIP 1 -#define KVM_IRQ_ROUTING_MSI 2 -#define KVM_IRQ_ROUTING_S390_ADAPTER 3 -#define KVM_IRQ_ROUTING_HV_SINT 4 + /* gsi routing entry types */ + #define KVM_IRQ_ROUTING_IRQCHIP 1 + #define KVM_IRQ_ROUTING_MSI 2 + #define KVM_IRQ_ROUTING_S390_ADAPTER 3 + #define KVM_IRQ_ROUTING_HV_SINT 4 flags: + - KVM_MSI_VALID_DEVID: used along with KVM_IRQ_ROUTING_MSI routing entry type, specifies that the devid field contains a valid value. The per-VM KVM_CAP_MSI_DEVID capability advertises the requirement to provide @@ -1569,12 +1734,14 @@ flags: never set the KVM_MSI_VALID_DEVID flag as the ioctl might fail. - zero otherwise -struct kvm_irq_routing_irqchip { +:: + + struct kvm_irq_routing_irqchip { __u32 irqchip; __u32 pin; -}; + }; -struct kvm_irq_routing_msi { + struct kvm_irq_routing_msi { __u32 address_lo; __u32 address_hi; __u32 data; @@ -1582,7 +1749,7 @@ struct kvm_irq_routing_msi { __u32 pad; __u32 devid; }; -}; + }; If KVM_MSI_VALID_DEVID is set, devid contains a unique device identifier for the device that wrote the MSI message. For PCI, this is usually a @@ -1593,39 +1760,43 @@ feature of KVM_CAP_X2APIC_API capability is enabled. If it is enabled, address_hi bits 31-8 provide bits 31-8 of the destination id. Bits 7-0 of address_hi must be zero. -struct kvm_irq_routing_s390_adapter { +:: + + struct kvm_irq_routing_s390_adapter { __u64 ind_addr; __u64 summary_addr; __u64 ind_offset; __u32 summary_offset; __u32 adapter_id; -}; + }; -struct kvm_irq_routing_hv_sint { + struct kvm_irq_routing_hv_sint { __u32 vcpu; __u32 sint; -}; + }; 4.55 KVM_SET_TSC_KHZ +-------------------- -Capability: KVM_CAP_TSC_CONTROL -Architectures: x86 -Type: vcpu ioctl -Parameters: virtual tsc_khz -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_TSC_CONTROL +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: virtual tsc_khz +:Returns: 0 on success, -1 on error Specifies the tsc frequency for the virtual machine. The unit of the frequency is KHz. 4.56 KVM_GET_TSC_KHZ +-------------------- -Capability: KVM_CAP_GET_TSC_KHZ -Architectures: x86 -Type: vcpu ioctl -Parameters: none -Returns: virtual tsc-khz on success, negative value on error +:Capability: KVM_CAP_GET_TSC_KHZ +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: none +:Returns: virtual tsc-khz on success, negative value on error Returns the tsc frequency of the guest. The unit of the return value is KHz. If the host has unstable tsc this ioctl returns -EIO instead as an @@ -1633,17 +1804,20 @@ error. 4.57 KVM_GET_LAPIC +------------------ -Capability: KVM_CAP_IRQCHIP -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_lapic_state (out) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_IRQCHIP +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_lapic_state (out) +:Returns: 0 on success, -1 on error -#define KVM_APIC_REG_SIZE 0x400 -struct kvm_lapic_state { +:: + + #define KVM_APIC_REG_SIZE 0x400 + struct kvm_lapic_state { char regs[KVM_APIC_REG_SIZE]; -}; + }; Reads the Local APIC registers and copies them into the input argument. The data format and layout are the same as documented in the architecture manual. @@ -1661,17 +1835,20 @@ always uses xAPIC format. 4.58 KVM_SET_LAPIC +------------------ -Capability: KVM_CAP_IRQCHIP -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_lapic_state (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_IRQCHIP +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_lapic_state (in) +:Returns: 0 on success, -1 on error -#define KVM_APIC_REG_SIZE 0x400 -struct kvm_lapic_state { +:: + + #define KVM_APIC_REG_SIZE 0x400 + struct kvm_lapic_state { char regs[KVM_APIC_REG_SIZE]; -}; + }; Copies the input argument into the Local APIC registers. The data format and layout are the same as documented in the architecture manual. @@ -1682,35 +1859,38 @@ See the note in KVM_GET_LAPIC. 4.59 KVM_IOEVENTFD +------------------ -Capability: KVM_CAP_IOEVENTFD -Architectures: all -Type: vm ioctl -Parameters: struct kvm_ioeventfd (in) -Returns: 0 on success, !0 on error +:Capability: KVM_CAP_IOEVENTFD +:Architectures: all +:Type: vm ioctl +:Parameters: struct kvm_ioeventfd (in) +:Returns: 0 on success, !0 on error This ioctl attaches or detaches an ioeventfd to a legal pio/mmio address within the guest. A guest write in the registered address will signal the provided event instead of triggering an exit. -struct kvm_ioeventfd { +:: + + struct kvm_ioeventfd { __u64 datamatch; __u64 addr; /* legal pio/mmio address */ __u32 len; /* 0, 1, 2, 4, or 8 bytes */ __s32 fd; __u32 flags; __u8 pad[36]; -}; + }; For the special case of virtio-ccw devices on s390, the ioevent is matched to a subchannel/virtqueue tuple instead. -The following flags are defined: +The following flags are defined:: -#define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch) -#define KVM_IOEVENTFD_FLAG_PIO (1 << kvm_ioeventfd_flag_nr_pio) -#define KVM_IOEVENTFD_FLAG_DEASSIGN (1 << kvm_ioeventfd_flag_nr_deassign) -#define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \ + #define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch) + #define KVM_IOEVENTFD_FLAG_PIO (1 << kvm_ioeventfd_flag_nr_pio) + #define KVM_IOEVENTFD_FLAG_DEASSIGN (1 << kvm_ioeventfd_flag_nr_deassign) + #define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \ (1 << kvm_ioeventfd_flag_nr_virtio_ccw_notify) If datamatch flag is set, the event will be signaled only if the written value @@ -1725,17 +1905,20 @@ The speedup may only apply to specific architectures, but the ioeventfd will work anyway. 4.60 KVM_DIRTY_TLB +------------------ -Capability: KVM_CAP_SW_TLB -Architectures: ppc -Type: vcpu ioctl -Parameters: struct kvm_dirty_tlb (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_SW_TLB +:Architectures: ppc +:Type: vcpu ioctl +:Parameters: struct kvm_dirty_tlb (in) +:Returns: 0 on success, -1 on error + +:: -struct kvm_dirty_tlb { + struct kvm_dirty_tlb { __u64 bitmap; __u32 num_dirty; -}; + }; This must be called whenever userspace has changed an entry in the shared TLB, prior to calling KVM_RUN on the associated vcpu. @@ -1758,23 +1941,26 @@ be set to the number of set bits in the bitmap. 4.62 KVM_CREATE_SPAPR_TCE +------------------------- -Capability: KVM_CAP_SPAPR_TCE -Architectures: powerpc -Type: vm ioctl -Parameters: struct kvm_create_spapr_tce (in) -Returns: file descriptor for manipulating the created TCE table +:Capability: KVM_CAP_SPAPR_TCE +:Architectures: powerpc +:Type: vm ioctl +:Parameters: struct kvm_create_spapr_tce (in) +:Returns: file descriptor for manipulating the created TCE table This creates a virtual TCE (translation control entry) table, which is an IOMMU for PAPR-style virtual I/O. It is used to translate logical addresses used in virtual I/O into guest physical addresses, and provides a scatter/gather capability for PAPR virtual I/O. -/* for KVM_CAP_SPAPR_TCE */ -struct kvm_create_spapr_tce { +:: + + /* for KVM_CAP_SPAPR_TCE */ + struct kvm_create_spapr_tce { __u64 liobn; __u32 window_size; -}; + }; The liobn field gives the logical IO bus number for which to create a TCE table. The window_size field specifies the size of the DMA window @@ -1794,12 +1980,13 @@ circumstances. 4.63 KVM_ALLOCATE_RMA +--------------------- -Capability: KVM_CAP_PPC_RMA -Architectures: powerpc -Type: vm ioctl -Parameters: struct kvm_allocate_rma (out) -Returns: file descriptor for mapping the allocated RMA +:Capability: KVM_CAP_PPC_RMA +:Architectures: powerpc +:Type: vm ioctl +:Parameters: struct kvm_allocate_rma (out) +:Returns: file descriptor for mapping the allocated RMA This allocates a Real Mode Area (RMA) from the pool allocated at boot time by the kernel. An RMA is a physically-contiguous, aligned region @@ -1808,10 +1995,12 @@ will be accessed by real-mode (MMU off) accesses in a KVM guest. POWER processors support a set of sizes for the RMA that usually includes 64MB, 128MB, 256MB and some larger powers of two. -/* for KVM_ALLOCATE_RMA */ -struct kvm_allocate_rma { +:: + + /* for KVM_ALLOCATE_RMA */ + struct kvm_allocate_rma { __u64 rma_size; -}; + }; The return value is a file descriptor which can be passed to mmap(2) to map the allocated RMA into userspace. The mapped area can then be @@ -1827,12 +2016,13 @@ because it supports the Virtual RMA (VRMA) facility. 4.64 KVM_NMI +------------ -Capability: KVM_CAP_USER_NMI -Architectures: x86 -Type: vcpu ioctl -Parameters: none -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_USER_NMI +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: none +:Returns: 0 on success, -1 on error Queues an NMI on the thread's vcpu. Note this is well defined only when KVM_CREATE_IRQCHIP has not been called, since this is an interface @@ -1853,14 +2043,16 @@ debugging. 4.65 KVM_S390_UCAS_MAP +---------------------- -Capability: KVM_CAP_S390_UCONTROL -Architectures: s390 -Type: vcpu ioctl -Parameters: struct kvm_s390_ucas_mapping (in) -Returns: 0 in case of success +:Capability: KVM_CAP_S390_UCONTROL +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: struct kvm_s390_ucas_mapping (in) +:Returns: 0 in case of success + +The parameter is defined like this:: -The parameter is defined like this: struct kvm_s390_ucas_mapping { __u64 user_addr; __u64 vcpu_addr; @@ -1873,14 +2065,16 @@ be aligned by 1 megabyte. 4.66 KVM_S390_UCAS_UNMAP +------------------------ -Capability: KVM_CAP_S390_UCONTROL -Architectures: s390 -Type: vcpu ioctl -Parameters: struct kvm_s390_ucas_mapping (in) -Returns: 0 in case of success +:Capability: KVM_CAP_S390_UCONTROL +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: struct kvm_s390_ucas_mapping (in) +:Returns: 0 in case of success + +The parameter is defined like this:: -The parameter is defined like this: struct kvm_s390_ucas_mapping { __u64 user_addr; __u64 vcpu_addr; @@ -1893,12 +2087,13 @@ All parameters need to be aligned by 1 megabyte. 4.67 KVM_S390_VCPU_FAULT +------------------------ -Capability: KVM_CAP_S390_UCONTROL -Architectures: s390 -Type: vcpu ioctl -Parameters: vcpu absolute address (in) -Returns: 0 in case of success +:Capability: KVM_CAP_S390_UCONTROL +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: vcpu absolute address (in) +:Returns: 0 in case of success This call creates a page table entry on the virtual cpu's address space (for user controlled virtual machines) or the virtual machine's address @@ -1910,23 +2105,31 @@ prior to calling the KVM_RUN ioctl. 4.68 KVM_SET_ONE_REG +-------------------- + +:Capability: KVM_CAP_ONE_REG +:Architectures: all +:Type: vcpu ioctl +:Parameters: struct kvm_one_reg (in) +:Returns: 0 on success, negative value on failure -Capability: KVM_CAP_ONE_REG -Architectures: all -Type: vcpu ioctl -Parameters: struct kvm_one_reg (in) -Returns: 0 on success, negative value on failure Errors: - ENOENT: no such register - EINVAL: invalid register ID, or no such register - EPERM: (arm64) register access not allowed before vcpu finalization + + ====== ============================================================ + ENOENT no such register + EINVAL invalid register ID, or no such register + EPERM (arm64) register access not allowed before vcpu finalization + ====== ============================================================ + (These error codes are indicative only: do not rely on a specific error code being returned in a specific situation.) -struct kvm_one_reg { +:: + + struct kvm_one_reg { __u64 id; __u64 addr; -}; + }; Using this ioctl, a single vcpu register can be set to a specific value defined by user space with the passed in struct kvm_one_reg, where id @@ -1936,217 +2139,226 @@ and architecture specific registers. Each have their own range of operation and their own constants and width. To keep track of the implemented registers, find a list below: - Arch | Register | Width (bits) - | | - PPC | KVM_REG_PPC_HIOR | 64 - PPC | KVM_REG_PPC_IAC1 | 64 - PPC | KVM_REG_PPC_IAC2 | 64 - PPC | KVM_REG_PPC_IAC3 | 64 - PPC | KVM_REG_PPC_IAC4 | 64 - PPC | KVM_REG_PPC_DAC1 | 64 - PPC | KVM_REG_PPC_DAC2 | 64 - PPC | KVM_REG_PPC_DABR | 64 - PPC | KVM_REG_PPC_DSCR | 64 - PPC | KVM_REG_PPC_PURR | 64 - PPC | KVM_REG_PPC_SPURR | 64 - PPC | KVM_REG_PPC_DAR | 64 - PPC | KVM_REG_PPC_DSISR | 32 - PPC | KVM_REG_PPC_AMR | 64 - PPC | KVM_REG_PPC_UAMOR | 64 - PPC | KVM_REG_PPC_MMCR0 | 64 - PPC | KVM_REG_PPC_MMCR1 | 64 - PPC | KVM_REG_PPC_MMCRA | 64 - PPC | KVM_REG_PPC_MMCR2 | 64 - PPC | KVM_REG_PPC_MMCRS | 64 - PPC | KVM_REG_PPC_SIAR | 64 - PPC | KVM_REG_PPC_SDAR | 64 - PPC | KVM_REG_PPC_SIER | 64 - PPC | KVM_REG_PPC_PMC1 | 32 - PPC | KVM_REG_PPC_PMC2 | 32 - PPC | KVM_REG_PPC_PMC3 | 32 - PPC | KVM_REG_PPC_PMC4 | 32 - PPC | KVM_REG_PPC_PMC5 | 32 - PPC | KVM_REG_PPC_PMC6 | 32 - PPC | KVM_REG_PPC_PMC7 | 32 - PPC | KVM_REG_PPC_PMC8 | 32 - PPC | KVM_REG_PPC_FPR0 | 64 - ... - PPC | KVM_REG_PPC_FPR31 | 64 - PPC | KVM_REG_PPC_VR0 | 128 - ... - PPC | KVM_REG_PPC_VR31 | 128 - PPC | KVM_REG_PPC_VSR0 | 128 - ... - PPC | KVM_REG_PPC_VSR31 | 128 - PPC | KVM_REG_PPC_FPSCR | 64 - PPC | KVM_REG_PPC_VSCR | 32 - PPC | KVM_REG_PPC_VPA_ADDR | 64 - PPC | KVM_REG_PPC_VPA_SLB | 128 - PPC | KVM_REG_PPC_VPA_DTL | 128 - PPC | KVM_REG_PPC_EPCR | 32 - PPC | KVM_REG_PPC_EPR | 32 - PPC | KVM_REG_PPC_TCR | 32 - PPC | KVM_REG_PPC_TSR | 32 - PPC | KVM_REG_PPC_OR_TSR | 32 - PPC | KVM_REG_PPC_CLEAR_TSR | 32 - PPC | KVM_REG_PPC_MAS0 | 32 - PPC | KVM_REG_PPC_MAS1 | 32 - PPC | KVM_REG_PPC_MAS2 | 64 - PPC | KVM_REG_PPC_MAS7_3 | 64 - PPC | KVM_REG_PPC_MAS4 | 32 - PPC | KVM_REG_PPC_MAS6 | 32 - PPC | KVM_REG_PPC_MMUCFG | 32 - PPC | KVM_REG_PPC_TLB0CFG | 32 - PPC | KVM_REG_PPC_TLB1CFG | 32 - PPC | KVM_REG_PPC_TLB2CFG | 32 - PPC | KVM_REG_PPC_TLB3CFG | 32 - PPC | KVM_REG_PPC_TLB0PS | 32 - PPC | KVM_REG_PPC_TLB1PS | 32 - PPC | KVM_REG_PPC_TLB2PS | 32 - PPC | KVM_REG_PPC_TLB3PS | 32 - PPC | KVM_REG_PPC_EPTCFG | 32 - PPC | KVM_REG_PPC_ICP_STATE | 64 - PPC | KVM_REG_PPC_VP_STATE | 128 - PPC | KVM_REG_PPC_TB_OFFSET | 64 - PPC | KVM_REG_PPC_SPMC1 | 32 - PPC | KVM_REG_PPC_SPMC2 | 32 - PPC | KVM_REG_PPC_IAMR | 64 - PPC | KVM_REG_PPC_TFHAR | 64 - PPC | KVM_REG_PPC_TFIAR | 64 - PPC | KVM_REG_PPC_TEXASR | 64 - PPC | KVM_REG_PPC_FSCR | 64 - PPC | KVM_REG_PPC_PSPB | 32 - PPC | KVM_REG_PPC_EBBHR | 64 - PPC | KVM_REG_PPC_EBBRR | 64 - PPC | KVM_REG_PPC_BESCR | 64 - PPC | KVM_REG_PPC_TAR | 64 - PPC | KVM_REG_PPC_DPDES | 64 - PPC | KVM_REG_PPC_DAWR | 64 - PPC | KVM_REG_PPC_DAWRX | 64 - PPC | KVM_REG_PPC_CIABR | 64 - PPC | KVM_REG_PPC_IC | 64 - PPC | KVM_REG_PPC_VTB | 64 - PPC | KVM_REG_PPC_CSIGR | 64 - PPC | KVM_REG_PPC_TACR | 64 - PPC | KVM_REG_PPC_TCSCR | 64 - PPC | KVM_REG_PPC_PID | 64 - PPC | KVM_REG_PPC_ACOP | 64 - PPC | KVM_REG_PPC_VRSAVE | 32 - PPC | KVM_REG_PPC_LPCR | 32 - PPC | KVM_REG_PPC_LPCR_64 | 64 - PPC | KVM_REG_PPC_PPR | 64 - PPC | KVM_REG_PPC_ARCH_COMPAT | 32 - PPC | KVM_REG_PPC_DABRX | 32 - PPC | KVM_REG_PPC_WORT | 64 - PPC | KVM_REG_PPC_SPRG9 | 64 - PPC | KVM_REG_PPC_DBSR | 32 - PPC | KVM_REG_PPC_TIDR | 64 - PPC | KVM_REG_PPC_PSSCR | 64 - PPC | KVM_REG_PPC_DEC_EXPIRY | 64 - PPC | KVM_REG_PPC_PTCR | 64 - PPC | KVM_REG_PPC_TM_GPR0 | 64 - ... - PPC | KVM_REG_PPC_TM_GPR31 | 64 - PPC | KVM_REG_PPC_TM_VSR0 | 128 - ... - PPC | KVM_REG_PPC_TM_VSR63 | 128 - PPC | KVM_REG_PPC_TM_CR | 64 - PPC | KVM_REG_PPC_TM_LR | 64 - PPC | KVM_REG_PPC_TM_CTR | 64 - PPC | KVM_REG_PPC_TM_FPSCR | 64 - PPC | KVM_REG_PPC_TM_AMR | 64 - PPC | KVM_REG_PPC_TM_PPR | 64 - PPC | KVM_REG_PPC_TM_VRSAVE | 64 - PPC | KVM_REG_PPC_TM_VSCR | 32 - PPC | KVM_REG_PPC_TM_DSCR | 64 - PPC | KVM_REG_PPC_TM_TAR | 64 - PPC | KVM_REG_PPC_TM_XER | 64 - | | - MIPS | KVM_REG_MIPS_R0 | 64 - ... - MIPS | KVM_REG_MIPS_R31 | 64 - MIPS | KVM_REG_MIPS_HI | 64 - MIPS | KVM_REG_MIPS_LO | 64 - MIPS | KVM_REG_MIPS_PC | 64 - MIPS | KVM_REG_MIPS_CP0_INDEX | 32 - MIPS | KVM_REG_MIPS_CP0_ENTRYLO0 | 64 - MIPS | KVM_REG_MIPS_CP0_ENTRYLO1 | 64 - MIPS | KVM_REG_MIPS_CP0_CONTEXT | 64 - MIPS | KVM_REG_MIPS_CP0_CONTEXTCONFIG| 32 - MIPS | KVM_REG_MIPS_CP0_USERLOCAL | 64 - MIPS | KVM_REG_MIPS_CP0_XCONTEXTCONFIG| 64 - MIPS | KVM_REG_MIPS_CP0_PAGEMASK | 32 - MIPS | KVM_REG_MIPS_CP0_PAGEGRAIN | 32 - MIPS | KVM_REG_MIPS_CP0_SEGCTL0 | 64 - MIPS | KVM_REG_MIPS_CP0_SEGCTL1 | 64 - MIPS | KVM_REG_MIPS_CP0_SEGCTL2 | 64 - MIPS | KVM_REG_MIPS_CP0_PWBASE | 64 - MIPS | KVM_REG_MIPS_CP0_PWFIELD | 64 - MIPS | KVM_REG_MIPS_CP0_PWSIZE | 64 - MIPS | KVM_REG_MIPS_CP0_WIRED | 32 - MIPS | KVM_REG_MIPS_CP0_PWCTL | 32 - MIPS | KVM_REG_MIPS_CP0_HWRENA | 32 - MIPS | KVM_REG_MIPS_CP0_BADVADDR | 64 - MIPS | KVM_REG_MIPS_CP0_BADINSTR | 32 - MIPS | KVM_REG_MIPS_CP0_BADINSTRP | 32 - MIPS | KVM_REG_MIPS_CP0_COUNT | 32 - MIPS | KVM_REG_MIPS_CP0_ENTRYHI | 64 - MIPS | KVM_REG_MIPS_CP0_COMPARE | 32 - MIPS | KVM_REG_MIPS_CP0_STATUS | 32 - MIPS | KVM_REG_MIPS_CP0_INTCTL | 32 - MIPS | KVM_REG_MIPS_CP0_CAUSE | 32 - MIPS | KVM_REG_MIPS_CP0_EPC | 64 - MIPS | KVM_REG_MIPS_CP0_PRID | 32 - MIPS | KVM_REG_MIPS_CP0_EBASE | 64 - MIPS | KVM_REG_MIPS_CP0_CONFIG | 32 - MIPS | KVM_REG_MIPS_CP0_CONFIG1 | 32 - MIPS | KVM_REG_MIPS_CP0_CONFIG2 | 32 - MIPS | KVM_REG_MIPS_CP0_CONFIG3 | 32 - MIPS | KVM_REG_MIPS_CP0_CONFIG4 | 32 - MIPS | KVM_REG_MIPS_CP0_CONFIG5 | 32 - MIPS | KVM_REG_MIPS_CP0_CONFIG7 | 32 - MIPS | KVM_REG_MIPS_CP0_XCONTEXT | 64 - MIPS | KVM_REG_MIPS_CP0_ERROREPC | 64 - MIPS | KVM_REG_MIPS_CP0_KSCRATCH1 | 64 - MIPS | KVM_REG_MIPS_CP0_KSCRATCH2 | 64 - MIPS | KVM_REG_MIPS_CP0_KSCRATCH3 | 64 - MIPS | KVM_REG_MIPS_CP0_KSCRATCH4 | 64 - MIPS | KVM_REG_MIPS_CP0_KSCRATCH5 | 64 - MIPS | KVM_REG_MIPS_CP0_KSCRATCH6 | 64 - MIPS | KVM_REG_MIPS_CP0_MAAR(0..63) | 64 - MIPS | KVM_REG_MIPS_COUNT_CTL | 64 - MIPS | KVM_REG_MIPS_COUNT_RESUME | 64 - MIPS | KVM_REG_MIPS_COUNT_HZ | 64 - MIPS | KVM_REG_MIPS_FPR_32(0..31) | 32 - MIPS | KVM_REG_MIPS_FPR_64(0..31) | 64 - MIPS | KVM_REG_MIPS_VEC_128(0..31) | 128 - MIPS | KVM_REG_MIPS_FCR_IR | 32 - MIPS | KVM_REG_MIPS_FCR_CSR | 32 - MIPS | KVM_REG_MIPS_MSA_IR | 32 - MIPS | KVM_REG_MIPS_MSA_CSR | 32 + ======= =============================== ============ + Arch Register Width (bits) + ======= =============================== ============ + PPC KVM_REG_PPC_HIOR 64 + PPC KVM_REG_PPC_IAC1 64 + PPC KVM_REG_PPC_IAC2 64 + PPC KVM_REG_PPC_IAC3 64 + PPC KVM_REG_PPC_IAC4 64 + PPC KVM_REG_PPC_DAC1 64 + PPC KVM_REG_PPC_DAC2 64 + PPC KVM_REG_PPC_DABR 64 + PPC KVM_REG_PPC_DSCR 64 + PPC KVM_REG_PPC_PURR 64 + PPC KVM_REG_PPC_SPURR 64 + PPC KVM_REG_PPC_DAR 64 + PPC KVM_REG_PPC_DSISR 32 + PPC KVM_REG_PPC_AMR 64 + PPC KVM_REG_PPC_UAMOR 64 + PPC KVM_REG_PPC_MMCR0 64 + PPC KVM_REG_PPC_MMCR1 64 + PPC KVM_REG_PPC_MMCRA 64 + PPC KVM_REG_PPC_MMCR2 64 + PPC KVM_REG_PPC_MMCRS 64 + PPC KVM_REG_PPC_SIAR 64 + PPC KVM_REG_PPC_SDAR 64 + PPC KVM_REG_PPC_SIER 64 + PPC KVM_REG_PPC_PMC1 32 + PPC KVM_REG_PPC_PMC2 32 + PPC KVM_REG_PPC_PMC3 32 + PPC KVM_REG_PPC_PMC4 32 + PPC KVM_REG_PPC_PMC5 32 + PPC KVM_REG_PPC_PMC6 32 + PPC KVM_REG_PPC_PMC7 32 + PPC KVM_REG_PPC_PMC8 32 + PPC KVM_REG_PPC_FPR0 64 + ... + PPC KVM_REG_PPC_FPR31 64 + PPC KVM_REG_PPC_VR0 128 + ... + PPC KVM_REG_PPC_VR31 128 + PPC KVM_REG_PPC_VSR0 128 + ... + PPC KVM_REG_PPC_VSR31 128 + PPC KVM_REG_PPC_FPSCR 64 + PPC KVM_REG_PPC_VSCR 32 + PPC KVM_REG_PPC_VPA_ADDR 64 + PPC KVM_REG_PPC_VPA_SLB 128 + PPC KVM_REG_PPC_VPA_DTL 128 + PPC KVM_REG_PPC_EPCR 32 + PPC KVM_REG_PPC_EPR 32 + PPC KVM_REG_PPC_TCR 32 + PPC KVM_REG_PPC_TSR 32 + PPC KVM_REG_PPC_OR_TSR 32 + PPC KVM_REG_PPC_CLEAR_TSR 32 + PPC KVM_REG_PPC_MAS0 32 + PPC KVM_REG_PPC_MAS1 32 + PPC KVM_REG_PPC_MAS2 64 + PPC KVM_REG_PPC_MAS7_3 64 + PPC KVM_REG_PPC_MAS4 32 + PPC KVM_REG_PPC_MAS6 32 + PPC KVM_REG_PPC_MMUCFG 32 + PPC KVM_REG_PPC_TLB0CFG 32 + PPC KVM_REG_PPC_TLB1CFG 32 + PPC KVM_REG_PPC_TLB2CFG 32 + PPC KVM_REG_PPC_TLB3CFG 32 + PPC KVM_REG_PPC_TLB0PS 32 + PPC KVM_REG_PPC_TLB1PS 32 + PPC KVM_REG_PPC_TLB2PS 32 + PPC KVM_REG_PPC_TLB3PS 32 + PPC KVM_REG_PPC_EPTCFG 32 + PPC KVM_REG_PPC_ICP_STATE 64 + PPC KVM_REG_PPC_VP_STATE 128 + PPC KVM_REG_PPC_TB_OFFSET 64 + PPC KVM_REG_PPC_SPMC1 32 + PPC KVM_REG_PPC_SPMC2 32 + PPC KVM_REG_PPC_IAMR 64 + PPC KVM_REG_PPC_TFHAR 64 + PPC KVM_REG_PPC_TFIAR 64 + PPC KVM_REG_PPC_TEXASR 64 + PPC KVM_REG_PPC_FSCR 64 + PPC KVM_REG_PPC_PSPB 32 + PPC KVM_REG_PPC_EBBHR 64 + PPC KVM_REG_PPC_EBBRR 64 + PPC KVM_REG_PPC_BESCR 64 + PPC KVM_REG_PPC_TAR 64 + PPC KVM_REG_PPC_DPDES 64 + PPC KVM_REG_PPC_DAWR 64 + PPC KVM_REG_PPC_DAWRX 64 + PPC KVM_REG_PPC_CIABR 64 + PPC KVM_REG_PPC_IC 64 + PPC KVM_REG_PPC_VTB 64 + PPC KVM_REG_PPC_CSIGR 64 + PPC KVM_REG_PPC_TACR 64 + PPC KVM_REG_PPC_TCSCR 64 + PPC KVM_REG_PPC_PID 64 + PPC KVM_REG_PPC_ACOP 64 + PPC KVM_REG_PPC_VRSAVE 32 + PPC KVM_REG_PPC_LPCR 32 + PPC KVM_REG_PPC_LPCR_64 64 + PPC KVM_REG_PPC_PPR 64 + PPC KVM_REG_PPC_ARCH_COMPAT 32 + PPC KVM_REG_PPC_DABRX 32 + PPC KVM_REG_PPC_WORT 64 + PPC KVM_REG_PPC_SPRG9 64 + PPC KVM_REG_PPC_DBSR 32 + PPC KVM_REG_PPC_TIDR 64 + PPC KVM_REG_PPC_PSSCR 64 + PPC KVM_REG_PPC_DEC_EXPIRY 64 + PPC KVM_REG_PPC_PTCR 64 + PPC KVM_REG_PPC_TM_GPR0 64 + ... + PPC KVM_REG_PPC_TM_GPR31 64 + PPC KVM_REG_PPC_TM_VSR0 128 + ... + PPC KVM_REG_PPC_TM_VSR63 128 + PPC KVM_REG_PPC_TM_CR 64 + PPC KVM_REG_PPC_TM_LR 64 + PPC KVM_REG_PPC_TM_CTR 64 + PPC KVM_REG_PPC_TM_FPSCR 64 + PPC KVM_REG_PPC_TM_AMR 64 + PPC KVM_REG_PPC_TM_PPR 64 + PPC KVM_REG_PPC_TM_VRSAVE 64 + PPC KVM_REG_PPC_TM_VSCR 32 + PPC KVM_REG_PPC_TM_DSCR 64 + PPC KVM_REG_PPC_TM_TAR 64 + PPC KVM_REG_PPC_TM_XER 64 + + MIPS KVM_REG_MIPS_R0 64 + ... + MIPS KVM_REG_MIPS_R31 64 + MIPS KVM_REG_MIPS_HI 64 + MIPS KVM_REG_MIPS_LO 64 + MIPS KVM_REG_MIPS_PC 64 + MIPS KVM_REG_MIPS_CP0_INDEX 32 + MIPS KVM_REG_MIPS_CP0_ENTRYLO0 64 + MIPS KVM_REG_MIPS_CP0_ENTRYLO1 64 + MIPS KVM_REG_MIPS_CP0_CONTEXT 64 + MIPS KVM_REG_MIPS_CP0_CONTEXTCONFIG 32 + MIPS KVM_REG_MIPS_CP0_USERLOCAL 64 + MIPS KVM_REG_MIPS_CP0_XCONTEXTCONFIG 64 + MIPS KVM_REG_MIPS_CP0_PAGEMASK 32 + MIPS KVM_REG_MIPS_CP0_PAGEGRAIN 32 + MIPS KVM_REG_MIPS_CP0_SEGCTL0 64 + MIPS KVM_REG_MIPS_CP0_SEGCTL1 64 + MIPS KVM_REG_MIPS_CP0_SEGCTL2 64 + MIPS KVM_REG_MIPS_CP0_PWBASE 64 + MIPS KVM_REG_MIPS_CP0_PWFIELD 64 + MIPS KVM_REG_MIPS_CP0_PWSIZE 64 + MIPS KVM_REG_MIPS_CP0_WIRED 32 + MIPS KVM_REG_MIPS_CP0_PWCTL 32 + MIPS KVM_REG_MIPS_CP0_HWRENA 32 + MIPS KVM_REG_MIPS_CP0_BADVADDR 64 + MIPS KVM_REG_MIPS_CP0_BADINSTR 32 + MIPS KVM_REG_MIPS_CP0_BADINSTRP 32 + MIPS KVM_REG_MIPS_CP0_COUNT 32 + MIPS KVM_REG_MIPS_CP0_ENTRYHI 64 + MIPS KVM_REG_MIPS_CP0_COMPARE 32 + MIPS KVM_REG_MIPS_CP0_STATUS 32 + MIPS KVM_REG_MIPS_CP0_INTCTL 32 + MIPS KVM_REG_MIPS_CP0_CAUSE 32 + MIPS KVM_REG_MIPS_CP0_EPC 64 + MIPS KVM_REG_MIPS_CP0_PRID 32 + MIPS KVM_REG_MIPS_CP0_EBASE 64 + MIPS KVM_REG_MIPS_CP0_CONFIG 32 + MIPS KVM_REG_MIPS_CP0_CONFIG1 32 + MIPS KVM_REG_MIPS_CP0_CONFIG2 32 + MIPS KVM_REG_MIPS_CP0_CONFIG3 32 + MIPS KVM_REG_MIPS_CP0_CONFIG4 32 + MIPS KVM_REG_MIPS_CP0_CONFIG5 32 + MIPS KVM_REG_MIPS_CP0_CONFIG7 32 + MIPS KVM_REG_MIPS_CP0_XCONTEXT 64 + MIPS KVM_REG_MIPS_CP0_ERROREPC 64 + MIPS KVM_REG_MIPS_CP0_KSCRATCH1 64 + MIPS KVM_REG_MIPS_CP0_KSCRATCH2 64 + MIPS KVM_REG_MIPS_CP0_KSCRATCH3 64 + MIPS KVM_REG_MIPS_CP0_KSCRATCH4 64 + MIPS KVM_REG_MIPS_CP0_KSCRATCH5 64 + MIPS KVM_REG_MIPS_CP0_KSCRATCH6 64 + MIPS KVM_REG_MIPS_CP0_MAAR(0..63) 64 + MIPS KVM_REG_MIPS_COUNT_CTL 64 + MIPS KVM_REG_MIPS_COUNT_RESUME 64 + MIPS KVM_REG_MIPS_COUNT_HZ 64 + MIPS KVM_REG_MIPS_FPR_32(0..31) 32 + MIPS KVM_REG_MIPS_FPR_64(0..31) 64 + MIPS KVM_REG_MIPS_VEC_128(0..31) 128 + MIPS KVM_REG_MIPS_FCR_IR 32 + MIPS KVM_REG_MIPS_FCR_CSR 32 + MIPS KVM_REG_MIPS_MSA_IR 32 + MIPS KVM_REG_MIPS_MSA_CSR 32 + ======= =============================== ============ ARM registers are mapped using the lower 32 bits. The upper 16 of that is the register group type, or coprocessor number: -ARM core registers have the following id bit patterns: +ARM core registers have the following id bit patterns:: + 0x4020 0000 0010 <index into the kvm_regs struct:16> -ARM 32-bit CP15 registers have the following id bit patterns: +ARM 32-bit CP15 registers have the following id bit patterns:: + 0x4020 0000 000F <zero:1> <crn:4> <crm:4> <opc1:4> <opc2:3> -ARM 64-bit CP15 registers have the following id bit patterns: +ARM 64-bit CP15 registers have the following id bit patterns:: + 0x4030 0000 000F <zero:1> <zero:4> <crm:4> <opc1:4> <zero:3> -ARM CCSIDR registers are demultiplexed by CSSELR value: +ARM CCSIDR registers are demultiplexed by CSSELR value:: + 0x4020 0000 0011 00 <csselr:8> -ARM 32-bit VFP control registers have the following id bit patterns: +ARM 32-bit VFP control registers have the following id bit patterns:: + 0x4020 0000 0012 1 <regno:12> -ARM 64-bit FP registers have the following id bit patterns: +ARM 64-bit FP registers have the following id bit patterns:: + 0x4030 0000 0012 0 <regno:12> -ARM firmware pseudo-registers have the following bit pattern: +ARM firmware pseudo-registers have the following bit pattern:: + 0x4030 0000 0014 <regno:16> @@ -2156,15 +2368,18 @@ that is the register group type, or coprocessor number: arm64 core/FP-SIMD registers have the following id bit patterns. Note that the size of the access is variable, as the kvm_regs structure contains elements ranging from 32 to 128 bits. The index is a 32bit -value in the kvm_regs structure seen as a 32bit array. +value in the kvm_regs structure seen as a 32bit array:: + 0x60x0 0000 0010 <index into the kvm_regs struct:16> Specifically: + +======================= ========= ===== ======================================= Encoding Register Bits kvm_regs member ----------------------------------------------------------------- +======================= ========= ===== ======================================= 0x6030 0000 0010 0000 X0 64 regs.regs[0] 0x6030 0000 0010 0002 X1 64 regs.regs[1] - ... + ... 0x6030 0000 0010 003c X30 64 regs.regs[30] 0x6030 0000 0010 003e SP 64 regs.sp 0x6030 0000 0010 0040 PC 64 regs.pc @@ -2176,27 +2391,31 @@ Specifically: 0x6030 0000 0010 004c SPSR_UND 64 spsr[KVM_SPSR_UND] 0x6030 0000 0010 004e SPSR_IRQ 64 spsr[KVM_SPSR_IRQ] 0x6060 0000 0010 0050 SPSR_FIQ 64 spsr[KVM_SPSR_FIQ] - 0x6040 0000 0010 0054 V0 128 fp_regs.vregs[0] (*) - 0x6040 0000 0010 0058 V1 128 fp_regs.vregs[1] (*) - ... - 0x6040 0000 0010 00d0 V31 128 fp_regs.vregs[31] (*) + 0x6040 0000 0010 0054 V0 128 fp_regs.vregs[0] [1]_ + 0x6040 0000 0010 0058 V1 128 fp_regs.vregs[1] [1]_ + ... + 0x6040 0000 0010 00d0 V31 128 fp_regs.vregs[31] [1]_ 0x6020 0000 0010 00d4 FPSR 32 fp_regs.fpsr 0x6020 0000 0010 00d5 FPCR 32 fp_regs.fpcr +======================= ========= ===== ======================================= -(*) These encodings are not accepted for SVE-enabled vcpus. See - KVM_ARM_VCPU_INIT. +.. [1] These encodings are not accepted for SVE-enabled vcpus. See + KVM_ARM_VCPU_INIT. - The equivalent register content can be accessed via bits [127:0] of - the corresponding SVE Zn registers instead for vcpus that have SVE - enabled (see below). + The equivalent register content can be accessed via bits [127:0] of + the corresponding SVE Zn registers instead for vcpus that have SVE + enabled (see below). + +arm64 CCSIDR registers are demultiplexed by CSSELR value:: -arm64 CCSIDR registers are demultiplexed by CSSELR value: 0x6020 0000 0011 00 <csselr:8> -arm64 system registers have the following id bit patterns: +arm64 system registers have the following id bit patterns:: + 0x6030 0000 0013 <op0:2> <op1:3> <crn:4> <crm:4> <op2:3> -WARNING: +.. warning:: + Two system register IDs do not follow the specified pattern. These are KVM_REG_ARM_TIMER_CVAL and KVM_REG_ARM_TIMER_CNT, which map to system registers CNTV_CVAL_EL0 and CNTVCT_EL0 respectively. These @@ -2205,10 +2424,12 @@ WARNING: derived from the register encoding for CNTV_CVAL_EL0. As this is API, it must remain this way. -arm64 firmware pseudo-registers have the following bit pattern: +arm64 firmware pseudo-registers have the following bit pattern:: + 0x6030 0000 0014 <regno:16> -arm64 SVE registers have the following bit patterns: +arm64 SVE registers have the following bit patterns:: + 0x6080 0000 0015 00 <n:5> <slice:5> Zn bits[2048*slice + 2047 : 2048*slice] 0x6050 0000 0015 04 <n:4> <slice:5> Pn bits[256*slice + 255 : 256*slice] 0x6050 0000 0015 060 <slice:5> FFR bits[256*slice + 255 : 256*slice] @@ -2216,7 +2437,7 @@ arm64 SVE registers have the following bit patterns: Access to register IDs where 2048 * slice >= 128 * max_vq will fail with ENOENT. max_vq is the vcpu's maximum supported vector length in 128-bit -quadwords: see (**) below. +quadwords: see [2]_ below. These registers are only accessible on vcpus for which SVE is enabled. See KVM_ARM_VCPU_INIT for details. @@ -2231,21 +2452,21 @@ lengths supported by the vcpu to be discovered and configured by userspace. When transferred to or from user memory via KVM_GET_ONE_REG or KVM_SET_ONE_REG, the value of this register is of type __u64[KVM_ARM64_SVE_VLS_WORDS], and encodes the set of vector lengths as -follows: +follows:: -__u64 vector_lengths[KVM_ARM64_SVE_VLS_WORDS]; + __u64 vector_lengths[KVM_ARM64_SVE_VLS_WORDS]; -if (vq >= SVE_VQ_MIN && vq <= SVE_VQ_MAX && - ((vector_lengths[(vq - KVM_ARM64_SVE_VQ_MIN) / 64] >> + if (vq >= SVE_VQ_MIN && vq <= SVE_VQ_MAX && + ((vector_lengths[(vq - KVM_ARM64_SVE_VQ_MIN) / 64] >> ((vq - KVM_ARM64_SVE_VQ_MIN) % 64)) & 1)) /* Vector length vq * 16 bytes supported */ -else + else /* Vector length vq * 16 bytes not supported */ -(**) The maximum value vq for which the above condition is true is -max_vq. This is the maximum vector length available to the guest on -this vcpu, and determines which register slices are visible through -this ioctl interface. +.. [2] The maximum value vq for which the above condition is true is + max_vq. This is the maximum vector length available to the guest on + this vcpu, and determines which register slices are visible through + this ioctl interface. (See Documentation/arm64/sve.rst for an explanation of the "vq" nomenclature.) @@ -2270,11 +2491,13 @@ write this register will fail with EPERM. MIPS registers are mapped using the lower 32 bits. The upper 16 of that is the register group type: -MIPS core registers (see above) have the following id bit patterns: +MIPS core registers (see above) have the following id bit patterns:: + 0x7030 0000 0000 <reg:16> MIPS CP0 registers (see KVM_REG_MIPS_CP0_* above) have the following id bit -patterns depending on whether they're 32-bit or 64-bit registers: +patterns depending on whether they're 32-bit or 64-bit registers:: + 0x7020 0000 0001 00 <reg:5> <sel:3> (32-bit) 0x7030 0000 0001 00 <reg:5> <sel:3> (64-bit) @@ -2285,10 +2508,12 @@ with the RI and XI bits (if they exist) in bits 63 and 62 respectively, and the PFNX field starting at bit 30. MIPS MAARs (see KVM_REG_MIPS_CP0_MAAR(*) above) have the following id bit -patterns: +patterns:: + 0x7030 0000 0001 01 <reg:8> -MIPS KVM control registers (see above) have the following id bit patterns: +MIPS KVM control registers (see above) have the following id bit patterns:: + 0x7030 0000 0002 <reg:16> MIPS FPU registers (see KVM_REG_MIPS_FPR_{32,64}() above) have the following @@ -2297,31 +2522,40 @@ always accessed according to the current guest FPU mode (Status.FR and Config5.FRE), i.e. as the guest would see them, and they become unpredictable if the guest FPU mode is changed. MIPS SIMD Architecture (MSA) vector registers (see KVM_REG_MIPS_VEC_128() above) have similar patterns as they -overlap the FPU registers: +overlap the FPU registers:: + 0x7020 0000 0003 00 <0:3> <reg:5> (32-bit FPU registers) 0x7030 0000 0003 00 <0:3> <reg:5> (64-bit FPU registers) 0x7040 0000 0003 00 <0:3> <reg:5> (128-bit MSA vector registers) MIPS FPU control registers (see KVM_REG_MIPS_FCR_{IR,CSR} above) have the -following id bit patterns: +following id bit patterns:: + 0x7020 0000 0003 01 <0:3> <reg:5> MIPS MSA control registers (see KVM_REG_MIPS_MSA_{IR,CSR} above) have the -following id bit patterns: +following id bit patterns:: + 0x7020 0000 0003 02 <0:3> <reg:5> 4.69 KVM_GET_ONE_REG +-------------------- + +:Capability: KVM_CAP_ONE_REG +:Architectures: all +:Type: vcpu ioctl +:Parameters: struct kvm_one_reg (in and out) +:Returns: 0 on success, negative value on failure -Capability: KVM_CAP_ONE_REG -Architectures: all -Type: vcpu ioctl -Parameters: struct kvm_one_reg (in and out) -Returns: 0 on success, negative value on failure Errors include: - ENOENT: no such register - EINVAL: invalid register ID, or no such register - EPERM: (arm64) register access not allowed before vcpu finalization + + ======== ============================================================ + ENOENT no such register + EINVAL invalid register ID, or no such register + EPERM (arm64) register access not allowed before vcpu finalization + ======== ============================================================ + (These error codes are indicative only: do not rely on a specific error code being returned in a specific situation.) @@ -2335,12 +2569,13 @@ list in 4.68. 4.70 KVM_KVMCLOCK_CTRL +---------------------- -Capability: KVM_CAP_KVMCLOCK_CTRL -Architectures: Any that implement pvclocks (currently x86 only) -Type: vcpu ioctl -Parameters: None -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_KVMCLOCK_CTRL +:Architectures: Any that implement pvclocks (currently x86 only) +:Type: vcpu ioctl +:Parameters: None +:Returns: 0 on success, -1 on error This signals to the host kernel that the specified guest is being paused by userspace. The host will set a flag in the pvclock structure that is checked @@ -2356,26 +2591,30 @@ after pausing the vcpu, but before it is resumed. 4.71 KVM_SIGNAL_MSI +------------------- -Capability: KVM_CAP_SIGNAL_MSI -Architectures: x86 arm arm64 -Type: vm ioctl -Parameters: struct kvm_msi (in) -Returns: >0 on delivery, 0 if guest blocked the MSI, and -1 on error +:Capability: KVM_CAP_SIGNAL_MSI +:Architectures: x86 arm arm64 +:Type: vm ioctl +:Parameters: struct kvm_msi (in) +:Returns: >0 on delivery, 0 if guest blocked the MSI, and -1 on error Directly inject a MSI message. Only valid with in-kernel irqchip that handles MSI messages. -struct kvm_msi { +:: + + struct kvm_msi { __u32 address_lo; __u32 address_hi; __u32 data; __u32 flags; __u32 devid; __u8 pad[12]; -}; + }; -flags: KVM_MSI_VALID_DEVID: devid contains a valid value. The per-VM +flags: + KVM_MSI_VALID_DEVID: devid contains a valid value. The per-VM KVM_CAP_MSI_DEVID capability advertises the requirement to provide the device ID. If this capability is not available, userspace should never set the KVM_MSI_VALID_DEVID flag as the ioctl might fail. @@ -2391,30 +2630,31 @@ address_hi must be zero. 4.71 KVM_CREATE_PIT2 +-------------------- -Capability: KVM_CAP_PIT2 -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_pit_config (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_PIT2 +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_pit_config (in) +:Returns: 0 on success, -1 on error Creates an in-kernel device model for the i8254 PIT. This call is only valid after enabling in-kernel irqchip support via KVM_CREATE_IRQCHIP. The following -parameters have to be passed: +parameters have to be passed:: -struct kvm_pit_config { + struct kvm_pit_config { __u32 flags; __u32 pad[15]; -}; + }; -Valid flags are: +Valid flags are:: -#define KVM_PIT_SPEAKER_DUMMY 1 /* emulate speaker port stub */ + #define KVM_PIT_SPEAKER_DUMMY 1 /* emulate speaker port stub */ PIT timer interrupts may use a per-VM kernel thread for injection. If it -exists, this thread will have a name of the following pattern: +exists, this thread will have a name of the following pattern:: -kvm-pit/<owner-process-pid> + kvm-pit/<owner-process-pid> When running a guest with elevated priorities, the scheduling parameters of this thread may have to be adjusted accordingly. @@ -2423,37 +2663,39 @@ This IOCTL replaces the obsolete KVM_CREATE_PIT. 4.72 KVM_GET_PIT2 +----------------- -Capability: KVM_CAP_PIT_STATE2 -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_pit_state2 (out) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_PIT_STATE2 +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_pit_state2 (out) +:Returns: 0 on success, -1 on error Retrieves the state of the in-kernel PIT model. Only valid after -KVM_CREATE_PIT2. The state is returned in the following structure: +KVM_CREATE_PIT2. The state is returned in the following structure:: -struct kvm_pit_state2 { + struct kvm_pit_state2 { struct kvm_pit_channel_state channels[3]; __u32 flags; __u32 reserved[9]; -}; + }; -Valid flags are: +Valid flags are:: -/* disable PIT in HPET legacy mode */ -#define KVM_PIT_FLAGS_HPET_LEGACY 0x00000001 + /* disable PIT in HPET legacy mode */ + #define KVM_PIT_FLAGS_HPET_LEGACY 0x00000001 This IOCTL replaces the obsolete KVM_GET_PIT. 4.73 KVM_SET_PIT2 +----------------- -Capability: KVM_CAP_PIT_STATE2 -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_pit_state2 (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_PIT_STATE2 +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_pit_state2 (in) +:Returns: 0 on success, -1 on error Sets the state of the in-kernel PIT model. Only valid after KVM_CREATE_PIT2. See KVM_GET_PIT2 for details on struct kvm_pit_state2. @@ -2462,12 +2704,13 @@ This IOCTL replaces the obsolete KVM_SET_PIT. 4.74 KVM_PPC_GET_SMMU_INFO +-------------------------- -Capability: KVM_CAP_PPC_GET_SMMU_INFO -Architectures: powerpc -Type: vm ioctl -Parameters: None -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_PPC_GET_SMMU_INFO +:Architectures: powerpc +:Type: vm ioctl +:Parameters: None +:Returns: 0 on success, -1 on error This populates and returns a structure describing the features of the "Server" class MMU emulation supported by KVM. @@ -2475,7 +2718,7 @@ This can in turn be used by userspace to generate the appropriate device-tree properties for the guest operating system. The structure contains some global information, followed by an -array of supported segment page sizes: +array of supported segment page sizes:: struct kvm_ppc_smmu_info { __u64 flags; @@ -2503,7 +2746,7 @@ The "slb_size" field indicates how many SLB entries are supported The "sps" array contains 8 entries indicating the supported base page sizes for a segment in increasing order. Each entry is defined -as follow: +as follow:: struct kvm_ppc_one_seg_page_size { __u32 page_shift; /* Base page shift of segment (or 0) */ @@ -2524,7 +2767,7 @@ size provides the list of supported actual page sizes (which can be only larger or equal to the base page size), along with the corresponding encoding in the hash PTE. Similarly, the array is 8 entries sorted by increasing sizes and an entry with a "0" shift -is an empty entry and a terminator: +is an empty entry and a terminator:: struct kvm_ppc_one_page_size { __u32 page_shift; /* Page shift (or 0) */ @@ -2536,12 +2779,13 @@ PTE's RPN field (ie, it needs to be shifted left by 12 to OR it into the hash PTE second double word). 4.75 KVM_IRQFD +-------------- -Capability: KVM_CAP_IRQFD -Architectures: x86 s390 arm arm64 -Type: vm ioctl -Parameters: struct kvm_irqfd (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_IRQFD +:Architectures: x86 s390 arm arm64 +:Type: vm ioctl +:Parameters: struct kvm_irqfd (in) +:Returns: 0 on success, -1 on error Allows setting an eventfd to directly trigger a guest interrupt. kvm_irqfd.fd specifies the file descriptor to use as the eventfd and @@ -2565,6 +2809,7 @@ irqfd. The KVM_IRQFD_FLAG_RESAMPLE is only necessary on assignment and need not be specified with KVM_IRQFD_FLAG_DEASSIGN. On arm/arm64, gsi routing being supported, the following can happen: + - in case no routing entry is associated to this gsi, injection fails - in case the gsi is associated to an irqchip routing entry, irqchip.pin + 32 corresponds to the injected SPI ID. @@ -2573,12 +2818,13 @@ On arm/arm64, gsi routing being supported, the following can happen: to GICv3 ITS in-kernel emulation). 4.76 KVM_PPC_ALLOCATE_HTAB +-------------------------- -Capability: KVM_CAP_PPC_ALLOC_HTAB -Architectures: powerpc -Type: vm ioctl -Parameters: Pointer to u32 containing hash table order (in/out) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_PPC_ALLOC_HTAB +:Architectures: powerpc +:Type: vm ioctl +:Parameters: Pointer to u32 containing hash table order (in/out) +:Returns: 0 on success, -1 on error This requests the host kernel to allocate an MMU hash table for a guest using the PAPR paravirtualization interface. This only does @@ -2609,75 +2855,88 @@ real-mode area (VRMA) facility, the kernel will re-create the VMRA HPTEs on the next KVM_RUN of any vcpu. 4.77 KVM_S390_INTERRUPT +----------------------- -Capability: basic -Architectures: s390 -Type: vm ioctl, vcpu ioctl -Parameters: struct kvm_s390_interrupt (in) -Returns: 0 on success, -1 on error +:Capability: basic +:Architectures: s390 +:Type: vm ioctl, vcpu ioctl +:Parameters: struct kvm_s390_interrupt (in) +:Returns: 0 on success, -1 on error Allows to inject an interrupt to the guest. Interrupts can be floating (vm ioctl) or per cpu (vcpu ioctl), depending on the interrupt type. -Interrupt parameters are passed via kvm_s390_interrupt: +Interrupt parameters are passed via kvm_s390_interrupt:: -struct kvm_s390_interrupt { + struct kvm_s390_interrupt { __u32 type; __u32 parm; __u64 parm64; -}; + }; type can be one of the following: -KVM_S390_SIGP_STOP (vcpu) - sigp stop; optional flags in parm -KVM_S390_PROGRAM_INT (vcpu) - program check; code in parm -KVM_S390_SIGP_SET_PREFIX (vcpu) - sigp set prefix; prefix address in parm -KVM_S390_RESTART (vcpu) - restart -KVM_S390_INT_CLOCK_COMP (vcpu) - clock comparator interrupt -KVM_S390_INT_CPU_TIMER (vcpu) - CPU timer interrupt -KVM_S390_INT_VIRTIO (vm) - virtio external interrupt; external interrupt - parameters in parm and parm64 -KVM_S390_INT_SERVICE (vm) - sclp external interrupt; sclp parameter in parm -KVM_S390_INT_EMERGENCY (vcpu) - sigp emergency; source cpu in parm -KVM_S390_INT_EXTERNAL_CALL (vcpu) - sigp external call; source cpu in parm -KVM_S390_INT_IO(ai,cssid,ssid,schid) (vm) - compound value to indicate an - I/O interrupt (ai - adapter interrupt; cssid,ssid,schid - subchannel); - I/O interruption parameters in parm (subchannel) and parm64 (intparm, - interruption subclass) -KVM_S390_MCHK (vm, vcpu) - machine check interrupt; cr 14 bits in parm, - machine check interrupt code in parm64 (note that - machine checks needing further payload are not - supported by this ioctl) +KVM_S390_SIGP_STOP (vcpu) + - sigp stop; optional flags in parm +KVM_S390_PROGRAM_INT (vcpu) + - program check; code in parm +KVM_S390_SIGP_SET_PREFIX (vcpu) + - sigp set prefix; prefix address in parm +KVM_S390_RESTART (vcpu) + - restart +KVM_S390_INT_CLOCK_COMP (vcpu) + - clock comparator interrupt +KVM_S390_INT_CPU_TIMER (vcpu) + - CPU timer interrupt +KVM_S390_INT_VIRTIO (vm) + - virtio external interrupt; external interrupt + parameters in parm and parm64 +KVM_S390_INT_SERVICE (vm) + - sclp external interrupt; sclp parameter in parm +KVM_S390_INT_EMERGENCY (vcpu) + - sigp emergency; source cpu in parm +KVM_S390_INT_EXTERNAL_CALL (vcpu) + - sigp external call; source cpu in parm +KVM_S390_INT_IO(ai,cssid,ssid,schid) (vm) + - compound value to indicate an + I/O interrupt (ai - adapter interrupt; cssid,ssid,schid - subchannel); + I/O interruption parameters in parm (subchannel) and parm64 (intparm, + interruption subclass) +KVM_S390_MCHK (vm, vcpu) + - machine check interrupt; cr 14 bits in parm, machine check interrupt + code in parm64 (note that machine checks needing further payload are not + supported by this ioctl) This is an asynchronous vcpu ioctl and can be invoked from any thread. 4.78 KVM_PPC_GET_HTAB_FD +------------------------ -Capability: KVM_CAP_PPC_HTAB_FD -Architectures: powerpc -Type: vm ioctl -Parameters: Pointer to struct kvm_get_htab_fd (in) -Returns: file descriptor number (>= 0) on success, -1 on error +:Capability: KVM_CAP_PPC_HTAB_FD +:Architectures: powerpc +:Type: vm ioctl +:Parameters: Pointer to struct kvm_get_htab_fd (in) +:Returns: file descriptor number (>= 0) on success, -1 on error This returns a file descriptor that can be used either to read out the entries in the guest's hashed page table (HPT), or to write entries to initialize the HPT. The returned fd can only be written to if the KVM_GET_HTAB_WRITE bit is set in the flags field of the argument, and can only be read if that bit is clear. The argument struct looks like -this: +this:: -/* For KVM_PPC_GET_HTAB_FD */ -struct kvm_get_htab_fd { + /* For KVM_PPC_GET_HTAB_FD */ + struct kvm_get_htab_fd { __u64 flags; __u64 start_index; __u64 reserved[2]; -}; + }; -/* Values for kvm_get_htab_fd.flags */ -#define KVM_GET_HTAB_BOLTED_ONLY ((__u64)0x1) -#define KVM_GET_HTAB_WRITE ((__u64)0x2) + /* Values for kvm_get_htab_fd.flags */ + #define KVM_GET_HTAB_BOLTED_ONLY ((__u64)0x1) + #define KVM_GET_HTAB_WRITE ((__u64)0x2) -The `start_index' field gives the index in the HPT of the entry at +The 'start_index' field gives the index in the HPT of the entry at which to start reading. It is ignored when writing. Reads on the fd will initially supply information about all @@ -2692,29 +2951,34 @@ Data read or written is structured as a header (8 bytes) followed by a series of valid HPT entries (16 bytes) each. The header indicates how many valid HPT entries there are and how many invalid entries follow the valid entries. The invalid entries are not represented explicitly -in the stream. The header format is: +in the stream. The header format is:: -struct kvm_get_htab_header { + struct kvm_get_htab_header { __u32 index; __u16 n_valid; __u16 n_invalid; -}; + }; Writes to the fd create HPT entries starting at the index given in the -header; first `n_valid' valid entries with contents from the data -written, then `n_invalid' invalid entries, invalidating any previously +header; first 'n_valid' valid entries with contents from the data +written, then 'n_invalid' invalid entries, invalidating any previously valid entries found. 4.79 KVM_CREATE_DEVICE +---------------------- + +:Capability: KVM_CAP_DEVICE_CTRL +:Type: vm ioctl +:Parameters: struct kvm_create_device (in/out) +:Returns: 0 on success, -1 on error -Capability: KVM_CAP_DEVICE_CTRL -Type: vm ioctl -Parameters: struct kvm_create_device (in/out) -Returns: 0 on success, -1 on error Errors: - ENODEV: The device type is unknown or unsupported - EEXIST: Device already created, and this type of device may not + + ====== ======================================================= + ENODEV The device type is unknown or unsupported + EEXIST Device already created, and this type of device may not be instantiated multiple times + ====== ======================================================= Other error conditions may be defined by individual device types or have their standard meanings. @@ -2730,25 +2994,32 @@ Individual devices should not define flags. Attributes should be used for specifying any behavior that is not implied by the device type number. -struct kvm_create_device { +:: + + struct kvm_create_device { __u32 type; /* in: KVM_DEV_TYPE_xxx */ __u32 fd; /* out: device handle */ __u32 flags; /* in: KVM_CREATE_DEVICE_xxx */ -}; + }; 4.80 KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR +-------------------------------------------- + +:Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device, + KVM_CAP_VCPU_ATTRIBUTES for vcpu device +:Type: device ioctl, vm ioctl, vcpu ioctl +:Parameters: struct kvm_device_attr +:Returns: 0 on success, -1 on error -Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device, - KVM_CAP_VCPU_ATTRIBUTES for vcpu device -Type: device ioctl, vm ioctl, vcpu ioctl -Parameters: struct kvm_device_attr -Returns: 0 on success, -1 on error Errors: - ENXIO: The group or attribute is unknown/unsupported for this device + + ===== ============================================================= + ENXIO The group or attribute is unknown/unsupported for this device or hardware support is missing. - EPERM: The attribute cannot (currently) be accessed this way + EPERM The attribute cannot (currently) be accessed this way (e.g. read-only attribute, or attribute that only makes sense when the device is in a different state) + ===== ============================================================= Other error conditions may be defined by individual device types. @@ -2757,23 +3028,30 @@ semantics are device-specific. See individual device documentation in the "devices" directory. As with ONE_REG, the size of the data transferred is defined by the particular attribute. -struct kvm_device_attr { +:: + + struct kvm_device_attr { __u32 flags; /* no flags currently defined */ __u32 group; /* device-defined */ __u64 attr; /* group-defined */ __u64 addr; /* userspace address of attr data */ -}; + }; 4.81 KVM_HAS_DEVICE_ATTR +------------------------ + +:Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device, + KVM_CAP_VCPU_ATTRIBUTES for vcpu device +:Type: device ioctl, vm ioctl, vcpu ioctl +:Parameters: struct kvm_device_attr +:Returns: 0 on success, -1 on error -Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device, - KVM_CAP_VCPU_ATTRIBUTES for vcpu device -Type: device ioctl, vm ioctl, vcpu ioctl -Parameters: struct kvm_device_attr -Returns: 0 on success, -1 on error Errors: - ENXIO: The group or attribute is unknown/unsupported for this device + + ===== ============================================================= + ENXIO The group or attribute is unknown/unsupported for this device or hardware support is missing. + ===== ============================================================= Tests whether a device supports a particular attribute. A successful return indicates the attribute is implemented. It does not necessarily @@ -2781,15 +3059,20 @@ indicate that the attribute can be read or written in the device's current state. "addr" is ignored. 4.82 KVM_ARM_VCPU_INIT +---------------------- + +:Capability: basic +:Architectures: arm, arm64 +:Type: vcpu ioctl +:Parameters: struct kvm_vcpu_init (in) +:Returns: 0 on success; -1 on error -Capability: basic -Architectures: arm, arm64 -Type: vcpu ioctl -Parameters: struct kvm_vcpu_init (in) -Returns: 0 on success; -1 on error Errors: - EINVAL: the target is unknown, or the combination of features is invalid. - ENOENT: a features bit specified is unknown. + + ====== ================================================================= + EINVAL the target is unknown, or the combination of features is invalid. + ENOENT a features bit specified is unknown. + ====== ================================================================= This tells KVM what type of CPU to present to the guest, and what optional features it should have. This will cause a reset of the cpu @@ -2805,6 +3088,7 @@ state. All calls to this function after the initial call must use the same target and same set of feature flags, otherwise EINVAL will be returned. Possible features: + - KVM_ARM_VCPU_POWER_OFF: Starts the CPU in a power-off state. Depends on KVM_CAP_ARM_PSCI. If not set, the CPU will be powered on and execute guest code when KVM_RUN is called. @@ -2861,14 +3145,19 @@ Possible features: no longer be written using KVM_SET_ONE_REG. 4.83 KVM_ARM_PREFERRED_TARGET +----------------------------- + +:Capability: basic +:Architectures: arm, arm64 +:Type: vm ioctl +:Parameters: struct struct kvm_vcpu_init (out) +:Returns: 0 on success; -1 on error -Capability: basic -Architectures: arm, arm64 -Type: vm ioctl -Parameters: struct struct kvm_vcpu_init (out) -Returns: 0 on success; -1 on error Errors: - ENODEV: no preferred target available for the host + + ====== ========================================== + ENODEV no preferred target available for the host + ====== ========================================== This queries KVM for preferred CPU target type which can be emulated by KVM on underlying host. @@ -2885,43 +3174,57 @@ in VCPU matching underlying host. 4.84 KVM_GET_REG_LIST +--------------------- + +:Capability: basic +:Architectures: arm, arm64, mips +:Type: vcpu ioctl +:Parameters: struct kvm_reg_list (in/out) +:Returns: 0 on success; -1 on error -Capability: basic -Architectures: arm, arm64, mips -Type: vcpu ioctl -Parameters: struct kvm_reg_list (in/out) -Returns: 0 on success; -1 on error Errors: - E2BIG: the reg index list is too big to fit in the array specified by + + ===== ============================================================== + E2BIG the reg index list is too big to fit in the array specified by the user (the number required will be written into n). + ===== ============================================================== + +:: -struct kvm_reg_list { + struct kvm_reg_list { __u64 n; /* number of registers in reg[] */ __u64 reg[0]; -}; + }; This ioctl returns the guest registers that are supported for the KVM_GET_ONE_REG/KVM_SET_ONE_REG calls. 4.85 KVM_ARM_SET_DEVICE_ADDR (deprecated) +----------------------------------------- + +:Capability: KVM_CAP_ARM_SET_DEVICE_ADDR +:Architectures: arm, arm64 +:Type: vm ioctl +:Parameters: struct kvm_arm_device_address (in) +:Returns: 0 on success, -1 on error -Capability: KVM_CAP_ARM_SET_DEVICE_ADDR -Architectures: arm, arm64 -Type: vm ioctl -Parameters: struct kvm_arm_device_address (in) -Returns: 0 on success, -1 on error Errors: - ENODEV: The device id is unknown - ENXIO: Device not supported on current system - EEXIST: Address already set - E2BIG: Address outside guest physical address space - EBUSY: Address overlaps with other device range -struct kvm_arm_device_addr { + ====== ============================================ + ENODEV The device id is unknown + ENXIO Device not supported on current system + EEXIST Address already set + E2BIG Address outside guest physical address space + EBUSY Address overlaps with other device range + ====== ============================================ + +:: + + struct kvm_arm_device_addr { __u64 id; __u64 addr; -}; + }; Specify a device address in the guest's physical address space where guests can access emulated or directly exposed devices, which the host kernel needs @@ -2929,7 +3232,7 @@ to know about. The id field is an architecture specific identifier for a specific device. ARM/arm64 divides the id field into two parts, a device id and an -address type id specific to the individual device. +address type id specific to the individual device:: bits: | 63 ... 32 | 31 ... 16 | 15 ... 0 | field: | 0x00000000 | device id | addr type id | @@ -2947,12 +3250,13 @@ should be used instead. 4.86 KVM_PPC_RTAS_DEFINE_TOKEN +------------------------------ -Capability: KVM_CAP_PPC_RTAS -Architectures: ppc -Type: vm ioctl -Parameters: struct kvm_rtas_token_args -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_PPC_RTAS +:Architectures: ppc +:Type: vm ioctl +:Parameters: struct kvm_rtas_token_args +:Returns: 0 on success, -1 on error Defines a token value for a RTAS (Run Time Abstraction Services) service in order to allow it to be handled in the kernel. The @@ -2966,18 +3270,21 @@ calls by the guest for that service will be passed to userspace to be handled. 4.87 KVM_SET_GUEST_DEBUG +------------------------ -Capability: KVM_CAP_SET_GUEST_DEBUG -Architectures: x86, s390, ppc, arm64 -Type: vcpu ioctl -Parameters: struct kvm_guest_debug (in) -Returns: 0 on success; -1 on error +:Capability: KVM_CAP_SET_GUEST_DEBUG +:Architectures: x86, s390, ppc, arm64 +:Type: vcpu ioctl +:Parameters: struct kvm_guest_debug (in) +:Returns: 0 on success; -1 on error + +:: -struct kvm_guest_debug { + struct kvm_guest_debug { __u32 control; __u32 pad; struct kvm_guest_debug_arch arch; -}; + }; Set up the processor specific debug registers and configure vcpu for handling guest debug events. There are two parts to the structure, the @@ -3019,26 +3326,31 @@ KVM_EXIT_DEBUG with the kvm_debug_exit_arch part of the kvm_run structure containing architecture specific debug information. 4.88 KVM_GET_EMULATED_CPUID +--------------------------- + +:Capability: KVM_CAP_EXT_EMUL_CPUID +:Architectures: x86 +:Type: system ioctl +:Parameters: struct kvm_cpuid2 (in/out) +:Returns: 0 on success, -1 on error -Capability: KVM_CAP_EXT_EMUL_CPUID -Architectures: x86 -Type: system ioctl -Parameters: struct kvm_cpuid2 (in/out) -Returns: 0 on success, -1 on error +:: -struct kvm_cpuid2 { + struct kvm_cpuid2 { __u32 nent; __u32 flags; struct kvm_cpuid_entry2 entries[0]; -}; + }; The member 'flags' is used for passing flags from userspace. -#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0) -#define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1) -#define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2) +:: -struct kvm_cpuid_entry2 { + #define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0) + #define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1) + #define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2) + + struct kvm_cpuid_entry2 { __u32 function; __u32 index; __u32 flags; @@ -3047,7 +3359,7 @@ struct kvm_cpuid_entry2 { __u32 ecx; __u32 edx; __u32 padding[3]; -}; + }; This ioctl returns x86 cpuid features which are emulated by kvm.Userspace can use the information returned by this ioctl to query @@ -3072,10 +3384,14 @@ emulated efficiently and thus not included here. The fields in each entry are defined as follows: - function: the eax value used to obtain the entry - index: the ecx value used to obtain the entry (for entries that are + function: + the eax value used to obtain the entry + index: + the ecx value used to obtain the entry (for entries that are affected by ecx) - flags: an OR of zero or more of the following: + flags: + an OR of zero or more of the following: + KVM_CPUID_FLAG_SIGNIFCANT_INDEX: if the index field is valid KVM_CPUID_FLAG_STATEFUL_FUNC: @@ -3085,24 +3401,28 @@ The fields in each entry are defined as follows: KVM_CPUID_FLAG_STATE_READ_NEXT: for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is the first entry to be read by a cpu - eax, ebx, ecx, edx: the values returned by the cpuid instruction for + + eax, ebx, ecx, edx: + + the values returned by the cpuid instruction for this function/index combination 4.89 KVM_S390_MEM_OP +-------------------- -Capability: KVM_CAP_S390_MEM_OP -Architectures: s390 -Type: vcpu ioctl -Parameters: struct kvm_s390_mem_op (in) -Returns: = 0 on success, - < 0 on generic error (e.g. -EFAULT or -ENOMEM), - > 0 if an exception occurred while walking the page tables +:Capability: KVM_CAP_S390_MEM_OP +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: struct kvm_s390_mem_op (in) +:Returns: = 0 on success, + < 0 on generic error (e.g. -EFAULT or -ENOMEM), + > 0 if an exception occurred while walking the page tables Read or write data from/to the logical (virtual) memory of a VCPU. -Parameters are specified via the following structure: +Parameters are specified via the following structure:: -struct kvm_s390_mem_op { + struct kvm_s390_mem_op { __u64 gaddr; /* the guest address */ __u64 flags; /* flags */ __u32 size; /* amount of bytes */ @@ -3110,7 +3430,7 @@ struct kvm_s390_mem_op { __u64 buf; /* buffer in userspace */ __u8 ar; /* the access register number */ __u8 reserved[31]; /* should be set to 0 */ -}; + }; The type of operation is specified in the "op" field. It is either KVM_S390_MEMOP_LOGICAL_READ for reading from logical memory space or @@ -3137,24 +3457,25 @@ The "reserved" field is meant for future extensions. It is not used by KVM with the currently defined set of flags. 4.90 KVM_S390_GET_SKEYS +----------------------- -Capability: KVM_CAP_S390_SKEYS -Architectures: s390 -Type: vm ioctl -Parameters: struct kvm_s390_skeys -Returns: 0 on success, KVM_S390_GET_KEYS_NONE if guest is not using storage - keys, negative value on error +:Capability: KVM_CAP_S390_SKEYS +:Architectures: s390 +:Type: vm ioctl +:Parameters: struct kvm_s390_skeys +:Returns: 0 on success, KVM_S390_GET_KEYS_NONE if guest is not using storage + keys, negative value on error This ioctl is used to get guest storage key values on the s390 -architecture. The ioctl takes parameters via the kvm_s390_skeys struct. +architecture. The ioctl takes parameters via the kvm_s390_skeys struct:: -struct kvm_s390_skeys { + struct kvm_s390_skeys { __u64 start_gfn; __u64 count; __u64 skeydata_addr; __u32 flags; __u32 reserved[9]; -}; + }; The start_gfn field is the number of the first guest frame whose storage keys you want to get. @@ -3168,12 +3489,13 @@ The skeydata_addr field is the address to a buffer large enough to hold count bytes. This buffer will be filled with storage key data by the ioctl. 4.91 KVM_S390_SET_SKEYS +----------------------- -Capability: KVM_CAP_S390_SKEYS -Architectures: s390 -Type: vm ioctl -Parameters: struct kvm_s390_skeys -Returns: 0 on success, negative value on error +:Capability: KVM_CAP_S390_SKEYS +:Architectures: s390 +:Type: vm ioctl +:Parameters: struct kvm_s390_skeys +:Returns: 0 on success, negative value on error This ioctl is used to set guest storage key values on the s390 architecture. The ioctl takes parameters via the kvm_s390_skeys struct. @@ -3195,21 +3517,27 @@ Note: If any architecturally invalid key value is found in the given data then the ioctl will return -EINVAL. 4.92 KVM_S390_IRQ +----------------- + +:Capability: KVM_CAP_S390_INJECT_IRQ +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: struct kvm_s390_irq (in) +:Returns: 0 on success, -1 on error -Capability: KVM_CAP_S390_INJECT_IRQ -Architectures: s390 -Type: vcpu ioctl -Parameters: struct kvm_s390_irq (in) -Returns: 0 on success, -1 on error Errors: - EINVAL: interrupt type is invalid - type is KVM_S390_SIGP_STOP and flag parameter is invalid value + + + ====== ================================================================= + EINVAL interrupt type is invalid + type is KVM_S390_SIGP_STOP and flag parameter is invalid value, type is KVM_S390_INT_EXTERNAL_CALL and code is bigger - than the maximum of VCPUs - EBUSY: type is KVM_S390_SIGP_SET_PREFIX and vcpu is not stopped - type is KVM_S390_SIGP_STOP and a stop irq is already pending + than the maximum of VCPUs + EBUSY type is KVM_S390_SIGP_SET_PREFIX and vcpu is not stopped, + type is KVM_S390_SIGP_STOP and a stop irq is already pending, type is KVM_S390_INT_EXTERNAL_CALL and an external call interrupt - is already pending + is already pending + ====== ================================================================= Allows to inject an interrupt to the guest. @@ -3217,9 +3545,9 @@ Using struct kvm_s390_irq as a parameter allows to inject additional payload which is not possible via KVM_S390_INTERRUPT. -Interrupt parameters are passed via kvm_s390_irq: +Interrupt parameters are passed via kvm_s390_irq:: -struct kvm_s390_irq { + struct kvm_s390_irq { __u64 type; union { struct kvm_s390_io_info io; @@ -3232,44 +3560,45 @@ struct kvm_s390_irq { struct kvm_s390_mchk_info mchk; char reserved[64]; } u; -}; + }; type can be one of the following: -KVM_S390_SIGP_STOP - sigp stop; parameter in .stop -KVM_S390_PROGRAM_INT - program check; parameters in .pgm -KVM_S390_SIGP_SET_PREFIX - sigp set prefix; parameters in .prefix -KVM_S390_RESTART - restart; no parameters -KVM_S390_INT_CLOCK_COMP - clock comparator interrupt; no parameters -KVM_S390_INT_CPU_TIMER - CPU timer interrupt; no parameters -KVM_S390_INT_EMERGENCY - sigp emergency; parameters in .emerg -KVM_S390_INT_EXTERNAL_CALL - sigp external call; parameters in .extcall -KVM_S390_MCHK - machine check interrupt; parameters in .mchk +- KVM_S390_SIGP_STOP - sigp stop; parameter in .stop +- KVM_S390_PROGRAM_INT - program check; parameters in .pgm +- KVM_S390_SIGP_SET_PREFIX - sigp set prefix; parameters in .prefix +- KVM_S390_RESTART - restart; no parameters +- KVM_S390_INT_CLOCK_COMP - clock comparator interrupt; no parameters +- KVM_S390_INT_CPU_TIMER - CPU timer interrupt; no parameters +- KVM_S390_INT_EMERGENCY - sigp emergency; parameters in .emerg +- KVM_S390_INT_EXTERNAL_CALL - sigp external call; parameters in .extcall +- KVM_S390_MCHK - machine check interrupt; parameters in .mchk This is an asynchronous vcpu ioctl and can be invoked from any thread. 4.94 KVM_S390_GET_IRQ_STATE +--------------------------- -Capability: KVM_CAP_S390_IRQ_STATE -Architectures: s390 -Type: vcpu ioctl -Parameters: struct kvm_s390_irq_state (out) -Returns: >= number of bytes copied into buffer, - -EINVAL if buffer size is 0, - -ENOBUFS if buffer size is too small to fit all pending interrupts, - -EFAULT if the buffer address was invalid +:Capability: KVM_CAP_S390_IRQ_STATE +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: struct kvm_s390_irq_state (out) +:Returns: >= number of bytes copied into buffer, + -EINVAL if buffer size is 0, + -ENOBUFS if buffer size is too small to fit all pending interrupts, + -EFAULT if the buffer address was invalid This ioctl allows userspace to retrieve the complete state of all currently pending interrupts in a single buffer. Use cases include migration and introspection. The parameter structure contains the address of a -userspace buffer and its length: +userspace buffer and its length:: -struct kvm_s390_irq_state { + struct kvm_s390_irq_state { __u64 buf; __u32 flags; /* will stay unused for compatibility reasons */ __u32 len; __u32 reserved[4]; /* will stay unused for compatibility reasons */ -}; + }; Userspace passes in the above struct and for each pending interrupt a struct kvm_s390_irq is copied to the provided buffer. @@ -3283,29 +3612,30 @@ If -ENOBUFS is returned the buffer provided was too small and userspace may retry with a bigger buffer. 4.95 KVM_S390_SET_IRQ_STATE - -Capability: KVM_CAP_S390_IRQ_STATE -Architectures: s390 -Type: vcpu ioctl -Parameters: struct kvm_s390_irq_state (in) -Returns: 0 on success, - -EFAULT if the buffer address was invalid, - -EINVAL for an invalid buffer length (see below), - -EBUSY if there were already interrupts pending, - errors occurring when actually injecting the +--------------------------- + +:Capability: KVM_CAP_S390_IRQ_STATE +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: struct kvm_s390_irq_state (in) +:Returns: 0 on success, + -EFAULT if the buffer address was invalid, + -EINVAL for an invalid buffer length (see below), + -EBUSY if there were already interrupts pending, + errors occurring when actually injecting the interrupt. See KVM_S390_IRQ. This ioctl allows userspace to set the complete state of all cpu-local interrupts currently pending for the vcpu. It is intended for restoring interrupt state after a migration. The input parameter is a userspace buffer -containing a struct kvm_s390_irq_state: +containing a struct kvm_s390_irq_state:: -struct kvm_s390_irq_state { + struct kvm_s390_irq_state { __u64 buf; __u32 flags; /* will stay unused for compatibility reasons */ __u32 len; __u32 reserved[4]; /* will stay unused for compatibility reasons */ -}; + }; The restrictions for flags and reserved apply as well. (see KVM_S390_GET_IRQ_STATE) @@ -3320,20 +3650,22 @@ and it must not exceed (max_vcpus + 32) * sizeof(struct kvm_s390_irq), which is the maximum number of possibly pending cpu-local interrupts. 4.96 KVM_SMI +------------ -Capability: KVM_CAP_X86_SMM -Architectures: x86 -Type: vcpu ioctl -Parameters: none -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_X86_SMM +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: none +:Returns: 0 on success, -1 on error Queues an SMI on the thread's vcpu. 4.97 KVM_CAP_PPC_MULTITCE +------------------------- -Capability: KVM_CAP_PPC_MULTITCE -Architectures: ppc -Type: vm +:Capability: KVM_CAP_PPC_MULTITCE +:Architectures: ppc +:Type: vm This capability means the kernel is capable of handling hypercalls H_PUT_TCE_INDIRECT and H_STUFF_TCE without passing those into the user @@ -3355,26 +3687,27 @@ an implementation for these despite the in kernel acceleration. This capability is always enabled. 4.98 KVM_CREATE_SPAPR_TCE_64 +---------------------------- -Capability: KVM_CAP_SPAPR_TCE_64 -Architectures: powerpc -Type: vm ioctl -Parameters: struct kvm_create_spapr_tce_64 (in) -Returns: file descriptor for manipulating the created TCE table +:Capability: KVM_CAP_SPAPR_TCE_64 +:Architectures: powerpc +:Type: vm ioctl +:Parameters: struct kvm_create_spapr_tce_64 (in) +:Returns: file descriptor for manipulating the created TCE table This is an extension for KVM_CAP_SPAPR_TCE which only supports 32bit windows, described in 4.62 KVM_CREATE_SPAPR_TCE -This capability uses extended struct in ioctl interface: +This capability uses extended struct in ioctl interface:: -/* for KVM_CAP_SPAPR_TCE_64 */ -struct kvm_create_spapr_tce_64 { + /* for KVM_CAP_SPAPR_TCE_64 */ + struct kvm_create_spapr_tce_64 { __u64 liobn; __u32 page_shift; __u32 flags; __u64 offset; /* in pages */ __u64 size; /* in pages */ -}; + }; The aim of extension is to support an additional bigger DMA window with a variable page size. @@ -3387,12 +3720,13 @@ of IOMMU pages. The rest of functionality is identical to KVM_CREATE_SPAPR_TCE. 4.99 KVM_REINJECT_CONTROL +------------------------- -Capability: KVM_CAP_REINJECT_CONTROL -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_reinject_control (in) -Returns: 0 on success, +:Capability: KVM_CAP_REINJECT_CONTROL +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_reinject_control (in) +:Returns: 0 on success, -EFAULT if struct kvm_reinject_control cannot be read, -ENXIO if KVM_CREATE_PIT or KVM_CREATE_PIT2 didn't succeed earlier. @@ -3402,21 +3736,24 @@ vector(s) that i8254 injects. Reinject mode dequeues a tick and injects its interrupt whenever there isn't a pending interrupt from i8254. !reinject mode injects an interrupt as soon as a tick arrives. -struct kvm_reinject_control { +:: + + struct kvm_reinject_control { __u8 pit_reinject; __u8 reserved[31]; -}; + }; pit_reinject = 0 (!reinject mode) is recommended, unless running an old operating system that uses the PIT for timing (e.g. Linux 2.4.x). 4.100 KVM_PPC_CONFIGURE_V3_MMU +------------------------------ -Capability: KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 -Architectures: ppc -Type: vm ioctl -Parameters: struct kvm_ppc_mmuv3_cfg (in) -Returns: 0 on success, +:Capability: KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 +:Architectures: ppc +:Type: vm ioctl +:Parameters: struct kvm_ppc_mmuv3_cfg (in) +:Returns: 0 on success, -EFAULT if struct kvm_ppc_mmuv3_cfg cannot be read, -EINVAL if the configuration is invalid @@ -3424,10 +3761,12 @@ This ioctl controls whether the guest will use radix or HPT (hashed page table) translation, and sets the pointer to the process table for the guest. -struct kvm_ppc_mmuv3_cfg { +:: + + struct kvm_ppc_mmuv3_cfg { __u64 flags; __u64 process_table; -}; + }; There are two bits that can be set in flags; KVM_PPC_MMUV3_RADIX and KVM_PPC_MMUV3_GTSE. KVM_PPC_MMUV3_RADIX, if set, configures the guest @@ -3442,12 +3781,13 @@ as the second doubleword of the partition table entry, as defined in the Power ISA V3.00, Book III section 5.7.6.1. 4.101 KVM_PPC_GET_RMMU_INFO +--------------------------- -Capability: KVM_CAP_PPC_RADIX_MMU -Architectures: ppc -Type: vm ioctl -Parameters: struct kvm_ppc_rmmu_info (out) -Returns: 0 on success, +:Capability: KVM_CAP_PPC_RADIX_MMU +:Architectures: ppc +:Type: vm ioctl +:Parameters: struct kvm_ppc_rmmu_info (out) +:Returns: 0 on success, -EFAULT if struct kvm_ppc_rmmu_info cannot be written, -EINVAL if no useful information can be returned @@ -3456,14 +3796,16 @@ containing supported radix tree geometries, and (b) a list that maps page sizes to put in the "AP" (actual page size) field for the tlbie (TLB invalidate entry) instruction. -struct kvm_ppc_rmmu_info { +:: + + struct kvm_ppc_rmmu_info { struct kvm_ppc_radix_geom { __u8 page_shift; __u8 level_bits[4]; __u8 pad[3]; } geometries[8]; __u32 ap_encodings[8]; -}; + }; The geometries[] field gives up to 8 supported geometries for the radix page table, in terms of the log base 2 of the smallest page @@ -3476,19 +3818,54 @@ encodings, encoded with the AP value in the top 3 bits and the log base 2 of the page size in the bottom 6 bits. 4.102 KVM_PPC_RESIZE_HPT_PREPARE +-------------------------------- -Capability: KVM_CAP_SPAPR_RESIZE_HPT -Architectures: powerpc -Type: vm ioctl -Parameters: struct kvm_ppc_resize_hpt (in) -Returns: 0 on successful completion, +:Capability: KVM_CAP_SPAPR_RESIZE_HPT +:Architectures: powerpc +:Type: vm ioctl +:Parameters: struct kvm_ppc_resize_hpt (in) +:Returns: 0 on successful completion, >0 if a new HPT is being prepared, the value is an estimated - number of milliseconds until preparation is complete + number of milliseconds until preparation is complete, -EFAULT if struct kvm_reinject_control cannot be read, - -EINVAL if the supplied shift or flags are invalid - -ENOMEM if unable to allocate the new HPT - -ENOSPC if there was a hash collision when moving existing - HPT entries to the new HPT + -EINVAL if the supplied shift or flags are invalid, + -ENOMEM if unable to allocate the new HPT, + -ENOSPC if there was a hash collision + +:: + + struct kvm_ppc_rmmu_info { + struct kvm_ppc_radix_geom { + __u8 page_shift; + __u8 level_bits[4]; + __u8 pad[3]; + } geometries[8]; + __u32 ap_encodings[8]; + }; + +The geometries[] field gives up to 8 supported geometries for the +radix page table, in terms of the log base 2 of the smallest page +size, and the number of bits indexed at each level of the tree, from +the PTE level up to the PGD level in that order. Any unused entries +will have 0 in the page_shift field. + +The ap_encodings gives the supported page sizes and their AP field +encodings, encoded with the AP value in the top 3 bits and the log +base 2 of the page size in the bottom 6 bits. + +4.102 KVM_PPC_RESIZE_HPT_PREPARE +-------------------------------- + +:Capability: KVM_CAP_SPAPR_RESIZE_HPT +:Architectures: powerpc +:Type: vm ioctl +:Parameters: struct kvm_ppc_resize_hpt (in) +:Returns: 0 on successful completion, + >0 if a new HPT is being prepared, the value is an estimated + number of milliseconds until preparation is complete, + -EFAULT if struct kvm_reinject_control cannot be read, + -EINVAL if the supplied shift or flags are invalid,when moving existing + HPT entries to the new HPT, -EIO on other error conditions Used to implement the PAPR extension for runtime resizing of a guest's @@ -3506,6 +3883,7 @@ requested in the parameters, discards the existing pending HPT and creates a new one as above. If called when there is a pending HPT of the size requested, will: + * If preparation of the pending HPT is already complete, return 0 * If preparation of the pending HPT has failed, return an error code, then discard the pending HPT. @@ -3522,26 +3900,29 @@ Normally this will be called repeatedly with the same parameters until it returns <= 0. The first call will initiate preparation, subsequent ones will monitor preparation until it completes or fails. -struct kvm_ppc_resize_hpt { +:: + + struct kvm_ppc_resize_hpt { __u64 flags; __u32 shift; __u32 pad; -}; + }; 4.103 KVM_PPC_RESIZE_HPT_COMMIT +------------------------------- -Capability: KVM_CAP_SPAPR_RESIZE_HPT -Architectures: powerpc -Type: vm ioctl -Parameters: struct kvm_ppc_resize_hpt (in) -Returns: 0 on successful completion, +:Capability: KVM_CAP_SPAPR_RESIZE_HPT +:Architectures: powerpc +:Type: vm ioctl +:Parameters: struct kvm_ppc_resize_hpt (in) +:Returns: 0 on successful completion, -EFAULT if struct kvm_reinject_control cannot be read, - -EINVAL if the supplied shift or flags are invalid + -EINVAL if the supplied shift or flags are invalid, -ENXIO is there is no pending HPT, or the pending HPT doesn't - have the requested size - -EBUSY if the pending HPT is not fully prepared + have the requested size, + -EBUSY if the pending HPT is not fully prepared, -ENOSPC if there was a hash collision when moving existing - HPT entries to the new HPT + HPT entries to the new HPT, -EIO on other error conditions Used to implement the PAPR extension for runtime resizing of a guest's @@ -3564,31 +3945,35 @@ HPT and the previous HPT will be discarded. On failure, the guest will still be operating on its previous HPT. -struct kvm_ppc_resize_hpt { +:: + + struct kvm_ppc_resize_hpt { __u64 flags; __u32 shift; __u32 pad; -}; + }; 4.104 KVM_X86_GET_MCE_CAP_SUPPORTED +----------------------------------- -Capability: KVM_CAP_MCE -Architectures: x86 -Type: system ioctl -Parameters: u64 mce_cap (out) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_MCE +:Architectures: x86 +:Type: system ioctl +:Parameters: u64 mce_cap (out) +:Returns: 0 on success, -1 on error Returns supported MCE capabilities. The u64 mce_cap parameter has the same format as the MSR_IA32_MCG_CAP register. Supported capabilities will have the corresponding bits set. 4.105 KVM_X86_SETUP_MCE +----------------------- -Capability: KVM_CAP_MCE -Architectures: x86 -Type: vcpu ioctl -Parameters: u64 mcg_cap (in) -Returns: 0 on success, +:Capability: KVM_CAP_MCE +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: u64 mcg_cap (in) +:Returns: 0 on success, -EFAULT if u64 mcg_cap cannot be read, -EINVAL if the requested number of banks is invalid, -EINVAL if requested MCE capability is not supported. @@ -3601,20 +3986,21 @@ checking for KVM_CAP_MCE. The supported capabilities can be retrieved with KVM_X86_GET_MCE_CAP_SUPPORTED. 4.106 KVM_X86_SET_MCE +--------------------- -Capability: KVM_CAP_MCE -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_x86_mce (in) -Returns: 0 on success, +:Capability: KVM_CAP_MCE +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_x86_mce (in) +:Returns: 0 on success, -EFAULT if struct kvm_x86_mce cannot be read, -EINVAL if the bank number is invalid, -EINVAL if VAL bit is not set in status field. Inject a machine check error (MCE) into the guest. The input -parameter is: +parameter is:: -struct kvm_x86_mce { + struct kvm_x86_mce { __u64 status; __u64 addr; __u64 misc; @@ -3622,7 +4008,7 @@ struct kvm_x86_mce { __u8 bank; __u8 pad1[7]; __u64 pad2[3]; -}; + }; If the MCE being reported is an uncorrected error, KVM will inject it as an MCE exception into the guest. If the guest @@ -3634,15 +4020,17 @@ store it in the corresponding bank (provided this bank is not holding a previously reported uncorrected error). 4.107 KVM_S390_GET_CMMA_BITS +---------------------------- -Capability: KVM_CAP_S390_CMMA_MIGRATION -Architectures: s390 -Type: vm ioctl -Parameters: struct kvm_s390_cmma_log (in, out) -Returns: 0 on success, a negative value on error +:Capability: KVM_CAP_S390_CMMA_MIGRATION +:Architectures: s390 +:Type: vm ioctl +:Parameters: struct kvm_s390_cmma_log (in, out) +:Returns: 0 on success, a negative value on error This ioctl is used to get the values of the CMMA bits on the s390 architecture. It is meant to be used in two scenarios: + - During live migration to save the CMMA values. Live migration needs to be enabled via the KVM_REQ_START_MIGRATION VM property. - To non-destructively peek at the CMMA values, with the flag @@ -3652,9 +4040,12 @@ The ioctl takes parameters via the kvm_s390_cmma_log struct. The desired values are written to a buffer whose location is indicated via the "values" member in the kvm_s390_cmma_log struct. The values in the input struct are also updated as needed. + Each CMMA value takes up one byte. -struct kvm_s390_cmma_log { +:: + + struct kvm_s390_cmma_log { __u64 start_gfn; __u32 count; __u32 flags; @@ -3663,7 +4054,7 @@ struct kvm_s390_cmma_log { __u64 mask; }; __u64 values; -}; + }; start_gfn is the number of the first guest frame whose CMMA values are to be retrieved, @@ -3724,12 +4115,13 @@ KVM_S390_CMMA_PEEK is not set but migration mode was not enabled, with present for the addresses (e.g. when using hugepages). 4.108 KVM_S390_SET_CMMA_BITS +---------------------------- -Capability: KVM_CAP_S390_CMMA_MIGRATION -Architectures: s390 -Type: vm ioctl -Parameters: struct kvm_s390_cmma_log (in) -Returns: 0 on success, a negative value on error +:Capability: KVM_CAP_S390_CMMA_MIGRATION +:Architectures: s390 +:Type: vm ioctl +:Parameters: struct kvm_s390_cmma_log (in) +:Returns: 0 on success, a negative value on error This ioctl is used to set the values of the CMMA bits on the s390 architecture. It is meant to be used during live migration to restore @@ -3737,16 +4129,18 @@ the CMMA values, but there are no restrictions on its use. The ioctl takes parameters via the kvm_s390_cmma_values struct. Each CMMA value takes up one byte. -struct kvm_s390_cmma_log { +:: + + struct kvm_s390_cmma_log { __u64 start_gfn; __u32 count; __u32 flags; union { __u64 remaining; __u64 mask; - }; + }; __u64 values; -}; + }; start_gfn indicates the starting guest frame number, @@ -3769,26 +4163,27 @@ or if no page table is present for the addresses (e.g. when using hugepages). 4.109 KVM_PPC_GET_CPU_CHAR +-------------------------- -Capability: KVM_CAP_PPC_GET_CPU_CHAR -Architectures: powerpc -Type: vm ioctl -Parameters: struct kvm_ppc_cpu_char (out) -Returns: 0 on successful completion +:Capability: KVM_CAP_PPC_GET_CPU_CHAR +:Architectures: powerpc +:Type: vm ioctl +:Parameters: struct kvm_ppc_cpu_char (out) +:Returns: 0 on successful completion, -EFAULT if struct kvm_ppc_cpu_char cannot be written This ioctl gives userspace information about certain characteristics of the CPU relating to speculative execution of instructions and possible information leakage resulting from speculative execution (see CVE-2017-5715, CVE-2017-5753 and CVE-2017-5754). The information is -returned in struct kvm_ppc_cpu_char, which looks like this: +returned in struct kvm_ppc_cpu_char, which looks like this:: -struct kvm_ppc_cpu_char { + struct kvm_ppc_cpu_char { __u64 character; /* characteristics of the CPU */ __u64 behaviour; /* recommended software behaviour */ __u64 character_mask; /* valid bits in character */ __u64 behaviour_mask; /* valid bits in behaviour */ -}; + }; For extensibility, the character_mask and behaviour_mask fields indicate which bits of character and behaviour have been filled in by @@ -3815,12 +4210,13 @@ These fields use the same bit definitions as the new H_GET_CPU_CHARACTERISTICS hypercall. 4.110 KVM_MEMORY_ENCRYPT_OP +--------------------------- -Capability: basic -Architectures: x86 -Type: system -Parameters: an opaque platform specific structure (in/out) -Returns: 0 on success; -1 on error +:Capability: basic +:Architectures: x86 +:Type: system +:Parameters: an opaque platform specific structure (in/out) +:Returns: 0 on success; -1 on error If the platform supports creating encrypted VMs then this ioctl can be used for issuing platform-specific memory encryption commands to manage those @@ -3831,12 +4227,13 @@ Currently, this ioctl is used for issuing Secure Encrypted Virtualization Documentation/virt/kvm/amd-memory-encryption.rst. 4.111 KVM_MEMORY_ENCRYPT_REG_REGION +----------------------------------- -Capability: basic -Architectures: x86 -Type: system -Parameters: struct kvm_enc_region (in) -Returns: 0 on success; -1 on error +:Capability: basic +:Architectures: x86 +:Type: system +:Parameters: struct kvm_enc_region (in) +:Returns: 0 on success; -1 on error This ioctl can be used to register a guest memory region which may contain encrypted data (e.g. guest RAM, SMRAM etc). @@ -3854,60 +4251,71 @@ swap or migrate (move) ciphertext pages. Hence, for now we pin the guest memory region registered with the ioctl. 4.112 KVM_MEMORY_ENCRYPT_UNREG_REGION +------------------------------------- -Capability: basic -Architectures: x86 -Type: system -Parameters: struct kvm_enc_region (in) -Returns: 0 on success; -1 on error +:Capability: basic +:Architectures: x86 +:Type: system +:Parameters: struct kvm_enc_region (in) +:Returns: 0 on success; -1 on error This ioctl can be used to unregister the guest memory region registered with KVM_MEMORY_ENCRYPT_REG_REGION ioctl above. 4.113 KVM_HYPERV_EVENTFD +------------------------ -Capability: KVM_CAP_HYPERV_EVENTFD -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_hyperv_eventfd (in) +:Capability: KVM_CAP_HYPERV_EVENTFD +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_hyperv_eventfd (in) This ioctl (un)registers an eventfd to receive notifications from the guest on the specified Hyper-V connection id through the SIGNAL_EVENT hypercall, without causing a user exit. SIGNAL_EVENT hypercall with non-zero event flag number (bits 24-31) still triggers a KVM_EXIT_HYPERV_HCALL user exit. -struct kvm_hyperv_eventfd { +:: + + struct kvm_hyperv_eventfd { __u32 conn_id; __s32 fd; __u32 flags; __u32 padding[3]; -}; + }; -The conn_id field should fit within 24 bits: +The conn_id field should fit within 24 bits:: -#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff + #define KVM_HYPERV_CONN_ID_MASK 0x00ffffff -The acceptable values for the flags field are: +The acceptable values for the flags field are:: -#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) + #define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) -Returns: 0 on success, - -EINVAL if conn_id or flags is outside the allowed range - -ENOENT on deassign if the conn_id isn't registered - -EEXIST on assign if the conn_id is already registered +:Returns: 0 on success, + -EINVAL if conn_id or flags is outside the allowed range, + -ENOENT on deassign if the conn_id isn't registered, + -EEXIST on assign if the conn_id is already registered 4.114 KVM_GET_NESTED_STATE +-------------------------- + +:Capability: KVM_CAP_NESTED_STATE +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_nested_state (in/out) +:Returns: 0 on success, -1 on error -Capability: KVM_CAP_NESTED_STATE -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_nested_state (in/out) -Returns: 0 on success, -1 on error Errors: - E2BIG: the total state size exceeds the value of 'size' specified by + + ===== ============================================================= + E2BIG the total state size exceeds the value of 'size' specified by the user; the size required will be written into size. + ===== ============================================================= -struct kvm_nested_state { +:: + + struct kvm_nested_state { __u16 flags; __u16 format; __u32 size; @@ -3924,33 +4332,33 @@ struct kvm_nested_state { struct kvm_vmx_nested_state_data vmx[0]; struct kvm_svm_nested_state_data svm[0]; } data; -}; + }; -#define KVM_STATE_NESTED_GUEST_MODE 0x00000001 -#define KVM_STATE_NESTED_RUN_PENDING 0x00000002 -#define KVM_STATE_NESTED_EVMCS 0x00000004 + #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 + #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 + #define KVM_STATE_NESTED_EVMCS 0x00000004 -#define KVM_STATE_NESTED_FORMAT_VMX 0 -#define KVM_STATE_NESTED_FORMAT_SVM 1 + #define KVM_STATE_NESTED_FORMAT_VMX 0 + #define KVM_STATE_NESTED_FORMAT_SVM 1 -#define KVM_STATE_NESTED_VMX_VMCS_SIZE 0x1000 + #define KVM_STATE_NESTED_VMX_VMCS_SIZE 0x1000 -#define KVM_STATE_NESTED_VMX_SMM_GUEST_MODE 0x00000001 -#define KVM_STATE_NESTED_VMX_SMM_VMXON 0x00000002 + #define KVM_STATE_NESTED_VMX_SMM_GUEST_MODE 0x00000001 + #define KVM_STATE_NESTED_VMX_SMM_VMXON 0x00000002 -struct kvm_vmx_nested_state_hdr { + struct kvm_vmx_nested_state_hdr { __u64 vmxon_pa; __u64 vmcs12_pa; struct { __u16 flags; } smm; -}; + }; -struct kvm_vmx_nested_state_data { + struct kvm_vmx_nested_state_data { __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; __u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; -}; + }; This ioctl copies the vcpu's nested virtualization state from the kernel to userspace. @@ -3959,24 +4367,26 @@ The maximum size of the state can be retrieved by passing KVM_CAP_NESTED_STATE to the KVM_CHECK_EXTENSION ioctl(). 4.115 KVM_SET_NESTED_STATE +-------------------------- -Capability: KVM_CAP_NESTED_STATE -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_nested_state (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_NESTED_STATE +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_nested_state (in) +:Returns: 0 on success, -1 on error This copies the vcpu's kvm_nested_state struct from userspace to the kernel. For the definition of struct kvm_nested_state, see KVM_GET_NESTED_STATE. 4.116 KVM_(UN)REGISTER_COALESCED_MMIO +------------------------------------- -Capability: KVM_CAP_COALESCED_MMIO (for coalesced mmio) - KVM_CAP_COALESCED_PIO (for coalesced pio) -Architectures: all -Type: vm ioctl -Parameters: struct kvm_coalesced_mmio_zone -Returns: 0 on success, < 0 on error +:Capability: KVM_CAP_COALESCED_MMIO (for coalesced mmio) + KVM_CAP_COALESCED_PIO (for coalesced pio) +:Architectures: all +:Type: vm ioctl +:Parameters: struct kvm_coalesced_mmio_zone +:Returns: 0 on success, < 0 on error Coalesced I/O is a performance optimization that defers hardware register write emulation so that userspace exits are avoided. It is @@ -3998,15 +4408,18 @@ between coalesced mmio and pio except that coalesced pio records accesses to I/O ports. 4.117 KVM_CLEAR_DIRTY_LOG (vm ioctl) +------------------------------------ + +:Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 +:Architectures: x86, arm, arm64, mips +:Type: vm ioctl +:Parameters: struct kvm_dirty_log (in) +:Returns: 0 on success, -1 on error -Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 -Architectures: x86, arm, arm64, mips -Type: vm ioctl -Parameters: struct kvm_dirty_log (in) -Returns: 0 on success, -1 on error +:: -/* for KVM_CLEAR_DIRTY_LOG */ -struct kvm_clear_dirty_log { + /* for KVM_CLEAR_DIRTY_LOG */ + struct kvm_clear_dirty_log { __u32 slot; __u32 num_pages; __u64 first_page; @@ -4014,7 +4427,7 @@ struct kvm_clear_dirty_log { void __user *dirty_bitmap; /* one bit per page */ __u64 padding; }; -}; + }; The ioctl clears the dirty status of pages in a memory slot, according to the bitmap that is passed in struct kvm_clear_dirty_log's dirty_bitmap @@ -4038,20 +4451,23 @@ However, it can always be used as long as KVM_CHECK_EXTENSION confirms that KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is present. 4.118 KVM_GET_SUPPORTED_HV_CPUID +-------------------------------- -Capability: KVM_CAP_HYPERV_CPUID -Architectures: x86 -Type: vcpu ioctl -Parameters: struct kvm_cpuid2 (in/out) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_HYPERV_CPUID +:Architectures: x86 +:Type: vcpu ioctl +:Parameters: struct kvm_cpuid2 (in/out) +:Returns: 0 on success, -1 on error + +:: -struct kvm_cpuid2 { + struct kvm_cpuid2 { __u32 nent; __u32 padding; struct kvm_cpuid_entry2 entries[0]; -}; + }; -struct kvm_cpuid_entry2 { + struct kvm_cpuid_entry2 { __u32 function; __u32 index; __u32 flags; @@ -4060,7 +4476,7 @@ struct kvm_cpuid_entry2 { __u32 ecx; __u32 edx; __u32 padding[3]; -}; + }; This ioctl returns x86 cpuid features leaves related to Hyper-V emulation in KVM. Userspace can use the information returned by this ioctl to construct @@ -4073,13 +4489,13 @@ KVM_GET_SUPPORTED_CPUID ioctl because some of them intersect with KVM feature leaves (0x40000000, 0x40000001). Currently, the following list of CPUID leaves are returned: - HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS - HYPERV_CPUID_INTERFACE - HYPERV_CPUID_VERSION - HYPERV_CPUID_FEATURES - HYPERV_CPUID_ENLIGHTMENT_INFO - HYPERV_CPUID_IMPLEMENT_LIMITS - HYPERV_CPUID_NESTED_FEATURES + - HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS + - HYPERV_CPUID_INTERFACE + - HYPERV_CPUID_VERSION + - HYPERV_CPUID_FEATURES + - HYPERV_CPUID_ENLIGHTMENT_INFO + - HYPERV_CPUID_IMPLEMENT_LIMITS + - HYPERV_CPUID_NESTED_FEATURES HYPERV_CPUID_NESTED_FEATURES leaf is only exposed when Enlightened VMCS was enabled on the corresponding vCPU (KVM_CAP_HYPERV_ENLIGHTENED_VMCS). @@ -4095,17 +4511,25 @@ number of valid entries in the 'entries' array, which is then filled. userspace should not expect to get any particular value there. 4.119 KVM_ARM_VCPU_FINALIZE +--------------------------- + +:Architectures: arm, arm64 +:Type: vcpu ioctl +:Parameters: int feature (in) +:Returns: 0 on success, -1 on error -Architectures: arm, arm64 -Type: vcpu ioctl -Parameters: int feature (in) -Returns: 0 on success, -1 on error Errors: - EPERM: feature not enabled, needs configuration, or already finalized - EINVAL: feature unknown or not present + + ====== ============================================================== + EPERM feature not enabled, needs configuration, or already finalized + EINVAL feature unknown or not present + ====== ============================================================== Recognised values for feature: + + ===== =========================================== arm64 KVM_ARM_VCPU_SVE (requires KVM_CAP_ARM_SVE) + ===== =========================================== Finalizes the configuration of the specified vcpu feature. @@ -4129,21 +4553,24 @@ See KVM_ARM_VCPU_INIT for details of vcpu features that require finalization using this ioctl. 4.120 KVM_SET_PMU_EVENT_FILTER +------------------------------ -Capability: KVM_CAP_PMU_EVENT_FILTER -Architectures: x86 -Type: vm ioctl -Parameters: struct kvm_pmu_event_filter (in) -Returns: 0 on success, -1 on error +:Capability: KVM_CAP_PMU_EVENT_FILTER +:Architectures: x86 +:Type: vm ioctl +:Parameters: struct kvm_pmu_event_filter (in) +:Returns: 0 on success, -1 on error -struct kvm_pmu_event_filter { +:: + + struct kvm_pmu_event_filter { __u32 action; __u32 nevents; __u32 fixed_counter_bitmap; __u32 flags; __u32 pad[4]; __u64 events[0]; -}; + }; This ioctl restricts the set of PMU events that the guest can program. The argument holds a list of events which will be allowed or denied. @@ -4154,20 +4581,26 @@ counters are controlled by the fixed_counter_bitmap. No flags are defined yet, the field must be zero. -Valid values for 'action': -#define KVM_PMU_EVENT_ALLOW 0 -#define KVM_PMU_EVENT_DENY 1 +Valid values for 'action':: + + #define KVM_PMU_EVENT_ALLOW 0 + #define KVM_PMU_EVENT_DENY 1 4.121 KVM_PPC_SVM_OFF +--------------------- + +:Capability: basic +:Architectures: powerpc +:Type: vm ioctl +:Parameters: none +:Returns: 0 on successful completion, -Capability: basic -Architectures: powerpc -Type: vm ioctl -Parameters: none -Returns: 0 on successful completion, Errors: - EINVAL: if ultravisor failed to terminate the secure guest - ENOMEM: if hypervisor failed to allocate new radix page tables for guest + + ====== ================================================================ + EINVAL if ultravisor failed to terminate the secure guest + ENOMEM if hypervisor failed to allocate new radix page tables for guest + ====== ================================================================ This ioctl is used to turn off the secure mode of the guest or transition the guest from secure mode to normal mode. This is invoked when the guest @@ -4214,7 +4647,7 @@ into ESA mode. This reset is a superset of the initial reset. 5. The kvm_run structure ------------------------- +======================== Application code obtains a pointer to the kvm_run structure by mmap()ing a vcpu fd. From that point, application code can control @@ -4222,13 +4655,17 @@ execution by changing fields in kvm_run prior to calling the KVM_RUN ioctl, and obtain information about the reason KVM_RUN returned by looking up structure members. -struct kvm_run { +:: + + struct kvm_run { /* in */ __u8 request_interrupt_window; Request that KVM_RUN return when it becomes possible to inject external interrupts into the guest. Useful in conjunction with KVM_INTERRUPT. +:: + __u8 immediate_exit; This field is polled once when KVM_RUN starts; if non-zero, KVM_RUN @@ -4240,6 +4677,8 @@ a signal handler that sets run->immediate_exit to a non-zero value. This field is ignored if KVM_CAP_IMMEDIATE_EXIT is not available. +:: + __u8 padding1[6]; /* out */ @@ -4249,16 +4688,22 @@ When KVM_RUN has returned successfully (return value 0), this informs application code why KVM_RUN has returned. Allowable values for this field are detailed below. +:: + __u8 ready_for_interrupt_injection; If request_interrupt_window has been specified, this field indicates an interrupt can be injected now with KVM_INTERRUPT. +:: + __u8 if_flag; The value of the current interrupt flag. Only valid if in-kernel local APIC is not used. +:: + __u16 flags; More architecture-specific flags detailing state of the VCPU that may @@ -4266,17 +4711,23 @@ affect the device's behavior. The only currently defined flag is KVM_RUN_X86_SMM, which is valid on x86 machines and is set if the VCPU is in system management mode. +:: + /* in (pre_kvm_run), out (post_kvm_run) */ __u64 cr8; The value of the cr8 register. Only valid if in-kernel local APIC is not used. Both input and output. +:: + __u64 apic_base; The value of the APIC BASE msr. Only valid if in-kernel local APIC is not used. Both input and output. +:: + union { /* KVM_EXIT_UNKNOWN */ struct { @@ -4287,6 +4738,8 @@ If exit_reason is KVM_EXIT_UNKNOWN, the vcpu has exited due to unknown reasons. Further architecture-specific information is available in hardware_exit_reason. +:: + /* KVM_EXIT_FAIL_ENTRY */ struct { __u64 hardware_entry_failure_reason; @@ -4296,6 +4749,8 @@ If exit_reason is KVM_EXIT_FAIL_ENTRY, the vcpu could not be run due to unknown reasons. Further architecture-specific information is available in hardware_entry_failure_reason. +:: + /* KVM_EXIT_EXCEPTION */ struct { __u32 exception; @@ -4304,10 +4759,12 @@ available in hardware_entry_failure_reason. Unused. +:: + /* KVM_EXIT_IO */ struct { -#define KVM_EXIT_IO_IN 0 -#define KVM_EXIT_IO_OUT 1 + #define KVM_EXIT_IO_IN 0 + #define KVM_EXIT_IO_OUT 1 __u8 direction; __u8 size; /* bytes */ __u16 port; @@ -4321,6 +4778,8 @@ data_offset describes where the data is located (KVM_EXIT_IO_OUT) or where kvm expects application code to place the data for the next KVM_RUN invocation (KVM_EXIT_IO_IN). Data format is a packed array. +:: + /* KVM_EXIT_DEBUG */ struct { struct kvm_debug_exit_arch arch; @@ -4329,6 +4788,8 @@ KVM_RUN invocation (KVM_EXIT_IO_IN). Data format is a packed array. If the exit_reason is KVM_EXIT_DEBUG, then a vcpu is processing a debug event for which architecture specific information is returned. +:: + /* KVM_EXIT_MMIO */ struct { __u64 phys_addr; @@ -4346,14 +4807,19 @@ The 'data' member contains, in its first 'len' bytes, the value as it would appear if the VCPU performed a load or store of the appropriate width directly to the byte array. -NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR and +.. note:: + + For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR and KVM_EXIT_EPR the corresponding + operations are complete (and guest state is consistent) only after userspace has re-entered the kernel with KVM_RUN. The kernel side will first finish incomplete operations and then check for pending signals. Userspace can re-enter the guest with an unmasked signal pending to complete pending operations. +:: + /* KVM_EXIT_HYPERCALL */ struct { __u64 nr; @@ -4365,7 +4831,10 @@ pending operations. Unused. This was once used for 'hypercall to userspace'. To implement such functionality, use KVM_EXIT_IO (x86) or KVM_EXIT_MMIO (all except s390). -Note KVM_EXIT_IO is significantly faster than KVM_EXIT_MMIO. + +.. note:: KVM_EXIT_IO is significantly faster than KVM_EXIT_MMIO. + +:: /* KVM_EXIT_TPR_ACCESS */ struct { @@ -4376,6 +4845,8 @@ Note KVM_EXIT_IO is significantly faster than KVM_EXIT_MMIO. To be documented (KVM_TPR_ACCESS_REPORTING). +:: + /* KVM_EXIT_S390_SIEIC */ struct { __u8 icptcode; @@ -4387,16 +4858,20 @@ To be documented (KVM_TPR_ACCESS_REPORTING). s390 specific. +:: + /* KVM_EXIT_S390_RESET */ -#define KVM_S390_RESET_POR 1 -#define KVM_S390_RESET_CLEAR 2 -#define KVM_S390_RESET_SUBSYSTEM 4 -#define KVM_S390_RESET_CPU_INIT 8 -#define KVM_S390_RESET_IPL 16 + #define KVM_S390_RESET_POR 1 + #define KVM_S390_RESET_CLEAR 2 + #define KVM_S390_RESET_SUBSYSTEM 4 + #define KVM_S390_RESET_CPU_INIT 8 + #define KVM_S390_RESET_IPL 16 __u64 s390_reset_flags; s390 specific. +:: + /* KVM_EXIT_S390_UCONTROL */ struct { __u64 trans_exc_code; @@ -4411,6 +4886,8 @@ in the cpu's lowcore are presented here as defined by the z Architecture Principles of Operation Book in the Chapter for Dynamic Address Translation (DAT) +:: + /* KVM_EXIT_DCR */ struct { __u32 dcrn; @@ -4420,6 +4897,8 @@ Principles of Operation Book in the Chapter for Dynamic Address Translation Deprecated - was used for 440 KVM. +:: + /* KVM_EXIT_OSI */ struct { __u64 gprs[32]; @@ -4433,6 +4912,8 @@ Userspace can now handle the hypercall and when it's done modify the gprs as necessary. Upon guest entry all guest GPRs will then be replaced by the values in this struct. +:: + /* KVM_EXIT_PAPR_HCALL */ struct { __u64 nr; @@ -4450,6 +4931,8 @@ The possible hypercalls are defined in the Power Architecture Platform Requirements (PAPR) document available from www.power.org (free developer registration required to access it). +:: + /* KVM_EXIT_S390_TSCH */ struct { __u16 subchannel_id; @@ -4466,6 +4949,8 @@ interrupt for the target subchannel has been dequeued and subchannel_id, subchannel_nr, io_int_parm and io_int_word contain the parameters for that interrupt. ipb is needed for instruction parameter decoding. +:: + /* KVM_EXIT_EPR */ struct { __u32 epr; @@ -4485,11 +4970,13 @@ It gets triggered whenever both KVM_CAP_PPC_EPR are enabled and an external interrupt has just been delivered into the guest. User space should put the acknowledged interrupt vector into the 'epr' field. +:: + /* KVM_EXIT_SYSTEM_EVENT */ struct { -#define KVM_SYSTEM_EVENT_SHUTDOWN 1 -#define KVM_SYSTEM_EVENT_RESET 2 -#define KVM_SYSTEM_EVENT_CRASH 3 + #define KVM_SYSTEM_EVENT_SHUTDOWN 1 + #define KVM_SYSTEM_EVENT_RESET 2 + #define KVM_SYSTEM_EVENT_CRASH 3 __u32 type; __u64 flags; } system_event; @@ -4502,18 +4989,21 @@ the system-level event type. The 'flags' field describes architecture specific flags for the system-level event. Valid values for 'type' are: - KVM_SYSTEM_EVENT_SHUTDOWN -- the guest has requested a shutdown of the + + - KVM_SYSTEM_EVENT_SHUTDOWN -- the guest has requested a shutdown of the VM. Userspace is not obliged to honour this, and if it does honour this does not need to destroy the VM synchronously (ie it may call KVM_RUN again before shutdown finally occurs). - KVM_SYSTEM_EVENT_RESET -- the guest has requested a reset of the VM. + - KVM_SYSTEM_EVENT_RESET -- the guest has requested a reset of the VM. As with SHUTDOWN, userspace can choose to ignore the request, or to schedule the reset to occur in the future and may call KVM_RUN again. - KVM_SYSTEM_EVENT_CRASH -- the guest crash occurred and the guest + - KVM_SYSTEM_EVENT_CRASH -- the guest crash occurred and the guest has requested a crash condition maintenance. Userspace can choose to ignore the request, or to gather VM memory core dump and/or reset/shutdown of the VM. +:: + /* KVM_EXIT_IOAPIC_EOI */ struct { __u8 vector; @@ -4526,9 +5016,11 @@ the userspace IOAPIC should process the EOI and retrigger the interrupt if it is still asserted. Vector is the LAPIC interrupt vector for which the EOI was received. +:: + struct kvm_hyperv_exit { -#define KVM_EXIT_HYPERV_SYNIC 1 -#define KVM_EXIT_HYPERV_HCALL 2 + #define KVM_EXIT_HYPERV_SYNIC 1 + #define KVM_EXIT_HYPERV_HCALL 2 __u32 type; union { struct { @@ -4546,14 +5038,20 @@ EOI was received. }; /* KVM_EXIT_HYPERV */ struct kvm_hyperv_exit hyperv; + Indicates that the VCPU exits into userspace to process some tasks related to Hyper-V emulation. + Valid values for 'type' are: - KVM_EXIT_HYPERV_SYNIC -- synchronously notify user-space about + + - KVM_EXIT_HYPERV_SYNIC -- synchronously notify user-space about + Hyper-V SynIC state change. Notification is used to remap SynIC event/message pages and to enable/disable SynIC messages/events processing in userspace. +:: + /* KVM_EXIT_ARM_NISV */ struct { __u64 esr_iss; @@ -4587,6 +5085,8 @@ Note that KVM does not skip the faulting instruction as it does for KVM_EXIT_MMIO, but userspace has to emulate any change to the processing state if it decides to decode and emulate the instruction. +:: + /* Fix the size of the union. */ char padding[256]; }; @@ -4611,18 +5111,20 @@ avoid some system call overhead if userspace has to handle the exit. Userspace can query the validity of the structure by checking kvm_valid_regs for specific bits. These bits are architecture specific and usually define the validity of a groups of registers. (e.g. one bit - for general purpose registers) +for general purpose registers) Please note that the kernel is allowed to use the kvm_run structure as the primary storage for certain register types. Therefore, the kernel may use the values in kvm_run even if the corresponding bit in kvm_dirty_regs is not set. -}; +:: + + }; 6. Capabilities that can be enabled on vCPUs --------------------------------------------- +============================================ There are certain capabilities that change the behavior of the virtual CPU or the virtual machine when enabled. To enable them, please see section 4.37. @@ -4631,23 +5133,28 @@ the virtual machine is when enabling them. The following information is provided along with the description: - Architectures: which instruction set architectures provide this ioctl. + Architectures: + which instruction set architectures provide this ioctl. x86 includes both i386 and x86_64. - Target: whether this is a per-vcpu or per-vm capability. + Target: + whether this is a per-vcpu or per-vm capability. - Parameters: what parameters are accepted by the capability. + Parameters: + what parameters are accepted by the capability. - Returns: the return value. General error numbers (EBADF, ENOMEM, EINVAL) + Returns: + the return value. General error numbers (EBADF, ENOMEM, EINVAL) are not detailed, but errors with specific meanings are. 6.1 KVM_CAP_PPC_OSI +------------------- -Architectures: ppc -Target: vcpu -Parameters: none -Returns: 0 on success; -1 on error +:Architectures: ppc +:Target: vcpu +:Parameters: none +:Returns: 0 on success; -1 on error This capability enables interception of OSI hypercalls that otherwise would be treated as normal system calls to be injected into the guest. OSI hypercalls @@ -4658,11 +5165,12 @@ When this capability is enabled, KVM_EXIT_OSI can occur. 6.2 KVM_CAP_PPC_PAPR +-------------------- -Architectures: ppc -Target: vcpu -Parameters: none -Returns: 0 on success; -1 on error +:Architectures: ppc +:Target: vcpu +:Parameters: none +:Returns: 0 on success; -1 on error This capability enables interception of PAPR hypercalls. PAPR hypercalls are done using the hypercall instruction "sc 1". @@ -4678,18 +5186,21 @@ When this capability is enabled, KVM_EXIT_PAPR_HCALL can occur. 6.3 KVM_CAP_SW_TLB +------------------ + +:Architectures: ppc +:Target: vcpu +:Parameters: args[0] is the address of a struct kvm_config_tlb +:Returns: 0 on success; -1 on error -Architectures: ppc -Target: vcpu -Parameters: args[0] is the address of a struct kvm_config_tlb -Returns: 0 on success; -1 on error +:: -struct kvm_config_tlb { + struct kvm_config_tlb { __u64 params; __u64 array; __u32 mmu_type; __u32 array_len; -}; + }; Configures the virtual CPU's TLB array, establishing a shared memory area between userspace and KVM. The "params" and "array" fields are userspace @@ -4708,6 +5219,7 @@ to tell KVM which entries have been changed, prior to calling KVM_RUN again on this vcpu. For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV: + - The "params" field is of type "struct kvm_book3e_206_tlb_params". - The "array" field points to an array of type "struct kvm_book3e_206_tlb_entry". @@ -4721,11 +5233,12 @@ For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV: hardware ignores this value for TLB0. 6.4 KVM_CAP_S390_CSS_SUPPORT +---------------------------- -Architectures: s390 -Target: vcpu -Parameters: none -Returns: 0 on success; -1 on error +:Architectures: s390 +:Target: vcpu +:Parameters: none +:Returns: 0 on success; -1 on error This capability enables support for handling of channel I/O instructions. @@ -4739,11 +5252,12 @@ Note that even though this capability is enabled per-vcpu, the complete virtual machine is affected. 6.5 KVM_CAP_PPC_EPR +------------------- -Architectures: ppc -Target: vcpu -Parameters: args[0] defines whether the proxy facility is active -Returns: 0 on success; -1 on error +:Architectures: ppc +:Target: vcpu +:Parameters: args[0] defines whether the proxy facility is active +:Returns: 0 on success; -1 on error This capability enables or disables the delivery of interrupts through the external proxy facility. @@ -4757,62 +5271,70 @@ When disabled (args[0] == 0), behavior is as if this facility is unsupported. When this capability is enabled, KVM_EXIT_EPR can occur. 6.6 KVM_CAP_IRQ_MPIC +-------------------- -Architectures: ppc -Parameters: args[0] is the MPIC device fd - args[1] is the MPIC CPU number for this vcpu +:Architectures: ppc +:Parameters: args[0] is the MPIC device fd; + args[1] is the MPIC CPU number for this vcpu This capability connects the vcpu to an in-kernel MPIC device. 6.7 KVM_CAP_IRQ_XICS +-------------------- -Architectures: ppc -Target: vcpu -Parameters: args[0] is the XICS device fd - args[1] is the XICS CPU number (server ID) for this vcpu +:Architectures: ppc +:Target: vcpu +:Parameters: args[0] is the XICS device fd; + args[1] is the XICS CPU number (server ID) for this vcpu This capability connects the vcpu to an in-kernel XICS device. 6.8 KVM_CAP_S390_IRQCHIP +------------------------ -Architectures: s390 -Target: vm -Parameters: none +:Architectures: s390 +:Target: vm +:Parameters: none This capability enables the in-kernel irqchip for s390. Please refer to "4.24 KVM_CREATE_IRQCHIP" for details. 6.9 KVM_CAP_MIPS_FPU +-------------------- -Architectures: mips -Target: vcpu -Parameters: args[0] is reserved for future use (should be 0). +:Architectures: mips +:Target: vcpu +:Parameters: args[0] is reserved for future use (should be 0). This capability allows the use of the host Floating Point Unit by the guest. It allows the Config1.FP bit to be set to enable the FPU in the guest. Once this is -done the KVM_REG_MIPS_FPR_* and KVM_REG_MIPS_FCR_* registers can be accessed -(depending on the current guest FPU register mode), and the Status.FR, +done the ``KVM_REG_MIPS_FPR_*`` and ``KVM_REG_MIPS_FCR_*`` registers can be +accessed (depending on the current guest FPU register mode), and the Status.FR, Config5.FRE bits are accessible via the KVM API and also from the guest, depending on them being supported by the FPU. 6.10 KVM_CAP_MIPS_MSA +--------------------- -Architectures: mips -Target: vcpu -Parameters: args[0] is reserved for future use (should be 0). +:Architectures: mips +:Target: vcpu +:Parameters: args[0] is reserved for future use (should be 0). This capability allows the use of the MIPS SIMD Architecture (MSA) by the guest. It allows the Config3.MSAP bit to be set to enable the use of MSA by the guest. -Once this is done the KVM_REG_MIPS_VEC_* and KVM_REG_MIPS_MSA_* registers can be -accessed, and the Config5.MSAEn bit is accessible via the KVM API and also from -the guest. +Once this is done the ``KVM_REG_MIPS_VEC_*`` and ``KVM_REG_MIPS_MSA_*`` +registers can be accessed, and the Config5.MSAEn bit is accessible via the +KVM API and also from the guest. 6.74 KVM_CAP_SYNC_REGS -Architectures: s390, x86 -Target: s390: always enabled, x86: vcpu -Parameters: none -Returns: x86: KVM_CHECK_EXTENSION returns a bit-array indicating which register -sets are supported (bitfields defined in arch/x86/include/uapi/asm/kvm.h). +---------------------- + +:Architectures: s390, x86 +:Target: s390: always enabled, x86: vcpu +:Parameters: none +:Returns: x86: KVM_CHECK_EXTENSION returns a bit-array indicating which register + sets are supported + (bitfields defined in arch/x86/include/uapi/asm/kvm.h). As described above in the kvm_sync_regs struct info in section 5 (kvm_run): KVM_CAP_SYNC_REGS "allow[s] userspace to access certain guest registers @@ -4825,6 +5347,7 @@ userspace. For s390 specifics, please refer to the source code. For x86: + - the register sets to be copied out to kvm_run are selectable by userspace (rather that all sets being copied out for every exit). - vcpu_events are available in addition to regs and sregs. @@ -4841,23 +5364,26 @@ into the vCPU even if they've been modified. Unused bitfields in the bitarrays must be set to zero. -struct kvm_sync_regs { +:: + + struct kvm_sync_regs { struct kvm_regs regs; struct kvm_sregs sregs; struct kvm_vcpu_events events; -}; + }; 6.75 KVM_CAP_PPC_IRQ_XIVE +------------------------- -Architectures: ppc -Target: vcpu -Parameters: args[0] is the XIVE device fd - args[1] is the XIVE CPU number (server ID) for this vcpu +:Architectures: ppc +:Target: vcpu +:Parameters: args[0] is the XIVE device fd; + args[1] is the XIVE CPU number (server ID) for this vcpu This capability connects the vcpu to an in-kernel XIVE device. 7. Capabilities that can be enabled on VMs ------------------------------------------- +========================================== There are certain capabilities that change the behavior of the virtual machine when enabled. To enable them, please see section 4.37. Below @@ -4866,20 +5392,24 @@ is when enabling them. The following information is provided along with the description: - Architectures: which instruction set architectures provide this ioctl. + Architectures: + which instruction set architectures provide this ioctl. x86 includes both i386 and x86_64. - Parameters: what parameters are accepted by the capability. + Parameters: + what parameters are accepted by the capability. - Returns: the return value. General error numbers (EBADF, ENOMEM, EINVAL) + Returns: + the return value. General error numbers (EBADF, ENOMEM, EINVAL) are not detailed, but errors with specific meanings are. 7.1 KVM_CAP_PPC_ENABLE_HCALL +---------------------------- -Architectures: ppc -Parameters: args[0] is the sPAPR hcall number - args[1] is 0 to disable, 1 to enable in-kernel handling +:Architectures: ppc +:Parameters: args[0] is the sPAPR hcall number; + args[1] is 0 to disable, 1 to enable in-kernel handling This capability controls whether individual sPAPR hypercalls (hcalls) get handled by the kernel or not. Enabling or disabling in-kernel @@ -4897,13 +5427,15 @@ implementation, the KVM_ENABLE_CAP ioctl will fail with an EINVAL error. 7.2 KVM_CAP_S390_USER_SIGP +-------------------------- -Architectures: s390 -Parameters: none +:Architectures: s390 +:Parameters: none This capability controls which SIGP orders will be handled completely in user space. With this capability enabled, all fast orders will be handled completely in the kernel: + - SENSE - SENSE RUNNING - EXTERNAL CALL @@ -4917,48 +5449,52 @@ in the hardware prior to interception). If this capability is not enabled, the old way of handling SIGP orders is used (partially in kernel and user space). 7.3 KVM_CAP_S390_VECTOR_REGISTERS +--------------------------------- -Architectures: s390 -Parameters: none -Returns: 0 on success, negative value on error +:Architectures: s390 +:Parameters: none +:Returns: 0 on success, negative value on error Allows use of the vector registers introduced with z13 processor, and provides for the synchronization between host and user space. Will return -EINVAL if the machine does not support vectors. 7.4 KVM_CAP_S390_USER_STSI +-------------------------- -Architectures: s390 -Parameters: none +:Architectures: s390 +:Parameters: none This capability allows post-handlers for the STSI instruction. After initial handling in the kernel, KVM exits to user space with KVM_EXIT_S390_STSI to allow user space to insert further data. Before exiting to userspace, kvm handlers should fill in s390_stsi field of -vcpu->run: -struct { +vcpu->run:: + + struct { __u64 addr; __u8 ar; __u8 reserved; __u8 fc; __u8 sel1; __u16 sel2; -} s390_stsi; + } s390_stsi; -@addr - guest address of STSI SYSIB -@fc - function code -@sel1 - selector 1 -@sel2 - selector 2 -@ar - access register number + @addr - guest address of STSI SYSIB + @fc - function code + @sel1 - selector 1 + @sel2 - selector 2 + @ar - access register number KVM handlers should exit to userspace with rc = -EREMOTE. 7.5 KVM_CAP_SPLIT_IRQCHIP +------------------------- -Architectures: x86 -Parameters: args[0] - number of routes reserved for userspace IOAPICs -Returns: 0 on success, -1 on error +:Architectures: x86 +:Parameters: args[0] - number of routes reserved for userspace IOAPICs +:Returns: 0 on success, -1 on error Create a local apic for each processor in the kernel. This can be used instead of KVM_CREATE_IRQCHIP if the userspace VMM wishes to emulate the @@ -4975,24 +5511,26 @@ Fails if VCPU has already been created, or if the irqchip is already in the kernel (i.e. KVM_CREATE_IRQCHIP has already been called). 7.6 KVM_CAP_S390_RI +------------------- -Architectures: s390 -Parameters: none +:Architectures: s390 +:Parameters: none Allows use of runtime-instrumentation introduced with zEC12 processor. Will return -EINVAL if the machine does not support runtime-instrumentation. Will return -EBUSY if a VCPU has already been created. 7.7 KVM_CAP_X2APIC_API +---------------------- -Architectures: x86 -Parameters: args[0] - features that should be enabled -Returns: 0 on success, -EINVAL when args[0] contains invalid features +:Architectures: x86 +:Parameters: args[0] - features that should be enabled +:Returns: 0 on success, -EINVAL when args[0] contains invalid features -Valid feature flags in args[0] are +Valid feature flags in args[0] are:: -#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) -#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) + #define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) + #define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) Enabling KVM_X2APIC_API_USE_32BIT_IDS changes the behavior of KVM_SET_GSI_ROUTING, KVM_SIGNAL_MSI, KVM_SET_LAPIC, and KVM_GET_LAPIC, @@ -5006,9 +5544,10 @@ without interrupt remapping. This is undesirable in logical mode, where 0xff represents CPUs 0-7 in cluster 0. 7.8 KVM_CAP_S390_USER_INSTR0 +---------------------------- -Architectures: s390 -Parameters: none +:Architectures: s390 +:Parameters: none With this capability enabled, all illegal instructions 0x0000 (2 bytes) will be intercepted and forwarded to user space. User space can use this @@ -5020,26 +5559,29 @@ This capability can be enabled dynamically even if VCPUs were already created and are running. 7.9 KVM_CAP_S390_GS +------------------- -Architectures: s390 -Parameters: none -Returns: 0 on success; -EINVAL if the machine does not support - guarded storage; -EBUSY if a VCPU has already been created. +:Architectures: s390 +:Parameters: none +:Returns: 0 on success; -EINVAL if the machine does not support + guarded storage; -EBUSY if a VCPU has already been created. Allows use of guarded storage for the KVM guest. 7.10 KVM_CAP_S390_AIS +--------------------- -Architectures: s390 -Parameters: none +:Architectures: s390 +:Parameters: none Allow use of adapter-interruption suppression. -Returns: 0 on success; -EBUSY if a VCPU has already been created. +:Returns: 0 on success; -EBUSY if a VCPU has already been created. 7.11 KVM_CAP_PPC_SMT +-------------------- -Architectures: ppc -Parameters: vsmt_mode, flags +:Architectures: ppc +:Parameters: vsmt_mode, flags Enabling this capability on a VM provides userspace with a way to set the desired virtual SMT mode (i.e. the number of virtual CPUs per @@ -5054,9 +5596,10 @@ The KVM_CAP_PPC_SMT_POSSIBLE capability indicates which virtual SMT modes are available. 7.12 KVM_CAP_PPC_FWNMI +---------------------- -Architectures: ppc -Parameters: none +:Architectures: ppc +:Parameters: none With this capability a machine check exception in the guest address space will cause KVM to exit the guest with NMI exit reason. This @@ -5065,17 +5608,18 @@ machine check handling routine. Without this capability KVM will branch to guests' 0x200 interrupt vector. 7.13 KVM_CAP_X86_DISABLE_EXITS +------------------------------ -Architectures: x86 -Parameters: args[0] defines which exits are disabled -Returns: 0 on success, -EINVAL when args[0] contains invalid exits +:Architectures: x86 +:Parameters: args[0] defines which exits are disabled +:Returns: 0 on success, -EINVAL when args[0] contains invalid exits -Valid bits in args[0] are +Valid bits in args[0] are:: -#define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0) -#define KVM_X86_DISABLE_EXITS_HLT (1 << 1) -#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2) -#define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3) + #define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0) + #define KVM_X86_DISABLE_EXITS_HLT (1 << 1) + #define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2) + #define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3) Enabling this capability on a VM provides userspace with a way to no longer intercept some instructions for improved latency in some @@ -5087,12 +5631,13 @@ all such vmexits. Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits. 7.14 KVM_CAP_S390_HPAGE_1M +-------------------------- -Architectures: s390 -Parameters: none -Returns: 0 on success, -EINVAL if hpage module parameter was not set - or cmma is enabled, or the VM has the KVM_VM_S390_UCONTROL - flag set +:Architectures: s390 +:Parameters: none +:Returns: 0 on success, -EINVAL if hpage module parameter was not set + or cmma is enabled, or the VM has the KVM_VM_S390_UCONTROL + flag set With this capability the KVM support for memory backing with 1m pages through hugetlbfs can be enabled for a VM. After the capability is @@ -5104,20 +5649,22 @@ While it is generally possible to create a huge page backed VM without this capability, the VM will not be able to run. 7.15 KVM_CAP_MSR_PLATFORM_INFO +------------------------------ -Architectures: x86 -Parameters: args[0] whether feature should be enabled or not +:Architectures: x86 +:Parameters: args[0] whether feature should be enabled or not With this capability, a guest may read the MSR_PLATFORM_INFO MSR. Otherwise, a #GP would be raised when the guest tries to access. Currently, this capability does not enable write permissions of this MSR for the guest. 7.16 KVM_CAP_PPC_NESTED_HV +-------------------------- -Architectures: ppc -Parameters: none -Returns: 0 on success, -EINVAL when the implementation doesn't support - nested-HV virtualization. +:Architectures: ppc +:Parameters: none +:Returns: 0 on success, -EINVAL when the implementation doesn't support + nested-HV virtualization. HV-KVM on POWER9 and later systems allows for "nested-HV" virtualization, which provides a way for a guest VM to run guests that @@ -5127,9 +5674,10 @@ the necessary functionality and on the facility being enabled with a kvm-hv module parameter. 7.17 KVM_CAP_EXCEPTION_PAYLOAD +------------------------------ -Architectures: x86 -Parameters: args[0] whether feature should be enabled or not +:Architectures: x86 +:Parameters: args[0] whether feature should be enabled or not With this capability enabled, CR2 will not be modified prior to the emulated VM-exit when L1 intercepts a #PF exception that occurs in @@ -5140,21 +5688,21 @@ L2. As a result, when KVM_GET_VCPU_EVENTS reports a pending #PF (or faulting address (or the new DR6 bits*) will be reported in the exception_payload field. Similarly, when userspace injects a #PF (or #DB) into L2 using KVM_SET_VCPU_EVENTS, it is expected to set -exception.has_payload and to put the faulting address (or the new DR6 -bits*) in the exception_payload field. +exception.has_payload and to put the faulting address - or the new DR6 +bits\ [#]_ - in the exception_payload field. This capability also enables exception.pending in struct kvm_vcpu_events, which allows userspace to distinguish between pending and injected exceptions. -* For the new DR6 bits, note that bit 16 is set iff the #DB exception - will clear DR6.RTM. +.. [#] For the new DR6 bits, note that bit 16 is set iff the #DB exception + will clear DR6.RTM. 7.18 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 -Architectures: x86, arm, arm64, mips -Parameters: args[0] whether feature should be enabled or not +:Architectures: x86, arm, arm64, mips +:Parameters: args[0] whether feature should be enabled or not With this capability enabled, KVM_GET_DIRTY_LOG will not automatically clear and write-protect all pages that are returned as dirty. @@ -5181,14 +5729,15 @@ KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 signals that those bugs are fixed. Userspace should not try to use KVM_CAP_MANUAL_DIRTY_LOG_PROTECT. 8. Other capabilities. ----------------------- +====================== This section lists capabilities that give information about other features of the KVM implementation. 8.1 KVM_CAP_PPC_HWRNG +--------------------- -Architectures: ppc +:Architectures: ppc This capability, if KVM_CHECK_EXTENSION indicates that it is available, means that that the kernel has an implementation of the @@ -5197,8 +5746,10 @@ If present, the kernel H_RANDOM handler can be enabled for guest use with the KVM_CAP_PPC_ENABLE_HCALL capability. 8.2 KVM_CAP_HYPERV_SYNIC +------------------------ + +:Architectures: x86 -Architectures: x86 This capability, if KVM_CHECK_EXTENSION indicates that it is available, means that that the kernel has an implementation of the Hyper-V Synthetic interrupt controller(SynIC). Hyper-V SynIC is @@ -5210,8 +5761,9 @@ will disable the use of APIC hardware virtualization even if supported by the CPU, as it's incompatible with SynIC auto-EOI behavior. 8.3 KVM_CAP_PPC_RADIX_MMU +------------------------- -Architectures: ppc +:Architectures: ppc This capability, if KVM_CHECK_EXTENSION indicates that it is available, means that that the kernel can support guests using the @@ -5219,8 +5771,9 @@ radix MMU defined in Power ISA V3.00 (as implemented in the POWER9 processor). 8.4 KVM_CAP_PPC_HASH_MMU_V3 +--------------------------- -Architectures: ppc +:Architectures: ppc This capability, if KVM_CHECK_EXTENSION indicates that it is available, means that that the kernel can support guests using the @@ -5228,8 +5781,9 @@ hashed page table MMU defined in Power ISA V3.00 (as implemented in the POWER9 processor), including in-memory segment tables. 8.5 KVM_CAP_MIPS_VZ +------------------- -Architectures: mips +:Architectures: mips This capability, if KVM_CHECK_EXTENSION on the main kvm handle indicates that it is available, means that full hardware assisted virtualization capabilities @@ -5247,16 +5801,19 @@ values (see below). All other values are reserved. This is to allow for the possibility of other hardware assisted virtualization implementations which may be incompatible with the MIPS VZ ASE. - 0: The trap & emulate implementation is in use to run guest code in user +== ========================================================================== + 0 The trap & emulate implementation is in use to run guest code in user mode. Guest virtual memory segments are rearranged to fit the guest in the user mode address space. - 1: The MIPS VZ ASE is in use, providing full hardware assisted + 1 The MIPS VZ ASE is in use, providing full hardware assisted virtualization, including standard guest virtual memory segments. +== ========================================================================== 8.6 KVM_CAP_MIPS_TE +------------------- -Architectures: mips +:Architectures: mips This capability, if KVM_CHECK_EXTENSION on the main kvm handle indicates that it is available, means that the trap & emulate implementation is available to @@ -5268,8 +5825,9 @@ If KVM_CHECK_EXTENSION on a kvm VM handle indicates that this capability is available, it means that the VM is using trap & emulate. 8.7 KVM_CAP_MIPS_64BIT +---------------------- -Architectures: mips +:Architectures: mips This capability indicates the supported architecture type of the guest, i.e. the supported register and address width. @@ -5279,22 +5837,26 @@ kvm VM handle correspond roughly to the CP0_Config.AT register field, and should be checked specifically against known values (see below). All other values are reserved. - 0: MIPS32 or microMIPS32. +== ======================================================================== + 0 MIPS32 or microMIPS32. Both registers and addresses are 32-bits wide. It will only be possible to run 32-bit guest code. - 1: MIPS64 or microMIPS64 with access only to 32-bit compatibility segments. + 1 MIPS64 or microMIPS64 with access only to 32-bit compatibility segments. Registers are 64-bits wide, but addresses are 32-bits wide. 64-bit guest code may run but cannot access MIPS64 memory segments. It will also be possible to run 32-bit guest code. - 2: MIPS64 or microMIPS64 with access to all address segments. + 2 MIPS64 or microMIPS64 with access to all address segments. Both registers and addresses are 64-bits wide. It will be possible to run 64-bit or 32-bit guest code. +== ======================================================================== 8.9 KVM_CAP_ARM_USER_IRQ +------------------------ + +:Architectures: arm, arm64 -Architectures: arm, arm64 This capability, if KVM_CHECK_EXTENSION indicates that it is available, means that if userspace creates a VM without an in-kernel interrupt controller, it will be notified of changes to the output level of in-kernel emulated devices, @@ -5321,7 +5883,7 @@ If KVM_CAP_ARM_USER_IRQ is supported, the KVM_CHECK_EXTENSION ioctl returns a number larger than 0 indicating the version of this capability is implemented and thereby which bits in in run->s.regs.device_irq_level can signal values. -Currently the following bits are defined for the device_irq_level bitmap: +Currently the following bits are defined for the device_irq_level bitmap:: KVM_CAP_ARM_USER_IRQ >= 1: @@ -5334,8 +5896,9 @@ indicated by returning a higher number from KVM_CHECK_EXTENSION and will be listed above. 8.10 KVM_CAP_PPC_SMT_POSSIBLE +----------------------------- -Architectures: ppc +:Architectures: ppc Querying this capability returns a bitmap indicating the possible virtual SMT modes that can be set using KVM_CAP_PPC_SMT. If bit N @@ -5343,8 +5906,9 @@ virtual SMT modes that can be set using KVM_CAP_PPC_SMT. If bit N available. 8.11 KVM_CAP_HYPERV_SYNIC2 +-------------------------- -Architectures: x86 +:Architectures: x86 This capability enables a newer version of Hyper-V Synthetic interrupt controller (SynIC). The only difference with KVM_CAP_HYPERV_SYNIC is that KVM @@ -5352,8 +5916,9 @@ doesn't clear SynIC message and event flags pages when they are enabled by writing to the respective MSRs. 8.12 KVM_CAP_HYPERV_VP_INDEX +---------------------------- -Architectures: x86 +:Architectures: x86 This capability indicates that userspace can load HV_X64_MSR_VP_INDEX msr. Its value is used to denote the target vcpu for a SynIC interrupt. For @@ -5361,47 +5926,53 @@ compatibilty, KVM initializes this msr to KVM's internal vcpu index. When this capability is absent, userspace can still query this msr's value. 8.13 KVM_CAP_S390_AIS_MIGRATION +------------------------------- -Architectures: s390 -Parameters: none +:Architectures: s390 +:Parameters: none This capability indicates if the flic device will be able to get/set the AIS states for migration via the KVM_DEV_FLIC_AISM_ALL attribute and allows to discover this without having to create a flic device. 8.14 KVM_CAP_S390_PSW +--------------------- -Architectures: s390 +:Architectures: s390 This capability indicates that the PSW is exposed via the kvm_run structure. 8.15 KVM_CAP_S390_GMAP +---------------------- -Architectures: s390 +:Architectures: s390 This capability indicates that the user space memory used as guest mapping can be anywhere in the user memory address space, as long as the memory slots are aligned and sized to a segment (1MB) boundary. 8.16 KVM_CAP_S390_COW +--------------------- -Architectures: s390 +:Architectures: s390 This capability indicates that the user space memory used as guest mapping can use copy-on-write semantics as well as dirty pages tracking via read-only page tables. 8.17 KVM_CAP_S390_BPB +--------------------- -Architectures: s390 +:Architectures: s390 This capability indicates that kvm will implement the interfaces to handle reset, migration and nested KVM for branch prediction blocking. The stfle facility 82 should not be provided to the guest without this capability. 8.18 KVM_CAP_HYPERV_TLBFLUSH +---------------------------- -Architectures: x86 +:Architectures: x86 This capability indicates that KVM supports paravirtualized Hyper-V TLB Flush hypercalls: @@ -5409,8 +5980,9 @@ HvFlushVirtualAddressSpace, HvFlushVirtualAddressSpaceEx, HvFlushVirtualAddressList, HvFlushVirtualAddressListEx. 8.19 KVM_CAP_ARM_INJECT_SERROR_ESR +---------------------------------- -Architectures: arm, arm64 +:Architectures: arm, arm64 This capability indicates that userspace can specify (via the KVM_SET_VCPU_EVENTS ioctl) the syndrome value reported to the guest when it @@ -5421,16 +5993,20 @@ CPU when the exception is taken. If this virtual SError is taken to EL1 using AArch64, this value will be reported in the ISS field of ESR_ELx. See KVM_CAP_VCPU_EVENTS for more details. + 8.20 KVM_CAP_HYPERV_SEND_IPI +---------------------------- -Architectures: x86 +:Architectures: x86 This capability indicates that KVM supports paravirtualized Hyper-V IPI send hypercalls: HvCallSendSyntheticClusterIpi, HvCallSendSyntheticClusterIpiEx. + 8.21 KVM_CAP_HYPERV_DIRECT_TLBFLUSH +----------------------------------- -Architecture: x86 +:Architecture: x86 This capability indicates that KVM running on top of Hyper-V hypervisor enables Direct TLB flush for its guests meaning that TLB flush diff --git a/Documentation/virt/kvm/arm/hyp-abi.txt b/Documentation/virt/kvm/arm/hyp-abi.rst index a20a0bee268d..d1fc27d848e9 100644 --- a/Documentation/virt/kvm/arm/hyp-abi.txt +++ b/Documentation/virt/kvm/arm/hyp-abi.rst @@ -1,4 +1,8 @@ -* Internal ABI between the kernel and HYP +.. SPDX-License-Identifier: GPL-2.0 + +======================================= +Internal ABI between the kernel and HYP +======================================= This file documents the interaction between the Linux kernel and the hypervisor layer when running Linux as a hypervisor (for example @@ -19,25 +23,31 @@ and only act on individual CPUs. Unless specified otherwise, any built-in hypervisor must implement these functions (see arch/arm{,64}/include/asm/virt.h): -* r0/x0 = HVC_SET_VECTORS - r1/x1 = vectors +* :: + + r0/x0 = HVC_SET_VECTORS + r1/x1 = vectors Set HVBAR/VBAR_EL2 to 'vectors' to enable a hypervisor. 'vectors' must be a physical address, and respect the alignment requirements of the architecture. Only implemented by the initial stubs, not by Linux hypervisors. -* r0/x0 = HVC_RESET_VECTORS +* :: + + r0/x0 = HVC_RESET_VECTORS Turn HYP/EL2 MMU off, and reset HVBAR/VBAR_EL2 to the initials stubs' exception vector value. This effectively disables an existing hypervisor. -* r0/x0 = HVC_SOFT_RESTART - r1/x1 = restart address - x2 = x0's value when entering the next payload (arm64) - x3 = x1's value when entering the next payload (arm64) - x4 = x2's value when entering the next payload (arm64) +* :: + + r0/x0 = HVC_SOFT_RESTART + r1/x1 = restart address + x2 = x0's value when entering the next payload (arm64) + x3 = x1's value when entering the next payload (arm64) + x4 = x2's value when entering the next payload (arm64) Mask all exceptions, disable the MMU, move the arguments into place (arm64 only), and jump to the restart address while at HYP/EL2. This diff --git a/Documentation/virt/kvm/arm/index.rst b/Documentation/virt/kvm/arm/index.rst new file mode 100644 index 000000000000..3e2b2aba90fc --- /dev/null +++ b/Documentation/virt/kvm/arm/index.rst @@ -0,0 +1,12 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=== +ARM +=== + +.. toctree:: + :maxdepth: 2 + + hyp-abi + psci + pvtime diff --git a/Documentation/virt/kvm/arm/psci.txt b/Documentation/virt/kvm/arm/psci.rst index 559586fc9d37..d52c2e83b5b8 100644 --- a/Documentation/virt/kvm/arm/psci.txt +++ b/Documentation/virt/kvm/arm/psci.rst @@ -1,3 +1,9 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========================================= +Power State Coordination Interface (PSCI) +========================================= + KVM implements the PSCI (Power State Coordination Interface) specification in order to provide services such as CPU on/off, reset and power-off to the guest. @@ -30,32 +36,42 @@ The following register is defined: - Affects the whole VM (even if the register view is per-vcpu) * KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: - Holds the state of the firmware support to mitigate CVE-2017-5715, as - offered by KVM to the guest via a HVC call. The workaround is described - under SMCCC_ARCH_WORKAROUND_1 in [1]. + Holds the state of the firmware support to mitigate CVE-2017-5715, as + offered by KVM to the guest via a HVC call. The workaround is described + under SMCCC_ARCH_WORKAROUND_1 in [1]. + Accepted values are: - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL: KVM does not offer + + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL: + KVM does not offer firmware support for the workaround. The mitigation status for the guest is unknown. - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL: The workaround HVC call is + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL: + The workaround HVC call is available to the guest and required for the mitigation. - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED: The workaround HVC call + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED: + The workaround HVC call is available to the guest, but it is not needed on this VCPU. * KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: - Holds the state of the firmware support to mitigate CVE-2018-3639, as - offered by KVM to the guest via a HVC call. The workaround is described - under SMCCC_ARCH_WORKAROUND_2 in [1]. + Holds the state of the firmware support to mitigate CVE-2018-3639, as + offered by KVM to the guest via a HVC call. The workaround is described + under SMCCC_ARCH_WORKAROUND_2 in [1]_. + Accepted values are: - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL: A workaround is not + + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL: + A workaround is not available. KVM does not offer firmware support for the workaround. - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN: The workaround state is + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN: + The workaround state is unknown. KVM does not offer firmware support for the workaround. - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL: The workaround is available, + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL: + The workaround is available, and can be disabled by a vCPU. If KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED is set, it is active for this vCPU. - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED: The workaround is - always active on this vCPU or it is not needed. + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED: + The workaround is always active on this vCPU or it is not needed. -[1] https://developer.arm.com/-/media/developer/pdf/ARM_DEN_0070A_Firmware_interfaces_for_mitigating_CVE-2017-5715.pdf +.. [1] https://developer.arm.com/-/media/developer/pdf/ARM_DEN_0070A_Firmware_interfaces_for_mitigating_CVE-2017-5715.pdf diff --git a/Documentation/virt/kvm/devices/arm-vgic-its.txt b/Documentation/virt/kvm/devices/arm-vgic-its.rst index eeaa95b893a8..6c304fd2b1b4 100644 --- a/Documentation/virt/kvm/devices/arm-vgic-its.txt +++ b/Documentation/virt/kvm/devices/arm-vgic-its.rst @@ -1,3 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=============================================== ARM Virtual Interrupt Translation Service (ITS) =============================================== @@ -12,22 +15,32 @@ There can be multiple ITS controllers per guest, each of them has to have a separate, non-overlapping MMIO region. -Groups: - KVM_DEV_ARM_VGIC_GRP_ADDR +Groups +====== + +KVM_DEV_ARM_VGIC_GRP_ADDR +------------------------- + Attributes: KVM_VGIC_ITS_ADDR_TYPE (rw, 64-bit) Base address in the guest physical address space of the GICv3 ITS control register frame. This address needs to be 64K aligned and the region covers 128K. + Errors: - -E2BIG: Address outside of addressable IPA range - -EINVAL: Incorrectly aligned address - -EEXIST: Address already configured - -EFAULT: Invalid user pointer for attr->addr. - -ENODEV: Incorrect attribute or the ITS is not supported. + ======= ================================================= + -E2BIG Address outside of addressable IPA range + -EINVAL Incorrectly aligned address + -EEXIST Address already configured + -EFAULT Invalid user pointer for attr->addr. + -ENODEV Incorrect attribute or the ITS is not supported. + ======= ================================================= + + +KVM_DEV_ARM_VGIC_GRP_CTRL +------------------------- - KVM_DEV_ARM_VGIC_GRP_CTRL Attributes: KVM_DEV_ARM_VGIC_CTRL_INIT request the initialization of the ITS, no additional parameter in @@ -58,16 +71,21 @@ Groups: "ITS Restore Sequence". Errors: - -ENXIO: ITS not properly configured as required prior to setting + + ======= ========================================================== + -ENXIO ITS not properly configured as required prior to setting this attribute - -ENOMEM: Memory shortage when allocating ITS internal data - -EINVAL: Inconsistent restored data - -EFAULT: Invalid guest ram access - -EBUSY: One or more VCPUS are running - -EACCES: The virtual ITS is backed by a physical GICv4 ITS, and the + -ENOMEM Memory shortage when allocating ITS internal data + -EINVAL Inconsistent restored data + -EFAULT Invalid guest ram access + -EBUSY One or more VCPUS are running + -EACCES The virtual ITS is backed by a physical GICv4 ITS, and the state is not available + ======= ========================================================== + +KVM_DEV_ARM_VGIC_GRP_ITS_REGS +----------------------------- - KVM_DEV_ARM_VGIC_GRP_ITS_REGS Attributes: The attr field of kvm_device_attr encodes the offset of the ITS register, relative to the ITS control frame base address @@ -78,6 +96,7 @@ Groups: be accessed with full length. Writes to read-only registers are ignored by the kernel except for: + - GITS_CREADR. It must be restored otherwise commands in the queue will be re-executed after restoring CWRITER. GITS_CREADR must be restored before restoring the GITS_CTLR which is likely to enable the @@ -91,30 +110,36 @@ Groups: For other registers, getting or setting a register has the same effect as reading/writing the register on real hardware. + Errors: - -ENXIO: Offset does not correspond to any supported register - -EFAULT: Invalid user pointer for attr->addr - -EINVAL: Offset is not 64-bit aligned - -EBUSY: one or more VCPUS are running - ITS Restore Sequence: - ------------------------- + ======= ==================================================== + -ENXIO Offset does not correspond to any supported register + -EFAULT Invalid user pointer for attr->addr + -EINVAL Offset is not 64-bit aligned + -EBUSY one or more VCPUS are running + ======= ==================================================== + +ITS Restore Sequence: +--------------------- The following ordering must be followed when restoring the GIC and the ITS: + a) restore all guest memory and create vcpus b) restore all redistributors c) provide the ITS base address (KVM_DEV_ARM_VGIC_GRP_ADDR) d) restore the ITS in the following order: - 1. Restore GITS_CBASER - 2. Restore all other GITS_ registers, except GITS_CTLR! - 3. Load the ITS table data (KVM_DEV_ARM_ITS_RESTORE_TABLES) - 4. Restore GITS_CTLR + + 1. Restore GITS_CBASER + 2. Restore all other ``GITS_`` registers, except GITS_CTLR! + 3. Load the ITS table data (KVM_DEV_ARM_ITS_RESTORE_TABLES) + 4. Restore GITS_CTLR Then vcpus can be started. - ITS Table ABI REV0: - ------------------- +ITS Table ABI REV0: +------------------- Revision 0 of the ABI only supports the features of a virtual GICv3, and does not support a virtual GICv4 with support for direct injection of virtual @@ -125,12 +150,13 @@ Then vcpus can be started. entries in the collection are listed in no particular order. All entries are 8 bytes. - Device Table Entry (DTE): + Device Table Entry (DTE):: - bits: | 63| 62 ... 49 | 48 ... 5 | 4 ... 0 | - values: | V | next | ITT_addr | Size | + bits: | 63| 62 ... 49 | 48 ... 5 | 4 ... 0 | + values: | V | next | ITT_addr | Size | + + where: - where; - V indicates whether the entry is valid. If not, other fields are not meaningful. - next: equals to 0 if this entry is the last one; otherwise it @@ -140,32 +166,34 @@ Then vcpus can be started. - Size specifies the supported number of bits for the EventID, minus one - Collection Table Entry (CTE): + Collection Table Entry (CTE):: - bits: | 63| 62 .. 52 | 51 ... 16 | 15 ... 0 | - values: | V | RES0 | RDBase | ICID | + bits: | 63| 62 .. 52 | 51 ... 16 | 15 ... 0 | + values: | V | RES0 | RDBase | ICID | where: + - V indicates whether the entry is valid. If not, other fields are not meaningful. - RES0: reserved field with Should-Be-Zero-or-Preserved behavior. - RDBase is the PE number (GICR_TYPER.Processor_Number semantic), - ICID is the collection ID - Interrupt Translation Entry (ITE): + Interrupt Translation Entry (ITE):: - bits: | 63 ... 48 | 47 ... 16 | 15 ... 0 | - values: | next | pINTID | ICID | + bits: | 63 ... 48 | 47 ... 16 | 15 ... 0 | + values: | next | pINTID | ICID | where: + - next: equals to 0 if this entry is the last one; otherwise it corresponds to the EventID offset to the next ITE capped by 2^16 -1. - pINTID is the physical LPI ID; if zero, it means the entry is not valid and other fields are not meaningful. - ICID is the collection ID - ITS Reset State: - ---------------- +ITS Reset State: +---------------- RESET returns the ITS to the same state that it was when first created and initialized. When the RESET command returns, the following things are diff --git a/Documentation/virt/kvm/devices/arm-vgic-v3.txt b/Documentation/virt/kvm/devices/arm-vgic-v3.rst index ff290b43c8e5..5dd3bff51978 100644 --- a/Documentation/virt/kvm/devices/arm-vgic-v3.txt +++ b/Documentation/virt/kvm/devices/arm-vgic-v3.rst @@ -1,9 +1,12 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============================================================== ARM Virtual Generic Interrupt Controller v3 and later (VGICv3) ============================================================== Device types supported: - KVM_DEV_TYPE_ARM_VGIC_V3 ARM Generic Interrupt Controller v3.0 + - KVM_DEV_TYPE_ARM_VGIC_V3 ARM Generic Interrupt Controller v3.0 Only one VGIC instance may be instantiated through this API. The created VGIC will act as the VM interrupt controller, requiring emulated user-space devices @@ -15,7 +18,8 @@ Creating a guest GICv3 device requires a host GICv3 as well. Groups: KVM_DEV_ARM_VGIC_GRP_ADDR - Attributes: + Attributes: + KVM_VGIC_V3_ADDR_TYPE_DIST (rw, 64-bit) Base address in the guest physical address space of the GICv3 distributor register mappings. Only valid for KVM_DEV_TYPE_ARM_VGIC_V3. @@ -29,21 +33,25 @@ Groups: This address needs to be 64K aligned. KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION (rw, 64-bit) - The attribute data pointed to by kvm_device_attr.addr is a __u64 value: - bits: | 63 .... 52 | 51 .... 16 | 15 - 12 |11 - 0 - values: | count | base | flags | index + The attribute data pointed to by kvm_device_attr.addr is a __u64 value:: + + bits: | 63 .... 52 | 51 .... 16 | 15 - 12 |11 - 0 + values: | count | base | flags | index + - index encodes the unique redistributor region index - flags: reserved for future use, currently 0 - base field encodes bits [51:16] of the guest physical base address of the first redistributor in the region. - count encodes the number of redistributors in the region. Must be greater than 0. + There are two 64K pages for each redistributor in the region and redistributors are laid out contiguously within the region. Regions are filled with redistributors in the index order. The sum of all region count fields must be greater than or equal to the number of VCPUs. Redistributor regions must be registered in the incremental index order, starting from index 0. + The characteristics of a specific redistributor region can be read by presetting the index field in the attr data. Only valid for KVM_DEV_TYPE_ARM_VGIC_V3. @@ -52,23 +60,27 @@ Groups: KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION attributes. Errors: - -E2BIG: Address outside of addressable IPA range - -EINVAL: Incorrectly aligned address, bad redistributor region + + ======= ============================================================= + -E2BIG Address outside of addressable IPA range + -EINVAL Incorrectly aligned address, bad redistributor region count/index, mixed redistributor region attribute usage - -EEXIST: Address already configured - -ENOENT: Attempt to read the characteristics of a non existing + -EEXIST Address already configured + -ENOENT Attempt to read the characteristics of a non existing redistributor region - -ENXIO: The group or attribute is unknown/unsupported for this device + -ENXIO The group or attribute is unknown/unsupported for this device or hardware support is missing. - -EFAULT: Invalid user pointer for attr->addr. + -EFAULT Invalid user pointer for attr->addr. + ======= ============================================================= + + KVM_DEV_ARM_VGIC_GRP_DIST_REGS, KVM_DEV_ARM_VGIC_GRP_REDIST_REGS + Attributes: - KVM_DEV_ARM_VGIC_GRP_DIST_REGS - KVM_DEV_ARM_VGIC_GRP_REDIST_REGS - Attributes: - The attr field of kvm_device_attr encodes two values: - bits: | 63 .... 32 | 31 .... 0 | - values: | mpidr | offset | + The attr field of kvm_device_attr encodes two values:: + + bits: | 63 .... 32 | 31 .... 0 | + values: | mpidr | offset | All distributor regs are (rw, 32-bit) and kvm_device_attr.addr points to a __u32 value. 64-bit registers must be accessed by separately accessing the @@ -93,7 +105,8 @@ Groups: redistributor is accessed. The mpidr is ignored for the distributor. The mpidr encoding is based on the affinity information in the - architecture defined MPIDR, and the field is encoded as follows: + architecture defined MPIDR, and the field is encoded as follows:: + | 63 .... 56 | 55 .... 48 | 47 .... 40 | 39 .... 32 | | Aff3 | Aff2 | Aff1 | Aff0 | @@ -148,24 +161,30 @@ Groups: ignored. Errors: - -ENXIO: Getting or setting this register is not yet supported - -EBUSY: One or more VCPUs are running + + ====== ===================================================== + -ENXIO Getting or setting this register is not yet supported + -EBUSY One or more VCPUs are running + ====== ===================================================== KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS - Attributes: - The attr field of kvm_device_attr encodes two values: - bits: | 63 .... 32 | 31 .... 16 | 15 .... 0 | - values: | mpidr | RES | instr | + Attributes: + + The attr field of kvm_device_attr encodes two values:: + + bits: | 63 .... 32 | 31 .... 16 | 15 .... 0 | + values: | mpidr | RES | instr | The mpidr field encodes the CPU ID based on the affinity information in the - architecture defined MPIDR, and the field is encoded as follows: + architecture defined MPIDR, and the field is encoded as follows:: + | 63 .... 56 | 55 .... 48 | 47 .... 40 | 39 .... 32 | | Aff3 | Aff2 | Aff1 | Aff0 | The instr field encodes the system register to access based on the fields defined in the A64 instruction set encoding for system register access - (RES means the bits are reserved for future use and should be zero): + (RES means the bits are reserved for future use and should be zero):: | 15 ... 14 | 13 ... 11 | 10 ... 7 | 6 ... 3 | 2 ... 0 | | Op 0 | Op1 | CRn | CRm | Op2 | @@ -178,26 +197,35 @@ Groups: CPU interface registers access is not implemented for AArch32 mode. Error -ENXIO is returned when accessed in AArch32 mode. + Errors: - -ENXIO: Getting or setting this register is not yet supported - -EBUSY: VCPU is running - -EINVAL: Invalid mpidr or register value supplied + + ======= ===================================================== + -ENXIO Getting or setting this register is not yet supported + -EBUSY VCPU is running + -EINVAL Invalid mpidr or register value supplied + ======= ===================================================== KVM_DEV_ARM_VGIC_GRP_NR_IRQS - Attributes: + Attributes: + A value describing the number of interrupts (SGI, PPI and SPI) for this GIC instance, ranging from 64 to 1024, in increments of 32. kvm_device_attr.addr points to a __u32 value. Errors: - -EINVAL: Value set is out of the expected range - -EBUSY: Value has already be set. + + ======= ====================================== + -EINVAL Value set is out of the expected range + -EBUSY Value has already be set. + ======= ====================================== KVM_DEV_ARM_VGIC_GRP_CTRL - Attributes: + Attributes: + KVM_DEV_ARM_VGIC_CTRL_INIT request the initialization of the VGIC, no additional parameter in kvm_device_attr.addr. @@ -205,20 +233,26 @@ Groups: save all LPI pending bits into guest RAM pending tables. The first kB of the pending table is not altered by this operation. + Errors: - -ENXIO: VGIC not properly configured as required prior to calling - this attribute - -ENODEV: no online VCPU - -ENOMEM: memory shortage when allocating vgic internal data - -EFAULT: Invalid guest ram access - -EBUSY: One or more VCPUS are running + + ======= ======================================================== + -ENXIO VGIC not properly configured as required prior to calling + this attribute + -ENODEV no online VCPU + -ENOMEM memory shortage when allocating vgic internal data + -EFAULT Invalid guest ram access + -EBUSY One or more VCPUS are running + ======= ======================================================== KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO - Attributes: - The attr field of kvm_device_attr encodes the following values: - bits: | 63 .... 32 | 31 .... 10 | 9 .... 0 | - values: | mpidr | info | vINTID | + Attributes: + + The attr field of kvm_device_attr encodes the following values:: + + bits: | 63 .... 32 | 31 .... 10 | 9 .... 0 | + values: | mpidr | info | vINTID | The vINTID specifies which set of IRQs is reported on. @@ -228,6 +262,7 @@ Groups: VGIC_LEVEL_INFO_LINE_LEVEL: Get/Set the input level of the IRQ line for a set of 32 contiguously numbered interrupts. + vINTID must be a multiple of 32. kvm_device_attr.addr points to a __u32 value which will contain a @@ -243,9 +278,14 @@ Groups: reported with the same value regardless of the mpidr specified. The mpidr field encodes the CPU ID based on the affinity information in the - architecture defined MPIDR, and the field is encoded as follows: + architecture defined MPIDR, and the field is encoded as follows:: + | 63 .... 56 | 55 .... 48 | 47 .... 40 | 39 .... 32 | | Aff3 | Aff2 | Aff1 | Aff0 | + Errors: - -EINVAL: vINTID is not multiple of 32 or - info field is not VGIC_LEVEL_INFO_LINE_LEVEL + + ======= ============================================= + -EINVAL vINTID is not multiple of 32 or info field is + not VGIC_LEVEL_INFO_LINE_LEVEL + ======= ============================================= diff --git a/Documentation/virt/kvm/devices/arm-vgic.txt b/Documentation/virt/kvm/devices/arm-vgic.rst index 97b6518148f8..40bdeea1d86e 100644 --- a/Documentation/virt/kvm/devices/arm-vgic.txt +++ b/Documentation/virt/kvm/devices/arm-vgic.rst @@ -1,8 +1,12 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================================== ARM Virtual Generic Interrupt Controller v2 (VGIC) ================================================== Device types supported: - KVM_DEV_TYPE_ARM_VGIC_V2 ARM Generic Interrupt Controller v2.0 + + - KVM_DEV_TYPE_ARM_VGIC_V2 ARM Generic Interrupt Controller v2.0 Only one VGIC instance may be instantiated through either this API or the legacy KVM_CREATE_IRQCHIP API. The created VGIC will act as the VM interrupt @@ -17,7 +21,8 @@ create both a GICv3 and GICv2 device on the same VM. Groups: KVM_DEV_ARM_VGIC_GRP_ADDR - Attributes: + Attributes: + KVM_VGIC_V2_ADDR_TYPE_DIST (rw, 64-bit) Base address in the guest physical address space of the GIC distributor register mappings. Only valid for KVM_DEV_TYPE_ARM_VGIC_V2. @@ -27,19 +32,25 @@ Groups: Base address in the guest physical address space of the GIC virtual cpu interface register mappings. Only valid for KVM_DEV_TYPE_ARM_VGIC_V2. This address needs to be 4K aligned and the region covers 4 KByte. + Errors: - -E2BIG: Address outside of addressable IPA range - -EINVAL: Incorrectly aligned address - -EEXIST: Address already configured - -ENXIO: The group or attribute is unknown/unsupported for this device + + ======= ============================================================= + -E2BIG Address outside of addressable IPA range + -EINVAL Incorrectly aligned address + -EEXIST Address already configured + -ENXIO The group or attribute is unknown/unsupported for this device or hardware support is missing. - -EFAULT: Invalid user pointer for attr->addr. + -EFAULT Invalid user pointer for attr->addr. + ======= ============================================================= KVM_DEV_ARM_VGIC_GRP_DIST_REGS - Attributes: - The attr field of kvm_device_attr encodes two values: - bits: | 63 .... 40 | 39 .. 32 | 31 .... 0 | - values: | reserved | vcpu_index | offset | + Attributes: + + The attr field of kvm_device_attr encodes two values:: + + bits: | 63 .... 40 | 39 .. 32 | 31 .... 0 | + values: | reserved | vcpu_index | offset | All distributor regs are (rw, 32-bit) @@ -58,16 +69,22 @@ Groups: KVM_DEV_ARM_VGIC_GRP_DIST_REGS and KVM_DEV_ARM_VGIC_GRP_CPU_REGS) to ensure the expected behavior. Unless GICD_IIDR has been set from userspace, writes to the interrupt group registers (GICD_IGROUPR) are ignored. + Errors: - -ENXIO: Getting or setting this register is not yet supported - -EBUSY: One or more VCPUs are running - -EINVAL: Invalid vcpu_index supplied + + ======= ===================================================== + -ENXIO Getting or setting this register is not yet supported + -EBUSY One or more VCPUs are running + -EINVAL Invalid vcpu_index supplied + ======= ===================================================== KVM_DEV_ARM_VGIC_GRP_CPU_REGS - Attributes: - The attr field of kvm_device_attr encodes two values: - bits: | 63 .... 40 | 39 .. 32 | 31 .... 0 | - values: | reserved | vcpu_index | offset | + Attributes: + + The attr field of kvm_device_attr encodes two values:: + + bits: | 63 .... 40 | 39 .. 32 | 31 .... 0 | + values: | reserved | vcpu_index | offset | All CPU interface regs are (rw, 32-bit) @@ -101,27 +118,39 @@ Groups: value left by 3 places to obtain the actual priority mask level. Errors: - -ENXIO: Getting or setting this register is not yet supported - -EBUSY: One or more VCPUs are running - -EINVAL: Invalid vcpu_index supplied + + ======= ===================================================== + -ENXIO Getting or setting this register is not yet supported + -EBUSY One or more VCPUs are running + -EINVAL Invalid vcpu_index supplied + ======= ===================================================== KVM_DEV_ARM_VGIC_GRP_NR_IRQS - Attributes: + Attributes: + A value describing the number of interrupts (SGI, PPI and SPI) for this GIC instance, ranging from 64 to 1024, in increments of 32. Errors: - -EINVAL: Value set is out of the expected range - -EBUSY: Value has already be set, or GIC has already been initialized - with default values. + + ======= ============================================================= + -EINVAL Value set is out of the expected range + -EBUSY Value has already be set, or GIC has already been initialized + with default values. + ======= ============================================================= KVM_DEV_ARM_VGIC_GRP_CTRL - Attributes: + Attributes: + KVM_DEV_ARM_VGIC_CTRL_INIT request the initialization of the VGIC or ITS, no additional parameter in kvm_device_attr.addr. + Errors: - -ENXIO: VGIC not properly configured as required prior to calling - this attribute - -ENODEV: no online VCPU - -ENOMEM: memory shortage when allocating vgic internal data + + ======= ========================================================= + -ENXIO VGIC not properly configured as required prior to calling + this attribute + -ENODEV no online VCPU + -ENOMEM memory shortage when allocating vgic internal data + ======= ========================================================= diff --git a/Documentation/virt/kvm/devices/index.rst b/Documentation/virt/kvm/devices/index.rst new file mode 100644 index 000000000000..192cda7405c8 --- /dev/null +++ b/Documentation/virt/kvm/devices/index.rst @@ -0,0 +1,19 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======= +Devices +======= + +.. toctree:: + :maxdepth: 2 + + arm-vgic-its + arm-vgic + arm-vgic-v3 + mpic + s390_flic + vcpu + vfio + vm + xics + xive diff --git a/Documentation/virt/kvm/devices/mpic.txt b/Documentation/virt/kvm/devices/mpic.rst index 8257397adc3c..55cefe030d41 100644 --- a/Documentation/virt/kvm/devices/mpic.txt +++ b/Documentation/virt/kvm/devices/mpic.rst @@ -1,9 +1,13 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========================= MPIC interrupt controller ========================= Device types supported: - KVM_DEV_TYPE_FSL_MPIC_20 Freescale MPIC v2.0 - KVM_DEV_TYPE_FSL_MPIC_42 Freescale MPIC v4.2 + + - KVM_DEV_TYPE_FSL_MPIC_20 Freescale MPIC v2.0 + - KVM_DEV_TYPE_FSL_MPIC_42 Freescale MPIC v4.2 Only one MPIC instance, of any type, may be instantiated. The created MPIC will act as the system interrupt controller, connecting to each @@ -11,7 +15,8 @@ vcpu's interrupt inputs. Groups: KVM_DEV_MPIC_GRP_MISC - Attributes: + Attributes: + KVM_DEV_MPIC_BASE_ADDR (rw, 64-bit) Base address of the 256 KiB MPIC register space. Must be naturally aligned. A value of zero disables the mapping. diff --git a/Documentation/virt/kvm/devices/s390_flic.txt b/Documentation/virt/kvm/devices/s390_flic.rst index a4e20a090174..954190da7d04 100644 --- a/Documentation/virt/kvm/devices/s390_flic.txt +++ b/Documentation/virt/kvm/devices/s390_flic.rst @@ -1,3 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +==================================== FLIC (floating interrupt controller) ==================================== @@ -31,8 +34,10 @@ Groups: Copies all floating interrupts into a buffer provided by userspace. When the buffer is too small it returns -ENOMEM, which is the indication for userspace to try again with a bigger buffer. + -ENOBUFS is returned when the allocation of a kernelspace buffer has failed. + -EFAULT is returned when copying data to userspace failed. All interrupts remain pending, i.e. are not deleted from the list of currently pending interrupts. @@ -60,38 +65,41 @@ Groups: KVM_DEV_FLIC_ADAPTER_REGISTER Register an I/O adapter interrupt source. Takes a kvm_s390_io_adapter - describing the adapter to register: + describing the adapter to register:: -struct kvm_s390_io_adapter { - __u32 id; - __u8 isc; - __u8 maskable; - __u8 swap; - __u8 flags; -}; + struct kvm_s390_io_adapter { + __u32 id; + __u8 isc; + __u8 maskable; + __u8 swap; + __u8 flags; + }; id contains the unique id for the adapter, isc the I/O interruption subclass to use, maskable whether this adapter may be masked (interrupts turned off), swap whether the indicators need to be byte swapped, and flags contains further characteristics of the adapter. + Currently defined values for 'flags' are: + - KVM_S390_ADAPTER_SUPPRESSIBLE: adapter is subject to AIS (adapter-interrupt-suppression) facility. This flag only has an effect if the AIS capability is enabled. + Unknown flag values are ignored. KVM_DEV_FLIC_ADAPTER_MODIFY Modifies attributes of an existing I/O adapter interrupt source. Takes - a kvm_s390_io_adapter_req specifying the adapter and the operation: + a kvm_s390_io_adapter_req specifying the adapter and the operation:: -struct kvm_s390_io_adapter_req { - __u32 id; - __u8 type; - __u8 mask; - __u16 pad0; - __u64 addr; -}; + struct kvm_s390_io_adapter_req { + __u32 id; + __u8 type; + __u8 mask; + __u16 pad0; + __u64 addr; + }; id specifies the adapter and type the operation. The supported operations are: @@ -103,8 +111,9 @@ struct kvm_s390_io_adapter_req { perform a gmap translation for the guest address provided in addr, pin a userspace page for the translated address and add it to the list of mappings - Note: A new mapping will be created unconditionally; therefore, - the calling code should avoid making duplicate mappings. + + .. note:: A new mapping will be created unconditionally; therefore, + the calling code should avoid making duplicate mappings. KVM_S390_IO_ADAPTER_UNMAP release a userspace page for the translated address specified in addr @@ -112,16 +121,17 @@ struct kvm_s390_io_adapter_req { KVM_DEV_FLIC_AISM modify the adapter-interruption-suppression mode for a given isc if the - AIS capability is enabled. Takes a kvm_s390_ais_req describing: + AIS capability is enabled. Takes a kvm_s390_ais_req describing:: -struct kvm_s390_ais_req { - __u8 isc; - __u16 mode; -}; + struct kvm_s390_ais_req { + __u8 isc; + __u16 mode; + }; isc contains the target I/O interruption subclass, mode the target adapter-interruption-suppression mode. The following modes are currently supported: + - KVM_S390_AIS_MODE_ALL: ALL-Interruptions Mode, i.e. airq injection is always allowed; - KVM_S390_AIS_MODE_SINGLE: SINGLE-Interruption Mode, i.e. airq @@ -139,12 +149,12 @@ struct kvm_s390_ais_req { KVM_DEV_FLIC_AISM_ALL Gets or sets the adapter-interruption-suppression mode for all ISCs. Takes - a kvm_s390_ais_all describing: + a kvm_s390_ais_all describing:: -struct kvm_s390_ais_all { - __u8 simm; /* Single-Interruption-Mode mask */ - __u8 nimm; /* No-Interruption-Mode mask * -}; + struct kvm_s390_ais_all { + __u8 simm; /* Single-Interruption-Mode mask */ + __u8 nimm; /* No-Interruption-Mode mask * + }; simm contains Single-Interruption-Mode mask for all ISCs, nimm contains No-Interruption-Mode mask for all ISCs. Each bit in simm and nimm corresponds @@ -159,5 +169,5 @@ ENXIO, as specified in the API documentation). It is not possible to conclude that a FLIC operation is unavailable based on the error code resulting from a usage attempt. -Note: The KVM_DEV_FLIC_CLEAR_IO_IRQ ioctl will return EINVAL in case a zero -schid is specified. +.. note:: The KVM_DEV_FLIC_CLEAR_IO_IRQ ioctl will return EINVAL in case a + zero schid is specified. diff --git a/Documentation/virt/kvm/devices/vcpu.rst b/Documentation/virt/kvm/devices/vcpu.rst new file mode 100644 index 000000000000..9963e680770a --- /dev/null +++ b/Documentation/virt/kvm/devices/vcpu.rst @@ -0,0 +1,114 @@ +.. SPDX-License-Identifier: GPL-2.0 + +====================== +Generic vcpu interface +====================== + +The virtual cpu "device" also accepts the ioctls KVM_SET_DEVICE_ATTR, +KVM_GET_DEVICE_ATTR, and KVM_HAS_DEVICE_ATTR. The interface uses the same struct +kvm_device_attr as other devices, but targets VCPU-wide settings and controls. + +The groups and attributes per virtual cpu, if any, are architecture specific. + +1. GROUP: KVM_ARM_VCPU_PMU_V3_CTRL +================================== + +:Architectures: ARM64 + +1.1. ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_IRQ +--------------------------------------- + +:Parameters: in kvm_device_attr.addr the address for PMU overflow interrupt is a + pointer to an int + +Returns: + + ======= ======================================================== + -EBUSY The PMU overflow interrupt is already set + -ENXIO The overflow interrupt not set when attempting to get it + -ENODEV PMUv3 not supported + -EINVAL Invalid PMU overflow interrupt number supplied or + trying to set the IRQ number without using an in-kernel + irqchip. + ======= ======================================================== + +A value describing the PMUv3 (Performance Monitor Unit v3) overflow interrupt +number for this vcpu. This interrupt could be a PPI or SPI, but the interrupt +type must be same for each vcpu. As a PPI, the interrupt number is the same for +all vcpus, while as an SPI it must be a separate number per vcpu. + +1.2 ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_INIT +--------------------------------------- + +:Parameters: no additional parameter in kvm_device_attr.addr + +Returns: + + ======= ====================================================== + -ENODEV PMUv3 not supported or GIC not initialized + -ENXIO PMUv3 not properly configured or in-kernel irqchip not + configured as required prior to calling this attribute + -EBUSY PMUv3 already initialized + ======= ====================================================== + +Request the initialization of the PMUv3. If using the PMUv3 with an in-kernel +virtual GIC implementation, this must be done after initializing the in-kernel +irqchip. + + +2. GROUP: KVM_ARM_VCPU_TIMER_CTRL +================================= + +:Architectures: ARM, ARM64 + +2.1. ATTRIBUTES: KVM_ARM_VCPU_TIMER_IRQ_VTIMER, KVM_ARM_VCPU_TIMER_IRQ_PTIMER +----------------------------------------------------------------------------- + +:Parameters: in kvm_device_attr.addr the address for the timer interrupt is a + pointer to an int + +Returns: + + ======= ================================= + -EINVAL Invalid timer interrupt number + -EBUSY One or more VCPUs has already run + ======= ================================= + +A value describing the architected timer interrupt number when connected to an +in-kernel virtual GIC. These must be a PPI (16 <= intid < 32). Setting the +attribute overrides the default values (see below). + +============================= ========================================== +KVM_ARM_VCPU_TIMER_IRQ_VTIMER The EL1 virtual timer intid (default: 27) +KVM_ARM_VCPU_TIMER_IRQ_PTIMER The EL1 physical timer intid (default: 30) +============================= ========================================== + +Setting the same PPI for different timers will prevent the VCPUs from running. +Setting the interrupt number on a VCPU configures all VCPUs created at that +time to use the number provided for a given timer, overwriting any previously +configured values on other VCPUs. Userspace should configure the interrupt +numbers on at least one VCPU after creating all VCPUs and before running any +VCPUs. + +3. GROUP: KVM_ARM_VCPU_PVTIME_CTRL +================================== + +:Architectures: ARM64 + +3.1 ATTRIBUTE: KVM_ARM_VCPU_PVTIME_IPA +-------------------------------------- + +:Parameters: 64-bit base address + +Returns: + + ======= ====================================== + -ENXIO Stolen time not implemented + -EEXIST Base address already set for this VCPU + -EINVAL Base address not 64 byte aligned + ======= ====================================== + +Specifies the base address of the stolen time structure for this VCPU. The +base address must be 64 byte aligned and exist within a valid guest memory +region. See Documentation/virt/kvm/arm/pvtime.txt for more information +including the layout of the stolen time structure. diff --git a/Documentation/virt/kvm/devices/vcpu.txt b/Documentation/virt/kvm/devices/vcpu.txt deleted file mode 100644 index 6f3bd64a05b0..000000000000 --- a/Documentation/virt/kvm/devices/vcpu.txt +++ /dev/null @@ -1,76 +0,0 @@ -Generic vcpu interface -==================================== - -The virtual cpu "device" also accepts the ioctls KVM_SET_DEVICE_ATTR, -KVM_GET_DEVICE_ATTR, and KVM_HAS_DEVICE_ATTR. The interface uses the same struct -kvm_device_attr as other devices, but targets VCPU-wide settings and controls. - -The groups and attributes per virtual cpu, if any, are architecture specific. - -1. GROUP: KVM_ARM_VCPU_PMU_V3_CTRL -Architectures: ARM64 - -1.1. ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_IRQ -Parameters: in kvm_device_attr.addr the address for PMU overflow interrupt is a - pointer to an int -Returns: -EBUSY: The PMU overflow interrupt is already set - -ENXIO: The overflow interrupt not set when attempting to get it - -ENODEV: PMUv3 not supported - -EINVAL: Invalid PMU overflow interrupt number supplied or - trying to set the IRQ number without using an in-kernel - irqchip. - -A value describing the PMUv3 (Performance Monitor Unit v3) overflow interrupt -number for this vcpu. This interrupt could be a PPI or SPI, but the interrupt -type must be same for each vcpu. As a PPI, the interrupt number is the same for -all vcpus, while as an SPI it must be a separate number per vcpu. - -1.2 ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_INIT -Parameters: no additional parameter in kvm_device_attr.addr -Returns: -ENODEV: PMUv3 not supported or GIC not initialized - -ENXIO: PMUv3 not properly configured or in-kernel irqchip not - configured as required prior to calling this attribute - -EBUSY: PMUv3 already initialized - -Request the initialization of the PMUv3. If using the PMUv3 with an in-kernel -virtual GIC implementation, this must be done after initializing the in-kernel -irqchip. - - -2. GROUP: KVM_ARM_VCPU_TIMER_CTRL -Architectures: ARM,ARM64 - -2.1. ATTRIBUTE: KVM_ARM_VCPU_TIMER_IRQ_VTIMER -2.2. ATTRIBUTE: KVM_ARM_VCPU_TIMER_IRQ_PTIMER -Parameters: in kvm_device_attr.addr the address for the timer interrupt is a - pointer to an int -Returns: -EINVAL: Invalid timer interrupt number - -EBUSY: One or more VCPUs has already run - -A value describing the architected timer interrupt number when connected to an -in-kernel virtual GIC. These must be a PPI (16 <= intid < 32). Setting the -attribute overrides the default values (see below). - -KVM_ARM_VCPU_TIMER_IRQ_VTIMER: The EL1 virtual timer intid (default: 27) -KVM_ARM_VCPU_TIMER_IRQ_PTIMER: The EL1 physical timer intid (default: 30) - -Setting the same PPI for different timers will prevent the VCPUs from running. -Setting the interrupt number on a VCPU configures all VCPUs created at that -time to use the number provided for a given timer, overwriting any previously -configured values on other VCPUs. Userspace should configure the interrupt -numbers on at least one VCPU after creating all VCPUs and before running any -VCPUs. - -3. GROUP: KVM_ARM_VCPU_PVTIME_CTRL -Architectures: ARM64 - -3.1 ATTRIBUTE: KVM_ARM_VCPU_PVTIME_IPA -Parameters: 64-bit base address -Returns: -ENXIO: Stolen time not implemented - -EEXIST: Base address already set for this VCPU - -EINVAL: Base address not 64 byte aligned - -Specifies the base address of the stolen time structure for this VCPU. The -base address must be 64 byte aligned and exist within a valid guest memory -region. See Documentation/virt/kvm/arm/pvtime.txt for more information -including the layout of the stolen time structure. diff --git a/Documentation/virt/kvm/devices/vfio.txt b/Documentation/virt/kvm/devices/vfio.rst index 528c77c8022c..2d20dc561069 100644 --- a/Documentation/virt/kvm/devices/vfio.txt +++ b/Documentation/virt/kvm/devices/vfio.rst @@ -1,8 +1,12 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=================== VFIO virtual device =================== Device types supported: - KVM_DEV_TYPE_VFIO + + - KVM_DEV_TYPE_VFIO Only one VFIO instance may be created per VM. The created device tracks VFIO groups in use by the VM and features of those groups @@ -23,14 +27,15 @@ KVM_DEV_VFIO_GROUP attributes: for the VFIO group. KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: attaches a guest visible TCE table allocated by sPAPR KVM. - kvm_device_attr.addr points to a struct: + kvm_device_attr.addr points to a struct:: + + struct kvm_vfio_spapr_tce { + __s32 groupfd; + __s32 tablefd; + }; - struct kvm_vfio_spapr_tce { - __s32 groupfd; - __s32 tablefd; - }; + where: - where - @groupfd is a file descriptor for a VFIO group; - @tablefd is a file descriptor for a TCE table allocated via - KVM_CREATE_SPAPR_TCE. + - @groupfd is a file descriptor for a VFIO group; + - @tablefd is a file descriptor for a TCE table allocated via + KVM_CREATE_SPAPR_TCE. diff --git a/Documentation/virt/kvm/devices/vm.txt b/Documentation/virt/kvm/devices/vm.rst index 4ffb82b02468..0aa5b1cfd700 100644 --- a/Documentation/virt/kvm/devices/vm.txt +++ b/Documentation/virt/kvm/devices/vm.rst @@ -1,5 +1,8 @@ +.. SPDX-License-Identifier: GPL-2.0 + +==================== Generic vm interface -==================================== +==================== The virtual machine "device" also accepts the ioctls KVM_SET_DEVICE_ATTR, KVM_GET_DEVICE_ATTR, and KVM_HAS_DEVICE_ATTR. The interface uses the same @@ -10,30 +13,38 @@ The groups and attributes per virtual machine, if any, are architecture specific. 1. GROUP: KVM_S390_VM_MEM_CTRL -Architectures: s390 +============================== + +:Architectures: s390 1.1. ATTRIBUTE: KVM_S390_VM_MEM_ENABLE_CMMA -Parameters: none -Returns: -EBUSY if a vcpu is already defined, otherwise 0 +------------------------------------------- + +:Parameters: none +:Returns: -EBUSY if a vcpu is already defined, otherwise 0 Enables Collaborative Memory Management Assist (CMMA) for the virtual machine. 1.2. ATTRIBUTE: KVM_S390_VM_MEM_CLR_CMMA -Parameters: none -Returns: -EINVAL if CMMA was not enabled - 0 otherwise +---------------------------------------- + +:Parameters: none +:Returns: -EINVAL if CMMA was not enabled; + 0 otherwise Clear the CMMA status for all guest pages, so any pages the guest marked as unused are again used any may not be reclaimed by the host. 1.3. ATTRIBUTE KVM_S390_VM_MEM_LIMIT_SIZE -Parameters: in attr->addr the address for the new limit of guest memory -Returns: -EFAULT if the given address is not accessible - -EINVAL if the virtual machine is of type UCONTROL - -E2BIG if the given guest memory is to big for that machine - -EBUSY if a vcpu is already defined - -ENOMEM if not enough memory is available for a new shadow guest mapping - 0 otherwise +----------------------------------------- + +:Parameters: in attr->addr the address for the new limit of guest memory +:Returns: -EFAULT if the given address is not accessible; + -EINVAL if the virtual machine is of type UCONTROL; + -E2BIG if the given guest memory is to big for that machine; + -EBUSY if a vcpu is already defined; + -ENOMEM if not enough memory is available for a new shadow guest mapping; + 0 otherwise. Allows userspace to query the actual limit and set a new limit for the maximum guest memory size. The limit will be rounded up to @@ -42,78 +53,92 @@ the number of page table levels. In the case that there is no limit we will set the limit to KVM_S390_NO_MEM_LIMIT (U64_MAX). 2. GROUP: KVM_S390_VM_CPU_MODEL -Architectures: s390 +=============================== + +:Architectures: s390 2.1. ATTRIBUTE: KVM_S390_VM_CPU_MACHINE (r/o) +--------------------------------------------- -Allows user space to retrieve machine and kvm specific cpu related information: +Allows user space to retrieve machine and kvm specific cpu related information:: -struct kvm_s390_vm_cpu_machine { + struct kvm_s390_vm_cpu_machine { __u64 cpuid; # CPUID of host __u32 ibc; # IBC level range offered by host __u8 pad[4]; __u64 fac_mask[256]; # set of cpu facilities enabled by KVM __u64 fac_list[256]; # set of cpu facilities offered by host -} + } -Parameters: address of buffer to store the machine related cpu data - of type struct kvm_s390_vm_cpu_machine* -Returns: -EFAULT if the given address is not accessible from kernel space - -ENOMEM if not enough memory is available to process the ioctl - 0 in case of success +:Parameters: address of buffer to store the machine related cpu data + of type struct kvm_s390_vm_cpu_machine* +:Returns: -EFAULT if the given address is not accessible from kernel space; + -ENOMEM if not enough memory is available to process the ioctl; + 0 in case of success. 2.2. ATTRIBUTE: KVM_S390_VM_CPU_PROCESSOR (r/w) +=============================================== -Allows user space to retrieve or request to change cpu related information for a vcpu: +Allows user space to retrieve or request to change cpu related information for a vcpu:: -struct kvm_s390_vm_cpu_processor { + struct kvm_s390_vm_cpu_processor { __u64 cpuid; # CPUID currently (to be) used by this vcpu __u16 ibc; # IBC level currently (to be) used by this vcpu __u8 pad[6]; __u64 fac_list[256]; # set of cpu facilities currently (to be) used - # by this vcpu -} + # by this vcpu + } KVM does not enforce or limit the cpu model data in any form. Take the information retrieved by means of KVM_S390_VM_CPU_MACHINE as hint for reasonable configuration setups. Instruction interceptions triggered by additionally set facility bits that are not handled by KVM need to by imlemented in the VM driver code. -Parameters: address of buffer to store/set the processor related cpu - data of type struct kvm_s390_vm_cpu_processor*. -Returns: -EBUSY in case 1 or more vcpus are already activated (only in write case) - -EFAULT if the given address is not accessible from kernel space - -ENOMEM if not enough memory is available to process the ioctl - 0 in case of success +:Parameters: address of buffer to store/set the processor related cpu + data of type struct kvm_s390_vm_cpu_processor*. +:Returns: -EBUSY in case 1 or more vcpus are already activated (only in write case); + -EFAULT if the given address is not accessible from kernel space; + -ENOMEM if not enough memory is available to process the ioctl; + 0 in case of success. + +.. _KVM_S390_VM_CPU_MACHINE_FEAT: 2.3. ATTRIBUTE: KVM_S390_VM_CPU_MACHINE_FEAT (r/o) +-------------------------------------------------- Allows user space to retrieve available cpu features. A feature is available if provided by the hardware and supported by kvm. In theory, cpu features could even be completely emulated by kvm. -struct kvm_s390_vm_cpu_feat { - __u64 feat[16]; # Bitmap (1 = feature available), MSB 0 bit numbering -}; +:: -Parameters: address of a buffer to load the feature list from. -Returns: -EFAULT if the given address is not accessible from kernel space. - 0 in case of success. + struct kvm_s390_vm_cpu_feat { + __u64 feat[16]; # Bitmap (1 = feature available), MSB 0 bit numbering + }; + +:Parameters: address of a buffer to load the feature list from. +:Returns: -EFAULT if the given address is not accessible from kernel space; + 0 in case of success. 2.4. ATTRIBUTE: KVM_S390_VM_CPU_PROCESSOR_FEAT (r/w) +---------------------------------------------------- Allows user space to retrieve or change enabled cpu features for all VCPUs of a VM. Features that are not available cannot be enabled. -See 2.3. for a description of the parameter struct. +See :ref:`KVM_S390_VM_CPU_MACHINE_FEAT` for +a description of the parameter struct. -Parameters: address of a buffer to store/load the feature list from. -Returns: -EFAULT if the given address is not accessible from kernel space. - -EINVAL if a cpu feature that is not available is to be enabled. - -EBUSY if at least one VCPU has already been defined. +:Parameters: address of a buffer to store/load the feature list from. +:Returns: -EFAULT if the given address is not accessible from kernel space; + -EINVAL if a cpu feature that is not available is to be enabled; + -EBUSY if at least one VCPU has already been defined; 0 in case of success. +.. _KVM_S390_VM_CPU_MACHINE_SUBFUNC: + 2.5. ATTRIBUTE: KVM_S390_VM_CPU_MACHINE_SUBFUNC (r/o) +----------------------------------------------------- Allows user space to retrieve available cpu subfunctions without any filtering done by a set IBC. These subfunctions are indicated to the guest VCPU via @@ -126,7 +151,9 @@ contained in the returned struct. If the affected instruction indicates subfunctions via a "test bit" mechanism, the subfunction codes are contained in the returned struct in MSB 0 bit numbering. -struct kvm_s390_vm_cpu_subfunc { +:: + + struct kvm_s390_vm_cpu_subfunc { u8 plo[32]; # always valid (ESA/390 feature) u8 ptff[16]; # valid with TOD-clock steering u8 kmac[16]; # valid with Message-Security-Assist @@ -143,13 +170,14 @@ struct kvm_s390_vm_cpu_subfunc { u8 kma[16]; # valid with Message-Security-Assist-Extension 8 u8 kdsa[16]; # valid with Message-Security-Assist-Extension 9 u8 reserved[1792]; # reserved for future instructions -}; + }; -Parameters: address of a buffer to load the subfunction blocks from. -Returns: -EFAULT if the given address is not accessible from kernel space. +:Parameters: address of a buffer to load the subfunction blocks from. +:Returns: -EFAULT if the given address is not accessible from kernel space; 0 in case of success. 2.6. ATTRIBUTE: KVM_S390_VM_CPU_PROCESSOR_SUBFUNC (r/w) +------------------------------------------------------- Allows user space to retrieve or change cpu subfunctions to be indicated for all VCPUs of a VM. This attribute will only be available if kernel and @@ -164,107 +192,125 @@ As long as no data has been written, a read will fail. The IBC will be used to determine available subfunctions in this case, this will guarantee backward compatibility. -See 2.5. for a description of the parameter struct. +See :ref:`KVM_S390_VM_CPU_MACHINE_SUBFUNC` for a +description of the parameter struct. -Parameters: address of a buffer to store/load the subfunction blocks from. -Returns: -EFAULT if the given address is not accessible from kernel space. - -EINVAL when reading, if there was no write yet. - -EBUSY if at least one VCPU has already been defined. +:Parameters: address of a buffer to store/load the subfunction blocks from. +:Returns: -EFAULT if the given address is not accessible from kernel space; + -EINVAL when reading, if there was no write yet; + -EBUSY if at least one VCPU has already been defined; 0 in case of success. 3. GROUP: KVM_S390_VM_TOD -Architectures: s390 +========================= + +:Architectures: s390 3.1. ATTRIBUTE: KVM_S390_VM_TOD_HIGH +------------------------------------ Allows user space to set/get the TOD clock extension (u8) (superseded by KVM_S390_VM_TOD_EXT). -Parameters: address of a buffer in user space to store the data (u8) to -Returns: -EFAULT if the given address is not accessible from kernel space +:Parameters: address of a buffer in user space to store the data (u8) to +:Returns: -EFAULT if the given address is not accessible from kernel space; -EINVAL if setting the TOD clock extension to != 0 is not supported 3.2. ATTRIBUTE: KVM_S390_VM_TOD_LOW +----------------------------------- Allows user space to set/get bits 0-63 of the TOD clock register as defined in the POP (u64). -Parameters: address of a buffer in user space to store the data (u64) to -Returns: -EFAULT if the given address is not accessible from kernel space +:Parameters: address of a buffer in user space to store the data (u64) to +:Returns: -EFAULT if the given address is not accessible from kernel space 3.3. ATTRIBUTE: KVM_S390_VM_TOD_EXT +----------------------------------- + Allows user space to set/get bits 0-63 of the TOD clock register as defined in the POP (u64). If the guest CPU model supports the TOD clock extension (u8), it also allows user space to get/set it. If the guest CPU model does not support it, it is stored as 0 and not allowed to be set to a value != 0. -Parameters: address of a buffer in user space to store the data - (kvm_s390_vm_tod_clock) to -Returns: -EFAULT if the given address is not accessible from kernel space +:Parameters: address of a buffer in user space to store the data + (kvm_s390_vm_tod_clock) to +:Returns: -EFAULT if the given address is not accessible from kernel space; -EINVAL if setting the TOD clock extension to != 0 is not supported 4. GROUP: KVM_S390_VM_CRYPTO -Architectures: s390 +============================ + +:Architectures: s390 4.1. ATTRIBUTE: KVM_S390_VM_CRYPTO_ENABLE_AES_KW (w/o) +------------------------------------------------------ Allows user space to enable aes key wrapping, including generating a new wrapping key. -Parameters: none -Returns: 0 +:Parameters: none +:Returns: 0 4.2. ATTRIBUTE: KVM_S390_VM_CRYPTO_ENABLE_DEA_KW (w/o) +------------------------------------------------------ Allows user space to enable dea key wrapping, including generating a new wrapping key. -Parameters: none -Returns: 0 +:Parameters: none +:Returns: 0 4.3. ATTRIBUTE: KVM_S390_VM_CRYPTO_DISABLE_AES_KW (w/o) +------------------------------------------------------- Allows user space to disable aes key wrapping, clearing the wrapping key. -Parameters: none -Returns: 0 +:Parameters: none +:Returns: 0 4.4. ATTRIBUTE: KVM_S390_VM_CRYPTO_DISABLE_DEA_KW (w/o) +------------------------------------------------------- Allows user space to disable dea key wrapping, clearing the wrapping key. -Parameters: none -Returns: 0 +:Parameters: none +:Returns: 0 5. GROUP: KVM_S390_VM_MIGRATION -Architectures: s390 +=============================== + +:Architectures: s390 5.1. ATTRIBUTE: KVM_S390_VM_MIGRATION_STOP (w/o) +------------------------------------------------ Allows userspace to stop migration mode, needed for PGSTE migration. Setting this attribute when migration mode is not active will have no effects. -Parameters: none -Returns: 0 +:Parameters: none +:Returns: 0 5.2. ATTRIBUTE: KVM_S390_VM_MIGRATION_START (w/o) +------------------------------------------------- Allows userspace to start migration mode, needed for PGSTE migration. Setting this attribute when migration mode is already active will have no effects. -Parameters: none -Returns: -ENOMEM if there is not enough free memory to start migration mode - -EINVAL if the state of the VM is invalid (e.g. no memory defined) +:Parameters: none +:Returns: -ENOMEM if there is not enough free memory to start migration mode; + -EINVAL if the state of the VM is invalid (e.g. no memory defined); 0 in case of success. 5.3. ATTRIBUTE: KVM_S390_VM_MIGRATION_STATUS (r/o) +-------------------------------------------------- Allows userspace to query the status of migration mode. -Parameters: address of a buffer in user space to store the data (u64) to; - the data itself is either 0 if migration mode is disabled or 1 - if it is enabled -Returns: -EFAULT if the given address is not accessible from kernel space +:Parameters: address of a buffer in user space to store the data (u64) to; + the data itself is either 0 if migration mode is disabled or 1 + if it is enabled +:Returns: -EFAULT if the given address is not accessible from kernel space; 0 in case of success. diff --git a/Documentation/virt/kvm/devices/xics.txt b/Documentation/virt/kvm/devices/xics.rst index 423332dda7bc..2d6927e0b776 100644 --- a/Documentation/virt/kvm/devices/xics.txt +++ b/Documentation/virt/kvm/devices/xics.rst @@ -1,20 +1,31 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========================= XICS interrupt controller +========================= Device type supported: KVM_DEV_TYPE_XICS Groups: 1. KVM_DEV_XICS_GRP_SOURCES - Attributes: One per interrupt source, indexed by the source number. + Attributes: + One per interrupt source, indexed by the source number. 2. KVM_DEV_XICS_GRP_CTRL - Attributes: - 2.1 KVM_DEV_XICS_NR_SERVERS (write only) + Attributes: + + 2.1 KVM_DEV_XICS_NR_SERVERS (write only) + The kvm_device_attr.addr points to a __u32 value which is the number of interrupt server numbers (ie, highest possible vcpu id plus one). + Errors: - -EINVAL: Value greater than KVM_MAX_VCPU_ID. - -EFAULT: Invalid user pointer for attr->addr. - -EBUSY: A vcpu is already connected to the device. + + ======= ========================================== + -EINVAL Value greater than KVM_MAX_VCPU_ID. + -EFAULT Invalid user pointer for attr->addr. + -EBUSY A vcpu is already connected to the device. + ======= ========================================== This device emulates the XICS (eXternal Interrupt Controller Specification) defined in PAPR. The XICS has a set of interrupt @@ -53,24 +64,29 @@ the interrupt source number. The 64 bit state word has the following bitfields, starting from the least-significant end of the word: * Destination (server number), 32 bits + This specifies where the interrupt should be sent, and is the interrupt server number specified for the destination vcpu. * Priority, 8 bits + This is the priority specified for this interrupt source, where 0 is the highest priority and 255 is the lowest. An interrupt with a priority of 255 will never be delivered. * Level sensitive flag, 1 bit + This bit is 1 for a level-sensitive interrupt source, or 0 for edge-sensitive (or MSI). * Masked flag, 1 bit + This bit is set to 1 if the interrupt is masked (cannot be delivered regardless of its priority), for example by the ibm,int-off RTAS call, or 0 if it is not masked. * Pending flag, 1 bit + This bit is 1 if the source has a pending interrupt, otherwise 0. Only one XICS instance may be created per VM. diff --git a/Documentation/virt/kvm/devices/xive.txt b/Documentation/virt/kvm/devices/xive.rst index f5d1d6b5af61..8bdf3dc38f01 100644 --- a/Documentation/virt/kvm/devices/xive.txt +++ b/Documentation/virt/kvm/devices/xive.rst @@ -1,8 +1,11 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=========================================================== POWER9 eXternal Interrupt Virtualization Engine (XIVE Gen1) -========================================================== +=========================================================== Device types supported: - KVM_DEV_TYPE_XIVE POWER9 XIVE Interrupt Controller generation 1 + - KVM_DEV_TYPE_XIVE POWER9 XIVE Interrupt Controller generation 1 This device acts as a VM interrupt controller. It provides the KVM interface to configure the interrupt sources of a VM in the underlying @@ -64,72 +67,100 @@ the legacy interrupt mode, referred as XICS (POWER7/8). * Groups: - 1. KVM_DEV_XIVE_GRP_CTRL - Provides global controls on the device +1. KVM_DEV_XIVE_GRP_CTRL + Provides global controls on the device + Attributes: 1.1 KVM_DEV_XIVE_RESET (write only) Resets the interrupt controller configuration for sources and event queues. To be used by kexec and kdump. + Errors: none 1.2 KVM_DEV_XIVE_EQ_SYNC (write only) Sync all the sources and queues and mark the EQ pages dirty. This to make sure that a consistent memory state is captured when migrating the VM. + Errors: none 1.3 KVM_DEV_XIVE_NR_SERVERS (write only) The kvm_device_attr.addr points to a __u32 value which is the number of interrupt server numbers (ie, highest possible vcpu id plus one). + Errors: - -EINVAL: Value greater than KVM_MAX_VCPU_ID. - -EFAULT: Invalid user pointer for attr->addr. - -EBUSY: A vCPU is already connected to the device. - 2. KVM_DEV_XIVE_GRP_SOURCE (write only) - Initializes a new source in the XIVE device and mask it. + ======= ========================================== + -EINVAL Value greater than KVM_MAX_VCPU_ID. + -EFAULT Invalid user pointer for attr->addr. + -EBUSY A vCPU is already connected to the device. + ======= ========================================== + +2. KVM_DEV_XIVE_GRP_SOURCE (write only) + Initializes a new source in the XIVE device and mask it. + Attributes: Interrupt source number (64-bit) - The kvm_device_attr.addr points to a __u64 value: - bits: | 63 .... 2 | 1 | 0 - values: | unused | level | type + + The kvm_device_attr.addr points to a __u64 value:: + + bits: | 63 .... 2 | 1 | 0 + values: | unused | level | type + - type: 0:MSI 1:LSI - level: assertion level in case of an LSI. + Errors: - -E2BIG: Interrupt source number is out of range - -ENOMEM: Could not create a new source block - -EFAULT: Invalid user pointer for attr->addr. - -ENXIO: Could not allocate underlying HW interrupt - 3. KVM_DEV_XIVE_GRP_SOURCE_CONFIG (write only) - Configures source targeting + ======= ========================================== + -E2BIG Interrupt source number is out of range + -ENOMEM Could not create a new source block + -EFAULT Invalid user pointer for attr->addr. + -ENXIO Could not allocate underlying HW interrupt + ======= ========================================== + +3. KVM_DEV_XIVE_GRP_SOURCE_CONFIG (write only) + Configures source targeting + Attributes: Interrupt source number (64-bit) - The kvm_device_attr.addr points to a __u64 value: - bits: | 63 .... 33 | 32 | 31 .. 3 | 2 .. 0 - values: | eisn | mask | server | priority + + The kvm_device_attr.addr points to a __u64 value:: + + bits: | 63 .... 33 | 32 | 31 .. 3 | 2 .. 0 + values: | eisn | mask | server | priority + - priority: 0-7 interrupt priority level - server: CPU number chosen to handle the interrupt - mask: mask flag (unused) - eisn: Effective Interrupt Source Number + Errors: - -ENOENT: Unknown source number - -EINVAL: Not initialized source number - -EINVAL: Invalid priority - -EINVAL: Invalid CPU number. - -EFAULT: Invalid user pointer for attr->addr. - -ENXIO: CPU event queues not configured or configuration of the - underlying HW interrupt failed - -EBUSY: No CPU available to serve interrupt - - 4. KVM_DEV_XIVE_GRP_EQ_CONFIG (read-write) - Configures an event queue of a CPU + + ======= ======================================================= + -ENOENT Unknown source number + -EINVAL Not initialized source number + -EINVAL Invalid priority + -EINVAL Invalid CPU number. + -EFAULT Invalid user pointer for attr->addr. + -ENXIO CPU event queues not configured or configuration of the + underlying HW interrupt failed + -EBUSY No CPU available to serve interrupt + ======= ======================================================= + +4. KVM_DEV_XIVE_GRP_EQ_CONFIG (read-write) + Configures an event queue of a CPU + Attributes: EQ descriptor identifier (64-bit) - The EQ descriptor identifier is a tuple (server, priority) : - bits: | 63 .... 32 | 31 .. 3 | 2 .. 0 - values: | unused | server | priority - The kvm_device_attr.addr points to : + + The EQ descriptor identifier is a tuple (server, priority):: + + bits: | 63 .... 32 | 31 .. 3 | 2 .. 0 + values: | unused | server | priority + + The kvm_device_attr.addr points to:: + struct kvm_ppc_xive_eq { __u32 flags; __u32 qshift; @@ -138,8 +169,9 @@ the legacy interrupt mode, referred as XICS (POWER7/8). __u32 qindex; __u8 pad[40]; }; + - flags: queue flags - KVM_XIVE_EQ_ALWAYS_NOTIFY (required) + KVM_XIVE_EQ_ALWAYS_NOTIFY (required) forces notification without using the coalescing mechanism provided by the XIVE END ESBs. - qshift: queue size (power of 2) @@ -147,22 +179,31 @@ the legacy interrupt mode, referred as XICS (POWER7/8). - qtoggle: current queue toggle bit - qindex: current queue index - pad: reserved for future use + Errors: - -ENOENT: Invalid CPU number - -EINVAL: Invalid priority - -EINVAL: Invalid flags - -EINVAL: Invalid queue size - -EINVAL: Invalid queue address - -EFAULT: Invalid user pointer for attr->addr. - -EIO: Configuration of the underlying HW failed - - 5. KVM_DEV_XIVE_GRP_SOURCE_SYNC (write only) - Synchronize the source to flush event notifications + + ======= ========================================= + -ENOENT Invalid CPU number + -EINVAL Invalid priority + -EINVAL Invalid flags + -EINVAL Invalid queue size + -EINVAL Invalid queue address + -EFAULT Invalid user pointer for attr->addr. + -EIO Configuration of the underlying HW failed + ======= ========================================= + +5. KVM_DEV_XIVE_GRP_SOURCE_SYNC (write only) + Synchronize the source to flush event notifications + Attributes: Interrupt source number (64-bit) + Errors: - -ENOENT: Unknown source number - -EINVAL: Not initialized source number + + ======= ============================= + -ENOENT Unknown source number + -EINVAL Not initialized source number + ======= ============================= * VCPU state @@ -175,11 +216,12 @@ the legacy interrupt mode, referred as XICS (POWER7/8). as it synthesizes the priorities of the pending interrupts. We capture a bit more to report debug information. - KVM_REG_PPC_VP_STATE (2 * 64bits) - bits: | 63 .... 32 | 31 .... 0 | - values: | TIMA word0 | TIMA word1 | - bits: | 127 .......... 64 | - values: | unused | + KVM_REG_PPC_VP_STATE (2 * 64bits):: + + bits: | 63 .... 32 | 31 .... 0 | + values: | TIMA word0 | TIMA word1 | + bits: | 127 .......... 64 | + values: | unused | * Migration: @@ -196,7 +238,7 @@ the legacy interrupt mode, referred as XICS (POWER7/8). 3. Capture the state of the source targeting, the EQs configuration and the state of thread interrupt context registers. - Restore is similar : + Restore is similar: 1. Restore the EQ configuration. As targeting depends on it. 2. Restore targeting diff --git a/Documentation/virt/kvm/halt-polling.txt b/Documentation/virt/kvm/halt-polling.rst index 4f791b128dd2..4922e4a15f18 100644 --- a/Documentation/virt/kvm/halt-polling.txt +++ b/Documentation/virt/kvm/halt-polling.rst @@ -1,3 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=========================== The KVM halt polling system =========================== @@ -68,7 +71,8 @@ steady state polling interval but will only really do a good job for wakeups which come at an approximately constant rate, otherwise there will be constant adjustment of the polling interval. -[0] total block time: the time between when the halt polling function is +[0] total block time: + the time between when the halt polling function is invoked and a wakeup source received (irrespective of whether the scheduler is invoked within that function). @@ -81,31 +85,32 @@ shrunk. These variables are defined in include/linux/kvm_host.h and as module parameters in virt/kvm/kvm_main.c, or arch/powerpc/kvm/book3s_hv.c in the powerpc kvm-hv case. -Module Parameter | Description | Default Value --------------------------------------------------------------------------------- -halt_poll_ns | The global max polling | KVM_HALT_POLL_NS_DEFAULT - | interval which defines | - | the ceiling value of the | - | polling interval for | (per arch value) - | each vcpu. | --------------------------------------------------------------------------------- -halt_poll_ns_grow | The value by which the | 2 - | halt polling interval is | - | multiplied in the | - | grow_halt_poll_ns() | - | function. | --------------------------------------------------------------------------------- -halt_poll_ns_grow_start | The initial value to grow | 10000 - | to from zero in the | - | grow_halt_poll_ns() | - | function. | --------------------------------------------------------------------------------- -halt_poll_ns_shrink | The value by which the | 0 - | halt polling interval is | - | divided in the | - | shrink_halt_poll_ns() | - | function. | --------------------------------------------------------------------------------- ++-----------------------+---------------------------+-------------------------+ +|Module Parameter | Description | Default Value | ++-----------------------+---------------------------+-------------------------+ +|halt_poll_ns | The global max polling | KVM_HALT_POLL_NS_DEFAULT| +| | interval which defines | | +| | the ceiling value of the | | +| | polling interval for | (per arch value) | +| | each vcpu. | | ++-----------------------+---------------------------+-------------------------+ +|halt_poll_ns_grow | The value by which the | 2 | +| | halt polling interval is | | +| | multiplied in the | | +| | grow_halt_poll_ns() | | +| | function. | | ++-----------------------+---------------------------+-------------------------+ +|halt_poll_ns_grow_start| The initial value to grow | 10000 | +| | to from zero in the | | +| | grow_halt_poll_ns() | | +| | function. | | ++-----------------------+---------------------------+-------------------------+ +|halt_poll_ns_shrink | The value by which the | 0 | +| | halt polling interval is | | +| | divided in the | | +| | shrink_halt_poll_ns() | | +| | function. | | ++-----------------------+---------------------------+-------------------------+ These module parameters can be set from the debugfs files in: @@ -117,20 +122,19 @@ Note: that these module parameters are system wide values and are not able to Further Notes ============= -- Care should be taken when setting the halt_poll_ns module parameter as a -large value has the potential to drive the cpu usage to 100% on a machine which -would be almost entirely idle otherwise. This is because even if a guest has -wakeups during which very little work is done and which are quite far apart, if -the period is shorter than the global max polling interval (halt_poll_ns) then -the host will always poll for the entire block time and thus cpu utilisation -will go to 100%. - -- Halt polling essentially presents a trade off between power usage and latency -and the module parameters should be used to tune the affinity for this. Idle -cpu time is essentially converted to host kernel time with the aim of decreasing -latency when entering the guest. - -- Halt polling will only be conducted by the host when no other tasks are -runnable on that cpu, otherwise the polling will cease immediately and -schedule will be invoked to allow that other task to run. Thus this doesn't -allow a guest to denial of service the cpu. +- Care should be taken when setting the halt_poll_ns module parameter as a large value + has the potential to drive the cpu usage to 100% on a machine which would be almost + entirely idle otherwise. This is because even if a guest has wakeups during which very + little work is done and which are quite far apart, if the period is shorter than the + global max polling interval (halt_poll_ns) then the host will always poll for the + entire block time and thus cpu utilisation will go to 100%. + +- Halt polling essentially presents a trade off between power usage and latency and + the module parameters should be used to tune the affinity for this. Idle cpu time is + essentially converted to host kernel time with the aim of decreasing latency when + entering the guest. + +- Halt polling will only be conducted by the host when no other tasks are runnable on + that cpu, otherwise the polling will cease immediately and schedule will be invoked to + allow that other task to run. Thus this doesn't allow a guest to denial of service the + cpu. diff --git a/Documentation/virt/kvm/hypercalls.txt b/Documentation/virt/kvm/hypercalls.rst index 5f6d291bd004..dbaf207e560d 100644 --- a/Documentation/virt/kvm/hypercalls.txt +++ b/Documentation/virt/kvm/hypercalls.rst @@ -1,5 +1,9 @@ -Linux KVM Hypercall: +.. SPDX-License-Identifier: GPL-2.0 + +=================== +Linux KVM Hypercall =================== + X86: KVM Hypercalls have a three-byte sequence of either the vmcall or the vmmcall instruction. The hypervisor can replace it with instructions that are @@ -20,7 +24,7 @@ S390: For further information on the S390 diagnose call as supported by KVM, refer to Documentation/virt/kvm/s390-diag.txt. - PowerPC: +PowerPC: It uses R3-R10 and hypercall number in R11. R4-R11 are used as output registers. Return value is placed in R3. @@ -34,7 +38,8 @@ MIPS: the return value is placed in $2 (v0). KVM Hypercalls Documentation -=========================== +============================ + The template for each hypercall is: 1. Hypercall name. 2. Architecture(s) @@ -43,56 +48,64 @@ The template for each hypercall is: 1. KVM_HC_VAPIC_POLL_IRQ ------------------------ -Architecture: x86 -Status: active -Purpose: Trigger guest exit so that the host can check for pending -interrupts on reentry. + +:Architecture: x86 +:Status: active +:Purpose: Trigger guest exit so that the host can check for pending + interrupts on reentry. 2. KVM_HC_MMU_OP ------------------------- -Architecture: x86 -Status: deprecated. -Purpose: Support MMU operations such as writing to PTE, -flushing TLB, release PT. +---------------- + +:Architecture: x86 +:Status: deprecated. +:Purpose: Support MMU operations such as writing to PTE, + flushing TLB, release PT. 3. KVM_HC_FEATURES ------------------------- -Architecture: PPC -Status: active -Purpose: Expose hypercall availability to the guest. On x86 platforms, cpuid -used to enumerate which hypercalls are available. On PPC, either device tree -based lookup ( which is also what EPAPR dictates) OR KVM specific enumeration -mechanism (which is this hypercall) can be used. +------------------ + +:Architecture: PPC +:Status: active +:Purpose: Expose hypercall availability to the guest. On x86 platforms, cpuid + used to enumerate which hypercalls are available. On PPC, either + device tree based lookup ( which is also what EPAPR dictates) + OR KVM specific enumeration mechanism (which is this hypercall) + can be used. 4. KVM_HC_PPC_MAP_MAGIC_PAGE ------------------------- -Architecture: PPC -Status: active -Purpose: To enable communication between the hypervisor and guest there is a -shared page that contains parts of supervisor visible register state. -The guest can map this shared page to access its supervisor register through -memory using this hypercall. +---------------------------- + +:Architecture: PPC +:Status: active +:Purpose: To enable communication between the hypervisor and guest there is a + shared page that contains parts of supervisor visible register state. + The guest can map this shared page to access its supervisor register + through memory using this hypercall. 5. KVM_HC_KICK_CPU ------------------------- -Architecture: x86 -Status: active -Purpose: Hypercall used to wakeup a vcpu from HLT state -Usage example : A vcpu of a paravirtualized guest that is busywaiting in guest -kernel mode for an event to occur (ex: a spinlock to become available) can -execute HLT instruction once it has busy-waited for more than a threshold -time-interval. Execution of HLT instruction would cause the hypervisor to put -the vcpu to sleep until occurrence of an appropriate event. Another vcpu of the -same guest can wakeup the sleeping vcpu by issuing KVM_HC_KICK_CPU hypercall, -specifying APIC ID (a1) of the vcpu to be woken up. An additional argument (a0) -is used in the hypercall for future use. +------------------ + +:Architecture: x86 +:Status: active +:Purpose: Hypercall used to wakeup a vcpu from HLT state +:Usage example: + A vcpu of a paravirtualized guest that is busywaiting in guest + kernel mode for an event to occur (ex: a spinlock to become available) can + execute HLT instruction once it has busy-waited for more than a threshold + time-interval. Execution of HLT instruction would cause the hypervisor to put + the vcpu to sleep until occurrence of an appropriate event. Another vcpu of the + same guest can wakeup the sleeping vcpu by issuing KVM_HC_KICK_CPU hypercall, + specifying APIC ID (a1) of the vcpu to be woken up. An additional argument (a0) + is used in the hypercall for future use. 6. KVM_HC_CLOCK_PAIRING ------------------------- -Architecture: x86 -Status: active -Purpose: Hypercall used to synchronize host and guest clocks. +----------------------- +:Architecture: x86 +:Status: active +:Purpose: Hypercall used to synchronize host and guest clocks. + Usage: a0: guest physical address where host copies @@ -101,6 +114,8 @@ a0: guest physical address where host copies a1: clock_type, ATM only KVM_CLOCK_PAIRING_WALLCLOCK (0) is supported (corresponding to the host's CLOCK_REALTIME clock). + :: + struct kvm_clock_pairing { __s64 sec; __s64 nsec; @@ -123,15 +138,16 @@ Returns KVM_EOPNOTSUPP if the host does not use TSC clocksource, or if clock type is different than KVM_CLOCK_PAIRING_WALLCLOCK. 6. KVM_HC_SEND_IPI ------------------------- -Architecture: x86 -Status: active -Purpose: Send IPIs to multiple vCPUs. +------------------ + +:Architecture: x86 +:Status: active +:Purpose: Send IPIs to multiple vCPUs. -a0: lower part of the bitmap of destination APIC IDs -a1: higher part of the bitmap of destination APIC IDs -a2: the lowest APIC ID in bitmap -a3: APIC ICR +- a0: lower part of the bitmap of destination APIC IDs +- a1: higher part of the bitmap of destination APIC IDs +- a2: the lowest APIC ID in bitmap +- a3: APIC ICR The hypercall lets a guest send multicast IPIs, with at most 128 128 destinations per hypercall in 64-bit mode and 64 vCPUs per @@ -143,12 +159,13 @@ corresponds to the APIC ID a2+1, and so on. Returns the number of CPUs to which the IPIs were delivered successfully. 7. KVM_HC_SCHED_YIELD ------------------------- -Architecture: x86 -Status: active -Purpose: Hypercall used to yield if the IPI target vCPU is preempted +--------------------- + +:Architecture: x86 +:Status: active +:Purpose: Hypercall used to yield if the IPI target vCPU is preempted a0: destination APIC ID -Usage example: When sending a call-function IPI-many to vCPUs, yield if -any of the IPI target vCPUs was preempted. +:Usage example: When sending a call-function IPI-many to vCPUs, yield if + any of the IPI target vCPUs was preempted. diff --git a/Documentation/virt/kvm/index.rst b/Documentation/virt/kvm/index.rst index ada224a511fe..774deaebf7fa 100644 --- a/Documentation/virt/kvm/index.rst +++ b/Documentation/virt/kvm/index.rst @@ -7,6 +7,22 @@ KVM .. toctree:: :maxdepth: 2 + api amd-memory-encryption cpuid + halt-polling + hypercalls + locking + mmu + msr + nested-vmx + ppc-pv + s390-diag + timekeeping vcpu-requests + + review-checklist + + arm/index + + devices/index diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst new file mode 100644 index 000000000000..c02291beac3f --- /dev/null +++ b/Documentation/virt/kvm/locking.rst @@ -0,0 +1,243 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================= +KVM Lock Overview +================= + +1. Acquisition Orders +--------------------- + +The acquisition orders for mutexes are as follows: + +- kvm->lock is taken outside vcpu->mutex + +- kvm->lock is taken outside kvm->slots_lock and kvm->irq_lock + +- kvm->slots_lock is taken outside kvm->irq_lock, though acquiring + them together is quite rare. + +On x86, vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock. + +Everything else is a leaf: no other lock is taken inside the critical +sections. + +2. Exception +------------ + +Fast page fault: + +Fast page fault is the fast path which fixes the guest page fault out of +the mmu-lock on x86. Currently, the page fault can be fast in one of the +following two cases: + +1. Access Tracking: The SPTE is not present, but it is marked for access + tracking i.e. the SPTE_SPECIAL_MASK is set. That means we need to + restore the saved R/X bits. This is described in more detail later below. + +2. Write-Protection: The SPTE is present and the fault is + caused by write-protect. That means we just need to change the W bit of + the spte. + +What we use to avoid all the race is the SPTE_HOST_WRITEABLE bit and +SPTE_MMU_WRITEABLE bit on the spte: + +- SPTE_HOST_WRITEABLE means the gfn is writable on host. +- SPTE_MMU_WRITEABLE means the gfn is writable on mmu. The bit is set when + the gfn is writable on guest mmu and it is not write-protected by shadow + page write-protection. + +On fast page fault path, we will use cmpxchg to atomically set the spte W +bit if spte.SPTE_HOST_WRITEABLE = 1 and spte.SPTE_WRITE_PROTECT = 1, or +restore the saved R/X bits if VMX_EPT_TRACK_ACCESS mask is set, or both. This +is safe because whenever changing these bits can be detected by cmpxchg. + +But we need carefully check these cases: + +1) The mapping from gfn to pfn + +The mapping from gfn to pfn may be changed since we can only ensure the pfn +is not changed during cmpxchg. This is a ABA problem, for example, below case +will happen: + ++------------------------------------------------------------------------+ +| At the beginning:: | +| | +| gpte = gfn1 | +| gfn1 is mapped to pfn1 on host | +| spte is the shadow page table entry corresponding with gpte and | +| spte = pfn1 | ++------------------------------------------------------------------------+ +| On fast page fault path: | ++------------------------------------+-----------------------------------+ +| CPU 0: | CPU 1: | ++------------------------------------+-----------------------------------+ +| :: | | +| | | +| old_spte = *spte; | | ++------------------------------------+-----------------------------------+ +| | pfn1 is swapped out:: | +| | | +| | spte = 0; | +| | | +| | pfn1 is re-alloced for gfn2. | +| | | +| | gpte is changed to point to | +| | gfn2 by the guest:: | +| | | +| | spte = pfn1; | ++------------------------------------+-----------------------------------+ +| :: | +| | +| if (cmpxchg(spte, old_spte, old_spte+W) | +| mark_page_dirty(vcpu->kvm, gfn1) | +| OOPS!!! | ++------------------------------------------------------------------------+ + +We dirty-log for gfn1, that means gfn2 is lost in dirty-bitmap. + +For direct sp, we can easily avoid it since the spte of direct sp is fixed +to gfn. For indirect sp, before we do cmpxchg, we call gfn_to_pfn_atomic() +to pin gfn to pfn, because after gfn_to_pfn_atomic(): + +- We have held the refcount of pfn that means the pfn can not be freed and + be reused for another gfn. +- The pfn is writable that means it can not be shared between different gfns + by KSM. + +Then, we can ensure the dirty bitmaps is correctly set for a gfn. + +Currently, to simplify the whole things, we disable fast page fault for +indirect shadow page. + +2) Dirty bit tracking + +In the origin code, the spte can be fast updated (non-atomically) if the +spte is read-only and the Accessed bit has already been set since the +Accessed bit and Dirty bit can not be lost. + +But it is not true after fast page fault since the spte can be marked +writable between reading spte and updating spte. Like below case: + ++------------------------------------------------------------------------+ +| At the beginning:: | +| | +| spte.W = 0 | +| spte.Accessed = 1 | ++------------------------------------+-----------------------------------+ +| CPU 0: | CPU 1: | ++------------------------------------+-----------------------------------+ +| In mmu_spte_clear_track_bits():: | | +| | | +| old_spte = *spte; | | +| | | +| | | +| /* 'if' condition is satisfied. */| | +| if (old_spte.Accessed == 1 && | | +| old_spte.W == 0) | | +| spte = 0ull; | | ++------------------------------------+-----------------------------------+ +| | on fast page fault path:: | +| | | +| | spte.W = 1 | +| | | +| | memory write on the spte:: | +| | | +| | spte.Dirty = 1 | ++------------------------------------+-----------------------------------+ +| :: | | +| | | +| else | | +| old_spte = xchg(spte, 0ull) | | +| if (old_spte.Accessed == 1) | | +| kvm_set_pfn_accessed(spte.pfn);| | +| if (old_spte.Dirty == 1) | | +| kvm_set_pfn_dirty(spte.pfn); | | +| OOPS!!! | | ++------------------------------------+-----------------------------------+ + +The Dirty bit is lost in this case. + +In order to avoid this kind of issue, we always treat the spte as "volatile" +if it can be updated out of mmu-lock, see spte_has_volatile_bits(), it means, +the spte is always atomically updated in this case. + +3) flush tlbs due to spte updated + +If the spte is updated from writable to readonly, we should flush all TLBs, +otherwise rmap_write_protect will find a read-only spte, even though the +writable spte might be cached on a CPU's TLB. + +As mentioned before, the spte can be updated to writable out of mmu-lock on +fast page fault path, in order to easily audit the path, we see if TLBs need +be flushed caused by this reason in mmu_spte_update() since this is a common +function to update spte (present -> present). + +Since the spte is "volatile" if it can be updated out of mmu-lock, we always +atomically update the spte, the race caused by fast page fault can be avoided, +See the comments in spte_has_volatile_bits() and mmu_spte_update(). + +Lockless Access Tracking: + +This is used for Intel CPUs that are using EPT but do not support the EPT A/D +bits. In this case, when the KVM MMU notifier is called to track accesses to a +page (via kvm_mmu_notifier_clear_flush_young), it marks the PTE as not-present +by clearing the RWX bits in the PTE and storing the original R & X bits in +some unused/ignored bits. In addition, the SPTE_SPECIAL_MASK is also set on the +PTE (using the ignored bit 62). When the VM tries to access the page later on, +a fault is generated and the fast page fault mechanism described above is used +to atomically restore the PTE to a Present state. The W bit is not saved when +the PTE is marked for access tracking and during restoration to the Present +state, the W bit is set depending on whether or not it was a write access. If +it wasn't, then the W bit will remain clear until a write access happens, at +which time it will be set using the Dirty tracking mechanism described above. + +3. Reference +------------ + +:Name: kvm_lock +:Type: mutex +:Arch: any +:Protects: - vm_list + +:Name: kvm_count_lock +:Type: raw_spinlock_t +:Arch: any +:Protects: - hardware virtualization enable/disable +:Comment: 'raw' because hardware enabling/disabling must be atomic /wrt + migration. + +:Name: kvm_arch::tsc_write_lock +:Type: raw_spinlock +:Arch: x86 +:Protects: - kvm_arch::{last_tsc_write,last_tsc_nsec,last_tsc_offset} + - tsc offset in vmcb +:Comment: 'raw' because updating the tsc offsets must not be preempted. + +:Name: kvm->mmu_lock +:Type: spinlock_t +:Arch: any +:Protects: -shadow page/shadow tlb entry +:Comment: it is a spinlock since it is used in mmu notifier. + +:Name: kvm->srcu +:Type: srcu lock +:Arch: any +:Protects: - kvm->memslots + - kvm->buses +:Comment: The srcu read lock must be held while accessing memslots (e.g. + when using gfn_to_* functions) and while accessing in-kernel + MMIO/PIO address->device structure mapping (kvm->buses). + The srcu index can be stored in kvm_vcpu->srcu_idx per vcpu + if it is needed by multiple functions. + +:Name: blocked_vcpu_on_cpu_lock +:Type: spinlock_t +:Arch: x86 +:Protects: blocked_vcpu_on_cpu +:Comment: This is a per-CPU lock and it is used for VT-d posted-interrupts. + When VT-d posted-interrupts is supported and the VM has assigned + devices, we put the blocked vCPU on the list blocked_vcpu_on_cpu + protected by blocked_vcpu_on_cpu_lock, when VT-d hardware issues + wakeup notification event since external interrupts from the + assigned devices happens, we will find the vCPU on the list to + wakeup. diff --git a/Documentation/virt/kvm/locking.txt b/Documentation/virt/kvm/locking.txt deleted file mode 100644 index 635cd6eaf714..000000000000 --- a/Documentation/virt/kvm/locking.txt +++ /dev/null @@ -1,215 +0,0 @@ -KVM Lock Overview -================= - -1. Acquisition Orders ---------------------- - -The acquisition orders for mutexes are as follows: - -- kvm->lock is taken outside vcpu->mutex - -- kvm->lock is taken outside kvm->slots_lock and kvm->irq_lock - -- kvm->slots_lock is taken outside kvm->irq_lock, though acquiring - them together is quite rare. - -On x86, vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock. - -Everything else is a leaf: no other lock is taken inside the critical -sections. - -2: Exception ------------- - -Fast page fault: - -Fast page fault is the fast path which fixes the guest page fault out of -the mmu-lock on x86. Currently, the page fault can be fast in one of the -following two cases: - -1. Access Tracking: The SPTE is not present, but it is marked for access -tracking i.e. the SPTE_SPECIAL_MASK is set. That means we need to -restore the saved R/X bits. This is described in more detail later below. - -2. Write-Protection: The SPTE is present and the fault is -caused by write-protect. That means we just need to change the W bit of the -spte. - -What we use to avoid all the race is the SPTE_HOST_WRITEABLE bit and -SPTE_MMU_WRITEABLE bit on the spte: -- SPTE_HOST_WRITEABLE means the gfn is writable on host. -- SPTE_MMU_WRITEABLE means the gfn is writable on mmu. The bit is set when - the gfn is writable on guest mmu and it is not write-protected by shadow - page write-protection. - -On fast page fault path, we will use cmpxchg to atomically set the spte W -bit if spte.SPTE_HOST_WRITEABLE = 1 and spte.SPTE_WRITE_PROTECT = 1, or -restore the saved R/X bits if VMX_EPT_TRACK_ACCESS mask is set, or both. This -is safe because whenever changing these bits can be detected by cmpxchg. - -But we need carefully check these cases: -1): The mapping from gfn to pfn -The mapping from gfn to pfn may be changed since we can only ensure the pfn -is not changed during cmpxchg. This is a ABA problem, for example, below case -will happen: - -At the beginning: -gpte = gfn1 -gfn1 is mapped to pfn1 on host -spte is the shadow page table entry corresponding with gpte and -spte = pfn1 - - VCPU 0 VCPU0 -on fast page fault path: - - old_spte = *spte; - pfn1 is swapped out: - spte = 0; - - pfn1 is re-alloced for gfn2. - - gpte is changed to point to - gfn2 by the guest: - spte = pfn1; - - if (cmpxchg(spte, old_spte, old_spte+W) - mark_page_dirty(vcpu->kvm, gfn1) - OOPS!!! - -We dirty-log for gfn1, that means gfn2 is lost in dirty-bitmap. - -For direct sp, we can easily avoid it since the spte of direct sp is fixed -to gfn. For indirect sp, before we do cmpxchg, we call gfn_to_pfn_atomic() -to pin gfn to pfn, because after gfn_to_pfn_atomic(): -- We have held the refcount of pfn that means the pfn can not be freed and - be reused for another gfn. -- The pfn is writable that means it can not be shared between different gfns - by KSM. - -Then, we can ensure the dirty bitmaps is correctly set for a gfn. - -Currently, to simplify the whole things, we disable fast page fault for -indirect shadow page. - -2): Dirty bit tracking -In the origin code, the spte can be fast updated (non-atomically) if the -spte is read-only and the Accessed bit has already been set since the -Accessed bit and Dirty bit can not be lost. - -But it is not true after fast page fault since the spte can be marked -writable between reading spte and updating spte. Like below case: - -At the beginning: -spte.W = 0 -spte.Accessed = 1 - - VCPU 0 VCPU0 -In mmu_spte_clear_track_bits(): - - old_spte = *spte; - - /* 'if' condition is satisfied. */ - if (old_spte.Accessed == 1 && - old_spte.W == 0) - spte = 0ull; - on fast page fault path: - spte.W = 1 - memory write on the spte: - spte.Dirty = 1 - - - else - old_spte = xchg(spte, 0ull) - - - if (old_spte.Accessed == 1) - kvm_set_pfn_accessed(spte.pfn); - if (old_spte.Dirty == 1) - kvm_set_pfn_dirty(spte.pfn); - OOPS!!! - -The Dirty bit is lost in this case. - -In order to avoid this kind of issue, we always treat the spte as "volatile" -if it can be updated out of mmu-lock, see spte_has_volatile_bits(), it means, -the spte is always atomically updated in this case. - -3): flush tlbs due to spte updated -If the spte is updated from writable to readonly, we should flush all TLBs, -otherwise rmap_write_protect will find a read-only spte, even though the -writable spte might be cached on a CPU's TLB. - -As mentioned before, the spte can be updated to writable out of mmu-lock on -fast page fault path, in order to easily audit the path, we see if TLBs need -be flushed caused by this reason in mmu_spte_update() since this is a common -function to update spte (present -> present). - -Since the spte is "volatile" if it can be updated out of mmu-lock, we always -atomically update the spte, the race caused by fast page fault can be avoided, -See the comments in spte_has_volatile_bits() and mmu_spte_update(). - -Lockless Access Tracking: - -This is used for Intel CPUs that are using EPT but do not support the EPT A/D -bits. In this case, when the KVM MMU notifier is called to track accesses to a -page (via kvm_mmu_notifier_clear_flush_young), it marks the PTE as not-present -by clearing the RWX bits in the PTE and storing the original R & X bits in -some unused/ignored bits. In addition, the SPTE_SPECIAL_MASK is also set on the -PTE (using the ignored bit 62). When the VM tries to access the page later on, -a fault is generated and the fast page fault mechanism described above is used -to atomically restore the PTE to a Present state. The W bit is not saved when -the PTE is marked for access tracking and during restoration to the Present -state, the W bit is set depending on whether or not it was a write access. If -it wasn't, then the W bit will remain clear until a write access happens, at -which time it will be set using the Dirty tracking mechanism described above. - -3. Reference ------------- - -Name: kvm_lock -Type: mutex -Arch: any -Protects: - vm_list - -Name: kvm_count_lock -Type: raw_spinlock_t -Arch: any -Protects: - hardware virtualization enable/disable -Comment: 'raw' because hardware enabling/disabling must be atomic /wrt - migration. - -Name: kvm_arch::tsc_write_lock -Type: raw_spinlock -Arch: x86 -Protects: - kvm_arch::{last_tsc_write,last_tsc_nsec,last_tsc_offset} - - tsc offset in vmcb -Comment: 'raw' because updating the tsc offsets must not be preempted. - -Name: kvm->mmu_lock -Type: spinlock_t -Arch: any -Protects: -shadow page/shadow tlb entry -Comment: it is a spinlock since it is used in mmu notifier. - -Name: kvm->srcu -Type: srcu lock -Arch: any -Protects: - kvm->memslots - - kvm->buses -Comment: The srcu read lock must be held while accessing memslots (e.g. - when using gfn_to_* functions) and while accessing in-kernel - MMIO/PIO address->device structure mapping (kvm->buses). - The srcu index can be stored in kvm_vcpu->srcu_idx per vcpu - if it is needed by multiple functions. - -Name: blocked_vcpu_on_cpu_lock -Type: spinlock_t -Arch: x86 -Protects: blocked_vcpu_on_cpu -Comment: This is a per-CPU lock and it is used for VT-d posted-interrupts. - When VT-d posted-interrupts is supported and the VM has assigned - devices, we put the blocked vCPU on the list blocked_vcpu_on_cpu - protected by blocked_vcpu_on_cpu_lock, when VT-d hardware issues - wakeup notification event since external interrupts from the - assigned devices happens, we will find the vCPU on the list to - wakeup. diff --git a/Documentation/virt/kvm/mmu.txt b/Documentation/virt/kvm/mmu.rst index dadb29e8738f..60981887d20b 100644 --- a/Documentation/virt/kvm/mmu.txt +++ b/Documentation/virt/kvm/mmu.rst @@ -1,3 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +====================== The x86 kvm shadow mmu ====================== @@ -7,27 +10,37 @@ physical addresses to host physical addresses. The mmu code attempts to satisfy the following requirements: -- correctness: the guest should not be able to determine that it is running +- correctness: + the guest should not be able to determine that it is running on an emulated mmu except for timing (we attempt to comply with the specification, not emulate the characteristics of a particular implementation such as tlb size) -- security: the guest must not be able to touch host memory not assigned +- security: + the guest must not be able to touch host memory not assigned to it -- performance: minimize the performance penalty imposed by the mmu -- scaling: need to scale to large memory and large vcpu guests -- hardware: support the full range of x86 virtualization hardware -- integration: Linux memory management code must be in control of guest memory +- performance: + minimize the performance penalty imposed by the mmu +- scaling: + need to scale to large memory and large vcpu guests +- hardware: + support the full range of x86 virtualization hardware +- integration: + Linux memory management code must be in control of guest memory so that swapping, page migration, page merging, transparent hugepages, and similar features work without change -- dirty tracking: report writes to guest memory to enable live migration +- dirty tracking: + report writes to guest memory to enable live migration and framebuffer-based displays -- footprint: keep the amount of pinned kernel memory low (most memory +- footprint: + keep the amount of pinned kernel memory low (most memory should be shrinkable) -- reliability: avoid multipage or GFP_ATOMIC allocations +- reliability: + avoid multipage or GFP_ATOMIC allocations Acronyms ======== +==== ==================================================================== pfn host page frame number hpa host physical address hva host virtual address @@ -41,6 +54,7 @@ pte page table entry (used also to refer generically to paging structure gpte guest pte (referring to gfns) spte shadow pte (referring to pfns) tdp two dimensional paging (vendor neutral term for NPT and EPT) +==== ==================================================================== Virtual and real hardware supported =================================== @@ -90,11 +104,13 @@ Events The mmu is driven by events, some from the guest, some from the host. Guest generated events: + - writes to control registers (especially cr3) - invlpg/invlpga instruction execution - access to missing or protected translations Host generated events: + - changes in the gpa->hpa translation (either through gpa->hva changes or through hva->hpa changes) - memory pressure (the shrinker) @@ -117,16 +133,19 @@ Leaf ptes point at guest pages. The following table shows translations encoded by leaf ptes, with higher-level translations in parentheses: - Non-nested guests: + Non-nested guests:: + nonpaging: gpa->hpa paging: gva->gpa->hpa paging, tdp: (gva->)gpa->hpa - Nested guests: + + Nested guests:: + non-tdp: ngva->gpa->hpa (*) tdp: (ngva->)ngpa->gpa->hpa -(*) the guest hypervisor will encode the ngva->gpa translation into its page - tables if npt is not present + (*) the guest hypervisor will encode the ngva->gpa translation into its page + tables if npt is not present Shadow pages contain the following information: role.level: @@ -291,28 +310,41 @@ Handling a page fault is performed as follows: - if the RSV bit of the error code is set, the page fault is caused by guest accessing MMIO and cached MMIO information is available. + - walk shadow page table - check for valid generation number in the spte (see "Fast invalidation of MMIO sptes" below) - cache the information to vcpu->arch.mmio_gva, vcpu->arch.mmio_access and vcpu->arch.mmio_gfn, and call the emulator + - If both P bit and R/W bit of error code are set, this could possibly be handled as a "fast page fault" (fixed without taking the MMU lock). See the description in Documentation/virt/kvm/locking.txt. + - if needed, walk the guest page tables to determine the guest translation (gva->gpa or ngpa->gpa) + - if permissions are insufficient, reflect the fault back to the guest + - determine the host page + - if this is an mmio request, there is no host page; cache the info to vcpu->arch.mmio_gva, vcpu->arch.mmio_access and vcpu->arch.mmio_gfn + - walk the shadow page table to find the spte for the translation, instantiating missing intermediate page tables as necessary + - If this is an mmio request, cache the mmio info to the spte and set some reserved bit on the spte (see callers of kvm_mmu_set_mmio_spte_mask) + - try to unsynchronize the page + - if successful, we can let the guest continue and modify the gpte + - emulate the instruction + - if failed, unshadow the page and let the guest continue + - update any translations that were modified by the instruction invlpg handling: @@ -324,10 +356,12 @@ invlpg handling: Guest control register updates: - mov to cr3 + - look up new shadow roots - synchronize newly reachable shadow pages - mov to cr0/cr4/efer + - set up mmu context for new paging mode - look up new shadow roots - synchronize newly reachable shadow pages @@ -358,6 +392,7 @@ on fault type: (user write faults generate a #PF) In the first case there are two additional complications: + - if CR4.SMEP is enabled: since we've turned the page into a kernel page, the kernel may now execute it. We handle this by also setting spte.nx. If we get a user fetch or read fault, we'll change spte.u=1 and @@ -446,4 +481,3 @@ Further reading - NPT presentation from KVM Forum 2008 http://www.linux-kvm.org/images/c/c8/KvmForum2008%24kdf2008_21.pdf - diff --git a/Documentation/virt/kvm/msr.txt b/Documentation/virt/kvm/msr.rst index df1f4338b3ca..33892036672d 100644 --- a/Documentation/virt/kvm/msr.txt +++ b/Documentation/virt/kvm/msr.rst @@ -1,6 +1,10 @@ -KVM-specific MSRs. -Glauber Costa <glommer@redhat.com>, Red Hat Inc, 2010 -===================================================== +.. SPDX-License-Identifier: GPL-2.0 + +================= +KVM-specific MSRs +================= + +:Author: Glauber Costa <glommer@redhat.com>, Red Hat Inc, 2010 KVM makes use of some custom MSRs to service some requests. @@ -9,34 +13,39 @@ Custom MSRs have a range reserved for them, that goes from but they are deprecated and their use is discouraged. Custom MSR list --------- +--------------- The current supported Custom MSR list is: -MSR_KVM_WALL_CLOCK_NEW: 0x4b564d00 +MSR_KVM_WALL_CLOCK_NEW: + 0x4b564d00 - data: 4-byte alignment physical address of a memory area which must be +data: + 4-byte alignment physical address of a memory area which must be in guest RAM. This memory is expected to hold a copy of the following - structure: + structure:: - struct pvclock_wall_clock { + struct pvclock_wall_clock { u32 version; u32 sec; u32 nsec; - } __attribute__((__packed__)); + } __attribute__((__packed__)); whose data will be filled in by the hypervisor. The hypervisor is only guaranteed to update this data at the moment of MSR write. Users that want to reliably query this information more than once have to write more than once to this MSR. Fields have the following meanings: - version: guest has to check version before and after grabbing + version: + guest has to check version before and after grabbing time information and check that they are both equal and even. An odd version indicates an in-progress update. - sec: number of seconds for wallclock at time of boot. + sec: + number of seconds for wallclock at time of boot. - nsec: number of nanoseconds for wallclock at time of boot. + nsec: + number of nanoseconds for wallclock at time of boot. In order to get the current wallclock time, the system_time from MSR_KVM_SYSTEM_TIME_NEW needs to be added. @@ -47,13 +56,15 @@ MSR_KVM_WALL_CLOCK_NEW: 0x4b564d00 Availability of this MSR must be checked via bit 3 in 0x4000001 cpuid leaf prior to usage. -MSR_KVM_SYSTEM_TIME_NEW: 0x4b564d01 +MSR_KVM_SYSTEM_TIME_NEW: + 0x4b564d01 - data: 4-byte aligned physical address of a memory area which must be in +data: + 4-byte aligned physical address of a memory area which must be in guest RAM, plus an enable bit in bit 0. This memory is expected to hold - a copy of the following structure: + a copy of the following structure:: - struct pvclock_vcpu_time_info { + struct pvclock_vcpu_time_info { u32 version; u32 pad0; u64 tsc_timestamp; @@ -62,7 +73,7 @@ MSR_KVM_SYSTEM_TIME_NEW: 0x4b564d01 s8 tsc_shift; u8 flags; u8 pad[2]; - } __attribute__((__packed__)); /* 32 bytes */ + } __attribute__((__packed__)); /* 32 bytes */ whose data will be filled in by the hypervisor periodically. Only one write, or registration, is needed for each VCPU. The interval between @@ -72,23 +83,28 @@ MSR_KVM_SYSTEM_TIME_NEW: 0x4b564d01 Fields have the following meanings: - version: guest has to check version before and after grabbing + version: + guest has to check version before and after grabbing time information and check that they are both equal and even. An odd version indicates an in-progress update. - tsc_timestamp: the tsc value at the current VCPU at the time + tsc_timestamp: + the tsc value at the current VCPU at the time of the update of this structure. Guests can subtract this value from current tsc to derive a notion of elapsed time since the structure update. - system_time: a host notion of monotonic time, including sleep + system_time: + a host notion of monotonic time, including sleep time at the time this structure was last updated. Unit is nanoseconds. - tsc_to_system_mul: multiplier to be used when converting + tsc_to_system_mul: + multiplier to be used when converting tsc-related quantity to nanoseconds - tsc_shift: shift to be used when converting tsc-related + tsc_shift: + shift to be used when converting tsc-related quantity to nanoseconds. This shift will ensure that multiplication with tsc_to_system_mul does not overflow. A positive value denotes a left shift, a negative value @@ -96,7 +112,7 @@ MSR_KVM_SYSTEM_TIME_NEW: 0x4b564d01 The conversion from tsc to nanoseconds involves an additional right shift by 32 bits. With this information, guests can - derive per-CPU time by doing: + derive per-CPU time by doing:: time = (current_tsc - tsc_timestamp) if (tsc_shift >= 0) @@ -106,29 +122,34 @@ MSR_KVM_SYSTEM_TIME_NEW: 0x4b564d01 time = (time * tsc_to_system_mul) >> 32 time = time + system_time - flags: bits in this field indicate extended capabilities + flags: + bits in this field indicate extended capabilities coordinated between the guest and the hypervisor. Availability of specific flags has to be checked in 0x40000001 cpuid leaf. Current flags are: - flag bit | cpuid bit | meaning - ------------------------------------------------------------- - | | time measures taken across - 0 | 24 | multiple cpus are guaranteed to - | | be monotonic - ------------------------------------------------------------- - | | guest vcpu has been paused by - 1 | N/A | the host - | | See 4.70 in api.txt - ------------------------------------------------------------- + + +-----------+--------------+----------------------------------+ + | flag bit | cpuid bit | meaning | + +-----------+--------------+----------------------------------+ + | | | time measures taken across | + | 0 | 24 | multiple cpus are guaranteed to | + | | | be monotonic | + +-----------+--------------+----------------------------------+ + | | | guest vcpu has been paused by | + | 1 | N/A | the host | + | | | See 4.70 in api.txt | + +-----------+--------------+----------------------------------+ Availability of this MSR must be checked via bit 3 in 0x4000001 cpuid leaf prior to usage. -MSR_KVM_WALL_CLOCK: 0x11 +MSR_KVM_WALL_CLOCK: + 0x11 - data and functioning: same as MSR_KVM_WALL_CLOCK_NEW. Use that instead. +data and functioning: + same as MSR_KVM_WALL_CLOCK_NEW. Use that instead. This MSR falls outside the reserved KVM range and may be removed in the future. Its usage is deprecated. @@ -136,9 +157,11 @@ MSR_KVM_WALL_CLOCK: 0x11 Availability of this MSR must be checked via bit 0 in 0x4000001 cpuid leaf prior to usage. -MSR_KVM_SYSTEM_TIME: 0x12 +MSR_KVM_SYSTEM_TIME: + 0x12 - data and functioning: same as MSR_KVM_SYSTEM_TIME_NEW. Use that instead. +data and functioning: + same as MSR_KVM_SYSTEM_TIME_NEW. Use that instead. This MSR falls outside the reserved KVM range and may be removed in the future. Its usage is deprecated. @@ -146,7 +169,7 @@ MSR_KVM_SYSTEM_TIME: 0x12 Availability of this MSR must be checked via bit 0 in 0x4000001 cpuid leaf prior to usage. - The suggested algorithm for detecting kvmclock presence is then: + The suggested algorithm for detecting kvmclock presence is then:: if (!kvm_para_available()) /* refer to cpuid.txt */ return NON_PRESENT; @@ -163,8 +186,11 @@ MSR_KVM_SYSTEM_TIME: 0x12 } else return NON_PRESENT; -MSR_KVM_ASYNC_PF_EN: 0x4b564d02 - data: Bits 63-6 hold 64-byte aligned physical address of a +MSR_KVM_ASYNC_PF_EN: + 0x4b564d02 + +data: + Bits 63-6 hold 64-byte aligned physical address of a 64 byte memory area which must be in guest RAM and must be zeroed. Bits 5-3 are reserved and should be zero. Bit 0 is 1 when asynchronous page faults are enabled on the vcpu 0 when @@ -200,20 +226,22 @@ MSR_KVM_ASYNC_PF_EN: 0x4b564d02 Currently type 2 APF will be always delivered on the same vcpu as type 1 was, but guest should not rely on that. -MSR_KVM_STEAL_TIME: 0x4b564d03 +MSR_KVM_STEAL_TIME: + 0x4b564d03 - data: 64-byte alignment physical address of a memory area which must be +data: + 64-byte alignment physical address of a memory area which must be in guest RAM, plus an enable bit in bit 0. This memory is expected to - hold a copy of the following structure: + hold a copy of the following structure:: - struct kvm_steal_time { + struct kvm_steal_time { __u64 steal; __u32 version; __u32 flags; __u8 preempted; __u8 u8_pad[3]; __u32 pad[11]; - } + } whose data will be filled in by the hypervisor periodically. Only one write, or registration, is needed for each VCPU. The interval between @@ -224,25 +252,32 @@ MSR_KVM_STEAL_TIME: 0x4b564d03 Fields have the following meanings: - version: a sequence counter. In other words, guest has to check + version: + a sequence counter. In other words, guest has to check this field before and after grabbing time information and make sure they are both equal and even. An odd version indicates an in-progress update. - flags: At this point, always zero. May be used to indicate + flags: + At this point, always zero. May be used to indicate changes in this structure in the future. - steal: the amount of time in which this vCPU did not run, in + steal: + the amount of time in which this vCPU did not run, in nanoseconds. Time during which the vcpu is idle, will not be reported as steal time. - preempted: indicate the vCPU who owns this struct is running or + preempted: + indicate the vCPU who owns this struct is running or not. Non-zero values mean the vCPU has been preempted. Zero means the vCPU is not preempted. NOTE, it is always zero if the the hypervisor doesn't support this field. -MSR_KVM_EOI_EN: 0x4b564d04 - data: Bit 0 is 1 when PV end of interrupt is enabled on the vcpu; 0 +MSR_KVM_EOI_EN: + 0x4b564d04 + +data: + Bit 0 is 1 when PV end of interrupt is enabled on the vcpu; 0 when disabled. Bit 1 is reserved and must be zero. When PV end of interrupt is enabled (bit 0 set), bits 63-2 hold a 4-byte aligned physical address of a 4 byte memory area which must be in guest RAM and @@ -274,11 +309,13 @@ MSR_KVM_EOI_EN: 0x4b564d04 clear it using a single CPU instruction, such as test and clear, or compare and exchange. -MSR_KVM_POLL_CONTROL: 0x4b564d05 +MSR_KVM_POLL_CONTROL: + 0x4b564d05 + Control host-side polling. - data: Bit 0 enables (1) or disables (0) host-side HLT polling logic. +data: + Bit 0 enables (1) or disables (0) host-side HLT polling logic. KVM guests can request the host not to poll on HLT, for example if they are performing polling themselves. - diff --git a/Documentation/virt/kvm/nested-vmx.txt b/Documentation/virt/kvm/nested-vmx.rst index 97eb1353e962..592b0ab6970b 100644 --- a/Documentation/virt/kvm/nested-vmx.txt +++ b/Documentation/virt/kvm/nested-vmx.rst @@ -1,3 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========== Nested VMX ========== @@ -41,9 +44,9 @@ No modifications are required to user space (qemu). However, qemu's default emulated CPU type (qemu64) does not list the "VMX" CPU feature, so it must be explicitly enabled, by giving qemu one of the following options: - -cpu host (emulated CPU has all features of the real CPU) + - cpu host (emulated CPU has all features of the real CPU) - -cpu qemu64,+vmx (add just the vmx feature to a named CPU type) + - cpu qemu64,+vmx (add just the vmx feature to a named CPU type) ABIs @@ -75,6 +78,8 @@ of this structure changes, this can break live migration across KVM versions. VMCS12_REVISION (from vmx.c) should be changed if struct vmcs12 or its inner struct shadow_vmcs is ever changed. +:: + typedef u64 natural_width; struct __packed vmcs12 { /* According to the Intel spec, a VMCS region must start with @@ -220,21 +225,21 @@ Authors ------- These patches were written by: - Abel Gordon, abelg <at> il.ibm.com - Nadav Har'El, nyh <at> il.ibm.com - Orit Wasserman, oritw <at> il.ibm.com - Ben-Ami Yassor, benami <at> il.ibm.com - Muli Ben-Yehuda, muli <at> il.ibm.com + - Abel Gordon, abelg <at> il.ibm.com + - Nadav Har'El, nyh <at> il.ibm.com + - Orit Wasserman, oritw <at> il.ibm.com + - Ben-Ami Yassor, benami <at> il.ibm.com + - Muli Ben-Yehuda, muli <at> il.ibm.com With contributions by: - Anthony Liguori, aliguori <at> us.ibm.com - Mike Day, mdday <at> us.ibm.com - Michael Factor, factor <at> il.ibm.com - Zvi Dubitzky, dubi <at> il.ibm.com + - Anthony Liguori, aliguori <at> us.ibm.com + - Mike Day, mdday <at> us.ibm.com + - Michael Factor, factor <at> il.ibm.com + - Zvi Dubitzky, dubi <at> il.ibm.com And valuable reviews by: - Avi Kivity, avi <at> redhat.com - Gleb Natapov, gleb <at> redhat.com - Marcelo Tosatti, mtosatti <at> redhat.com - Kevin Tian, kevin.tian <at> intel.com - and others. + - Avi Kivity, avi <at> redhat.com + - Gleb Natapov, gleb <at> redhat.com + - Marcelo Tosatti, mtosatti <at> redhat.com + - Kevin Tian, kevin.tian <at> intel.com + - and others. diff --git a/Documentation/virt/kvm/ppc-pv.txt b/Documentation/virt/kvm/ppc-pv.rst index e26115ce4258..5fdb907670be 100644 --- a/Documentation/virt/kvm/ppc-pv.txt +++ b/Documentation/virt/kvm/ppc-pv.rst @@ -1,3 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================= The PPC KVM paravirtual interface ================================= @@ -34,8 +37,9 @@ up the hypercall. To call a hypercall, just call these instructions. The parameters are as follows: + ======== ================ ================ Register IN OUT - + ======== ================ ================ r0 - volatile r3 1st parameter Return code r4 2nd parameter 1st output value @@ -47,6 +51,7 @@ The parameters are as follows: r10 8th parameter 7th output value r11 hypercall number 8th output value r12 - volatile + ======== ================ ================ Hypercall definitions are shared in generic code, so the same hypercall numbers apply for x86 and powerpc alike with the exception that each KVM hypercall @@ -54,11 +59,13 @@ also needs to be ORed with the KVM vendor code which is (42 << 16). Return codes can be as follows: + ==== ========================= Code Meaning - + ==== ========================= 0 Success 12 Hypercall not implemented <0 Error + ==== ========================= The magic page ============== @@ -72,7 +79,7 @@ desired location. The first parameter indicates the effective address when the MMU is enabled. The second parameter indicates the address in real mode, if applicable to the target. For now, we always map the page to -4096. This way we can access it using absolute load and store functions. The following -instruction reads the first field of the magic page: +instruction reads the first field of the magic page:: ld rX, -4096(0) @@ -93,8 +100,10 @@ a bitmap of available features inside the magic page. The following enhancements to the magic page are currently available: + ============================ ======================================= KVM_MAGIC_FEAT_SR Maps SR registers r/w in the magic page KVM_MAGIC_FEAT_MAS0_TO_SPRG7 Maps MASn, ESR, PIR and high SPRGs + ============================ ======================================= For enhanced features in the magic page, please check for the existence of the feature before using them! @@ -121,8 +130,8 @@ when entering the guest or don't have any impact on the hypervisor's behavior. The following bits are safe to be set inside the guest: - MSR_EE - MSR_RI + - MSR_EE + - MSR_RI If any other bit changes in the MSR, please still use mtmsr(d). @@ -138,9 +147,9 @@ guest. Implementing any of those mappings is optional, as the instruction traps also act on the shared page. So calling privileged instructions still works as before. +======================= ================================ From To -==== == - +======================= ================================ mfmsr rX ld rX, magic_page->msr mfsprg rX, 0 ld rX, magic_page->sprg0 mfsprg rX, 1 ld rX, magic_page->sprg1 @@ -173,7 +182,7 @@ mtsrin rX, rY b <special mtsrin section> [BookE only] wrteei [0|1] b <special wrteei section> - +======================= ================================ Some instructions require more logic to determine what's going on than a load or store instruction can deliver. To enable patching of those, we keep some @@ -191,6 +200,7 @@ for example. Hypercall ABIs in KVM on PowerPC ================================= + 1) KVM hypercalls (ePAPR) These are ePAPR compliant hypercall implementation (mentioned above). Even diff --git a/Documentation/virt/kvm/review-checklist.txt b/Documentation/virt/kvm/review-checklist.rst index 499af499e296..1f86a9d3f705 100644 --- a/Documentation/virt/kvm/review-checklist.txt +++ b/Documentation/virt/kvm/review-checklist.rst @@ -1,3 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================ Review checklist for kvm patches ================================ diff --git a/Documentation/virt/kvm/s390-diag.txt b/Documentation/virt/kvm/s390-diag.rst index 7c52e5f8b210..eaac4864d3d6 100644 --- a/Documentation/virt/kvm/s390-diag.txt +++ b/Documentation/virt/kvm/s390-diag.rst @@ -1,3 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============================= The s390 DIAGNOSE call on KVM ============================= @@ -16,12 +19,12 @@ DIAGNOSE calls by the guest cause a mandatory intercept. This implies all supported DIAGNOSE calls need to be handled by either KVM or its userspace. -All DIAGNOSE calls supported by KVM use the RS-a format: +All DIAGNOSE calls supported by KVM use the RS-a format:: --------------------------------------- -| '83' | R1 | R3 | B2 | D2 | --------------------------------------- -0 8 12 16 20 31 + -------------------------------------- + | '83' | R1 | R3 | B2 | D2 | + -------------------------------------- + 0 8 12 16 20 31 The second-operand address (obtained by the base/displacement calculation) is not used to address data. Instead, bits 48-63 of this address specify diff --git a/Documentation/virt/kvm/timekeeping.txt b/Documentation/virt/kvm/timekeeping.rst index 76808a17ad84..21ae7efa29ba 100644 --- a/Documentation/virt/kvm/timekeeping.txt +++ b/Documentation/virt/kvm/timekeeping.rst @@ -1,17 +1,21 @@ +.. SPDX-License-Identifier: GPL-2.0 - Timekeeping Virtualization for X86-Based Architectures +====================================================== +Timekeeping Virtualization for X86-Based Architectures +====================================================== - Zachary Amsden <zamsden@redhat.com> - Copyright (c) 2010, Red Hat. All rights reserved. +:Author: Zachary Amsden <zamsden@redhat.com> +:Copyright: (c) 2010, Red Hat. All rights reserved. -1) Overview -2) Timing Devices -3) TSC Hardware -4) Virtualization Problems +.. Contents -========================================================================= + 1) Overview + 2) Timing Devices + 3) TSC Hardware + 4) Virtualization Problems -1) Overview +1. Overview +=========== One of the most complicated parts of the X86 platform, and specifically, the virtualization of this platform is the plethora of timing devices available @@ -27,15 +31,15 @@ The purpose of this document is to collect data and information relevant to timekeeping which may be difficult to find elsewhere, specifically, information relevant to KVM and hardware-based virtualization. -========================================================================= - -2) Timing Devices +2. Timing Devices +================= First we discuss the basic hardware devices available. TSC and the related KVM clock are special enough to warrant a full exposition and are described in the following section. -2.1) i8254 - PIT +2.1. i8254 - PIT +---------------- One of the first timer devices available is the programmable interrupt timer, or PIT. The PIT has a fixed frequency 1.193182 MHz base clock and three @@ -50,13 +54,13 @@ The PIT uses I/O ports 0x40 - 0x43. Access to the 16-bit counters is done using single or multiple byte access to the I/O ports. There are 6 modes available, but not all modes are available to all timers, as only timer 2 has a connected gate input, required for modes 1 and 5. The gate line is -controlled by port 61h, bit 0, as illustrated in the following diagram. +controlled by port 61h, bit 0, as illustrated in the following diagram:: - -------------- ---------------- -| | | | -| 1.1932 MHz |---------->| CLOCK OUT | ---------> IRQ 0 -| Clock | | | | - -------------- | +->| GATE TIMER 0 | + -------------- ---------------- + | | | | + | 1.1932 MHz|---------->| CLOCK OUT | ---------> IRQ 0 + | Clock | | | | + -------------- | +->| GATE TIMER 0 | | ---------------- | | ---------------- @@ -70,29 +74,33 @@ controlled by port 61h, bit 0, as illustrated in the following diagram. | | | |------>| CLOCK OUT | ---------> Port 61h, bit 5 | | | -Port 61h, bit 0 ---------->| GATE TIMER 2 | \_.---- ____ + Port 61h, bit 0 -------->| GATE TIMER 2 | \_.---- ____ ---------------- _| )--|LPF|---Speaker / *---- \___/ -Port 61h, bit 1 -----------------------------------/ + Port 61h, bit 1 ---------------------------------/ The timer modes are now described. -Mode 0: Single Timeout. This is a one-shot software timeout that counts down +Mode 0: Single Timeout. + This is a one-shot software timeout that counts down when the gate is high (always true for timers 0 and 1). When the count reaches zero, the output goes high. -Mode 1: Triggered One-shot. The output is initially set high. When the gate +Mode 1: Triggered One-shot. + The output is initially set high. When the gate line is set high, a countdown is initiated (which does not stop if the gate is lowered), during which the output is set low. When the count reaches zero, the output goes high. -Mode 2: Rate Generator. The output is initially set high. When the countdown +Mode 2: Rate Generator. + The output is initially set high. When the countdown reaches 1, the output goes low for one count and then returns high. The value is reloaded and the countdown automatically resumes. If the gate line goes low, the count is halted. If the output is low when the gate is lowered, the output automatically goes high (this only affects timer 2). -Mode 3: Square Wave. This generates a high / low square wave. The count +Mode 3: Square Wave. + This generates a high / low square wave. The count determines the length of the pulse, which alternates between high and low when zero is reached. The count only proceeds when gate is high and is automatically reloaded on reaching zero. The count is decremented twice at @@ -103,12 +111,14 @@ Mode 3: Square Wave. This generates a high / low square wave. The count values are not observed when reading. This is the intended mode for timer 2, which generates sine-like tones by low-pass filtering the square wave output. -Mode 4: Software Strobe. After programming this mode and loading the counter, +Mode 4: Software Strobe. + After programming this mode and loading the counter, the output remains high until the counter reaches zero. Then the output goes low for 1 clock cycle and returns high. The counter is not reloaded. Counting only occurs when gate is high. -Mode 5: Hardware Strobe. After programming and loading the counter, the +Mode 5: Hardware Strobe. + After programming and loading the counter, the output remains high. When the gate is raised, a countdown is initiated (which does not stop if the gate is lowered). When the counter reaches zero, the output goes low for 1 clock cycle and then returns high. The counter is @@ -118,49 +128,49 @@ In addition to normal binary counting, the PIT supports BCD counting. The command port, 0x43 is used to set the counter and mode for each of the three timers. -PIT commands, issued to port 0x43, using the following bit encoding: +PIT commands, issued to port 0x43, using the following bit encoding:: -Bit 7-4: Command (See table below) -Bit 3-1: Mode (000 = Mode 0, 101 = Mode 5, 11X = undefined) -Bit 0 : Binary (0) / BCD (1) + Bit 7-4: Command (See table below) + Bit 3-1: Mode (000 = Mode 0, 101 = Mode 5, 11X = undefined) + Bit 0 : Binary (0) / BCD (1) -Command table: +Command table:: -0000 - Latch Timer 0 count for port 0x40 + 0000 - Latch Timer 0 count for port 0x40 sample and hold the count to be read in port 0x40; additional commands ignored until counter is read; mode bits ignored. -0001 - Set Timer 0 LSB mode for port 0x40 + 0001 - Set Timer 0 LSB mode for port 0x40 set timer to read LSB only and force MSB to zero; mode bits set timer mode -0010 - Set Timer 0 MSB mode for port 0x40 + 0010 - Set Timer 0 MSB mode for port 0x40 set timer to read MSB only and force LSB to zero; mode bits set timer mode -0011 - Set Timer 0 16-bit mode for port 0x40 + 0011 - Set Timer 0 16-bit mode for port 0x40 set timer to read / write LSB first, then MSB; mode bits set timer mode -0100 - Latch Timer 1 count for port 0x41 - as described above -0101 - Set Timer 1 LSB mode for port 0x41 - as described above -0110 - Set Timer 1 MSB mode for port 0x41 - as described above -0111 - Set Timer 1 16-bit mode for port 0x41 - as described above + 0100 - Latch Timer 1 count for port 0x41 - as described above + 0101 - Set Timer 1 LSB mode for port 0x41 - as described above + 0110 - Set Timer 1 MSB mode for port 0x41 - as described above + 0111 - Set Timer 1 16-bit mode for port 0x41 - as described above -1000 - Latch Timer 2 count for port 0x42 - as described above -1001 - Set Timer 2 LSB mode for port 0x42 - as described above -1010 - Set Timer 2 MSB mode for port 0x42 - as described above -1011 - Set Timer 2 16-bit mode for port 0x42 as described above + 1000 - Latch Timer 2 count for port 0x42 - as described above + 1001 - Set Timer 2 LSB mode for port 0x42 - as described above + 1010 - Set Timer 2 MSB mode for port 0x42 - as described above + 1011 - Set Timer 2 16-bit mode for port 0x42 as described above -1101 - General counter latch + 1101 - General counter latch Latch combination of counters into corresponding ports Bit 3 = Counter 2 Bit 2 = Counter 1 Bit 1 = Counter 0 Bit 0 = Unused -1110 - Latch timer status + 1110 - Latch timer status Latch combination of counter mode into corresponding ports Bit 3 = Counter 2 Bit 2 = Counter 1 @@ -177,7 +187,8 @@ Command table: Bit 3-1 = Mode Bit 0 = Binary (0) / BCD mode (1) -2.2) RTC +2.2. RTC +-------- The second device which was available in the original PC was the MC146818 real time clock. The original device is now obsolete, and usually emulated by the @@ -201,21 +212,21 @@ in progress, as indicated in the status register. The clock uses a 32.768kHz crystal, so bits 6-4 of register A should be programmed to a 32kHz divider if the RTC is to count seconds. -This is the RAM map originally used for the RTC/CMOS: - -Location Size Description ------------------------------------------- -00h byte Current second (BCD) -01h byte Seconds alarm (BCD) -02h byte Current minute (BCD) -03h byte Minutes alarm (BCD) -04h byte Current hour (BCD) -05h byte Hours alarm (BCD) -06h byte Current day of week (BCD) -07h byte Current day of month (BCD) -08h byte Current month (BCD) -09h byte Current year (BCD) -0Ah byte Register A +This is the RAM map originally used for the RTC/CMOS:: + + Location Size Description + ------------------------------------------ + 00h byte Current second (BCD) + 01h byte Seconds alarm (BCD) + 02h byte Current minute (BCD) + 03h byte Minutes alarm (BCD) + 04h byte Current hour (BCD) + 05h byte Hours alarm (BCD) + 06h byte Current day of week (BCD) + 07h byte Current day of month (BCD) + 08h byte Current month (BCD) + 09h byte Current year (BCD) + 0Ah byte Register A bit 7 = Update in progress bit 6-4 = Divider for clock 000 = 4.194 MHz @@ -234,7 +245,7 @@ Location Size Description 1101 = 125 mS 1110 = 250 mS 1111 = 500 mS -0Bh byte Register B + 0Bh byte Register B bit 7 = Run (0) / Halt (1) bit 6 = Periodic interrupt enable bit 5 = Alarm interrupt enable @@ -243,19 +254,20 @@ Location Size Description bit 2 = BCD calendar (0) / Binary (1) bit 1 = 12-hour mode (0) / 24-hour mode (1) bit 0 = 0 (DST off) / 1 (DST enabled) -OCh byte Register C (read only) + OCh byte Register C (read only) bit 7 = interrupt request flag (IRQF) bit 6 = periodic interrupt flag (PF) bit 5 = alarm interrupt flag (AF) bit 4 = update interrupt flag (UF) bit 3-0 = reserved -ODh byte Register D (read only) + ODh byte Register D (read only) bit 7 = RTC has power bit 6-0 = reserved -32h byte Current century BCD (*) + 32h byte Current century BCD (*) (*) location vendor specific and now determined from ACPI global tables -2.3) APIC +2.3. APIC +--------- On Pentium and later processors, an on-board timer is available to each CPU as part of the Advanced Programmable Interrupt Controller. The APIC is @@ -276,7 +288,8 @@ timer is programmed through the LVT (local vector timer) register, is capable of one-shot or periodic operation, and is based on the bus clock divided down by the programmable divider register. -2.4) HPET +2.4. HPET +--------- HPET is quite complex, and was originally intended to replace the PIT / RTC support of the X86 PC. It remains to be seen whether that will be the case, as @@ -297,7 +310,8 @@ indicated through ACPI tables by the BIOS. Detailed specification of the HPET is beyond the current scope of this document, as it is also very well documented elsewhere. -2.5) Offboard Timers +2.5. Offboard Timers +-------------------- Several cards, both proprietary (watchdog boards) and commonplace (e1000) have timing chips built into the cards which may have registers which are accessible @@ -307,9 +321,8 @@ general frowned upon as not playing by the agreed rules of the game. Such a timer device would require additional support to be virtualized properly and is not considered important at this time as no known operating system does this. -========================================================================= - -3) TSC Hardware +3. TSC Hardware +=============== The TSC or time stamp counter is relatively simple in theory; it counts instruction cycles issued by the processor, which can be used as a measure of @@ -340,7 +353,8 @@ allows the guest visible TSC to be offset by a constant. Newer implementations promise to allow the TSC to additionally be scaled, but this hardware is not yet widely available. -3.1) TSC synchronization +3.1. TSC synchronization +------------------------ The TSC is a CPU-local clock in most implementations. This means, on SMP platforms, the TSCs of different CPUs may start at different times depending @@ -357,7 +371,8 @@ practice, getting a perfectly synchronized TSC will not be possible unless all values are read from the same clock, which generally only is possible on single socket systems or those with special hardware support. -3.2) TSC and CPU hotplug +3.2. TSC and CPU hotplug +------------------------ As touched on already, CPUs which arrive later than the boot time of the system may not have a TSC value that is synchronized with the rest of the system. @@ -367,7 +382,8 @@ a guarantee. This can have the effect of bringing a system from a state where TSC is synchronized back to a state where TSC synchronization flaws, however small, may be exposed to the OS and any virtualization environment. -3.3) TSC and multi-socket / NUMA +3.3. TSC and multi-socket / NUMA +-------------------------------- Multi-socket systems, especially large multi-socket systems are likely to have individual clocksources rather than a single, universally distributed clock. @@ -385,7 +401,8 @@ standards for telecommunications and computer equipment. It is recommended not to trust the TSCs to remain synchronized on NUMA or multiple socket systems for these reasons. -3.4) TSC and C-states +3.4. TSC and C-states +--------------------- C-states, or idling states of the processor, especially C1E and deeper sleep states may be problematic for TSC as well. The TSC may stop advancing in such @@ -396,7 +413,8 @@ based on CPU and chipset identifications. The TSC in such a case may be corrected by catching it up to a known external clocksource. -3.5) TSC frequency change / P-states +3.5. TSC frequency change / P-states +------------------------------------ To make things slightly more interesting, some CPUs may change frequency. They may or may not run the TSC at the same rate, and because the frequency change @@ -416,14 +434,16 @@ other processors. In such cases, the TSC on halted CPUs could advance faster than that of non-halted processors. AMD Turion processors are known to have this problem. -3.6) TSC and STPCLK / T-states +3.6. TSC and STPCLK / T-states +------------------------------ External signals given to the processor may also have the effect of stopping the TSC. This is typically done for thermal emergency power control to prevent an overheating condition, and typically, there is no way to detect that this condition has happened. -3.7) TSC virtualization - VMX +3.7. TSC virtualization - VMX +----------------------------- VMX provides conditional trapping of RDTSC, RDMSR, WRMSR and RDTSCP instructions, which is enough for full virtualization of TSC in any manner. In @@ -431,14 +451,16 @@ addition, VMX allows passing through the host TSC plus an additional TSC_OFFSET field specified in the VMCS. Special instructions must be used to read and write the VMCS field. -3.8) TSC virtualization - SVM +3.8. TSC virtualization - SVM +----------------------------- SVM provides conditional trapping of RDTSC, RDMSR, WRMSR and RDTSCP instructions, which is enough for full virtualization of TSC in any manner. In addition, SVM allows passing through the host TSC plus an additional offset field specified in the SVM control block. -3.9) TSC feature bits in Linux +3.9. TSC feature bits in Linux +------------------------------ In summary, there is no way to guarantee the TSC remains in perfect synchronization unless it is explicitly guaranteed by the architecture. Even @@ -448,13 +470,16 @@ despite being locally consistent. The following feature bits are used by Linux to signal various TSC attributes, but they can only be taken to be meaningful for UP or single node systems. -X86_FEATURE_TSC : The TSC is available in hardware -X86_FEATURE_RDTSCP : The RDTSCP instruction is available -X86_FEATURE_CONSTANT_TSC : The TSC rate is unchanged with P-states -X86_FEATURE_NONSTOP_TSC : The TSC does not stop in C-states -X86_FEATURE_TSC_RELIABLE : TSC sync checks are skipped (VMware) +========================= ======================================= +X86_FEATURE_TSC The TSC is available in hardware +X86_FEATURE_RDTSCP The RDTSCP instruction is available +X86_FEATURE_CONSTANT_TSC The TSC rate is unchanged with P-states +X86_FEATURE_NONSTOP_TSC The TSC does not stop in C-states +X86_FEATURE_TSC_RELIABLE TSC sync checks are skipped (VMware) +========================= ======================================= -4) Virtualization Problems +4. Virtualization Problems +========================== Timekeeping is especially problematic for virtualization because a number of challenges arise. The most obvious problem is that time is now shared between @@ -473,7 +498,8 @@ BIOS, but not in such an extreme fashion. However, the fact that SMM mode may cause similar problems to virtualization makes it a good justification for solving many of these problems on bare metal. -4.1) Interrupt clocking +4.1. Interrupt clocking +----------------------- One of the most immediate problems that occurs with legacy operating systems is that the system timekeeping routines are often designed to keep track of @@ -502,7 +528,8 @@ thus requires interrupt slewing to keep proper time. It does use a low enough rate (ed: is it 18.2 Hz?) however that it has not yet been a problem in practice. -4.2) TSC sampling and serialization +4.2. TSC sampling and serialization +----------------------------------- As the highest precision time source available, the cycle counter of the CPU has aroused much interest from developers. As explained above, this timer has @@ -524,7 +551,8 @@ it may be necessary for an implementation to guard against "backwards" reads of the TSC as seen from other CPUs, even in an otherwise perfectly synchronized system. -4.3) Timespec aliasing +4.3. Timespec aliasing +---------------------- Additionally, this lack of serialization from the TSC poses another challenge when using results of the TSC when measured against another time source. As @@ -548,7 +576,8 @@ This aliasing requires care in the computation and recalibration of kvmclock and any other values derived from TSC computation (such as TSC virtualization itself). -4.4) Migration +4.4. Migration +-------------- Migration of a virtual machine raises problems for timekeeping in two ways. First, the migration itself may take time, during which interrupts cannot be @@ -566,7 +595,8 @@ always be caught up to the original rate. KVM clock avoids these problems by simply storing multipliers and offsets against the TSC for the guest to convert back into nanosecond resolution values. -4.5) Scheduling +4.5. Scheduling +--------------- Since scheduling may be based on precise timing and firing of interrupts, the scheduling algorithms of an operating system may be adversely affected by @@ -579,7 +609,8 @@ In an attempt to work around this, several implementations have provided a paravirtualized scheduler clock, which reveals the true amount of CPU time for which a virtual machine has been running. -4.6) Watchdogs +4.6. Watchdogs +-------------- Watchdog timers, such as the lock detector in Linux may fire accidentally when running under hardware virtualization due to timer interrupts being delayed or @@ -587,7 +618,8 @@ misinterpretation of the passage of real time. Usually, these warnings are spurious and can be ignored, but in some circumstances it may be necessary to disable such detection. -4.7) Delays and precision timing +4.7. Delays and precision timing +-------------------------------- Precise timing and delays may not be possible in a virtualized system. This can happen if the system is controlling physical hardware, or issues delays to @@ -600,7 +632,8 @@ The second issue may cause performance problems, but this is unlikely to be a significant issue. In many cases these delays may be eliminated through configuration or paravirtualization. -4.8) Covert channels and leaks +4.8. Covert channels and leaks +------------------------------ In addition to the above problems, time information will inevitably leak to the guest about the host in anything but a perfect implementation of virtualized diff --git a/Documentation/virt/uml/UserModeLinux-HOWTO.txt b/Documentation/virt/uml/user_mode_linux.rst index 87b80f589e1c..de0f0b2c9d5b 100644 --- a/Documentation/virt/uml/UserModeLinux-HOWTO.txt +++ b/Documentation/virt/uml/user_mode_linux.rst @@ -1,12 +1,17 @@ - User Mode Linux HOWTO - User Mode Linux Core Team - Mon Nov 18 14:16:16 EST 2002 +.. SPDX-License-Identifier: GPL-2.0 - This document describes the use and abuse of Jeff Dike's User Mode - Linux: a port of the Linux kernel as a normal Intel Linux process. - ______________________________________________________________________ +===================== +User Mode Linux HOWTO +===================== - Table of Contents +:Author: User Mode Linux Core Team +:Last-updated: Sat Jan 25 16:07:55 CET 2020 + +This document describes the use and abuse of Jeff Dike's User Mode +Linux: a port of the Linux kernel as a normal Intel Linux process. + + +.. Table of Contents 1. Introduction @@ -132,19 +137,19 @@ 15.5 Other contributions - ______________________________________________________________________ - - 1. Introduction +1. Introduction +================ Welcome to User Mode Linux. It's going to be fun. - 1.1. How is User Mode Linux Different? +1.1. How is User Mode Linux Different? +--------------------------------------- Normally, the Linux Kernel talks straight to your hardware (video card, keyboard, hard drives, etc), and any programs which run ask the - kernel to operate the hardware, like so: + kernel to operate the hardware, like so:: @@ -160,10 +165,10 @@ The User Mode Linux Kernel is different; instead of talking to the - hardware, it talks to a `real' Linux kernel (called the `host kernel' + hardware, it talks to a `real` Linux kernel (called the `host kernel` from now on), like any other program. Programs can then run inside User-Mode Linux as if they were running under a normal kernel, like - so: + so:: @@ -181,7 +186,8 @@ - 1.2. Why Would I Want User Mode Linux? +1.2. Why Would I Want User Mode Linux? +--------------------------------------- 1. If User Mode Linux crashes, your host kernel is still fine. @@ -204,83 +210,41 @@ +.. _Compiling_the_kernel_and_modules: - - 2. Compiling the kernel and modules +2. Compiling the kernel and modules +==================================== - 2.1. Compiling the kernel +2.1. Compiling the kernel +-------------------------- Compiling the user mode kernel is just like compiling any other - kernel. Let's go through the steps, using 2.4.0-prerelease (current - as of this writing) as an example: - - - 1. Download the latest UML patch from - - the download page <http://user-mode-linux.sourceforge.net/ - - In this example, the file is uml-patch-2.4.0-prerelease.bz2. + kernel. - 2. Download the matching kernel from your favourite kernel mirror, + 1. Download the latest kernel from your favourite kernel mirror, such as: - ftp://ftp.ca.kernel.org/pub/kernel/v2.4/linux-2.4.0-prerelease.tar.bz2 - <ftp://ftp.ca.kernel.org/pub/kernel/v2.4/linux-2.4.0-prerelease.tar.bz2> - . - - - 3. Make a directory and unpack the kernel into it. - + https://mirrors.edge.kernel.org/pub/linux/kernel/v5.x/linux-5.4.14.tar.xz + 2. Make a directory and unpack the kernel into it:: host% mkdir ~/uml - - - - - host% cd ~/uml - - - - - - host% - tar -xzvf linux-2.4.0-prerelease.tar.bz2 - - - - - - - 4. Apply the patch using - - - - host% - cd ~/uml/linux - - - host% - bzcat uml-patch-2.4.0-prerelease.bz2 | patch -p1 + tar xvf linux-5.4.14.tar.xz - - - - - 5. Run your favorite config; `make xconfig ARCH=um' is the most - convenient. `make config ARCH=um' and 'make menuconfig ARCH=um' + 3. Run your favorite config; ``make xconfig ARCH=um`` is the most + convenient. ``make config ARCH=um`` and ``make menuconfig ARCH=um`` will work as well. The defaults will give you a useful kernel. If you want to change something, go ahead, it probably won't hurt anything. @@ -288,44 +252,20 @@ Note: If the host is configured with a 2G/2G address space split rather than the usual 3G/1G split, then the packaged UML binaries - will not run. They will immediately segfault. See ``UML on 2G/2G - hosts'' for the scoop on running UML on your system. - - - - 6. Finish with `make linux ARCH=um': the result is a file called - `linux' in the top directory of your source tree. - - Make sure that you don't build this kernel in /usr/src/linux. On some - distributions, /usr/include/asm is a link into this pool. The user- - mode build changes the other end of that link, and things that include - <asm/anything.h> stop compiling. - - The sources are also available from cvs at the project's cvs page, - which has directions on getting the sources. You can also browse the - CVS pool from there. + will not run. They will immediately segfault. See + :ref:`UML_on_2G/2G_hosts` for the scoop on running UML on your system. - If you get the CVS sources, you will have to check them out into an - empty directory. You will then have to copy each file into the - corresponding directory in the appropriate kernel pool. - If you don't have the latest kernel pool, you can get the - corresponding user-mode sources with + 4. Finish with ``make linux ARCH=um``: the result is a file called + ``linux`` in the top directory of your source tree. - host% cvs co -r v_2_3_x linux - - - - where 'x' is the version in your pool. Note that you will not get the - bug fixes and enhancements that have gone into subsequent releases. - - - 2.2. Compiling and installing kernel modules +2.2. Compiling and installing kernel modules +--------------------------------------------- UML modules are built in the same way as the native kernel (with the - exception of the 'ARCH=um' that you always need for UML): + exception of the 'ARCH=um' that you always need for UML):: host% make modules ARCH=um @@ -337,12 +277,12 @@ the user-mode pool. Modules from the native kernel won't work. You can install them by using ftp or something to copy them into the - virtual machine and dropping them into /lib/modules/`uname -r`. + virtual machine and dropping them into ``/lib/modules/$(uname -r)``. You can also get the kernel build process to install them as follows: 1. with the kernel not booted, mount the root filesystem in the top - level of the kernel pool: + level of the kernel pool:: host% mount root_fs mnt -o loop @@ -352,7 +292,7 @@ - 2. run + 2. run:: host% @@ -363,7 +303,7 @@ - 3. unmount the filesystem + 3. unmount the filesystem:: host% umount mnt @@ -381,27 +321,28 @@ as modules, especially filesystems and network protocols and filters, so most symbols which need to be exported probably already are. However, if you do find symbols that need exporting, let us - <http://user-mode-linux.sourceforge.net/> know, and + know at http://user-mode-linux.sourceforge.net/, and they'll be "taken care of". - 2.3. Compiling and installing uml_utilities +2.3. Compiling and installing uml_utilities +-------------------------------------------- Many features of the UML kernel require a user-space helper program, so a uml_utilities package is distributed separately from the kernel patch which provides these helpers. Included within this is: - o port-helper - Used by consoles which connect to xterms or ports + - port-helper - Used by consoles which connect to xterms or ports - o tunctl - Configuration tool to create and delete tap devices + - tunctl - Configuration tool to create and delete tap devices - o uml_net - Setuid binary for automatic tap device configuration + - uml_net - Setuid binary for automatic tap device configuration - o uml_switch - User-space virtual switch required for daemon + - uml_switch - User-space virtual switch required for daemon transport - The uml_utilities tree is compiled with: + The uml_utilities tree is compiled with:: host# @@ -423,38 +364,42 @@ - 3. Running UML and logging in +3. Running UML and logging in +============================== - 3.1. Running UML +3.1. Running UML +----------------- - It runs on 2.2.15 or later, and all 2.4 kernels. + It runs on 2.2.15 or later, and all kernel versions since 2.4. Booting UML is straightforward. Simply run 'linux': it will try to - mount the file `root_fs' in the current directory. You do not need to - run it as root. If your root filesystem is not named `root_fs', then - you need to put a `ubd0=root_fs_whatever' switch on the linux command + mount the file ``root_fs`` in the current directory. You do not need to + run it as root. If your root filesystem is not named ``root_fs``, then + you need to put a ``ubd0=root_fs_whatever`` switch on the linux command line. You will need a filesystem to boot UML from. There are a number - available for download from here <http://user-mode- - linux.sourceforge.net/> . There are also several tools - <http://user-mode-linux.sourceforge.net/> which can be + available for download from http://user-mode-linux.sourceforge.net. + There are also several tools at + http://user-mode-linux.sourceforge.net/ which can be used to generate UML-compatible filesystem images from media. The kernel will boot up and present you with a login prompt. - Note: If the host is configured with a 2G/2G address space split +Note: + If the host is configured with a 2G/2G address space split rather than the usual 3G/1G split, then the packaged UML binaries will - not run. They will immediately segfault. See ``UML on 2G/2G hosts'' + not run. They will immediately segfault. See :ref:`UML_on_2G/2G_hosts` for the scoop on running UML on your system. - 3.2. Logging in +3.2. Logging in +---------------- @@ -468,22 +413,22 @@ There are a couple of other ways to log in: - o On a virtual console + - On a virtual console Each virtual console that is configured (i.e. the device exists in /dev and /etc/inittab runs a getty on it) will come up in its own - xterm. If you get tired of the xterms, read ``Setting up serial - lines and consoles'' to see how to attach the consoles to - something else, like host ptys. + xterm. If you get tired of the xterms, read + :ref:`setting_up_serial_lines_and_consoles` to see how to attach + the consoles to something else, like host ptys. - o Over the serial line + - Over the serial line - In the boot output, find a line that looks like: + In the boot output, find a line that looks like:: @@ -493,7 +438,7 @@ Attach your favorite terminal program to the corresponding tty. I.e. - for minicom, the command would be + for minicom, the command would be:: host% minicom -o -p /dev/ttyp1 @@ -503,37 +448,40 @@ - o Over the net + - Over the net If the network is running, then you can telnet to the virtual - machine and log in to it. See ``Setting up the network'' to learn + machine and log in to it. See :ref:`Setting_up_the_network` to learn about setting up a virtual network. When you're done using it, run halt, and the kernel will bring itself down and the process will exit. - 3.3. Examples +3.3. Examples +-------------- Here are some examples of UML in action: - o A login session <http://user-mode-linux.sourceforge.net/login.html> + - A login session http://user-mode-linux.sourceforge.net/old/login.html - o A virtual network <http://user-mode-linux.sourceforge.net/net.html> + - A virtual network http://user-mode-linux.sourceforge.net/old/net.html +.. _UML_on_2G/2G_hosts: +4. UML on 2G/2G hosts +====================== - 4. UML on 2G/2G hosts - - 4.1. Introduction +4.1. Introduction +------------------ Most Linux machines are configured so that the kernel occupies the @@ -546,7 +494,8 @@ - 4.2. The problem +4.2. The problem +----------------- The prebuilt UML binaries on this site will not run on 2G/2G hosts @@ -558,13 +507,14 @@ - 4.3. The solution +4.3. The solution +------------------ The fix for this is to rebuild UML from source after enabling CONFIG_HOST_2G_2G (under 'General Setup'). This will cause UML to load itself in the top .5G of that smaller process address space, - where it will run fine. See ``Compiling the kernel and modules'' if + where it will run fine. See :ref:`Compiling_the_kernel_and_modules` if you need help building UML from source. @@ -573,10 +523,11 @@ +.. _setting_up_serial_lines_and_consoles: - - 5. Setting up serial lines and consoles +5. Setting up serial lines and consoles +======================================== It is possible to attach UML serial lines and consoles to many types @@ -584,22 +535,23 @@ You can attach them to host ptys, ttys, file descriptors, and ports. - This allows you to do things like + This allows you to do things like: - o have a UML console appear on an unused host console, + - have a UML console appear on an unused host console, - o hook two virtual machines together by having one attach to a pty + - hook two virtual machines together by having one attach to a pty and having the other attach to the corresponding tty - o make a virtual machine accessible from the net by attaching a + - make a virtual machine accessible from the net by attaching a console to a port on the host. - The general format of the command line option is device=channel. + The general format of the command line option is ``device=channel``. - 5.1. Specifying the device +5.1. Specifying the device +--------------------------- Devices are specified with "con" or "ssl" (console or serial line, respectively), optionally with a device number if you are talking @@ -613,7 +565,7 @@ A specific device name will override a less general "con=" or "ssl=". So, for example, you can assign a pty to each of the serial lines - except for the first two like this: + except for the first two like this:: ssl=pty ssl0=tty:/dev/tty0 ssl1=tty:/dev/tty1 @@ -626,13 +578,14 @@ - 5.2. Specifying the channel +5.2. Specifying the channel +---------------------------- There are a number of different types of channels to attach a UML device to, each with a different way of specifying exactly what to attach to. - o pseudo-terminals - device=pty pts terminals - device=pts + - pseudo-terminals - device=pty pts terminals - device=pts This will cause UML to allocate a free host pseudo-terminal for the @@ -640,23 +593,23 @@ log. You access it by attaching a terminal program to the corresponding tty: - o screen /dev/pts/n + - screen /dev/pts/n - o screen /dev/ttyxx + - screen /dev/ttyxx - o minicom -o -p /dev/ttyxx - minicom seems not able to handle pts + - minicom -o -p /dev/ttyxx - minicom seems not able to handle pts devices - o kermit - start it up, 'open' the device, then 'connect' + - kermit - start it up, 'open' the device, then 'connect' - o terminals - device=tty:tty device file + - terminals - device=tty:tty device file - This will make UML attach the device to the specified tty (i.e + This will make UML attach the device to the specified tty (i.e:: con1=tty:/dev/tty3 @@ -672,7 +625,7 @@ - o xterms - device=xterm + - xterms - device=xterm UML will run an xterm and the device will be attached to it. @@ -681,12 +634,12 @@ - o Port - device=port:port number + - Port - device=port:port number This will attach the UML devices to the specified host port. Attaching console 1 to the host's port 9000 would be done like - this: + this:: con1=port:9000 @@ -694,7 +647,7 @@ - Attaching all the serial lines to that port would be done similarly: + Attaching all the serial lines to that port would be done similarly:: ssl=port:9000 @@ -702,8 +655,8 @@ - You access these devices by telnetting to that port. Each active tel- - net session gets a different device. If there are more telnets to a + You access these devices by telnetting to that port. Each active + telnet session gets a different device. If there are more telnets to a port than UML devices attached to it, then the extra telnet sessions will block until an existing telnet detaches, or until another device becomes active (i.e. by being activated in /etc/inittab). @@ -725,13 +678,13 @@ - o already-existing file descriptors - device=file descriptor + - already-existing file descriptors - device=file descriptor If you set up a file descriptor on the UML command line, you can attach a UML device to it. This is most commonly used to put the main console back on stdin and stdout after assigning all the other - consoles to something else: + consoles to something else:: con0=fd:0,fd:1 con=pts @@ -743,7 +696,7 @@ - o Nothing - device=null + - Nothing - device=null This allows the device to be opened, in contrast to 'none', but @@ -754,7 +707,7 @@ - o None - device=none + - None - device=none This causes the device to disappear. @@ -762,7 +715,7 @@ You can also specify different input and output channels for a device - by putting a comma between them: + by putting a comma between them:: ssl3=tty:/dev/tty2,xterm @@ -785,14 +738,15 @@ - 5.3. Examples +5.3. Examples +-------------- There are a number of interesting things you can do with this capability. First, this is how you get rid of those bleeding console xterms by - attaching them to host ptys: + attaching them to host ptys:: con=pty con0=fd:0,fd:1 @@ -802,7 +756,7 @@ This will make a UML console take over an unused host virtual console, so that when you switch to it, you will see the UML login prompt - rather than the host login prompt: + rather than the host login prompt:: con1=tty:/dev/tty6 @@ -813,7 +767,7 @@ You can attach two virtual machines together with what amounts to a serial line as follows: - Run one UML with a serial line attached to a pty - + Run one UML with a serial line attached to a pty:: ssl1=pty @@ -825,7 +779,7 @@ that it got /dev/ptyp1). Boot the other UML with a serial line attached to the corresponding - tty - + tty:: ssl1=tty:/dev/ttyp1 @@ -838,7 +792,10 @@ prompt of the other virtual machine. - 6. Setting up the network +.. _setting_up_the_network: + +6. Setting up the network +========================== @@ -858,19 +815,19 @@ There are currently five transport types available for a UML virtual machine to exchange packets with other hosts: - o ethertap + - ethertap - o TUN/TAP + - TUN/TAP - o Multicast + - Multicast - o a switch daemon + - a switch daemon - o slip + - slip - o slirp + - slirp - o pcap + - pcap The TUN/TAP, ethertap, slip, and slirp transports allow a UML instance to exchange packets with the host. They may be directed @@ -893,28 +850,28 @@ With so many host transports, which one should you use? Here's when you should use each one: - o ethertap - if you want access to the host networking and it is + - ethertap - if you want access to the host networking and it is running 2.2 - o TUN/TAP - if you want access to the host networking and it is + - TUN/TAP - if you want access to the host networking and it is running 2.4. Also, the TUN/TAP transport is able to use a preconfigured device, allowing it to avoid using the setuid uml_net helper, which is a security advantage. - o Multicast - if you want a purely virtual network and you don't want + - Multicast - if you want a purely virtual network and you don't want to set up anything but the UML - o a switch daemon - if you want a purely virtual network and you + - a switch daemon - if you want a purely virtual network and you don't mind running the daemon in order to get somewhat better performance - o slip - there is no particular reason to run the slip backend unless + - slip - there is no particular reason to run the slip backend unless ethertap and TUN/TAP are just not available for some reason - o slirp - if you don't have root access on the host to setup + - slirp - if you don't have root access on the host to setup networking, or if you don't want to allocate an IP to your UML - o pcap - not much use for actual network connectivity, but great for + - pcap - not much use for actual network connectivity, but great for monitoring traffic on the host Ethertap is available on 2.4 and works fine. TUN/TAP is preferred @@ -926,7 +883,8 @@ exploit the helper's root privileges. - 6.1. General setup +6.1. General setup +------------------- First, you must have the virtual network enabled in your UML. If are running a prebuilt kernel from this site, everything is already @@ -938,7 +896,7 @@ The next step is to provide a network device to the virtual machine. This is done by describing it on the kernel command line. - The general format is + The general format is:: eth <n> = <transport> , <transport args> @@ -947,7 +905,7 @@ For example, a virtual ethernet device may be attached to a host - ethertap device as follows: + ethertap device as follows:: eth0=ethertap,tap0,fe:fd:0:0:0:1,192.168.0.254 @@ -978,7 +936,7 @@ You can also add devices to a UML and remove them at runtime. See the - ``The Management Console'' page for details. + :ref:`The_Management_Console` page for details. The sections below describe this in more detail. @@ -995,7 +953,8 @@ - 6.2. Userspace daemons +6.2. Userspace daemons +----------------------- You will likely need the setuid helper, or the switch daemon, or both. They are both installed with the RPM and deb, so if you've installed @@ -1011,7 +970,8 @@ - 6.3. Specifying ethernet addresses +6.3. Specifying ethernet addresses +----------------------------------- Below, you will see that the TUN/TAP, ethertap, and daemon interfaces allow you to specify hardware addresses for the virtual ethernet @@ -1023,21 +983,21 @@ sufficient to guarantee a unique hardware address for the device. A couple of exceptions are: - o Another set of virtual ethernet devices are on the same network and + - Another set of virtual ethernet devices are on the same network and they are assigned hardware addresses using a different scheme which may conflict with the UML IP address-based scheme - o You aren't going to use the device for IP networking, so you don't + - You aren't going to use the device for IP networking, so you don't assign the device an IP address If you let the driver provide the hardware address, you should make sure that the device IP address is known before the interface is - brought up. So, inside UML, this will guarantee that: + brought up. So, inside UML, this will guarantee that:: - UML# - ifconfig eth0 192.168.0.250 up + UML# + ifconfig eth0 192.168.0.250 up @@ -1049,13 +1009,14 @@ - 6.4. UML interface setup +6.4. UML interface setup +------------------------- Once the network devices have been described on the command line, you should boot UML and log in. - The first thing to do is bring the interface up: + The first thing to do is bring the interface up:: UML# ifconfig ethn ip-address up @@ -1067,7 +1028,7 @@ To reach the rest of the world, you should set a default route to the - host: + host:: UML# route add default gw host ip @@ -1075,7 +1036,7 @@ - Again, with host ip of 192.168.0.4: + Again, with host ip of 192.168.0.4:: UML# route add default gw 192.168.0.4 @@ -1097,29 +1058,25 @@ Note: If you can't communicate with other hosts on your physical ethernet, it's probably because of a network route that's automatically set up. If you run 'route -n' and see a route that - looks like this: + looks like this:: - Destination Gateway Genmask Flags Metric Ref Use Iface - 192.168.0.0 0.0.0.0 255.255.255.0 U 0 0 0 eth0 + Destination Gateway Genmask Flags Metric Ref Use Iface + 192.168.0.0 0.0.0.0 255.255.255.0 U 0 0 0 eth0 with a mask that's not 255.255.255.255, then replace it with a route - to your host: + to your host:: UML# route del -net 192.168.0.0 dev eth0 netmask 255.255.255.0 - - - - UML# route add -host 192.168.0.4 dev eth0 @@ -1131,7 +1088,8 @@ - 6.5. Multicast +6.5. Multicast +--------------- The simplest way to set up a virtual network between multiple UMLs is to use the mcast transport. This was written by Harald Welte and is @@ -1142,7 +1100,7 @@ messages when you bring the device up inside UML. - To use it, run two UMLs with + To use it, run two UMLs with:: eth0=mcast @@ -1151,16 +1109,12 @@ on their command lines. Log in, configure the ethernet device in each - machine with different IP addresses: + machine with different IP addresses:: UML1# ifconfig eth0 192.168.0.254 - - - - UML2# ifconfig eth0 192.168.0.253 @@ -1168,7 +1122,7 @@ and they should be able to talk to each other. - The full set of command line options for this transport are + The full set of command line options for this transport are:: @@ -1177,16 +1131,11 @@ - - Harald's original README is here <http://user-mode-linux.source- - forge.net/> and explains these in detail, as well as - some other issues. - There is also a related point-to-point only "ucast" transport. This is useful when your network does not support multicast, and all network connections are simple point to point links. - The full set of command line options for this transport are + The full set of command line options for this transport are:: ethn=ucast,ethernet address,remote address,listen port,remote port @@ -1194,7 +1143,8 @@ - 6.6. TUN/TAP with the uml_net helper +6.6. TUN/TAP with the uml_net helper +------------------------------------- TUN/TAP is the preferred mechanism on 2.4 to exchange packets with the host. The TUN/TAP backend has been in UML since 2.4.9-3um. @@ -1216,7 +1166,7 @@ kernel or as the tun.o module. The format of the command line switch to attach a device to a TUN/TAP - device is + device is:: eth <n> =tuntap,,, <IP address> @@ -1226,7 +1176,7 @@ For example, this argument will attach the UML's eth0 to the next available tap device and assign an ethernet address to it based on its - IP address + IP address:: eth0=tuntap,,,192.168.0.254 @@ -1247,10 +1197,10 @@ There are a couple potential problems with running the TUN/TAP transport on a 2.4 host kernel - o TUN/TAP seems not to work on 2.4.3 and earlier. Upgrade the host + - TUN/TAP seems not to work on 2.4.3 and earlier. Upgrade the host kernel or use the ethertap transport. - o With an upgraded kernel, TUN/TAP may fail with + - With an upgraded kernel, TUN/TAP may fail with:: File descriptor in bad state @@ -1263,13 +1213,12 @@ make sure that /usr/src/linux points to the headers for the running kernel. - These were pointed out by Tim Robinson <timro at trkr dot net> in - <http://www.geocrawler.com/> name="this uml- - user post"> . + These were pointed out by Tim Robinson <timro at trkr dot net> in the past. - 6.7. TUN/TAP with a preconfigured tap device +6.7. TUN/TAP with a preconfigured tap device +--------------------------------------------- If you prefer not to have UML use uml_net (which is somewhat insecure), with UML 2.4.17-11, you can set up a TUN/TAP device @@ -1277,8 +1226,8 @@ there is no need for root assistance. Setting up the device is done as follows: - o Create the device with tunctl (available from the UML utilities - tarball) + - Create the device with tunctl (available from the UML utilities + tarball):: @@ -1291,8 +1240,8 @@ where uid is the user id or username that UML will be run as. This will tell you what device was created. - o Configure the device IP (change IP addresses and device name to - suit) + - Configure the device IP (change IP addresses and device name to + suit):: @@ -1303,8 +1252,8 @@ - o Set up routing and arping if desired - this is my recipe, there are - other ways of doing the same thing + - Set up routing and arping if desired - this is my recipe, there are + other ways of doing the same thing:: host# @@ -1313,19 +1262,9 @@ host# route add -host 192.168.0.253 dev tap0 - - - - - host# bash -c 'echo 1 > /proc/sys/net/ipv4/conf/tap0/proxy_arp' - - - - - host# arp -Ds 192.168.0.253 eth0 pub @@ -1338,76 +1277,43 @@ utility which reads the information from a config file and sets up devices at boot time. - o Rather than using up two IPs and ARPing for one of them, you can + - Rather than using up two IPs and ARPing for one of them, you can also provide direct access to your LAN by the UML by using a - bridge. + bridge:: host# brctl addbr br0 - - - - host# ifconfig eth0 0.0.0.0 promisc up - - - - host# ifconfig tap0 0.0.0.0 promisc up - - - - host# ifconfig br0 192.168.0.1 netmask 255.255.255.0 up - - - - - - host# - brctl stp br0 off - - - - + host# + brctl stp br0 off host# brctl setfd br0 1 - - - - host# brctl sethello br0 1 - - - - host# brctl addif br0 eth0 - - - - host# brctl addif br0 tap0 @@ -1417,12 +1323,12 @@ Note that 'br0' should be setup using ifconfig with the existing IP address of eth0, as eth0 no longer has its own IP. - o + - Also, the /dev/net/tun device must be writable by the user running UML in order for the UML to use the device that's been configured - for it. The simplest thing to do is + for it. The simplest thing to do is:: host# chmod 666 /dev/net/tun @@ -1438,14 +1344,14 @@ devices and chgrp /dev/net/tun to that group with mode 664 or 660. - o Once the device is set up, run UML with 'eth0=tuntap,device name' + - Once the device is set up, run UML with 'eth0=tuntap,device name' (i.e. 'eth0=tuntap,tap0') on the command line (or do it with the mconsole config command). - o Bring the eth device up in UML and you're in business. + - Bring the eth device up in UML and you're in business. If you don't want that tap device any more, you can make it non- - persistent with + persistent with:: host# tunctl -d tap device @@ -1455,7 +1361,7 @@ Finally, tunctl has a -b (for brief mode) switch which causes it to output only the name of the tap device it created. This makes it - suitable for capture by a script: + suitable for capture by a script:: host# TAP=`tunctl -u 1000 -b` @@ -1465,7 +1371,8 @@ - 6.8. Ethertap +6.8. Ethertap +-------------- Ethertap is the general mechanism on 2.2 for userspace processes to exchange packets with the kernel. @@ -1473,7 +1380,7 @@ To use this transport, you need to describe the virtual network device - on the UML command line. The general format for this is + on the UML command line. The general format for this is:: eth <n> =ethertap, <device> , <ethernet address> , <tap IP address> @@ -1481,7 +1388,7 @@ - So, the previous example + So, the previous example:: eth0=ethertap,tap0,fe:fd:0:0:0:1,192.168.0.254 @@ -1521,7 +1428,7 @@ If you want to set things up yourself, you need to make sure that the appropriate /dev entry exists. If it doesn't, become root and create - it as follows: + it as follows:: mknod /dev/tap <minor> c 36 <minor> + 16 @@ -1529,7 +1436,7 @@ - For example, this is how to create /dev/tap0: + For example, this is how to create /dev/tap0:: mknod /dev/tap0 c 36 0 + 16 @@ -1539,7 +1446,7 @@ You also need to make sure that the host kernel has ethertap support. If ethertap is enabled as a module, you apparently need to insmod - ethertap once for each ethertap device you want to enable. So, + ethertap once for each ethertap device you want to enable. So,:: host# @@ -1549,7 +1456,7 @@ will give you the tap0 interface. To get the tap1 interface, you need - to run + to run:: host# @@ -1561,7 +1468,8 @@ - 6.9. The switch daemon +6.9. The switch daemon +----------------------- Note: This is the daemon formerly known as uml_router, but which was renamed so the network weenies of the world would stop growling at me. @@ -1577,7 +1485,7 @@ sockets. - If you want it to listen on a different pair of sockets, use + If you want it to listen on a different pair of sockets, use:: -unix control socket data socket @@ -1586,7 +1494,7 @@ - If you want it to act as a hub rather than a switch, use + If you want it to act as a hub rather than a switch, use:: -hub @@ -1596,7 +1504,7 @@ If you want the switch to be connected to host networking (allowing - the umls to get access to the outside world through the host), use + the umls to get access to the outside world through the host), use:: -tap tap0 @@ -1610,7 +1518,7 @@ device than tap0, specify that instead of tap0. - uml_switch can be backgrounded as follows + uml_switch can be backgrounded as follows:: host% @@ -1623,7 +1531,7 @@ stdin for EOF. When it sees that, it exits. - The general format of the kernel command line switch is + The general format of the kernel command line switch is:: @@ -1639,7 +1547,8 @@ how to communicate with the daemon. You should only specify them if you told the daemon to use different sockets than the default. So, if you ran the daemon with no arguments, running the UML on the same - machine with + machine with:: + eth0=daemon @@ -1649,7 +1558,8 @@ - 6.10. Slip +6.10. Slip +----------- Slip is another, less general, mechanism for a process to communicate with the host networking. In contrast to the ethertap interface, @@ -1658,7 +1568,7 @@ IP. - The general format of the command line switch is + The general format of the command line switch is:: @@ -1681,7 +1591,8 @@ - 6.11. Slirp +6.11. Slirp +------------ slirp uses an external program, usually /usr/bin/slirp, to provide IP only networking connectivity through the host. This is similar to IP @@ -1691,7 +1602,7 @@ root access or setuid binaries on the host. - The general format of the command line switch for slirp is: + The general format of the command line switch for slirp is:: @@ -1716,7 +1627,7 @@ The eth0 interface on UML should be set up with the IP 10.2.0.15, although you can use anything as long as it is not used by a network you will be connecting to. The default route on UML should be set to - use + use:: UML# @@ -1737,10 +1648,11 @@ - 6.12. pcap +6.12. pcap +----------- The pcap transport is attached to a UML ethernet device on the command - line or with uml_mconsole with the following syntax: + line or with uml_mconsole with the following syntax:: @@ -1762,7 +1674,7 @@ expression optimizer is used. - Example: + Example:: @@ -1777,7 +1689,8 @@ - 6.13. Setting up the host yourself +6.13. Setting up the host yourself +----------------------------------- If you don't specify an address for the host side of the ethertap or slip device, UML won't do any setup on the host. So this is what is @@ -1785,19 +1698,15 @@ 192.168.0.251 and a UML-side IP of 192.168.0.250 - adjust to suit your own network): - o The device needs to be configured with its IP address. Tap devices + - The device needs to be configured with its IP address. Tap devices are also configured with an mtu of 1484. Slip devices are configured with a point-to-point address pointing at the UML ip - address. + address:: host# ifconfig tap0 arp mtu 1484 192.168.0.251 up - - - - host# ifconfig sl0 192.168.0.251 pointopoint 192.168.0.250 up @@ -1805,7 +1714,7 @@ - o If a tap device is being set up, a route is set to the UML IP. + - If a tap device is being set up, a route is set to the UML IP:: UML# route add -host 192.168.0.250 gw 192.168.0.251 @@ -1814,8 +1723,8 @@ - o To allow other hosts on your network to see the virtual machine, - proxy arp is set up for it. + - To allow other hosts on your network to see the virtual machine, + proxy arp is set up for it:: host# arp -Ds 192.168.0.250 eth0 pub @@ -1824,7 +1733,7 @@ - o Finally, the host is set up to route packets. + - Finally, the host is set up to route packets:: host# echo 1 > /proc/sys/net/ipv4/ip_forward @@ -1838,12 +1747,14 @@ - 7. Sharing Filesystems between Virtual Machines +7. Sharing Filesystems between Virtual Machines +================================================ - 7.1. A warning +7.1. A warning +--------------- Don't attempt to share filesystems simply by booting two UMLs from the same file. That's the same thing as booting two physical machines @@ -1851,7 +1762,8 @@ - 7.2. Using layered block devices +7.2. Using layered block devices +--------------------------------- The way to share a filesystem between two virtual machines is to use the copy-on-write (COW) layering capability of the ubd block driver. @@ -1872,7 +1784,7 @@ To add a copy-on-write layer to an existing block device file, simply - add the name of the COW file to the appropriate ubd switch: + add the name of the COW file to the appropriate ubd switch:: ubd0=root_fs_cow,root_fs_debian_22 @@ -1883,7 +1795,7 @@ where 'root_fs_cow' is the private COW file and 'root_fs_debian_22' is the existing shared filesystem. The COW file need not exist. If it doesn't, the driver will create and initialize it. Once the COW file - has been initialized, it can be used on its own on the command line: + has been initialized, it can be used on its own on the command line:: ubd0=root_fs_cow @@ -1896,14 +1808,16 @@ - 7.3. Note! +7.3. Note! +----------- When checking the size of the COW file in order to see the gobs of space that you're saving, make sure you use 'ls -ls' to see the actual disk consumption rather than the length of the file. The COW file is sparse, so the length will be very different from the disk usage. Here is a 'ls -l' of a COW file and backing file from one boot and - shutdown: + shutdown:: + host% ls -l cow.debian debian2.2 -rw-r--r-- 1 jdike jdike 492504064 Aug 6 21:16 cow.debian -rwxrw-rw- 1 jdike jdike 537919488 Aug 6 20:42 debian2.2 @@ -1911,7 +1825,7 @@ - Doesn't look like much saved space, does it? Well, here's 'ls -ls': + Doesn't look like much saved space, does it? Well, here's 'ls -ls':: host% ls -ls cow.debian debian2.2 @@ -1926,7 +1840,8 @@ - 7.4. Another warning +7.4. Another warning +--------------------- Once a filesystem is being used as a readonly backing file for a COW file, do not boot directly from it or modify it in any way. Doing so @@ -1952,7 +1867,8 @@ - 7.5. uml_moo : Merging a COW file with its backing file +7.5. uml_moo : Merging a COW file with its backing file +-------------------------------------------------------- Depending on how you use UML and COW devices, it may be advisable to merge the changes in the COW file into the backing file every once in @@ -1961,7 +1877,7 @@ - The utility that does this is uml_moo. Its usage is + The utility that does this is uml_moo. Its usage is:: host% uml_moo COW file new backing file @@ -1991,8 +1907,8 @@ uml_moo is installed with the UML deb and RPM. If you didn't install UML from one of those packages, you can also get it from the UML - utilities <http://user-mode-linux.sourceforge.net/ - utilities> tar file in tools/moo. + utilities http://user-mode-linux.sourceforge.net/utilities tar file + in tools/moo. @@ -2001,7 +1917,8 @@ - 8. Creating filesystems +8. Creating filesystems +======================== You may want to create and mount new UML filesystems, either because @@ -2015,13 +1932,14 @@ should be easy to translate to the filesystem of your choice. - 8.1. Create the filesystem file +8.1. Create the filesystem file +================================ dd is your friend. All you need to do is tell dd to create an empty file of the appropriate size. I usually make it sparse to save time and to avoid allocating disk space until it's actually used. For example, the following command will create a sparse 100 meg file full - of zeroes. + of zeroes:: host% @@ -2034,9 +1952,9 @@ 8.2. Assign the file to a UML device - Add an argument like the following to the UML command line: + Add an argument like the following to the UML command line:: - ubd4=new_filesystem + ubd4=new_filesystem @@ -2053,7 +1971,7 @@ etc), then get them into UML by way of the net or hostfs. - Make the new filesystem on the device assigned to the new file: + Make the new filesystem on the device assigned to the new file:: host# mkreiserfs /dev/ubd/4 @@ -2077,7 +1995,7 @@ - Now, mount it: + Now, mount it:: UML# @@ -2096,7 +2014,8 @@ - 9. Host file access +9. Host file access +==================== If you want to access files on the host machine from inside UML, you @@ -2112,10 +2031,11 @@ files contained in it just as you would on the host. - 9.1. Using hostfs +9.1. Using hostfs +------------------ To begin with, make sure that hostfs is available inside the virtual - machine with + machine with:: UML# cat /proc/filesystems @@ -2127,7 +2047,7 @@ module and available inside the virtual machine, and insmod it. - Now all you need to do is run mount: + Now all you need to do is run mount:: UML# mount none /mnt/host -t hostfs @@ -2139,7 +2059,7 @@ If you don't want to mount the host root directory, then you can - specify a subdirectory to mount with the -o switch to mount: + specify a subdirectory to mount with the -o switch to mount:: UML# mount none /mnt/home -t hostfs -o /home @@ -2151,13 +2071,14 @@ - 9.2. hostfs as the root filesystem +9.2. hostfs as the root filesystem +----------------------------------- It's possible to boot from a directory hierarchy on the host using hostfs rather than using the standard filesystem in a file. To start, you need that hierarchy. The easiest way is to loop mount - an existing root_fs file: + an existing root_fs file:: host# mount root_fs uml_root_dir -o loop @@ -2166,15 +2087,15 @@ You need to change the filesystem type of / in etc/fstab to be - 'hostfs', so that line looks like this: + 'hostfs', so that line looks like this:: - /dev/ubd/0 / hostfs defaults 1 1 + /dev/ubd/0 / hostfs defaults 1 1 Then you need to chown to yourself all the files in that directory - that are owned by root. This worked for me: + that are owned by root. This worked for me:: host# find . -uid 0 -exec chown jdike {} \; @@ -2183,7 +2104,7 @@ Next, make sure that your UML kernel has hostfs compiled in, not as a - module. Then run UML with the boot device pointing at that directory: + module. Then run UML with the boot device pointing at that directory:: ubd0=/path/to/uml/root/directory @@ -2194,41 +2115,35 @@ UML should then boot as it does normally. - 9.3. Building hostfs +9.3. Building hostfs +--------------------- If you need to build hostfs because it's not in your kernel, you have two choices: - o Compiling hostfs into the kernel: + - Compiling hostfs into the kernel: Reconfigure the kernel and set the 'Host filesystem' option under - o Compiling hostfs as a module: + - Compiling hostfs as a module: Reconfigure the kernel and set the 'Host filesystem' option under be in arch/um/fs/hostfs/hostfs.o. Install that in - /lib/modules/`uname -r`/fs in the virtual machine, boot it up, and + ``/lib/modules/$(uname -r)/fs`` in the virtual machine, boot it up, and:: UML# insmod hostfs +.. _The_Management_Console: - - - - - - - - - - 10. The Management Console +10. The Management Console +=========================== @@ -2240,15 +2155,15 @@ There are a number of things you can do with the mconsole interface: - o get the kernel version + - get the kernel version - o add and remove devices + - add and remove devices - o halt or reboot the machine + - halt or reboot the machine - o Send SysRq commands + - Send SysRq commands - o Pause and resume the UML + - Pause and resume the UML You need the mconsole client (uml_mconsole) which is present in CVS @@ -2257,7 +2172,7 @@ You also need CONFIG_MCONSOLE (under 'General Setup') enabled in UML. - When you boot UML, you'll see a line like: + When you boot UML, you'll see a line like:: mconsole initialized on /home/jdike/.uml/umlNJ32yL/mconsole @@ -2265,7 +2180,7 @@ - If you specify a unique machine id one the UML command line, i.e. + If you specify a unique machine id one the UML command line, i.e.:: umid=debian @@ -2273,7 +2188,7 @@ - you'll see this + you'll see this:: mconsole initialized on /home/jdike/.uml/debian/mconsole @@ -2282,7 +2197,7 @@ That file is the socket that uml_mconsole will use to communicate with - UML. Run it with either the umid or the full path as its argument: + UML. Run it with either the umid or the full path as its argument:: host% uml_mconsole debian @@ -2290,7 +2205,7 @@ - or + or:: host% uml_mconsole /home/jdike/.uml/debian/mconsole @@ -2300,30 +2215,31 @@ You'll get a prompt, at which you can run one of these commands: - o version + - version - o halt + - halt - o reboot + - reboot - o config + - config - o remove + - remove - o sysrq + - sysrq - o help + - help - o cad + - cad - o stop + - stop - o go + - go - 10.1. version +10.1. version +-------------- - This takes no arguments. It prints the UML version. + This takes no arguments. It prints the UML version:: (mconsole) version @@ -2342,11 +2258,12 @@ - 10.2. halt and reboot +10.2. halt and reboot +---------------------- These take no arguments. They shut the machine down immediately, with no syncing of disks and no clean shutdown of userspace. So, they are - pretty close to crashing the machine. + pretty close to crashing the machine:: (mconsole) halt @@ -2357,34 +2274,36 @@ - 10.3. config +10.3. config +------------- "config" adds a new device to the virtual machine. Currently the ubd and network drivers support this. It takes one argument, which is the - device to add, with the same syntax as the kernel command line. + device to add, with the same syntax as the kernel command line:: - (mconsole) - config ubd3=/home/jdike/incoming/roots/root_fs_debian22 + (mconsole) + config ubd3=/home/jdike/incoming/roots/root_fs_debian22 - OK - (mconsole) config eth1=mcast - OK + OK + (mconsole) config eth1=mcast + OK - 10.4. remove +10.4. remove +------------- "remove" deletes a device from the system. Its argument is just the name of the device to be removed. The device must be idle in whatever sense the driver considers necessary. In the case of the ubd driver, the removed block device must not be mounted, swapped on, or otherwise - open, and in the case of the network driver, the device must be down. + open, and in the case of the network driver, the device must be down:: (mconsole) remove ubd3 @@ -2397,7 +2316,8 @@ - 10.5. sysrq +10.5. sysrq +------------ This takes one argument, which is a single letter. It calls the generic kernel's SysRq driver, which does whatever is called for by @@ -2407,19 +2327,21 @@ - 10.6. help +10.6. help +----------- "help" returns a string listing the valid commands and what each one does. - 10.7. cad +10.7. cad +---------- This invokes the Ctl-Alt-Del action on init. What exactly this ends up doing is up to /etc/inittab. Normally, it reboots the machine. With UML, this is usually not desired, so if a halt would be better, - then find the section of inittab that looks like this + then find the section of inittab that looks like this:: # What to do when CTRL-ALT-DEL is pressed. @@ -2432,7 +2354,8 @@ - 10.8. stop +10.8. stop +----------- This puts the UML in a loop reading mconsole requests until a 'go' mconsole command is received. This is very useful for making backups @@ -2448,7 +2371,8 @@ - 10.9. go +10.9. go +--------- This resumes a UML after being paused by a 'stop' command. Note that when the UML has resumed, TCP connections may have timed out and if @@ -2460,9 +2384,10 @@ +.. _Kernel_debugging: - - 11. Kernel debugging +11. Kernel debugging +===================== Note: The interface that makes debugging, as described here, possible @@ -2477,15 +2402,16 @@ In order to debug the kernel, you need build it from source. See - ``Compiling the kernel and modules'' for information on doing that. + :ref:`Compiling_the_kernel_and_modules` for information on doing that. Make sure that you enable CONFIG_DEBUGSYM and CONFIG_PT_PROXY during - the config. These will compile the kernel with -g, and enable the + the config. These will compile the kernel with ``-g``, and enable the ptrace proxy so that gdb works with UML, respectively. - 11.1. Starting the kernel under gdb +11.1. Starting the kernel under gdb +------------------------------------ You can have the kernel running under the control of gdb from the beginning by putting 'debug' on the command line. You will get an @@ -2498,7 +2424,11 @@ There is a transcript of a debugging session here <debug- session.html> , with breakpoints being set in the scheduler and in an interrupt handler. - 11.2. Examining sleeping processes + + +11.2. Examining sleeping processes +----------------------------------- + Not every bug is evident in the currently running process. Sometimes, processes hang in the kernel when they shouldn't because they've @@ -2516,7 +2446,7 @@ Now what you do is this: - o detach from the current thread + - detach from the current thread:: (UML gdb) det @@ -2525,7 +2455,7 @@ - o attach to the thread you are interested in + - attach to the thread you are interested in:: (UML gdb) att <host pid> @@ -2534,7 +2464,7 @@ - o look at its stack and anything else of interest + - look at its stack and anything else of interest:: (UML gdb) bt @@ -2545,18 +2475,14 @@ Note that you can't do anything at this point that requires that a process execute, e.g. calling a function - o when you're done looking at that process, reattach to the current - thread and continue it + - when you're done looking at that process, reattach to the current + thread and continue it:: (UML gdb) att 1 - - - - (UML gdb) c @@ -2569,12 +2495,13 @@ - 11.3. Running ddd on UML +11.3. Running ddd on UML +------------------------- ddd works on UML, but requires a special kludge. The process goes like this: - o Start ddd + - Start ddd:: host% ddd linux @@ -2583,14 +2510,14 @@ - o With ps, get the pid of the gdb that ddd started. You can ask the + - With ps, get the pid of the gdb that ddd started. You can ask the gdb to tell you, but for some reason that confuses things and causes a hang. - o run UML with 'debug=parent gdb-pid=<pid>' added to the command line + - run UML with 'debug=parent gdb-pid=<pid>' added to the command line - it will just sit there after you hit return - o type 'att 1' to the ddd gdb and you will see something like + - type 'att 1' to the ddd gdb and you will see something like:: 0xa013dc51 in __kill () @@ -2602,12 +2529,14 @@ - o At this point, type 'c', UML will boot up, and you can use ddd just + - At this point, type 'c', UML will boot up, and you can use ddd just as you do on any other process. - 11.4. Debugging modules +11.4. Debugging modules +------------------------ + gdb has support for debugging code which is dynamically loaded into the process. This support is what is needed to debug kernel modules @@ -2629,7 +2558,8 @@ First, you must tell it where your modules are. There is a list in - the script that looks like this: + the script that looks like this:: + set MODULE_PATHS { "fat" "/usr/src/uml/linux-2.4.18/fs/fat/fat.o" "isofs" "/usr/src/uml/linux-2.4.18/fs/isofs/isofs.o" @@ -2641,9 +2571,7 @@ You change that to list the names and paths of the modules that you are going to debug. Then you run it from the toplevel directory of - your UML pool and it basically tells you what to do: - - + your UML pool and it basically tells you what to do:: ******** GDB pid is 21903 ******** @@ -2666,7 +2594,7 @@ After you run UML and it sits there doing nothing, you hit return at - the 'att 1' and continue it: + the 'att 1' and continue it:: Attaching to program: /home/jdike/linux/2.4/um/./linux, process 1 @@ -2678,63 +2606,48 @@ At this point, you debug normally. When you insmod something, the - expect magic will kick in and you'll see something like: - - - - - - - - - - - - - - - - - - *** Module hostfs loaded *** - Breakpoint 1, sys_init_module (name_user=0x805abb0 "hostfs", - mod_user=0x8070e00) at module.c:349 - 349 char *name, *n_name, *name_tmp = NULL; - (UML gdb) finish - Run till exit from #0 sys_init_module (name_user=0x805abb0 "hostfs", - mod_user=0x8070e00) at module.c:349 - 0xa00e2e23 in execute_syscall (r=0xa8140284) at syscall_kern.c:411 - 411 else res = EXECUTE_SYSCALL(syscall, regs); - Value returned is $1 = 0 - (UML gdb) - p/x (int)module_list + module_list->size_of_struct - - $2 = 0xa9021054 - (UML gdb) symbol-file ./linux - Load new symbol table from "./linux"? (y or n) y - Reading symbols from ./linux... - done. - (UML gdb) - add-symbol-file /home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o 0xa9021054 - - add symbol table from file "/home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o" at - .text_addr = 0xa9021054 - (y or n) y - - Reading symbols from /home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o... - done. - (UML gdb) p *module_list - $1 = {size_of_struct = 84, next = 0xa0178720, name = 0xa9022de0 "hostfs", - size = 9016, uc = {usecount = {counter = 0}, pad = 0}, flags = 1, - nsyms = 57, ndeps = 0, syms = 0xa9023170, deps = 0x0, refs = 0x0, - init = 0xa90221f0 <init_hostfs>, cleanup = 0xa902222c <exit_hostfs>, - ex_table_start = 0x0, ex_table_end = 0x0, persist_start = 0x0, - persist_end = 0x0, can_unload = 0, runsize = 0, kallsyms_start = 0x0, - kallsyms_end = 0x0, - archdata_start = 0x1b855 <Address 0x1b855 out of bounds>, - archdata_end = 0xe5890000 <Address 0xe5890000 out of bounds>, - kernel_data = 0xf689c35d <Address 0xf689c35d out of bounds>} - >> Finished loading symbols for hostfs ... + expect magic will kick in and you'll see something like:: + + + *** Module hostfs loaded *** + Breakpoint 1, sys_init_module (name_user=0x805abb0 "hostfs", + mod_user=0x8070e00) at module.c:349 + 349 char *name, *n_name, *name_tmp = NULL; + (UML gdb) finish + Run till exit from #0 sys_init_module (name_user=0x805abb0 "hostfs", + mod_user=0x8070e00) at module.c:349 + 0xa00e2e23 in execute_syscall (r=0xa8140284) at syscall_kern.c:411 + 411 else res = EXECUTE_SYSCALL(syscall, regs); + Value returned is $1 = 0 + (UML gdb) + p/x (int)module_list + module_list->size_of_struct + + $2 = 0xa9021054 + (UML gdb) symbol-file ./linux + Load new symbol table from "./linux"? (y or n) y + Reading symbols from ./linux... + done. + (UML gdb) + add-symbol-file /home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o 0xa9021054 + + add symbol table from file "/home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o" at + .text_addr = 0xa9021054 + (y or n) y + + Reading symbols from /home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o... + done. + (UML gdb) p *module_list + $1 = {size_of_struct = 84, next = 0xa0178720, name = 0xa9022de0 "hostfs", + size = 9016, uc = {usecount = {counter = 0}, pad = 0}, flags = 1, + nsyms = 57, ndeps = 0, syms = 0xa9023170, deps = 0x0, refs = 0x0, + init = 0xa90221f0 <init_hostfs>, cleanup = 0xa902222c <exit_hostfs>, + ex_table_start = 0x0, ex_table_end = 0x0, persist_start = 0x0, + persist_end = 0x0, can_unload = 0, runsize = 0, kallsyms_start = 0x0, + kallsyms_end = 0x0, + archdata_start = 0x1b855 <Address 0x1b855 out of bounds>, + archdata_end = 0xe5890000 <Address 0xe5890000 out of bounds>, + kernel_data = 0xf689c35d <Address 0xf689c35d out of bounds>} + >> Finished loading symbols for hostfs ... @@ -2744,7 +2657,7 @@ Boot the kernel under the debugger and load the module with insmod or - modprobe. With gdb, do: + modprobe. With gdb, do:: (UML gdb) p module_list @@ -2758,12 +2671,12 @@ the name fields until find the module you want to debug. Take the address of that structure, and add module.size_of_struct (which in 2.4.10 kernels is 96 (0x60)) to it. Gdb can make this hard addition - for you :-): + for you :-):: - (UML gdb) - printf "%#x\n", (int)module_list module_list->size_of_struct + (UML gdb) + printf "%#x\n", (int)module_list module_list->size_of_struct @@ -2771,7 +2684,7 @@ The offset from the module start occasionally changes (before 2.4.0, it was module.size_of_struct + 4), so it's a good idea to check the init and cleanup addresses once in a while, as describe below. Now - do: + do:: (UML gdb) @@ -2786,7 +2699,7 @@ If there's any doubt that you got the offset right, like breakpoints appear not to work, or they're appearing in the wrong place, you can check it by looking at the module structure. The init and cleanup - fields should look like: + fields should look like:: init = 0x588066b0 <init_hostfs>, cleanup = 0x588066c0 <exit_hostfs> @@ -2801,7 +2714,7 @@ When you want to load in a new version of the module, you need to get gdb to forget about the old one. The only way I've found to do that - is to tell gdb to forget about all symbols that it knows about: + is to tell gdb to forget about all symbols that it knows about:: (UML gdb) symbol-file @@ -2809,7 +2722,7 @@ - Then reload the symbols from the kernel binary: + Then reload the symbols from the kernel binary:: (UML gdb) symbol-file /path/to/kernel @@ -2823,17 +2736,19 @@ - 11.5. Attaching gdb to the kernel +11.5. Attaching gdb to the kernel +---------------------------------- If you don't have the kernel running under gdb, you can attach gdb to it later by sending the tracing thread a SIGUSR1. The first line of - the console output identifies its pid: + the console output identifies its pid:: + tracing thread pid = 20093 - When you send it the signal: + When you send it the signal:: host% kill -USR1 20093 @@ -2845,7 +2760,7 @@ If you have the mconsole compiled into UML, then the mconsole client - can be used to start gdb: + can be used to start gdb:: (mconsole) (mconsole) config gdb=xterm @@ -2857,7 +2772,8 @@ - 11.6. Using alternate debuggers +11.6. Using alternate debuggers +-------------------------------- UML has support for attaching to an already running debugger rather than starting gdb itself. This is present in CVS as of 17 Apr 2001. @@ -2886,7 +2802,7 @@ An example of an alternate debugger is strace. You can strace the actual kernel as follows: - o Run the following in a shell + - Run the following in a shell:: host% @@ -2894,13 +2810,13 @@ - o Run UML with 'debug' and 'gdb-pid=<pid>' with the pid printed out + - Run UML with 'debug' and 'gdb-pid=<pid>' with the pid printed out by the previous command - o Hit return in the shell, and UML will start running, and strace + - Hit return in the shell, and UML will start running, and strace output will start accumulating in the output file. - Note that this is different from running + Note that this is different from running:: host% strace ./linux @@ -2917,95 +2833,57 @@ - 12. Kernel debugging examples +12. Kernel debugging examples +============================== - 12.1. The case of the hung fsck +12.1. The case of the hung fsck +-------------------------------- When booting up the kernel, fsck failed, and dropped me into a shell - to fix things up. I ran fsck -y, which hung: - - - - - - - - - - - - - - - - - - - - - - - - - + to fix things up. I ran fsck -y, which hung:: + Setting hostname uml [ OK ] + Checking root filesystem + /dev/fhd0 was not cleanly unmounted, check forced. + Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780. + /dev/fhd0: UNEXPECTED INCONSISTENCY; RUN fsck MANUALLY. + (i.e., without -a or -p options) + [ FAILED ] + *** An error occurred during the file system check. + *** Dropping you to a shell; the system will reboot + *** when you leave the shell. + Give root password for maintenance + (or type Control-D for normal startup): + [root@uml /root]# fsck -y /dev/fhd0 + fsck -y /dev/fhd0 + Parallelizing fsck version 1.14 (9-Jan-1999) + e2fsck 1.14, 9-Jan-1999 for EXT2 FS 0.5b, 95/08/09 + /dev/fhd0 contains a file system with errors, check forced. + Pass 1: Checking inodes, blocks, and sizes + Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780. Ignore error? yes + Inode 19780, i_blocks is 1548, should be 540. Fix? yes + Pass 2: Checking directory structure + Error reading block 49405 (Attempt to read block from filesystem resulted in short read). Ignore error? yes + Directory inode 11858, block 0, offset 0: directory corrupted + Salvage? yes + Missing '.' in directory inode 11858. + Fix? yes - - - Setting hostname uml [ OK ] - Checking root filesystem - /dev/fhd0 was not cleanly unmounted, check forced. - Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780. - - /dev/fhd0: UNEXPECTED INCONSISTENCY; RUN fsck MANUALLY. - (i.e., without -a or -p options) - [ FAILED ] - - *** An error occurred during the file system check. - *** Dropping you to a shell; the system will reboot - *** when you leave the shell. - Give root password for maintenance - (or type Control-D for normal startup): - - [root@uml /root]# fsck -y /dev/fhd0 - fsck -y /dev/fhd0 - Parallelizing fsck version 1.14 (9-Jan-1999) - e2fsck 1.14, 9-Jan-1999 for EXT2 FS 0.5b, 95/08/09 - /dev/fhd0 contains a file system with errors, check forced. - Pass 1: Checking inodes, blocks, and sizes - Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780. Ignore error? yes - - Inode 19780, i_blocks is 1548, should be 540. Fix? yes - - Pass 2: Checking directory structure - Error reading block 49405 (Attempt to read block from filesystem resulted in short read). Ignore error? yes - - Directory inode 11858, block 0, offset 0: directory corrupted - Salvage? yes - - Missing '.' in directory inode 11858. - Fix? yes - - Missing '..' in directory inode 11858. - Fix? yes - - - + Missing '..' in directory inode 11858. + Fix? yes The standard drill in this sort of situation is to fire up gdb on the signal thread, which, in this case, was pid 1935. In another window, - I run gdb and attach pid 1935. - - + I run gdb and attach pid 1935:: ~/linux/2.3.26/um 1016: gdb linux @@ -3022,11 +2900,7 @@ 0x100756d9 in __wait4 () - - - - - Let's see what's currently running: + Let's see what's currently running:: @@ -3041,7 +2915,7 @@ reason and never woke up. - Let's guess that the last process in the process list is fsck: + Let's guess that the last process in the process list is fsck:: @@ -3052,7 +2926,7 @@ - It is, so let's see what it thinks it's up to: + It is, so let's see what it thinks it's up to:: @@ -3068,8 +2942,6 @@ - - The interesting things here are the fact that its .thread.syscall.id is __NR_write (see the big switch in arch/um/kernel/syscall_kern.c or the defines in include/asm-um/arch/unistd.h), and that it never @@ -3081,30 +2953,20 @@ The fact that it never returned from write means that its stack should be fairly interesting. Its pid is 1980 (.thread.extern_pid). That process is being ptraced by the signal thread, so it must be detached - before gdb can attach it: - - - - - - + before gdb can attach it:: + (gdb) call detach(1980) - (gdb) call detach(1980) - - Program received signal SIGSEGV, Segmentation fault. - <function called from gdb> - The program being debugged stopped while in a function called from GDB. - When the function (detach) is done executing, GDB will silently - stop (instead of continuing to evaluate the expression containing - the function call). - (gdb) call detach(1980) - $15 = 0 - - - + Program received signal SIGSEGV, Segmentation fault. + <function called from gdb> + The program being debugged stopped while in a function called from GDB. + When the function (detach) is done executing, GDB will silently + stop (instead of continuing to evaluate the expression containing + the function call). + (gdb) call detach(1980) + $15 = 0 The first detach segfaults for some reason, and the second one @@ -3112,7 +2974,7 @@ Now I detach from the signal thread, attach to the fsck thread, and - look at its stack: + look at its stack:: (gdb) det @@ -3152,14 +3014,14 @@ - The interesting things here are : + The interesting things here are: - o There are two segfaults on this stack (frames 9 and 14) + - There are two segfaults on this stack (frames 9 and 14) - o The first faulting address (frame 11) is 0x50000800 + - The first faulting address (frame 11) is 0x50000800:: - (gdb) p (void *)1342179328 - $16 = (void *) 0x50000800 + (gdb) p (void *)1342179328 + $16 = (void *) 0x50000800 @@ -3175,7 +3037,7 @@ However, the more immediate problem is that second segfault and I'm going to concentrate on that. First, I want to see where the fault - happened, so I have to go look at the sigcontent struct in frame 8: + happened, so I have to go look at the sigcontent struct in frame 8:: @@ -3211,7 +3073,7 @@ - That's not very useful, so I'll try a more manual method: + That's not very useful, so I'll try a more manual method:: (gdb) p *((struct sigcontext *) (&sig + 1)) @@ -3224,7 +3086,7 @@ - The ip is in handle_mm_fault: + The ip is in handle_mm_fault:: (gdb) p (void *)268480945 @@ -3236,7 +3098,7 @@ - Specifically, it's in pte_alloc: + Specifically, it's in pte_alloc:: (gdb) i line *$20 @@ -3249,7 +3111,7 @@ To find where in handle_mm_fault this is, I'll jump forward in the - code until I see an address in that procedure: + code until I see an address in that procedure:: @@ -3286,21 +3148,21 @@ Something is apparently wrong with the page tables or vma_structs, so - lets go back to frame 11 and have a look at them: + lets go back to frame 11 and have a look at them:: - #11 0x1006c0aa in segv (address=1342179328, is_write=2) at trap_kern.c:50 - 50 handle_mm_fault(current, vma, address, is_write); - (gdb) call pgd_offset_proc(vma->vm_mm, address) - $22 = (pgd_t *) 0x80a548c + #11 0x1006c0aa in segv (address=1342179328, is_write=2) at trap_kern.c:50 + 50 handle_mm_fault(current, vma, address, is_write); + (gdb) call pgd_offset_proc(vma->vm_mm, address) + $22 = (pgd_t *) 0x80a548c That's pretty bogus. Page tables aren't supposed to be in process - text or data areas. Let's see what's in the vma: + text or data areas. Let's see what's in the vma:: (gdb) p *vma @@ -3325,12 +3187,9 @@ - - This also pretty bogus. With all of the 0x80xxxxx and 0xaffffxxx addresses, this is looking like a stack was plonked down on top of - these structures. Maybe it's a stack overflow from the next page: - + these structures. Maybe it's a stack overflow from the next page:: (gdb) p vma @@ -3338,52 +3197,36 @@ - - That's towards the lower quarter of the page, so that would have to - have been pretty heavy stack overflow: - - - - - - - - - - - - - - - (gdb) x/100x $25 - 0x507d2434: 0x507d2434 0x00000000 0x08048000 0x080a4f8c - 0x507d2444: 0x00000000 0x080a79e0 0x080a8c94 0x080d1000 - 0x507d2454: 0xaffffdb0 0xaffffe63 0xaffffe7a 0xaffffe7a - 0x507d2464: 0xafffffec 0x00000062 0x0000008a 0x00000000 - 0x507d2474: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d2484: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d2494: 0x00000000 0x00000000 0x507d2fe0 0x00000000 - 0x507d24a4: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d24b4: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d24c4: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d24d4: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d24e4: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d24f4: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d2504: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d2514: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d2524: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d2534: 0x00000000 0x00000000 0x507d25dc 0x00000000 - 0x507d2544: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d2554: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d2564: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d2574: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d2584: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d2594: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d25a4: 0x00000000 0x00000000 0x00000000 0x00000000 - 0x507d25b4: 0x00000000 0x00000000 0x00000000 0x00000000 - - + have been pretty heavy stack overflow:: + + + (gdb) x/100x $25 + 0x507d2434: 0x507d2434 0x00000000 0x08048000 0x080a4f8c + 0x507d2444: 0x00000000 0x080a79e0 0x080a8c94 0x080d1000 + 0x507d2454: 0xaffffdb0 0xaffffe63 0xaffffe7a 0xaffffe7a + 0x507d2464: 0xafffffec 0x00000062 0x0000008a 0x00000000 + 0x507d2474: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d2484: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d2494: 0x00000000 0x00000000 0x507d2fe0 0x00000000 + 0x507d24a4: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d24b4: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d24c4: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d24d4: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d24e4: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d24f4: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d2504: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d2514: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d2524: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d2534: 0x00000000 0x00000000 0x507d25dc 0x00000000 + 0x507d2544: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d2554: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d2564: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d2574: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d2584: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d2594: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d25a4: 0x00000000 0x00000000 0x00000000 0x00000000 + 0x507d25b4: 0x00000000 0x00000000 0x00000000 0x00000000 @@ -3399,65 +3242,53 @@ on will be somewhat clearer. - 12.2. Episode 2: The case of the hung fsck +12.2. Episode 2: The case of the hung fsck +------------------------------------------- After setting a trap in the SEGV handler for accesses to the signal thread's stack, I reran the kernel. - fsck hung again, this time by hitting the trap: - - + fsck hung again, this time by hitting the trap:: + Setting hostname uml [ OK ] + Checking root filesystem + /dev/fhd0 contains a file system with errors, check forced. + Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780. + /dev/fhd0: UNEXPECTED INCONSISTENCY; RUN fsck MANUALLY. + (i.e., without -a or -p options) + [ FAILED ] + *** An error occurred during the file system check. + *** Dropping you to a shell; the system will reboot + *** when you leave the shell. + Give root password for maintenance + (or type Control-D for normal startup): + [root@uml /root]# fsck -y /dev/fhd0 + fsck -y /dev/fhd0 + Parallelizing fsck version 1.14 (9-Jan-1999) + e2fsck 1.14, 9-Jan-1999 for EXT2 FS 0.5b, 95/08/09 + /dev/fhd0 contains a file system with errors, check forced. + Pass 1: Checking inodes, blocks, and sizes + Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780. Ignore error? yes + Pass 2: Checking directory structure + Error reading block 49405 (Attempt to read block from filesystem resulted in short read). Ignore error? yes + Directory inode 11858, block 0, offset 0: directory corrupted + Salvage? yes + Missing '.' in directory inode 11858. + Fix? yes + Missing '..' in directory inode 11858. + Fix? yes - - - - Setting hostname uml [ OK ] - Checking root filesystem - /dev/fhd0 contains a file system with errors, check forced. - Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780. - - /dev/fhd0: UNEXPECTED INCONSISTENCY; RUN fsck MANUALLY. - (i.e., without -a or -p options) - [ FAILED ] - - *** An error occurred during the file system check. - *** Dropping you to a shell; the system will reboot - *** when you leave the shell. - Give root password for maintenance - (or type Control-D for normal startup): - - [root@uml /root]# fsck -y /dev/fhd0 - fsck -y /dev/fhd0 - Parallelizing fsck version 1.14 (9-Jan-1999) - e2fsck 1.14, 9-Jan-1999 for EXT2 FS 0.5b, 95/08/09 - /dev/fhd0 contains a file system with errors, check forced. - Pass 1: Checking inodes, blocks, and sizes - Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780. Ignore error? yes - - Pass 2: Checking directory structure - Error reading block 49405 (Attempt to read block from filesystem resulted in short read). Ignore error? yes - - Directory inode 11858, block 0, offset 0: directory corrupted - Salvage? yes - - Missing '.' in directory inode 11858. - Fix? yes - - Missing '..' in directory inode 11858. - Fix? yes - - Untested (4127) [100fe44c]: trap_kern.c line 31 + Untested (4127) [100fe44c]: trap_kern.c line 31 @@ -3465,7 +3296,7 @@ I need to get the signal thread to detach from pid 4127 so that I can attach to it with gdb. This is done by sending it a SIGUSR1, which is - caught by the signal thread, which detaches the process: + caught by the signal thread, which detaches the process:: kill -USR1 4127 @@ -3474,31 +3305,20 @@ - Now I can run gdb on it: - - - - - - - + Now I can run gdb on it:: - - - - - ~/linux/2.3.26/um 1034: gdb linux - GNU gdb 4.17.0.11 with Linux support - Copyright 1998 Free Software Foundation, Inc. - GDB is free software, covered by the GNU General Public License, and you are - welcome to change it and/or distribute copies of it under certain conditions. - Type "show copying" to see the conditions. - There is absolutely no warranty for GDB. Type "show warranty" for details. - This GDB was configured as "i386-redhat-linux"... - (gdb) att 4127 - Attaching to program `/home/dike/linux/2.3.26/um/linux', Pid 4127 - 0x10075891 in __libc_nanosleep () + ~/linux/2.3.26/um 1034: gdb linux + GNU gdb 4.17.0.11 with Linux support + Copyright 1998 Free Software Foundation, Inc. + GDB is free software, covered by the GNU General Public License, and you are + welcome to change it and/or distribute copies of it under certain conditions. + Type "show copying" to see the conditions. + There is absolutely no warranty for GDB. Type "show warranty" for details. + This GDB was configured as "i386-redhat-linux"... + (gdb) att 4127 + Attaching to program `/home/dike/linux/2.3.26/um/linux', Pid 4127 + 0x10075891 in __libc_nanosleep () @@ -3506,7 +3326,7 @@ The backtrace shows that it was in a write and that the fault address (address in frame 3) is 0x50000800, which is right in the middle of - the signal thread's stack page: + the signal thread's stack page:: (gdb) bt @@ -3540,58 +3360,48 @@ - - Going up the stack to the segv_handler frame and looking at where in the code the access happened shows that it happened near line 110 of - block_dev.c: - - - - - - - - - - (gdb) up - #1 0x1007584d in __sleep (seconds=1000000) - at ../sysdeps/unix/sysv/linux/sleep.c:78 - ../sysdeps/unix/sysv/linux/sleep.c:78: No such file or directory. - (gdb) - #2 0x1006ce9a in stop () at user_util.c:191 - 191 while(1) sleep(1000000); - (gdb) - #3 0x1006bf88 in segv (address=1342179328, is_write=2) at trap_kern.c:31 - 31 KERN_UNTESTED(); - (gdb) - #4 0x1006c628 in segv_handler (sc=0x5006eaf8) at trap_user.c:174 - 174 segv(sc->cr2, sc->err & 2); - (gdb) p *sc - $1 = {gs = 0, __gsh = 0, fs = 0, __fsh = 0, es = 43, __esh = 0, ds = 43, - __dsh = 0, edi = 1342179328, esi = 134973440, ebp = 1342631484, - esp = 1342630864, ebx = 256, edx = 0, ecx = 256, eax = 1024, trapno = 14, - err = 6, eip = 268550834, cs = 35, __csh = 0, eflags = 66070, - esp_at_signal = 1342630864, ss = 43, __ssh = 0, fpstate = 0x0, oldmask = 0, - cr2 = 1342179328} - (gdb) p (void *)268550834 - $2 = (void *) 0x1001c2b2 - (gdb) i sym $2 - block_write + 1090 in section .text - (gdb) i line *$2 - Line 209 of "/home/dike/linux/2.3.26/um/include/asm/arch/string.h" - starts at address 0x1001c2a1 <block_write+1073> - and ends at 0x1001c2bf <block_write+1103>. - (gdb) i line *0x1001c2c0 - Line 110 of "block_dev.c" starts at address 0x1001c2bf <block_write+1103> - and ends at 0x1001c2e3 <block_write+1139>. - - + block_dev.c:: + + + + (gdb) up + #1 0x1007584d in __sleep (seconds=1000000) + at ../sysdeps/unix/sysv/linux/sleep.c:78 + ../sysdeps/unix/sysv/linux/sleep.c:78: No such file or directory. + (gdb) + #2 0x1006ce9a in stop () at user_util.c:191 + 191 while(1) sleep(1000000); + (gdb) + #3 0x1006bf88 in segv (address=1342179328, is_write=2) at trap_kern.c:31 + 31 KERN_UNTESTED(); + (gdb) + #4 0x1006c628 in segv_handler (sc=0x5006eaf8) at trap_user.c:174 + 174 segv(sc->cr2, sc->err & 2); + (gdb) p *sc + $1 = {gs = 0, __gsh = 0, fs = 0, __fsh = 0, es = 43, __esh = 0, ds = 43, + __dsh = 0, edi = 1342179328, esi = 134973440, ebp = 1342631484, + esp = 1342630864, ebx = 256, edx = 0, ecx = 256, eax = 1024, trapno = 14, + err = 6, eip = 268550834, cs = 35, __csh = 0, eflags = 66070, + esp_at_signal = 1342630864, ss = 43, __ssh = 0, fpstate = 0x0, oldmask = 0, + cr2 = 1342179328} + (gdb) p (void *)268550834 + $2 = (void *) 0x1001c2b2 + (gdb) i sym $2 + block_write + 1090 in section .text + (gdb) i line *$2 + Line 209 of "/home/dike/linux/2.3.26/um/include/asm/arch/string.h" + starts at address 0x1001c2a1 <block_write+1073> + and ends at 0x1001c2bf <block_write+1103>. + (gdb) i line *0x1001c2c0 + Line 110 of "block_dev.c" starts at address 0x1001c2bf <block_write+1103> + and ends at 0x1001c2e3 <block_write+1139>. Looking at the source shows that the fault happened during a call to - copy_from_user to copy the data into the kernel: + copy_from_user to copy the data into the kernel:: 107 count -= chars; @@ -3601,10 +3411,8 @@ - - p is the pointer which must contain 0x50000800, since buf contains - 0x80b8800 (frame 8 above). It is defined as: + 0x80b8800 (frame 8 above). It is defined as:: p = offset + bh->b_data; @@ -3615,24 +3423,22 @@ I need to figure out what bh is, and it just so happens that bh is passed as an argument to mark_buffer_uptodate and mark_buffer_dirty a - few lines later, so I do a little disassembly: - - + few lines later, so I do a little disassembly:: - (gdb) disas 0x1001c2bf 0x1001c2e0 - Dump of assembler code from 0x1001c2bf to 0x1001c2d0: - 0x1001c2bf <block_write+1103>: addl %eax,0xc(%ebp) - 0x1001c2c2 <block_write+1106>: movl 0xfffffdd4(%ebp),%edx - 0x1001c2c8 <block_write+1112>: btsl $0x0,0x18(%edx) - 0x1001c2cd <block_write+1117>: btsl $0x1,0x18(%edx) - 0x1001c2d2 <block_write+1122>: sbbl %ecx,%ecx - 0x1001c2d4 <block_write+1124>: testl %ecx,%ecx - 0x1001c2d6 <block_write+1126>: jne 0x1001c2e3 <block_write+1139> - 0x1001c2d8 <block_write+1128>: pushl $0x0 - 0x1001c2da <block_write+1130>: pushl %edx - 0x1001c2db <block_write+1131>: call 0x1001819c <__mark_buffer_dirty> - End of assembler dump. + (gdb) disas 0x1001c2bf 0x1001c2e0 + Dump of assembler code from 0x1001c2bf to 0x1001c2d0: + 0x1001c2bf <block_write+1103>: addl %eax,0xc(%ebp) + 0x1001c2c2 <block_write+1106>: movl 0xfffffdd4(%ebp),%edx + 0x1001c2c8 <block_write+1112>: btsl $0x0,0x18(%edx) + 0x1001c2cd <block_write+1117>: btsl $0x1,0x18(%edx) + 0x1001c2d2 <block_write+1122>: sbbl %ecx,%ecx + 0x1001c2d4 <block_write+1124>: testl %ecx,%ecx + 0x1001c2d6 <block_write+1126>: jne 0x1001c2e3 <block_write+1139> + 0x1001c2d8 <block_write+1128>: pushl $0x0 + 0x1001c2da <block_write+1130>: pushl %edx + 0x1001c2db <block_write+1131>: call 0x1001819c <__mark_buffer_dirty> + End of assembler dump. @@ -3640,7 +3446,7 @@ At that point, bh is in %edx (address 0x1001c2da), which is calculated at 0x1001c2c2 as %ebp + 0xfffffdd4, so I figure exactly what that is, - taking %ebp from the sigcontext_struct above: + taking %ebp from the sigcontext_struct above:: (gdb) p (void *)1342631484 @@ -3657,7 +3463,7 @@ Now, I look at the structure to see what's in it, and particularly, - what its b_data field contains: + what its b_data field contains:: (gdb) p *((struct buffer_head *)0x50100200) @@ -3682,18 +3488,18 @@ The b_page field is a pointer to the page_struct representing the 0x50000000 page. Looking at it shows the kernel's idea of the state - of that page: + of that page:: - (gdb) p *$13.b_page - $17 = {list = {next = 0x50004a5c, prev = 0x100c5174}, mapping = 0x0, - index = 0, next_hash = 0x0, count = {counter = 1}, flags = 132, lru = { - next = 0x50008460, prev = 0x50019350}, wait = { - lock = <optimized out or zero length>, task_list = {next = 0x50004024, - prev = 0x50004024}, __magic = 1342193708, __creator = 0}, - pprev_hash = 0x0, buffers = 0x501002c0, virtual = 1342177280, - zone = 0x100c5160} + (gdb) p *$13.b_page + $17 = {list = {next = 0x50004a5c, prev = 0x100c5174}, mapping = 0x0, + index = 0, next_hash = 0x0, count = {counter = 1}, flags = 132, lru = { + next = 0x50008460, prev = 0x50019350}, wait = { + lock = <optimized out or zero length>, task_list = {next = 0x50004024, + prev = 0x50004024}, __magic = 1342193708, __creator = 0}, + pprev_hash = 0x0, buffers = 0x501002c0, virtual = 1342177280, + zone = 0x100c5160} @@ -3702,7 +3508,7 @@ Some sanity-checking: the virtual field shows the "virtual" address of this page, which in this kernel is the same as its "physical" address, and the page_struct itself should be mem_map[0], since it represents - the first page of memory: + the first page of memory:: @@ -3719,7 +3525,7 @@ Now to check out the page_struct itself. In particular, the flags - field shows whether the page is considered free or not: + field shows whether the page is considered free or not:: (gdb) p (void *)132 @@ -3739,7 +3545,7 @@ In my setup_arch procedure, I have the following code which looks just - fine: + fine:: @@ -3762,7 +3568,7 @@ Stepping into init_bootmem, and looking at bootmem_map before looking - at what it contains shows the following: + at what it contains shows the following:: @@ -3788,18 +3594,20 @@ - 13. What to do when UML doesn't work +13. What to do when UML doesn't work +===================================== - 13.1. Strange compilation errors when you build from source +13.1. Strange compilation errors when you build from source +------------------------------------------------------------ As of test11, it is necessary to have "ARCH=um" in the environment or on the make command line for all steps in building UML, including clean, distclean, or mrproper, config, menuconfig, or xconfig, dep, and linux. If you forget for any of them, the i386 build seems to - contaminate the UML build. If this happens, start from scratch with + contaminate the UML build. If this happens, start from scratch with:: host% @@ -3811,7 +3619,7 @@ and repeat the build process with ARCH=um on all the steps. - See ``Compiling the kernel and modules'' for more details. + See :ref:`Compiling_the_kernel_and_modules` for more details. Another cause of strange compilation errors is building UML in @@ -3824,11 +3632,11 @@ - 13.3. A variety of panics and hangs with /tmp on a reiserfs filesys- - tem +13.3. A variety of panics and hangs with /tmp on a reiserfs filesystem +----------------------------------------------------------------------- I saw this on reiserfs 3.5.21 and it seems to be fixed in 3.5.27. - Panics preceded by + Panics preceded by:: Detaching pid nnnn @@ -3854,17 +3662,19 @@ - 13.5. UML doesn't work when /tmp is an NFS filesystem +13.5. UML doesn't work when /tmp is an NFS filesystem +------------------------------------------------------ This seems to be a similar situation with the ReiserFS problem above. Some versions of NFS seems not to handle mmap correctly, which UML depends on. The workaround is have /tmp be a non-NFS directory. - 13.6. UML hangs on boot when compiled with gprof support +13.6. UML hangs on boot when compiled with gprof support +--------------------------------------------------------- If you build UML with gprof support and, early in the boot, it does - this + this:: kernel BUG at page_alloc.c:100! @@ -3878,10 +3688,11 @@ - 13.7. syslogd dies with a SIGTERM on startup +13.7. syslogd dies with a SIGTERM on startup +--------------------------------------------- The exact boot error depends on the distribution that you're booting, - but Debian produces this: + but Debian produces this:: /etc/rc2.d/S10sysklogd: line 49: 93 Terminated @@ -3891,23 +3702,21 @@ This is a syslogd bug. There's a race between a parent process - installing a signal handler and its child sending the signal. See - this uml-devel post <http://www.geocrawler.com/lists/3/Source- - Forge/709/0/6612801> for the details. + installing a signal handler and its child sending the signal. - 13.8. TUN/TAP networking doesn't work on a 2.4 host +13.8. TUN/TAP networking doesn't work on a 2.4 host +---------------------------------------------------- - There are a couple of problems which were - <http://www.geocrawler.com/lists/3/SourceForge/597/0/> name="pointed - out"> by Tim Robinson <timro at trkr dot net> + There are a couple of problems which were reported by + Tim Robinson <timro at trkr dot net> - o It doesn't work on hosts running 2.4.7 (or thereabouts) or earlier. + - It doesn't work on hosts running 2.4.7 (or thereabouts) or earlier. The fix is to upgrade to something more recent and then read the next item. - o If you see + - If you see:: File descriptor in bad state @@ -3921,8 +3730,8 @@ - 13.9. You can network to the host but not to other machines on the - net +13.9. You can network to the host but not to other machines on the net +======================================================================= If you can connect to the host, and the host can connect to UML, but you cannot connect to any other machines, then you may need to enable @@ -3930,7 +3739,7 @@ using private IP addresses (192.168.x.x or 10.x.x.x) for host/UML networking, rather than the public address space that your host is connected to. UML does not enable IP Masquerading, so you will need - to create a static rule to enable it: + to create a static rule to enable it:: host% @@ -3944,11 +3753,11 @@ Documentation on IP Masquerading, and SNAT, can be found at - www.netfilter.org <http://www.netfilter.org> . + http://www.netfilter.org. If you can reach the local net, but not the outside Internet, then - that is usually a routing problem. The UML needs a default route: + that is usually a routing problem. The UML needs a default route:: UML# @@ -3972,7 +3781,8 @@ - 13.10. I have no root and I want to scream +13.10. I have no root and I want to scream +=========================================== Thanks to Birgit Wahlich for telling me about this strange one. It turns out that there's a limit of six environment variables on the @@ -3987,14 +3797,16 @@ - 13.11. UML build conflict between ptrace.h and ucontext.h +13.11. UML build conflict between ptrace.h and ucontext.h +========================================================== On some older systems, /usr/include/asm/ptrace.h and /usr/include/sys/ucontext.h define the same names. So, when they're included together, the defines from one completely mess up the parsing - of the other, producing errors like: + of the other, producing errors like:: + /usr/include/sys/ucontext.h:47: parse error before - `10' + `10` @@ -4007,7 +3819,8 @@ - 13.12. The UML BogoMips is exactly half the host's BogoMips +13.12. The UML BogoMips is exactly half the host's BogoMips +------------------------------------------------------------ On i386 kernels, there are two ways of running the loop that is used to calculate the BogoMips rating, using the TSC if it's there or using @@ -4019,15 +3832,17 @@ - 13.13. When you run UML, it immediately segfaults +13.13. When you run UML, it immediately segfaults +-------------------------------------------------- If the host is configured with the 2G/2G address space split, that's - why. See ``UML on 2G/2G hosts'' for the details on getting UML to + why. See ref:`UML_on_2G/2G_hosts` for the details on getting UML to run on your host. - 13.14. xterms appear, then immediately disappear +13.14. xterms appear, then immediately disappear +------------------------------------------------- If you're running an up to date kernel with an old release of uml_utilities, the port-helper program will not work properly, so @@ -4039,7 +3854,8 @@ - 13.15. Any other panic, hang, or strange behavior +13.15. Any other panic, hang, or strange behavior +-------------------------------------------------- If you're seeing truly strange behavior, such as hangs or panics that happen in random places, or you try running the debugger to see what's @@ -4057,9 +3873,13 @@ it and that a fix is imminent. - If you want to be super-helpful, read ``Diagnosing Problems'' and + If you want to be super-helpful, read :ref:`Diagnosing_Problems` and follow the instructions contained therein. - 14. Diagnosing Problems + +.. _Diagnosing_Problems: + +14. Diagnosing Problems +======================== If you get UML to crash, hang, or otherwise misbehave, you should @@ -4074,21 +3894,22 @@ For any diagnosis, you're going to need to build a debugging kernel. The binaries from this site aren't debuggable. If you haven't done - this before, read about ``Compiling the kernel and modules'' and - ``Kernel debugging'' UML first. + this before, read about :ref:`Compiling_the_kernel_and_modules` and + :ref:`Kernel_debugging` UML first. - 14.1. Case 1 : Normal kernel panics +14.1. Case 1 : Normal kernel panics +------------------------------------ The most common case is for a normal thread to panic. To debug this, you will need to run it under the debugger (add 'debug' to the command line). An xterm will start up with gdb running inside it. Continue - it when it stops in start_kernel and make it crash. Now ^C gdb and + it when it stops in start_kernel and make it crash. Now ``^C gdb`` and If the panic was a "Kernel mode fault", then there will be a segv frame on the stack and I'm going to want some more information. The - stack might look something like this: + stack might look something like this:: (UML gdb) backtrace @@ -4107,7 +3928,7 @@ I'm going to want to see the symbol and line information for the value - of ip in the segv frame. In this case, you would do the following: + of ip in the segv frame. In this case, you would do the following:: (UML gdb) i sym 268849158 @@ -4115,7 +3936,7 @@ - and + and:: (UML gdb) i line *268849158 @@ -4128,7 +3949,8 @@ to get that information from the faulting ip. - 14.2. Case 2 : Tracing thread panics +14.2. Case 2 : Tracing thread panics +------------------------------------- The less common and more painful case is when the tracing thread panics. In this case, the kernel debugger will be useless because it @@ -4136,7 +3958,7 @@ do is get a backtrace from the tracing thread. This is done by figuring out what its pid is, firing up gdb, and attaching it to that pid. You can figure out the tracing thread pid by looking at the - first line of the console output, which will look like this: + first line of the console output, which will look like this:: tracing thread pid = 15851 @@ -4145,7 +3967,7 @@ or by running ps on the host and finding the line that looks like - this: + this:: jdike 15851 4.5 0.4 132568 1104 pts/0 S 21:34 0:05 ./linux [(tracing thread)] @@ -4164,7 +3986,7 @@ 14.3. Case 3 : Tracing thread panics caused by other threads However, there are cases where the misbehavior of another thread - caused the problem. The most common panic of this type is: + caused the problem. The most common panic of this type is:: wait_for_stop failed to wait for <pid> to stop with <signal number> @@ -4177,7 +3999,7 @@ debugger is defunct and without some fancy footwork, another gdb can't attach to it. So, this is how the fancy footwork goes: - In a shell: + In a shell:: host% kill -STOP pid @@ -4185,7 +4007,7 @@ - Run gdb on the tracing thread as described in case 2 and do: + Run gdb on the tracing thread as described in case 2 and do:: (host gdb) call detach(pid) @@ -4193,7 +4015,7 @@ If you get a segfault, do it again. It always works the second time. - Detach from the tracing thread and attach to that other thread: + Detach from the tracing thread and attach to that other thread:: (host gdb) detach @@ -4209,7 +4031,7 @@ If gdb hangs when attaching to that process, go back to a shell and - do: + do:: host% @@ -4218,7 +4040,7 @@ - And then get the backtrace: + And then get the backtrace:: (host gdb) backtrace @@ -4227,13 +4049,14 @@ - 14.4. Case 4 : Hangs +14.4. Case 4 : Hangs +--------------------- Hangs seem to be fairly rare, but they sometimes happen. When a hang happens, we need a backtrace from the offending process. Run the kernel debugger as described in case 1 and get a backtrace. If the current process is not the idle thread, then send in the backtrace. - You can tell that it's the idle thread if the stack looks like this: + You can tell that it's the idle thread if the stack looks like this:: #0 0x100b1401 in __libc_nanosleep () @@ -4257,7 +4080,8 @@ - 15. Thanks +15. Thanks +=========== A number of people have helped this project in various ways, and this @@ -4274,20 +4098,21 @@ bookkeeping lapses and I forget about contributions. - 15.1. Code and Documentation +15.1. Code and Documentation +----------------------------- Rusty Russell <rusty at linuxcare.com.au> - - o wrote the HOWTO <http://user-mode- - linux.sourceforge.net/UserModeLinux-HOWTO.html> + - wrote the HOWTO + http://user-mode-linux.sourceforge.net/old/UserModeLinux-HOWTO.html - o prodded me into making this project official and putting it on + - prodded me into making this project official and putting it on SourceForge - o came up with the way cool UML logo <http://user-mode- - linux.sourceforge.net/uml-small.png> + - came up with the way cool UML logo + http://user-mode-linux.sourceforge.net/uml-small.png - o redid the config process + - redid the config process Peter Moulder <reiter at netspace.net.au> - Fixed my config and build @@ -4296,34 +4121,32 @@ Bill Stearns <wstearns at pobox.com> - - o HOWTO updates + - HOWTO updates - o lots of bug reports + - lots of bug reports - o lots of testing + - lots of testing - o dedicated a box (uml.ists.dartmouth.edu) to support UML development + - dedicated a box (uml.ists.dartmouth.edu) to support UML development - o wrote the mkrootfs script, which allows bootable filesystems of + - wrote the mkrootfs script, which allows bootable filesystems of RPM-based distributions to be cranked out - o cranked out a large number of filesystems with said script + - cranked out a large number of filesystems with said script Jim Leu <jleu at mindspring.com> - Wrote the virtual ethernet driver and associated usermode tools - Lars Brinkhoff <http://lars.nocrew.org/> - Contributed the ptrace - proxy from his own project <http://a386.nocrew.org/> to allow easier - kernel debugging + Lars Brinkhoff http://lars.nocrew.org/ - Contributed the ptrace + proxy from his own project to allow easier kernel debugging Andrea Arcangeli <andrea at suse.de> - Redid some of the early boot code so that it would work on machines with Large File Support - Chris Emerson <http://www.chiark.greenend.org.uk/~cemerson/> - Did - the first UML port to Linux/ppc + Chris Emerson - Did the first UML port to Linux/ppc Harald Welte <laforge at gnumonks.org> - Wrote the multicast @@ -4338,7 +4161,7 @@ wrote the iomem emulation support - Henrik Nordstrom <http://hem.passagen.se/hno/> - Provided a variety + Henrik Nordstrom http://hem.passagen.se/hno/ - Provided a variety of patches, fixes, and clues @@ -4373,190 +4196,193 @@ submitted patches for the slip transport and lots of other things. - David Coulson <http://davidcoulson.net> - + David Coulson http://davidcoulson.net - - o Set up the usermodelinux.org <http://usermodelinux.org> site, + - Set up the http://usermodelinux.org site, which is a great way of keeping the UML user community on top of UML goings-on. - o Site documentation and updates + - Site documentation and updates - o Nifty little UML management daemon UMLd - <http://uml.openconsultancy.com/umld/> + - Nifty little UML management daemon UMLd - o Lots of testing and bug reports + - Lots of testing and bug reports - 15.2. Flushing out bugs +15.2. Flushing out bugs +------------------------ - o Yuri Pudgorodsky + - Yuri Pudgorodsky - o Gerald Britton + - Gerald Britton - o Ian Wehrman + - Ian Wehrman - o Gord Lamb + - Gord Lamb - o Eugene Koontz + - Eugene Koontz - o John H. Hartman + - John H. Hartman - o Anders Karlsson + - Anders Karlsson - o Daniel Phillips + - Daniel Phillips - o John Fremlin + - John Fremlin - o Rainer Burgstaller + - Rainer Burgstaller - o James Stevenson + - James Stevenson - o Matt Clay + - Matt Clay - o Cliff Jefferies + - Cliff Jefferies - o Geoff Hoff + - Geoff Hoff - o Lennert Buytenhek + - Lennert Buytenhek - o Al Viro + - Al Viro - o Frank Klingenhoefer + - Frank Klingenhoefer - o Livio Baldini Soares + - Livio Baldini Soares - o Jon Burgess + - Jon Burgess - o Petru Paler + - Petru Paler - o Paul + - Paul - o Chris Reahard + - Chris Reahard - o Sverker Nilsson + - Sverker Nilsson - o Gong Su + - Gong Su - o johan verrept + - johan verrept - o Bjorn Eriksson + - Bjorn Eriksson - o Lorenzo Allegrucci + - Lorenzo Allegrucci - o Muli Ben-Yehuda + - Muli Ben-Yehuda - o David Mansfield + - David Mansfield - o Howard Goff + - Howard Goff - o Mike Anderson + - Mike Anderson - o John Byrne + - John Byrne - o Sapan J. Batia + - Sapan J. Batia - o Iris Huang + - Iris Huang - o Jan Hudec + - Jan Hudec - o Voluspa + - Voluspa - 15.3. Buglets and clean-ups +15.3. Buglets and clean-ups +---------------------------- - o Dave Zarzycki + - Dave Zarzycki - o Adam Lazur + - Adam Lazur - o Boria Feigin + - Boria Feigin - o Brian J. Murrell + - Brian J. Murrell - o JS + - JS - o Roman Zippel + - Roman Zippel - o Wil Cooley + - Wil Cooley - o Ayelet Shemesh + - Ayelet Shemesh - o Will Dyson + - Will Dyson - o Sverker Nilsson + - Sverker Nilsson - o dvorak + - dvorak - o v.naga srinivas + - v.naga srinivas - o Shlomi Fish + - Shlomi Fish - o Roger Binns + - Roger Binns - o johan verrept + - johan verrept - o MrChuoi + - MrChuoi - o Peter Cleve + - Peter Cleve - o Vincent Guffens + - Vincent Guffens - o Nathan Scott + - Nathan Scott - o Patrick Caulfield + - Patrick Caulfield - o jbearce + - jbearce - o Catalin Marinas + - Catalin Marinas - o Shane Spencer + - Shane Spencer - o Zou Min + - Zou Min - o Ryan Boder + - Ryan Boder - o Lorenzo Colitti + - Lorenzo Colitti - o Gwendal Grignou + - Gwendal Grignou - o Andre' Breiler + - Andre' Breiler - o Tsutomu Yasuda + - Tsutomu Yasuda - 15.4. Case Studies +15.4. Case Studies +------------------- - o Jon Wright + - Jon Wright - o William McEwan + - William McEwan - o Michael Richardson + - Michael Richardson - 15.5. Other contributions +15.5. Other contributions +-------------------------- Bill Carr <Bill.Carr at compaq.com> made the Red Hat mkrootfs script work with RH 6.2. Michael Jennings <mikejen at hevanet.com> sent in some material which - is now gracing the top of the index page <http://user-mode- - linux.sourceforge.net/> of this site. + is now gracing the top of the index page + http://user-mode-linux.sourceforge.net/ of this site. - SGI <http://www.sgi.com> (and more specifically Ralf Baechle <ralf at - uni-koblenz.de> ) gave me an account on oss.sgi.com - <http://www.oss.sgi.com> . The bandwidth there made it possible to + SGI (and more specifically Ralf Baechle <ralf at + uni-koblenz.de> ) gave me an account on oss.sgi.com. + The bandwidth there made it possible to produce most of the filesystems available on the project download page. @@ -4573,17 +4399,5 @@ Chris Reahard built a specialized root filesystem for running a DNS server jailed inside UML. It's available from the download - <http://user-mode-linux.sourceforge.net/dl-sf.html> page in the Jail + http://user-mode-linux.sourceforge.net/old/dl-sf.html page in the Jail Filesystems section. - - - - - - - - - - - - diff --git a/MAINTAINERS b/MAINTAINERS index a0d86490c2c6..2af5fa73155e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3909,7 +3909,7 @@ S: Supported F: Documentation/filesystems/ceph.txt F: fs/ceph/ -CERTIFICATE HANDLING: +CERTIFICATE HANDLING M: David Howells <dhowells@redhat.com> M: David Woodhouse <dwmw2@infradead.org> L: keyrings@vger.kernel.org @@ -3919,7 +3919,7 @@ F: certs/ F: scripts/sign-file.c F: scripts/extract-cert.c -CERTIFIED WIRELESS USB (WUSB) SUBSYSTEM: +CERTIFIED WIRELESS USB (WUSB) SUBSYSTEM L: devel@driverdev.osuosl.org S: Obsolete F: drivers/staging/wusbcore/ @@ -5932,12 +5932,12 @@ S: Maintained F: drivers/media/dvb-frontends/ec100* ECRYPT FILE SYSTEM -M: Tyler Hicks <tyhicks@canonical.com> +M: Tyler Hicks <code@tyhicks.com> L: ecryptfs@vger.kernel.org W: http://ecryptfs.org W: https://launchpad.net/ecryptfs T: git git://git.kernel.org/pub/scm/linux/kernel/git/tyhicks/ecryptfs.git -S: Supported +S: Odd Fixes F: Documentation/filesystems/ecryptfs.txt F: fs/ecryptfs/ @@ -7047,7 +7047,7 @@ L: kvm@vger.kernel.org S: Supported F: drivers/uio/uio_pci_generic.c -GENERIC VDSO LIBRARY: +GENERIC VDSO LIBRARY M: Andy Lutomirski <luto@kernel.org> M: Thomas Gleixner <tglx@linutronix.de> M: Vincenzo Frascino <vincenzo.frascino@arm.com> @@ -8392,7 +8392,7 @@ M: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> M: Rodrigo Vivi <rodrigo.vivi@intel.com> L: intel-gfx@lists.freedesktop.org W: https://01.org/linuxgraphics/ -B: https://01.org/linuxgraphics/documentation/how-report-bugs +B: https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs C: irc://chat.freenode.net/intel-gfx Q: http://patchwork.freedesktop.org/project/intel-gfx/ T: git git://anongit.freedesktop.org/drm-intel @@ -9278,7 +9278,7 @@ F: include/keys/trusted-type.h F: security/keys/trusted.c F: include/keys/trusted.h -KEYS/KEYRINGS: +KEYS/KEYRINGS M: David Howells <dhowells@redhat.com> M: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com> L: keyrings@vger.kernel.org @@ -11484,7 +11484,7 @@ F: drivers/scsi/mac_scsi.* F: drivers/scsi/sun3_scsi.* F: drivers/scsi/sun3_scsi_vme.c -NCSI LIBRARY: +NCSI LIBRARY M: Samuel Mendoza-Jonas <sam@mendozajonas.com> S: Maintained F: net/ncsi/ @@ -13512,7 +13512,7 @@ L: linuxppc-dev@lists.ozlabs.org S: Maintained F: drivers/block/ps3vram.c -PSAMPLE PACKET SAMPLING SUPPORT: +PSAMPLE PACKET SAMPLING SUPPORT M: Yotam Gigi <yotam.gi@gmail.com> S: Maintained F: net/psample @@ -14582,10 +14582,10 @@ F: drivers/media/pci/saa7146/ F: include/media/drv-intf/saa7146* SAFESETID SECURITY MODULE -M: Micah Morton <mortonm@chromium.org> -S: Supported -F: security/safesetid/ -F: Documentation/admin-guide/LSM/SafeSetID.rst +M: Micah Morton <mortonm@chromium.org> +S: Supported +F: security/safesetid/ +F: Documentation/admin-guide/LSM/SafeSetID.rst SAMSUNG AUDIO (ASoC) DRIVERS M: Krzysztof Kozlowski <krzk@kernel.org> @@ -16552,8 +16552,8 @@ M: Michael Jamet <michael.jamet@intel.com> M: Mika Westerberg <mika.westerberg@linux.intel.com> M: Yehezkel Bernat <YehezkelShB@gmail.com> L: linux-usb@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/westeri/thunderbolt.git S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/westeri/thunderbolt.git F: Documentation/admin-guide/thunderbolt.rst F: drivers/thunderbolt/ F: include/linux/thunderbolt.h @@ -17080,7 +17080,7 @@ S: Maintained F: Documentation/admin-guide/ufs.rst F: fs/ufs/ -UHID USERSPACE HID IO DRIVER: +UHID USERSPACE HID IO DRIVER M: David Herrmann <dh.herrmann@googlemail.com> L: linux-input@vger.kernel.org S: Maintained @@ -17094,18 +17094,18 @@ S: Maintained F: drivers/usb/common/ulpi.c F: include/linux/ulpi/ -ULTRA-WIDEBAND (UWB) SUBSYSTEM: +ULTRA-WIDEBAND (UWB) SUBSYSTEM L: devel@driverdev.osuosl.org S: Obsolete F: drivers/staging/uwb/ -UNICODE SUBSYSTEM: +UNICODE SUBSYSTEM M: Gabriel Krisman Bertazi <krisman@collabora.com> L: linux-fsdevel@vger.kernel.org S: Supported F: fs/unicode/ -UNICORE32 ARCHITECTURE: +UNICORE32 ARCHITECTURE M: Guan Xuetao <gxt@pku.edu.cn> W: http://mprc.pku.edu.cn/~guanxuetao/linux S: Maintained @@ -17392,11 +17392,14 @@ F: drivers/usb/ F: include/linux/usb.h F: include/linux/usb/ -USB TYPEC PI3USB30532 MUX DRIVER -M: Hans de Goede <hdegoede@redhat.com> +USB TYPEC BUS FOR ALTERNATE MODES +M: Heikki Krogerus <heikki.krogerus@linux.intel.com> L: linux-usb@vger.kernel.org S: Maintained -F: drivers/usb/typec/mux/pi3usb30532.c +F: Documentation/ABI/testing/sysfs-bus-typec +F: Documentation/driver-api/usb/typec_bus.rst +F: drivers/usb/typec/altmodes/ +F: include/linux/usb/typec_altmode.h USB TYPEC CLASS M: Heikki Krogerus <heikki.krogerus@linux.intel.com> @@ -17407,14 +17410,11 @@ F: Documentation/driver-api/usb/typec.rst F: drivers/usb/typec/ F: include/linux/usb/typec.h -USB TYPEC BUS FOR ALTERNATE MODES -M: Heikki Krogerus <heikki.krogerus@linux.intel.com> +USB TYPEC PI3USB30532 MUX DRIVER +M: Hans de Goede <hdegoede@redhat.com> L: linux-usb@vger.kernel.org S: Maintained -F: Documentation/ABI/testing/sysfs-bus-typec -F: Documentation/driver-api/usb/typec_bus.rst -F: drivers/usb/typec/altmodes/ -F: include/linux/usb/typec_altmode.h +F: drivers/usb/typec/mux/pi3usb30532.c USB TYPEC PORT CONTROLLER DRIVERS M: Guenter Roeck <linux@roeck-us.net> @@ -17791,7 +17791,7 @@ F: include/linux/vbox_utils.h F: include/uapi/linux/vbox*.h F: drivers/virt/vboxguest/ -VIRTUAL BOX SHARED FOLDER VFS DRIVER: +VIRTUAL BOX SHARED FOLDER VFS DRIVER M: Hans de Goede <hdegoede@redhat.com> L: linux-fsdevel@vger.kernel.org S: Maintained @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 6 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Kleptomaniac Octopus # *DOCUMENTATION* diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h index d429f7701c36..5d10051c3e62 100644 --- a/arch/arm64/include/asm/lse.h +++ b/arch/arm64/include/asm/lse.h @@ -6,7 +6,7 @@ #ifdef CONFIG_ARM64_LSE_ATOMICS -#define __LSE_PREAMBLE ".arch armv8-a+lse\n" +#define __LSE_PREAMBLE ".arch_extension lse\n" #include <linux/compiler_types.h> #include <linux/export.h> diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index a4f9ca5479b0..4d94676e5a8b 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -213,7 +213,7 @@ static inline unsigned long kaslr_offset(void) ((__force __typeof__(addr))sign_extend64((__force u64)(addr), 55)) #define untagged_addr(addr) ({ \ - u64 __addr = (__force u64)addr; \ + u64 __addr = (__force u64)(addr); \ __addr &= __untagged_addr(__addr); \ (__force __typeof__(addr))__addr; \ }) diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 86332080399a..080a0bf8e54b 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -295,8 +295,13 @@ static inline bool pfn_valid(unsigned long pfn) /* * Some number of bits at the level of the page table that points to * a hugepte are used to encode the size. This masks those bits. + * On 8xx, HW assistance requires 4k alignment for the hugepte. */ +#ifdef CONFIG_PPC_8xx +#define HUGEPD_SHIFT_MASK 0xfff +#else #define HUGEPD_SHIFT_MASK 0x3f +#endif #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 8387698bd5b6..eedcbfb9a6ff 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -168,6 +168,10 @@ struct thread_struct { unsigned long srr1; unsigned long dar; unsigned long dsisr; +#ifdef CONFIG_PPC_BOOK3S_32 + unsigned long r0, r3, r4, r5, r6, r8, r9, r11; + unsigned long lr, ctr; +#endif #endif /* Debug Registers */ struct debug_reg debug; diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index c25e562f1cd9..fcf24a365fc0 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -132,6 +132,18 @@ int main(void) OFFSET(SRR1, thread_struct, srr1); OFFSET(DAR, thread_struct, dar); OFFSET(DSISR, thread_struct, dsisr); +#ifdef CONFIG_PPC_BOOK3S_32 + OFFSET(THR0, thread_struct, r0); + OFFSET(THR3, thread_struct, r3); + OFFSET(THR4, thread_struct, r4); + OFFSET(THR5, thread_struct, r5); + OFFSET(THR6, thread_struct, r6); + OFFSET(THR8, thread_struct, r8); + OFFSET(THR9, thread_struct, r9); + OFFSET(THR11, thread_struct, r11); + OFFSET(THLR, thread_struct, lr); + OFFSET(THCTR, thread_struct, ctr); +#endif #endif #ifdef CONFIG_SPE OFFSET(THREAD_EVR0, thread_struct, evr[0]); diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index a1eaffe868de..7b048cee767c 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -1184,6 +1184,17 @@ void eeh_handle_special_event(void) eeh_pe_state_mark(pe, EEH_PE_RECOVERING); eeh_handle_normal_event(pe); } else { + eeh_for_each_pe(pe, tmp_pe) + eeh_pe_for_each_dev(tmp_pe, edev, tmp_edev) + edev->mode &= ~EEH_DEV_NO_HANDLER; + + /* Notify all devices to be down */ + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true); + eeh_set_channel_state(pe, pci_channel_io_perm_failure); + eeh_pe_report( + "error_detected(permanent failure)", pe, + eeh_report_failure, NULL); + pci_lock_rescan_remove(); list_for_each_entry(hose, &hose_list, list_node) { phb_pe = eeh_phb_pe_get(hose); @@ -1192,16 +1203,6 @@ void eeh_handle_special_event(void) (phb_pe->state & EEH_PE_RECOVERING)) continue; - eeh_for_each_pe(pe, tmp_pe) - eeh_pe_for_each_dev(tmp_pe, edev, tmp_edev) - edev->mode &= ~EEH_DEV_NO_HANDLER; - - /* Notify all devices to be down */ - eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true); - eeh_set_channel_state(pe, pci_channel_io_perm_failure); - eeh_pe_report( - "error_detected(permanent failure)", pe, - eeh_report_failure, NULL); bus = eeh_pe_bus_get(phb_pe); if (!bus) { pr_err("%s: Cannot find PCI bus for " diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 0713daa651d9..16af0d8d90a8 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -783,7 +783,7 @@ fast_exception_return: 1: lis r3,exc_exit_restart_end@ha addi r3,r3,exc_exit_restart_end@l cmplw r12,r3 -#if CONFIG_PPC_BOOK3S_601 +#ifdef CONFIG_PPC_BOOK3S_601 bge 2b #else bge 3f @@ -791,7 +791,7 @@ fast_exception_return: lis r4,exc_exit_restart@ha addi r4,r4,exc_exit_restart@l cmplw r12,r4 -#if CONFIG_PPC_BOOK3S_601 +#ifdef CONFIG_PPC_BOOK3S_601 blt 2b #else blt 3f @@ -1354,12 +1354,17 @@ _GLOBAL(enter_rtas) mtspr SPRN_SRR0,r8 mtspr SPRN_SRR1,r9 RFI -1: tophys(r9,r1) +1: tophys_novmstack r9, r1 +#ifdef CONFIG_VMAP_STACK + li r0, MSR_KERNEL & ~MSR_IR /* can take DTLB miss */ + mtmsr r0 + isync +#endif lwz r8,INT_FRAME_SIZE+4(r9) /* get return address */ lwz r9,8(r9) /* original msr value */ addi r1,r1,INT_FRAME_SIZE li r0,0 - tophys(r7, r2) + tophys_novmstack r7, r2 stw r0, THREAD + RTAS_SP(r7) mtspr SPRN_SRR0,r8 mtspr SPRN_SRR1,r9 diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 0493fcac6409..97c887950c3c 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -290,17 +290,55 @@ MachineCheck: 7: EXCEPTION_PROLOG_2 addi r3,r1,STACK_FRAME_OVERHEAD #ifdef CONFIG_PPC_CHRP - bne cr1,1f +#ifdef CONFIG_VMAP_STACK + mfspr r4, SPRN_SPRG_THREAD + tovirt(r4, r4) + lwz r4, RTAS_SP(r4) + cmpwi cr1, r4, 0 #endif - EXC_XFER_STD(0x200, machine_check_exception) -#ifdef CONFIG_PPC_CHRP -1: b machine_check_in_rtas + beq cr1, machine_check_tramp + b machine_check_in_rtas +#else + b machine_check_tramp #endif /* Data access exception. */ . = 0x300 DO_KVM 0x300 DataAccess: +#ifdef CONFIG_VMAP_STACK + mtspr SPRN_SPRG_SCRATCH0,r10 + mfspr r10, SPRN_SPRG_THREAD +BEGIN_MMU_FTR_SECTION + stw r11, THR11(r10) + mfspr r10, SPRN_DSISR + mfcr r11 +#ifdef CONFIG_PPC_KUAP + andis. r10, r10, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH | DSISR_PROTFAULT)@h +#else + andis. r10, r10, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH)@h +#endif + mfspr r10, SPRN_SPRG_THREAD + beq hash_page_dsi +.Lhash_page_dsi_cont: + mtcr r11 + lwz r11, THR11(r10) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) + mtspr SPRN_SPRG_SCRATCH1,r11 + mfspr r11, SPRN_DAR + stw r11, DAR(r10) + mfspr r11, SPRN_DSISR + stw r11, DSISR(r10) + mfspr r11, SPRN_SRR0 + stw r11, SRR0(r10) + mfspr r11, SPRN_SRR1 /* check whether user or kernel */ + stw r11, SRR1(r10) + mfcr r10 + andi. r11, r11, MSR_PR + + EXCEPTION_PROLOG_1 + b handle_page_fault_tramp_1 +#else /* CONFIG_VMAP_STACK */ EXCEPTION_PROLOG handle_dar_dsisr=1 get_and_save_dar_dsisr_on_stack r4, r5, r11 BEGIN_MMU_FTR_SECTION @@ -316,11 +354,32 @@ BEGIN_MMU_FTR_SECTION FTR_SECTION_ELSE b handle_page_fault_tramp_2 ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE) +#endif /* CONFIG_VMAP_STACK */ /* Instruction access exception. */ . = 0x400 DO_KVM 0x400 InstructionAccess: +#ifdef CONFIG_VMAP_STACK + mtspr SPRN_SPRG_SCRATCH0,r10 + mtspr SPRN_SPRG_SCRATCH1,r11 + mfspr r10, SPRN_SPRG_THREAD + mfspr r11, SPRN_SRR0 + stw r11, SRR0(r10) + mfspr r11, SPRN_SRR1 /* check whether user or kernel */ + stw r11, SRR1(r10) + mfcr r10 +BEGIN_MMU_FTR_SECTION + andis. r11, r11, SRR1_ISI_NOPT@h /* no pte found? */ + bne hash_page_isi +.Lhash_page_isi_cont: + mfspr r11, SPRN_SRR1 /* check whether user or kernel */ +END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) + andi. r11, r11, MSR_PR + + EXCEPTION_PROLOG_1 + EXCEPTION_PROLOG_2 +#else /* CONFIG_VMAP_STACK */ EXCEPTION_PROLOG andis. r0,r9,SRR1_ISI_NOPT@h /* no pte found? */ beq 1f /* if so, try to put a PTE */ @@ -329,6 +388,7 @@ InstructionAccess: BEGIN_MMU_FTR_SECTION bl hash_page END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) +#endif /* CONFIG_VMAP_STACK */ 1: mr r4,r12 andis. r5,r9,DSISR_SRR1_MATCH_32S@h /* Filter relevant SRR1 bits */ stw r4, _DAR(r11) @@ -344,7 +404,7 @@ Alignment: EXCEPTION_PROLOG handle_dar_dsisr=1 save_dar_dsisr_on_stack r4, r5, r11 addi r3,r1,STACK_FRAME_OVERHEAD - EXC_XFER_STD(0x600, alignment_exception) + b alignment_exception_tramp /* Program check exception */ EXCEPTION(0x700, ProgramCheck, program_check_exception, EXC_XFER_STD) @@ -645,15 +705,100 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_NEED_DTLB_SW_LRU) . = 0x3000 +machine_check_tramp: + EXC_XFER_STD(0x200, machine_check_exception) + +alignment_exception_tramp: + EXC_XFER_STD(0x600, alignment_exception) + handle_page_fault_tramp_1: +#ifdef CONFIG_VMAP_STACK + EXCEPTION_PROLOG_2 handle_dar_dsisr=1 +#endif lwz r4, _DAR(r11) lwz r5, _DSISR(r11) /* fall through */ handle_page_fault_tramp_2: EXC_XFER_LITE(0x300, handle_page_fault) +#ifdef CONFIG_VMAP_STACK +.macro save_regs_thread thread + stw r0, THR0(\thread) + stw r3, THR3(\thread) + stw r4, THR4(\thread) + stw r5, THR5(\thread) + stw r6, THR6(\thread) + stw r8, THR8(\thread) + stw r9, THR9(\thread) + mflr r0 + stw r0, THLR(\thread) + mfctr r0 + stw r0, THCTR(\thread) +.endm + +.macro restore_regs_thread thread + lwz r0, THLR(\thread) + mtlr r0 + lwz r0, THCTR(\thread) + mtctr r0 + lwz r0, THR0(\thread) + lwz r3, THR3(\thread) + lwz r4, THR4(\thread) + lwz r5, THR5(\thread) + lwz r6, THR6(\thread) + lwz r8, THR8(\thread) + lwz r9, THR9(\thread) +.endm + +hash_page_dsi: + save_regs_thread r10 + mfdsisr r3 + mfdar r4 + mfsrr0 r5 + mfsrr1 r9 + rlwinm r3, r3, 32 - 15, _PAGE_RW /* DSISR_STORE -> _PAGE_RW */ + bl hash_page + mfspr r10, SPRN_SPRG_THREAD + restore_regs_thread r10 + b .Lhash_page_dsi_cont + +hash_page_isi: + mr r11, r10 + mfspr r10, SPRN_SPRG_THREAD + save_regs_thread r10 + li r3, 0 + lwz r4, SRR0(r10) + lwz r9, SRR1(r10) + bl hash_page + mfspr r10, SPRN_SPRG_THREAD + restore_regs_thread r10 + mr r10, r11 + b .Lhash_page_isi_cont + + .globl fast_hash_page_return +fast_hash_page_return: + andis. r10, r9, SRR1_ISI_NOPT@h /* Set on ISI, cleared on DSI */ + mfspr r10, SPRN_SPRG_THREAD + restore_regs_thread r10 + bne 1f + + /* DSI */ + mtcr r11 + lwz r11, THR11(r10) + mfspr r10, SPRN_SPRG_SCRATCH0 + SYNC + RFI + +1: /* ISI */ + mtcr r11 + mfspr r11, SPRN_SPRG_SCRATCH1 + mfspr r10, SPRN_SPRG_SCRATCH0 + SYNC + RFI + stack_overflow: vmap_stack_overflow_exception +#endif AltiVecUnavailable: EXCEPTION_PROLOG diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h index a6a5fbbf8504..9db162f79fe6 100644 --- a/arch/powerpc/kernel/head_32.h +++ b/arch/powerpc/kernel/head_32.h @@ -64,11 +64,25 @@ .endm .macro EXCEPTION_PROLOG_2 handle_dar_dsisr=0 +#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_PPC_BOOK3S) +BEGIN_MMU_FTR_SECTION + mtcr r10 +FTR_SECTION_ELSE + stw r10, _CCR(r11) +ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE) +#else stw r10,_CCR(r11) /* save registers */ +#endif + mfspr r10, SPRN_SPRG_SCRATCH0 stw r12,GPR12(r11) stw r9,GPR9(r11) - mfspr r10,SPRN_SPRG_SCRATCH0 stw r10,GPR10(r11) +#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_PPC_BOOK3S) +BEGIN_MMU_FTR_SECTION + mfcr r10 + stw r10, _CCR(r11) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) +#endif mfspr r12,SPRN_SPRG_SCRATCH1 stw r12,GPR11(r11) mflr r10 @@ -83,6 +97,11 @@ stw r10, _DSISR(r11) .endif lwz r9, SRR1(r12) +#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_PPC_BOOK3S) +BEGIN_MMU_FTR_SECTION + andi. r10, r9, MSR_PR +END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) +#endif lwz r12, SRR0(r12) #else mfspr r12,SPRN_SRR0 diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 9922306ae512..073a651787df 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -256,7 +256,7 @@ InstructionTLBMiss: * set. All other Linux PTE bits control the behavior * of the MMU. */ - rlwimi r10, r10, 0, 0x0f00 /* Clear bits 20-23 */ + rlwinm r10, r10, 0, ~0x0f00 /* Clear bits 20-23 */ rlwimi r10, r10, 4, 0x0400 /* Copy _PAGE_EXEC into bit 21 */ ori r10, r10, RPN_PATTERN | 0x200 /* Set 22 and 24-27 */ mtspr SPRN_MI_RPN, r10 /* Update TLB entry */ diff --git a/arch/powerpc/kernel/idle_6xx.S b/arch/powerpc/kernel/idle_6xx.S index 0ffdd18b9f26..433d97bea1f3 100644 --- a/arch/powerpc/kernel/idle_6xx.S +++ b/arch/powerpc/kernel/idle_6xx.S @@ -166,7 +166,11 @@ BEGIN_FTR_SECTION mfspr r9,SPRN_HID0 andis. r9,r9,HID0_NAP@h beq 1f +#ifdef CONFIG_VMAP_STACK + addis r9, r11, nap_save_msscr0@ha +#else addis r9,r11,(nap_save_msscr0-KERNELBASE)@ha +#endif lwz r9,nap_save_msscr0@l(r9) mtspr SPRN_MSSCR0, r9 sync @@ -174,7 +178,11 @@ BEGIN_FTR_SECTION 1: END_FTR_SECTION_IFSET(CPU_FTR_NAP_DISABLE_L2_PR) BEGIN_FTR_SECTION +#ifdef CONFIG_VMAP_STACK + addis r9, r11, nap_save_hid1@ha +#else addis r9,r11,(nap_save_hid1-KERNELBASE)@ha +#endif lwz r9,nap_save_hid1@l(r9) mtspr SPRN_HID1, r9 END_FTR_SECTION_IFSET(CPU_FTR_DUAL_PLL_750FX) diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index e6c30cee6abf..d215f9554553 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -200,14 +200,27 @@ unsigned long get_tm_stackpointer(struct task_struct *tsk) * normal/non-checkpointed stack pointer. */ + unsigned long ret = tsk->thread.regs->gpr[1]; + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM BUG_ON(tsk != current); if (MSR_TM_ACTIVE(tsk->thread.regs->msr)) { + preempt_disable(); tm_reclaim_current(TM_CAUSE_SIGNAL); if (MSR_TM_TRANSACTIONAL(tsk->thread.regs->msr)) - return tsk->thread.ckpt_regs.gpr[1]; + ret = tsk->thread.ckpt_regs.gpr[1]; + + /* + * If we treclaim, we must clear the current thread's TM bits + * before re-enabling preemption. Otherwise we might be + * preempted and have the live MSR[TS] changed behind our back + * (tm_recheckpoint_new_task() would recheckpoint). Besides, we + * enter the signal handler in non-transactional state. + */ + tsk->thread.regs->msr &= ~MSR_TS_MASK; + preempt_enable(); } #endif - return tsk->thread.regs->gpr[1]; + return ret; } diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 98600b276f76..1b090a76b444 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -489,19 +489,11 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame, */ static int save_tm_user_regs(struct pt_regs *regs, struct mcontext __user *frame, - struct mcontext __user *tm_frame, int sigret) + struct mcontext __user *tm_frame, int sigret, + unsigned long msr) { - unsigned long msr = regs->msr; - WARN_ON(tm_suspend_disabled); - /* Remove TM bits from thread's MSR. The MSR in the sigcontext - * just indicates to userland that we were doing a transaction, but we - * don't want to return in transactional state. This also ensures - * that flush_fp_to_thread won't set TIF_RESTORE_TM again. - */ - regs->msr &= ~MSR_TS_MASK; - /* Save both sets of general registers */ if (save_general_regs(¤t->thread.ckpt_regs, frame) || save_general_regs(regs, tm_frame)) @@ -912,6 +904,10 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, int sigret; unsigned long tramp; struct pt_regs *regs = tsk->thread.regs; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* Save the thread's msr before get_tm_stackpointer() changes it */ + unsigned long msr = regs->msr; +#endif BUG_ON(tsk != current); @@ -944,13 +940,13 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, #ifdef CONFIG_PPC_TRANSACTIONAL_MEM tm_frame = &rt_sf->uc_transact.uc_mcontext; - if (MSR_TM_ACTIVE(regs->msr)) { + if (MSR_TM_ACTIVE(msr)) { if (__put_user((unsigned long)&rt_sf->uc_transact, &rt_sf->uc.uc_link) || __put_user((unsigned long)tm_frame, &rt_sf->uc_transact.uc_regs)) goto badframe; - if (save_tm_user_regs(regs, frame, tm_frame, sigret)) + if (save_tm_user_regs(regs, frame, tm_frame, sigret, msr)) goto badframe; } else @@ -1369,6 +1365,10 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset, int sigret; unsigned long tramp; struct pt_regs *regs = tsk->thread.regs; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* Save the thread's msr before get_tm_stackpointer() changes it */ + unsigned long msr = regs->msr; +#endif BUG_ON(tsk != current); @@ -1402,9 +1402,9 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset, #ifdef CONFIG_PPC_TRANSACTIONAL_MEM tm_mctx = &frame->mctx_transact; - if (MSR_TM_ACTIVE(regs->msr)) { + if (MSR_TM_ACTIVE(msr)) { if (save_tm_user_regs(regs, &frame->mctx, &frame->mctx_transact, - sigret)) + sigret, msr)) goto badframe; } else diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 117515564ec7..84ed2e77ef9c 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -192,7 +192,8 @@ static long setup_sigcontext(struct sigcontext __user *sc, static long setup_tm_sigcontexts(struct sigcontext __user *sc, struct sigcontext __user *tm_sc, struct task_struct *tsk, - int signr, sigset_t *set, unsigned long handler) + int signr, sigset_t *set, unsigned long handler, + unsigned long msr) { /* When CONFIG_ALTIVEC is set, we _always_ setup v_regs even if the * process never used altivec yet (MSR_VEC is zero in pt_regs of @@ -207,12 +208,11 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, elf_vrreg_t __user *tm_v_regs = sigcontext_vmx_regs(tm_sc); #endif struct pt_regs *regs = tsk->thread.regs; - unsigned long msr = tsk->thread.regs->msr; long err = 0; BUG_ON(tsk != current); - BUG_ON(!MSR_TM_ACTIVE(regs->msr)); + BUG_ON(!MSR_TM_ACTIVE(msr)); WARN_ON(tm_suspend_disabled); @@ -222,13 +222,6 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc, */ msr |= tsk->thread.ckpt_regs.msr & (MSR_FP | MSR_VEC | MSR_VSX); - /* Remove TM bits from thread's MSR. The MSR in the sigcontext - * just indicates to userland that we were doing a transaction, but we - * don't want to return in transactional state. This also ensures - * that flush_fp_to_thread won't set TIF_RESTORE_TM again. - */ - regs->msr &= ~MSR_TS_MASK; - #ifdef CONFIG_ALTIVEC err |= __put_user(v_regs, &sc->v_regs); err |= __put_user(tm_v_regs, &tm_sc->v_regs); @@ -824,6 +817,10 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, unsigned long newsp = 0; long err = 0; struct pt_regs *regs = tsk->thread.regs; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* Save the thread's msr before get_tm_stackpointer() changes it */ + unsigned long msr = regs->msr; +#endif BUG_ON(tsk != current); @@ -841,7 +838,7 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, err |= __put_user(0, &frame->uc.uc_flags); err |= __save_altstack(&frame->uc.uc_stack, regs->gpr[1]); #ifdef CONFIG_PPC_TRANSACTIONAL_MEM - if (MSR_TM_ACTIVE(regs->msr)) { + if (MSR_TM_ACTIVE(msr)) { /* The ucontext_t passed to userland points to the second * ucontext_t (for transactional state) with its uc_link ptr. */ @@ -849,7 +846,8 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, err |= setup_tm_sigcontexts(&frame->uc.uc_mcontext, &frame->uc_transact.uc_mcontext, tsk, ksig->sig, NULL, - (unsigned long)ksig->ka.sa.sa_handler); + (unsigned long)ksig->ka.sa.sa_handler, + msr); } else #endif { diff --git a/arch/powerpc/mm/book3s32/hash_low.S b/arch/powerpc/mm/book3s32/hash_low.S index c11b0a005196..2015c4f96238 100644 --- a/arch/powerpc/mm/book3s32/hash_low.S +++ b/arch/powerpc/mm/book3s32/hash_low.S @@ -25,12 +25,6 @@ #include <asm/feature-fixups.h> #include <asm/code-patching-asm.h> -#ifdef CONFIG_VMAP_STACK -#define ADDR_OFFSET 0 -#else -#define ADDR_OFFSET PAGE_OFFSET -#endif - #ifdef CONFIG_SMP .section .bss .align 2 @@ -53,8 +47,8 @@ mmu_hash_lock: .text _GLOBAL(hash_page) #ifdef CONFIG_SMP - lis r8, (mmu_hash_lock - ADDR_OFFSET)@h - ori r8, r8, (mmu_hash_lock - ADDR_OFFSET)@l + lis r8, (mmu_hash_lock - PAGE_OFFSET)@h + ori r8, r8, (mmu_hash_lock - PAGE_OFFSET)@l lis r0,0x0fff b 10f 11: lwz r6,0(r8) @@ -72,12 +66,9 @@ _GLOBAL(hash_page) cmplw 0,r4,r0 ori r3,r3,_PAGE_USER|_PAGE_PRESENT /* test low addresses as user */ mfspr r5, SPRN_SPRG_PGDIR /* phys page-table root */ -#ifdef CONFIG_VMAP_STACK - tovirt(r5, r5) -#endif blt+ 112f /* assume user more likely */ - lis r5, (swapper_pg_dir - ADDR_OFFSET)@ha /* if kernel address, use */ - addi r5 ,r5 ,(swapper_pg_dir - ADDR_OFFSET)@l /* kernel page table */ + lis r5, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ + addi r5 ,r5 ,(swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */ rlwimi r3,r9,32-12,29,29 /* MSR_PR -> _PAGE_USER */ 112: #ifndef CONFIG_PTE_64BIT @@ -89,9 +80,6 @@ _GLOBAL(hash_page) lwzx r8,r8,r5 /* Get L1 entry */ rlwinm. r8,r8,0,0,20 /* extract pt base address */ #endif -#ifdef CONFIG_VMAP_STACK - tovirt(r8, r8) -#endif #ifdef CONFIG_SMP beq- hash_page_out /* return if no mapping */ #else @@ -143,30 +131,36 @@ retry: bne- retry /* retry if someone got there first */ mfsrin r3,r4 /* get segment reg for segment */ +#ifndef CONFIG_VMAP_STACK mfctr r0 stw r0,_CTR(r11) +#endif bl create_hpte /* add the hash table entry */ #ifdef CONFIG_SMP eieio - lis r8, (mmu_hash_lock - ADDR_OFFSET)@ha + lis r8, (mmu_hash_lock - PAGE_OFFSET)@ha li r0,0 - stw r0, (mmu_hash_lock - ADDR_OFFSET)@l(r8) + stw r0, (mmu_hash_lock - PAGE_OFFSET)@l(r8) #endif +#ifdef CONFIG_VMAP_STACK + b fast_hash_page_return +#else /* Return from the exception */ lwz r5,_CTR(r11) mtctr r5 lwz r0,GPR0(r11) lwz r8,GPR8(r11) b fast_exception_return +#endif #ifdef CONFIG_SMP hash_page_out: eieio - lis r8, (mmu_hash_lock - ADDR_OFFSET)@ha + lis r8, (mmu_hash_lock - PAGE_OFFSET)@ha li r0,0 - stw r0, (mmu_hash_lock - ADDR_OFFSET)@l(r8) + stw r0, (mmu_hash_lock - PAGE_OFFSET)@l(r8) blr #endif /* CONFIG_SMP */ @@ -341,7 +335,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) patch_site 1f, patch__hash_page_A1 patch_site 2f, patch__hash_page_A2 /* Get the address of the primary PTE group in the hash table (r3) */ -0: lis r0, (Hash_base - ADDR_OFFSET)@h /* base address of hash table */ +0: lis r0, (Hash_base - PAGE_OFFSET)@h /* base address of hash table */ 1: rlwimi r0,r3,LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* VSID -> hash */ 2: rlwinm r3,r4,20+LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* PI -> hash */ xor r3,r3,r0 /* make primary hash */ @@ -355,10 +349,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) beq+ 10f /* no PTE: go look for an empty slot */ tlbie r4 - lis r4, (htab_hash_searches - ADDR_OFFSET)@ha - lwz r6, (htab_hash_searches - ADDR_OFFSET)@l(r4) + lis r4, (htab_hash_searches - PAGE_OFFSET)@ha + lwz r6, (htab_hash_searches - PAGE_OFFSET)@l(r4) addi r6,r6,1 /* count how many searches we do */ - stw r6, (htab_hash_searches - ADDR_OFFSET)@l(r4) + stw r6, (htab_hash_searches - PAGE_OFFSET)@l(r4) /* Search the primary PTEG for a PTE whose 1st (d)word matches r5 */ mtctr r0 @@ -390,10 +384,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) beq+ found_empty /* update counter of times that the primary PTEG is full */ - lis r4, (primary_pteg_full - ADDR_OFFSET)@ha - lwz r6, (primary_pteg_full - ADDR_OFFSET)@l(r4) + lis r4, (primary_pteg_full - PAGE_OFFSET)@ha + lwz r6, (primary_pteg_full - PAGE_OFFSET)@l(r4) addi r6,r6,1 - stw r6, (primary_pteg_full - ADDR_OFFSET)@l(r4) + stw r6, (primary_pteg_full - PAGE_OFFSET)@l(r4) patch_site 0f, patch__hash_page_C /* Search the secondary PTEG for an empty slot */ @@ -427,8 +421,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) * lockup here but that shouldn't happen */ -1: lis r4, (next_slot - ADDR_OFFSET)@ha /* get next evict slot */ - lwz r6, (next_slot - ADDR_OFFSET)@l(r4) +1: lis r4, (next_slot - PAGE_OFFSET)@ha /* get next evict slot */ + lwz r6, (next_slot - PAGE_OFFSET)@l(r4) addi r6,r6,HPTE_SIZE /* search for candidate */ andi. r6,r6,7*HPTE_SIZE stw r6,next_slot@l(r4) diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index 0a1c65a2c565..f888cbb109b9 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -413,7 +413,7 @@ void __init MMU_init_hw(void) void __init MMU_init_hw_patch(void) { unsigned int hmask = Hash_mask >> (16 - LG_HPTEG_SIZE); - unsigned int hash; + unsigned int hash = (unsigned int)Hash - PAGE_OFFSET; if (ppc_md.progress) ppc_md.progress("hash:patch", 0x345); @@ -425,11 +425,6 @@ void __init MMU_init_hw_patch(void) /* * Patch up the instructions in hashtable.S:create_hpte */ - if (IS_ENABLED(CONFIG_VMAP_STACK)) - hash = (unsigned int)Hash; - else - hash = (unsigned int)Hash - PAGE_OFFSET; - modify_instruction_site(&patch__hash_page_A0, 0xffff, hash >> 16); modify_instruction_site(&patch__hash_page_A1, 0x7c0, hash_mb << 6); modify_instruction_site(&patch__hash_page_A2, 0x7c0, hash_mb2 << 6); @@ -439,8 +434,7 @@ void __init MMU_init_hw_patch(void) /* * Patch up the instructions in hashtable.S:flush_hash_page */ - modify_instruction_site(&patch__flush_hash_A0, 0xffff, - ((unsigned int)Hash - PAGE_OFFSET) >> 16); + modify_instruction_site(&patch__flush_hash_A0, 0xffff, hash >> 16); modify_instruction_site(&patch__flush_hash_A1, 0x7c0, hash_mb << 6); modify_instruction_site(&patch__flush_hash_A2, 0x7c0, hash_mb2 << 6); modify_instruction_site(&patch__flush_hash_B, 0xffff, hmask); diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 73d4873fc7f8..33b3461d91e8 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -53,20 +53,24 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, if (pshift >= pdshift) { cachep = PGT_CACHE(PTE_T_ORDER); num_hugepd = 1 << (pshift - pdshift); + new = NULL; } else if (IS_ENABLED(CONFIG_PPC_8xx)) { - cachep = PGT_CACHE(PTE_INDEX_SIZE); + cachep = NULL; num_hugepd = 1; + new = pte_alloc_one(mm); } else { cachep = PGT_CACHE(pdshift - pshift); num_hugepd = 1; + new = NULL; } - if (!cachep) { + if (!cachep && !new) { WARN_ONCE(1, "No page table cache created for hugetlb tables"); return -ENOMEM; } - new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL)); + if (cachep) + new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL)); BUG_ON(pshift > HUGEPD_SHIFT_MASK); BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK); @@ -97,7 +101,10 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, if (i < num_hugepd) { for (i = i - 1 ; i >= 0; i--, hpdp--) *hpdp = __hugepd(0); - kmem_cache_free(cachep, new); + if (cachep) + kmem_cache_free(cachep, new); + else + pte_free(mm, new); } else { kmemleak_ignore(new); } @@ -324,8 +331,7 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif if (shift >= pdshift) hugepd_free(tlb, hugepte); else if (IS_ENABLED(CONFIG_PPC_8xx)) - pgtable_free_tlb(tlb, hugepte, - get_hugepd_cache_index(PTE_INDEX_SIZE)); + pgtable_free_tlb(tlb, hugepte, 0); else pgtable_free_tlb(tlb, hugepte, get_hugepd_cache_index(pdshift - shift)); @@ -639,12 +645,13 @@ static int __init hugetlbpage_init(void) * if we have pdshift and shift value same, we don't * use pgt cache for hugepd. */ - if (pdshift > shift && IS_ENABLED(CONFIG_PPC_8xx)) - pgtable_cache_add(PTE_INDEX_SIZE); - else if (pdshift > shift) - pgtable_cache_add(pdshift - shift); - else if (IS_ENABLED(CONFIG_PPC_FSL_BOOK3E) || IS_ENABLED(CONFIG_PPC_8xx)) + if (pdshift > shift) { + if (!IS_ENABLED(CONFIG_PPC_8xx)) + pgtable_cache_add(pdshift - shift); + } else if (IS_ENABLED(CONFIG_PPC_FSL_BOOK3E) || + IS_ENABLED(CONFIG_PPC_8xx)) { pgtable_cache_add(PTE_T_ORDER); + } configured = true; } diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c index 16dd95bd0749..db5664dde5ff 100644 --- a/arch/powerpc/mm/kasan/kasan_init_32.c +++ b/arch/powerpc/mm/kasan/kasan_init_32.c @@ -185,8 +185,7 @@ u8 __initdata early_hash[256 << 10] __aligned(256 << 10) = {0}; static void __init kasan_early_hash_table(void) { - unsigned int hash = IS_ENABLED(CONFIG_VMAP_STACK) ? (unsigned int)early_hash : - __pa(early_hash); + unsigned int hash = __pa(early_hash); modify_instruction_site(&patch__hash_page_A0, 0xffff, hash >> 16); modify_instruction_site(&patch__flush_hash_A0, 0xffff, hash >> 16); diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index e8c84d265602..0ec9640335bb 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -3435,6 +3435,11 @@ getstring(char *s, int size) int c; c = skipbl(); + if (c == '\n') { + *s = 0; + return; + } + do { if( size > 1 ){ *s++ = c; diff --git a/arch/s390/Makefile b/arch/s390/Makefile index e0e3a465bbfd..8dfa2cf1f05c 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -146,7 +146,7 @@ all: bzImage #KBUILD_IMAGE is necessary for packaging targets like rpm-pkg, deb-pkg... KBUILD_IMAGE := $(boot)/bzImage -install: vmlinux +install: $(Q)$(MAKE) $(build)=$(boot) $@ bzImage: vmlinux diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile index e2c47d3a1c89..0ff9261c915e 100644 --- a/arch/s390/boot/Makefile +++ b/arch/s390/boot/Makefile @@ -70,7 +70,7 @@ $(obj)/compressed/vmlinux: $(obj)/startup.a FORCE $(obj)/startup.a: $(OBJECTS) FORCE $(call if_changed,ar) -install: $(CONFIGURE) $(obj)/bzImage +install: sh -x $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/bzImage \ System.map "$(INSTALL_PATH)" diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c index 5d12352545c5..5591243d673e 100644 --- a/arch/s390/boot/kaslr.c +++ b/arch/s390/boot/kaslr.c @@ -75,7 +75,7 @@ static unsigned long get_random(unsigned long limit) *(unsigned long *) prng.parm_block ^= seed; for (i = 0; i < 16; i++) { cpacf_kmc(CPACF_KMC_PRNG, prng.parm_block, - (char *) entropy, (char *) entropy, + (u8 *) entropy, (u8 *) entropy, sizeof(entropy)); memcpy(prng.parm_block, entropy, sizeof(entropy)); } diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 2e60c80395ab..0c86ba19fa2b 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -53,6 +53,7 @@ CONFIG_VFIO_AP=m CONFIG_CRASH_DUMP=y CONFIG_HIBERNATION=y CONFIG_PM_DEBUG=y +CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y CONFIG_CMM=m CONFIG_APPLDATA_BASE=y CONFIG_KVM=m @@ -474,7 +475,6 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_EMULEX is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_GOOGLE is not set -# CONFIG_NET_VENDOR_HP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set @@ -684,7 +684,6 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_CRC32=m -CONFIG_CRYPTO_XXHASH=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -748,7 +747,6 @@ CONFIG_DEBUG_INFO_DWARF4=y CONFIG_GDB_SCRIPTS=y CONFIG_FRAME_WARN=1024 CONFIG_HEADERS_INSTALL=y -CONFIG_HEADERS_CHECK=y CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_PAGEALLOC=y @@ -772,9 +770,9 @@ CONFIG_DEBUG_MEMORY_INIT=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m CONFIG_DEBUG_PER_CPU_MAPS=y CONFIG_DEBUG_SHIRQ=y +CONFIG_PANIC_ON_OOPS=y CONFIG_DETECT_HUNG_TASK=y CONFIG_WQ_WATCHDOG=y -CONFIG_PANIC_ON_OOPS=y CONFIG_DEBUG_TIMEKEEPING=y CONFIG_PROVE_LOCKING=y CONFIG_LOCK_STAT=y @@ -783,9 +781,20 @@ CONFIG_DEBUG_ATOMIC_SLEEP=y CONFIG_DEBUG_LOCKING_API_SELFTESTS=y CONFIG_DEBUG_SG=y CONFIG_DEBUG_NOTIFIERS=y +CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_DEBUG_CREDENTIALS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=300 +CONFIG_LATENCYTOP=y +CONFIG_FUNCTION_PROFILER=y +CONFIG_STACK_TRACER=y +CONFIG_IRQSOFF_TRACER=y +CONFIG_PREEMPT_TRACER=y +CONFIG_SCHED_TRACER=y +CONFIG_FTRACE_SYSCALLS=y +CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_HIST_TRIGGERS=y +CONFIG_S390_PTDUMP=y CONFIG_NOTIFIER_ERROR_INJECTION=m CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m CONFIG_FAULT_INJECTION=y @@ -796,15 +805,6 @@ CONFIG_FAIL_IO_TIMEOUT=y CONFIG_FAIL_FUTEX=y CONFIG_FAULT_INJECTION_DEBUG_FS=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y -CONFIG_LATENCYTOP=y -CONFIG_IRQSOFF_TRACER=y -CONFIG_PREEMPT_TRACER=y -CONFIG_SCHED_TRACER=y -CONFIG_FTRACE_SYSCALLS=y -CONFIG_STACK_TRACER=y -CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_FUNCTION_PROFILER=y -CONFIG_HIST_TRIGGERS=y CONFIG_LKDTM=m CONFIG_TEST_LIST_SORT=y CONFIG_TEST_SORT=y @@ -814,5 +814,3 @@ CONFIG_INTERVAL_TREE_TEST=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y CONFIG_TEST_BPF=m -CONFIG_BUG_ON_DATA_CORRUPTION=y -CONFIG_S390_PTDUMP=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 25f799849582..6b27d861a9a3 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -53,6 +53,7 @@ CONFIG_VFIO_AP=m CONFIG_CRASH_DUMP=y CONFIG_HIBERNATION=y CONFIG_PM_DEBUG=y +CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y CONFIG_CMM=m CONFIG_APPLDATA_BASE=y CONFIG_KVM=m @@ -470,7 +471,6 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_EMULEX is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_GOOGLE is not set -# CONFIG_NET_VENDOR_HP is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set @@ -677,7 +677,6 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_CRC32=m -CONFIG_CRYPTO_XXHASH=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -739,18 +738,18 @@ CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_PANIC_ON_OOPS=y +CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_LATENCYTOP=y +CONFIG_FUNCTION_PROFILER=y +CONFIG_STACK_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y -CONFIG_STACK_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_FUNCTION_PROFILER=y CONFIG_HIST_TRIGGERS=y +CONFIG_S390_PTDUMP=y CONFIG_LKDTM=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y CONFIG_TEST_BPF=m -CONFIG_BUG_ON_DATA_CORRUPTION=y -CONFIG_S390_PTDUMP=y diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 85e944f04c70..1019efd85b9d 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -42,7 +42,7 @@ void __storage_key_init_range(unsigned long start, unsigned long end); static inline void storage_key_init_range(unsigned long start, unsigned long end) { - if (PAGE_DEFAULT_KEY) + if (PAGE_DEFAULT_KEY != 0) __storage_key_init_range(start, end); } diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 361ef5eda468..aadb3d0e2adc 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -84,7 +84,6 @@ void s390_update_cpu_mhz(void); void cpu_detect_mhz_feature(void); extern const struct seq_operations cpuinfo_op; -extern int sysctl_ieee_emulation_warnings; extern void execve_tail(void); extern void __bpon(void); diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h index 71e3f0146cda..1e3517b0518b 100644 --- a/arch/s390/include/asm/qdio.h +++ b/arch/s390/include/asm/qdio.h @@ -201,7 +201,7 @@ struct slib { * @scount: SBAL count * @sflags: whole SBAL flags * @length: length - * @addr: address + * @addr: absolute data address */ struct qdio_buffer_element { u8 eflags; @@ -211,7 +211,7 @@ struct qdio_buffer_element { u8 scount; u8 sflags; u32 length; - void *addr; + u64 addr; } __attribute__ ((packed, aligned(16))); /** @@ -227,7 +227,7 @@ struct qdio_buffer { * @sbal: absolute SBAL address */ struct sl_element { - unsigned long sbal; + u64 sbal; } __attribute__ ((packed)); /** diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 4dffbc10d3f8..40a0c0fd95ca 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -781,9 +781,19 @@ struct kvm_vcpu_arch { u64 msr_kvm_poll_control; /* - * Indicate whether the access faults on its page table in guest - * which is set when fix page fault and used to detect unhandeable - * instruction. + * Indicates the guest is trying to write a gfn that contains one or + * more of the PTEs used to translate the write itself, i.e. the access + * is changing its own translation in the guest page tables. KVM exits + * to userspace if emulation of the faulting instruction fails and this + * flag is set, as KVM cannot make forward progress. + * + * If emulation fails for a write to guest page tables, KVM unprotects + * (zaps) the shadow page for the target gfn and resumes the guest to + * retry the non-emulatable instruction (on hardware). Unprotecting the + * gfn doesn't allow forward progress for a self-changing access because + * doing so also zaps the translation for the gfn, i.e. retrying the + * instruction will hit a !PRESENT fault, which results in a new shadow + * page and sends KVM back to square one. */ bool write_fault_to_shadow_pgtable; diff --git a/arch/x86/kernel/ima_arch.c b/arch/x86/kernel/ima_arch.c index 4d4f5d9faac3..23054909c8dd 100644 --- a/arch/x86/kernel/ima_arch.c +++ b/arch/x86/kernel/ima_arch.c @@ -10,8 +10,6 @@ extern struct boot_params boot_params; static enum efi_secureboot_mode get_sb_mode(void) { - efi_char16_t efi_SecureBoot_name[] = L"SecureBoot"; - efi_char16_t efi_SetupMode_name[] = L"SecureBoot"; efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID; efi_status_t status; unsigned long size; @@ -25,7 +23,7 @@ static enum efi_secureboot_mode get_sb_mode(void) } /* Get variable contents into buffer */ - status = efi.get_variable(efi_SecureBoot_name, &efi_variable_guid, + status = efi.get_variable(L"SecureBoot", &efi_variable_guid, NULL, &size, &secboot); if (status == EFI_NOT_FOUND) { pr_info("ima: secureboot mode disabled\n"); @@ -38,7 +36,7 @@ static enum efi_secureboot_mode get_sb_mode(void) } size = sizeof(setupmode); - status = efi.get_variable(efi_SetupMode_name, &efi_variable_guid, + status = efi.get_variable(L"SetupMode", &efi_variable_guid, NULL, &size, &setupmode); if (status != EFI_SUCCESS) /* ignore unknown SetupMode */ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index eafc631d305c..afcd30d44cbb 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1080,9 +1080,6 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, result = 1; /* assumes that there are only KVM_APIC_INIT/SIPI */ apic->pending_events = (1UL << KVM_APIC_INIT); - /* make sure pending_events is visible before sending - * the request */ - smp_wmb(); kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); } diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index d55674f44a18..a647601c9e1c 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -102,6 +102,19 @@ static inline void kvm_mmu_load_cr3(struct kvm_vcpu *vcpu) kvm_get_active_pcid(vcpu)); } +int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, + bool prefault); + +static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + u32 err, bool prefault) +{ +#ifdef CONFIG_RETPOLINE + if (likely(vcpu->arch.mmu->page_fault == kvm_tdp_page_fault)) + return kvm_tdp_page_fault(vcpu, cr2_or_gpa, err, prefault); +#endif + return vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa, err, prefault); +} + /* * Currently, we have two sorts of write-protection, a) the first one * write-protects guest page to sync the guest modification, b) another one is diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 7011a4e54866..87e9ba27ada1 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4219,8 +4219,8 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, } EXPORT_SYMBOL_GPL(kvm_handle_page_fault); -static int tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, - bool prefault) +int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, + bool prefault) { int max_level; @@ -4925,7 +4925,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) return; context->mmu_role.as_u64 = new_role.as_u64; - context->page_fault = tdp_page_fault; + context->page_fault = kvm_tdp_page_fault; context->sync_page = nonpaging_sync_page; context->invlpg = nonpaging_invlpg; context->update_pte = nonpaging_update_pte; @@ -5436,9 +5436,8 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, } if (r == RET_PF_INVALID) { - r = vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa, - lower_32_bits(error_code), - false); + r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa, + lower_32_bits(error_code), false); WARN_ON(r == RET_PF_INVALID); } diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 4e1ef0473663..e4c8a4cbf407 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -33,7 +33,7 @@ #define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT #define PT_HAVE_ACCESSED_DIRTY(mmu) true #ifdef CONFIG_X86_64 - #define PT_MAX_FULL_LEVELS 4 + #define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL #define CMPXCHG cmpxchg #else #define CMPXCHG cmpxchg64 diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index a3e32d61d60c..bef0ba35f121 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -2175,7 +2175,6 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u32 dummy; u32 eax = 1; - vcpu->arch.microcode_version = 0x01000065; svm->spec_ctrl = 0; svm->virt_spec_ctrl = 0; @@ -2266,6 +2265,7 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) init_vmcb(svm); svm_init_osvw(vcpu); + vcpu->arch.microcode_version = 0x01000065; return 0; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 657c2eda357c..3589cd3c0fcc 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -544,7 +544,8 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1, } } -static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) { +static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) +{ int msr; for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { @@ -1981,7 +1982,7 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu, } /* - * Clean fields data can't de used on VMLAUNCH and when we switch + * Clean fields data can't be used on VMLAUNCH and when we switch * between different L2 guests as KVM keeps a single VMCS12 per L1. */ if (from_launch || evmcs_gpa_changed) @@ -3575,6 +3576,33 @@ static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu, nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual); } +/* + * Returns true if a debug trap is pending delivery. + * + * In KVM, debug traps bear an exception payload. As such, the class of a #DB + * exception may be inferred from the presence of an exception payload. + */ +static inline bool vmx_pending_dbg_trap(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.exception.pending && + vcpu->arch.exception.nr == DB_VECTOR && + vcpu->arch.exception.payload; +} + +/* + * Certain VM-exits set the 'pending debug exceptions' field to indicate a + * recognized #DB (data or single-step) that has yet to be delivered. Since KVM + * represents these debug traps with a payload that is said to be compatible + * with the 'pending debug exceptions' field, write the payload to the VMCS + * field if a VM-exit is delivered before the debug trap. + */ +static void nested_vmx_update_pending_dbg(struct kvm_vcpu *vcpu) +{ + if (vmx_pending_dbg_trap(vcpu)) + vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, + vcpu->arch.exception.payload); +} + static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3587,6 +3615,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) test_bit(KVM_APIC_INIT, &apic->pending_events)) { if (block_nested_events) return -EBUSY; + nested_vmx_update_pending_dbg(vcpu); clear_bit(KVM_APIC_INIT, &apic->pending_events); nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0); return 0; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 9a6664886f2e..3be25ecae145 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2947,6 +2947,9 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) static int get_ept_level(struct kvm_vcpu *vcpu) { + /* Nested EPT currently only supports 4-level walks. */ + if (is_guest_mode(vcpu) && nested_cpu_has_ept(get_vmcs12(vcpu))) + return 4; if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48)) return 5; return 4; @@ -4238,7 +4241,6 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmx->msr_ia32_umwait_control = 0; - vcpu->arch.microcode_version = 0x100000000ULL; vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); vmx->hv_deadline_tsc = -1; kvm_set_cr8(vcpu, 0); @@ -6763,6 +6765,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; + vcpu->arch.microcode_version = 0x100000000ULL; vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED; /* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index fbabb2f06273..fb5d64ebc35d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -438,6 +438,14 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu) * for #DB exceptions under VMX. */ vcpu->arch.dr6 ^= payload & DR6_RTM; + + /* + * The #DB payload is defined as compatible with the 'pending + * debug exceptions' field under VMX, not DR6. While bit 12 is + * defined in the 'pending debug exceptions' field (enabled + * breakpoint), it is reserved and must be zero in DR6. + */ + vcpu->arch.dr6 &= ~BIT(12); break; case PF_VECTOR: vcpu->arch.cr2 = payload; @@ -490,19 +498,7 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, vcpu->arch.exception.error_code = error_code; vcpu->arch.exception.has_payload = has_payload; vcpu->arch.exception.payload = payload; - /* - * In guest mode, payload delivery should be deferred, - * so that the L1 hypervisor can intercept #PF before - * CR2 is modified (or intercept #DB before DR6 is - * modified under nVMX). However, for ABI - * compatibility with KVM_GET_VCPU_EVENTS and - * KVM_SET_VCPU_EVENTS, we can't delay payload - * delivery unless userspace has enabled this - * functionality via the per-VM capability, - * KVM_CAP_EXCEPTION_PAYLOAD. - */ - if (!vcpu->kvm->arch.exception_payload_enabled || - !is_guest_mode(vcpu)) + if (!is_guest_mode(vcpu)) kvm_deliver_exception_payload(vcpu); return; } @@ -2448,7 +2444,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) vcpu->hv_clock.tsc_timestamp = tsc_timestamp; vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset; vcpu->last_guest_tsc = tsc_timestamp; - WARN_ON(vcpu->hv_clock.system_time < 0); + WARN_ON((s64)vcpu->hv_clock.system_time < 0); /* If the host uses TSC clocksource, then it is stable */ pvclock_flags = 0; @@ -3796,6 +3792,21 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, process_nmi(vcpu); /* + * In guest mode, payload delivery should be deferred, + * so that the L1 hypervisor can intercept #PF before + * CR2 is modified (or intercept #DB before DR6 is + * modified under nVMX). Unless the per-VM capability, + * KVM_CAP_EXCEPTION_PAYLOAD, is set, we may not defer the delivery of + * an exception payload and handle after a KVM_GET_VCPU_EVENTS. Since we + * opportunistically defer the exception payload, deliver it if the + * capability hasn't been requested before processing a + * KVM_GET_VCPU_EVENTS. + */ + if (!vcpu->kvm->arch.exception_payload_enabled && + vcpu->arch.exception.pending && vcpu->arch.exception.has_payload) + kvm_deliver_exception_payload(vcpu); + + /* * The API doesn't provide the instruction length for software * exceptions, so don't report them. As long as the guest RIP * isn't advanced, we should expect to encounter the exception @@ -8942,7 +8953,6 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, kvm_rip_write(vcpu, ctxt->eip); kvm_set_rflags(vcpu, ctxt->eflags); - kvm_make_request(KVM_REQ_EVENT, vcpu); return 1; } EXPORT_SYMBOL_GPL(kvm_task_switch); @@ -10182,7 +10192,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu)) return; - vcpu->arch.mmu->page_fault(vcpu, work->cr2_or_gpa, 0, true); + kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true); } static inline u32 kvm_async_pf_hash_fn(gfn_t gfn) diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 1f756ffffe8b..79409120a603 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -896,14 +896,15 @@ static u64 xen_read_msr_safe(unsigned int msr, int *err) static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) { int ret; +#ifdef CONFIG_X86_64 + unsigned int which; + u64 base; +#endif ret = 0; switch (msr) { #ifdef CONFIG_X86_64 - unsigned which; - u64 base; - case MSR_FS_BASE: which = SEGBASE_FS; goto set; case MSR_KERNEL_GS_BASE: which = SEGBASE_GS_USER; goto set; case MSR_GS_BASE: which = SEGBASE_GS_KERNEL; goto set; diff --git a/crypto/hash_info.c b/crypto/hash_info.c index c754cb75dd1a..a49ff96bde77 100644 --- a/crypto/hash_info.c +++ b/crypto/hash_info.c @@ -26,7 +26,7 @@ const char *const hash_algo_name[HASH_ALGO__LAST] = { [HASH_ALGO_TGR_128] = "tgr128", [HASH_ALGO_TGR_160] = "tgr160", [HASH_ALGO_TGR_192] = "tgr192", - [HASH_ALGO_SM3_256] = "sm3-256", + [HASH_ALGO_SM3_256] = "sm3", [HASH_ALGO_STREEBOG_256] = "streebog256", [HASH_ALGO_STREEBOG_512] = "streebog512", }; diff --git a/drivers/acpi/acpica/evevent.c b/drivers/acpi/acpica/evevent.c index 8c83d8c620dc..789d5e920aaf 100644 --- a/drivers/acpi/acpica/evevent.c +++ b/drivers/acpi/acpica/evevent.c @@ -265,4 +265,49 @@ static u32 acpi_ev_fixed_event_dispatch(u32 event) handler) (acpi_gbl_fixed_event_handlers[event].context)); } +/******************************************************************************* + * + * FUNCTION: acpi_any_fixed_event_status_set + * + * PARAMETERS: None + * + * RETURN: TRUE or FALSE + * + * DESCRIPTION: Checks the PM status register for active fixed events + * + ******************************************************************************/ + +u32 acpi_any_fixed_event_status_set(void) +{ + acpi_status status; + u32 in_status; + u32 in_enable; + u32 i; + + status = acpi_hw_register_read(ACPI_REGISTER_PM1_ENABLE, &in_enable); + if (ACPI_FAILURE(status)) { + return (FALSE); + } + + status = acpi_hw_register_read(ACPI_REGISTER_PM1_STATUS, &in_status); + if (ACPI_FAILURE(status)) { + return (FALSE); + } + + /* + * Check for all possible Fixed Events and dispatch those that are active + */ + for (i = 0; i < ACPI_NUM_FIXED_EVENTS; i++) { + + /* Both the status and enable bits must be on for this event */ + + if ((in_status & acpi_gbl_fixed_event_info[i].status_bit_mask) && + (in_enable & acpi_gbl_fixed_event_info[i].enable_bit_mask)) { + return (TRUE); + } + } + + return (FALSE); +} + #endif /* !ACPI_REDUCED_HARDWARE */ diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 152f7fc0b200..e5f95922bc21 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -1006,6 +1006,13 @@ static bool acpi_s2idle_wake(void) return true; /* + * If the status bit of any enabled fixed event is set, the + * wakeup is regarded as valid. + */ + if (acpi_any_fixed_event_status_set()) + return true; + + /* * If there are no EC events to process and at least one of the * other enabled GPEs is active, the wakeup is regarded as a * genuine one. diff --git a/drivers/char/ipmi/ipmb_dev_int.c b/drivers/char/ipmi/ipmb_dev_int.c index 1ff4fb1def7c..382b28f1cf2f 100644 --- a/drivers/char/ipmi/ipmb_dev_int.c +++ b/drivers/char/ipmi/ipmb_dev_int.c @@ -19,7 +19,7 @@ #include <linux/spinlock.h> #include <linux/wait.h> -#define MAX_MSG_LEN 128 +#define MAX_MSG_LEN 240 #define IPMB_REQUEST_LEN_MIN 7 #define NETFN_RSP_BIT_MASK 0x4 #define REQUEST_QUEUE_MAX_LEN 256 @@ -63,6 +63,7 @@ struct ipmb_dev { spinlock_t lock; wait_queue_head_t wait_queue; struct mutex file_mutex; + bool is_i2c_protocol; }; static inline struct ipmb_dev *to_ipmb_dev(struct file *file) @@ -112,6 +113,25 @@ static ssize_t ipmb_read(struct file *file, char __user *buf, size_t count, return ret < 0 ? ret : count; } +static int ipmb_i2c_write(struct i2c_client *client, u8 *msg, u8 addr) +{ + struct i2c_msg i2c_msg; + + /* + * subtract 1 byte (rq_sa) from the length of the msg passed to + * raw i2c_transfer + */ + i2c_msg.len = msg[IPMB_MSG_LEN_IDX] - 1; + + /* Assign message to buffer except first 2 bytes (length and address) */ + i2c_msg.buf = msg + 2; + + i2c_msg.addr = addr; + i2c_msg.flags = client->flags & I2C_CLIENT_PEC; + + return i2c_transfer(client->adapter, &i2c_msg, 1); +} + static ssize_t ipmb_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { @@ -133,6 +153,12 @@ static ssize_t ipmb_write(struct file *file, const char __user *buf, rq_sa = GET_7BIT_ADDR(msg[RQ_SA_8BIT_IDX]); netf_rq_lun = msg[NETFN_LUN_IDX]; + /* Check i2c block transfer vs smbus */ + if (ipmb_dev->is_i2c_protocol) { + ret = ipmb_i2c_write(ipmb_dev->client, msg, rq_sa); + return (ret == 1) ? count : ret; + } + /* * subtract rq_sa and netf_rq_lun from the length of the msg passed to * i2c_smbus_xfer @@ -253,7 +279,7 @@ static int ipmb_slave_cb(struct i2c_client *client, break; case I2C_SLAVE_WRITE_RECEIVED: - if (ipmb_dev->msg_idx >= sizeof(struct ipmb_msg)) + if (ipmb_dev->msg_idx >= sizeof(struct ipmb_msg) - 1) break; buf[++ipmb_dev->msg_idx] = *val; @@ -302,6 +328,9 @@ static int ipmb_probe(struct i2c_client *client, if (ret) return ret; + ipmb_dev->is_i2c_protocol + = device_property_read_bool(&client->dev, "i2c-protocol"); + ipmb_dev->client = client; i2c_set_clientdata(client, ipmb_dev); ret = i2c_slave_register(client, ipmb_slave_cb); diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index 22c6a2e61236..8ac390c2b514 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -775,10 +775,14 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result, flags = ipmi_ssif_lock_cond(ssif_info, &oflags); msg = ssif_info->curr_msg; if (msg) { + if (data) { + if (len > IPMI_MAX_MSG_LENGTH) + len = IPMI_MAX_MSG_LENGTH; + memcpy(msg->rsp, data, len); + } else { + len = 0; + } msg->rsp_size = len; - if (msg->rsp_size > IPMI_MAX_MSG_LENGTH) - msg->rsp_size = IPMI_MAX_MSG_LENGTH; - memcpy(msg->rsp, data, msg->rsp_size); ssif_info->curr_msg = NULL; } diff --git a/drivers/char/tpm/Makefile b/drivers/char/tpm/Makefile index 5a0d99d4fec0..9567e5197f74 100644 --- a/drivers/char/tpm/Makefile +++ b/drivers/char/tpm/Makefile @@ -21,9 +21,11 @@ tpm-$(CONFIG_EFI) += eventlog/efi.o tpm-$(CONFIG_OF) += eventlog/of.o obj-$(CONFIG_TCG_TIS_CORE) += tpm_tis_core.o obj-$(CONFIG_TCG_TIS) += tpm_tis.o -obj-$(CONFIG_TCG_TIS_SPI) += tpm_tis_spi_mod.o -tpm_tis_spi_mod-y := tpm_tis_spi.o -tpm_tis_spi_mod-$(CONFIG_TCG_TIS_SPI_CR50) += tpm_tis_spi_cr50.o + +obj-$(CONFIG_TCG_TIS_SPI) += tpm_tis_spi.o +tpm_tis_spi-y := tpm_tis_spi_main.o +tpm_tis_spi-$(CONFIG_TCG_TIS_SPI_CR50) += tpm_tis_spi_cr50.o + obj-$(CONFIG_TCG_TIS_I2C_ATMEL) += tpm_i2c_atmel.o obj-$(CONFIG_TCG_TIS_I2C_INFINEON) += tpm_i2c_infineon.o obj-$(CONFIG_TCG_TIS_I2C_NUVOTON) += tpm_i2c_nuvoton.o diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index 13696deceae8..760329598b99 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -525,6 +525,8 @@ static int tpm2_init_bank_info(struct tpm_chip *chip, u32 bank_index) return 0; } + bank->crypto_id = HASH_ALGO__LAST; + return tpm2_pcr_read(chip, 0, &digest, &bank->digest_size); } diff --git a/drivers/char/tpm/tpm_tis_spi.c b/drivers/char/tpm/tpm_tis_spi_main.c index d1754fd6c573..d1754fd6c573 100644 --- a/drivers/char/tpm/tpm_tis_spi.c +++ b/drivers/char/tpm/tpm_tis_spi_main.c diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index 7243b88f81d8..69e0d90460e6 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -505,16 +505,10 @@ void edac_mc_free(struct mem_ctl_info *mci) { edac_dbg(1, "\n"); - /* If we're not yet registered with sysfs free only what was allocated - * in edac_mc_alloc(). - */ - if (!device_is_registered(&mci->dev)) { - _edac_mc_free(mci); - return; - } + if (device_is_registered(&mci->dev)) + edac_unregister_sysfs(mci); - /* the mci instance is freed here, when the sysfs object is dropped */ - edac_unregister_sysfs(mci); + _edac_mc_free(mci); } EXPORT_SYMBOL_GPL(edac_mc_free); diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index 0367554e7437..c70ec0a306d8 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -276,10 +276,7 @@ static const struct attribute_group *csrow_attr_groups[] = { static void csrow_attr_release(struct device *dev) { - struct csrow_info *csrow = container_of(dev, struct csrow_info, dev); - - edac_dbg(1, "device %s released\n", dev_name(dev)); - kfree(csrow); + /* release device with _edac_mc_free() */ } static const struct device_type csrow_attr_type = { @@ -447,8 +444,7 @@ error: csrow = mci->csrows[i]; if (!nr_pages_per_csrow(csrow)) continue; - - device_del(&mci->csrows[i]->dev); + device_unregister(&mci->csrows[i]->dev); } return err; @@ -608,10 +604,7 @@ static const struct attribute_group *dimm_attr_groups[] = { static void dimm_attr_release(struct device *dev) { - struct dimm_info *dimm = container_of(dev, struct dimm_info, dev); - - edac_dbg(1, "device %s released\n", dev_name(dev)); - kfree(dimm); + /* release device with _edac_mc_free() */ } static const struct device_type dimm_attr_type = { @@ -893,10 +886,7 @@ static const struct attribute_group *mci_attr_groups[] = { static void mci_attr_release(struct device *dev) { - struct mem_ctl_info *mci = container_of(dev, struct mem_ctl_info, dev); - - edac_dbg(1, "device %s released\n", dev_name(dev)); - kfree(mci); + /* release device with _edac_mc_free() */ } static const struct device_type mci_attr_type = { diff --git a/drivers/fsi/Kconfig b/drivers/fsi/Kconfig index 92ce6d85802c..4cc0e630ab79 100644 --- a/drivers/fsi/Kconfig +++ b/drivers/fsi/Kconfig @@ -55,6 +55,7 @@ config FSI_MASTER_AST_CF config FSI_MASTER_ASPEED tristate "FSI ASPEED master" + depends on HAS_IOMEM help This option enables a FSI master that is present behind an OPB bridge in the AST2600. diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 3a1570dafe34..146f96661b6b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -1013,6 +1013,30 @@ static int psp_dtm_initialize(struct psp_context *psp) return 0; } +static int psp_dtm_unload(struct psp_context *psp) +{ + int ret; + struct psp_gfx_cmd_resp *cmd; + + /* + * TODO: bypass the unloading in sriov for now + */ + if (amdgpu_sriov_vf(psp->adev)) + return 0; + + cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL); + if (!cmd) + return -ENOMEM; + + psp_prep_ta_unload_cmd_buf(cmd, psp->dtm_context.session_id); + + ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr); + + kfree(cmd); + + return ret; +} + int psp_dtm_invoke(struct psp_context *psp, uint32_t ta_cmd_id) { /* @@ -1037,7 +1061,7 @@ static int psp_dtm_terminate(struct psp_context *psp) if (!psp->dtm_context.dtm_initialized) return 0; - ret = psp_hdcp_unload(psp); + ret = psp_dtm_unload(psp); if (ret) return ret; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 1785fdad6ecb..22bbb36c768e 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -3923,11 +3923,13 @@ static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev) { uint64_t clock; + amdgpu_gfx_off_ctrl(adev, false); mutex_lock(&adev->gfx.gpu_clock_mutex); WREG32_SOC15(GC, 0, mmRLC_CAPTURE_GPU_CLOCK_COUNT, 1); clock = (uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_LSB) | ((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL); mutex_unlock(&adev->gfx.gpu_clock_mutex); + amdgpu_gfx_off_ctrl(adev, true); return clock; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index b33a4eb39193..3afdbbd6aaad 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1193,6 +1193,14 @@ static bool gfx_v9_0_should_disable_gfxoff(struct pci_dev *pdev) return false; } +static bool is_raven_kicker(struct amdgpu_device *adev) +{ + if (adev->pm.fw_version >= 0x41e2b) + return true; + else + return false; +} + static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev) { if (gfx_v9_0_should_disable_gfxoff(adev->pdev)) @@ -1205,9 +1213,8 @@ static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev) break; case CHIP_RAVEN: if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8) && - ((adev->gfx.rlc_fw_version != 106 && + ((!is_raven_kicker(adev) && adev->gfx.rlc_fw_version < 531) || - (adev->gfx.rlc_fw_version == 53815) || (adev->gfx.rlc_feature_version < 1) || !adev->gfx.rlc.is_rlc_v2_1)) adev->pm.pp_feature &= ~PP_GFXOFF_MASK; @@ -3959,6 +3966,7 @@ static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev) { uint64_t clock; + amdgpu_gfx_off_ctrl(adev, false); mutex_lock(&adev->gfx.gpu_clock_mutex); if (adev->asic_type == CHIP_VEGA10 && amdgpu_sriov_runtime(adev)) { uint32_t tmp, lsb, msb, i = 0; @@ -3977,6 +3985,7 @@ static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev) ((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL); } mutex_unlock(&adev->gfx.gpu_clock_mutex); + amdgpu_gfx_off_ctrl(adev, true); return clock; } diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 15f3424a1ff7..2b488dfb2f21 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -272,7 +272,12 @@ static u32 soc15_get_config_memsize(struct amdgpu_device *adev) static u32 soc15_get_xclk(struct amdgpu_device *adev) { - return adev->clock.spll.reference_freq; + u32 reference_clock = adev->clock.spll.reference_freq; + + if (adev->asic_type == CHIP_RAVEN) + return reference_clock / 4; + + return reference_clock; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 63e8a12a74bc..e8f66fbf399e 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1911,7 +1911,7 @@ static void handle_hpd_irq(void *param) mutex_lock(&aconnector->hpd_lock); #ifdef CONFIG_DRM_AMD_DC_HDCP - if (adev->asic_type >= CHIP_RAVEN) + if (adev->dm.hdcp_workqueue) hdcp_reset_display(adev->dm.hdcp_workqueue, aconnector->dc_link->link_index); #endif if (aconnector->fake_enable) @@ -2088,8 +2088,10 @@ static void handle_hpd_rx_irq(void *param) } } #ifdef CONFIG_DRM_AMD_DC_HDCP - if (hpd_irq_data.bytes.device_service_irq.bits.CP_IRQ) - hdcp_handle_cpirq(adev->dm.hdcp_workqueue, aconnector->base.index); + if (hpd_irq_data.bytes.device_service_irq.bits.CP_IRQ) { + if (adev->dm.hdcp_workqueue) + hdcp_handle_cpirq(adev->dm.hdcp_workqueue, aconnector->base.index); + } #endif if ((dc_link->cur_link_settings.lane_count != LANE_COUNT_UNKNOWN) || (dc_link->type == dc_connection_mst_branch)) @@ -5702,7 +5704,7 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm, drm_connector_attach_vrr_capable_property( &aconnector->base); #ifdef CONFIG_DRM_AMD_DC_HDCP - if (adev->asic_type >= CHIP_RAVEN) + if (adev->dm.hdcp_workqueue) drm_connector_attach_content_protection_property(&aconnector->base, true); #endif } diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c index f730b94ac3c0..55246711700b 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c @@ -46,8 +46,8 @@ static inline enum mod_hdcp_status check_hdcp2_capable(struct mod_hdcp *hdcp) enum mod_hdcp_status status; if (is_dp_hdcp(hdcp)) - status = (hdcp->auth.msg.hdcp2.rxcaps_dp[2] & HDCP_2_2_RX_CAPS_VERSION_VAL) && - HDCP_2_2_DP_HDCP_CAPABLE(hdcp->auth.msg.hdcp2.rxcaps_dp[0]) ? + status = (hdcp->auth.msg.hdcp2.rxcaps_dp[0] == HDCP_2_2_RX_CAPS_VERSION_VAL) && + HDCP_2_2_DP_HDCP_CAPABLE(hdcp->auth.msg.hdcp2.rxcaps_dp[2]) ? MOD_HDCP_STATUS_SUCCESS : MOD_HDCP_STATUS_HDCP2_NOT_CAPABLE; else diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c index 0dc49479a7eb..b06c057a9002 100644 --- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c +++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c @@ -898,6 +898,9 @@ int smu_v11_0_system_features_control(struct smu_context *smu, if (ret) return ret; + bitmap_zero(feature->enabled, feature->feature_num); + bitmap_zero(feature->supported, feature->feature_num); + if (en) { ret = smu_feature_get_enabled_mask(smu, feature_mask, 2); if (ret) @@ -907,9 +910,6 @@ int smu_v11_0_system_features_control(struct smu_context *smu, feature->feature_num); bitmap_copy(feature->supported, (unsigned long *)&feature_mask, feature->feature_num); - } else { - bitmap_zero(feature->enabled, feature->feature_num); - bitmap_zero(feature->supported, feature->feature_num); } return ret; diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c index 3709e5ace724..fbdb42d4e772 100644 --- a/drivers/gpu/drm/bridge/tc358767.c +++ b/drivers/gpu/drm/bridge/tc358767.c @@ -297,7 +297,7 @@ static inline int tc_poll_timeout(struct tc_data *tc, unsigned int addr, static int tc_aux_wait_busy(struct tc_data *tc) { - return tc_poll_timeout(tc, DP0_AUXSTATUS, AUX_BUSY, 0, 1000, 100000); + return tc_poll_timeout(tc, DP0_AUXSTATUS, AUX_BUSY, 0, 100, 100000); } static int tc_aux_write_data(struct tc_data *tc, const void *data, @@ -640,7 +640,7 @@ static int tc_aux_link_setup(struct tc_data *tc) if (ret) goto err; - ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 1, 1000); + ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 100, 100000); if (ret == -ETIMEDOUT) { dev_err(tc->dev, "Timeout waiting for PHY to become ready"); return ret; @@ -876,7 +876,7 @@ static int tc_wait_link_training(struct tc_data *tc) int ret; ret = tc_poll_timeout(tc, DP0_LTSTAT, LT_LOOPDONE, - LT_LOOPDONE, 1, 1000); + LT_LOOPDONE, 500, 100000); if (ret) { dev_err(tc->dev, "Link training timeout waiting for LT_LOOPDONE!\n"); return ret; @@ -949,7 +949,7 @@ static int tc_main_link_enable(struct tc_data *tc) dp_phy_ctrl &= ~(DP_PHY_RST | PHY_M1_RST | PHY_M0_RST); ret = regmap_write(tc->regmap, DP_PHY_CTRL, dp_phy_ctrl); - ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 1, 1000); + ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 500, 100000); if (ret) { dev_err(dev, "timeout waiting for phy become ready"); return ret; diff --git a/drivers/gpu/drm/bridge/ti-tfp410.c b/drivers/gpu/drm/bridge/ti-tfp410.c index 6f6d6d1e60ae..f195a4732e0b 100644 --- a/drivers/gpu/drm/bridge/ti-tfp410.c +++ b/drivers/gpu/drm/bridge/ti-tfp410.c @@ -140,7 +140,8 @@ static int tfp410_attach(struct drm_bridge *bridge) dvi->connector_type, dvi->ddc); if (ret) { - dev_err(dvi->dev, "drm_connector_init() failed: %d\n", ret); + dev_err(dvi->dev, "drm_connector_init_with_ddc() failed: %d\n", + ret); return ret; } diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c index 6d4a29e99ae2..3035584f6dc7 100644 --- a/drivers/gpu/drm/drm_client_modeset.c +++ b/drivers/gpu/drm/drm_client_modeset.c @@ -951,7 +951,8 @@ bool drm_client_rotation(struct drm_mode_set *modeset, unsigned int *rotation) * depending on the hardware this may require the framebuffer * to be in a specific tiling format. */ - if ((*rotation & DRM_MODE_ROTATE_MASK) != DRM_MODE_ROTATE_180 || + if (((*rotation & DRM_MODE_ROTATE_MASK) != DRM_MODE_ROTATE_0 && + (*rotation & DRM_MODE_ROTATE_MASK) != DRM_MODE_ROTATE_180) || !plane->rotation_property) return false; diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index 10336b144c72..d4d64518e11b 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -1698,6 +1698,13 @@ static int drm_mode_parse_cmdline_options(const char *str, if (rotation && freestanding) return -EINVAL; + if (!(rotation & DRM_MODE_ROTATE_MASK)) + rotation |= DRM_MODE_ROTATE_0; + + /* Make sure there is exactly one rotation defined */ + if (!is_power_of_2(rotation & DRM_MODE_ROTATE_MASK)) + return -EINVAL; + mode->rotation_reflection = rotation; return 0; diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig index ba9595960bbe..907c4471f591 100644 --- a/drivers/gpu/drm/i915/Kconfig +++ b/drivers/gpu/drm/i915/Kconfig @@ -75,9 +75,8 @@ config DRM_I915_CAPTURE_ERROR help This option enables capturing the GPU state when a hang is detected. This information is vital for triaging hangs and assists in debugging. - Please report any hang to - https://bugs.freedesktop.org/enter_bug.cgi?product=DRI - for triaging. + Please report any hang for triaging according to: + https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs If in doubt, say "Y". diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 33f1dc3d7c1a..d9a61f341070 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -4251,7 +4251,9 @@ static bool intel_ddi_is_audio_enabled(struct drm_i915_private *dev_priv, void intel_ddi_compute_min_voltage_level(struct drm_i915_private *dev_priv, struct intel_crtc_state *crtc_state) { - if (INTEL_GEN(dev_priv) >= 11 && crtc_state->port_clock > 594000) + if (IS_ELKHARTLAKE(dev_priv) && crtc_state->port_clock > 594000) + crtc_state->min_voltage_level = 3; + else if (INTEL_GEN(dev_priv) >= 11 && crtc_state->port_clock > 594000) crtc_state->min_voltage_level = 1; else if (IS_CANNONLAKE(dev_priv) && crtc_state->port_clock > 594000) crtc_state->min_voltage_level = 2; diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 064dd99bbc49..aa453953908b 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -11087,7 +11087,7 @@ static u32 intel_cursor_base(const struct intel_plane_state *plane_state) u32 base; if (INTEL_INFO(dev_priv)->display.cursor_needs_physical) - base = obj->phys_handle->busaddr; + base = sg_dma_address(obj->mm.pages->sgl); else base = intel_plane_ggtt_offset(plane_state); @@ -17433,6 +17433,24 @@ retry: * have readout for pipe gamma enable. */ crtc_state->uapi.color_mgmt_changed = true; + + /* + * FIXME hack to force full modeset when DSC is being + * used. + * + * As long as we do not have full state readout and + * config comparison of crtc_state->dsc, we have no way + * to ensure reliable fastset. Remove once we have + * readout for DSC. + */ + if (crtc_state->dsc.compression_enable) { + ret = drm_atomic_add_affected_connectors(state, + &crtc->base); + if (ret) + goto out; + crtc_state->uapi.mode_changed = true; + drm_dbg_kms(dev, "Force full modeset for DSC\n"); + } } } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index a2e57e62af30..151a1e8ae36a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -565,6 +565,22 @@ static int __context_set_persistence(struct i915_gem_context *ctx, bool state) if (!(ctx->i915->caps.scheduler & I915_SCHEDULER_CAP_PREEMPTION)) return -ENODEV; + /* + * If the cancel fails, we then need to reset, cleanly! + * + * If the per-engine reset fails, all hope is lost! We resort + * to a full GPU reset in that unlikely case, but realistically + * if the engine could not reset, the full reset does not fare + * much better. The damage has been done. + * + * However, if we cannot reset an engine by itself, we cannot + * cleanup a hanging persistent context without causing + * colateral damage, and we should not pretend we can by + * exposing the interface. + */ + if (!intel_has_reset_engine(&ctx->i915->gt)) + return -ENODEV; + i915_gem_context_clear_persistence(ctx); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index f64ad77e6b1e..c2174da35bb0 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -285,9 +285,6 @@ struct drm_i915_gem_object { void *gvt_info; }; - - /** for phys allocated objects */ - struct drm_dma_handle *phys_handle; }; static inline struct drm_i915_gem_object * diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c index b1b7c1b3038a..b07bb40edd5a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c @@ -22,88 +22,87 @@ static int i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj) { struct address_space *mapping = obj->base.filp->f_mapping; - struct drm_dma_handle *phys; - struct sg_table *st; struct scatterlist *sg; - char *vaddr; + struct sg_table *st; + dma_addr_t dma; + void *vaddr; + void *dst; int i; - int err; if (WARN_ON(i915_gem_object_needs_bit17_swizzle(obj))) return -EINVAL; - /* Always aligning to the object size, allows a single allocation + /* + * Always aligning to the object size, allows a single allocation * to handle all possible callers, and given typical object sizes, * the alignment of the buddy allocation will naturally match. */ - phys = drm_pci_alloc(obj->base.dev, - roundup_pow_of_two(obj->base.size), - roundup_pow_of_two(obj->base.size)); - if (!phys) + vaddr = dma_alloc_coherent(&obj->base.dev->pdev->dev, + roundup_pow_of_two(obj->base.size), + &dma, GFP_KERNEL); + if (!vaddr) return -ENOMEM; - vaddr = phys->vaddr; + st = kmalloc(sizeof(*st), GFP_KERNEL); + if (!st) + goto err_pci; + + if (sg_alloc_table(st, 1, GFP_KERNEL)) + goto err_st; + + sg = st->sgl; + sg->offset = 0; + sg->length = obj->base.size; + + sg_assign_page(sg, (struct page *)vaddr); + sg_dma_address(sg) = dma; + sg_dma_len(sg) = obj->base.size; + + dst = vaddr; for (i = 0; i < obj->base.size / PAGE_SIZE; i++) { struct page *page; - char *src; + void *src; page = shmem_read_mapping_page(mapping, i); - if (IS_ERR(page)) { - err = PTR_ERR(page); - goto err_phys; - } + if (IS_ERR(page)) + goto err_st; src = kmap_atomic(page); - memcpy(vaddr, src, PAGE_SIZE); - drm_clflush_virt_range(vaddr, PAGE_SIZE); + memcpy(dst, src, PAGE_SIZE); + drm_clflush_virt_range(dst, PAGE_SIZE); kunmap_atomic(src); put_page(page); - vaddr += PAGE_SIZE; + dst += PAGE_SIZE; } intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt); - st = kmalloc(sizeof(*st), GFP_KERNEL); - if (!st) { - err = -ENOMEM; - goto err_phys; - } - - if (sg_alloc_table(st, 1, GFP_KERNEL)) { - kfree(st); - err = -ENOMEM; - goto err_phys; - } - - sg = st->sgl; - sg->offset = 0; - sg->length = obj->base.size; - - sg_dma_address(sg) = phys->busaddr; - sg_dma_len(sg) = obj->base.size; - - obj->phys_handle = phys; - __i915_gem_object_set_pages(obj, st, sg->length); return 0; -err_phys: - drm_pci_free(obj->base.dev, phys); - - return err; +err_st: + kfree(st); +err_pci: + dma_free_coherent(&obj->base.dev->pdev->dev, + roundup_pow_of_two(obj->base.size), + vaddr, dma); + return -ENOMEM; } static void i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj, struct sg_table *pages) { + dma_addr_t dma = sg_dma_address(pages->sgl); + void *vaddr = sg_page(pages->sgl); + __i915_gem_object_release_shmem(obj, pages, false); if (obj->mm.dirty) { struct address_space *mapping = obj->base.filp->f_mapping; - char *vaddr = obj->phys_handle->vaddr; + void *src = vaddr; int i; for (i = 0; i < obj->base.size / PAGE_SIZE; i++) { @@ -115,15 +114,16 @@ i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj, continue; dst = kmap_atomic(page); - drm_clflush_virt_range(vaddr, PAGE_SIZE); - memcpy(dst, vaddr, PAGE_SIZE); + drm_clflush_virt_range(src, PAGE_SIZE); + memcpy(dst, src, PAGE_SIZE); kunmap_atomic(dst); set_page_dirty(page); if (obj->mm.madv == I915_MADV_WILLNEED) mark_page_accessed(page); put_page(page); - vaddr += PAGE_SIZE; + + src += PAGE_SIZE; } obj->mm.dirty = false; } @@ -131,7 +131,9 @@ i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj, sg_free_table(pages); kfree(pages); - drm_pci_free(obj->base.dev, obj->phys_handle); + dma_free_coherent(&obj->base.dev->pdev->dev, + roundup_pow_of_two(obj->base.size), + vaddr, dma); } static void phys_release(struct drm_i915_gem_object *obj) diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c index 0ba524a414c6..cbad7fe722ce 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c @@ -136,6 +136,9 @@ static void add_retire(struct intel_breadcrumbs *b, struct intel_timeline *tl) struct intel_engine_cs *engine = container_of(b, struct intel_engine_cs, breadcrumbs); + if (unlikely(intel_engine_is_virtual(engine))) + engine = intel_virtual_engine_get_sibling(engine, 0); + intel_engine_add_retire(engine, tl); } diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c index 7ef1d37970f6..8a5054f21bf8 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c @@ -99,6 +99,9 @@ static bool add_retire(struct intel_engine_cs *engine, void intel_engine_add_retire(struct intel_engine_cs *engine, struct intel_timeline *tl) { + /* We don't deal well with the engine disappearing beneath us */ + GEM_BUG_ON(intel_engine_is_virtual(engine)); + if (add_retire(engine, tl)) schedule_work(&engine->retire_work); } diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index a13a8c4b65ab..fe8a59aaa629 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -237,7 +237,8 @@ static void execlists_init_reg_state(u32 *reg_state, bool close); static void __execlists_update_reg_state(const struct intel_context *ce, - const struct intel_engine_cs *engine); + const struct intel_engine_cs *engine, + u32 head); static void mark_eio(struct i915_request *rq) { @@ -1186,12 +1187,11 @@ static void reset_active(struct i915_request *rq, head = rq->tail; else head = active_request(ce->timeline, rq)->head; - ce->ring->head = intel_ring_wrap(ce->ring, head); - intel_ring_update_space(ce->ring); + head = intel_ring_wrap(ce->ring, head); /* Scrub the context image to prevent replaying the previous batch */ restore_default_state(ce, engine); - __execlists_update_reg_state(ce, engine); + __execlists_update_reg_state(ce, engine, head); /* We've switched away, so this should be a no-op, but intent matters */ ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; @@ -1321,7 +1321,7 @@ static u64 execlists_update_context(struct i915_request *rq) { struct intel_context *ce = rq->context; u64 desc = ce->lrc_desc; - u32 tail; + u32 tail, prev; /* * WaIdleLiteRestore:bdw,skl @@ -1334,9 +1334,15 @@ static u64 execlists_update_context(struct i915_request *rq) * subsequent resubmissions (for lite restore). Should that fail us, * and we try and submit the same tail again, force the context * reload. + * + * If we need to return to a preempted context, we need to skip the + * lite-restore and force it to reload the RING_TAIL. Otherwise, the + * HW has a tendency to ignore us rewinding the TAIL to the end of + * an earlier request. */ tail = intel_ring_set_tail(rq->ring, rq->tail); - if (unlikely(ce->lrc_reg_state[CTX_RING_TAIL] == tail)) + prev = ce->lrc_reg_state[CTX_RING_TAIL]; + if (unlikely(intel_ring_direction(rq->ring, tail, prev) <= 0)) desc |= CTX_DESC_FORCE_RESTORE; ce->lrc_reg_state[CTX_RING_TAIL] = tail; rq->tail = rq->wa_tail; @@ -1605,6 +1611,11 @@ last_active(const struct intel_engine_execlists *execlists) return *last; } +#define for_each_waiter(p__, rq__) \ + list_for_each_entry_lockless(p__, \ + &(rq__)->sched.waiters_list, \ + wait_link) + static void defer_request(struct i915_request *rq, struct list_head * const pl) { LIST_HEAD(list); @@ -1622,7 +1633,7 @@ static void defer_request(struct i915_request *rq, struct list_head * const pl) GEM_BUG_ON(i915_request_is_active(rq)); list_move_tail(&rq->sched.link, pl); - list_for_each_entry(p, &rq->sched.waiters_list, wait_link) { + for_each_waiter(p, rq) { struct i915_request *w = container_of(p->waiter, typeof(*w), sched); @@ -1834,14 +1845,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine) */ __unwind_incomplete_requests(engine); - /* - * If we need to return to the preempted context, we - * need to skip the lite-restore and force it to - * reload the RING_TAIL. Otherwise, the HW has a - * tendency to ignore us rewinding the TAIL to the - * end of an earlier request. - */ - last->context->lrc_desc |= CTX_DESC_FORCE_RESTORE; last = NULL; } else if (need_timeslice(engine, last) && timer_expired(&engine->execlists.timer)) { @@ -2860,16 +2863,17 @@ static void execlists_context_unpin(struct intel_context *ce) static void __execlists_update_reg_state(const struct intel_context *ce, - const struct intel_engine_cs *engine) + const struct intel_engine_cs *engine, + u32 head) { struct intel_ring *ring = ce->ring; u32 *regs = ce->lrc_reg_state; - GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->head)); + GEM_BUG_ON(!intel_ring_offset_valid(ring, head)); GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->tail)); regs[CTX_RING_START] = i915_ggtt_offset(ring->vma); - regs[CTX_RING_HEAD] = ring->head; + regs[CTX_RING_HEAD] = head; regs[CTX_RING_TAIL] = ring->tail; /* RPCS */ @@ -2898,7 +2902,7 @@ __execlists_context_pin(struct intel_context *ce, ce->lrc_desc = lrc_descriptor(ce, engine) | CTX_DESC_FORCE_RESTORE; ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE; - __execlists_update_reg_state(ce, engine); + __execlists_update_reg_state(ce, engine, ce->ring->tail); return 0; } @@ -2939,7 +2943,7 @@ static void execlists_context_reset(struct intel_context *ce) /* Scrub away the garbage */ execlists_init_reg_state(ce->lrc_reg_state, ce, ce->engine, ce->ring, true); - __execlists_update_reg_state(ce, ce->engine); + __execlists_update_reg_state(ce, ce->engine, ce->ring->tail); ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; } @@ -3494,6 +3498,7 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled) struct intel_engine_execlists * const execlists = &engine->execlists; struct intel_context *ce; struct i915_request *rq; + u32 head; mb(); /* paranoia: read the CSB pointers from after the reset */ clflush(execlists->csb_write); @@ -3521,15 +3526,15 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled) if (i915_request_completed(rq)) { /* Idle context; tidy up the ring so we can restart afresh */ - ce->ring->head = intel_ring_wrap(ce->ring, rq->tail); + head = intel_ring_wrap(ce->ring, rq->tail); goto out_replay; } /* Context has requests still in-flight; it should not be idle! */ GEM_BUG_ON(i915_active_is_idle(&ce->active)); rq = active_request(ce->timeline, rq); - ce->ring->head = intel_ring_wrap(ce->ring, rq->head); - GEM_BUG_ON(ce->ring->head == ce->ring->tail); + head = intel_ring_wrap(ce->ring, rq->head); + GEM_BUG_ON(head == ce->ring->tail); /* * If this request hasn't started yet, e.g. it is waiting on a @@ -3574,10 +3579,9 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled) out_replay: ENGINE_TRACE(engine, "replay {head:%04x, tail:%04x}\n", - ce->ring->head, ce->ring->tail); - intel_ring_update_space(ce->ring); + head, ce->ring->tail); __execlists_reset_reg_state(ce, engine); - __execlists_update_reg_state(ce, engine); + __execlists_update_reg_state(ce, engine, head); ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; /* paranoid: GPU was reset! */ unwind: @@ -5220,10 +5224,7 @@ void intel_lr_context_reset(struct intel_engine_cs *engine, restore_default_state(ce, engine); /* Rerun the request; its payload has been neutered (if guilty). */ - ce->ring->head = head; - intel_ring_update_space(ce->ring); - - __execlists_update_reg_state(ce, engine); + __execlists_update_reg_state(ce, engine, head); } bool diff --git a/drivers/gpu/drm/i915/gt/intel_ring.c b/drivers/gpu/drm/i915/gt/intel_ring.c index 374b28f13ca0..6ff803f397c4 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring.c +++ b/drivers/gpu/drm/i915/gt/intel_ring.c @@ -145,6 +145,7 @@ intel_engine_create_ring(struct intel_engine_cs *engine, int size) kref_init(&ring->ref); ring->size = size; + ring->wrap = BITS_PER_TYPE(ring->size) - ilog2(size); /* * Workaround an erratum on the i830 which causes a hang if diff --git a/drivers/gpu/drm/i915/gt/intel_ring.h b/drivers/gpu/drm/i915/gt/intel_ring.h index ea2839d9e044..5bdce24994aa 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring.h +++ b/drivers/gpu/drm/i915/gt/intel_ring.h @@ -56,6 +56,14 @@ static inline u32 intel_ring_wrap(const struct intel_ring *ring, u32 pos) return pos & (ring->size - 1); } +static inline int intel_ring_direction(const struct intel_ring *ring, + u32 next, u32 prev) +{ + typecheck(typeof(ring->size), next); + typecheck(typeof(ring->size), prev); + return (next - prev) << ring->wrap; +} + static inline bool intel_ring_offset_valid(const struct intel_ring *ring, unsigned int pos) diff --git a/drivers/gpu/drm/i915/gt/intel_ring_types.h b/drivers/gpu/drm/i915/gt/intel_ring_types.h index d9f17f38e0cc..1a189ea00fd8 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring_types.h +++ b/drivers/gpu/drm/i915/gt/intel_ring_types.h @@ -39,12 +39,13 @@ struct intel_ring { */ atomic_t pin_count; - u32 head; - u32 tail; - u32 emit; + u32 head; /* updated during retire, loosely tracks RING_HEAD */ + u32 tail; /* updated on submission, used for RING_TAIL */ + u32 emit; /* updated during request construction */ u32 space; u32 size; + u32 wrap; u32 effective_size; }; diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c index 65718ca2326e..b292f8cbd0bf 100644 --- a/drivers/gpu/drm/i915/gt/selftest_lrc.c +++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c @@ -186,7 +186,7 @@ static int live_unlite_restore(struct intel_gt *gt, int prio) } GEM_BUG_ON(!ce[1]->ring->size); intel_ring_reset(ce[1]->ring, ce[1]->ring->size / 2); - __execlists_update_reg_state(ce[1], engine); + __execlists_update_reg_state(ce[1], engine, ce[1]->ring->head); rq[0] = igt_spinner_create_request(&spin, ce[0], MI_ARB_CHECK); if (IS_ERR(rq[0])) { diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index c2de2f45b459..5f6e63952821 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -180,7 +180,7 @@ i915_gem_phys_pwrite(struct drm_i915_gem_object *obj, struct drm_i915_gem_pwrite *args, struct drm_file *file) { - void *vaddr = obj->phys_handle->vaddr + args->offset; + void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset; char __user *user_data = u64_to_user_ptr(args->data_ptr); /* @@ -844,10 +844,10 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data, ret = i915_gem_gtt_pwrite_fast(obj, args); if (ret == -EFAULT || ret == -ENOSPC) { - if (obj->phys_handle) - ret = i915_gem_phys_pwrite(obj, args, file); - else + if (i915_gem_object_has_struct_page(obj)) ret = i915_gem_shmem_pwrite(obj, args); + else + ret = i915_gem_phys_pwrite(obj, args, file); } i915_gem_object_unpin_pages(obj); diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 594341e27a47..9e401a5fcae8 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1852,7 +1852,8 @@ void i915_error_state_store(struct i915_gpu_coredump *error) if (!xchg(&warned, true) && ktime_get_real_seconds() - DRIVER_TIMESTAMP < DAY_AS_SECONDS(180)) { pr_info("GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.\n"); - pr_info("Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel\n"); + pr_info("Please file a _new_ bug report at https://gitlab.freedesktop.org/drm/intel/issues/new.\n"); + pr_info("Please see https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs for details.\n"); pr_info("drm/i915 developers can then reassign to the right component if it's not a kernel issue.\n"); pr_info("The GPU crash dump is required to analyze GPU hangs, so please always attach it.\n"); pr_info("GPU crash dump saved to /sys/class/drm/card%d/error\n", diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 78a5f5d3c070..f56b046a32de 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -595,6 +595,8 @@ static void __i915_request_ctor(void *arg) i915_sw_fence_init(&rq->submit, submit_notify); i915_sw_fence_init(&rq->semaphore, semaphore_notify); + dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock, 0, 0); + rq->file_priv = NULL; rq->capture_list = NULL; @@ -653,25 +655,30 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp) } } - ret = intel_timeline_get_seqno(tl, rq, &seqno); - if (ret) - goto err_free; - rq->i915 = ce->engine->i915; rq->context = ce; rq->engine = ce->engine; rq->ring = ce->ring; rq->execution_mask = ce->engine->mask; + kref_init(&rq->fence.refcount); + rq->fence.flags = 0; + rq->fence.error = 0; + INIT_LIST_HEAD(&rq->fence.cb_list); + + ret = intel_timeline_get_seqno(tl, rq, &seqno); + if (ret) + goto err_free; + + rq->fence.context = tl->fence_context; + rq->fence.seqno = seqno; + RCU_INIT_POINTER(rq->timeline, tl); RCU_INIT_POINTER(rq->hwsp_cacheline, tl->hwsp_cacheline); rq->hwsp_seqno = tl->hwsp_seqno; rq->rcustate = get_state_synchronize_rcu(); /* acts as smp_mb() */ - dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock, - tl->fence_context, seqno); - /* We bump the ref for the fence chain */ i915_sw_fence_reinit(&i915_request_get(rq)->submit); i915_sw_fence_reinit(&i915_request_get(rq)->semaphore); diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c index 5d96cfba40f8..34b654b4e58a 100644 --- a/drivers/gpu/drm/i915/i915_scheduler.c +++ b/drivers/gpu/drm/i915/i915_scheduler.c @@ -423,8 +423,6 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node, if (!node_signaled(signal)) { INIT_LIST_HEAD(&dep->dfs_link); - list_add(&dep->wait_link, &signal->waiters_list); - list_add(&dep->signal_link, &node->signalers_list); dep->signaler = signal; dep->waiter = node; dep->flags = flags; @@ -434,6 +432,10 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node, !node_started(signal)) node->flags |= I915_SCHED_HAS_SEMAPHORE_CHAIN; + /* All set, now publish. Beware the lockless walkers. */ + list_add(&dep->signal_link, &node->signalers_list); + list_add_rcu(&dep->wait_link, &signal->waiters_list); + /* * As we do not allow WAIT to preempt inflight requests, * once we have executed a request, along with triggering diff --git a/drivers/gpu/drm/i915/i915_utils.c b/drivers/gpu/drm/i915/i915_utils.c index c47261ae86ea..632d6953c78d 100644 --- a/drivers/gpu/drm/i915/i915_utils.c +++ b/drivers/gpu/drm/i915/i915_utils.c @@ -8,9 +8,8 @@ #include "i915_drv.h" #include "i915_utils.h" -#define FDO_BUG_URL "https://bugs.freedesktop.org/enter_bug.cgi?product=DRI" -#define FDO_BUG_MSG "Please file a bug at " FDO_BUG_URL " against DRM/Intel " \ - "providing the dmesg log by booting with drm.debug=0xf" +#define FDO_BUG_URL "https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs" +#define FDO_BUG_MSG "Please file a bug on drm/i915; see " FDO_BUG_URL " for details." void __i915_printk(struct drm_i915_private *dev_priv, const char *level, diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 983afeaee737..748cd379065f 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -796,12 +796,41 @@ bool a6xx_gmu_isidle(struct a6xx_gmu *gmu) return true; } +#define GBIF_CLIENT_HALT_MASK BIT(0) +#define GBIF_ARB_HALT_MASK BIT(1) + +static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu) +{ + struct msm_gpu *gpu = &adreno_gpu->base; + + if (!a6xx_has_gbif(adreno_gpu)) { + gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf); + spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) & + 0xf) == 0xf); + gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0); + + return; + } + + /* Halt new client requests on GBIF */ + gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK); + spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) & + (GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK); + + /* Halt all AXI requests on GBIF */ + gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK); + spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) & + (GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK); + + /* The GBIF halt needs to be explicitly cleared */ + gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0); +} + /* Gracefully try to shut down the GMU and by extension the GPU */ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu) { struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; - struct msm_gpu *gpu = &adreno_gpu->base; u32 val; /* @@ -819,11 +848,7 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu) return; } - /* Clear the VBIF pipe before shutting down */ - gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf); - spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) & 0xf) - == 0xf); - gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0); + a6xx_bus_clear_pending_transactions(adreno_gpu); /* tell the GMU we want to slumber */ a6xx_gmu_notify_slumber(gmu); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index daf07800cde0..68af24150de5 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -378,18 +378,6 @@ static int a6xx_hw_init(struct msm_gpu *gpu) struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); int ret; - /* - * During a previous slumber, GBIF halt is asserted to ensure - * no further transaction can go through GPU before GPU - * headswitch is turned off. - * - * This halt is deasserted once headswitch goes off but - * incase headswitch doesn't goes off clear GBIF halt - * here to ensure GPU wake-up doesn't fail because of - * halted GPU transactions. - */ - gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0); - /* Make sure the GMU keeps the GPU on while we set it up */ a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET); @@ -470,10 +458,12 @@ static int a6xx_hw_init(struct msm_gpu *gpu) /* Select CP0 to always count cycles */ gpu_write(gpu, REG_A6XX_CP_PERFCTR_CP_SEL_0, PERF_CP_ALWAYS_COUNT); - gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL, 2 << 1); - gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, 2 << 1); - gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL, 2 << 1); - gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL, 2 << 21); + if (adreno_is_a630(adreno_gpu)) { + gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL, 2 << 1); + gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, 2 << 1); + gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL, 2 << 1); + gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL, 2 << 21); + } /* Enable fault detection */ gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL, @@ -748,39 +738,6 @@ static const u32 a6xx_register_offsets[REG_ADRENO_REGISTER_MAX] = { REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_CNTL, REG_A6XX_CP_RB_CNTL), }; -#define GBIF_CLIENT_HALT_MASK BIT(0) -#define GBIF_ARB_HALT_MASK BIT(1) - -static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu) -{ - struct msm_gpu *gpu = &adreno_gpu->base; - - if(!a6xx_has_gbif(adreno_gpu)){ - gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf); - spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) & - 0xf) == 0xf); - gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0); - - return; - } - - /* Halt new client requests on GBIF */ - gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK); - spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) & - (GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK); - - /* Halt all AXI requests on GBIF */ - gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK); - spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) & - (GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK); - - /* - * GMU needs DDR access in slumber path. Deassert GBIF halt now - * to allow for GMU to access system memory. - */ - gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0); -} - static int a6xx_pm_resume(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); @@ -805,16 +762,6 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu) devfreq_suspend_device(gpu->devfreq.devfreq); - /* - * Make sure the GMU is idle before continuing (because some transitions - * may use VBIF - */ - a6xx_gmu_wait_for_idle(&a6xx_gpu->gmu); - - /* Clear the VBIF pipe before shutting down */ - /* FIXME: This accesses the GPU - do we need to make sure it is on? */ - a6xx_bus_clear_pending_transactions(adreno_gpu); - return a6xx_gmu_stop(a6xx_gpu); } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c index eda11abc5f01..e450e0b97211 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c @@ -7,6 +7,7 @@ #include "a6xx_gmu.h" #include "a6xx_gmu.xml.h" +#include "a6xx_gpu.h" #define HFI_MSG_ID(val) [val] = #val @@ -216,48 +217,82 @@ static int a6xx_hfi_send_perf_table(struct a6xx_gmu *gmu) NULL, 0); } -static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu) +static void a618_build_bw_table(struct a6xx_hfi_msg_bw_table *msg) { - struct a6xx_hfi_msg_bw_table msg = { 0 }; + /* Send a single "off" entry since the 618 GMU doesn't do bus scaling */ + msg->bw_level_num = 1; + + msg->ddr_cmds_num = 3; + msg->ddr_wait_bitmask = 0x01; + + msg->ddr_cmds_addrs[0] = 0x50000; + msg->ddr_cmds_addrs[1] = 0x5003c; + msg->ddr_cmds_addrs[2] = 0x5000c; + + msg->ddr_cmds_data[0][0] = 0x40000000; + msg->ddr_cmds_data[0][1] = 0x40000000; + msg->ddr_cmds_data[0][2] = 0x40000000; /* - * The sdm845 GMU doesn't do bus frequency scaling on its own but it - * does need at least one entry in the list because it might be accessed - * when the GMU is shutting down. Send a single "off" entry. + * These are the CX (CNOC) votes - these are used by the GMU but the + * votes are known and fixed for the target */ + msg->cnoc_cmds_num = 1; + msg->cnoc_wait_bitmask = 0x01; + + msg->cnoc_cmds_addrs[0] = 0x5007c; + msg->cnoc_cmds_data[0][0] = 0x40000000; + msg->cnoc_cmds_data[1][0] = 0x60000001; +} - msg.bw_level_num = 1; +static void a6xx_build_bw_table(struct a6xx_hfi_msg_bw_table *msg) +{ + /* Send a single "off" entry since the 630 GMU doesn't do bus scaling */ + msg->bw_level_num = 1; - msg.ddr_cmds_num = 3; - msg.ddr_wait_bitmask = 0x07; + msg->ddr_cmds_num = 3; + msg->ddr_wait_bitmask = 0x07; - msg.ddr_cmds_addrs[0] = 0x50000; - msg.ddr_cmds_addrs[1] = 0x5005c; - msg.ddr_cmds_addrs[2] = 0x5000c; + msg->ddr_cmds_addrs[0] = 0x50000; + msg->ddr_cmds_addrs[1] = 0x5005c; + msg->ddr_cmds_addrs[2] = 0x5000c; - msg.ddr_cmds_data[0][0] = 0x40000000; - msg.ddr_cmds_data[0][1] = 0x40000000; - msg.ddr_cmds_data[0][2] = 0x40000000; + msg->ddr_cmds_data[0][0] = 0x40000000; + msg->ddr_cmds_data[0][1] = 0x40000000; + msg->ddr_cmds_data[0][2] = 0x40000000; /* * These are the CX (CNOC) votes. This is used but the values for the * sdm845 GMU are known and fixed so we can hard code them. */ - msg.cnoc_cmds_num = 3; - msg.cnoc_wait_bitmask = 0x05; + msg->cnoc_cmds_num = 3; + msg->cnoc_wait_bitmask = 0x05; - msg.cnoc_cmds_addrs[0] = 0x50034; - msg.cnoc_cmds_addrs[1] = 0x5007c; - msg.cnoc_cmds_addrs[2] = 0x5004c; + msg->cnoc_cmds_addrs[0] = 0x50034; + msg->cnoc_cmds_addrs[1] = 0x5007c; + msg->cnoc_cmds_addrs[2] = 0x5004c; - msg.cnoc_cmds_data[0][0] = 0x40000000; - msg.cnoc_cmds_data[0][1] = 0x00000000; - msg.cnoc_cmds_data[0][2] = 0x40000000; + msg->cnoc_cmds_data[0][0] = 0x40000000; + msg->cnoc_cmds_data[0][1] = 0x00000000; + msg->cnoc_cmds_data[0][2] = 0x40000000; + + msg->cnoc_cmds_data[1][0] = 0x60000001; + msg->cnoc_cmds_data[1][1] = 0x20000001; + msg->cnoc_cmds_data[1][2] = 0x60000001; +} + + +static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu) +{ + struct a6xx_hfi_msg_bw_table msg = { 0 }; + struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; - msg.cnoc_cmds_data[1][0] = 0x60000001; - msg.cnoc_cmds_data[1][1] = 0x20000001; - msg.cnoc_cmds_data[1][2] = 0x60000001; + if (adreno_is_a618(adreno_gpu)) + a618_build_bw_table(&msg); + else + a6xx_build_bw_table(&msg); return a6xx_hfi_send_msg(gmu, HFI_H2F_MSG_BW_TABLE, &msg, sizeof(msg), NULL, 0); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c index 528632690f1e..a05282dede91 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c @@ -255,13 +255,13 @@ static const struct dpu_format dpu_format_map[] = { INTERLEAVED_RGB_FMT(RGB565, 0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT, - C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3, + C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3, false, 2, 0, DPU_FETCH_LINEAR, 1), INTERLEAVED_RGB_FMT(BGR565, 0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT, - C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3, + C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3, false, 2, 0, DPU_FETCH_LINEAR, 1), diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c index 29705e773a4b..80d3cfc14007 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c @@ -12,6 +12,7 @@ #define to_dpu_mdss(x) container_of(x, struct dpu_mdss, base) +#define HW_REV 0x0 #define HW_INTR_STATUS 0x0010 /* Max BW defined in KBps */ @@ -22,6 +23,17 @@ struct dpu_irq_controller { struct irq_domain *domain; }; +struct dpu_hw_cfg { + u32 val; + u32 offset; +}; + +struct dpu_mdss_hw_init_handler { + u32 hw_rev; + u32 hw_reg_count; + struct dpu_hw_cfg* hw_cfg; +}; + struct dpu_mdss { struct msm_mdss base; void __iomem *mmio; @@ -32,6 +44,44 @@ struct dpu_mdss { u32 num_paths; }; +static struct dpu_hw_cfg hw_cfg[] = { + { + /* UBWC global settings */ + .val = 0x1E, + .offset = 0x144, + } +}; + +static struct dpu_mdss_hw_init_handler cfg_handler[] = { + { .hw_rev = DPU_HW_VER_620, + .hw_reg_count = ARRAY_SIZE(hw_cfg), + .hw_cfg = hw_cfg + }, +}; + +static void dpu_mdss_hw_init(struct dpu_mdss *dpu_mdss, u32 hw_rev) +{ + int i; + u32 count = 0; + struct dpu_hw_cfg *hw_cfg = NULL; + + for (i = 0; i < ARRAY_SIZE(cfg_handler); i++) { + if (cfg_handler[i].hw_rev == hw_rev) { + hw_cfg = cfg_handler[i].hw_cfg; + count = cfg_handler[i].hw_reg_count; + break; + } + } + + for (i = 0; i < count; i++ ) { + writel_relaxed(hw_cfg->val, + dpu_mdss->mmio + hw_cfg->offset); + hw_cfg++; + } + + return; +} + static int dpu_mdss_parse_data_bus_icc_path(struct drm_device *dev, struct dpu_mdss *dpu_mdss) { @@ -174,12 +224,18 @@ static int dpu_mdss_enable(struct msm_mdss *mdss) struct dpu_mdss *dpu_mdss = to_dpu_mdss(mdss); struct dss_module_power *mp = &dpu_mdss->mp; int ret; + u32 mdss_rev; dpu_mdss_icc_request_bw(mdss); ret = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true); - if (ret) + if (ret) { DPU_ERROR("clock enable failed, ret:%d\n", ret); + return ret; + } + + mdss_rev = readl_relaxed(dpu_mdss->mmio + HW_REV); + dpu_mdss_hw_init(dpu_mdss, mdss_rev); return ret; } diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c index 05cc04f729d6..e1cc541e0ef2 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c @@ -1109,8 +1109,8 @@ static void mdp5_crtc_wait_for_pp_done(struct drm_crtc *crtc) ret = wait_for_completion_timeout(&mdp5_crtc->pp_completion, msecs_to_jiffies(50)); if (ret == 0) - dev_warn(dev->dev, "pp done time out, lm=%d\n", - mdp5_cstate->pipeline.mixer->lm); + dev_warn_ratelimited(dev->dev, "pp done time out, lm=%d\n", + mdp5_cstate->pipeline.mixer->lm); } static void mdp5_crtc_wait_for_flush_done(struct drm_crtc *crtc) diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c index 104115d112eb..4864b9558f65 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_manager.c +++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c @@ -336,7 +336,7 @@ static int dsi_mgr_connector_get_modes(struct drm_connector *connector) return num; } -static int dsi_mgr_connector_mode_valid(struct drm_connector *connector, +static enum drm_mode_status dsi_mgr_connector_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { int id = dsi_mgr_connector_get_id(connector); @@ -506,6 +506,7 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge) struct msm_dsi *msm_dsi1 = dsi_mgr_get_dsi(DSI_1); struct mipi_dsi_host *host = msm_dsi->host; struct drm_panel *panel = msm_dsi->panel; + struct msm_dsi_pll *src_pll; bool is_dual_dsi = IS_DUAL_DSI(); int ret; @@ -539,6 +540,10 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge) id, ret); } + /* Save PLL status if it is a clock source */ + src_pll = msm_dsi_phy_get_pll(msm_dsi->phy); + msm_dsi_pll_save_state(src_pll); + ret = msm_dsi_host_power_off(host); if (ret) pr_err("%s: host %d power off failed,%d\n", __func__, id, ret); diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index b0cfa67d2a57..f509ebd77500 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -724,10 +724,6 @@ void msm_dsi_phy_disable(struct msm_dsi_phy *phy) if (!phy || !phy->cfg->ops.disable) return; - /* Save PLL status if it is a clock source */ - if (phy->usecase != MSM_DSI_PHY_SLAVE) - msm_dsi_pll_save_state(phy->pll); - phy->cfg->ops.disable(phy); dsi_phy_regulator_disable(phy); diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c index 1c894548dd72..6ac04fc303f5 100644 --- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c +++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c @@ -411,6 +411,12 @@ static int dsi_pll_10nm_vco_prepare(struct clk_hw *hw) if (pll_10nm->slave) dsi_pll_enable_pll_bias(pll_10nm->slave); + rc = dsi_pll_10nm_vco_set_rate(hw,pll_10nm->vco_current_rate, 0); + if (rc) { + pr_err("vco_set_rate failed, rc=%d\n", rc); + return rc; + } + /* Start PLL */ pll_write(pll_10nm->phy_cmn_mmio + REG_DSI_10nm_PHY_CMN_PLL_CNTRL, 0x01); diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c index 890315291b01..bb737f9281e6 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c @@ -458,6 +458,8 @@ nv50_wndw_atomic_check(struct drm_plane *plane, struct drm_plane_state *state) asyw->clr.ntfy = armw->ntfy.handle != 0; asyw->clr.sema = armw->sema.handle != 0; asyw->clr.xlut = armw->xlut.handle != 0; + if (asyw->clr.xlut && asyw->visible) + asyw->set.xlut = asyw->xlut.handle != 0; asyw->clr.csc = armw->csc.valid; if (wndw->func->image_clr) asyw->clr.image = armw->image.handle[0] != 0; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index c7d700916eae..8ebbe1656008 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -2579,6 +2579,7 @@ nv166_chipset = { static const struct nvkm_device_chip nv167_chipset = { .name = "TU117", + .acr = tu102_acr_new, .bar = tu102_bar_new, .bios = nvkm_bios_new, .bus = gf100_bus_new, @@ -2607,6 +2608,7 @@ nv167_chipset = { .disp = tu102_disp_new, .dma = gv100_dma_new, .fifo = tu102_fifo_new, + .gr = tu102_gr_new, .nvdec[0] = gm107_nvdec_new, .nvenc[0] = gm107_nvenc_new, .sec2 = tu102_sec2_new, @@ -2615,6 +2617,7 @@ nv167_chipset = { static const struct nvkm_device_chip nv168_chipset = { .name = "TU116", + .acr = tu102_acr_new, .bar = tu102_bar_new, .bios = nvkm_bios_new, .bus = gf100_bus_new, @@ -2643,6 +2646,7 @@ nv168_chipset = { .disp = tu102_disp_new, .dma = gv100_dma_new, .fifo = tu102_fifo_new, + .gr = tu102_gr_new, .nvdec[0] = gm107_nvdec_new, .nvenc[0] = gm107_nvenc_new, .sec2 = tu102_sec2_new, diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c index 454668b1cf54..a9efa4d78be9 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c @@ -164,6 +164,32 @@ MODULE_FIRMWARE("nvidia/tu106/gr/sw_nonctx.bin"); MODULE_FIRMWARE("nvidia/tu106/gr/sw_bundle_init.bin"); MODULE_FIRMWARE("nvidia/tu106/gr/sw_method_init.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/fecs_bl.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/fecs_inst.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/fecs_data.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/fecs_sig.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/gpccs_bl.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/gpccs_inst.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/gpccs_data.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/gpccs_sig.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/sw_ctx.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/sw_nonctx.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/sw_bundle_init.bin"); +MODULE_FIRMWARE("nvidia/tu117/gr/sw_method_init.bin"); + +MODULE_FIRMWARE("nvidia/tu116/gr/fecs_bl.bin"); +MODULE_FIRMWARE("nvidia/tu116/gr/fecs_inst.bin"); +MODULE_FIRMWARE("nvidia/tu116/gr/fecs_data.bin"); +MODULE_FIRMWARE("nvidia/tu116/gr/fecs_sig.bin"); +MODULE_FIRMWARE("nvidia/tu116/gr/gpccs_bl.bin"); +MODULE_FIRMWARE("nvidia/tu116/gr/gpccs_inst.bin"); +MODULE_FIRMWARE("nvidia/tu116/gr/gpccs_data.bin"); +MODULE_FIRMWARE("nvidia/tu116/gr/gpccs_sig.bin"); +MODULE_FIRMWARE("nvidia/tu116/gr/sw_ctx.bin"); +MODULE_FIRMWARE("nvidia/tu116/gr/sw_nonctx.bin"); +MODULE_FIRMWARE("nvidia/tu116/gr/sw_bundle_init.bin"); +MODULE_FIRMWARE("nvidia/tu116/gr/sw_method_init.bin"); + static const struct gf100_gr_fwif tu102_gr_fwif[] = { { 0, gm200_gr_load, &tu102_gr, &gp108_gr_fecs_acr, &gp108_gr_gpccs_acr }, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/tu102.c index 7f4b89d82d32..d28d8f36ae24 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/tu102.c @@ -107,6 +107,12 @@ MODULE_FIRMWARE("nvidia/tu104/acr/ucode_unload.bin"); MODULE_FIRMWARE("nvidia/tu106/acr/unload_bl.bin"); MODULE_FIRMWARE("nvidia/tu106/acr/ucode_unload.bin"); +MODULE_FIRMWARE("nvidia/tu116/acr/unload_bl.bin"); +MODULE_FIRMWARE("nvidia/tu116/acr/ucode_unload.bin"); + +MODULE_FIRMWARE("nvidia/tu117/acr/unload_bl.bin"); +MODULE_FIRMWARE("nvidia/tu117/acr/ucode_unload.bin"); + static const struct nvkm_acr_hsf_fwif tu102_acr_unload_fwif[] = { { 0, nvkm_acr_hsfw_load, &gp108_acr_unload_0 }, @@ -130,6 +136,8 @@ tu102_acr_asb_0 = { MODULE_FIRMWARE("nvidia/tu102/acr/ucode_asb.bin"); MODULE_FIRMWARE("nvidia/tu104/acr/ucode_asb.bin"); MODULE_FIRMWARE("nvidia/tu106/acr/ucode_asb.bin"); +MODULE_FIRMWARE("nvidia/tu116/acr/ucode_asb.bin"); +MODULE_FIRMWARE("nvidia/tu117/acr/ucode_asb.bin"); static const struct nvkm_acr_hsf_fwif tu102_acr_asb_fwif[] = { @@ -154,6 +162,12 @@ MODULE_FIRMWARE("nvidia/tu104/acr/ucode_ahesasc.bin"); MODULE_FIRMWARE("nvidia/tu106/acr/bl.bin"); MODULE_FIRMWARE("nvidia/tu106/acr/ucode_ahesasc.bin"); +MODULE_FIRMWARE("nvidia/tu116/acr/bl.bin"); +MODULE_FIRMWARE("nvidia/tu116/acr/ucode_ahesasc.bin"); + +MODULE_FIRMWARE("nvidia/tu117/acr/bl.bin"); +MODULE_FIRMWARE("nvidia/tu117/acr/ucode_ahesasc.bin"); + static const struct nvkm_acr_hsf_fwif tu102_acr_ahesasc_fwif[] = { { 0, nvkm_acr_hsfw_load, &tu102_acr_ahesasc_0 }, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c index 389bad312bf2..10ff5d053f7e 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c @@ -51,3 +51,5 @@ MODULE_FIRMWARE("nvidia/gv100/nvdec/scrubber.bin"); MODULE_FIRMWARE("nvidia/tu102/nvdec/scrubber.bin"); MODULE_FIRMWARE("nvidia/tu104/nvdec/scrubber.bin"); MODULE_FIRMWARE("nvidia/tu106/nvdec/scrubber.bin"); +MODULE_FIRMWARE("nvidia/tu116/nvdec/scrubber.bin"); +MODULE_FIRMWARE("nvidia/tu117/nvdec/scrubber.bin"); diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c index 7157dfd7dea3..9a1a72a748e7 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.c +++ b/drivers/gpu/drm/panfrost/panfrost_job.c @@ -280,12 +280,8 @@ static void panfrost_job_cleanup(struct kref *ref) } if (job->bos) { - struct panfrost_gem_object *bo; - - for (i = 0; i < job->bo_count; i++) { - bo = to_panfrost_bo(job->bos[i]); + for (i = 0; i < job->bo_count; i++) drm_gem_object_put_unlocked(job->bos[i]); - } kvfree(job->bos); } diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index 763cfca886a7..3107b0738e40 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -151,7 +151,12 @@ u32 panfrost_mmu_as_get(struct panfrost_device *pfdev, struct panfrost_mmu *mmu) as = mmu->as; if (as >= 0) { int en = atomic_inc_return(&mmu->as_count); - WARN_ON(en >= NUM_JOB_SLOTS); + + /* + * AS can be retained by active jobs or a perfcnt context, + * hence the '+ 1' here. + */ + WARN_ON(en >= (NUM_JOB_SLOTS + 1)); list_move(&mmu->list, &pfdev->as_lru_list); goto out; diff --git a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c index 684820448be3..6913578d5aa7 100644 --- a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c +++ b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c @@ -73,7 +73,7 @@ static int panfrost_perfcnt_enable_locked(struct panfrost_device *pfdev, struct panfrost_file_priv *user = file_priv->driver_priv; struct panfrost_perfcnt *perfcnt = pfdev->perfcnt; struct drm_gem_shmem_object *bo; - u32 cfg; + u32 cfg, as; int ret; if (user == perfcnt->user) @@ -126,12 +126,8 @@ static int panfrost_perfcnt_enable_locked(struct panfrost_device *pfdev, perfcnt->user = user; - /* - * Always use address space 0 for now. - * FIXME: this needs to be updated when we start using different - * address space. - */ - cfg = GPU_PERFCNT_CFG_AS(0) | + as = panfrost_mmu_as_get(pfdev, perfcnt->mapping->mmu); + cfg = GPU_PERFCNT_CFG_AS(as) | GPU_PERFCNT_CFG_MODE(GPU_PERFCNT_CFG_MODE_MANUAL); /* @@ -195,6 +191,7 @@ static int panfrost_perfcnt_disable_locked(struct panfrost_device *pfdev, drm_gem_shmem_vunmap(&perfcnt->mapping->obj->base.base, perfcnt->buf); perfcnt->buf = NULL; panfrost_gem_close(&perfcnt->mapping->obj->base.base, file_priv); + panfrost_mmu_as_put(pfdev, perfcnt->mapping->mmu); panfrost_gem_mapping_put(perfcnt->mapping); perfcnt->mapping = NULL; pm_runtime_mark_last_busy(pfdev->dev); diff --git a/drivers/gpu/drm/selftests/drm_cmdline_selftests.h b/drivers/gpu/drm/selftests/drm_cmdline_selftests.h index ceac7af9a172..29e367db6118 100644 --- a/drivers/gpu/drm/selftests/drm_cmdline_selftests.h +++ b/drivers/gpu/drm/selftests/drm_cmdline_selftests.h @@ -53,6 +53,7 @@ cmdline_test(drm_cmdline_test_rotate_0) cmdline_test(drm_cmdline_test_rotate_90) cmdline_test(drm_cmdline_test_rotate_180) cmdline_test(drm_cmdline_test_rotate_270) +cmdline_test(drm_cmdline_test_rotate_multiple) cmdline_test(drm_cmdline_test_rotate_invalid_val) cmdline_test(drm_cmdline_test_rotate_truncated) cmdline_test(drm_cmdline_test_hmirror) diff --git a/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c b/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c index 520f3e66a384..d96cd890def6 100644 --- a/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c +++ b/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c @@ -856,6 +856,17 @@ static int drm_cmdline_test_rotate_270(void *ignored) return 0; } +static int drm_cmdline_test_rotate_multiple(void *ignored) +{ + struct drm_cmdline_mode mode = { }; + + FAIL_ON(drm_mode_parse_command_line_for_connector("720x480,rotate=0,rotate=90", + &no_connector, + &mode)); + + return 0; +} + static int drm_cmdline_test_rotate_invalid_val(void *ignored) { struct drm_cmdline_mode mode = { }; @@ -888,7 +899,7 @@ static int drm_cmdline_test_hmirror(void *ignored) FAIL_ON(!mode.specified); FAIL_ON(mode.xres != 720); FAIL_ON(mode.yres != 480); - FAIL_ON(mode.rotation_reflection != DRM_MODE_REFLECT_X); + FAIL_ON(mode.rotation_reflection != (DRM_MODE_ROTATE_0 | DRM_MODE_REFLECT_X)); FAIL_ON(mode.refresh_specified); @@ -913,7 +924,7 @@ static int drm_cmdline_test_vmirror(void *ignored) FAIL_ON(!mode.specified); FAIL_ON(mode.xres != 720); FAIL_ON(mode.yres != 480); - FAIL_ON(mode.rotation_reflection != DRM_MODE_REFLECT_Y); + FAIL_ON(mode.rotation_reflection != (DRM_MODE_ROTATE_0 | DRM_MODE_REFLECT_Y)); FAIL_ON(mode.refresh_specified); diff --git a/drivers/hwmon/acpi_power_meter.c b/drivers/hwmon/acpi_power_meter.c index 4cf25458f0b9..0db8ef4fd6e1 100644 --- a/drivers/hwmon/acpi_power_meter.c +++ b/drivers/hwmon/acpi_power_meter.c @@ -355,7 +355,9 @@ static ssize_t show_str(struct device *dev, struct acpi_device *acpi_dev = to_acpi_device(dev); struct acpi_power_meter_resource *resource = acpi_dev->driver_data; acpi_string val; + int ret; + mutex_lock(&resource->lock); switch (attr->index) { case 0: val = resource->model_number; @@ -372,8 +374,9 @@ static ssize_t show_str(struct device *dev, val = ""; break; } - - return sprintf(buf, "%s\n", val); + ret = sprintf(buf, "%s\n", val); + mutex_unlock(&resource->lock); + return ret; } static ssize_t show_val(struct device *dev, @@ -817,11 +820,12 @@ static void acpi_power_meter_notify(struct acpi_device *device, u32 event) resource = acpi_driver_data(device); - mutex_lock(&resource->lock); switch (event) { case METER_NOTIFY_CONFIG: + mutex_lock(&resource->lock); free_capabilities(resource); res = read_capabilities(resource); + mutex_unlock(&resource->lock); if (res) break; @@ -830,15 +834,12 @@ static void acpi_power_meter_notify(struct acpi_device *device, u32 event) break; case METER_NOTIFY_TRIP: sysfs_notify(&device->dev.kobj, NULL, POWER_AVERAGE_NAME); - update_meter(resource); break; case METER_NOTIFY_CAP: sysfs_notify(&device->dev.kobj, NULL, POWER_CAP_NAME); - update_cap(resource); break; case METER_NOTIFY_INTERVAL: sysfs_notify(&device->dev.kobj, NULL, POWER_AVG_INTERVAL_NAME); - update_avg_interval(resource); break; case METER_NOTIFY_CAPPING: sysfs_notify(&device->dev.kobj, NULL, POWER_ALARM_NAME); @@ -848,7 +849,6 @@ static void acpi_power_meter_notify(struct acpi_device *device, u32 event) WARN(1, "Unexpected event %d\n", event); break; } - mutex_unlock(&resource->lock); acpi_bus_generate_netlink_event(ACPI_POWER_METER_CLASS, dev_name(&device->dev), event, 0); @@ -912,8 +912,8 @@ static int acpi_power_meter_remove(struct acpi_device *device) resource = acpi_driver_data(device); hwmon_device_unregister(resource->hwmon_dev); - free_capabilities(resource); remove_attrs(resource); + free_capabilities(resource); kfree(resource); return 0; diff --git a/drivers/hwmon/w83627ehf.c b/drivers/hwmon/w83627ehf.c index 7ffadc2da57b..5a5120121e50 100644 --- a/drivers/hwmon/w83627ehf.c +++ b/drivers/hwmon/w83627ehf.c @@ -1346,8 +1346,13 @@ w83627ehf_is_visible(const void *drvdata, enum hwmon_sensor_types type, /* channel 0.., name 1.. */ if (!(data->have_temp & (1 << channel))) return 0; - if (attr == hwmon_temp_input || attr == hwmon_temp_label) + if (attr == hwmon_temp_input) return 0444; + if (attr == hwmon_temp_label) { + if (data->temp_label) + return 0444; + return 0; + } if (channel == 2 && data->temp3_val_only) return 0; if (attr == hwmon_temp_max) { diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index b273e421e910..a1a035270cab 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -2575,6 +2575,17 @@ isert_wait4logout(struct isert_conn *isert_conn) } } +static void +isert_wait4cmds(struct iscsi_conn *conn) +{ + isert_info("iscsi_conn %p\n", conn); + + if (conn->sess) { + target_sess_cmd_list_set_waiting(conn->sess->se_sess); + target_wait_for_sess_cmds(conn->sess->se_sess); + } +} + /** * isert_put_unsol_pending_cmds() - Drop commands waiting for * unsolicitate dataout @@ -2622,6 +2633,7 @@ static void isert_wait_conn(struct iscsi_conn *conn) ib_drain_qp(isert_conn->qp); isert_put_unsol_pending_cmds(conn); + isert_wait4cmds(conn); isert_wait4logout(isert_conn); queue_work(isert_release_wq, &isert_conn->release_work); diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index 2104fb8afc06..9f33fdb3bb05 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -14,8 +14,8 @@ obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o amd_iommu_quirks.o obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd_iommu_debugfs.o obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o -obj-$(CONFIG_ARM_SMMU) += arm-smmu-mod.o -arm-smmu-mod-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-qcom.o +obj-$(CONFIG_ARM_SMMU) += arm_smmu.o +arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-qcom.o obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o obj-$(CONFIG_DMAR_TABLE) += dmar.o obj-$(CONFIG_INTEL_IOMMU) += intel-iommu.o intel-pasid.o diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 2759a8d57b7f..6be3853a5d97 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -2523,6 +2523,7 @@ static int __init early_amd_iommu_init(void) struct acpi_table_header *ivrs_base; acpi_status status; int i, remap_cache_sz, ret = 0; + u32 pci_id; if (!amd_iommu_detected) return -ENODEV; @@ -2610,6 +2611,16 @@ static int __init early_amd_iommu_init(void) if (ret) goto out; + /* Disable IOMMU if there's Stoney Ridge graphics */ + for (i = 0; i < 32; i++) { + pci_id = read_pci_config(0, i, 0, 0); + if ((pci_id & 0xffff) == 0x1002 && (pci_id >> 16) == 0x98e4) { + pr_info("Disable IOMMU on Stoney Ridge\n"); + amd_iommu_disabled = true; + break; + } + } + /* Disable any previously enabled IOMMUs */ if (!is_kdump_kernel() || amd_iommu_disabled) disable_iommus(); @@ -2718,7 +2729,7 @@ static int __init state_next(void) ret = early_amd_iommu_init(); init_state = ret ? IOMMU_INIT_ERROR : IOMMU_ACPI_FINISHED; if (init_state == IOMMU_ACPI_FINISHED && amd_iommu_disabled) { - pr_info("AMD IOMMU disabled on kernel command-line\n"); + pr_info("AMD IOMMU disabled\n"); init_state = IOMMU_CMDLINE_DISABLED; ret = -EINVAL; } diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 9dc37672bf89..6fa6de2b6ad5 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -762,6 +762,11 @@ static int iommu_dummy(struct device *dev) return dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO; } +static bool attach_deferred(struct device *dev) +{ + return dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO; +} + /** * is_downstream_to_pci_bridge - test if a device belongs to the PCI * sub-hierarchy of a candidate PCI-PCI bridge @@ -2510,8 +2515,7 @@ struct dmar_domain *find_domain(struct device *dev) { struct device_domain_info *info; - if (unlikely(dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO || - dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO)) + if (unlikely(attach_deferred(dev) || iommu_dummy(dev))) return NULL; if (dev_is_pci(dev)) @@ -2525,18 +2529,14 @@ struct dmar_domain *find_domain(struct device *dev) return NULL; } -static struct dmar_domain *deferred_attach_domain(struct device *dev) +static void do_deferred_attach(struct device *dev) { - if (unlikely(dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO)) { - struct iommu_domain *domain; - - dev->archdata.iommu = NULL; - domain = iommu_get_domain_for_dev(dev); - if (domain) - intel_iommu_attach_device(domain, dev); - } + struct iommu_domain *domain; - return find_domain(dev); + dev->archdata.iommu = NULL; + domain = iommu_get_domain_for_dev(dev); + if (domain) + intel_iommu_attach_device(domain, dev); } static inline struct device_domain_info * @@ -2916,7 +2916,7 @@ static int identity_mapping(struct device *dev) struct device_domain_info *info; info = dev->archdata.iommu; - if (info && info != DUMMY_DEVICE_DOMAIN_INFO && info != DEFER_DEVICE_DOMAIN_INFO) + if (info) return (info->domain == si_domain); return 0; @@ -3587,6 +3587,9 @@ static bool iommu_need_mapping(struct device *dev) if (iommu_dummy(dev)) return false; + if (unlikely(attach_deferred(dev))) + do_deferred_attach(dev); + ret = identity_mapping(dev); if (ret) { u64 dma_mask = *dev->dma_mask; @@ -3635,7 +3638,7 @@ static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr, BUG_ON(dir == DMA_NONE); - domain = deferred_attach_domain(dev); + domain = find_domain(dev); if (!domain) return DMA_MAPPING_ERROR; @@ -3855,7 +3858,7 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele if (!iommu_need_mapping(dev)) return dma_direct_map_sg(dev, sglist, nelems, dir, attrs); - domain = deferred_attach_domain(dev); + domain = find_domain(dev); if (!domain) return 0; @@ -3950,7 +3953,11 @@ bounce_map_single(struct device *dev, phys_addr_t paddr, size_t size, int prot = 0; int ret; - domain = deferred_attach_domain(dev); + if (unlikely(attach_deferred(dev))) + do_deferred_attach(dev); + + domain = find_domain(dev); + if (WARN_ON(dir == DMA_NONE || !domain)) return DMA_MAPPING_ERROR; @@ -6133,7 +6140,7 @@ intel_iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev) static bool intel_iommu_is_attach_deferred(struct iommu_domain *domain, struct device *dev) { - return dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO; + return attach_deferred(dev); } static int diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index 39759db4f003..4328da0b0a9f 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -344,21 +344,19 @@ static void qcom_iommu_domain_free(struct iommu_domain *domain) { struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain); - if (WARN_ON(qcom_domain->iommu)) /* forgot to detach? */ - return; - iommu_put_dma_cookie(domain); - /* NOTE: unmap can be called after client device is powered off, - * for example, with GPUs or anything involving dma-buf. So we - * cannot rely on the device_link. Make sure the IOMMU is on to - * avoid unclocked accesses in the TLB inv path: - */ - pm_runtime_get_sync(qcom_domain->iommu->dev); - - free_io_pgtable_ops(qcom_domain->pgtbl_ops); - - pm_runtime_put_sync(qcom_domain->iommu->dev); + if (qcom_domain->iommu) { + /* + * NOTE: unmap can be called after client device is powered + * off, for example, with GPUs or anything involving dma-buf. + * So we cannot rely on the device_link. Make sure the IOMMU + * is on to avoid unclocked accesses in the TLB inv path: + */ + pm_runtime_get_sync(qcom_domain->iommu->dev); + free_io_pgtable_ops(qcom_domain->pgtbl_ops); + pm_runtime_put_sync(qcom_domain->iommu->dev); + } kfree(qcom_domain); } @@ -404,7 +402,7 @@ static void qcom_iommu_detach_dev(struct iommu_domain *domain, struct device *de struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain); unsigned i; - if (!qcom_domain->iommu) + if (WARN_ON(!qcom_domain->iommu)) return; pm_runtime_get_sync(qcom_iommu->dev); @@ -417,8 +415,6 @@ static void qcom_iommu_detach_dev(struct iommu_domain *domain, struct device *de ctx->domain = NULL; } pm_runtime_put_sync(qcom_iommu->dev); - - qcom_domain->iommu = NULL; } static int qcom_iommu_map(struct iommu_domain *domain, unsigned long iova, diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c index a1df0d95151c..8bc1faf71ff2 100644 --- a/drivers/md/bcache/alloc.c +++ b/drivers/md/bcache/alloc.c @@ -67,6 +67,7 @@ #include <linux/blkdev.h> #include <linux/kthread.h> #include <linux/random.h> +#include <linux/sched/signal.h> #include <trace/events/bcache.h> #define MAX_OPEN_BUCKETS 128 @@ -733,8 +734,21 @@ int bch_open_buckets_alloc(struct cache_set *c) int bch_cache_allocator_start(struct cache *ca) { - struct task_struct *k = kthread_run(bch_allocator_thread, - ca, "bcache_allocator"); + struct task_struct *k; + + /* + * In case previous btree check operation occupies too many + * system memory for bcache btree node cache, and the + * registering process is selected by OOM killer. Here just + * ignore the SIGKILL sent by OOM killer if there is, to + * avoid kthread_run() being failed by pending signals. The + * bcache registering process will exit after the registration + * done. + */ + if (signal_pending(current)) + flush_signals(current); + + k = kthread_run(bch_allocator_thread, ca, "bcache_allocator"); if (IS_ERR(k)) return PTR_ERR(k); diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index fa872df4e770..b12186c87f52 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -34,6 +34,7 @@ #include <linux/random.h> #include <linux/rcupdate.h> #include <linux/sched/clock.h> +#include <linux/sched/signal.h> #include <linux/rculist.h> #include <linux/delay.h> #include <trace/events/bcache.h> @@ -1913,6 +1914,18 @@ static int bch_gc_thread(void *arg) int bch_gc_thread_start(struct cache_set *c) { + /* + * In case previous btree check operation occupies too many + * system memory for bcache btree node cache, and the + * registering process is selected by OOM killer. Here just + * ignore the SIGKILL sent by OOM killer if there is, to + * avoid kthread_run() being failed by pending signals. The + * bcache registering process will exit after the registration + * done. + */ + if (signal_pending(current)) + flush_signals(current); + c->gc_thread = kthread_run(bch_gc_thread, c, "bcache_gc"); return PTR_ERR_OR_ZERO(c->gc_thread); } diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index 6730820780b0..0e3ff9745ac7 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -417,8 +417,6 @@ err: /* Journalling */ -#define nr_to_fifo_front(p, front_p, mask) (((p) - (front_p)) & (mask)) - static void btree_flush_write(struct cache_set *c) { struct btree *b, *t, *btree_nodes[BTREE_FLUSH_NR]; @@ -510,9 +508,8 @@ static void btree_flush_write(struct cache_set *c) * journal entry can be reclaimed). These selected nodes * will be ignored and skipped in the folowing for-loop. */ - if (nr_to_fifo_front(btree_current_write(b)->journal, - fifo_front_p, - mask) != 0) { + if (((btree_current_write(b)->journal - fifo_front_p) & + mask) != 0) { mutex_unlock(&b->write_lock); continue; } diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 2749daf09724..0c3c5419c52b 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1917,23 +1917,6 @@ static int run_cache_set(struct cache_set *c) if (bch_btree_check(c)) goto err; - /* - * bch_btree_check() may occupy too much system memory which - * has negative effects to user space application (e.g. data - * base) performance. Shrink the mca cache memory proactively - * here to avoid competing memory with user space workloads.. - */ - if (!c->shrinker_disabled) { - struct shrink_control sc; - - sc.gfp_mask = GFP_KERNEL; - sc.nr_to_scan = c->btree_cache_used * c->btree_pages; - /* first run to clear b->accessed tag */ - c->shrink.scan_objects(&c->shrink, &sc); - /* second run to reap non-accessed nodes */ - c->shrink.scan_objects(&c->shrink, &sc); - } - bch_journal_mark(c, &journal); bch_initial_gc_finish(c); pr_debug("btree_check() done"); diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c index b155e9549076..b680b0caa69b 100644 --- a/drivers/misc/habanalabs/device.c +++ b/drivers/misc/habanalabs/device.c @@ -598,7 +598,9 @@ int hl_device_set_debug_mode(struct hl_device *hdev, bool enable) goto out; } - hdev->asic_funcs->halt_coresight(hdev); + if (!hdev->hard_reset_pending) + hdev->asic_funcs->halt_coresight(hdev); + hdev->in_debug = 0; goto out; @@ -1189,6 +1191,7 @@ int hl_device_init(struct hl_device *hdev, struct class *hclass) if (hdev->asic_funcs->get_hw_state(hdev) == HL_DEVICE_HW_STATE_DIRTY) { dev_info(hdev->dev, "H/W state is dirty, must reset before initializing\n"); + hdev->asic_funcs->halt_engines(hdev, true); hdev->asic_funcs->hw_fini(hdev, true); } diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 7344e8a222ae..b8a8de24aaf7 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -895,6 +895,11 @@ void goya_init_dma_qmans(struct hl_device *hdev) */ static void goya_disable_external_queues(struct hl_device *hdev) { + struct goya_device *goya = hdev->asic_specific; + + if (!(goya->hw_cap_initialized & HW_CAP_DMA)) + return; + WREG32(mmDMA_QM_0_GLBL_CFG0, 0); WREG32(mmDMA_QM_1_GLBL_CFG0, 0); WREG32(mmDMA_QM_2_GLBL_CFG0, 0); @@ -956,6 +961,11 @@ static int goya_stop_external_queues(struct hl_device *hdev) { int rc, retval = 0; + struct goya_device *goya = hdev->asic_specific; + + if (!(goya->hw_cap_initialized & HW_CAP_DMA)) + return retval; + rc = goya_stop_queue(hdev, mmDMA_QM_0_GLBL_CFG1, mmDMA_QM_0_CP_STS, @@ -1744,9 +1754,18 @@ void goya_init_tpc_qmans(struct hl_device *hdev) */ static void goya_disable_internal_queues(struct hl_device *hdev) { + struct goya_device *goya = hdev->asic_specific; + + if (!(goya->hw_cap_initialized & HW_CAP_MME)) + goto disable_tpc; + WREG32(mmMME_QM_GLBL_CFG0, 0); WREG32(mmMME_CMDQ_GLBL_CFG0, 0); +disable_tpc: + if (!(goya->hw_cap_initialized & HW_CAP_TPC)) + return; + WREG32(mmTPC0_QM_GLBL_CFG0, 0); WREG32(mmTPC0_CMDQ_GLBL_CFG0, 0); @@ -1782,8 +1801,12 @@ static void goya_disable_internal_queues(struct hl_device *hdev) */ static int goya_stop_internal_queues(struct hl_device *hdev) { + struct goya_device *goya = hdev->asic_specific; int rc, retval = 0; + if (!(goya->hw_cap_initialized & HW_CAP_MME)) + goto stop_tpc; + /* * Each queue (QMAN) is a separate H/W logic. That means that each * QMAN can be stopped independently and failure to stop one does NOT @@ -1810,6 +1833,10 @@ static int goya_stop_internal_queues(struct hl_device *hdev) retval = -EIO; } +stop_tpc: + if (!(goya->hw_cap_initialized & HW_CAP_TPC)) + return retval; + rc = goya_stop_queue(hdev, mmTPC0_QM_GLBL_CFG1, mmTPC0_QM_CP_STS, @@ -1975,6 +2002,11 @@ static int goya_stop_internal_queues(struct hl_device *hdev) static void goya_dma_stall(struct hl_device *hdev) { + struct goya_device *goya = hdev->asic_specific; + + if (!(goya->hw_cap_initialized & HW_CAP_DMA)) + return; + WREG32(mmDMA_QM_0_GLBL_CFG1, 1 << DMA_QM_0_GLBL_CFG1_DMA_STOP_SHIFT); WREG32(mmDMA_QM_1_GLBL_CFG1, 1 << DMA_QM_1_GLBL_CFG1_DMA_STOP_SHIFT); WREG32(mmDMA_QM_2_GLBL_CFG1, 1 << DMA_QM_2_GLBL_CFG1_DMA_STOP_SHIFT); @@ -1984,6 +2016,11 @@ static void goya_dma_stall(struct hl_device *hdev) static void goya_tpc_stall(struct hl_device *hdev) { + struct goya_device *goya = hdev->asic_specific; + + if (!(goya->hw_cap_initialized & HW_CAP_TPC)) + return; + WREG32(mmTPC0_CFG_TPC_STALL, 1 << TPC0_CFG_TPC_STALL_V_SHIFT); WREG32(mmTPC1_CFG_TPC_STALL, 1 << TPC1_CFG_TPC_STALL_V_SHIFT); WREG32(mmTPC2_CFG_TPC_STALL, 1 << TPC2_CFG_TPC_STALL_V_SHIFT); @@ -1996,6 +2033,11 @@ static void goya_tpc_stall(struct hl_device *hdev) static void goya_mme_stall(struct hl_device *hdev) { + struct goya_device *goya = hdev->asic_specific; + + if (!(goya->hw_cap_initialized & HW_CAP_MME)) + return; + WREG32(mmMME_STALL, 0xFFFFFFFF); } @@ -4648,8 +4690,6 @@ static int goya_memset_device_memory(struct hl_device *hdev, u64 addr, u64 size, rc = goya_send_job_on_qman0(hdev, job); - hl_cb_put(job->patched_cb); - hl_debugfs_remove_job(hdev, job); kfree(job); cb->cs_cnt--; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 48d5ec770b94..d10805e5e623 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3526,6 +3526,47 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res, } } +#ifdef CONFIG_LOCKDEP +static int bond_get_lowest_level_rcu(struct net_device *dev) +{ + struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int cur = 0, max = 0; + + now = dev; + iter = &dev->adj_list.lower; + + while (1) { + next = NULL; + while (1) { + ldev = netdev_next_lower_dev_rcu(now, &iter); + if (!ldev) + break; + + next = ldev; + niter = &ldev->adj_list.lower; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + if (max <= cur) + max = cur; + break; + } + + if (!next) { + if (!cur) + return max; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; + } + + return max; +} +#endif + static void bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 *stats) { @@ -3533,11 +3574,17 @@ static void bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 temp; struct list_head *iter; struct slave *slave; + int nest_level = 0; - spin_lock(&bond->stats_lock); - memcpy(stats, &bond->bond_stats, sizeof(*stats)); rcu_read_lock(); +#ifdef CONFIG_LOCKDEP + nest_level = bond_get_lowest_level_rcu(bond_dev); +#endif + + spin_lock_nested(&bond->stats_lock, nest_level); + memcpy(stats, &bond->bond_stats, sizeof(*stats)); + bond_for_each_slave_rcu(bond, slave, iter) { const struct rtnl_link_stats64 *new = dev_get_stats(slave->dev, &temp); @@ -3547,10 +3594,10 @@ static void bond_get_stats(struct net_device *bond_dev, /* save off the slave stats for the next run */ memcpy(&slave->slave_stats, new, sizeof(*new)); } - rcu_read_unlock(); memcpy(&bond->bond_stats, stats, sizeof(*stats)); spin_unlock(&bond->stats_lock); + rcu_read_unlock(); } static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd) @@ -3640,6 +3687,8 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd case BOND_RELEASE_OLD: case SIOCBONDRELEASE: res = bond_release(bond_dev, slave_dev); + if (!res) + netdev_update_lockdep_key(slave_dev); break; case BOND_SETHWADDR_OLD: case SIOCBONDSETHWADDR: diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index ddb3916d3506..215c10923289 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -1398,6 +1398,8 @@ static int bond_option_slaves_set(struct bonding *bond, case '-': slave_dbg(bond->dev, dev, "Releasing interface\n"); ret = bond_release(bond->dev, dev); + if (!ret) + netdev_update_lockdep_key(dev); break; default: diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 449a22172e07..1a69286daa8d 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1366,6 +1366,9 @@ void b53_vlan_add(struct dsa_switch *ds, int port, b53_get_vlan_entry(dev, vid, vl); + if (vid == 0 && vid == b53_default_pvid(dev)) + untagged = true; + vl->members |= BIT(port); if (untagged && !dsa_is_cpu_port(ds, port)) vl->untag |= BIT(port); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c index a1f99bef4a68..7b55633d2cb9 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c @@ -722,6 +722,11 @@ static int aq_ethtool_set_priv_flags(struct net_device *ndev, u32 flags) if (flags & ~AQ_PRIV_FLAGS_MASK) return -EOPNOTSUPP; + if (hweight32((flags | priv_flags) & AQ_HW_LOOPBACK_MASK) > 1) { + netdev_info(ndev, "Can't enable more than one loopback simultaneously\n"); + return -EINVAL; + } + cfg->priv_flags = flags; if ((priv_flags ^ flags) & BIT(AQ_HW_LOOPBACK_DMA_NET)) { diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c index 6102251bb909..03ff92bc4a7f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c @@ -163,7 +163,7 @@ aq_check_approve_fvlan(struct aq_nic_s *aq_nic, } if ((aq_nic->ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) && - (!test_bit(be16_to_cpu(fsp->h_ext.vlan_tci), + (!test_bit(be16_to_cpu(fsp->h_ext.vlan_tci) & VLAN_VID_MASK, aq_nic->active_vlans))) { netdev_err(aq_nic->ndev, "ethtool: unknown vlan-id specified"); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h index cc70c606b6ef..251767c31f7e 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h @@ -337,6 +337,8 @@ struct aq_fw_ops { void (*enable_ptp)(struct aq_hw_s *self, int enable); + void (*adjust_ptp)(struct aq_hw_s *self, uint64_t adj); + int (*set_eee_rate)(struct aq_hw_s *self, u32 speed); int (*get_eee_rate)(struct aq_hw_s *self, u32 *rate, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index c85e3e29012c..e95f6a6bef73 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -533,8 +533,10 @@ unsigned int aq_nic_map_skb(struct aq_nic_s *self, struct sk_buff *skb, dx_buff->len, DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(aq_nic_get_dev(self), dx_buff->pa))) + if (unlikely(dma_mapping_error(aq_nic_get_dev(self), dx_buff->pa))) { + ret = 0; goto exit; + } first = dx_buff; dx_buff->len_pkt = skb->len; @@ -655,10 +657,6 @@ int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb) if (likely(frags)) { err = self->aq_hw_ops->hw_ring_tx_xmit(self->aq_hw, ring, frags); - if (err >= 0) { - ++ring->stats.tx.packets; - ring->stats.tx.bytes += skb->len; - } } else { err = NETDEV_TX_BUSY; } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index 6b27af0db499..78b6f3248756 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -359,7 +359,8 @@ static int aq_suspend_common(struct device *dev, bool deep) netif_device_detach(nic->ndev); netif_tx_stop_all_queues(nic->ndev); - aq_nic_stop(nic); + if (netif_running(nic->ndev)) + aq_nic_stop(nic); if (deep) { aq_nic_deinit(nic, !nic->aq_hw->aq_nic_cfg->wol); @@ -375,7 +376,7 @@ static int atl_resume_common(struct device *dev, bool deep) { struct pci_dev *pdev = to_pci_dev(dev); struct aq_nic_s *nic; - int ret; + int ret = 0; nic = pci_get_drvdata(pdev); @@ -390,9 +391,11 @@ static int atl_resume_common(struct device *dev, bool deep) goto err_exit; } - ret = aq_nic_start(nic); - if (ret) - goto err_exit; + if (netif_running(nic->ndev)) { + ret = aq_nic_start(nic); + if (ret) + goto err_exit; + } netif_device_attach(nic->ndev); netif_tx_start_all_queues(nic->ndev); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 951d86f8b66e..bae95a618560 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -272,9 +272,12 @@ bool aq_ring_tx_clean(struct aq_ring_s *self) } } - if (unlikely(buff->is_eop)) - dev_kfree_skb_any(buff->skb); + if (unlikely(buff->is_eop)) { + ++self->stats.rx.packets; + self->stats.tx.bytes += buff->skb->len; + dev_kfree_skb_any(buff->skb); + } buff->pa = 0U; buff->eop_index = 0xffffU; self->sw_head = aq_ring_next_dx(self, self->sw_head); @@ -351,7 +354,8 @@ int aq_ring_rx_clean(struct aq_ring_s *self, err = 0; goto err_exit; } - if (buff->is_error || buff->is_cso_err) { + if (buff->is_error || + (buff->is_lro && buff->is_cso_err)) { buff_ = buff; do { next_ = buff_->next, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h index 991e4d31b094..2c96f20f6289 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h @@ -78,7 +78,8 @@ struct __packed aq_ring_buff_s { u32 is_cleaned:1; u32 is_error:1; u32 is_vlan:1; - u32 rsvd3:4; + u32 is_lro:1; + u32 rsvd3:3; u16 eop_index; u16 rsvd4; }; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index ec041f78d063..d20d91cdece8 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -823,6 +823,8 @@ static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self, } } + buff->is_lro = !!(HW_ATL_B0_RXD_WB_STAT2_RSCCNT & + rxd_wb->status); if (HW_ATL_B0_RXD_WB_STAT2_EOP & rxd_wb->status) { buff->len = rxd_wb->pkt_len % AQ_CFG_RX_FRAME_MAX; @@ -835,8 +837,7 @@ static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self, rxd_wb->pkt_len > AQ_CFG_RX_FRAME_MAX ? AQ_CFG_RX_FRAME_MAX : rxd_wb->pkt_len; - if (HW_ATL_B0_RXD_WB_STAT2_RSCCNT & - rxd_wb->status) { + if (buff->is_lro) { /* LRO */ buff->next = rxd_wb->next_desc_ptr; ++ring->stats.rx.lro_packets; @@ -884,13 +885,16 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self, { struct aq_nic_cfg_s *cfg = self->aq_nic_cfg; unsigned int i = 0U; + u32 vlan_promisc; + u32 l2_promisc; - hw_atl_rpfl2promiscuous_mode_en_set(self, - IS_FILTER_ENABLED(IFF_PROMISC)); + l2_promisc = IS_FILTER_ENABLED(IFF_PROMISC) || + !!(cfg->priv_flags & BIT(AQ_HW_LOOPBACK_DMA_NET)); + vlan_promisc = l2_promisc || cfg->is_vlan_force_promisc; - hw_atl_rpf_vlan_prom_mode_en_set(self, - IS_FILTER_ENABLED(IFF_PROMISC) || - cfg->is_vlan_force_promisc); + hw_atl_rpfl2promiscuous_mode_en_set(self, l2_promisc); + + hw_atl_rpf_vlan_prom_mode_en_set(self, vlan_promisc); hw_atl_rpfl2multicast_flr_en_set(self, IS_FILTER_ENABLED(IFF_ALLMULTI) && @@ -1161,6 +1165,8 @@ static int hw_atl_b0_adj_sys_clock(struct aq_hw_s *self, s64 delta) { self->ptp_clk_offset += delta; + self->aq_fw_ops->adjust_ptp(self, self->ptp_clk_offset); + return 0; } @@ -1211,7 +1217,7 @@ static int hw_atl_b0_gpio_pulse(struct aq_hw_s *self, u32 index, fwreq.ptp_gpio_ctrl.index = index; fwreq.ptp_gpio_ctrl.period = period; /* Apply time offset */ - fwreq.ptp_gpio_ctrl.start = start - self->ptp_clk_offset; + fwreq.ptp_gpio_ctrl.start = start; size = sizeof(fwreq.msg_id) + sizeof(fwreq.ptp_gpio_ctrl); return self->aq_fw_ops->send_fw_request(self, &fwreq, size); diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c index f547baa6c954..354705f9bc49 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c @@ -22,6 +22,7 @@ #define HW_ATL_MIF_ADDR 0x0208U #define HW_ATL_MIF_VAL 0x020CU +#define HW_ATL_MPI_RPC_ADDR 0x0334U #define HW_ATL_RPC_CONTROL_ADR 0x0338U #define HW_ATL_RPC_STATE_ADR 0x033CU @@ -53,15 +54,14 @@ enum mcp_area { }; static int hw_atl_utils_ver_match(u32 ver_expected, u32 ver_actual); - static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self, enum hal_atl_utils_fw_state_e state); - static u32 hw_atl_utils_get_mpi_mbox_tid(struct aq_hw_s *self); static u32 hw_atl_utils_mpi_get_state(struct aq_hw_s *self); static u32 hw_atl_utils_mif_cmd_get(struct aq_hw_s *self); static u32 hw_atl_utils_mif_addr_get(struct aq_hw_s *self); static u32 hw_atl_utils_rpc_state_get(struct aq_hw_s *self); +static u32 aq_fw1x_rpc_get(struct aq_hw_s *self); int hw_atl_utils_initfw(struct aq_hw_s *self, const struct aq_fw_ops **fw_ops) { @@ -476,6 +476,10 @@ static int hw_atl_utils_init_ucp(struct aq_hw_s *self, self, self->mbox_addr, self->mbox_addr != 0U, 1000U, 10000U); + err = readx_poll_timeout_atomic(aq_fw1x_rpc_get, self, + self->rpc_addr, + self->rpc_addr != 0U, + 1000U, 100000U); return err; } @@ -531,6 +535,12 @@ int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self, self, fw.val, sw.tid == fw.tid, 1000U, 100000U); + if (err < 0) + goto err_exit; + + err = aq_hw_err_from_flags(self); + if (err < 0) + goto err_exit; if (fw.len == 0xFFFFU) { err = hw_atl_utils_fw_rpc_call(self, sw.len); @@ -1025,6 +1035,11 @@ static u32 hw_atl_utils_rpc_state_get(struct aq_hw_s *self) return aq_hw_read_reg(self, HW_ATL_RPC_STATE_ADR); } +static u32 aq_fw1x_rpc_get(struct aq_hw_s *self) +{ + return aq_hw_read_reg(self, HW_ATL_MPI_RPC_ADDR); +} + const struct aq_fw_ops aq_fw_1x_ops = { .init = hw_atl_utils_mpi_create, .deinit = hw_atl_fw1x_deinit, diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c index 97ebf849695f..77a4ed64830f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c @@ -30,6 +30,9 @@ #define HW_ATL_FW3X_EXT_CONTROL_ADDR 0x378 #define HW_ATL_FW3X_EXT_STATE_ADDR 0x37c +#define HW_ATL_FW3X_PTP_ADJ_LSW_ADDR 0x50a0 +#define HW_ATL_FW3X_PTP_ADJ_MSW_ADDR 0x50a4 + #define HW_ATL_FW2X_CAP_PAUSE BIT(CAPS_HI_PAUSE) #define HW_ATL_FW2X_CAP_ASYM_PAUSE BIT(CAPS_HI_ASYMMETRIC_PAUSE) #define HW_ATL_FW2X_CAP_SLEEP_PROXY BIT(CAPS_HI_SLEEP_PROXY) @@ -475,6 +478,14 @@ static void aq_fw3x_enable_ptp(struct aq_hw_s *self, int enable) aq_hw_write_reg(self, HW_ATL_FW3X_EXT_CONTROL_ADDR, ptp_opts); } +static void aq_fw3x_adjust_ptp(struct aq_hw_s *self, uint64_t adj) +{ + aq_hw_write_reg(self, HW_ATL_FW3X_PTP_ADJ_LSW_ADDR, + (adj >> 0) & 0xffffffff); + aq_hw_write_reg(self, HW_ATL_FW3X_PTP_ADJ_MSW_ADDR, + (adj >> 32) & 0xffffffff); +} + static int aq_fw2x_led_control(struct aq_hw_s *self, u32 mode) { if (self->fw_ver_actual < HW_ATL_FW_VER_LED) @@ -633,4 +644,5 @@ const struct aq_fw_ops aq_fw_2x_ops = { .enable_ptp = aq_fw3x_enable_ptp, .led_control = aq_fw2x_led_control, .set_phyloopback = aq_fw2x_set_phyloopback, + .adjust_ptp = aq_fw3x_adjust_ptp, }; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 597e6fd5bfea..fd6e0e48cd51 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -11786,6 +11786,14 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (version_printed++ == 0) pr_info("%s", version); + /* Clear any pending DMA transactions from crash kernel + * while loading driver in capture kernel. + */ + if (is_kdump_kernel()) { + pci_clear_master(pdev); + pcie_flr(pdev); + } + max_irqs = bnxt_get_max_irq(pdev); dev = alloc_etherdev_mq(sizeof(*bp), max_irqs); if (!dev) @@ -11983,10 +11991,10 @@ static void bnxt_shutdown(struct pci_dev *pdev) dev_close(dev); bnxt_ulp_shutdown(bp); + bnxt_clear_int_mode(bp); + pci_disable_device(pdev); if (system_state == SYSTEM_POWER_OFF) { - bnxt_clear_int_mode(bp); - pci_disable_device(pdev); pci_wake_from_d3(pdev, bp->wol); pci_set_power_state(pdev, PCI_D3hot); } diff --git a/drivers/net/ethernet/broadcom/cnic_defs.h b/drivers/net/ethernet/broadcom/cnic_defs.h index b38499774071..99e2c6d4d8c3 100644 --- a/drivers/net/ethernet/broadcom/cnic_defs.h +++ b/drivers/net/ethernet/broadcom/cnic_defs.h @@ -543,13 +543,13 @@ struct l4_kwq_update_pg { #define L4_KWQ_UPDATE_PG_RESERVERD2_SHIFT 2 #endif #if defined(__BIG_ENDIAN) - u16 reserverd3; + u16 reserved3; u8 da0; u8 da1; #elif defined(__LITTLE_ENDIAN) u8 da1; u8 da0; - u16 reserverd3; + u16 reserved3; #endif #if defined(__BIG_ENDIAN) u8 da2; diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index dbf7070fcdba..a3f0f27fc79a 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -652,6 +652,7 @@ #define MACB_CAPS_GEM_HAS_PTP 0x00000040 #define MACB_CAPS_BD_RD_PREFETCH 0x00000080 #define MACB_CAPS_NEEDS_RSTONUBR 0x00000100 +#define MACB_CAPS_MACB_IS_EMAC 0x08000000 #define MACB_CAPS_FIFO_MODE 0x10000000 #define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000 #define MACB_CAPS_SG_DISABLED 0x40000000 diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 4508f0d150da..2c28da1737fe 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -572,8 +572,21 @@ static void macb_mac_config(struct phylink_config *config, unsigned int mode, old_ctrl = ctrl = macb_or_gem_readl(bp, NCFGR); /* Clear all the bits we might set later */ - ctrl &= ~(GEM_BIT(GBE) | MACB_BIT(SPD) | MACB_BIT(FD) | MACB_BIT(PAE) | - GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL)); + ctrl &= ~(MACB_BIT(SPD) | MACB_BIT(FD) | MACB_BIT(PAE)); + + if (bp->caps & MACB_CAPS_MACB_IS_EMAC) { + if (state->interface == PHY_INTERFACE_MODE_RMII) + ctrl |= MACB_BIT(RM9200_RMII); + } else { + ctrl &= ~(GEM_BIT(GBE) | GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL)); + + /* We do not support MLO_PAUSE_RX yet */ + if (state->pause & MLO_PAUSE_TX) + ctrl |= MACB_BIT(PAE); + + if (state->interface == PHY_INTERFACE_MODE_SGMII) + ctrl |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL); + } if (state->speed == SPEED_1000) ctrl |= GEM_BIT(GBE); @@ -583,13 +596,6 @@ static void macb_mac_config(struct phylink_config *config, unsigned int mode, if (state->duplex) ctrl |= MACB_BIT(FD); - /* We do not support MLO_PAUSE_RX yet */ - if (state->pause & MLO_PAUSE_TX) - ctrl |= MACB_BIT(PAE); - - if (state->interface == PHY_INTERFACE_MODE_SGMII) - ctrl |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL); - /* Apply the new configuration, if any */ if (old_ctrl ^ ctrl) macb_or_gem_writel(bp, NCFGR, ctrl); @@ -608,9 +614,10 @@ static void macb_mac_link_down(struct phylink_config *config, unsigned int mode, unsigned int q; u32 ctrl; - for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) - queue_writel(queue, IDR, - bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); + if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) + for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) + queue_writel(queue, IDR, + bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); /* Disable Rx and Tx */ ctrl = macb_readl(bp, NCR) & ~(MACB_BIT(RE) | MACB_BIT(TE)); @@ -627,17 +634,19 @@ static void macb_mac_link_up(struct phylink_config *config, unsigned int mode, struct macb_queue *queue; unsigned int q; - macb_set_tx_clk(bp->tx_clk, bp->speed, ndev); + if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) { + macb_set_tx_clk(bp->tx_clk, bp->speed, ndev); - /* Initialize rings & buffers as clearing MACB_BIT(TE) in link down - * cleared the pipeline and control registers. - */ - bp->macbgem_ops.mog_init_rings(bp); - macb_init_buffers(bp); + /* Initialize rings & buffers as clearing MACB_BIT(TE) in link down + * cleared the pipeline and control registers. + */ + bp->macbgem_ops.mog_init_rings(bp); + macb_init_buffers(bp); - for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) - queue_writel(queue, IER, - bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); + for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) + queue_writel(queue, IER, + bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); + } /* Enable Rx and Tx */ macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(RE) | MACB_BIT(TE)); @@ -3790,6 +3799,10 @@ static int at91ether_open(struct net_device *dev) u32 ctl; int ret; + ret = pm_runtime_get_sync(&lp->pdev->dev); + if (ret < 0) + return ret; + /* Clear internal statistics */ ctl = macb_readl(lp, NCR); macb_writel(lp, NCR, ctl | MACB_BIT(CLRSTAT)); @@ -3854,7 +3867,7 @@ static int at91ether_close(struct net_device *dev) q->rx_buffers, q->rx_buffers_dma); q->rx_buffers = NULL; - return 0; + return pm_runtime_put(&lp->pdev->dev); } /* Transmit packet */ @@ -4037,7 +4050,6 @@ static int at91ether_init(struct platform_device *pdev) struct net_device *dev = platform_get_drvdata(pdev); struct macb *bp = netdev_priv(dev); int err; - u32 reg; bp->queues[0].bp = bp; @@ -4051,11 +4063,7 @@ static int at91ether_init(struct platform_device *pdev) macb_writel(bp, NCR, 0); - reg = MACB_BF(CLK, MACB_CLK_DIV32) | MACB_BIT(BIG); - if (bp->phy_interface == PHY_INTERFACE_MODE_RMII) - reg |= MACB_BIT(RM9200_RMII); - - macb_writel(bp, NCFGR, reg); + macb_writel(bp, NCFGR, MACB_BF(CLK, MACB_CLK_DIV32) | MACB_BIT(BIG)); return 0; } @@ -4214,7 +4222,7 @@ static const struct macb_config sama5d4_config = { }; static const struct macb_config emac_config = { - .caps = MACB_CAPS_NEEDS_RSTONUBR, + .caps = MACB_CAPS_NEEDS_RSTONUBR | MACB_CAPS_MACB_IS_EMAC, .clk_init = at91ether_clk_init, .init = at91ether_init, }; diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 17a4110c2e49..8ff28ed04b7f 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -410,10 +410,19 @@ void bgx_lmac_rx_tx_enable(int node, int bgx_idx, int lmacid, bool enable) lmac = &bgx->lmac[lmacid]; cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG); - if (enable) + if (enable) { cfg |= CMR_PKT_RX_EN | CMR_PKT_TX_EN; - else + + /* enable TX FIFO Underflow interrupt */ + bgx_reg_modify(bgx, lmacid, BGX_GMP_GMI_TXX_INT_ENA_W1S, + GMI_TXX_INT_UNDFLW); + } else { cfg &= ~(CMR_PKT_RX_EN | CMR_PKT_TX_EN); + + /* Disable TX FIFO Underflow interrupt */ + bgx_reg_modify(bgx, lmacid, BGX_GMP_GMI_TXX_INT_ENA_W1C, + GMI_TXX_INT_UNDFLW); + } bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg); if (bgx->is_rgx) @@ -1535,6 +1544,48 @@ static int bgx_init_phy(struct bgx *bgx) return bgx_init_of_phy(bgx); } +static irqreturn_t bgx_intr_handler(int irq, void *data) +{ + struct bgx *bgx = (struct bgx *)data; + u64 status, val; + int lmac; + + for (lmac = 0; lmac < bgx->lmac_count; lmac++) { + status = bgx_reg_read(bgx, lmac, BGX_GMP_GMI_TXX_INT); + if (status & GMI_TXX_INT_UNDFLW) { + pci_err(bgx->pdev, "BGX%d lmac%d UNDFLW\n", + bgx->bgx_id, lmac); + val = bgx_reg_read(bgx, lmac, BGX_CMRX_CFG); + val &= ~CMR_EN; + bgx_reg_write(bgx, lmac, BGX_CMRX_CFG, val); + val |= CMR_EN; + bgx_reg_write(bgx, lmac, BGX_CMRX_CFG, val); + } + /* clear interrupts */ + bgx_reg_write(bgx, lmac, BGX_GMP_GMI_TXX_INT, status); + } + + return IRQ_HANDLED; +} + +static void bgx_register_intr(struct pci_dev *pdev) +{ + struct bgx *bgx = pci_get_drvdata(pdev); + int ret; + + ret = pci_alloc_irq_vectors(pdev, BGX_LMAC_VEC_OFFSET, + BGX_LMAC_VEC_OFFSET, PCI_IRQ_ALL_TYPES); + if (ret < 0) { + pci_err(pdev, "Req for #%d msix vectors failed\n", + BGX_LMAC_VEC_OFFSET); + return; + } + ret = pci_request_irq(pdev, GMPX_GMI_TX_INT, bgx_intr_handler, NULL, + bgx, "BGX%d", bgx->bgx_id); + if (ret) + pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx); +} + static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { int err; @@ -1550,7 +1601,7 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_drvdata(pdev, bgx); - err = pci_enable_device(pdev); + err = pcim_enable_device(pdev); if (err) { dev_err(dev, "Failed to enable PCI device\n"); pci_set_drvdata(pdev, NULL); @@ -1604,6 +1655,8 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) bgx_init_hw(bgx); + bgx_register_intr(pdev); + /* Enable all LMACs */ for (lmac = 0; lmac < bgx->lmac_count; lmac++) { err = bgx_lmac_enable(bgx, lmac); @@ -1620,6 +1673,7 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err_enable: bgx_vnic[bgx->bgx_id] = NULL; + pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx); err_release_regions: pci_release_regions(pdev); err_disable_device: @@ -1637,6 +1691,8 @@ static void bgx_remove(struct pci_dev *pdev) for (lmac = 0; lmac < bgx->lmac_count; lmac++) bgx_lmac_disable(bgx, lmac); + pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx); + bgx_vnic[bgx->bgx_id] = NULL; pci_release_regions(pdev); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h index 25888706bdcd..cdea49392185 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h @@ -180,6 +180,15 @@ #define BGX_GMP_GMI_TXX_BURST 0x38228 #define BGX_GMP_GMI_TXX_MIN_PKT 0x38240 #define BGX_GMP_GMI_TXX_SGMII_CTL 0x38300 +#define BGX_GMP_GMI_TXX_INT 0x38500 +#define BGX_GMP_GMI_TXX_INT_W1S 0x38508 +#define BGX_GMP_GMI_TXX_INT_ENA_W1C 0x38510 +#define BGX_GMP_GMI_TXX_INT_ENA_W1S 0x38518 +#define GMI_TXX_INT_PTP_LOST BIT_ULL(4) +#define GMI_TXX_INT_LATE_COL BIT_ULL(3) +#define GMI_TXX_INT_XSDEF BIT_ULL(2) +#define GMI_TXX_INT_XSCOL BIT_ULL(1) +#define GMI_TXX_INT_UNDFLW BIT_ULL(0) #define BGX_MSIX_VEC_0_29_ADDR 0x400000 /* +(0..29) << 4 */ #define BGX_MSIX_VEC_0_29_CTL 0x400008 diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c index 1ea3372775e6..e94ae9b94dbf 100644 --- a/drivers/net/ethernet/davicom/dm9000.c +++ b/drivers/net/ethernet/davicom/dm9000.c @@ -1405,6 +1405,8 @@ static struct dm9000_plat_data *dm9000_parse_dt(struct device *dev) mac_addr = of_get_mac_address(np); if (!IS_ERR(mac_addr)) ether_addr_copy(pdata->dev_addr, mac_addr); + else if (PTR_ERR(mac_addr) == -EPROBE_DEFER) + return ERR_CAST(mac_addr); return pdata; } diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index b002ab4e5838..77c412a7e7a4 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -2936,13 +2936,6 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) else return -EINVAL; - /* Tell the OS link is going down, the link will go back up when fw - * says it is ready asynchronously - */ - ice_print_link_msg(vsi, false); - netif_carrier_off(netdev); - netif_tx_stop_all_queues(netdev); - /* Set the FC mode and only restart AN if link is up */ status = ice_set_fc(pi, &aq_failures, link_up); @@ -3489,21 +3482,13 @@ ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec, return -EINVAL; } - /* hardware only supports an ITR granularity of 2us */ - if (coalesce_usecs % 2 != 0) { - netdev_info(vsi->netdev, "Invalid value, %s-usecs must be even\n", - c_type_str); - return -EINVAL; - } - if (use_adaptive_coalesce) { rc->itr_setting |= ICE_ITR_DYNAMIC; } else { - /* store user facing value how it was set */ + /* save the user set usecs */ rc->itr_setting = coalesce_usecs; - /* set to static and convert to value HW understands */ - rc->target_itr = - ITR_TO_REG(ITR_REG_ALIGN(rc->itr_setting)); + /* device ITR granularity is in 2 usec increments */ + rc->target_itr = ITR_REG_ALIGN(rc->itr_setting); } return 0; @@ -3597,6 +3582,30 @@ ice_is_coalesce_param_invalid(struct net_device *netdev, } /** + * ice_print_if_odd_usecs - print message if user tries to set odd [tx|rx]-usecs + * @netdev: netdev used for print + * @itr_setting: previous user setting + * @use_adaptive_coalesce: if adaptive coalesce is enabled or being enabled + * @coalesce_usecs: requested value of [tx|rx]-usecs + * @c_type_str: either "rx" or "tx" to match user set field of [tx|rx]-usecs + */ +static void +ice_print_if_odd_usecs(struct net_device *netdev, u16 itr_setting, + u32 use_adaptive_coalesce, u32 coalesce_usecs, + const char *c_type_str) +{ + if (use_adaptive_coalesce) + return; + + itr_setting = ITR_TO_REG(itr_setting); + + if (itr_setting != coalesce_usecs && (coalesce_usecs % 2)) + netdev_info(netdev, "User set %s-usecs to %d, device only supports even values. Rounding down and attempting to set %s-usecs to %d\n", + c_type_str, coalesce_usecs, c_type_str, + ITR_REG_ALIGN(coalesce_usecs)); +} + +/** * __ice_set_coalesce - set ITR/INTRL values for the device * @netdev: pointer to the netdev associated with this query * @ec: ethtool structure to fill with driver's coalesce settings @@ -3616,8 +3625,19 @@ __ice_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec, return -EINVAL; if (q_num < 0) { + struct ice_q_vector *q_vector = vsi->q_vectors[0]; int v_idx; + if (q_vector) { + ice_print_if_odd_usecs(netdev, q_vector->rx.itr_setting, + ec->use_adaptive_rx_coalesce, + ec->rx_coalesce_usecs, "rx"); + + ice_print_if_odd_usecs(netdev, q_vector->tx.itr_setting, + ec->use_adaptive_tx_coalesce, + ec->tx_coalesce_usecs, "tx"); + } + ice_for_each_q_vector(vsi, v_idx) { /* In some cases if DCB is configured the num_[rx|tx]q * can be less than vsi->num_q_vectors. This check diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 14a1bf445889..7ee00a128663 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -222,7 +222,7 @@ enum ice_rx_dtype { #define ICE_ITR_GRAN_S 1 /* ITR granularity is always 2us */ #define ICE_ITR_GRAN_US BIT(ICE_ITR_GRAN_S) #define ICE_ITR_MASK 0x1FFE /* ITR register value alignment mask */ -#define ITR_REG_ALIGN(setting) __ALIGN_MASK(setting, ~ICE_ITR_MASK) +#define ITR_REG_ALIGN(setting) ((setting) & ICE_ITR_MASK) #define ICE_ITR_ADAPTIVE_MIN_INC 0x0002 #define ICE_ITR_ADAPTIVE_MIN_USECS 0x0002 diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 262714d5f54a..75c70d432c72 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -1874,6 +1874,48 @@ error_param: } /** + * ice_wait_on_vf_reset - poll to make sure a given VF is ready after reset + * @vf: The VF being resseting + * + * The max poll time is about ~800ms, which is about the maximum time it takes + * for a VF to be reset and/or a VF driver to be removed. + */ +static void ice_wait_on_vf_reset(struct ice_vf *vf) +{ + int i; + + for (i = 0; i < ICE_MAX_VF_RESET_TRIES; i++) { + if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) + break; + msleep(ICE_MAX_VF_RESET_SLEEP_MS); + } +} + +/** + * ice_check_vf_ready_for_cfg - check if VF is ready to be configured/queried + * @vf: VF to check if it's ready to be configured/queried + * + * The purpose of this function is to make sure the VF is not in reset, not + * disabled, and initialized so it can be configured and/or queried by a host + * administrator. + */ +static int ice_check_vf_ready_for_cfg(struct ice_vf *vf) +{ + struct ice_pf *pf; + + ice_wait_on_vf_reset(vf); + + if (ice_is_vf_disabled(vf)) + return -EINVAL; + + pf = vf->pf; + if (ice_check_vf_init(pf, vf)) + return -EBUSY; + + return 0; +} + +/** * ice_set_vf_spoofchk * @netdev: network interface device structure * @vf_id: VF identifier @@ -1890,16 +1932,16 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) enum ice_status status; struct device *dev; struct ice_vf *vf; - int ret = 0; + int ret; dev = ice_pf_to_dev(pf); if (ice_validate_vf_id(pf, vf_id)) return -EINVAL; vf = &pf->vf[vf_id]; - - if (ice_check_vf_init(pf, vf)) - return -EBUSY; + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + return ret; vf_vsi = pf->vsi[vf->lan_vsi_idx]; if (!vf_vsi) { @@ -2696,7 +2738,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, struct ice_vsi *vsi; struct device *dev; struct ice_vf *vf; - int ret = 0; + int ret; dev = ice_pf_to_dev(pf); if (ice_validate_vf_id(pf, vf_id)) @@ -2714,13 +2756,15 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, vf = &pf->vf[vf_id]; vsi = pf->vsi[vf->lan_vsi_idx]; - if (ice_check_vf_init(pf, vf)) - return -EBUSY; + + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + return ret; if (le16_to_cpu(vsi->info.pvid) == vlanprio) { /* duplicate request, so just return success */ dev_dbg(dev, "Duplicate pvid %d request\n", vlanprio); - return ret; + return 0; } /* If PVID, then remove all filters on the old VLAN */ @@ -2731,7 +2775,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, if (vlan_id || qos) { ret = ice_vsi_manage_pvid(vsi, vlanprio, true); if (ret) - goto error_set_pvid; + return ret; } else { ice_vsi_manage_pvid(vsi, 0, false); vsi->info.pvid = 0; @@ -2744,7 +2788,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, /* add new VLAN filter for each MAC */ ret = ice_vsi_add_vlan(vsi, vlan_id); if (ret) - goto error_set_pvid; + return ret; } /* The Port VLAN needs to be saved across resets the same as the @@ -2752,8 +2796,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, */ vf->port_vlan_id = le16_to_cpu(vsi->info.pvid); -error_set_pvid: - return ret; + return 0; } /** @@ -3237,23 +3280,6 @@ ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi) } /** - * ice_wait_on_vf_reset - * @vf: The VF being resseting - * - * Poll to make sure a given VF is ready after reset - */ -static void ice_wait_on_vf_reset(struct ice_vf *vf) -{ - int i; - - for (i = 0; i < ICE_MAX_VF_RESET_WAIT; i++) { - if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) - break; - msleep(20); - } -} - -/** * ice_set_vf_mac * @netdev: network interface device structure * @vf_id: VF identifier @@ -3265,29 +3291,21 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) { struct ice_pf *pf = ice_netdev_to_pf(netdev); struct ice_vf *vf; - int ret = 0; + int ret; if (ice_validate_vf_id(pf, vf_id)) return -EINVAL; - vf = &pf->vf[vf_id]; - /* Don't set MAC on disabled VF */ - if (ice_is_vf_disabled(vf)) - return -EINVAL; - - /* In case VF is in reset mode, wait until it is completed. Depending - * on factors like queue disabling routine, this could take ~250ms - */ - ice_wait_on_vf_reset(vf); - - if (ice_check_vf_init(pf, vf)) - return -EBUSY; - if (is_zero_ether_addr(mac) || is_multicast_ether_addr(mac)) { netdev_err(netdev, "%pM not a valid unicast address\n", mac); return -EINVAL; } + vf = &pf->vf[vf_id]; + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + return ret; + /* copy MAC into dflt_lan_addr and trigger a VF reset. The reset * flow will use the updated dflt_lan_addr and add a MAC filter * using ice_add_mac. Also set pf_set_mac to indicate that the PF has @@ -3299,7 +3317,7 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) vf_id, mac); ice_vc_reset_vf(vf); - return ret; + return 0; } /** @@ -3314,22 +3332,15 @@ int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) { struct ice_pf *pf = ice_netdev_to_pf(netdev); struct ice_vf *vf; + int ret; if (ice_validate_vf_id(pf, vf_id)) return -EINVAL; vf = &pf->vf[vf_id]; - /* Don't set Trusted Mode on disabled VF */ - if (ice_is_vf_disabled(vf)) - return -EINVAL; - - /* In case VF is in reset mode, wait until it is completed. Depending - * on factors like queue disabling routine, this could take ~250ms - */ - ice_wait_on_vf_reset(vf); - - if (ice_check_vf_init(pf, vf)) - return -EBUSY; + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + return ret; /* Check if already trusted */ if (trusted == vf->trusted) @@ -3355,13 +3366,15 @@ int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state) { struct ice_pf *pf = ice_netdev_to_pf(netdev); struct ice_vf *vf; + int ret; if (ice_validate_vf_id(pf, vf_id)) return -EINVAL; vf = &pf->vf[vf_id]; - if (ice_check_vf_init(pf, vf)) - return -EBUSY; + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + return ret; switch (link_state) { case IFLA_VF_LINK_STATE_AUTO: @@ -3397,14 +3410,15 @@ int ice_get_vf_stats(struct net_device *netdev, int vf_id, struct ice_eth_stats *stats; struct ice_vsi *vsi; struct ice_vf *vf; + int ret; if (ice_validate_vf_id(pf, vf_id)) return -EINVAL; vf = &pf->vf[vf_id]; - - if (ice_check_vf_init(pf, vf)) - return -EBUSY; + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + return ret; vsi = pf->vsi[vf->lan_vsi_idx]; if (!vsi) diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h index 4647d636ed36..ac67982751df 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h @@ -38,7 +38,8 @@ #define ICE_MAX_POLICY_INTR_PER_VF 33 #define ICE_MIN_INTR_PER_VF (ICE_MIN_QS_PER_VF + 1) #define ICE_DFLT_INTR_PER_VF (ICE_DFLT_QS_PER_VF + 1) -#define ICE_MAX_VF_RESET_WAIT 15 +#define ICE_MAX_VF_RESET_TRIES 40 +#define ICE_MAX_VF_RESET_SLEEP_MS 20 #define ice_for_each_vf(pf, i) \ for ((i) = 0; (i) < (pf)->num_alloc_vfs; (i)++) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c index 3a975641f902..20b907dc1e29 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c @@ -200,7 +200,7 @@ int mlx5e_health_report(struct mlx5e_priv *priv, netdev_err(priv->netdev, err_str); if (!reporter) - return err_ctx->recover(&err_ctx->ctx); + return err_ctx->recover(err_ctx->ctx); return devlink_health_report(reporter, err_str, err_ctx); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index 7c8796d9743f..a226277b0980 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -179,6 +179,14 @@ mlx5e_tx_dma_unmap(struct device *pdev, struct mlx5e_sq_dma *dma) } } +static inline void mlx5e_rqwq_reset(struct mlx5e_rq *rq) +{ + if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) + mlx5_wq_ll_reset(&rq->mpwqe.wq); + else + mlx5_wq_cyc_reset(&rq->wqe.wq); +} + /* SW parser related functions */ struct mlx5e_swp_spec { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 454d3459bd8b..966983674663 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -712,6 +712,9 @@ int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state) if (!in) return -ENOMEM; + if (curr_state == MLX5_RQC_STATE_RST && next_state == MLX5_RQC_STATE_RDY) + mlx5e_rqwq_reset(rq); + rqc = MLX5_ADDR_OF(modify_rq_in, in, ctx); MLX5_SET(modify_rq_in, in, rq_state, curr_state); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 5acf60b1bbfe..e49acd0c5da5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -459,12 +459,16 @@ static void esw_destroy_legacy_table(struct mlx5_eswitch *esw) static int esw_legacy_enable(struct mlx5_eswitch *esw) { - int ret; + struct mlx5_vport *vport; + int ret, i; ret = esw_create_legacy_table(esw); if (ret) return ret; + mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) + vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO; + ret = mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_LEGACY_SRIOV_VPORT_EVENTS); if (ret) esw_destroy_legacy_table(esw); @@ -2452,25 +2456,17 @@ out: int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting) { - int err = 0; - if (!esw) return -EOPNOTSUPP; if (!ESW_ALLOWED(esw)) return -EPERM; - mutex_lock(&esw->state_lock); - if (esw->mode != MLX5_ESWITCH_LEGACY) { - err = -EOPNOTSUPP; - goto out; - } + if (esw->mode != MLX5_ESWITCH_LEGACY) + return -EOPNOTSUPP; *setting = esw->fdb_table.legacy.vepa_uplink_rule ? 1 : 0; - -out: - mutex_unlock(&esw->state_lock); - return err; + return 0; } int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 979f13bdc203..1a57b2bd74b8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1172,7 +1172,7 @@ static int esw_offloads_start(struct mlx5_eswitch *esw, return -EINVAL; } - mlx5_eswitch_disable(esw, true); + mlx5_eswitch_disable(esw, false); mlx5_eswitch_update_num_of_vfs(esw, esw->dev->priv.sriov.num_vfs); err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_OFFLOADS); if (err) { @@ -2065,7 +2065,7 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw, { int err, err1; - mlx5_eswitch_disable(esw, true); + mlx5_eswitch_disable(esw, false); err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_LEGACY); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c index c5a446e295aa..4276194b633f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c @@ -35,7 +35,7 @@ static const unsigned int ESW_POOLS[] = { 4 * 1024 * 1024, 1 * 1024 * 1024, 64 * 1024, - 4 * 1024, }; + 128 }; struct mlx5_esw_chains_priv { struct rhashtable chains_ht; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index c6c7d1defbd7..aade62a9ee5c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -2307,7 +2307,9 @@ static int dr_ste_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, struct mlx5dr_cmd_vport_cap *vport_cap; struct mlx5dr_domain *dmn = sb->dmn; struct mlx5dr_cmd_caps *caps; + u8 *bit_mask = sb->bit_mask; u8 *tag = hw_ste->tag; + bool source_gvmi_set; DR_STE_SET_TAG(src_gvmi_qp, tag, source_qp, misc, source_sqn); @@ -2328,7 +2330,8 @@ static int dr_ste_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, if (!vport_cap) return -EINVAL; - if (vport_cap->vport_gvmi) + source_gvmi_set = MLX5_GET(ste_src_gvmi_qp, bit_mask, source_gvmi); + if (vport_cap->vport_gvmi && source_gvmi_set) MLX5_SET(ste_src_gvmi_qp, tag, source_gvmi, vport_cap->vport_gvmi); misc->source_eswitch_owner_vhca_id = 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index 3abfc8125926..c2027192e21e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -66,15 +66,20 @@ static int mlx5_cmd_dr_create_flow_table(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *next_ft) { struct mlx5dr_table *tbl; + u32 flags; int err; if (mlx5_dr_is_fw_table(ft->flags)) return mlx5_fs_cmd_get_fw_cmds()->create_flow_table(ns, ft, log_size, next_ft); + flags = ft->flags; + /* turn off encap/decap if not supported for sw-str by fw */ + if (!MLX5_CAP_FLOWTABLE(ns->dev, sw_owner_reformat_supported)) + flags = ft->flags & ~(MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT | + MLX5_FLOW_TABLE_TUNNEL_EN_DECAP); - tbl = mlx5dr_table_create(ns->fs_dr_domain.dr_domain, - ft->level, ft->flags); + tbl = mlx5dr_table_create(ns->fs_dr_domain.dr_domain, ft->level, flags); if (!tbl) { mlx5_core_err(ns->dev, "Failed creating dr flow_table\n"); return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c index 02f7e4a39578..01f075fac276 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c @@ -94,6 +94,13 @@ void mlx5_wq_cyc_wqe_dump(struct mlx5_wq_cyc *wq, u16 ix, u8 nstrides) print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1, wqe, len, false); } +void mlx5_wq_cyc_reset(struct mlx5_wq_cyc *wq) +{ + wq->wqe_ctr = 0; + wq->cur_sz = 0; + mlx5_wq_cyc_update_db_record(wq); +} + int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, struct mlx5_wq_ctrl *wq_ctrl) @@ -192,6 +199,19 @@ err_db_free: return err; } +static void mlx5_wq_ll_init_list(struct mlx5_wq_ll *wq) +{ + struct mlx5_wqe_srq_next_seg *next_seg; + int i; + + for (i = 0; i < wq->fbc.sz_m1; i++) { + next_seg = mlx5_wq_ll_get_wqe(wq, i); + next_seg->next_wqe_index = cpu_to_be16(i + 1); + } + next_seg = mlx5_wq_ll_get_wqe(wq, i); + wq->tail_next = &next_seg->next_wqe_index; +} + int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *wqc, struct mlx5_wq_ll *wq, struct mlx5_wq_ctrl *wq_ctrl) @@ -199,9 +219,7 @@ int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, u8 log_wq_stride = MLX5_GET(wq, wqc, log_wq_stride); u8 log_wq_sz = MLX5_GET(wq, wqc, log_wq_sz); struct mlx5_frag_buf_ctrl *fbc = &wq->fbc; - struct mlx5_wqe_srq_next_seg *next_seg; int err; - int i; err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node); if (err) { @@ -220,13 +238,7 @@ int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, mlx5_init_fbc(wq_ctrl->buf.frags, log_wq_stride, log_wq_sz, fbc); - for (i = 0; i < fbc->sz_m1; i++) { - next_seg = mlx5_wq_ll_get_wqe(wq, i); - next_seg->next_wqe_index = cpu_to_be16(i + 1); - } - next_seg = mlx5_wq_ll_get_wqe(wq, i); - wq->tail_next = &next_seg->next_wqe_index; - + mlx5_wq_ll_init_list(wq); wq_ctrl->mdev = mdev; return 0; @@ -237,6 +249,15 @@ err_db_free: return err; } +void mlx5_wq_ll_reset(struct mlx5_wq_ll *wq) +{ + wq->head = 0; + wq->wqe_ctr = 0; + wq->cur_sz = 0; + mlx5_wq_ll_init_list(wq); + mlx5_wq_ll_update_db_record(wq); +} + void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl) { mlx5_frag_buf_free(wq_ctrl->mdev, &wq_ctrl->buf); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h index d9a94bc223c0..4cadc336593f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h @@ -80,6 +80,7 @@ int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *wqc, struct mlx5_wq_cyc *wq, struct mlx5_wq_ctrl *wq_ctrl); void mlx5_wq_cyc_wqe_dump(struct mlx5_wq_cyc *wq, u16 ix, u8 nstrides); +void mlx5_wq_cyc_reset(struct mlx5_wq_cyc *wq); int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, @@ -92,6 +93,7 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *wqc, struct mlx5_wq_ll *wq, struct mlx5_wq_ctrl *wq_ctrl); +void mlx5_wq_ll_reset(struct mlx5_wq_ll *wq); void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl); diff --git a/drivers/net/ethernet/micrel/ks8851_mll.c b/drivers/net/ethernet/micrel/ks8851_mll.c index a41a90c589db..1c9e70c8cc30 100644 --- a/drivers/net/ethernet/micrel/ks8851_mll.c +++ b/drivers/net/ethernet/micrel/ks8851_mll.c @@ -157,24 +157,6 @@ static int msg_enable; */ /** - * ks_rdreg8 - read 8 bit register from device - * @ks : The chip information - * @offset: The register address - * - * Read a 8bit register from the chip, returning the result - */ -static u8 ks_rdreg8(struct ks_net *ks, int offset) -{ - u16 data; - u8 shift_bit = offset & 0x03; - u8 shift_data = (offset & 1) << 3; - ks->cmd_reg_cache = (u16) offset | (u16)(BE0 << shift_bit); - iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd); - data = ioread16(ks->hw_addr); - return (u8)(data >> shift_data); -} - -/** * ks_rdreg16 - read 16 bit register from device * @ks : The chip information * @offset: The register address @@ -184,28 +166,12 @@ static u8 ks_rdreg8(struct ks_net *ks, int offset) static u16 ks_rdreg16(struct ks_net *ks, int offset) { - ks->cmd_reg_cache = (u16)offset | ((BE1 | BE0) << (offset & 0x02)); + ks->cmd_reg_cache = (u16)offset | ((BE3 | BE2) >> (offset & 0x02)); iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd); return ioread16(ks->hw_addr); } /** - * ks_wrreg8 - write 8bit register value to chip - * @ks: The chip information - * @offset: The register address - * @value: The value to write - * - */ -static void ks_wrreg8(struct ks_net *ks, int offset, u8 value) -{ - u8 shift_bit = (offset & 0x03); - u16 value_write = (u16)(value << ((offset & 1) << 3)); - ks->cmd_reg_cache = (u16)offset | (BE0 << shift_bit); - iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd); - iowrite16(value_write, ks->hw_addr); -} - -/** * ks_wrreg16 - write 16bit register value to chip * @ks: The chip information * @offset: The register address @@ -215,7 +181,7 @@ static void ks_wrreg8(struct ks_net *ks, int offset, u8 value) static void ks_wrreg16(struct ks_net *ks, int offset, u16 value) { - ks->cmd_reg_cache = (u16)offset | ((BE1 | BE0) << (offset & 0x02)); + ks->cmd_reg_cache = (u16)offset | ((BE3 | BE2) >> (offset & 0x02)); iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd); iowrite16(value, ks->hw_addr); } @@ -231,7 +197,7 @@ static inline void ks_inblk(struct ks_net *ks, u16 *wptr, u32 len) { len >>= 1; while (len--) - *wptr++ = (u16)ioread16(ks->hw_addr); + *wptr++ = be16_to_cpu(ioread16(ks->hw_addr)); } /** @@ -245,7 +211,7 @@ static inline void ks_outblk(struct ks_net *ks, u16 *wptr, u32 len) { len >>= 1; while (len--) - iowrite16(*wptr++, ks->hw_addr); + iowrite16(cpu_to_be16(*wptr++), ks->hw_addr); } static void ks_disable_int(struct ks_net *ks) @@ -324,8 +290,7 @@ static void ks_read_config(struct ks_net *ks) u16 reg_data = 0; /* Regardless of bus width, 8 bit read should always work.*/ - reg_data = ks_rdreg8(ks, KS_CCR) & 0x00FF; - reg_data |= ks_rdreg8(ks, KS_CCR+1) << 8; + reg_data = ks_rdreg16(ks, KS_CCR); /* addr/data bus are multiplexed */ ks->sharedbus = (reg_data & CCR_SHARED) == CCR_SHARED; @@ -429,7 +394,7 @@ static inline void ks_read_qmu(struct ks_net *ks, u16 *buf, u32 len) /* 1. set sudo DMA mode */ ks_wrreg16(ks, KS_RXFDPR, RXFDPR_RXFPAI); - ks_wrreg8(ks, KS_RXQCR, (ks->rc_rxqcr | RXQCR_SDA) & 0xff); + ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA); /* 2. read prepend data */ /** @@ -446,7 +411,7 @@ static inline void ks_read_qmu(struct ks_net *ks, u16 *buf, u32 len) ks_inblk(ks, buf, ALIGN(len, 4)); /* 4. reset sudo DMA Mode */ - ks_wrreg8(ks, KS_RXQCR, ks->rc_rxqcr); + ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr); } /** @@ -679,13 +644,13 @@ static void ks_write_qmu(struct ks_net *ks, u8 *pdata, u16 len) ks->txh.txw[1] = cpu_to_le16(len); /* 1. set sudo-DMA mode */ - ks_wrreg8(ks, KS_RXQCR, (ks->rc_rxqcr | RXQCR_SDA) & 0xff); + ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA); /* 2. write status/lenth info */ ks_outblk(ks, ks->txh.txw, 4); /* 3. write pkt data */ ks_outblk(ks, (u16 *)pdata, ALIGN(len, 4)); /* 4. reset sudo-DMA mode */ - ks_wrreg8(ks, KS_RXQCR, ks->rc_rxqcr); + ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr); /* 5. Enqueue Tx(move the pkt from TX buffer into TXQ) */ ks_wrreg16(ks, KS_TXQCR, TXQCR_METFE); /* 6. wait until TXQCR_METFE is auto-cleared */ diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c index b38820849faa..1135a18019c7 100644 --- a/drivers/net/ethernet/mscc/ocelot_board.c +++ b/drivers/net/ethernet/mscc/ocelot_board.c @@ -114,6 +114,14 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg) if (err != 4) break; + /* At this point the IFH was read correctly, so it is safe to + * presume that there is no error. The err needs to be reset + * otherwise a frame could come in CPU queue between the while + * condition and the check for error later on. And in that case + * the new frame is just removed and not processed. + */ + err = 0; + ocelot_parse_ifh(ifh, &info); ocelot_port = ocelot->ports[info.port]; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index 87f82f36812f..46107de5e6c3 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -103,7 +103,7 @@ int ionic_heartbeat_check(struct ionic *ionic) { struct ionic_dev *idev = &ionic->idev; unsigned long hb_time; - u32 fw_status; + u8 fw_status; u32 hb; /* wait a little more than one second before testing again */ @@ -111,9 +111,12 @@ int ionic_heartbeat_check(struct ionic *ionic) if (time_before(hb_time, (idev->last_hb_time + ionic->watchdog_period))) return 0; - /* firmware is useful only if fw_status is non-zero */ - fw_status = ioread32(&idev->dev_info_regs->fw_status); - if (!fw_status) + /* firmware is useful only if the running bit is set and + * fw_status != 0xff (bad PCI read) + */ + fw_status = ioread8(&idev->dev_info_regs->fw_status); + if (fw_status == 0xff || + !(fw_status & IONIC_FW_STS_F_RUNNING)) return -ENXIO; /* early FW has no heartbeat, else FW will return non-zero */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_if.h b/drivers/net/ethernet/pensando/ionic/ionic_if.h index ce07c2931a72..54547d53b0f2 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_if.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_if.h @@ -2445,6 +2445,7 @@ union ionic_dev_info_regs { u8 version; u8 asic_type; u8 asic_rev; +#define IONIC_FW_STS_F_RUNNING 0x1 u8 fw_status; u32 fw_heartbeat; char fw_version[IONIC_DEVINFO_FWVERS_BUFLEN]; diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index e8a1b27db84d..234c6f30effb 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -163,6 +163,8 @@ struct qede_rdma_dev { struct list_head entry; struct list_head rdma_event_list; struct workqueue_struct *rdma_wq; + struct kref refcnt; + struct completion event_comp; bool exp_recovery; }; diff --git a/drivers/net/ethernet/qlogic/qede/qede_rdma.c b/drivers/net/ethernet/qlogic/qede/qede_rdma.c index ffabc2d2f082..2d873ae8a234 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_rdma.c +++ b/drivers/net/ethernet/qlogic/qede/qede_rdma.c @@ -59,6 +59,9 @@ static void _qede_rdma_dev_add(struct qede_dev *edev) static int qede_rdma_create_wq(struct qede_dev *edev) { INIT_LIST_HEAD(&edev->rdma_info.rdma_event_list); + kref_init(&edev->rdma_info.refcnt); + init_completion(&edev->rdma_info.event_comp); + edev->rdma_info.rdma_wq = create_singlethread_workqueue("rdma_wq"); if (!edev->rdma_info.rdma_wq) { DP_NOTICE(edev, "qedr: Could not create workqueue\n"); @@ -83,8 +86,23 @@ static void qede_rdma_cleanup_event(struct qede_dev *edev) } } +static void qede_rdma_complete_event(struct kref *ref) +{ + struct qede_rdma_dev *rdma_dev = + container_of(ref, struct qede_rdma_dev, refcnt); + + /* no more events will be added after this */ + complete(&rdma_dev->event_comp); +} + static void qede_rdma_destroy_wq(struct qede_dev *edev) { + /* Avoid race with add_event flow, make sure it finishes before + * we start accessing the list and cleaning up the work + */ + kref_put(&edev->rdma_info.refcnt, qede_rdma_complete_event); + wait_for_completion(&edev->rdma_info.event_comp); + qede_rdma_cleanup_event(edev); destroy_workqueue(edev->rdma_info.rdma_wq); } @@ -310,15 +328,24 @@ static void qede_rdma_add_event(struct qede_dev *edev, if (!edev->rdma_info.qedr_dev) return; + /* We don't want the cleanup flow to start while we're allocating and + * scheduling the work + */ + if (!kref_get_unless_zero(&edev->rdma_info.refcnt)) + return; /* already being destroyed */ + event_node = qede_rdma_get_free_event_node(edev); if (!event_node) - return; + goto out; event_node->event = event; event_node->ptr = edev; INIT_WORK(&event_node->work, qede_rdma_handle_event); queue_work(edev->rdma_info.rdma_wq, &event_node->work); + +out: + kref_put(&edev->rdma_info.refcnt, qede_rdma_complete_event); } void qede_rdma_dev_event_open(struct qede_dev *edev) diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index 7d68b28bb893..a62229a8b1a4 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -410,7 +410,7 @@ static int bcm5481_config_aneg(struct phy_device *phydev) struct device_node *np = phydev->mdio.dev.of_node; int ret; - /* Aneg firsly. */ + /* Aneg firstly. */ ret = genphy_config_aneg(phydev); /* Then we can set up the delay. */ @@ -463,7 +463,7 @@ static int bcm54616s_config_aneg(struct phy_device *phydev) { int ret; - /* Aneg firsly. */ + /* Aneg firstly. */ if (phydev->dev_flags & PHY_BCM_FLAGS_MODE_1000BX) ret = genphy_c37_config_aneg(phydev); else diff --git a/drivers/net/phy/mdio-bcm-iproc.c b/drivers/net/phy/mdio-bcm-iproc.c index 7e9975d25066..f1ded03f0229 100644 --- a/drivers/net/phy/mdio-bcm-iproc.c +++ b/drivers/net/phy/mdio-bcm-iproc.c @@ -178,6 +178,23 @@ static int iproc_mdio_remove(struct platform_device *pdev) return 0; } +#ifdef CONFIG_PM_SLEEP +int iproc_mdio_resume(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct iproc_mdio_priv *priv = platform_get_drvdata(pdev); + + /* restore the mii clock configuration */ + iproc_mdio_config_clk(priv->base); + + return 0; +} + +static const struct dev_pm_ops iproc_mdio_pm_ops = { + .resume = iproc_mdio_resume +}; +#endif /* CONFIG_PM_SLEEP */ + static const struct of_device_id iproc_mdio_of_match[] = { { .compatible = "brcm,iproc-mdio", }, { /* sentinel */ }, @@ -188,6 +205,9 @@ static struct platform_driver iproc_mdio_driver = { .driver = { .name = "iproc-mdio", .of_match_table = iproc_mdio_of_match, +#ifdef CONFIG_PM_SLEEP + .pm = &iproc_mdio_pm_ops, +#endif }, .probe = iproc_mdio_probe, .remove = iproc_mdio_remove, diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c index 43db442b1373..cdc96968b0f4 100644 --- a/drivers/net/wireguard/device.c +++ b/drivers/net/wireguard/device.c @@ -258,6 +258,8 @@ static void wg_setup(struct net_device *dev) enum { WG_NETDEV_FEATURES = NETIF_F_HW_CSUM | NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO | NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA }; + const int overhead = MESSAGE_MINIMUM_LENGTH + sizeof(struct udphdr) + + max(sizeof(struct ipv6hdr), sizeof(struct iphdr)); dev->netdev_ops = &netdev_ops; dev->hard_header_len = 0; @@ -271,9 +273,8 @@ static void wg_setup(struct net_device *dev) dev->features |= WG_NETDEV_FEATURES; dev->hw_features |= WG_NETDEV_FEATURES; dev->hw_enc_features |= WG_NETDEV_FEATURES; - dev->mtu = ETH_DATA_LEN - MESSAGE_MINIMUM_LENGTH - - sizeof(struct udphdr) - - max(sizeof(struct ipv6hdr), sizeof(struct iphdr)); + dev->mtu = ETH_DATA_LEN - overhead; + dev->max_mtu = round_down(INT_MAX, MESSAGE_PADDING_MULTIPLE) - overhead; SET_NETDEV_DEVTYPE(dev, &device_type); diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index 9c6bab9c981f..4a153894cee2 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -118,10 +118,13 @@ static void wg_receive_handshake_packet(struct wg_device *wg, under_load = skb_queue_len(&wg->incoming_handshakes) >= MAX_QUEUED_INCOMING_HANDSHAKES / 8; - if (under_load) + if (under_load) { last_under_load = ktime_get_coarse_boottime_ns(); - else if (last_under_load) + } else if (last_under_load) { under_load = !wg_birthdate_has_expired(last_under_load, 1); + if (!under_load) + last_under_load = 0; + } mac_state = wg_cookie_validate_packet(&wg->cookie_checker, skb, under_load); if ((under_load && mac_state == VALID_MAC_WITH_COOKIE) || diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c index c13260563446..7348c10cbae3 100644 --- a/drivers/net/wireguard/send.c +++ b/drivers/net/wireguard/send.c @@ -143,16 +143,22 @@ static void keep_key_fresh(struct wg_peer *peer) static unsigned int calculate_skb_padding(struct sk_buff *skb) { + unsigned int padded_size, last_unit = skb->len; + + if (unlikely(!PACKET_CB(skb)->mtu)) + return ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE) - last_unit; + /* We do this modulo business with the MTU, just in case the networking * layer gives us a packet that's bigger than the MTU. In that case, we * wouldn't want the final subtraction to overflow in the case of the - * padded_size being clamped. + * padded_size being clamped. Fortunately, that's very rarely the case, + * so we optimize for that not happening. */ - unsigned int last_unit = skb->len % PACKET_CB(skb)->mtu; - unsigned int padded_size = ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE); + if (unlikely(last_unit > PACKET_CB(skb)->mtu)) + last_unit %= PACKET_CB(skb)->mtu; - if (padded_size > PACKET_CB(skb)->mtu) - padded_size = PACKET_CB(skb)->mtu; + padded_size = min(PACKET_CB(skb)->mtu, + ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE)); return padded_size - last_unit; } diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c index 262f3b5c819d..b0d6541582d3 100644 --- a/drivers/net/wireguard/socket.c +++ b/drivers/net/wireguard/socket.c @@ -432,7 +432,6 @@ void wg_socket_reinit(struct wg_device *wg, struct sock *new4, wg->incoming_port = ntohs(inet_sk(new4)->inet_sport); mutex_unlock(&wg->socket_update_lock); synchronize_rcu(); - synchronize_net(); sock_free(old4); sock_free(old6); } diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c index 720c89d6066e..4ac8cb262559 100644 --- a/drivers/nfc/pn544/i2c.c +++ b/drivers/nfc/pn544/i2c.c @@ -225,6 +225,7 @@ static void pn544_hci_i2c_platform_init(struct pn544_i2c_phy *phy) out: gpiod_set_value_cansleep(phy->gpiod_en, !phy->en_polarity); + usleep_range(10000, 15000); } static void pn544_hci_i2c_enable_mode(struct pn544_i2c_phy *phy, int run_mode) diff --git a/drivers/nfc/pn544/pn544.c b/drivers/nfc/pn544/pn544.c index 2b83156efe3f..b788870473e8 100644 --- a/drivers/nfc/pn544/pn544.c +++ b/drivers/nfc/pn544/pn544.c @@ -682,7 +682,7 @@ static int pn544_hci_tm_send(struct nfc_hci_dev *hdev, struct sk_buff *skb) static int pn544_hci_check_presence(struct nfc_hci_dev *hdev, struct nfc_target *target) { - pr_debug("supported protocol %d\b", target->supported_protocols); + pr_debug("supported protocol %d\n", target->supported_protocols); if (target->supported_protocols & (NFC_PROTO_ISO14443_MASK | NFC_PROTO_ISO14443_B_MASK)) { return nfc_hci_send_cmd(hdev, target->hci_reader_gate, diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 5dc32b72e7fa..a4d8c90ee7cc 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -66,8 +66,8 @@ MODULE_PARM_DESC(streams, "turn on support for Streams write directives"); * nvme_reset_wq - hosts nvme reset works * nvme_delete_wq - hosts nvme delete works * - * nvme_wq will host works such are scan, aen handling, fw activation, - * keep-alive error recovery, periodic reconnects etc. nvme_reset_wq + * nvme_wq will host works such as scan, aen handling, fw activation, + * keep-alive, periodic reconnects etc. nvme_reset_wq * runs reset works which also flush works hosted on nvme_wq for * serialization purposes. nvme_delete_wq host controller deletion * works which flush reset works for serialization. @@ -976,7 +976,7 @@ static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status) startka = true; spin_unlock_irqrestore(&ctrl->lock, flags); if (startka) - schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ); + queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ); } static int nvme_keep_alive(struct nvme_ctrl *ctrl) @@ -1006,7 +1006,7 @@ static void nvme_keep_alive_work(struct work_struct *work) dev_dbg(ctrl->device, "reschedule traffic based keep-alive timer\n"); ctrl->comp_seen = false; - schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ); + queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ); return; } @@ -1023,7 +1023,7 @@ static void nvme_start_keep_alive(struct nvme_ctrl *ctrl) if (unlikely(ctrl->kato == 0)) return; - schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ); + queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ); } void nvme_stop_keep_alive(struct nvme_ctrl *ctrl) @@ -1165,8 +1165,8 @@ static int nvme_identify_ns(struct nvme_ctrl *ctrl, static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid, unsigned int dword11, void *buffer, size_t buflen, u32 *result) { + union nvme_result res = { 0 }; struct nvme_command c; - union nvme_result res; int ret; memset(&c, 0, sizeof(c)); @@ -3867,7 +3867,7 @@ static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl) if (!log) return; - if (nvme_get_log(ctrl, NVME_NSID_ALL, 0, NVME_LOG_FW_SLOT, log, + if (nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_FW_SLOT, 0, log, sizeof(*log), 0)) dev_warn(ctrl->device, "Get FW SLOT INFO log error\n"); kfree(log); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 797c18337d96..a11900cf3a36 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -715,6 +715,7 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) } INIT_WORK(&ctrl->ana_work, nvme_ana_work); + kfree(ctrl->ana_log_buf); ctrl->ana_log_buf = kmalloc(ctrl->ana_log_size, GFP_KERNEL); if (!ctrl->ana_log_buf) { error = -ENOMEM; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index da392b50f73e..ace4dd9e953c 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1401,6 +1401,23 @@ static void nvme_disable_admin_queue(struct nvme_dev *dev, bool shutdown) nvme_poll_irqdisable(nvmeq, -1); } +/* + * Called only on a device that has been disabled and after all other threads + * that can check this device's completion queues have synced. This is the + * last chance for the driver to see a natural completion before + * nvme_cancel_request() terminates all incomplete requests. + */ +static void nvme_reap_pending_cqes(struct nvme_dev *dev) +{ + u16 start, end; + int i; + + for (i = dev->ctrl.queue_count - 1; i > 0; i--) { + nvme_process_cq(&dev->queues[i], &start, &end, -1); + nvme_complete_cqes(&dev->queues[i], start, end); + } +} + static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues, int entry_size) { @@ -2235,11 +2252,6 @@ static bool __nvme_disable_io_queues(struct nvme_dev *dev, u8 opcode) if (timeout == 0) return false; - /* handle any remaining CQEs */ - if (opcode == nvme_admin_delete_cq && - !test_bit(NVMEQ_DELETE_ERROR, &nvmeq->flags)) - nvme_poll_irqdisable(nvmeq, -1); - sent--; if (nr_queues) goto retry; @@ -2428,6 +2440,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) nvme_suspend_io_queues(dev); nvme_suspend_queue(&dev->queues[0]); nvme_pci_disable(dev); + nvme_reap_pending_cqes(dev); blk_mq_tagset_busy_iter(&dev->tagset, nvme_cancel_request, &dev->ctrl); blk_mq_tagset_busy_iter(&dev->admin_tagset, nvme_cancel_request, &dev->ctrl); @@ -2734,6 +2747,18 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev) (dmi_match(DMI_BOARD_NAME, "PRIME B350M-A") || dmi_match(DMI_BOARD_NAME, "PRIME Z370-A"))) return NVME_QUIRK_NO_APST; + } else if ((pdev->vendor == 0x144d && (pdev->device == 0xa801 || + pdev->device == 0xa808 || pdev->device == 0xa809)) || + (pdev->vendor == 0x1e0f && pdev->device == 0x0001)) { + /* + * Forcing to use host managed nvme power settings for + * lowest idle power with quick resume latency on + * Samsung and Toshiba SSDs based on suspend behavior + * on Coffee Lake board for LENOVO C640 + */ + if ((dmi_match(DMI_BOARD_VENDOR, "LENOVO")) && + dmi_match(DMI_BOARD_NAME, "LNVNB161216")) + return NVME_QUIRK_SIMPLE_SUSPEND; } return 0; @@ -3096,7 +3121,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_NO_DEEPEST_PS | NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, - { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) }, + { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001), + .driver_data = NVME_QUIRK_SINGLE_VECTOR }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2005), .driver_data = NVME_QUIRK_SINGLE_VECTOR | diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 2a47c6c5007e..3e85c5cacefd 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1088,7 +1088,7 @@ static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl) if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING)) return; - queue_work(nvme_wq, &ctrl->err_work); + queue_work(nvme_reset_wq, &ctrl->err_work); } static void nvme_rdma_wr_error(struct ib_cq *cq, struct ib_wc *wc, diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 6d43b23a0fc8..49d4373b84eb 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -422,7 +422,7 @@ static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl) if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) return; - queue_work(nvme_wq, &to_tcp_ctrl(ctrl)->err_work); + queue_work(nvme_reset_wq, &to_tcp_ctrl(ctrl)->err_work); } static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue, @@ -1054,7 +1054,12 @@ static void nvme_tcp_io_work(struct work_struct *w) } else if (unlikely(result < 0)) { dev_err(queue->ctrl->ctrl.device, "failed to send request %d\n", result); - if (result != -EPIPE) + + /* + * Fail the request unless peer closed the connection, + * in which case error recovery flow will complete all. + */ + if ((result != -EPIPE) && (result != -ECONNRESET)) nvme_tcp_fail_request(queue->request); nvme_tcp_done_send_req(queue); return; diff --git a/drivers/s390/cio/blacklist.c b/drivers/s390/cio/blacklist.c index da642e811f7f..4dd2eb634856 100644 --- a/drivers/s390/cio/blacklist.c +++ b/drivers/s390/cio/blacklist.c @@ -303,8 +303,10 @@ static void * cio_ignore_proc_seq_next(struct seq_file *s, void *it, loff_t *offset) { struct ccwdev_iter *iter; + loff_t p = *offset; - if (*offset >= (__MAX_SUBCHANNEL + 1) * (__MAX_SSID + 1)) + (*offset)++; + if (p >= (__MAX_SUBCHANNEL + 1) * (__MAX_SSID + 1)) return NULL; iter = it; if (iter->devno == __MAX_SUBCHANNEL) { @@ -314,7 +316,6 @@ cio_ignore_proc_seq_next(struct seq_file *s, void *it, loff_t *offset) return NULL; } else iter->devno++; - (*offset)++; return iter; } diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c index 51038ec309c1..dfcbe54591fb 100644 --- a/drivers/s390/cio/chp.c +++ b/drivers/s390/cio/chp.c @@ -135,7 +135,7 @@ static ssize_t chp_measurement_chars_read(struct file *filp, struct channel_path *chp; struct device *device; - device = container_of(kobj, struct device, kobj); + device = kobj_to_dev(kobj); chp = to_channelpath(device); if (chp->cmg == -1) return 0; @@ -184,7 +184,7 @@ static ssize_t chp_measurement_read(struct file *filp, struct kobject *kobj, struct device *device; unsigned int size; - device = container_of(kobj, struct device, kobj); + device = kobj_to_dev(kobj); chp = to_channelpath(device); css = to_css(chp->dev.parent); diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c index 3ab8e80d7bbc..e115623b86b2 100644 --- a/drivers/s390/cio/qdio_setup.c +++ b/drivers/s390/cio/qdio_setup.c @@ -8,6 +8,7 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/io.h> #include <asm/qdio.h> #include "cio.h" @@ -205,7 +206,7 @@ static void setup_storage_lists(struct qdio_q *q, struct qdio_irq *irq_ptr, /* fill in sl */ for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; j++) - q->sl->element[j].sbal = (unsigned long)q->sbal[j]; + q->sl->element[j].sbal = virt_to_phys(q->sbal[j]); } static void setup_queues(struct qdio_irq *irq_ptr, diff --git a/drivers/s390/crypto/zcrypt_ep11misc.c b/drivers/s390/crypto/zcrypt_ep11misc.c index d4caf46ff9df..2afe2153b34e 100644 --- a/drivers/s390/crypto/zcrypt_ep11misc.c +++ b/drivers/s390/crypto/zcrypt_ep11misc.c @@ -887,7 +887,7 @@ static int ep11_unwrapkey(u16 card, u16 domain, /* empty pin tag */ *p++ = 0x04; *p++ = 0; - /* encrytped key value tag and bytes */ + /* encrypted key value tag and bytes */ p += asn1tag_write(p, 0x04, enckey, enckeysize); /* reply cprb and payload */ @@ -1095,7 +1095,7 @@ int ep11_clr2keyblob(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, /* Step 1: generate AES 256 bit random kek key */ rc = ep11_genaeskey(card, domain, 256, - 0x00006c00, /* EN/DECRYTP, WRAP/UNWRAP */ + 0x00006c00, /* EN/DECRYPT, WRAP/UNWRAP */ kek, &keklen); if (rc) { DEBUG_ERR( diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 9639938581f5..8ca85c8a01a1 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -1128,9 +1128,10 @@ static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue, qeth_tx_complete_buf(buf, error, budget); for (i = 0; i < queue->max_elements; ++i) { - if (buf->buffer->element[i].addr && buf->is_header[i]) - kmem_cache_free(qeth_core_header_cache, - buf->buffer->element[i].addr); + void *data = phys_to_virt(buf->buffer->element[i].addr); + + if (data && buf->is_header[i]) + kmem_cache_free(qeth_core_header_cache, data); buf->is_header[i] = 0; } @@ -2641,7 +2642,8 @@ static int qeth_init_input_buffer(struct qeth_card *card, buf->pool_entry = pool_entry; for (i = 0; i < QETH_MAX_BUFFER_ELEMENTS(card); ++i) { buf->buffer->element[i].length = PAGE_SIZE; - buf->buffer->element[i].addr = pool_entry->elements[i]; + buf->buffer->element[i].addr = + virt_to_phys(pool_entry->elements[i]); if (i == QETH_MAX_BUFFER_ELEMENTS(card) - 1) buf->buffer->element[i].eflags = SBAL_EFLAGS_LAST_ENTRY; else @@ -3459,9 +3461,8 @@ static void qeth_qdio_cq_handler(struct qeth_card *card, unsigned int qdio_err, while ((e < QDIO_MAX_ELEMENTS_PER_BUFFER) && buffer->element[e].addr) { - unsigned long phys_aob_addr; + unsigned long phys_aob_addr = buffer->element[e].addr; - phys_aob_addr = (unsigned long) buffer->element[e].addr; qeth_qdio_handle_aob(card, phys_aob_addr); ++e; } @@ -3750,7 +3751,7 @@ static unsigned int __qeth_fill_buffer(struct sk_buff *skb, elem_length = min_t(unsigned int, length, PAGE_SIZE - offset_in_page(data)); - buffer->element[element].addr = data; + buffer->element[element].addr = virt_to_phys(data); buffer->element[element].length = elem_length; length -= elem_length; if (is_first_elem) { @@ -3780,7 +3781,7 @@ static unsigned int __qeth_fill_buffer(struct sk_buff *skb, elem_length = min_t(unsigned int, length, PAGE_SIZE - offset_in_page(data)); - buffer->element[element].addr = data; + buffer->element[element].addr = virt_to_phys(data); buffer->element[element].length = elem_length; buffer->element[element].eflags = SBAL_EFLAGS_MIDDLE_FRAG; @@ -3820,7 +3821,7 @@ static unsigned int qeth_fill_buffer(struct qeth_qdio_out_buffer *buf, int element = buf->next_element_to_fill; is_first_elem = false; - buffer->element[element].addr = hdr; + buffer->element[element].addr = virt_to_phys(hdr); buffer->element[element].length = hd_len; buffer->element[element].eflags = SBAL_EFLAGS_FIRST_FRAG; /* remember to free cache-allocated qeth_hdr: */ @@ -4746,10 +4747,10 @@ static void qeth_qdio_establish_cq(struct qeth_card *card, if (card->options.cq == QETH_CQ_ENABLED) { int offset = QDIO_MAX_BUFFERS_PER_Q * (card->qdio.no_in_queues - 1); - for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; ++i) { - in_sbal_ptrs[offset + i] = (struct qdio_buffer *) - virt_to_phys(card->qdio.c_q->bufs[i].buffer); - } + + for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; i++) + in_sbal_ptrs[offset + i] = + card->qdio.c_q->bufs[i].buffer; queue_start_poll[card->qdio.no_in_queues - 1] = NULL; } @@ -4783,10 +4784,9 @@ static int qeth_qdio_establish(struct qeth_card *card) rc = -ENOMEM; goto out_free_qib_param; } - for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; ++i) { - in_sbal_ptrs[i] = (struct qdio_buffer *) - virt_to_phys(card->qdio.in_q->bufs[i].buffer); - } + + for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; i++) + in_sbal_ptrs[i] = card->qdio.in_q->bufs[i].buffer; queue_start_poll = kcalloc(card->qdio.no_in_queues, sizeof(void *), GFP_KERNEL); @@ -4807,11 +4807,11 @@ static int qeth_qdio_establish(struct qeth_card *card) rc = -ENOMEM; goto out_free_queue_start_poll; } + for (i = 0, k = 0; i < card->qdio.no_out_queues; ++i) - for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j, ++k) { - out_sbal_ptrs[k] = (struct qdio_buffer *)virt_to_phys( - card->qdio.out_qs[i]->bufs[j]->buffer); - } + for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; j++, k++) + out_sbal_ptrs[k] = + card->qdio.out_qs[i]->bufs[j]->buffer; memset(&init_data, 0, sizeof(struct qdio_initialize)); init_data.cdev = CARD_DDEV(card); @@ -5289,7 +5289,7 @@ next_packet: offset = 0; } - hdr = element->addr + offset; + hdr = phys_to_virt(element->addr) + offset; offset += sizeof(*hdr); skb = NULL; @@ -5344,7 +5344,7 @@ next_packet: } use_rx_sg = (card->options.cq == QETH_CQ_ENABLED) || - ((skb_len >= card->options.rx_sg_cb) && + (skb_len > card->options.rx_sg_cb && !atomic_read(&card->force_alloc_skb) && !IS_OSN(card)); @@ -5388,7 +5388,7 @@ use_skb: walk_packet: while (skb_len) { int data_len = min(skb_len, (int)(element->length - offset)); - char *data = element->addr + offset; + char *data = phys_to_virt(element->addr) + offset; skb_len -= data_len; offset += data_len; @@ -5447,7 +5447,6 @@ static int qeth_extract_skbs(struct qeth_card *card, int budget, { int work_done = 0; - WARN_ON_ONCE(!budget); *done = false; while (budget) { diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 692bd2623401..9972d96820f3 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -1707,15 +1707,14 @@ int qeth_l2_vnicc_set_state(struct qeth_card *card, u32 vnicc, bool state) QETH_CARD_TEXT(card, 2, "vniccsch"); - /* do not change anything if BridgePort is enabled */ - if (qeth_bridgeport_is_in_use(card)) - return -EBUSY; - /* check if characteristic and enable/disable are supported */ if (!(card->options.vnicc.sup_chars & vnicc) || !(card->options.vnicc.set_char_sup & vnicc)) return -EOPNOTSUPP; + if (qeth_bridgeport_is_in_use(card)) + return -EBUSY; + /* set enable/disable command and store wanted characteristic */ if (state) { cmd = IPA_VNICC_ENABLE; @@ -1761,14 +1760,13 @@ int qeth_l2_vnicc_get_state(struct qeth_card *card, u32 vnicc, bool *state) QETH_CARD_TEXT(card, 2, "vniccgch"); - /* do not get anything if BridgePort is enabled */ - if (qeth_bridgeport_is_in_use(card)) - return -EBUSY; - /* check if characteristic is supported */ if (!(card->options.vnicc.sup_chars & vnicc)) return -EOPNOTSUPP; + if (qeth_bridgeport_is_in_use(card)) + return -EBUSY; + /* if card is ready, query current VNICC state */ if (qeth_card_hw_is_reachable(card)) rc = qeth_l2_vnicc_query_chars(card); @@ -1786,15 +1784,14 @@ int qeth_l2_vnicc_set_timeout(struct qeth_card *card, u32 timeout) QETH_CARD_TEXT(card, 2, "vniccsto"); - /* do not change anything if BridgePort is enabled */ - if (qeth_bridgeport_is_in_use(card)) - return -EBUSY; - /* check if characteristic and set_timeout are supported */ if (!(card->options.vnicc.sup_chars & QETH_VNICC_LEARNING) || !(card->options.vnicc.getset_timeout_sup & QETH_VNICC_LEARNING)) return -EOPNOTSUPP; + if (qeth_bridgeport_is_in_use(card)) + return -EBUSY; + /* do we need to do anything? */ if (card->options.vnicc.learning_timeout == timeout) return rc; @@ -1823,14 +1820,14 @@ int qeth_l2_vnicc_get_timeout(struct qeth_card *card, u32 *timeout) QETH_CARD_TEXT(card, 2, "vniccgto"); - /* do not get anything if BridgePort is enabled */ - if (qeth_bridgeport_is_in_use(card)) - return -EBUSY; - /* check if characteristic and get_timeout are supported */ if (!(card->options.vnicc.sup_chars & QETH_VNICC_LEARNING) || !(card->options.vnicc.getset_timeout_sup & QETH_VNICC_LEARNING)) return -EOPNOTSUPP; + + if (qeth_bridgeport_is_in_use(card)) + return -EBUSY; + /* if card is ready, get timeout. Otherwise, just return stored value */ *timeout = card->options.vnicc.learning_timeout; if (qeth_card_hw_is_reachable(card)) diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c index 223a805f0b0b..cae9b7ff79b0 100644 --- a/drivers/s390/scsi/zfcp_fsf.c +++ b/drivers/s390/scsi/zfcp_fsf.c @@ -2510,7 +2510,7 @@ void zfcp_fsf_reqid_check(struct zfcp_qdio *qdio, int sbal_idx) for (idx = 0; idx < QDIO_MAX_ELEMENTS_PER_BUFFER; idx++) { sbale = &sbal->element[idx]; - req_id = (unsigned long) sbale->addr; + req_id = sbale->addr; fsf_req = zfcp_reqlist_find_rm(adapter->req_list, req_id); if (!fsf_req) { diff --git a/drivers/s390/scsi/zfcp_qdio.c b/drivers/s390/scsi/zfcp_qdio.c index 661436a92f8e..f0d6296e673b 100644 --- a/drivers/s390/scsi/zfcp_qdio.c +++ b/drivers/s390/scsi/zfcp_qdio.c @@ -98,7 +98,7 @@ static void zfcp_qdio_int_resp(struct ccw_device *cdev, unsigned int qdio_err, memset(pl, 0, ZFCP_QDIO_MAX_SBALS_PER_REQ * sizeof(void *)); sbale = qdio->res_q[idx]->element; - req_id = (u64) sbale->addr; + req_id = sbale->addr; scount = min(sbale->scount + 1, ZFCP_QDIO_MAX_SBALS_PER_REQ + 1); /* incl. signaling SBAL */ @@ -199,7 +199,7 @@ int zfcp_qdio_sbals_from_sg(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req, q_req->sbal_number); return -EINVAL; } - sbale->addr = sg_virt(sg); + sbale->addr = sg_phys(sg); sbale->length = sg->length; } return 0; @@ -418,7 +418,7 @@ int zfcp_qdio_open(struct zfcp_qdio *qdio) sbale->length = 0; sbale->eflags = SBAL_EFLAGS_LAST_ENTRY; sbale->sflags = 0; - sbale->addr = NULL; + sbale->addr = 0; } if (do_QDIO(cdev, QDIO_FLAG_SYNC_INPUT, 0, 0, QDIO_MAX_BUFFERS_PER_Q)) diff --git a/drivers/s390/scsi/zfcp_qdio.h b/drivers/s390/scsi/zfcp_qdio.h index 2a816a37b3c0..6b43d6b254be 100644 --- a/drivers/s390/scsi/zfcp_qdio.h +++ b/drivers/s390/scsi/zfcp_qdio.h @@ -122,14 +122,14 @@ void zfcp_qdio_req_init(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req, % QDIO_MAX_BUFFERS_PER_Q; sbale = zfcp_qdio_sbale_req(qdio, q_req); - sbale->addr = (void *) req_id; + sbale->addr = req_id; sbale->eflags = 0; sbale->sflags = SBAL_SFLAGS0_COMMAND | sbtype; if (unlikely(!data)) return; sbale++; - sbale->addr = data; + sbale->addr = virt_to_phys(data); sbale->length = len; } @@ -152,7 +152,7 @@ void zfcp_qdio_fill_next(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req, BUG_ON(q_req->sbale_curr == qdio->max_sbale_per_sbal - 1); q_req->sbale_curr++; sbale = zfcp_qdio_sbale_curr(qdio, q_req); - sbale->addr = data; + sbale->addr = virt_to_phys(data); sbale->length = len; } diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c index f3b36fd0a0eb..b2ad96564484 100644 --- a/drivers/scsi/megaraid/megaraid_sas_fusion.c +++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c @@ -623,7 +623,8 @@ retry_alloc: fusion->io_request_frames = dma_pool_alloc(fusion->io_request_frames_pool, - GFP_KERNEL, &fusion->io_request_frames_phys); + GFP_KERNEL | __GFP_NOWARN, + &fusion->io_request_frames_phys); if (!fusion->io_request_frames) { if (instance->max_fw_cmds >= (MEGASAS_REDUCE_QD_COUNT * 2)) { instance->max_fw_cmds -= MEGASAS_REDUCE_QD_COUNT; @@ -661,7 +662,7 @@ retry_alloc: fusion->io_request_frames = dma_pool_alloc(fusion->io_request_frames_pool, - GFP_KERNEL, + GFP_KERNEL | __GFP_NOWARN, &fusion->io_request_frames_phys); if (!fusion->io_request_frames) { diff --git a/drivers/staging/android/Kconfig b/drivers/staging/android/Kconfig index d6d605d5cbde..8d8fd5c29349 100644 --- a/drivers/staging/android/Kconfig +++ b/drivers/staging/android/Kconfig @@ -14,14 +14,6 @@ config ASHMEM It is, in theory, a good memory allocator for low-memory devices, because it can discard shared memory units when under memory pressure. -config ANDROID_VSOC - tristate "Android Virtual SoC support" - depends on PCI_MSI - help - This option adds support for the Virtual SoC driver needed to boot - a 'cuttlefish' Android image inside QEmu. The driver interacts with - a QEmu ivshmem device. If built as a module, it will be called vsoc. - source "drivers/staging/android/ion/Kconfig" endif # if ANDROID diff --git a/drivers/staging/android/Makefile b/drivers/staging/android/Makefile index 14bd9c6ce10d..3b66cd0b0ec5 100644 --- a/drivers/staging/android/Makefile +++ b/drivers/staging/android/Makefile @@ -4,4 +4,3 @@ ccflags-y += -I$(src) # needed for trace events obj-y += ion/ obj-$(CONFIG_ASHMEM) += ashmem.o -obj-$(CONFIG_ANDROID_VSOC) += vsoc.o diff --git a/drivers/staging/android/TODO b/drivers/staging/android/TODO index 767dd98fd92d..80eccfaf6db5 100644 --- a/drivers/staging/android/TODO +++ b/drivers/staging/android/TODO @@ -9,14 +9,5 @@ ion/ - Split /dev/ion up into multiple nodes (e.g. /dev/ion/heap0) - Better test framework (integration with VGEM was suggested) -vsoc.c, uapi/vsoc_shm.h - - The current driver uses the same wait queue for all of the futexes in a - region. This will cause false wakeups in regions with a large number of - waiting threads. We should eventually use multiple queues and select the - queue based on the region. - - Add debugfs support for examining the permissions of regions. - - Remove VSOC_WAIT_FOR_INCOMING_INTERRUPT ioctl. This functionality has been - superseded by the futex and is there for legacy reasons. - Please send patches to Greg Kroah-Hartman <greg@kroah.com> and Cc: Arve Hjønnevåg <arve@android.com> and Riley Andrews <riandrews@android.com> diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c index 5891d0744a76..8044510d8ec6 100644 --- a/drivers/staging/android/ashmem.c +++ b/drivers/staging/android/ashmem.c @@ -351,8 +351,23 @@ static inline vm_flags_t calc_vm_may_flags(unsigned long prot) _calc_vm_trans(prot, PROT_EXEC, VM_MAYEXEC); } +static int ashmem_vmfile_mmap(struct file *file, struct vm_area_struct *vma) +{ + /* do not allow to mmap ashmem backing shmem file directly */ + return -EPERM; +} + +static unsigned long +ashmem_vmfile_get_unmapped_area(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + return current->mm->get_unmapped_area(file, addr, len, pgoff, flags); +} + static int ashmem_mmap(struct file *file, struct vm_area_struct *vma) { + static struct file_operations vmfile_fops; struct ashmem_area *asma = file->private_data; int ret = 0; @@ -393,6 +408,19 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma) } vmfile->f_mode |= FMODE_LSEEK; asma->file = vmfile; + /* + * override mmap operation of the vmfile so that it can't be + * remapped which would lead to creation of a new vma with no + * asma permission checks. Have to override get_unmapped_area + * as well to prevent VM_BUG_ON check for f_ops modification. + */ + if (!vmfile_fops.mmap) { + vmfile_fops = *vmfile->f_op; + vmfile_fops.mmap = ashmem_vmfile_mmap; + vmfile_fops.get_unmapped_area = + ashmem_vmfile_get_unmapped_area; + } + vmfile->f_op = &vmfile_fops; } get_file(asma->file); diff --git a/drivers/staging/android/uapi/vsoc_shm.h b/drivers/staging/android/uapi/vsoc_shm.h deleted file mode 100644 index 6291fb24efb2..000000000000 --- a/drivers/staging/android/uapi/vsoc_shm.h +++ /dev/null @@ -1,295 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2017 Google, Inc. - * - */ - -#ifndef _UAPI_LINUX_VSOC_SHM_H -#define _UAPI_LINUX_VSOC_SHM_H - -#include <linux/types.h> - -/** - * A permission is a token that permits a receiver to read and/or write an area - * of memory within a Vsoc region. - * - * An fd_scoped permission grants both read and write access, and can be - * attached to a file description (see open(2)). - * Ownership of the area can then be shared by passing a file descriptor - * among processes. - * - * begin_offset and end_offset define the area of memory that is controlled by - * the permission. owner_offset points to a word, also in shared memory, that - * controls ownership of the area. - * - * ownership of the region expires when the associated file description is - * released. - * - * At most one permission can be attached to each file description. - * - * This is useful when implementing HALs like gralloc that scope and pass - * ownership of shared resources via file descriptors. - * - * The caller is responsibe for doing any fencing. - * - * The calling process will normally identify a currently free area of - * memory. It will construct a proposed fd_scoped_permission_arg structure: - * - * begin_offset and end_offset describe the area being claimed - * - * owner_offset points to the location in shared memory that indicates the - * owner of the area. - * - * owned_value is the value that will be stored in owner_offset iff the - * permission can be granted. It must be different than VSOC_REGION_FREE. - * - * Two fd_scoped_permission structures are compatible if they vary only by - * their owned_value fields. - * - * The driver ensures that, for any group of simultaneous callers proposing - * compatible fd_scoped_permissions, it will accept exactly one of the - * propopsals. The other callers will get a failure with errno of EAGAIN. - * - * A process receiving a file descriptor can identify the region being - * granted using the VSOC_GET_FD_SCOPED_PERMISSION ioctl. - */ -struct fd_scoped_permission { - __u32 begin_offset; - __u32 end_offset; - __u32 owner_offset; - __u32 owned_value; -}; - -/* - * This value represents a free area of memory. The driver expects to see this - * value at owner_offset when creating a permission otherwise it will not do it, - * and will write this value back once the permission is no longer needed. - */ -#define VSOC_REGION_FREE ((__u32)0) - -/** - * ioctl argument for VSOC_CREATE_FD_SCOPE_PERMISSION - */ -struct fd_scoped_permission_arg { - struct fd_scoped_permission perm; - __s32 managed_region_fd; -}; - -#define VSOC_NODE_FREE ((__u32)0) - -/* - * Describes a signal table in shared memory. Each non-zero entry in the - * table indicates that the receiver should signal the futex at the given - * offset. Offsets are relative to the region, not the shared memory window. - * - * interrupt_signalled_offset is used to reliably signal interrupts across the - * vmm boundary. There are two roles: transmitter and receiver. For example, - * in the host_to_guest_signal_table the host is the transmitter and the - * guest is the receiver. The protocol is as follows: - * - * 1. The transmitter should convert the offset of the futex to an offset - * in the signal table [0, (1 << num_nodes_lg2)) - * The transmitter can choose any appropriate hashing algorithm, including - * hash = futex_offset & ((1 << num_nodes_lg2) - 1) - * - * 3. The transmitter should atomically compare and swap futex_offset with 0 - * at hash. There are 3 possible outcomes - * a. The swap fails because the futex_offset is already in the table. - * The transmitter should stop. - * b. Some other offset is in the table. This is a hash collision. The - * transmitter should move to another table slot and try again. One - * possible algorithm: - * hash = (hash + 1) & ((1 << num_nodes_lg2) - 1) - * c. The swap worked. Continue below. - * - * 3. The transmitter atomically swaps 1 with the value at the - * interrupt_signalled_offset. There are two outcomes: - * a. The prior value was 1. In this case an interrupt has already been - * posted. The transmitter is done. - * b. The prior value was 0, indicating that the receiver may be sleeping. - * The transmitter will issue an interrupt. - * - * 4. On waking the receiver immediately exchanges a 0 with the - * interrupt_signalled_offset. If it receives a 0 then this a spurious - * interrupt. That may occasionally happen in the current protocol, but - * should be rare. - * - * 5. The receiver scans the signal table by atomicaly exchanging 0 at each - * location. If a non-zero offset is returned from the exchange the - * receiver wakes all sleepers at the given offset: - * futex((int*)(region_base + old_value), FUTEX_WAKE, MAX_INT); - * - * 6. The receiver thread then does a conditional wait, waking immediately - * if the value at interrupt_signalled_offset is non-zero. This catches cases - * here additional signals were posted while the table was being scanned. - * On the guest the wait is handled via the VSOC_WAIT_FOR_INCOMING_INTERRUPT - * ioctl. - */ -struct vsoc_signal_table_layout { - /* log_2(Number of signal table entries) */ - __u32 num_nodes_lg2; - /* - * Offset to the first signal table entry relative to the start of the - * region - */ - __u32 futex_uaddr_table_offset; - /* - * Offset to an atomic_t / atomic uint32_t. A non-zero value indicates - * that one or more offsets are currently posted in the table. - * semi-unique access to an entry in the table - */ - __u32 interrupt_signalled_offset; -}; - -#define VSOC_REGION_WHOLE ((__s32)0) -#define VSOC_DEVICE_NAME_SZ 16 - -/** - * Each HAL would (usually) talk to a single device region - * Mulitple entities care about these regions: - * - The ivshmem_server will populate the regions in shared memory - * - The guest kernel will read the region, create minor device nodes, and - * allow interested parties to register for FUTEX_WAKE events in the region - * - HALs will access via the minor device nodes published by the guest kernel - * - Host side processes will access the region via the ivshmem_server: - * 1. Pass name to ivshmem_server at a UNIX socket - * 2. ivshmemserver will reply with 2 fds: - * - host->guest doorbell fd - * - guest->host doorbell fd - * - fd for the shared memory region - * - region offset - * 3. Start a futex receiver thread on the doorbell fd pointed at the - * signal_nodes - */ -struct vsoc_device_region { - __u16 current_version; - __u16 min_compatible_version; - __u32 region_begin_offset; - __u32 region_end_offset; - __u32 offset_of_region_data; - struct vsoc_signal_table_layout guest_to_host_signal_table; - struct vsoc_signal_table_layout host_to_guest_signal_table; - /* Name of the device. Must always be terminated with a '\0', so - * the longest supported device name is 15 characters. - */ - char device_name[VSOC_DEVICE_NAME_SZ]; - /* There are two ways that permissions to access regions are handled: - * - When subdivided_by is VSOC_REGION_WHOLE, any process that can - * open the device node for the region gains complete access to it. - * - When subdivided is set processes that open the region cannot - * access it. Access to a sub-region must be established by invoking - * the VSOC_CREATE_FD_SCOPE_PERMISSION ioctl on the region - * referenced in subdivided_by, providing a fileinstance - * (represented by a fd) opened on this region. - */ - __u32 managed_by; -}; - -/* - * The vsoc layout descriptor. - * The first 4K should be reserved for the shm header and region descriptors. - * The regions should be page aligned. - */ - -struct vsoc_shm_layout_descriptor { - __u16 major_version; - __u16 minor_version; - - /* size of the shm. This may be redundant but nice to have */ - __u32 size; - - /* number of shared memory regions */ - __u32 region_count; - - /* The offset to the start of region descriptors */ - __u32 vsoc_region_desc_offset; -}; - -/* - * This specifies the current version that should be stored in - * vsoc_shm_layout_descriptor.major_version and - * vsoc_shm_layout_descriptor.minor_version. - * It should be updated only if the vsoc_device_region and - * vsoc_shm_layout_descriptor structures have changed. - * Versioning within each region is transferred - * via the min_compatible_version and current_version fields in - * vsoc_device_region. The driver does not consult these fields: they are left - * for the HALs and host processes and will change independently of the layout - * version. - */ -#define CURRENT_VSOC_LAYOUT_MAJOR_VERSION 2 -#define CURRENT_VSOC_LAYOUT_MINOR_VERSION 0 - -#define VSOC_CREATE_FD_SCOPED_PERMISSION \ - _IOW(0xF5, 0, struct fd_scoped_permission) -#define VSOC_GET_FD_SCOPED_PERMISSION _IOR(0xF5, 1, struct fd_scoped_permission) - -/* - * This is used to signal the host to scan the guest_to_host_signal_table - * for new futexes to wake. This sends an interrupt if one is not already - * in flight. - */ -#define VSOC_MAYBE_SEND_INTERRUPT_TO_HOST _IO(0xF5, 2) - -/* - * When this returns the guest will scan host_to_guest_signal_table to - * check for new futexes to wake. - */ -/* TODO(ghartman): Consider moving this to the bottom half */ -#define VSOC_WAIT_FOR_INCOMING_INTERRUPT _IO(0xF5, 3) - -/* - * Guest HALs will use this to retrieve the region description after - * opening their device node. - */ -#define VSOC_DESCRIBE_REGION _IOR(0xF5, 4, struct vsoc_device_region) - -/* - * Wake any threads that may be waiting for a host interrupt on this region. - * This is mostly used during shutdown. - */ -#define VSOC_SELF_INTERRUPT _IO(0xF5, 5) - -/* - * This is used to signal the host to scan the guest_to_host_signal_table - * for new futexes to wake. This sends an interrupt unconditionally. - */ -#define VSOC_SEND_INTERRUPT_TO_HOST _IO(0xF5, 6) - -enum wait_types { - VSOC_WAIT_UNDEFINED = 0, - VSOC_WAIT_IF_EQUAL = 1, - VSOC_WAIT_IF_EQUAL_TIMEOUT = 2 -}; - -/* - * Wait for a condition to be true - * - * Note, this is sized and aligned so the 32 bit and 64 bit layouts are - * identical. - */ -struct vsoc_cond_wait { - /* Input: Offset of the 32 bit word to check */ - __u32 offset; - /* Input: Value that will be compared with the offset */ - __u32 value; - /* Monotonic time to wake at in seconds */ - __u64 wake_time_sec; - /* Input: Monotonic time to wait in nanoseconds */ - __u32 wake_time_nsec; - /* Input: Type of wait */ - __u32 wait_type; - /* Output: Number of times the thread woke before returning. */ - __u32 wakes; - /* Ensure that we're 8-byte aligned and 8 byte length for 32/64 bit - * compatibility. - */ - __u32 reserved_1; -}; - -#define VSOC_COND_WAIT _IOWR(0xF5, 7, struct vsoc_cond_wait) - -/* Wake any local threads waiting at the offset given in arg */ -#define VSOC_COND_WAKE _IO(0xF5, 8) - -#endif /* _UAPI_LINUX_VSOC_SHM_H */ diff --git a/drivers/staging/android/vsoc.c b/drivers/staging/android/vsoc.c deleted file mode 100644 index 1240bb0317d9..000000000000 --- a/drivers/staging/android/vsoc.c +++ /dev/null @@ -1,1149 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * drivers/android/staging/vsoc.c - * - * Android Virtual System on a Chip (VSoC) driver - * - * Copyright (C) 2017 Google, Inc. - * - * Author: ghartman@google.com - * - * Based on drivers/char/kvm_ivshmem.c - driver for KVM Inter-VM shared memory - * Copyright 2009 Cam Macdonell <cam@cs.ualberta.ca> - * - * Based on cirrusfb.c and 8139cp.c: - * Copyright 1999-2001 Jeff Garzik - * Copyright 2001-2004 Jeff Garzik - */ - -#include <linux/dma-mapping.h> -#include <linux/freezer.h> -#include <linux/futex.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/mutex.h> -#include <linux/pci.h> -#include <linux/proc_fs.h> -#include <linux/sched.h> -#include <linux/syscalls.h> -#include <linux/uaccess.h> -#include <linux/interrupt.h> -#include <linux/cdev.h> -#include <linux/file.h> -#include "uapi/vsoc_shm.h" - -#define VSOC_DEV_NAME "vsoc" - -/* - * Description of the ivshmem-doorbell PCI device used by QEmu. These - * constants follow docs/specs/ivshmem-spec.txt, which can be found in - * the QEmu repository. This was last reconciled with the version that - * came out with 2.8 - */ - -/* - * These constants are determined KVM Inter-VM shared memory device - * register offsets - */ -enum { - INTR_MASK = 0x00, /* Interrupt Mask */ - INTR_STATUS = 0x04, /* Interrupt Status */ - IV_POSITION = 0x08, /* VM ID */ - DOORBELL = 0x0c, /* Doorbell */ -}; - -static const int REGISTER_BAR; /* Equal to 0 */ -static const int MAX_REGISTER_BAR_LEN = 0x100; -/* - * The MSI-x BAR is not used directly. - * - * static const int MSI_X_BAR = 1; - */ -static const int SHARED_MEMORY_BAR = 2; - -struct vsoc_region_data { - char name[VSOC_DEVICE_NAME_SZ + 1]; - wait_queue_head_t interrupt_wait_queue; - /* TODO(b/73664181): Use multiple futex wait queues */ - wait_queue_head_t futex_wait_queue; - /* Flag indicating that an interrupt has been signalled by the host. */ - atomic_t *incoming_signalled; - /* Flag indicating the guest has signalled the host. */ - atomic_t *outgoing_signalled; - bool irq_requested; - bool device_created; -}; - -struct vsoc_device { - /* Kernel virtual address of REGISTER_BAR. */ - void __iomem *regs; - /* Physical address of SHARED_MEMORY_BAR. */ - phys_addr_t shm_phys_start; - /* Kernel virtual address of SHARED_MEMORY_BAR. */ - void __iomem *kernel_mapped_shm; - /* Size of the entire shared memory window in bytes. */ - size_t shm_size; - /* - * Pointer to the virtual address of the shared memory layout structure. - * This is probably identical to kernel_mapped_shm, but saving this - * here saves a lot of annoying casts. - */ - struct vsoc_shm_layout_descriptor *layout; - /* - * Points to a table of region descriptors in the kernel's virtual - * address space. Calculated from - * vsoc_shm_layout_descriptor.vsoc_region_desc_offset - */ - struct vsoc_device_region *regions; - /* Head of a list of permissions that have been granted. */ - struct list_head permissions; - struct pci_dev *dev; - /* Per-region (and therefore per-interrupt) information. */ - struct vsoc_region_data *regions_data; - /* - * Table of msi-x entries. This has to be separated from struct - * vsoc_region_data because the kernel deals with them as an array. - */ - struct msix_entry *msix_entries; - /* Mutex that protectes the permission list */ - struct mutex mtx; - /* Major number assigned by the kernel */ - int major; - /* Character device assigned by the kernel */ - struct cdev cdev; - /* Device class assigned by the kernel */ - struct class *class; - /* - * Flags that indicate what we've initialized. These are used to do an - * orderly cleanup of the device. - */ - bool enabled_device; - bool requested_regions; - bool cdev_added; - bool class_added; - bool msix_enabled; -}; - -static struct vsoc_device vsoc_dev; - -/* - * TODO(ghartman): Add a /sys filesystem entry that summarizes the permissions. - */ - -struct fd_scoped_permission_node { - struct fd_scoped_permission permission; - struct list_head list; -}; - -struct vsoc_private_data { - struct fd_scoped_permission_node *fd_scoped_permission_node; -}; - -static long vsoc_ioctl(struct file *, unsigned int, unsigned long); -static int vsoc_mmap(struct file *, struct vm_area_struct *); -static int vsoc_open(struct inode *, struct file *); -static int vsoc_release(struct inode *, struct file *); -static ssize_t vsoc_read(struct file *, char __user *, size_t, loff_t *); -static ssize_t vsoc_write(struct file *, const char __user *, size_t, loff_t *); -static loff_t vsoc_lseek(struct file *filp, loff_t offset, int origin); -static int -do_create_fd_scoped_permission(struct vsoc_device_region *region_p, - struct fd_scoped_permission_node *np, - struct fd_scoped_permission_arg __user *arg); -static void -do_destroy_fd_scoped_permission(struct vsoc_device_region *owner_region_p, - struct fd_scoped_permission *perm); -static long do_vsoc_describe_region(struct file *, - struct vsoc_device_region __user *); -static ssize_t vsoc_get_area(struct file *filp, __u32 *perm_off); - -/** - * Validate arguments on entry points to the driver. - */ -inline int vsoc_validate_inode(struct inode *inode) -{ - if (iminor(inode) >= vsoc_dev.layout->region_count) { - dev_err(&vsoc_dev.dev->dev, - "describe_region: invalid region %d\n", iminor(inode)); - return -ENODEV; - } - return 0; -} - -inline int vsoc_validate_filep(struct file *filp) -{ - int ret = vsoc_validate_inode(file_inode(filp)); - - if (ret) - return ret; - if (!filp->private_data) { - dev_err(&vsoc_dev.dev->dev, - "No private data on fd, region %d\n", - iminor(file_inode(filp))); - return -EBADFD; - } - return 0; -} - -/* Converts from shared memory offset to virtual address */ -static inline void *shm_off_to_virtual_addr(__u32 offset) -{ - return (void __force *)vsoc_dev.kernel_mapped_shm + offset; -} - -/* Converts from shared memory offset to physical address */ -static inline phys_addr_t shm_off_to_phys_addr(__u32 offset) -{ - return vsoc_dev.shm_phys_start + offset; -} - -/** - * Convenience functions to obtain the region from the inode or file. - * Dangerous to call before validating the inode/file. - */ -static -inline struct vsoc_device_region *vsoc_region_from_inode(struct inode *inode) -{ - return &vsoc_dev.regions[iminor(inode)]; -} - -static -inline struct vsoc_device_region *vsoc_region_from_filep(struct file *inode) -{ - return vsoc_region_from_inode(file_inode(inode)); -} - -static inline uint32_t vsoc_device_region_size(struct vsoc_device_region *r) -{ - return r->region_end_offset - r->region_begin_offset; -} - -static const struct file_operations vsoc_ops = { - .owner = THIS_MODULE, - .open = vsoc_open, - .mmap = vsoc_mmap, - .read = vsoc_read, - .unlocked_ioctl = vsoc_ioctl, - .compat_ioctl = vsoc_ioctl, - .write = vsoc_write, - .llseek = vsoc_lseek, - .release = vsoc_release, -}; - -static struct pci_device_id vsoc_id_table[] = { - {0x1af4, 0x1110, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, - {0}, -}; - -MODULE_DEVICE_TABLE(pci, vsoc_id_table); - -static void vsoc_remove_device(struct pci_dev *pdev); -static int vsoc_probe_device(struct pci_dev *pdev, - const struct pci_device_id *ent); - -static struct pci_driver vsoc_pci_driver = { - .name = "vsoc", - .id_table = vsoc_id_table, - .probe = vsoc_probe_device, - .remove = vsoc_remove_device, -}; - -static int -do_create_fd_scoped_permission(struct vsoc_device_region *region_p, - struct fd_scoped_permission_node *np, - struct fd_scoped_permission_arg __user *arg) -{ - struct file *managed_filp; - s32 managed_fd; - atomic_t *owner_ptr = NULL; - struct vsoc_device_region *managed_region_p; - - if (copy_from_user(&np->permission, - &arg->perm, sizeof(np->permission)) || - copy_from_user(&managed_fd, - &arg->managed_region_fd, sizeof(managed_fd))) { - return -EFAULT; - } - managed_filp = fdget(managed_fd).file; - /* Check that it's a valid fd, */ - if (!managed_filp || vsoc_validate_filep(managed_filp)) - return -EPERM; - /* EEXIST if the given fd already has a permission. */ - if (((struct vsoc_private_data *)managed_filp->private_data)-> - fd_scoped_permission_node) - return -EEXIST; - managed_region_p = vsoc_region_from_filep(managed_filp); - /* Check that the provided region is managed by this one */ - if (&vsoc_dev.regions[managed_region_p->managed_by] != region_p) - return -EPERM; - /* The area must be well formed and have non-zero size */ - if (np->permission.begin_offset >= np->permission.end_offset) - return -EINVAL; - /* The area must fit in the memory window */ - if (np->permission.end_offset > - vsoc_device_region_size(managed_region_p)) - return -ERANGE; - /* The area must be in the region data section */ - if (np->permission.begin_offset < - managed_region_p->offset_of_region_data) - return -ERANGE; - /* The area must be page aligned */ - if (!PAGE_ALIGNED(np->permission.begin_offset) || - !PAGE_ALIGNED(np->permission.end_offset)) - return -EINVAL; - /* Owner offset must be naturally aligned in the window */ - if (np->permission.owner_offset & - (sizeof(np->permission.owner_offset) - 1)) - return -EINVAL; - /* The owner flag must reside in the owner memory */ - if (np->permission.owner_offset + sizeof(np->permission.owner_offset) > - vsoc_device_region_size(region_p)) - return -ERANGE; - /* The owner flag must reside in the data section */ - if (np->permission.owner_offset < region_p->offset_of_region_data) - return -EINVAL; - /* The owner value must change to claim the memory */ - if (np->permission.owned_value == VSOC_REGION_FREE) - return -EINVAL; - owner_ptr = - (atomic_t *)shm_off_to_virtual_addr(region_p->region_begin_offset + - np->permission.owner_offset); - /* We've already verified that this is in the shared memory window, so - * it should be safe to write to this address. - */ - if (atomic_cmpxchg(owner_ptr, - VSOC_REGION_FREE, - np->permission.owned_value) != VSOC_REGION_FREE) { - return -EBUSY; - } - ((struct vsoc_private_data *)managed_filp->private_data)-> - fd_scoped_permission_node = np; - /* The file offset needs to be adjusted if the calling - * process did any read/write operations on the fd - * before creating the permission. - */ - if (managed_filp->f_pos) { - if (managed_filp->f_pos > np->permission.end_offset) { - /* If the offset is beyond the permission end, set it - * to the end. - */ - managed_filp->f_pos = np->permission.end_offset; - } else { - /* If the offset is within the permission interval - * keep it there otherwise reset it to zero. - */ - if (managed_filp->f_pos < np->permission.begin_offset) { - managed_filp->f_pos = 0; - } else { - managed_filp->f_pos -= - np->permission.begin_offset; - } - } - } - return 0; -} - -static void -do_destroy_fd_scoped_permission_node(struct vsoc_device_region *owner_region_p, - struct fd_scoped_permission_node *node) -{ - if (node) { - do_destroy_fd_scoped_permission(owner_region_p, - &node->permission); - mutex_lock(&vsoc_dev.mtx); - list_del(&node->list); - mutex_unlock(&vsoc_dev.mtx); - kfree(node); - } -} - -static void -do_destroy_fd_scoped_permission(struct vsoc_device_region *owner_region_p, - struct fd_scoped_permission *perm) -{ - atomic_t *owner_ptr = NULL; - int prev = 0; - - if (!perm) - return; - owner_ptr = (atomic_t *)shm_off_to_virtual_addr - (owner_region_p->region_begin_offset + perm->owner_offset); - prev = atomic_xchg(owner_ptr, VSOC_REGION_FREE); - if (prev != perm->owned_value) - dev_err(&vsoc_dev.dev->dev, - "%x-%x: owner (%s) %x: expected to be %x was %x", - perm->begin_offset, perm->end_offset, - owner_region_p->device_name, perm->owner_offset, - perm->owned_value, prev); -} - -static long do_vsoc_describe_region(struct file *filp, - struct vsoc_device_region __user *dest) -{ - struct vsoc_device_region *region_p; - int retval = vsoc_validate_filep(filp); - - if (retval) - return retval; - region_p = vsoc_region_from_filep(filp); - if (copy_to_user(dest, region_p, sizeof(*region_p))) - return -EFAULT; - return 0; -} - -/** - * Implements the inner logic of cond_wait. Copies to and from userspace are - * done in the helper function below. - */ -static int handle_vsoc_cond_wait(struct file *filp, struct vsoc_cond_wait *arg) -{ - DEFINE_WAIT(wait); - u32 region_number = iminor(file_inode(filp)); - struct vsoc_region_data *data = vsoc_dev.regions_data + region_number; - struct hrtimer_sleeper timeout, *to = NULL; - int ret = 0; - struct vsoc_device_region *region_p = vsoc_region_from_filep(filp); - atomic_t *address = NULL; - ktime_t wake_time; - - /* Ensure that the offset is aligned */ - if (arg->offset & (sizeof(uint32_t) - 1)) - return -EADDRNOTAVAIL; - /* Ensure that the offset is within shared memory */ - if (((uint64_t)arg->offset) + region_p->region_begin_offset + - sizeof(uint32_t) > region_p->region_end_offset) - return -E2BIG; - address = shm_off_to_virtual_addr(region_p->region_begin_offset + - arg->offset); - - /* Ensure that the type of wait is valid */ - switch (arg->wait_type) { - case VSOC_WAIT_IF_EQUAL: - break; - case VSOC_WAIT_IF_EQUAL_TIMEOUT: - to = &timeout; - break; - default: - return -EINVAL; - } - - if (to) { - /* Copy the user-supplied timesec into the kernel structure. - * We do things this way to flatten differences between 32 bit - * and 64 bit timespecs. - */ - if (arg->wake_time_nsec >= NSEC_PER_SEC) - return -EINVAL; - wake_time = ktime_set(arg->wake_time_sec, arg->wake_time_nsec); - - hrtimer_init_sleeper_on_stack(to, CLOCK_MONOTONIC, - HRTIMER_MODE_ABS); - hrtimer_set_expires_range_ns(&to->timer, wake_time, - current->timer_slack_ns); - } - - while (1) { - prepare_to_wait(&data->futex_wait_queue, &wait, - TASK_INTERRUPTIBLE); - /* - * Check the sentinel value after prepare_to_wait. If the value - * changes after this check the writer will call signal, - * changing the task state from INTERRUPTIBLE to RUNNING. That - * will ensure that schedule() will eventually schedule this - * task. - */ - if (atomic_read(address) != arg->value) { - ret = 0; - break; - } - if (to) { - hrtimer_sleeper_start_expires(to, HRTIMER_MODE_ABS); - if (likely(to->task)) - freezable_schedule(); - hrtimer_cancel(&to->timer); - if (!to->task) { - ret = -ETIMEDOUT; - break; - } - } else { - freezable_schedule(); - } - /* Count the number of times that we woke up. This is useful - * for unit testing. - */ - ++arg->wakes; - if (signal_pending(current)) { - ret = -EINTR; - break; - } - } - finish_wait(&data->futex_wait_queue, &wait); - if (to) - destroy_hrtimer_on_stack(&to->timer); - return ret; -} - -/** - * Handles the details of copying from/to userspace to ensure that the copies - * happen on all of the return paths of cond_wait. - */ -static int do_vsoc_cond_wait(struct file *filp, - struct vsoc_cond_wait __user *untrusted_in) -{ - struct vsoc_cond_wait arg; - int rval = 0; - - if (copy_from_user(&arg, untrusted_in, sizeof(arg))) - return -EFAULT; - /* wakes is an out parameter. Initialize it to something sensible. */ - arg.wakes = 0; - rval = handle_vsoc_cond_wait(filp, &arg); - if (copy_to_user(untrusted_in, &arg, sizeof(arg))) - return -EFAULT; - return rval; -} - -static int do_vsoc_cond_wake(struct file *filp, uint32_t offset) -{ - struct vsoc_device_region *region_p = vsoc_region_from_filep(filp); - u32 region_number = iminor(file_inode(filp)); - struct vsoc_region_data *data = vsoc_dev.regions_data + region_number; - /* Ensure that the offset is aligned */ - if (offset & (sizeof(uint32_t) - 1)) - return -EADDRNOTAVAIL; - /* Ensure that the offset is within shared memory */ - if (((uint64_t)offset) + region_p->region_begin_offset + - sizeof(uint32_t) > region_p->region_end_offset) - return -E2BIG; - /* - * TODO(b/73664181): Use multiple futex wait queues. - * We need to wake every sleeper when the condition changes. Typically - * only a single thread will be waiting on the condition, but there - * are exceptions. The worst case is about 10 threads. - */ - wake_up_interruptible_all(&data->futex_wait_queue); - return 0; -} - -static long vsoc_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) -{ - int rv = 0; - struct vsoc_device_region *region_p; - u32 reg_num; - struct vsoc_region_data *reg_data; - int retval = vsoc_validate_filep(filp); - - if (retval) - return retval; - region_p = vsoc_region_from_filep(filp); - reg_num = iminor(file_inode(filp)); - reg_data = vsoc_dev.regions_data + reg_num; - switch (cmd) { - case VSOC_CREATE_FD_SCOPED_PERMISSION: - { - struct fd_scoped_permission_node *node = NULL; - - node = kzalloc(sizeof(*node), GFP_KERNEL); - /* We can't allocate memory for the permission */ - if (!node) - return -ENOMEM; - INIT_LIST_HEAD(&node->list); - rv = do_create_fd_scoped_permission - (region_p, - node, - (struct fd_scoped_permission_arg __user *)arg); - if (!rv) { - mutex_lock(&vsoc_dev.mtx); - list_add(&node->list, &vsoc_dev.permissions); - mutex_unlock(&vsoc_dev.mtx); - } else { - kfree(node); - return rv; - } - } - break; - - case VSOC_GET_FD_SCOPED_PERMISSION: - { - struct fd_scoped_permission_node *node = - ((struct vsoc_private_data *)filp->private_data)-> - fd_scoped_permission_node; - if (!node) - return -ENOENT; - if (copy_to_user - ((struct fd_scoped_permission __user *)arg, - &node->permission, sizeof(node->permission))) - return -EFAULT; - } - break; - - case VSOC_MAYBE_SEND_INTERRUPT_TO_HOST: - if (!atomic_xchg(reg_data->outgoing_signalled, 1)) { - writel(reg_num, vsoc_dev.regs + DOORBELL); - return 0; - } else { - return -EBUSY; - } - break; - - case VSOC_SEND_INTERRUPT_TO_HOST: - writel(reg_num, vsoc_dev.regs + DOORBELL); - return 0; - case VSOC_WAIT_FOR_INCOMING_INTERRUPT: - wait_event_interruptible - (reg_data->interrupt_wait_queue, - (atomic_read(reg_data->incoming_signalled) != 0)); - break; - - case VSOC_DESCRIBE_REGION: - return do_vsoc_describe_region - (filp, - (struct vsoc_device_region __user *)arg); - - case VSOC_SELF_INTERRUPT: - atomic_set(reg_data->incoming_signalled, 1); - wake_up_interruptible(®_data->interrupt_wait_queue); - break; - - case VSOC_COND_WAIT: - return do_vsoc_cond_wait(filp, - (struct vsoc_cond_wait __user *)arg); - case VSOC_COND_WAKE: - return do_vsoc_cond_wake(filp, arg); - - default: - return -EINVAL; - } - return 0; -} - -static ssize_t vsoc_read(struct file *filp, char __user *buffer, size_t len, - loff_t *poffset) -{ - __u32 area_off; - const void *area_p; - ssize_t area_len; - int retval = vsoc_validate_filep(filp); - - if (retval) - return retval; - area_len = vsoc_get_area(filp, &area_off); - area_p = shm_off_to_virtual_addr(area_off); - area_p += *poffset; - area_len -= *poffset; - if (area_len <= 0) - return 0; - if (area_len < len) - len = area_len; - if (copy_to_user(buffer, area_p, len)) - return -EFAULT; - *poffset += len; - return len; -} - -static loff_t vsoc_lseek(struct file *filp, loff_t offset, int origin) -{ - ssize_t area_len = 0; - int retval = vsoc_validate_filep(filp); - - if (retval) - return retval; - area_len = vsoc_get_area(filp, NULL); - switch (origin) { - case SEEK_SET: - break; - - case SEEK_CUR: - if (offset > 0 && offset + filp->f_pos < 0) - return -EOVERFLOW; - offset += filp->f_pos; - break; - - case SEEK_END: - if (offset > 0 && offset + area_len < 0) - return -EOVERFLOW; - offset += area_len; - break; - - case SEEK_DATA: - if (offset >= area_len) - return -EINVAL; - if (offset < 0) - offset = 0; - break; - - case SEEK_HOLE: - /* Next hole is always the end of the region, unless offset is - * beyond that - */ - if (offset < area_len) - offset = area_len; - break; - - default: - return -EINVAL; - } - - if (offset < 0 || offset > area_len) - return -EINVAL; - filp->f_pos = offset; - - return offset; -} - -static ssize_t vsoc_write(struct file *filp, const char __user *buffer, - size_t len, loff_t *poffset) -{ - __u32 area_off; - void *area_p; - ssize_t area_len; - int retval = vsoc_validate_filep(filp); - - if (retval) - return retval; - area_len = vsoc_get_area(filp, &area_off); - area_p = shm_off_to_virtual_addr(area_off); - area_p += *poffset; - area_len -= *poffset; - if (area_len <= 0) - return 0; - if (area_len < len) - len = area_len; - if (copy_from_user(area_p, buffer, len)) - return -EFAULT; - *poffset += len; - return len; -} - -static irqreturn_t vsoc_interrupt(int irq, void *region_data_v) -{ - struct vsoc_region_data *region_data = - (struct vsoc_region_data *)region_data_v; - int reg_num = region_data - vsoc_dev.regions_data; - - if (unlikely(!region_data)) - return IRQ_NONE; - - if (unlikely(reg_num < 0 || - reg_num >= vsoc_dev.layout->region_count)) { - dev_err(&vsoc_dev.dev->dev, - "invalid irq @%p reg_num=0x%04x\n", - region_data, reg_num); - return IRQ_NONE; - } - if (unlikely(vsoc_dev.regions_data + reg_num != region_data)) { - dev_err(&vsoc_dev.dev->dev, - "irq not aligned @%p reg_num=0x%04x\n", - region_data, reg_num); - return IRQ_NONE; - } - wake_up_interruptible(®ion_data->interrupt_wait_queue); - return IRQ_HANDLED; -} - -static int vsoc_probe_device(struct pci_dev *pdev, - const struct pci_device_id *ent) -{ - int result; - int i; - resource_size_t reg_size; - dev_t devt; - - vsoc_dev.dev = pdev; - result = pci_enable_device(pdev); - if (result) { - dev_err(&pdev->dev, - "pci_enable_device failed %s: error %d\n", - pci_name(pdev), result); - return result; - } - vsoc_dev.enabled_device = true; - result = pci_request_regions(pdev, "vsoc"); - if (result < 0) { - dev_err(&pdev->dev, "pci_request_regions failed\n"); - vsoc_remove_device(pdev); - return -EBUSY; - } - vsoc_dev.requested_regions = true; - /* Set up the control registers in BAR 0 */ - reg_size = pci_resource_len(pdev, REGISTER_BAR); - if (reg_size > MAX_REGISTER_BAR_LEN) - vsoc_dev.regs = - pci_iomap(pdev, REGISTER_BAR, MAX_REGISTER_BAR_LEN); - else - vsoc_dev.regs = pci_iomap(pdev, REGISTER_BAR, reg_size); - - if (!vsoc_dev.regs) { - dev_err(&pdev->dev, - "cannot map registers of size %zu\n", - (size_t)reg_size); - vsoc_remove_device(pdev); - return -EBUSY; - } - - /* Map the shared memory in BAR 2 */ - vsoc_dev.shm_phys_start = pci_resource_start(pdev, SHARED_MEMORY_BAR); - vsoc_dev.shm_size = pci_resource_len(pdev, SHARED_MEMORY_BAR); - - dev_info(&pdev->dev, "shared memory @ DMA %pa size=0x%zx\n", - &vsoc_dev.shm_phys_start, vsoc_dev.shm_size); - vsoc_dev.kernel_mapped_shm = pci_iomap_wc(pdev, SHARED_MEMORY_BAR, 0); - if (!vsoc_dev.kernel_mapped_shm) { - dev_err(&vsoc_dev.dev->dev, "cannot iomap region\n"); - vsoc_remove_device(pdev); - return -EBUSY; - } - - vsoc_dev.layout = (struct vsoc_shm_layout_descriptor __force *) - vsoc_dev.kernel_mapped_shm; - dev_info(&pdev->dev, "major_version: %d\n", - vsoc_dev.layout->major_version); - dev_info(&pdev->dev, "minor_version: %d\n", - vsoc_dev.layout->minor_version); - dev_info(&pdev->dev, "size: 0x%x\n", vsoc_dev.layout->size); - dev_info(&pdev->dev, "regions: %d\n", vsoc_dev.layout->region_count); - if (vsoc_dev.layout->major_version != - CURRENT_VSOC_LAYOUT_MAJOR_VERSION) { - dev_err(&vsoc_dev.dev->dev, - "driver supports only major_version %d\n", - CURRENT_VSOC_LAYOUT_MAJOR_VERSION); - vsoc_remove_device(pdev); - return -EBUSY; - } - result = alloc_chrdev_region(&devt, 0, vsoc_dev.layout->region_count, - VSOC_DEV_NAME); - if (result) { - dev_err(&vsoc_dev.dev->dev, "alloc_chrdev_region failed\n"); - vsoc_remove_device(pdev); - return -EBUSY; - } - vsoc_dev.major = MAJOR(devt); - cdev_init(&vsoc_dev.cdev, &vsoc_ops); - vsoc_dev.cdev.owner = THIS_MODULE; - result = cdev_add(&vsoc_dev.cdev, devt, vsoc_dev.layout->region_count); - if (result) { - dev_err(&vsoc_dev.dev->dev, "cdev_add error\n"); - vsoc_remove_device(pdev); - return -EBUSY; - } - vsoc_dev.cdev_added = true; - vsoc_dev.class = class_create(THIS_MODULE, VSOC_DEV_NAME); - if (IS_ERR(vsoc_dev.class)) { - dev_err(&vsoc_dev.dev->dev, "class_create failed\n"); - vsoc_remove_device(pdev); - return PTR_ERR(vsoc_dev.class); - } - vsoc_dev.class_added = true; - vsoc_dev.regions = (struct vsoc_device_region __force *) - ((void *)vsoc_dev.layout + - vsoc_dev.layout->vsoc_region_desc_offset); - vsoc_dev.msix_entries = - kcalloc(vsoc_dev.layout->region_count, - sizeof(vsoc_dev.msix_entries[0]), GFP_KERNEL); - if (!vsoc_dev.msix_entries) { - dev_err(&vsoc_dev.dev->dev, - "unable to allocate msix_entries\n"); - vsoc_remove_device(pdev); - return -ENOSPC; - } - vsoc_dev.regions_data = - kcalloc(vsoc_dev.layout->region_count, - sizeof(vsoc_dev.regions_data[0]), GFP_KERNEL); - if (!vsoc_dev.regions_data) { - dev_err(&vsoc_dev.dev->dev, - "unable to allocate regions' data\n"); - vsoc_remove_device(pdev); - return -ENOSPC; - } - for (i = 0; i < vsoc_dev.layout->region_count; ++i) - vsoc_dev.msix_entries[i].entry = i; - - result = pci_enable_msix_exact(vsoc_dev.dev, vsoc_dev.msix_entries, - vsoc_dev.layout->region_count); - if (result) { - dev_info(&pdev->dev, "pci_enable_msix failed: %d\n", result); - vsoc_remove_device(pdev); - return -ENOSPC; - } - /* Check that all regions are well formed */ - for (i = 0; i < vsoc_dev.layout->region_count; ++i) { - const struct vsoc_device_region *region = vsoc_dev.regions + i; - - if (!PAGE_ALIGNED(region->region_begin_offset) || - !PAGE_ALIGNED(region->region_end_offset)) { - dev_err(&vsoc_dev.dev->dev, - "region %d not aligned (%x:%x)", i, - region->region_begin_offset, - region->region_end_offset); - vsoc_remove_device(pdev); - return -EFAULT; - } - if (region->region_begin_offset >= region->region_end_offset || - region->region_end_offset > vsoc_dev.shm_size) { - dev_err(&vsoc_dev.dev->dev, - "region %d offsets are wrong: %x %x %zx", - i, region->region_begin_offset, - region->region_end_offset, vsoc_dev.shm_size); - vsoc_remove_device(pdev); - return -EFAULT; - } - if (region->managed_by >= vsoc_dev.layout->region_count) { - dev_err(&vsoc_dev.dev->dev, - "region %d has invalid owner: %u", - i, region->managed_by); - vsoc_remove_device(pdev); - return -EFAULT; - } - } - vsoc_dev.msix_enabled = true; - for (i = 0; i < vsoc_dev.layout->region_count; ++i) { - const struct vsoc_device_region *region = vsoc_dev.regions + i; - size_t name_sz = sizeof(vsoc_dev.regions_data[i].name) - 1; - const struct vsoc_signal_table_layout *h_to_g_signal_table = - ®ion->host_to_guest_signal_table; - const struct vsoc_signal_table_layout *g_to_h_signal_table = - ®ion->guest_to_host_signal_table; - - vsoc_dev.regions_data[i].name[name_sz] = '\0'; - memcpy(vsoc_dev.regions_data[i].name, region->device_name, - name_sz); - dev_info(&pdev->dev, "region %d name=%s\n", - i, vsoc_dev.regions_data[i].name); - init_waitqueue_head - (&vsoc_dev.regions_data[i].interrupt_wait_queue); - init_waitqueue_head(&vsoc_dev.regions_data[i].futex_wait_queue); - vsoc_dev.regions_data[i].incoming_signalled = - shm_off_to_virtual_addr(region->region_begin_offset) + - h_to_g_signal_table->interrupt_signalled_offset; - vsoc_dev.regions_data[i].outgoing_signalled = - shm_off_to_virtual_addr(region->region_begin_offset) + - g_to_h_signal_table->interrupt_signalled_offset; - result = request_irq(vsoc_dev.msix_entries[i].vector, - vsoc_interrupt, 0, - vsoc_dev.regions_data[i].name, - vsoc_dev.regions_data + i); - if (result) { - dev_info(&pdev->dev, - "request_irq failed irq=%d vector=%d\n", - i, vsoc_dev.msix_entries[i].vector); - vsoc_remove_device(pdev); - return -ENOSPC; - } - vsoc_dev.regions_data[i].irq_requested = true; - if (!device_create(vsoc_dev.class, NULL, - MKDEV(vsoc_dev.major, i), - NULL, vsoc_dev.regions_data[i].name)) { - dev_err(&vsoc_dev.dev->dev, "device_create failed\n"); - vsoc_remove_device(pdev); - return -EBUSY; - } - vsoc_dev.regions_data[i].device_created = true; - } - return 0; -} - -/* - * This should undo all of the allocations in the probe function in reverse - * order. - * - * Notes: - * - * The device may have been partially initialized, so double check - * that the allocations happened. - * - * This function may be called multiple times, so mark resources as freed - * as they are deallocated. - */ -static void vsoc_remove_device(struct pci_dev *pdev) -{ - int i; - /* - * pdev is the first thing to be set on probe and the last thing - * to be cleared here. If it's NULL then there is no cleanup. - */ - if (!pdev || !vsoc_dev.dev) - return; - dev_info(&pdev->dev, "remove_device\n"); - if (vsoc_dev.regions_data) { - for (i = 0; i < vsoc_dev.layout->region_count; ++i) { - if (vsoc_dev.regions_data[i].device_created) { - device_destroy(vsoc_dev.class, - MKDEV(vsoc_dev.major, i)); - vsoc_dev.regions_data[i].device_created = false; - } - if (vsoc_dev.regions_data[i].irq_requested) - free_irq(vsoc_dev.msix_entries[i].vector, NULL); - vsoc_dev.regions_data[i].irq_requested = false; - } - kfree(vsoc_dev.regions_data); - vsoc_dev.regions_data = NULL; - } - if (vsoc_dev.msix_enabled) { - pci_disable_msix(pdev); - vsoc_dev.msix_enabled = false; - } - kfree(vsoc_dev.msix_entries); - vsoc_dev.msix_entries = NULL; - vsoc_dev.regions = NULL; - if (vsoc_dev.class_added) { - class_destroy(vsoc_dev.class); - vsoc_dev.class_added = false; - } - if (vsoc_dev.cdev_added) { - cdev_del(&vsoc_dev.cdev); - vsoc_dev.cdev_added = false; - } - if (vsoc_dev.major && vsoc_dev.layout) { - unregister_chrdev_region(MKDEV(vsoc_dev.major, 0), - vsoc_dev.layout->region_count); - vsoc_dev.major = 0; - } - vsoc_dev.layout = NULL; - if (vsoc_dev.kernel_mapped_shm) { - pci_iounmap(pdev, vsoc_dev.kernel_mapped_shm); - vsoc_dev.kernel_mapped_shm = NULL; - } - if (vsoc_dev.regs) { - pci_iounmap(pdev, vsoc_dev.regs); - vsoc_dev.regs = NULL; - } - if (vsoc_dev.requested_regions) { - pci_release_regions(pdev); - vsoc_dev.requested_regions = false; - } - if (vsoc_dev.enabled_device) { - pci_disable_device(pdev); - vsoc_dev.enabled_device = false; - } - /* Do this last: it indicates that the device is not initialized. */ - vsoc_dev.dev = NULL; -} - -static void __exit vsoc_cleanup_module(void) -{ - vsoc_remove_device(vsoc_dev.dev); - pci_unregister_driver(&vsoc_pci_driver); -} - -static int __init vsoc_init_module(void) -{ - int err = -ENOMEM; - - INIT_LIST_HEAD(&vsoc_dev.permissions); - mutex_init(&vsoc_dev.mtx); - - err = pci_register_driver(&vsoc_pci_driver); - if (err < 0) - return err; - return 0; -} - -static int vsoc_open(struct inode *inode, struct file *filp) -{ - /* Can't use vsoc_validate_filep because filp is still incomplete */ - int ret = vsoc_validate_inode(inode); - - if (ret) - return ret; - filp->private_data = - kzalloc(sizeof(struct vsoc_private_data), GFP_KERNEL); - if (!filp->private_data) - return -ENOMEM; - return 0; -} - -static int vsoc_release(struct inode *inode, struct file *filp) -{ - struct vsoc_private_data *private_data = NULL; - struct fd_scoped_permission_node *node = NULL; - struct vsoc_device_region *owner_region_p = NULL; - int retval = vsoc_validate_filep(filp); - - if (retval) - return retval; - private_data = (struct vsoc_private_data *)filp->private_data; - if (!private_data) - return 0; - - node = private_data->fd_scoped_permission_node; - if (node) { - owner_region_p = vsoc_region_from_inode(inode); - if (owner_region_p->managed_by != VSOC_REGION_WHOLE) { - owner_region_p = - &vsoc_dev.regions[owner_region_p->managed_by]; - } - do_destroy_fd_scoped_permission_node(owner_region_p, node); - private_data->fd_scoped_permission_node = NULL; - } - kfree(private_data); - filp->private_data = NULL; - - return 0; -} - -/* - * Returns the device relative offset and length of the area specified by the - * fd scoped permission. If there is no fd scoped permission set, a default - * permission covering the entire region is assumed, unless the region is owned - * by another one, in which case the default is a permission with zero size. - */ -static ssize_t vsoc_get_area(struct file *filp, __u32 *area_offset) -{ - __u32 off = 0; - ssize_t length = 0; - struct vsoc_device_region *region_p; - struct fd_scoped_permission *perm; - - region_p = vsoc_region_from_filep(filp); - off = region_p->region_begin_offset; - perm = &((struct vsoc_private_data *)filp->private_data)-> - fd_scoped_permission_node->permission; - if (perm) { - off += perm->begin_offset; - length = perm->end_offset - perm->begin_offset; - } else if (region_p->managed_by == VSOC_REGION_WHOLE) { - /* No permission set and the regions is not owned by another, - * default to full region access. - */ - length = vsoc_device_region_size(region_p); - } else { - /* return zero length, access is denied. */ - length = 0; - } - if (area_offset) - *area_offset = off; - return length; -} - -static int vsoc_mmap(struct file *filp, struct vm_area_struct *vma) -{ - unsigned long len = vma->vm_end - vma->vm_start; - __u32 area_off; - phys_addr_t mem_off; - ssize_t area_len; - int retval = vsoc_validate_filep(filp); - - if (retval) - return retval; - area_len = vsoc_get_area(filp, &area_off); - /* Add the requested offset */ - area_off += (vma->vm_pgoff << PAGE_SHIFT); - area_len -= (vma->vm_pgoff << PAGE_SHIFT); - if (area_len < len) - return -EINVAL; - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - mem_off = shm_off_to_phys_addr(area_off); - if (io_remap_pfn_range(vma, vma->vm_start, mem_off >> PAGE_SHIFT, - len, vma->vm_page_prot)) - return -EAGAIN; - return 0; -} - -module_init(vsoc_init_module); -module_exit(vsoc_cleanup_module); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Greg Hartman <ghartman@google.com>"); -MODULE_DESCRIPTION("VSoC interpretation of QEmu's ivshmem device"); -MODULE_VERSION("1.0"); diff --git a/drivers/staging/greybus/audio_manager.c b/drivers/staging/greybus/audio_manager.c index 9b19ea9d3fa1..9a3f7c034ab4 100644 --- a/drivers/staging/greybus/audio_manager.c +++ b/drivers/staging/greybus/audio_manager.c @@ -92,8 +92,8 @@ void gb_audio_manager_remove_all(void) list_for_each_entry_safe(module, next, &modules_list, list) { list_del(&module->list); - kobject_put(&module->kobj); ida_simple_remove(&module_id, module->id); + kobject_put(&module->kobj); } is_empty = list_empty(&modules_list); diff --git a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c index 9b6ea86d1dcf..ba53959e1303 100644 --- a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c +++ b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c @@ -2009,21 +2009,16 @@ static int wpa_supplicant_ioctl(struct net_device *dev, struct iw_point *p) struct ieee_param *param; uint ret = 0; - if (p->length < sizeof(struct ieee_param) || !p->pointer) { - ret = -EINVAL; - goto out; - } + if (!p->pointer || p->length != sizeof(struct ieee_param)) + return -EINVAL; param = (struct ieee_param *)rtw_malloc(p->length); - if (!param) { - ret = -ENOMEM; - goto out; - } + if (!param) + return -ENOMEM; if (copy_from_user(param, p->pointer, p->length)) { kfree(param); - ret = -EFAULT; - goto out; + return -EFAULT; } switch (param->cmd) { @@ -2054,9 +2049,6 @@ static int wpa_supplicant_ioctl(struct net_device *dev, struct iw_point *p) ret = -EFAULT; kfree(param); - -out: - return ret; } @@ -2791,26 +2783,19 @@ static int rtw_hostapd_ioctl(struct net_device *dev, struct iw_point *p) * so, we just check hw_init_completed */ - if (!padapter->hw_init_completed) { - ret = -EPERM; - goto out; - } + if (!padapter->hw_init_completed) + return -EPERM; - if (!p->pointer) { - ret = -EINVAL; - goto out; - } + if (!p->pointer || p->length != sizeof(struct ieee_param)) + return -EINVAL; param = (struct ieee_param *)rtw_malloc(p->length); - if (!param) { - ret = -ENOMEM; - goto out; - } + if (!param) + return -ENOMEM; if (copy_from_user(param, p->pointer, p->length)) { kfree(param); - ret = -EFAULT; - goto out; + return -EFAULT; } switch (param->cmd) { @@ -2865,7 +2850,6 @@ static int rtw_hostapd_ioctl(struct net_device *dev, struct iw_point *p) if (ret == 0 && copy_to_user(p->pointer, param, p->length)) ret = -EFAULT; kfree(param); -out: return ret; } #endif diff --git a/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c b/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c index b44e902ed338..b6d56cfb0a19 100644 --- a/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c +++ b/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c @@ -476,14 +476,13 @@ int rtl8723bs_xmit_thread(void *context) s32 ret; struct adapter *padapter; struct xmit_priv *pxmitpriv; - u8 thread_name[20] = "RTWHALXT"; - + u8 thread_name[20]; ret = _SUCCESS; padapter = context; pxmitpriv = &padapter->xmitpriv; - rtw_sprintf(thread_name, 20, "%s-"ADPT_FMT, thread_name, ADPT_ARG(padapter)); + rtw_sprintf(thread_name, 20, "RTWHALXT-" ADPT_FMT, ADPT_ARG(padapter)); thread_enter(thread_name); DBG_871X("start "FUNC_ADPT_FMT"\n", FUNC_ADPT_ARG(padapter)); diff --git a/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c b/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c index db6528a01229..9b9038e7deb1 100644 --- a/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c +++ b/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c @@ -3373,21 +3373,16 @@ static int wpa_supplicant_ioctl(struct net_device *dev, struct iw_point *p) /* down(&ieee->wx_sem); */ - if (p->length < sizeof(struct ieee_param) || !p->pointer) { - ret = -EINVAL; - goto out; - } + if (!p->pointer || p->length != sizeof(struct ieee_param)) + return -EINVAL; param = rtw_malloc(p->length); - if (param == NULL) { - ret = -ENOMEM; - goto out; - } + if (param == NULL) + return -ENOMEM; if (copy_from_user(param, p->pointer, p->length)) { kfree(param); - ret = -EFAULT; - goto out; + return -EFAULT; } switch (param->cmd) { @@ -3421,12 +3416,8 @@ static int wpa_supplicant_ioctl(struct net_device *dev, struct iw_point *p) kfree(param); -out: - /* up(&ieee->wx_sem); */ - return ret; - } static int rtw_set_encryption(struct net_device *dev, struct ieee_param *param, u32 param_len) @@ -4200,28 +4191,19 @@ static int rtw_hostapd_ioctl(struct net_device *dev, struct iw_point *p) * so, we just check hw_init_completed */ - if (!padapter->hw_init_completed) { - ret = -EPERM; - goto out; - } - + if (!padapter->hw_init_completed) + return -EPERM; - /* if (p->length < sizeof(struct ieee_param) || !p->pointer) { */ - if (!p->pointer) { - ret = -EINVAL; - goto out; - } + if (!p->pointer || p->length != sizeof(*param)) + return -EINVAL; param = rtw_malloc(p->length); - if (param == NULL) { - ret = -ENOMEM; - goto out; - } + if (param == NULL) + return -ENOMEM; if (copy_from_user(param, p->pointer, p->length)) { kfree(param); - ret = -EFAULT; - goto out; + return -EFAULT; } /* DBG_871X("%s, cmd =%d\n", __func__, param->cmd); */ @@ -4321,13 +4303,8 @@ static int rtw_hostapd_ioctl(struct net_device *dev, struct iw_point *p) if (ret == 0 && copy_to_user(p->pointer, param, p->length)) ret = -EFAULT; - kfree(param); - -out: - return ret; - } static int rtw_wx_set_priv(struct net_device *dev, diff --git a/drivers/staging/vt6656/dpc.c b/drivers/staging/vt6656/dpc.c index 821aae8ca402..a0b60e7d1086 100644 --- a/drivers/staging/vt6656/dpc.c +++ b/drivers/staging/vt6656/dpc.c @@ -98,7 +98,7 @@ int vnt_rx_data(struct vnt_private *priv, struct vnt_rcb *ptr_rcb, vnt_rf_rssi_to_dbm(priv, tail->rssi, &rx_dbm); - priv->bb_pre_ed_rssi = (u8)rx_dbm + 1; + priv->bb_pre_ed_rssi = (u8)-rx_dbm + 1; priv->current_rssi = priv->bb_pre_ed_rssi; skb_pull(skb, sizeof(*head)); diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index b94ed4e30770..09e55ea0bf5d 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -1165,9 +1165,7 @@ int iscsit_setup_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, hdr->cmdsn, be32_to_cpu(hdr->data_length), payload_length, conn->cid); - if (target_get_sess_cmd(&cmd->se_cmd, true) < 0) - return iscsit_add_reject_cmd(cmd, - ISCSI_REASON_WAITING_FOR_LOGOUT, buf); + target_get_sess_cmd(&cmd->se_cmd, true); cmd->sense_reason = transport_lookup_cmd_lun(&cmd->se_cmd, scsilun_to_int(&hdr->lun)); @@ -2004,9 +2002,7 @@ iscsit_handle_task_mgt_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, conn->sess->se_sess, 0, DMA_NONE, TCM_SIMPLE_TAG, cmd->sense_buffer + 2); - if (target_get_sess_cmd(&cmd->se_cmd, true) < 0) - return iscsit_add_reject_cmd(cmd, - ISCSI_REASON_WAITING_FOR_LOGOUT, buf); + target_get_sess_cmd(&cmd->se_cmd, true); /* * TASK_REASSIGN for ERL=2 / connection stays inside of @@ -4149,6 +4145,9 @@ int iscsit_close_connection( iscsit_stop_nopin_response_timer(conn); iscsit_stop_nopin_timer(conn); + if (conn->conn_transport->iscsit_wait_conn) + conn->conn_transport->iscsit_wait_conn(conn); + /* * During Connection recovery drop unacknowledged out of order * commands for this connection, and prepare the other commands @@ -4231,11 +4230,6 @@ int iscsit_close_connection( * must wait until they have completed. */ iscsit_check_conn_usage_count(conn); - target_sess_cmd_list_set_waiting(sess->se_sess); - target_wait_for_sess_cmds(sess->se_sess); - - if (conn->conn_transport->iscsit_wait_conn) - conn->conn_transport->iscsit_wait_conn(conn); ahash_request_free(conn->conn_tx_hash); if (conn->conn_rx_hash) { diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index ea482d4b1f00..0ae9e60fc4d5 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -666,6 +666,11 @@ static int transport_cmd_check_stop_to_fabric(struct se_cmd *cmd) target_remove_from_state_list(cmd); + /* + * Clear struct se_cmd->se_lun before the handoff to FE. + */ + cmd->se_lun = NULL; + spin_lock_irqsave(&cmd->t_state_lock, flags); /* * Determine if frontend context caller is requesting the stopping of @@ -693,6 +698,17 @@ static int transport_cmd_check_stop_to_fabric(struct se_cmd *cmd) return cmd->se_tfo->check_stop_free(cmd); } +static void transport_lun_remove_cmd(struct se_cmd *cmd) +{ + struct se_lun *lun = cmd->se_lun; + + if (!lun) + return; + + if (cmpxchg(&cmd->lun_ref_active, true, false)) + percpu_ref_put(&lun->lun_ref); +} + static void target_complete_failure_work(struct work_struct *work) { struct se_cmd *cmd = container_of(work, struct se_cmd, work); @@ -783,6 +799,8 @@ static void target_handle_abort(struct se_cmd *cmd) WARN_ON_ONCE(kref_read(&cmd->cmd_kref) == 0); + transport_lun_remove_cmd(cmd); + transport_cmd_check_stop_to_fabric(cmd); } @@ -1708,6 +1726,7 @@ static void target_complete_tmr_failure(struct work_struct *work) se_cmd->se_tmr_req->response = TMR_LUN_DOES_NOT_EXIST; se_cmd->se_tfo->queue_tm_rsp(se_cmd); + transport_lun_remove_cmd(se_cmd); transport_cmd_check_stop_to_fabric(se_cmd); } @@ -1898,6 +1917,7 @@ void transport_generic_request_failure(struct se_cmd *cmd, goto queue_full; check_stop: + transport_lun_remove_cmd(cmd); transport_cmd_check_stop_to_fabric(cmd); return; @@ -2195,6 +2215,7 @@ queue_status: transport_handle_queue_full(cmd, cmd->se_dev, ret, false); return; } + transport_lun_remove_cmd(cmd); transport_cmd_check_stop_to_fabric(cmd); } @@ -2289,6 +2310,7 @@ static void target_complete_ok_work(struct work_struct *work) if (ret) goto queue_full; + transport_lun_remove_cmd(cmd); transport_cmd_check_stop_to_fabric(cmd); return; } @@ -2314,6 +2336,7 @@ static void target_complete_ok_work(struct work_struct *work) if (ret) goto queue_full; + transport_lun_remove_cmd(cmd); transport_cmd_check_stop_to_fabric(cmd); return; } @@ -2349,6 +2372,7 @@ queue_rsp: if (ret) goto queue_full; + transport_lun_remove_cmd(cmd); transport_cmd_check_stop_to_fabric(cmd); return; } @@ -2384,6 +2408,7 @@ queue_status: break; } + transport_lun_remove_cmd(cmd); transport_cmd_check_stop_to_fabric(cmd); return; @@ -2710,6 +2735,9 @@ int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks) */ if (cmd->state_active) target_remove_from_state_list(cmd); + + if (cmd->se_lun) + transport_lun_remove_cmd(cmd); } if (aborted) cmd->free_compl = &compl; @@ -2781,9 +2809,6 @@ static void target_release_cmd_kref(struct kref *kref) struct completion *abrt_compl = se_cmd->abrt_compl; unsigned long flags; - if (se_cmd->lun_ref_active) - percpu_ref_put(&se_cmd->se_lun->lun_ref); - if (se_sess) { spin_lock_irqsave(&se_sess->sess_cmd_lock, flags); list_del_init(&se_cmd->se_cmd_list); diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index ad5479f21174..7d6ecc342508 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -348,6 +348,12 @@ out: return ret; } +static int tb_switch_nvm_no_read(void *priv, unsigned int offset, void *val, + size_t bytes) +{ + return -EPERM; +} + static int tb_switch_nvm_write(void *priv, unsigned int offset, void *val, size_t bytes) { @@ -393,6 +399,7 @@ static struct nvmem_device *register_nvmem(struct tb_switch *sw, int id, config.read_only = true; } else { config.name = "nvm_non_active"; + config.reg_read = tb_switch_nvm_no_read; config.reg_write = tb_switch_nvm_write; config.root_only = true; } diff --git a/drivers/tty/serdev/serdev-ttyport.c b/drivers/tty/serdev/serdev-ttyport.c index d1cdd2ab8b4c..d367803e2044 100644 --- a/drivers/tty/serdev/serdev-ttyport.c +++ b/drivers/tty/serdev/serdev-ttyport.c @@ -265,7 +265,6 @@ struct device *serdev_tty_port_register(struct tty_port *port, struct device *parent, struct tty_driver *drv, int idx) { - const struct tty_port_client_operations *old_ops; struct serdev_controller *ctrl; struct serport *serport; int ret; @@ -284,7 +283,6 @@ struct device *serdev_tty_port_register(struct tty_port *port, ctrl->ops = &ctrl_ops; - old_ops = port->client_ops; port->client_ops = &client_ops; port->client_data = ctrl; @@ -297,7 +295,7 @@ struct device *serdev_tty_port_register(struct tty_port *port, err_reset_data: port->client_data = NULL; - port->client_ops = old_ops; + port->client_ops = &tty_port_default_client_ops; serdev_controller_put(ctrl); return ERR_PTR(ret); @@ -312,8 +310,8 @@ int serdev_tty_port_unregister(struct tty_port *port) return -ENODEV; serdev_controller_remove(ctrl); - port->client_ops = NULL; port->client_data = NULL; + port->client_ops = &tty_port_default_client_ops; serdev_controller_put(ctrl); return 0; diff --git a/drivers/tty/serial/8250/8250_aspeed_vuart.c b/drivers/tty/serial/8250/8250_aspeed_vuart.c index d657aa14c3e4..c33e02cbde93 100644 --- a/drivers/tty/serial/8250/8250_aspeed_vuart.c +++ b/drivers/tty/serial/8250/8250_aspeed_vuart.c @@ -446,7 +446,6 @@ static int aspeed_vuart_probe(struct platform_device *pdev) port.port.line = rc; port.port.irq = irq_of_parse_and_map(np, 0); - port.port.irqflags = IRQF_SHARED; port.port.handle_irq = aspeed_vuart_handle_irq; port.port.iotype = UPIO_MEM; port.port.type = PORT_16550A; diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index 0894a22fd702..f2a33c9082a6 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -174,7 +174,7 @@ static int serial_link_irq_chain(struct uart_8250_port *up) struct hlist_head *h; struct hlist_node *n; struct irq_info *i; - int ret, irq_flags = up->port.flags & UPF_SHARE_IRQ ? IRQF_SHARED : 0; + int ret; mutex_lock(&hash_mutex); @@ -209,9 +209,8 @@ static int serial_link_irq_chain(struct uart_8250_port *up) INIT_LIST_HEAD(&up->list); i->head = &up->list; spin_unlock_irq(&i->lock); - irq_flags |= up->port.irqflags; ret = request_irq(up->port.irq, serial8250_interrupt, - irq_flags, up->port.name, i); + up->port.irqflags, up->port.name, i); if (ret < 0) serial_do_unlink(i, up); } diff --git a/drivers/tty/serial/8250/8250_of.c b/drivers/tty/serial/8250/8250_of.c index 531ad67395e0..f6687756ec5e 100644 --- a/drivers/tty/serial/8250/8250_of.c +++ b/drivers/tty/serial/8250/8250_of.c @@ -202,7 +202,6 @@ static int of_platform_serial_setup(struct platform_device *ofdev, port->type = type; port->uartclk = clk; - port->irqflags |= IRQF_SHARED; if (of_property_read_bool(np, "no-loopback-test")) port->flags |= UPF_SKIP_TEST; diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 430e3467aff7..0325f2e53b74 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -2177,6 +2177,10 @@ int serial8250_do_startup(struct uart_port *port) } } + /* Check if we need to have shared IRQs */ + if (port->irq && (up->port.flags & UPF_SHARE_IRQ)) + up->port.irqflags |= IRQF_SHARED; + if (port->irq && !(up->port.flags & UPF_NO_THRE_TEST)) { unsigned char iir1; /* diff --git a/drivers/tty/serial/ar933x_uart.c b/drivers/tty/serial/ar933x_uart.c index 3bdd56a1021b..ea12f10610b6 100644 --- a/drivers/tty/serial/ar933x_uart.c +++ b/drivers/tty/serial/ar933x_uart.c @@ -286,6 +286,10 @@ static void ar933x_uart_set_termios(struct uart_port *port, ar933x_uart_rmw_set(up, AR933X_UART_CS_REG, AR933X_UART_CS_HOST_INT_EN); + /* enable RX and TX ready overide */ + ar933x_uart_rmw_set(up, AR933X_UART_CS_REG, + AR933X_UART_CS_TX_READY_ORIDE | AR933X_UART_CS_RX_READY_ORIDE); + /* reenable the UART */ ar933x_uart_rmw(up, AR933X_UART_CS_REG, AR933X_UART_CS_IF_MODE_M << AR933X_UART_CS_IF_MODE_S, @@ -418,6 +422,10 @@ static int ar933x_uart_startup(struct uart_port *port) ar933x_uart_rmw_set(up, AR933X_UART_CS_REG, AR933X_UART_CS_HOST_INT_EN); + /* enable RX and TX ready overide */ + ar933x_uart_rmw_set(up, AR933X_UART_CS_REG, + AR933X_UART_CS_TX_READY_ORIDE | AR933X_UART_CS_RX_READY_ORIDE); + /* Enable RX interrupts */ up->ier = AR933X_UART_INT_RX_VALID; ar933x_uart_write(up, AR933X_UART_INT_EN_REG, up->ier); diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index c15c398c88a9..a39c87a7c2e1 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -570,7 +570,8 @@ static void atmel_stop_tx(struct uart_port *port) atmel_uart_writel(port, ATMEL_US_IDR, atmel_port->tx_done_mask); if (atmel_uart_is_half_duplex(port)) - atmel_start_rx(port); + if (!atomic_read(&atmel_port->tasklet_shutdown)) + atmel_start_rx(port); } diff --git a/drivers/tty/serial/cpm_uart/cpm_uart_core.c b/drivers/tty/serial/cpm_uart/cpm_uart_core.c index 19d5a4cf29a6..d4b81b06e0cb 100644 --- a/drivers/tty/serial/cpm_uart/cpm_uart_core.c +++ b/drivers/tty/serial/cpm_uart/cpm_uart_core.c @@ -1373,6 +1373,7 @@ static struct console cpm_scc_uart_console = { static int __init cpm_uart_console_init(void) { + cpm_muram_init(); register_console(&cpm_scc_uart_console); return 0; } diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index 0c6c63166250..d337782b3648 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -599,7 +599,7 @@ static void imx_uart_dma_tx(struct imx_port *sport) sport->tx_bytes = uart_circ_chars_pending(xmit); - if (xmit->tail < xmit->head) { + if (xmit->tail < xmit->head || xmit->head == 0) { sport->dma_tx_nents = 1; sg_init_one(sgl, xmit->buf + xmit->tail, sport->tx_bytes); } else { diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index 191abb18fc2a..0bd1684cabb3 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -129,6 +129,7 @@ static int handle_rx_console(struct uart_port *uport, u32 bytes, bool drop); static int handle_rx_uart(struct uart_port *uport, u32 bytes, bool drop); static unsigned int qcom_geni_serial_tx_empty(struct uart_port *port); static void qcom_geni_serial_stop_rx(struct uart_port *uport); +static void qcom_geni_serial_handle_rx(struct uart_port *uport, bool drop); static const unsigned long root_freq[] = {7372800, 14745600, 19200000, 29491200, 32000000, 48000000, 64000000, 80000000, @@ -599,7 +600,7 @@ static void qcom_geni_serial_stop_rx(struct uart_port *uport) u32 irq_en; u32 status; struct qcom_geni_serial_port *port = to_dev_port(uport, uport); - u32 irq_clear = S_CMD_DONE_EN; + u32 s_irq_status; irq_en = readl(uport->membase + SE_GENI_S_IRQ_EN); irq_en &= ~(S_RX_FIFO_WATERMARK_EN | S_RX_FIFO_LAST_EN); @@ -615,10 +616,19 @@ static void qcom_geni_serial_stop_rx(struct uart_port *uport) return; geni_se_cancel_s_cmd(&port->se); - qcom_geni_serial_poll_bit(uport, SE_GENI_S_CMD_CTRL_REG, - S_GENI_CMD_CANCEL, false); + qcom_geni_serial_poll_bit(uport, SE_GENI_S_IRQ_STATUS, + S_CMD_CANCEL_EN, true); + /* + * If timeout occurs secondary engine remains active + * and Abort sequence is executed. + */ + s_irq_status = readl(uport->membase + SE_GENI_S_IRQ_STATUS); + /* Flush the Rx buffer */ + if (s_irq_status & S_RX_FIFO_LAST_EN) + qcom_geni_serial_handle_rx(uport, true); + writel(s_irq_status, uport->membase + SE_GENI_S_IRQ_CLEAR); + status = readl(uport->membase + SE_GENI_STATUS); - writel(irq_clear, uport->membase + SE_GENI_S_IRQ_CLEAR); if (status & S_GENI_CMD_ACTIVE) qcom_geni_serial_abort_rx(uport); } diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c index 33034b852a51..8de8bac9c6c7 100644 --- a/drivers/tty/serial/serial-tegra.c +++ b/drivers/tty/serial/serial-tegra.c @@ -692,11 +692,22 @@ static void tegra_uart_copy_rx_to_tty(struct tegra_uart_port *tup, count, DMA_TO_DEVICE); } +static void do_handle_rx_pio(struct tegra_uart_port *tup) +{ + struct tty_struct *tty = tty_port_tty_get(&tup->uport.state->port); + struct tty_port *port = &tup->uport.state->port; + + tegra_uart_handle_rx_pio(tup, port); + if (tty) { + tty_flip_buffer_push(port); + tty_kref_put(tty); + } +} + static void tegra_uart_rx_buffer_push(struct tegra_uart_port *tup, unsigned int residue) { struct tty_port *port = &tup->uport.state->port; - struct tty_struct *tty = tty_port_tty_get(port); unsigned int count; async_tx_ack(tup->rx_dma_desc); @@ -705,11 +716,7 @@ static void tegra_uart_rx_buffer_push(struct tegra_uart_port *tup, /* If we are here, DMA is stopped */ tegra_uart_copy_rx_to_tty(tup, port, count); - tegra_uart_handle_rx_pio(tup, port); - if (tty) { - tty_flip_buffer_push(port); - tty_kref_put(tty); - } + do_handle_rx_pio(tup); } static void tegra_uart_rx_dma_complete(void *args) @@ -749,8 +756,10 @@ static void tegra_uart_terminate_rx_dma(struct tegra_uart_port *tup) { struct dma_tx_state state; - if (!tup->rx_dma_active) + if (!tup->rx_dma_active) { + do_handle_rx_pio(tup); return; + } dmaengine_terminate_all(tup->rx_dma_chan); dmaengine_tx_status(tup->rx_dma_chan, tup->rx_cookie, &state); @@ -816,18 +825,6 @@ static void tegra_uart_handle_modem_signal_change(struct uart_port *u) uart_handle_cts_change(&tup->uport, msr & UART_MSR_CTS); } -static void do_handle_rx_pio(struct tegra_uart_port *tup) -{ - struct tty_struct *tty = tty_port_tty_get(&tup->uport.state->port); - struct tty_port *port = &tup->uport.state->port; - - tegra_uart_handle_rx_pio(tup, port); - if (tty) { - tty_flip_buffer_push(port); - tty_kref_put(tty); - } -} - static irqreturn_t tegra_uart_isr(int irq, void *data) { struct tegra_uart_port *tup = data; diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c index 044c3cbdcfa4..ea80bf872f54 100644 --- a/drivers/tty/tty_port.c +++ b/drivers/tty/tty_port.c @@ -52,10 +52,11 @@ static void tty_port_default_wakeup(struct tty_port *port) } } -static const struct tty_port_client_operations default_client_ops = { +const struct tty_port_client_operations tty_port_default_client_ops = { .receive_buf = tty_port_default_receive_buf, .write_wakeup = tty_port_default_wakeup, }; +EXPORT_SYMBOL_GPL(tty_port_default_client_ops); void tty_port_init(struct tty_port *port) { @@ -68,7 +69,7 @@ void tty_port_init(struct tty_port *port) spin_lock_init(&port->lock); port->close_delay = (50 * HZ) / 100; port->closing_wait = (3000 * HZ) / 100; - port->client_ops = &default_client_ops; + port->client_ops = &tty_port_default_client_ops; kref_init(&port->kref); } EXPORT_SYMBOL(tty_port_init); diff --git a/drivers/tty/vt/selection.c b/drivers/tty/vt/selection.c index 78732feaf65b..0c50d7410b31 100644 --- a/drivers/tty/vt/selection.c +++ b/drivers/tty/vt/selection.c @@ -16,6 +16,7 @@ #include <linux/tty.h> #include <linux/sched.h> #include <linux/mm.h> +#include <linux/mutex.h> #include <linux/slab.h> #include <linux/types.h> @@ -29,6 +30,8 @@ #include <linux/console.h> #include <linux/tty_flip.h> +#include <linux/sched/signal.h> + /* Don't take this from <ctype.h>: 011-015 on the screen aren't spaces */ #define isspace(c) ((c) == ' ') @@ -43,6 +46,7 @@ static volatile int sel_start = -1; /* cleared by clear_selection */ static int sel_end; static int sel_buffer_lth; static char *sel_buffer; +static DEFINE_MUTEX(sel_lock); /* clear_selection, highlight and highlight_pointer can be called from interrupt (via scrollback/front) */ @@ -184,7 +188,7 @@ int set_selection_kernel(struct tiocl_selection *v, struct tty_struct *tty) char *bp, *obp; int i, ps, pe, multiplier; u32 c; - int mode; + int mode, ret = 0; poke_blanked_console(); @@ -210,6 +214,7 @@ int set_selection_kernel(struct tiocl_selection *v, struct tty_struct *tty) if (ps > pe) /* make sel_start <= sel_end */ swap(ps, pe); + mutex_lock(&sel_lock); if (sel_cons != vc_cons[fg_console].d) { clear_selection(); sel_cons = vc_cons[fg_console].d; @@ -255,9 +260,10 @@ int set_selection_kernel(struct tiocl_selection *v, struct tty_struct *tty) break; case TIOCL_SELPOINTER: highlight_pointer(pe); - return 0; + goto unlock; default: - return -EINVAL; + ret = -EINVAL; + goto unlock; } /* remove the pointer */ @@ -279,7 +285,7 @@ int set_selection_kernel(struct tiocl_selection *v, struct tty_struct *tty) else if (new_sel_start == sel_start) { if (new_sel_end == sel_end) /* no action required */ - return 0; + goto unlock; else if (new_sel_end > sel_end) /* extend to right */ highlight(sel_end + 2, new_sel_end); else /* contract from right */ @@ -307,7 +313,8 @@ int set_selection_kernel(struct tiocl_selection *v, struct tty_struct *tty) if (!bp) { printk(KERN_WARNING "selection: kmalloc() failed\n"); clear_selection(); - return -ENOMEM; + ret = -ENOMEM; + goto unlock; } kfree(sel_buffer); sel_buffer = bp; @@ -332,7 +339,9 @@ int set_selection_kernel(struct tiocl_selection *v, struct tty_struct *tty) } } sel_buffer_lth = bp - sel_buffer; - return 0; +unlock: + mutex_unlock(&sel_lock); + return ret; } EXPORT_SYMBOL_GPL(set_selection_kernel); @@ -350,6 +359,7 @@ int paste_selection(struct tty_struct *tty) unsigned int count; struct tty_ldisc *ld; DECLARE_WAITQUEUE(wait, current); + int ret = 0; console_lock(); poke_blanked_console(); @@ -361,10 +371,17 @@ int paste_selection(struct tty_struct *tty) tty_buffer_lock_exclusive(&vc->port); add_wait_queue(&vc->paste_wait, &wait); + mutex_lock(&sel_lock); while (sel_buffer && sel_buffer_lth > pasted) { set_current_state(TASK_INTERRUPTIBLE); + if (signal_pending(current)) { + ret = -EINTR; + break; + } if (tty_throttled(tty)) { + mutex_unlock(&sel_lock); schedule(); + mutex_lock(&sel_lock); continue; } __set_current_state(TASK_RUNNING); @@ -373,11 +390,12 @@ int paste_selection(struct tty_struct *tty) count); pasted += count; } + mutex_unlock(&sel_lock); remove_wait_queue(&vc->paste_wait, &wait); __set_current_state(TASK_RUNNING); tty_buffer_unlock_exclusive(&vc->port); tty_ldisc_deref(ld); - return 0; + return ret; } EXPORT_SYMBOL_GPL(paste_selection); diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 35d21cdb60d0..0cfbb7182b5a 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -936,10 +936,21 @@ static void flush_scrollback(struct vc_data *vc) WARN_CONSOLE_UNLOCKED(); set_origin(vc); - if (vc->vc_sw->con_flush_scrollback) + if (vc->vc_sw->con_flush_scrollback) { vc->vc_sw->con_flush_scrollback(vc); - else + } else if (con_is_visible(vc)) { + /* + * When no con_flush_scrollback method is provided then the + * legacy way for flushing the scrollback buffer is to use + * a side effect of the con_switch method. We do it only on + * the foreground console as background consoles have no + * scrollback buffers in that case and we obviously don't + * want to switch to them. + */ + hide_cursor(vc); vc->vc_sw->con_switch(vc); + set_cursor(vc); + } } /* diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c index 8b0ed139592f..ee6c91ef1f6c 100644 --- a/drivers/tty/vt/vt_ioctl.c +++ b/drivers/tty/vt/vt_ioctl.c @@ -876,15 +876,20 @@ int vt_ioctl(struct tty_struct *tty, return -EINVAL; for (i = 0; i < MAX_NR_CONSOLES; i++) { + struct vc_data *vcp; + if (!vc_cons[i].d) continue; console_lock(); - if (v.v_vlin) - vc_cons[i].d->vc_scan_lines = v.v_vlin; - if (v.v_clin) - vc_cons[i].d->vc_font.height = v.v_clin; - vc_cons[i].d->vc_resize_user = 1; - vc_resize(vc_cons[i].d, v.v_cols, v.v_rows); + vcp = vc_cons[i].d; + if (vcp) { + if (v.v_vlin) + vcp->vc_scan_lines = v.v_vlin; + if (v.v_clin) + vcp->vc_font.height = v.v_clin; + vcp->vc_resize_user = 1; + vc_resize(vcp, v.v_cols, v.v_rows); + } console_unlock(); } break; diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 26bc05e48d8a..b7918f695434 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -256,6 +256,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, struct usb_host_interface *ifp, int num_ep, unsigned char *buffer, int size) { + struct usb_device *udev = to_usb_device(ddev); unsigned char *buffer0 = buffer; struct usb_endpoint_descriptor *d; struct usb_host_endpoint *endpoint; @@ -297,6 +298,16 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, goto skip_to_next_endpoint_or_interface_descriptor; } + /* Ignore blacklisted endpoints */ + if (udev->quirks & USB_QUIRK_ENDPOINT_BLACKLIST) { + if (usb_endpoint_is_blacklisted(udev, ifp, d)) { + dev_warn(ddev, "config %d interface %d altsetting %d has a blacklisted endpoint with address 0x%X, skipping\n", + cfgno, inum, asnum, + d->bEndpointAddress); + goto skip_to_next_endpoint_or_interface_descriptor; + } + } + endpoint = &ifp->endpoint[ifp->desc.bNumEndpoints]; ++ifp->desc.bNumEndpoints; @@ -311,7 +322,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, j = 255; if (usb_endpoint_xfer_int(d)) { i = 1; - switch (to_usb_device(ddev)->speed) { + switch (udev->speed) { case USB_SPEED_SUPER_PLUS: case USB_SPEED_SUPER: case USB_SPEED_HIGH: @@ -332,8 +343,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, /* * This quirk fixes bIntervals reported in ms. */ - if (to_usb_device(ddev)->quirks & - USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL) { + if (udev->quirks & USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL) { n = clamp(fls(d->bInterval) + 3, i, j); i = j = n; } @@ -341,8 +351,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, * This quirk fixes bIntervals reported in * linear microframes. */ - if (to_usb_device(ddev)->quirks & - USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL) { + if (udev->quirks & USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL) { n = clamp(fls(d->bInterval), i, j); i = j = n; } @@ -359,7 +368,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, } else if (usb_endpoint_xfer_isoc(d)) { i = 1; j = 16; - switch (to_usb_device(ddev)->speed) { + switch (udev->speed) { case USB_SPEED_HIGH: n = 7; /* 8 ms = 2^(7-1) uframes */ break; @@ -381,8 +390,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, * explicitly forbidden by the USB spec. In an attempt to make * them usable, we will try treating them as Interrupt endpoints. */ - if (to_usb_device(ddev)->speed == USB_SPEED_LOW && - usb_endpoint_xfer_bulk(d)) { + if (udev->speed == USB_SPEED_LOW && usb_endpoint_xfer_bulk(d)) { dev_warn(ddev, "config %d interface %d altsetting %d " "endpoint 0x%X is Bulk; changing to Interrupt\n", cfgno, inum, asnum, d->bEndpointAddress); @@ -406,7 +414,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, /* Find the highest legal maxpacket size for this endpoint */ i = 0; /* additional transactions per microframe */ - switch (to_usb_device(ddev)->speed) { + switch (udev->speed) { case USB_SPEED_LOW: maxpacket_maxes = low_speed_maxpacket_maxes; break; @@ -442,8 +450,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, * maxpacket sizes other than 512. High speed HCDs may not * be able to handle that particular bug, so let's warn... */ - if (to_usb_device(ddev)->speed == USB_SPEED_HIGH - && usb_endpoint_xfer_bulk(d)) { + if (udev->speed == USB_SPEED_HIGH && usb_endpoint_xfer_bulk(d)) { if (maxp != 512) dev_warn(ddev, "config %d interface %d altsetting %d " "bulk endpoint 0x%X has invalid maxpacket %d\n", @@ -452,7 +459,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, } /* Parse a possible SuperSpeed endpoint companion descriptor */ - if (to_usb_device(ddev)->speed >= USB_SPEED_SUPER) + if (udev->speed >= USB_SPEED_SUPER) usb_parse_ss_endpoint_companion(ddev, cfgno, inum, asnum, endpoint, buffer, size); diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 3405b146edc9..1d212f82c69b 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -38,7 +38,9 @@ #include "otg_whitelist.h" #define USB_VENDOR_GENESYS_LOGIC 0x05e3 +#define USB_VENDOR_SMSC 0x0424 #define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND 0x01 +#define HUB_QUIRK_DISABLE_AUTOSUSPEND 0x02 #define USB_TP_TRANSMISSION_DELAY 40 /* ns */ #define USB_TP_TRANSMISSION_DELAY_MAX 65535 /* ns */ @@ -1217,11 +1219,6 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) #ifdef CONFIG_PM udev->reset_resume = 1; #endif - /* Don't set the change_bits when the device - * was powered off. - */ - if (test_bit(port1, hub->power_bits)) - set_bit(port1, hub->change_bits); } else { /* The power session is gone; tell hub_wq */ @@ -1731,6 +1728,10 @@ static void hub_disconnect(struct usb_interface *intf) kfree(hub->buffer); pm_suspend_ignore_children(&intf->dev, false); + + if (hub->quirk_disable_autosuspend) + usb_autopm_put_interface(intf); + kref_put(&hub->kref, hub_release); } @@ -1863,6 +1864,11 @@ static int hub_probe(struct usb_interface *intf, const struct usb_device_id *id) if (id->driver_info & HUB_QUIRK_CHECK_PORT_AUTOSUSPEND) hub->quirk_check_port_auto_suspend = 1; + if (id->driver_info & HUB_QUIRK_DISABLE_AUTOSUSPEND) { + hub->quirk_disable_autosuspend = 1; + usb_autopm_get_interface(intf); + } + if (hub_configure(hub, &desc->endpoint[0].desc) >= 0) return 0; @@ -5599,6 +5605,10 @@ out_hdev_lock: } static const struct usb_device_id hub_id_table[] = { + { .match_flags = USB_DEVICE_ID_MATCH_VENDOR | USB_DEVICE_ID_MATCH_INT_CLASS, + .idVendor = USB_VENDOR_SMSC, + .bInterfaceClass = USB_CLASS_HUB, + .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND}, { .match_flags = USB_DEVICE_ID_MATCH_VENDOR | USB_DEVICE_ID_MATCH_INT_CLASS, .idVendor = USB_VENDOR_GENESYS_LOGIC, diff --git a/drivers/usb/core/hub.h b/drivers/usb/core/hub.h index a9e24e4b8df1..a97dd1ba964e 100644 --- a/drivers/usb/core/hub.h +++ b/drivers/usb/core/hub.h @@ -61,6 +61,7 @@ struct usb_hub { unsigned quiescing:1; unsigned disconnected:1; unsigned in_reset:1; + unsigned quirk_disable_autosuspend:1; unsigned quirk_check_port_auto_suspend:1; diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 6b6413073584..2b24336a72e5 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -354,6 +354,10 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x0904, 0x6103), .driver_info = USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL }, + /* Sound Devices USBPre2 */ + { USB_DEVICE(0x0926, 0x0202), .driver_info = + USB_QUIRK_ENDPOINT_BLACKLIST }, + /* Keytouch QWERTY Panel keyboard */ { USB_DEVICE(0x0926, 0x3333), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, @@ -445,6 +449,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* INTEL VALUE SSD */ { USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME }, + /* novation SoundControl XL */ + { USB_DEVICE(0x1235, 0x0061), .driver_info = USB_QUIRK_RESET_RESUME }, + { } /* terminating entry must be last */ }; @@ -472,6 +479,39 @@ static const struct usb_device_id usb_amd_resume_quirk_list[] = { { } /* terminating entry must be last */ }; +/* + * Entries for blacklisted endpoints that should be ignored when parsing + * configuration descriptors. + * + * Matched for devices with USB_QUIRK_ENDPOINT_BLACKLIST. + */ +static const struct usb_device_id usb_endpoint_blacklist[] = { + { USB_DEVICE_INTERFACE_NUMBER(0x0926, 0x0202, 1), .driver_info = 0x85 }, + { } +}; + +bool usb_endpoint_is_blacklisted(struct usb_device *udev, + struct usb_host_interface *intf, + struct usb_endpoint_descriptor *epd) +{ + const struct usb_device_id *id; + unsigned int address; + + for (id = usb_endpoint_blacklist; id->match_flags; ++id) { + if (!usb_match_device(udev, id)) + continue; + + if (!usb_match_one_id_intf(udev, intf, id)) + continue; + + address = id->driver_info; + if (address == epd->bEndpointAddress) + return true; + } + + return false; +} + static bool usb_match_any_interface(struct usb_device *udev, const struct usb_device_id *id) { diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h index cf4783cf661a..3ad0ee57e859 100644 --- a/drivers/usb/core/usb.h +++ b/drivers/usb/core/usb.h @@ -37,6 +37,9 @@ extern void usb_authorize_interface(struct usb_interface *); extern void usb_detect_quirks(struct usb_device *udev); extern void usb_detect_interface_quirks(struct usb_device *udev); extern void usb_release_quirk_list(void); +extern bool usb_endpoint_is_blacklisted(struct usb_device *udev, + struct usb_host_interface *intf, + struct usb_endpoint_descriptor *epd); extern int usb_remove_device(struct usb_device *udev); extern int usb_get_device_descriptor(struct usb_device *dev, diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index 88f7d6d4ff2d..92ed32ec1607 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -1083,11 +1083,6 @@ static void dwc2_hsotg_start_req(struct dwc2_hsotg *hsotg, else packets = 1; /* send one packet if length is zero. */ - if (hs_ep->isochronous && length > (hs_ep->mc * hs_ep->ep.maxpacket)) { - dev_err(hsotg->dev, "req length > maxpacket*mc\n"); - return; - } - if (dir_in && index != 0) if (hs_ep->isochronous) epsize = DXEPTSIZ_MC(packets); @@ -1391,6 +1386,13 @@ static int dwc2_hsotg_ep_queue(struct usb_ep *ep, struct usb_request *req, req->actual = 0; req->status = -EINPROGRESS; + /* Don't queue ISOC request if length greater than mps*mc */ + if (hs_ep->isochronous && + req->length > (hs_ep->mc * hs_ep->ep.maxpacket)) { + dev_err(hs->dev, "req length > maxpacket*mc\n"); + return -EINVAL; + } + /* In DDMA mode for ISOC's don't queue request if length greater * than descriptor limits. */ @@ -1632,6 +1634,7 @@ static int dwc2_hsotg_process_req_status(struct dwc2_hsotg *hsotg, struct dwc2_hsotg_ep *ep0 = hsotg->eps_out[0]; struct dwc2_hsotg_ep *ep; __le16 reply; + u16 status; int ret; dev_dbg(hsotg->dev, "%s: USB_REQ_GET_STATUS\n", __func__); @@ -1643,11 +1646,10 @@ static int dwc2_hsotg_process_req_status(struct dwc2_hsotg *hsotg, switch (ctrl->bRequestType & USB_RECIP_MASK) { case USB_RECIP_DEVICE: - /* - * bit 0 => self powered - * bit 1 => remote wakeup - */ - reply = cpu_to_le16(0); + status = 1 << USB_DEVICE_SELF_POWERED; + status |= hsotg->remote_wakeup_allowed << + USB_DEVICE_REMOTE_WAKEUP; + reply = cpu_to_le16(status); break; case USB_RECIP_INTERFACE: @@ -1758,7 +1760,10 @@ static int dwc2_hsotg_process_req_feature(struct dwc2_hsotg *hsotg, case USB_RECIP_DEVICE: switch (wValue) { case USB_DEVICE_REMOTE_WAKEUP: - hsotg->remote_wakeup_allowed = 1; + if (set) + hsotg->remote_wakeup_allowed = 1; + else + hsotg->remote_wakeup_allowed = 0; break; case USB_DEVICE_TEST_MODE: @@ -1768,16 +1773,17 @@ static int dwc2_hsotg_process_req_feature(struct dwc2_hsotg *hsotg, return -EINVAL; hsotg->test_mode = wIndex >> 8; - ret = dwc2_hsotg_send_reply(hsotg, ep0, NULL, 0); - if (ret) { - dev_err(hsotg->dev, - "%s: failed to send reply\n", __func__); - return ret; - } break; default: return -ENOENT; } + + ret = dwc2_hsotg_send_reply(hsotg, ep0, NULL, 0); + if (ret) { + dev_err(hsotg->dev, + "%s: failed to send reply\n", __func__); + return ret; + } break; case USB_RECIP_ENDPOINT: diff --git a/drivers/usb/dwc3/debug.h b/drivers/usb/dwc3/debug.h index e56beb9d1e36..4a13ceaf4093 100644 --- a/drivers/usb/dwc3/debug.h +++ b/drivers/usb/dwc3/debug.h @@ -256,86 +256,77 @@ static inline const char *dwc3_ep_event_string(char *str, size_t size, u8 epnum = event->endpoint_number; size_t len; int status; - int ret; - ret = snprintf(str, size, "ep%d%s: ", epnum >> 1, + len = scnprintf(str, size, "ep%d%s: ", epnum >> 1, (epnum & 1) ? "in" : "out"); - if (ret < 0) - return "UNKNOWN"; status = event->status; switch (event->endpoint_event) { case DWC3_DEPEVT_XFERCOMPLETE: - len = strlen(str); - snprintf(str + len, size - len, "Transfer Complete (%c%c%c)", + len += scnprintf(str + len, size - len, + "Transfer Complete (%c%c%c)", status & DEPEVT_STATUS_SHORT ? 'S' : 's', status & DEPEVT_STATUS_IOC ? 'I' : 'i', status & DEPEVT_STATUS_LST ? 'L' : 'l'); - len = strlen(str); - if (epnum <= 1) - snprintf(str + len, size - len, " [%s]", + scnprintf(str + len, size - len, " [%s]", dwc3_ep0_state_string(ep0state)); break; case DWC3_DEPEVT_XFERINPROGRESS: - len = strlen(str); - - snprintf(str + len, size - len, "Transfer In Progress [%d] (%c%c%c)", + scnprintf(str + len, size - len, + "Transfer In Progress [%d] (%c%c%c)", event->parameters, status & DEPEVT_STATUS_SHORT ? 'S' : 's', status & DEPEVT_STATUS_IOC ? 'I' : 'i', status & DEPEVT_STATUS_LST ? 'M' : 'm'); break; case DWC3_DEPEVT_XFERNOTREADY: - len = strlen(str); - - snprintf(str + len, size - len, "Transfer Not Ready [%d]%s", + len += scnprintf(str + len, size - len, + "Transfer Not Ready [%d]%s", event->parameters, status & DEPEVT_STATUS_TRANSFER_ACTIVE ? " (Active)" : " (Not Active)"); - len = strlen(str); - /* Control Endpoints */ if (epnum <= 1) { int phase = DEPEVT_STATUS_CONTROL_PHASE(event->status); switch (phase) { case DEPEVT_STATUS_CONTROL_DATA: - snprintf(str + ret, size - ret, + scnprintf(str + len, size - len, " [Data Phase]"); break; case DEPEVT_STATUS_CONTROL_STATUS: - snprintf(str + ret, size - ret, + scnprintf(str + len, size - len, " [Status Phase]"); } } break; case DWC3_DEPEVT_RXTXFIFOEVT: - snprintf(str + ret, size - ret, "FIFO"); + scnprintf(str + len, size - len, "FIFO"); break; case DWC3_DEPEVT_STREAMEVT: status = event->status; switch (status) { case DEPEVT_STREAMEVT_FOUND: - snprintf(str + ret, size - ret, " Stream %d Found", + scnprintf(str + len, size - len, " Stream %d Found", event->parameters); break; case DEPEVT_STREAMEVT_NOTFOUND: default: - snprintf(str + ret, size - ret, " Stream Not Found"); + scnprintf(str + len, size - len, " Stream Not Found"); break; } break; case DWC3_DEPEVT_EPCMDCMPLT: - snprintf(str + ret, size - ret, "Endpoint Command Complete"); + scnprintf(str + len, size - len, "Endpoint Command Complete"); break; default: - snprintf(str, size, "UNKNOWN"); + scnprintf(str + len, size - len, "UNKNOWN"); } return str; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 1b8014ab0b25..1b7d2f9cb673 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2429,7 +2429,8 @@ static int dwc3_gadget_ep_reclaim_completed_trb(struct dwc3_ep *dep, if (event->status & DEPEVT_STATUS_SHORT && !chain) return 1; - if (event->status & DEPEVT_STATUS_IOC) + if ((trb->ctrl & DWC3_TRB_CTRL_IOC) || + (trb->ctrl & DWC3_TRB_CTRL_LST)) return 1; return 0; diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index 3b4f67000315..223f72d4d9ed 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -437,12 +437,14 @@ static u8 encode_bMaxPower(enum usb_device_speed speed, val = CONFIG_USB_GADGET_VBUS_DRAW; if (!val) return 0; - switch (speed) { - case USB_SPEED_SUPER: - return DIV_ROUND_UP(val, 8); - default: - return DIV_ROUND_UP(val, 2); - } + if (speed < USB_SPEED_SUPER) + return min(val, 500U) / 2; + else + /* + * USB 3.x supports up to 900mA, but since 900 isn't divisible + * by 8 the integral division will effectively cap to 896mA. + */ + return min(val, 900U) / 8; } static int config_buf(struct usb_configuration *config, @@ -854,6 +856,10 @@ static int set_config(struct usb_composite_dev *cdev, /* when we return, be sure our power usage is valid */ power = c->MaxPower ? c->MaxPower : CONFIG_USB_GADGET_VBUS_DRAW; + if (gadget->speed < USB_SPEED_SUPER) + power = min(power, 500U); + else + power = min(power, 900U); done: usb_gadget_vbus_draw(gadget, power); if (result >= 0 && cdev->delayed_status) @@ -2280,7 +2286,7 @@ void composite_resume(struct usb_gadget *gadget) { struct usb_composite_dev *cdev = get_gadget_data(gadget); struct usb_function *f; - u16 maxpower; + unsigned maxpower; /* REVISIT: should we have config level * suspend/resume callbacks? @@ -2294,10 +2300,14 @@ void composite_resume(struct usb_gadget *gadget) f->resume(f); } - maxpower = cdev->config->MaxPower; + maxpower = cdev->config->MaxPower ? + cdev->config->MaxPower : CONFIG_USB_GADGET_VBUS_DRAW; + if (gadget->speed < USB_SPEED_SUPER) + maxpower = min(maxpower, 500U); + else + maxpower = min(maxpower, 900U); - usb_gadget_vbus_draw(gadget, maxpower ? - maxpower : CONFIG_USB_GADGET_VBUS_DRAW); + usb_gadget_vbus_draw(gadget, maxpower); } cdev->suspended = 0; diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 6171d28331e6..571917677d35 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -1162,18 +1162,19 @@ static int ffs_aio_cancel(struct kiocb *kiocb) { struct ffs_io_data *io_data = kiocb->private; struct ffs_epfile *epfile = kiocb->ki_filp->private_data; + unsigned long flags; int value; ENTER(); - spin_lock_irq(&epfile->ffs->eps_lock); + spin_lock_irqsave(&epfile->ffs->eps_lock, flags); if (likely(io_data && io_data->ep && io_data->req)) value = usb_ep_dequeue(io_data->ep, io_data->req); else value = -EINVAL; - spin_unlock_irq(&epfile->ffs->eps_lock); + spin_unlock_irqrestore(&epfile->ffs->eps_lock, flags); return value; } diff --git a/drivers/usb/gadget/function/u_audio.c b/drivers/usb/gadget/function/u_audio.c index 6d956f190f5a..e6d32c536781 100644 --- a/drivers/usb/gadget/function/u_audio.c +++ b/drivers/usb/gadget/function/u_audio.c @@ -361,7 +361,7 @@ int u_audio_start_capture(struct g_audio *audio_dev) ep = audio_dev->out_ep; prm = &uac->c_prm; config_ep_by_speed(gadget, &audio_dev->func, ep); - req_len = prm->max_psize; + req_len = ep->maxpacket; prm->ep_enabled = true; usb_ep_enable(ep); @@ -379,7 +379,7 @@ int u_audio_start_capture(struct g_audio *audio_dev) req->context = &prm->ureq[i]; req->length = req_len; req->complete = u_audio_iso_complete; - req->buf = prm->rbuf + i * prm->max_psize; + req->buf = prm->rbuf + i * ep->maxpacket; } if (usb_ep_queue(ep, prm->ureq[i].req, GFP_ATOMIC)) @@ -430,9 +430,9 @@ int u_audio_start_playback(struct g_audio *audio_dev) uac->p_pktsize = min_t(unsigned int, uac->p_framesize * (params->p_srate / uac->p_interval), - prm->max_psize); + ep->maxpacket); - if (uac->p_pktsize < prm->max_psize) + if (uac->p_pktsize < ep->maxpacket) uac->p_pktsize_residue = uac->p_framesize * (params->p_srate % uac->p_interval); else @@ -457,7 +457,7 @@ int u_audio_start_playback(struct g_audio *audio_dev) req->context = &prm->ureq[i]; req->length = req_len; req->complete = u_audio_iso_complete; - req->buf = prm->rbuf + i * prm->max_psize; + req->buf = prm->rbuf + i * ep->maxpacket; } if (usb_ep_queue(ep, prm->ureq[i].req, GFP_ATOMIC)) diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index f986e5c55974..8167d379e115 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -561,8 +561,10 @@ static int gs_start_io(struct gs_port *port) port->n_read = 0; started = gs_start_rx(port); - /* unblock any pending writes into our circular buffer */ if (started) { + gs_start_tx(port); + /* Unblock any pending writes into our circular buffer, in case + * we didn't in gs_start_tx() */ tty_wakeup(port->port.tty); } else { gs_free_requests(ep, head, &port->read_allocated); diff --git a/drivers/usb/gadget/udc/udc-xilinx.c b/drivers/usb/gadget/udc/udc-xilinx.c index 29d8e5f8bb58..b1cfc8279c3d 100644 --- a/drivers/usb/gadget/udc/udc-xilinx.c +++ b/drivers/usb/gadget/udc/udc-xilinx.c @@ -1399,7 +1399,6 @@ err: /** * xudc_stop - stops the device. * @gadget: pointer to the usb gadget structure - * @driver: pointer to usb gadget driver structure * * Return: zero always */ diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index 7a3a29e5e9d2..af92b2576fe9 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -55,6 +55,7 @@ static u8 usb_bos_descriptor [] = { static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf, u16 wLength) { + struct xhci_port_cap *port_cap = NULL; int i, ssa_count; u32 temp; u16 desc_size, ssp_cap_size, ssa_size = 0; @@ -64,16 +65,24 @@ static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf, ssp_cap_size = sizeof(usb_bos_descriptor) - desc_size; /* does xhci support USB 3.1 Enhanced SuperSpeed */ - if (xhci->usb3_rhub.min_rev >= 0x01) { + for (i = 0; i < xhci->num_port_caps; i++) { + if (xhci->port_caps[i].maj_rev == 0x03 && + xhci->port_caps[i].min_rev >= 0x01) { + usb3_1 = true; + port_cap = &xhci->port_caps[i]; + break; + } + } + + if (usb3_1) { /* does xhci provide a PSI table for SSA speed attributes? */ - if (xhci->usb3_rhub.psi_count) { + if (port_cap->psi_count) { /* two SSA entries for each unique PSI ID, RX and TX */ - ssa_count = xhci->usb3_rhub.psi_uid_count * 2; + ssa_count = port_cap->psi_uid_count * 2; ssa_size = ssa_count * sizeof(u32); ssp_cap_size -= 16; /* skip copying the default SSA */ } desc_size += ssp_cap_size; - usb3_1 = true; } memcpy(buf, &usb_bos_descriptor, min(desc_size, wLength)); @@ -99,7 +108,7 @@ static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf, } /* If PSI table exists, add the custom speed attributes from it */ - if (usb3_1 && xhci->usb3_rhub.psi_count) { + if (usb3_1 && port_cap->psi_count) { u32 ssp_cap_base, bm_attrib, psi, psi_mant, psi_exp; int offset; @@ -111,7 +120,7 @@ static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf, /* attribute count SSAC bits 4:0 and ID count SSIC bits 8:5 */ bm_attrib = (ssa_count - 1) & 0x1f; - bm_attrib |= (xhci->usb3_rhub.psi_uid_count - 1) << 5; + bm_attrib |= (port_cap->psi_uid_count - 1) << 5; put_unaligned_le32(bm_attrib, &buf[ssp_cap_base + 4]); if (wLength < desc_size + ssa_size) @@ -124,8 +133,8 @@ static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf, * USB 3.1 requires two SSA entries (RX and TX) for every link */ offset = desc_size; - for (i = 0; i < xhci->usb3_rhub.psi_count; i++) { - psi = xhci->usb3_rhub.psi[i]; + for (i = 0; i < port_cap->psi_count; i++) { + psi = port_cap->psi[i]; psi &= ~USB_SSP_SUBLINK_SPEED_RSVD; psi_exp = XHCI_EXT_PORT_PSIE(psi); psi_mant = XHCI_EXT_PORT_PSIM(psi); diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 3b1388fa2f36..884c601bfa15 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1475,9 +1475,15 @@ int xhci_endpoint_init(struct xhci_hcd *xhci, /* Allow 3 retries for everything but isoc, set CErr = 3 */ if (!usb_endpoint_xfer_isoc(&ep->desc)) err_count = 3; - /* Some devices get this wrong */ - if (usb_endpoint_xfer_bulk(&ep->desc) && udev->speed == USB_SPEED_HIGH) - max_packet = 512; + /* HS bulk max packet should be 512, FS bulk supports 8, 16, 32 or 64 */ + if (usb_endpoint_xfer_bulk(&ep->desc)) { + if (udev->speed == USB_SPEED_HIGH) + max_packet = 512; + if (udev->speed == USB_SPEED_FULL) { + max_packet = rounddown_pow_of_two(max_packet); + max_packet = clamp_val(max_packet, 8, 64); + } + } /* xHCI 1.0 and 1.1 indicates that ctrl ep avg TRB Length should be 8 */ if (usb_endpoint_xfer_control(&ep->desc) && xhci->hci_version >= 0x100) avg_trb_len = 8; @@ -1909,17 +1915,17 @@ no_bw: xhci->usb3_rhub.num_ports = 0; xhci->num_active_eps = 0; kfree(xhci->usb2_rhub.ports); - kfree(xhci->usb2_rhub.psi); kfree(xhci->usb3_rhub.ports); - kfree(xhci->usb3_rhub.psi); kfree(xhci->hw_ports); kfree(xhci->rh_bw); kfree(xhci->ext_caps); + for (i = 0; i < xhci->num_port_caps; i++) + kfree(xhci->port_caps[i].psi); + kfree(xhci->port_caps); + xhci->num_port_caps = 0; xhci->usb2_rhub.ports = NULL; - xhci->usb2_rhub.psi = NULL; xhci->usb3_rhub.ports = NULL; - xhci->usb3_rhub.psi = NULL; xhci->hw_ports = NULL; xhci->rh_bw = NULL; xhci->ext_caps = NULL; @@ -2120,6 +2126,7 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports, u8 major_revision, minor_revision; struct xhci_hub *rhub; struct device *dev = xhci_to_hcd(xhci)->self.sysdev; + struct xhci_port_cap *port_cap; temp = readl(addr); major_revision = XHCI_EXT_PORT_MAJOR(temp); @@ -2154,31 +2161,39 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports, /* WTF? "Valid values are ‘1’ to MaxPorts" */ return; - rhub->psi_count = XHCI_EXT_PORT_PSIC(temp); - if (rhub->psi_count) { - rhub->psi = kcalloc_node(rhub->psi_count, sizeof(*rhub->psi), - GFP_KERNEL, dev_to_node(dev)); - if (!rhub->psi) - rhub->psi_count = 0; + port_cap = &xhci->port_caps[xhci->num_port_caps++]; + if (xhci->num_port_caps > max_caps) + return; + + port_cap->maj_rev = major_revision; + port_cap->min_rev = minor_revision; + port_cap->psi_count = XHCI_EXT_PORT_PSIC(temp); - rhub->psi_uid_count++; - for (i = 0; i < rhub->psi_count; i++) { - rhub->psi[i] = readl(addr + 4 + i); + if (port_cap->psi_count) { + port_cap->psi = kcalloc_node(port_cap->psi_count, + sizeof(*port_cap->psi), + GFP_KERNEL, dev_to_node(dev)); + if (!port_cap->psi) + port_cap->psi_count = 0; + + port_cap->psi_uid_count++; + for (i = 0; i < port_cap->psi_count; i++) { + port_cap->psi[i] = readl(addr + 4 + i); /* count unique ID values, two consecutive entries can * have the same ID if link is assymetric */ - if (i && (XHCI_EXT_PORT_PSIV(rhub->psi[i]) != - XHCI_EXT_PORT_PSIV(rhub->psi[i - 1]))) - rhub->psi_uid_count++; + if (i && (XHCI_EXT_PORT_PSIV(port_cap->psi[i]) != + XHCI_EXT_PORT_PSIV(port_cap->psi[i - 1]))) + port_cap->psi_uid_count++; xhci_dbg(xhci, "PSIV:%d PSIE:%d PLT:%d PFD:%d LP:%d PSIM:%d\n", - XHCI_EXT_PORT_PSIV(rhub->psi[i]), - XHCI_EXT_PORT_PSIE(rhub->psi[i]), - XHCI_EXT_PORT_PLT(rhub->psi[i]), - XHCI_EXT_PORT_PFD(rhub->psi[i]), - XHCI_EXT_PORT_LP(rhub->psi[i]), - XHCI_EXT_PORT_PSIM(rhub->psi[i])); + XHCI_EXT_PORT_PSIV(port_cap->psi[i]), + XHCI_EXT_PORT_PSIE(port_cap->psi[i]), + XHCI_EXT_PORT_PLT(port_cap->psi[i]), + XHCI_EXT_PORT_PFD(port_cap->psi[i]), + XHCI_EXT_PORT_LP(port_cap->psi[i]), + XHCI_EXT_PORT_PSIM(port_cap->psi[i])); } } /* cache usb2 port capabilities */ @@ -2213,6 +2228,7 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports, continue; } hw_port->rhub = rhub; + hw_port->port_cap = port_cap; rhub->num_ports++; } /* FIXME: Should we disable ports not in the Extended Capabilities? */ @@ -2303,6 +2319,11 @@ static int xhci_setup_port_arrays(struct xhci_hcd *xhci, gfp_t flags) if (!xhci->ext_caps) return -ENOMEM; + xhci->port_caps = kcalloc_node(cap_count, sizeof(*xhci->port_caps), + flags, dev_to_node(dev)); + if (!xhci->port_caps) + return -ENOMEM; + offset = cap_start; while (offset) { diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 4917c5b033fa..5e9b537df631 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -49,6 +49,7 @@ #define PCI_DEVICE_ID_INTEL_TITAN_RIDGE_4C_XHCI 0x15ec #define PCI_DEVICE_ID_INTEL_TITAN_RIDGE_DD_XHCI 0x15f0 #define PCI_DEVICE_ID_INTEL_ICE_LAKE_XHCI 0x8a13 +#define PCI_DEVICE_ID_INTEL_CML_XHCI 0xa3af #define PCI_DEVICE_ID_AMD_PROMONTORYA_4 0x43b9 #define PCI_DEVICE_ID_AMD_PROMONTORYA_3 0x43ba @@ -187,7 +188,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_B_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI || - pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI)) { + pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_CML_XHCI)) { xhci->quirks |= XHCI_PME_STUCK_QUIRK; } if (pdev->vendor == PCI_VENDOR_ID_INTEL && @@ -302,6 +304,9 @@ static int xhci_pci_setup(struct usb_hcd *hcd) if (!usb_hcd_is_primary_hcd(hcd)) return 0; + if (xhci->quirks & XHCI_PME_STUCK_QUIRK) + xhci_pme_acpi_rtd3_enable(pdev); + xhci_dbg(xhci, "Got SBRN %u\n", (unsigned int) xhci->sbrn); /* Find any debug ports */ @@ -359,9 +364,6 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) HCC_MAX_PSA(xhci->hcc_params) >= 4) xhci->shared_hcd->can_do_streams = 1; - if (xhci->quirks & XHCI_PME_STUCK_QUIRK) - xhci_pme_acpi_rtd3_enable(dev); - /* USB-2 and USB-3 roothubs initialized, allow runtime pm suspend */ pm_runtime_put_noidle(&dev->dev); diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 13d8838cd552..3ecee10fdcdc 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1702,12 +1702,20 @@ struct xhci_bus_state { * Intel Lynx Point LP xHCI host. */ #define XHCI_MAX_REXIT_TIMEOUT_MS 20 +struct xhci_port_cap { + u32 *psi; /* array of protocol speed ID entries */ + u8 psi_count; + u8 psi_uid_count; + u8 maj_rev; + u8 min_rev; +}; struct xhci_port { __le32 __iomem *addr; int hw_portnum; int hcd_portnum; struct xhci_hub *rhub; + struct xhci_port_cap *port_cap; }; struct xhci_hub { @@ -1719,9 +1727,6 @@ struct xhci_hub { /* supported prococol extended capabiliy values */ u8 maj_rev; u8 min_rev; - u32 *psi; /* array of protocol speed ID entries */ - u8 psi_count; - u8 psi_uid_count; }; /* There is one xhci_hcd structure per controller */ @@ -1880,6 +1885,9 @@ struct xhci_hcd { /* cached usb2 extened protocol capabilites */ u32 *ext_caps; unsigned int num_ext_caps; + /* cached extended protocol port capabilities */ + struct xhci_port_cap *port_caps; + unsigned int num_port_caps; /* Compliance Mode Recovery Data */ struct timer_list comp_mode_recovery_timer; u32 port_status_u0; diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c index dce44fbf031f..dce20301e367 100644 --- a/drivers/usb/misc/iowarrior.c +++ b/drivers/usb/misc/iowarrior.c @@ -33,6 +33,14 @@ #define USB_DEVICE_ID_CODEMERCS_IOWPV2 0x1512 /* full speed iowarrior */ #define USB_DEVICE_ID_CODEMERCS_IOW56 0x1503 +/* fuller speed iowarrior */ +#define USB_DEVICE_ID_CODEMERCS_IOW28 0x1504 +#define USB_DEVICE_ID_CODEMERCS_IOW28L 0x1505 +#define USB_DEVICE_ID_CODEMERCS_IOW100 0x1506 + +/* OEMed devices */ +#define USB_DEVICE_ID_CODEMERCS_IOW24SAG 0x158a +#define USB_DEVICE_ID_CODEMERCS_IOW56AM 0x158b /* Get a minor range for your devices from the usb maintainer */ #ifdef CONFIG_USB_DYNAMIC_MINORS @@ -133,6 +141,11 @@ static const struct usb_device_id iowarrior_ids[] = { {USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOWPV1)}, {USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOWPV2)}, {USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW56)}, + {USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW24SAG)}, + {USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW56AM)}, + {USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW28)}, + {USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW28L)}, + {USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW100)}, {} /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, iowarrior_ids); @@ -357,6 +370,7 @@ static ssize_t iowarrior_write(struct file *file, } switch (dev->product_id) { case USB_DEVICE_ID_CODEMERCS_IOW24: + case USB_DEVICE_ID_CODEMERCS_IOW24SAG: case USB_DEVICE_ID_CODEMERCS_IOWPV1: case USB_DEVICE_ID_CODEMERCS_IOWPV2: case USB_DEVICE_ID_CODEMERCS_IOW40: @@ -371,6 +385,10 @@ static ssize_t iowarrior_write(struct file *file, goto exit; break; case USB_DEVICE_ID_CODEMERCS_IOW56: + case USB_DEVICE_ID_CODEMERCS_IOW56AM: + case USB_DEVICE_ID_CODEMERCS_IOW28: + case USB_DEVICE_ID_CODEMERCS_IOW28L: + case USB_DEVICE_ID_CODEMERCS_IOW100: /* The IOW56 uses asynchronous IO and more urbs */ if (atomic_read(&dev->write_busy) == MAX_WRITES_IN_FLIGHT) { /* Wait until we are below the limit for submitted urbs */ @@ -493,6 +511,7 @@ static long iowarrior_ioctl(struct file *file, unsigned int cmd, switch (cmd) { case IOW_WRITE: if (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW24 || + dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW24SAG || dev->product_id == USB_DEVICE_ID_CODEMERCS_IOWPV1 || dev->product_id == USB_DEVICE_ID_CODEMERCS_IOWPV2 || dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW40) { @@ -767,7 +786,11 @@ static int iowarrior_probe(struct usb_interface *interface, goto error; } - if (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) { + if ((dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) || + (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56AM) || + (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28) || + (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28L) || + (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW100)) { res = usb_find_last_int_out_endpoint(iface_desc, &dev->int_out_endpoint); if (res) { @@ -780,7 +803,11 @@ static int iowarrior_probe(struct usb_interface *interface, /* we have to check the report_size often, so remember it in the endianness suitable for our machine */ dev->report_size = usb_endpoint_maxp(dev->int_in_endpoint); if ((dev->interface->cur_altsetting->desc.bInterfaceNumber == 0) && - (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56)) + ((dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) || + (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56AM) || + (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28) || + (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28L) || + (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW100))) /* IOWarrior56 has wMaxPacketSize different from report size */ dev->report_size = 7; diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c index 037e8eee737d..6153cc35aba0 100644 --- a/drivers/usb/phy/phy-tegra-usb.c +++ b/drivers/usb/phy/phy-tegra-usb.c @@ -969,6 +969,10 @@ static int utmi_phy_probe(struct tegra_usb_phy *tegra_phy, return -ENXIO; } + /* + * Note that UTMI pad registers are shared by all PHYs, therefore + * devm_platform_ioremap_resource() can't be used here. + */ tegra_phy->pad_regs = devm_ioremap(&pdev->dev, res->start, resource_size(res)); if (!tegra_phy->pad_regs) { @@ -1087,6 +1091,10 @@ static int tegra_usb_phy_probe(struct platform_device *pdev) return -ENXIO; } + /* + * Note that PHY and USB controller are using shared registers, + * therefore devm_platform_ioremap_resource() can't be used here. + */ tegra_phy->regs = devm_ioremap(&pdev->dev, res->start, resource_size(res)); if (!tegra_phy->regs) { diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c index d3f420f3a083..c5ecdcd51ffc 100644 --- a/drivers/usb/serial/ch341.c +++ b/drivers/usb/serial/ch341.c @@ -205,6 +205,16 @@ static int ch341_get_divisor(speed_t speed) 16 * speed - 16 * CH341_CLKRATE / (clk_div * (div + 1))) div++; + /* + * Prefer lower base clock (fact = 0) if even divisor. + * + * Note that this makes the receiver more tolerant to errors. + */ + if (fact == 1 && div % 2 == 0) { + div /= 2; + fact = 0; + } + return (0x100 - div) << 8 | fact << 2 | ps; } diff --git a/drivers/usb/serial/ir-usb.c b/drivers/usb/serial/ir-usb.c index 79d0586e2b33..172261a908d8 100644 --- a/drivers/usb/serial/ir-usb.c +++ b/drivers/usb/serial/ir-usb.c @@ -448,7 +448,7 @@ static void ir_set_termios(struct tty_struct *tty, usb_sndbulkpipe(udev, port->bulk_out_endpointAddress), transfer_buffer, 1, &actual_length, 5000); if (ret || actual_length != 1) { - if (actual_length != 1) + if (!ret) ret = -EIO; dev_err(&port->dev, "failed to change line speed: %d\n", ret); } diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index 95bba3ba6ac6..3670fda02c34 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -45,6 +45,7 @@ struct uas_dev_info { struct scsi_cmnd *cmnd[MAX_CMNDS]; spinlock_t lock; struct work_struct work; + struct work_struct scan_work; /* for async scanning */ }; enum { @@ -114,6 +115,17 @@ out: spin_unlock_irqrestore(&devinfo->lock, flags); } +static void uas_scan_work(struct work_struct *work) +{ + struct uas_dev_info *devinfo = + container_of(work, struct uas_dev_info, scan_work); + struct Scsi_Host *shost = usb_get_intfdata(devinfo->intf); + + dev_dbg(&devinfo->intf->dev, "starting scan\n"); + scsi_scan_host(shost); + dev_dbg(&devinfo->intf->dev, "scan complete\n"); +} + static void uas_add_work(struct uas_cmd_info *cmdinfo) { struct scsi_pointer *scp = (void *)cmdinfo; @@ -982,6 +994,7 @@ static int uas_probe(struct usb_interface *intf, const struct usb_device_id *id) init_usb_anchor(&devinfo->data_urbs); spin_lock_init(&devinfo->lock); INIT_WORK(&devinfo->work, uas_do_work); + INIT_WORK(&devinfo->scan_work, uas_scan_work); result = uas_configure_endpoints(devinfo); if (result) @@ -998,7 +1011,9 @@ static int uas_probe(struct usb_interface *intf, const struct usb_device_id *id) if (result) goto free_streams; - scsi_scan_host(shost); + /* Submit the delayed_work for SCSI-device scanning */ + schedule_work(&devinfo->scan_work); + return result; free_streams: @@ -1166,6 +1181,12 @@ static void uas_disconnect(struct usb_interface *intf) usb_kill_anchored_urbs(&devinfo->data_urbs); uas_zap_pending(devinfo, DID_NO_CONNECT); + /* + * Prevent SCSI scanning (if it hasn't started yet) + * or wait for the SCSI-scanning routine to stop. + */ + cancel_work_sync(&devinfo->scan_work); + scsi_remove_host(shost); uas_free_streams(devinfo); scsi_host_put(shost); diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index cec868f8db3f..9ea2b43d4b01 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -207,6 +207,7 @@ config DA9063_WATCHDOG config DA9062_WATCHDOG tristate "Dialog DA9062/61 Watchdog" depends on MFD_DA9062 || COMPILE_TEST + depends on I2C select WATCHDOG_CORE help Support for the watchdog in the DA9062 and DA9061 PMICs. @@ -841,6 +842,7 @@ config MEDIATEK_WATCHDOG tristate "Mediatek SoCs watchdog support" depends on ARCH_MEDIATEK || COMPILE_TEST select WATCHDOG_CORE + select RESET_CONTROLLER help Say Y here to include support for the watchdog timer in Mediatek SoCs. diff --git a/drivers/watchdog/da9062_wdt.c b/drivers/watchdog/da9062_wdt.c index 47eefe072b40..0ad15d55071c 100644 --- a/drivers/watchdog/da9062_wdt.c +++ b/drivers/watchdog/da9062_wdt.c @@ -16,6 +16,7 @@ #include <linux/jiffies.h> #include <linux/mfd/da9062/registers.h> #include <linux/mfd/da9062/core.h> +#include <linux/property.h> #include <linux/regmap.h> #include <linux/of.h> @@ -31,6 +32,7 @@ static const unsigned int wdt_timeout[] = { 0, 2, 4, 8, 16, 32, 65, 131 }; struct da9062_watchdog { struct da9062 *hw; struct watchdog_device wdtdev; + bool use_sw_pm; }; static unsigned int da9062_wdt_timeout_to_sel(unsigned int secs) @@ -95,13 +97,6 @@ static int da9062_wdt_stop(struct watchdog_device *wdd) struct da9062_watchdog *wdt = watchdog_get_drvdata(wdd); int ret; - ret = da9062_reset_watchdog_timer(wdt); - if (ret) { - dev_err(wdt->hw->dev, "Failed to ping the watchdog (err = %d)\n", - ret); - return ret; - } - ret = regmap_update_bits(wdt->hw->regmap, DA9062AA_CONTROL_D, DA9062AA_TWDSCALE_MASK, @@ -200,6 +195,8 @@ static int da9062_wdt_probe(struct platform_device *pdev) if (!wdt) return -ENOMEM; + wdt->use_sw_pm = device_property_present(dev, "dlg,use-sw-pm"); + wdt->hw = chip; wdt->wdtdev.info = &da9062_watchdog_info; @@ -226,6 +223,10 @@ static int da9062_wdt_probe(struct platform_device *pdev) static int __maybe_unused da9062_wdt_suspend(struct device *dev) { struct watchdog_device *wdd = dev_get_drvdata(dev); + struct da9062_watchdog *wdt = watchdog_get_drvdata(wdd); + + if (!wdt->use_sw_pm) + return 0; if (watchdog_active(wdd)) return da9062_wdt_stop(wdd); @@ -236,6 +237,10 @@ static int __maybe_unused da9062_wdt_suspend(struct device *dev) static int __maybe_unused da9062_wdt_resume(struct device *dev) { struct watchdog_device *wdd = dev_get_drvdata(dev); + struct da9062_watchdog *wdt = watchdog_get_drvdata(wdd); + + if (!wdt->use_sw_pm) + return 0; if (watchdog_active(wdd)) return da9062_wdt_start(wdd); diff --git a/drivers/xen/preempt.c b/drivers/xen/preempt.c index 70650b248de5..17240c5325a3 100644 --- a/drivers/xen/preempt.c +++ b/drivers/xen/preempt.c @@ -33,7 +33,9 @@ asmlinkage __visible void xen_maybe_preempt_hcall(void) * cpu. */ __this_cpu_write(xen_in_preemptible_hcall, false); - _cond_resched(); + local_irq_enable(); + cond_resched(); + local_irq_disable(); __this_cpu_write(xen_in_preemptible_hcall, true); } } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 7fa9bb79ad08..89422aa8e9d1 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3164,6 +3164,7 @@ int __cold open_ctree(struct super_block *sb, /* do not make disk changes in broken FS or nologreplay is given */ if (btrfs_super_log_root(disk_super) != 0 && !btrfs_test_opt(fs_info, NOLOGREPLAY)) { + btrfs_info(fs_info, "start tree-log replay"); ret = btrfs_replay_log(fs_info, fs_devices); if (ret) { err = ret; diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 6f417ff68980..bd6229fb2b6f 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -237,6 +237,17 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em) struct extent_map *merge = NULL; struct rb_node *rb; + /* + * We can't modify an extent map that is in the tree and that is being + * used by another task, as it can cause that other task to see it in + * inconsistent state during the merging. We always have 1 reference for + * the tree and 1 for this task (which is unpinning the extent map or + * clearing the logging flag), so anything > 2 means it's being used by + * other tasks too. + */ + if (refcount_read(&em->refs) > 2) + return; + if (em->start != 0) { rb = rb_prev(&em->rb_node); if (rb) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 5b3ec93ff911..36deef69f847 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4085,6 +4085,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, u64 bytes_deleted = 0; bool be_nice = false; bool should_throttle = false; + const u64 lock_start = ALIGN_DOWN(new_size, fs_info->sectorsize); + struct extent_state *cached_state = NULL; BUG_ON(new_size > 0 && min_type != BTRFS_EXTENT_DATA_KEY); @@ -4101,6 +4103,9 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, return -ENOMEM; path->reada = READA_BACK; + lock_extent_bits(&BTRFS_I(inode)->io_tree, lock_start, (u64)-1, + &cached_state); + /* * We want to drop from the next block forward in case this new size is * not block aligned since we will be keeping the last block of the @@ -4137,7 +4142,6 @@ search_again: goto out; } - path->leave_spinning = 1; ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret < 0) goto out; @@ -4289,7 +4293,6 @@ delete: root == fs_info->tree_root)) { struct btrfs_ref ref = { 0 }; - btrfs_set_path_blocking(path); bytes_deleted += extent_num_bytes; btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, @@ -4367,6 +4370,9 @@ out: btrfs_ordered_update_i_size(inode, last_size, NULL); } + unlock_extent_cached(&BTRFS_I(inode)->io_tree, lock_start, (u64)-1, + &cached_state); + btrfs_free_path(path); return ret; } diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index b57f3618e58e..454a1015d026 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -744,6 +744,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, */ be = add_block_entry(fs_info, bytenr, num_bytes, ref_root); if (IS_ERR(be)) { + kfree(ref); kfree(ra); ret = PTR_ERR(be); goto out; @@ -757,6 +758,8 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, "re-allocated a block that still has references to it!"); dump_block_entry(fs_info, be); dump_ref_action(fs_info, ra); + kfree(ref); + kfree(ra); goto out_unlock; } @@ -819,6 +822,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, "dropping a ref for a existing root that doesn't have a ref on the block"); dump_block_entry(fs_info, be); dump_ref_action(fs_info, ra); + kfree(ref); kfree(ra); goto out_unlock; } @@ -834,6 +838,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, "attempting to add another ref for an existing ref on a tree block"); dump_block_entry(fs_info, be); dump_ref_action(fs_info, ra); + kfree(ref); kfree(ra); goto out_unlock; } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 0616a5434793..67c63858812a 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1834,6 +1834,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) } if (btrfs_super_log_root(fs_info->super_copy) != 0) { + btrfs_warn(fs_info, + "mount required to replay tree-log, cannot remount read-write"); ret = -EINVAL; goto restore; } diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 7436422194da..3c10e78924d0 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -901,6 +901,12 @@ static int addrm_unknown_feature_attrs(struct btrfs_fs_info *fs_info, bool add) static void __btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs) { + if (fs_devs->devinfo_kobj) { + kobject_del(fs_devs->devinfo_kobj); + kobject_put(fs_devs->devinfo_kobj); + fs_devs->devinfo_kobj = NULL; + } + if (fs_devs->devices_kobj) { kobject_del(fs_devs->devices_kobj); kobject_put(fs_devs->devices_kobj); @@ -1289,7 +1295,7 @@ int btrfs_sysfs_add_device_link(struct btrfs_fs_devices *fs_devices, init_completion(&dev->kobj_unregister); error = kobject_init_and_add(&dev->devid_kobj, &devid_ktype, - fs_devices->devices_kobj, "%llu", + fs_devices->devinfo_kobj, "%llu", dev->devid); if (error) { kobject_put(&dev->devid_kobj); @@ -1369,6 +1375,15 @@ int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs) return -ENOMEM; } + fs_devs->devinfo_kobj = kobject_create_and_add("devinfo", + &fs_devs->fsid_kobj); + if (!fs_devs->devinfo_kobj) { + btrfs_err(fs_devs->fs_info, + "failed to init sysfs devinfo kobject"); + btrfs_sysfs_remove_fsid(fs_devs); + return -ENOMEM; + } + return 0; } diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 409f4816fb89..f01552a0785e 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -258,6 +258,7 @@ struct btrfs_fs_devices { /* sysfs kobjects */ struct kobject fsid_kobj; struct kobject *devices_kobj; + struct kobject *devinfo_kobj; struct completion kobj_unregister; }; diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 440828afcdde..716574aab3b6 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -601,7 +601,7 @@ static void access_flags_to_mode(__le32 ace_flags, int type, umode_t *pmode, ((flags & FILE_EXEC_RIGHTS) == FILE_EXEC_RIGHTS)) *pmode |= (S_IXUGO & (*pbits_to_set)); - cifs_dbg(NOISY, "access flags 0x%x mode now 0x%x\n", flags, *pmode); + cifs_dbg(NOISY, "access flags 0x%x mode now %04o\n", flags, *pmode); return; } @@ -630,7 +630,7 @@ static void mode_to_access_flags(umode_t mode, umode_t bits_to_use, if (mode & S_IXUGO) *pace_flags |= SET_FILE_EXEC_RIGHTS; - cifs_dbg(NOISY, "mode: 0x%x, access flags now 0x%x\n", + cifs_dbg(NOISY, "mode: %04o, access flags now 0x%x\n", mode, *pace_flags); return; } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index febab27cd838..46ebaf3f0824 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -414,7 +414,7 @@ cifs_show_security(struct seq_file *s, struct cifs_ses *ses) seq_puts(s, "ntlm"); break; case Kerberos: - seq_printf(s, "krb5,cruid=%u", from_kuid_munged(&init_user_ns,ses->cred_uid)); + seq_puts(s, "krb5"); break; case RawNTLMSSP: seq_puts(s, "ntlmssp"); @@ -427,6 +427,10 @@ cifs_show_security(struct seq_file *s, struct cifs_ses *ses) if (ses->sign) seq_puts(s, "i"); + + if (ses->sectype == Kerberos) + seq_printf(s, ",cruid=%u", + from_kuid_munged(&init_user_ns, ses->cred_uid)); } static void diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index a941ac7a659d..4804d1df8c1c 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -4151,7 +4151,7 @@ int cifs_setup_cifs_sb(struct smb_vol *pvolume_info, cifs_sb->mnt_gid = pvolume_info->linux_gid; cifs_sb->mnt_file_mode = pvolume_info->file_mode; cifs_sb->mnt_dir_mode = pvolume_info->dir_mode; - cifs_dbg(FYI, "file mode: 0x%hx dir mode: 0x%hx\n", + cifs_dbg(FYI, "file mode: %04ho dir mode: %04ho\n", cifs_sb->mnt_file_mode, cifs_sb->mnt_dir_mode); cifs_sb->actimeo = pvolume_info->actimeo; diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 9ba623b601ec..b5e6635c578e 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1648,7 +1648,7 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, umode_t mode) struct TCP_Server_Info *server; char *full_path; - cifs_dbg(FYI, "In cifs_mkdir, mode = 0x%hx inode = 0x%p\n", + cifs_dbg(FYI, "In cifs_mkdir, mode = %04ho inode = 0x%p\n", mode, inode); cifs_sb = CIFS_SB(inode->i_sb); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index baa825f4cec0..e47190cae163 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1116,7 +1116,8 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, void *data[1]; struct smb2_file_full_ea_info *ea = NULL; struct kvec close_iov[1]; - int rc; + struct smb2_query_info_rsp *rsp; + int rc, used_len = 0; if (smb3_encryption_required(tcon)) flags |= CIFS_TRANSFORM_REQ; @@ -1139,6 +1140,38 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, cifs_sb); if (rc == -ENODATA) goto sea_exit; + } else { + /* If we are adding a attribute we should first check + * if there will be enough space available to store + * the new EA. If not we should not add it since we + * would not be able to even read the EAs back. + */ + rc = smb2_query_info_compound(xid, tcon, utf16_path, + FILE_READ_EA, + FILE_FULL_EA_INFORMATION, + SMB2_O_INFO_FILE, + CIFSMaxBufSize - + MAX_SMB2_CREATE_RESPONSE_SIZE - + MAX_SMB2_CLOSE_RESPONSE_SIZE, + &rsp_iov[1], &resp_buftype[1], cifs_sb); + if (rc == 0) { + rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base; + used_len = le32_to_cpu(rsp->OutputBufferLength); + } + free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); + resp_buftype[1] = CIFS_NO_BUFFER; + memset(&rsp_iov[1], 0, sizeof(rsp_iov[1])); + rc = 0; + + /* Use a fudge factor of 256 bytes in case we collide + * with a different set_EAs command. + */ + if(CIFSMaxBufSize - MAX_SMB2_CREATE_RESPONSE_SIZE - + MAX_SMB2_CLOSE_RESPONSE_SIZE - 256 < + used_len + ea_name_len + ea_value_len + 1) { + rc = -ENOSPC; + goto sea_exit; + } } } @@ -4795,6 +4828,7 @@ struct smb_version_operations smb21_operations = { .wp_retry_size = smb2_wp_retry_size, .dir_needs_close = smb2_dir_needs_close, .enum_snapshots = smb3_enum_snapshots, + .notify = smb3_notify, .get_dfs_refer = smb2_get_dfs_refer, .select_sectype = smb2_select_sectype, #ifdef CONFIG_CIFS_XATTR diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index db1ef144c63a..2c449aed1b92 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -311,8 +311,10 @@ static int crypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat, struct extent_crypt_result ecr; int rc = 0; - BUG_ON(!crypt_stat || !crypt_stat->tfm - || !(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED)); + if (!crypt_stat || !crypt_stat->tfm + || !(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED)) + return -EINVAL; + if (unlikely(ecryptfs_verbosity > 0)) { ecryptfs_printk(KERN_DEBUG, "Key size [%zd]; key:\n", crypt_stat->key_size); diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index 1c1a56be7ea2..e6ac78c62ca4 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -8,7 +8,7 @@ * Copyright (C) 2004-2008 International Business Machines Corp. * Author(s): Michael A. Halcrow <mahalcro@us.ibm.com> * Trevor S. Highland <trevor.highland@gmail.com> - * Tyler Hicks <tyhicks@ou.edu> + * Tyler Hicks <code@tyhicks.com> */ #ifndef ECRYPTFS_KERNEL_H diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c index 7d326aa0308e..af3eb02bbca1 100644 --- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -1304,7 +1304,7 @@ parse_tag_1_packet(struct ecryptfs_crypt_stat *crypt_stat, printk(KERN_WARNING "Tag 1 packet contains key larger " "than ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES\n"); rc = -EINVAL; - goto out; + goto out_free; } memcpy((*new_auth_tok)->session_key.encrypted_key, &data[(*packet_size)], (body_size - (ECRYPTFS_SIG_SIZE + 2))); diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index b8a7ce379ffe..e63259fdef28 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -7,7 +7,7 @@ * Copyright (C) 2004-2007 International Business Machines Corp. * Author(s): Michael A. Halcrow <mahalcro@us.ibm.com> * Michael C. Thompson <mcthomps@us.ibm.com> - * Tyler Hicks <tyhicks@ou.edu> + * Tyler Hicks <code@tyhicks.com> */ #include <linux/dcache.h> diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c index d668e60b85b5..8646ba76def3 100644 --- a/fs/ecryptfs/messaging.c +++ b/fs/ecryptfs/messaging.c @@ -4,7 +4,7 @@ * * Copyright (C) 2004-2008 International Business Machines Corp. * Author(s): Michael A. Halcrow <mhalcrow@us.ibm.com> - * Tyler Hicks <tyhicks@ou.edu> + * Tyler Hicks <code@tyhicks.com> */ #include <linux/sched.h> #include <linux/slab.h> @@ -379,6 +379,7 @@ int __init ecryptfs_init_messaging(void) * ecryptfs_message_buf_len), GFP_KERNEL); if (!ecryptfs_msg_ctx_arr) { + kfree(ecryptfs_daemon_hash); rc = -ENOMEM; goto out; } diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index 1ee04e76bbe0..0a734ffb4310 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -207,6 +207,7 @@ static int ext4_protect_reserved_inode(struct super_block *sb, return PTR_ERR(inode); num = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; while (i < num) { + cond_resched(); map.m_lblk = i; map.m_len = num - i; n = ext4_map_blocks(NULL, inode, &map, 0); diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 1f340743c9a8..9aa1f75409b0 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -129,12 +129,14 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) if (err != ERR_BAD_DX_DIR) { return err; } - /* - * We don't set the inode dirty flag since it's not - * critical that it get flushed back to the disk. - */ - ext4_clear_inode_flag(file_inode(file), - EXT4_INODE_INDEX); + /* Can we just clear INDEX flag to ignore htree information? */ + if (!ext4_has_metadata_csum(sb)) { + /* + * We don't set the inode dirty flag since it's not + * critical that it gets flushed back to the disk. + */ + ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); + } } if (ext4_has_inline_data(inode)) { diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 9a2ee2428ecc..4441331d06cc 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2544,8 +2544,11 @@ void ext4_insert_dentry(struct inode *inode, struct ext4_filename *fname); static inline void ext4_update_dx_flag(struct inode *inode) { - if (!ext4_has_feature_dir_index(inode->i_sb)) + if (!ext4_has_feature_dir_index(inode->i_sb)) { + /* ext4_iget() should have caught this... */ + WARN_ON_ONCE(ext4_has_feature_metadata_csum(inode->i_sb)); ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); + } } static const unsigned char ext4_filetype_table[] = { DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 1305b810c44a..e60aca791d3f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4644,6 +4644,18 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, ret = -EFSCORRUPTED; goto bad_inode; } + /* + * If dir_index is not enabled but there's dir with INDEX flag set, + * we'd normally treat htree data as empty space. But with metadata + * checksumming that corrupts checksums so forbid that. + */ + if (!ext4_has_feature_dir_index(sb) && ext4_has_metadata_csum(sb) && + ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) { + ext4_error_inode(inode, function, line, 0, + "iget: Dir with htree data on filesystem without dir_index feature."); + ret = -EFSCORRUPTED; + goto bad_inode; + } ei->i_disksize = inode->i_size; #ifdef CONFIG_QUOTA ei->i_reserved_quota = 0; diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 1c44b1a32001..87f7551c5132 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -120,10 +120,10 @@ void __dump_mmp_msg(struct super_block *sb, struct mmp_struct *mmp, { __ext4_warning(sb, function, line, "%s", msg); __ext4_warning(sb, function, line, - "MMP failure info: last update time: %llu, last update " - "node: %s, last update device: %s", - (long long unsigned int) le64_to_cpu(mmp->mmp_time), - mmp->mmp_nodename, mmp->mmp_bdevname); + "MMP failure info: last update time: %llu, last update node: %.*s, last update device: %.*s", + (unsigned long long)le64_to_cpu(mmp->mmp_time), + (int)sizeof(mmp->mmp_nodename), mmp->mmp_nodename, + (int)sizeof(mmp->mmp_bdevname), mmp->mmp_bdevname); } /* @@ -154,6 +154,7 @@ static int kmmpd(void *data) mmp_check_interval = max(EXT4_MMP_CHECK_MULT * mmp_update_interval, EXT4_MMP_MIN_CHECK_INTERVAL); mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval); + BUILD_BUG_ON(sizeof(mmp->mmp_bdevname) < BDEVNAME_SIZE); bdevname(bh->b_bdev, mmp->mmp_bdevname); memcpy(mmp->mmp_nodename, init_utsname()->nodename, @@ -379,7 +380,8 @@ skip: /* * Start a kernel thread to update the MMP block periodically. */ - EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%s", + EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%.*s", + (int)sizeof(mmp->mmp_bdevname), bdevname(bh->b_bdev, mmp->mmp_bdevname)); if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) { diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 129d2ebae00d..ceff4b4b1877 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2213,6 +2213,13 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, retval = ext4_dx_add_entry(handle, &fname, dir, inode); if (!retval || (retval != ERR_BAD_DX_DIR)) goto out; + /* Can we just ignore htree data? */ + if (ext4_has_metadata_csum(sb)) { + EXT4_ERROR_INODE(dir, + "Directory has corrupted htree index."); + retval = -EFSCORRUPTED; + goto out; + } ext4_clear_inode_flag(dir, EXT4_INODE_INDEX); dx_fallback++; ext4_mark_inode_dirty(handle, dir); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 8434217549b3..f464dff09774 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3009,17 +3009,11 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly) return 0; } -#ifndef CONFIG_QUOTA - if (ext4_has_feature_quota(sb) && !readonly) { +#if !defined(CONFIG_QUOTA) || !defined(CONFIG_QFMT_V2) + if (!readonly && (ext4_has_feature_quota(sb) || + ext4_has_feature_project(sb))) { ext4_msg(sb, KERN_ERR, - "Filesystem with quota feature cannot be mounted RDWR " - "without CONFIG_QUOTA"); - return 0; - } - if (ext4_has_feature_project(sb) && !readonly) { - ext4_msg(sb, KERN_ERR, - "Filesystem with project quota feature cannot be mounted RDWR " - "without CONFIG_QUOTA"); + "The kernel was not built with CONFIG_QUOTA and CONFIG_QFMT_V2"); return 0; } #endif /* CONFIG_QUOTA */ @@ -3814,6 +3808,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) */ sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT; + blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); + if (blocksize < EXT4_MIN_BLOCK_SIZE || + blocksize > EXT4_MAX_BLOCK_SIZE) { + ext4_msg(sb, KERN_ERR, + "Unsupported filesystem blocksize %d (%d log_block_size)", + blocksize, le32_to_cpu(es->s_log_block_size)); + goto failed_mount; + } + if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) { sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE; sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO; @@ -3831,6 +3834,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) ext4_msg(sb, KERN_ERR, "unsupported inode size: %d", sbi->s_inode_size); + ext4_msg(sb, KERN_ERR, "blocksize: %d", blocksize); goto failed_mount; } /* @@ -4033,14 +4037,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (!ext4_feature_set_ok(sb, (sb_rdonly(sb)))) goto failed_mount; - blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); - if (blocksize < EXT4_MIN_BLOCK_SIZE || - blocksize > EXT4_MAX_BLOCK_SIZE) { - ext4_msg(sb, KERN_ERR, - "Unsupported filesystem blocksize %d (%d log_block_size)", - blocksize, le32_to_cpu(es->s_log_block_size)); - goto failed_mount; - } if (le32_to_cpu(es->s_log_block_size) > (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { ext4_msg(sb, KERN_ERR, @@ -5585,10 +5581,7 @@ static int ext4_statfs_project(struct super_block *sb, return PTR_ERR(dquot); spin_lock(&dquot->dq_dqb_lock); - limit = 0; - if (dquot->dq_dqb.dqb_bsoftlimit && - (!limit || dquot->dq_dqb.dqb_bsoftlimit < limit)) - limit = dquot->dq_dqb.dqb_bsoftlimit; + limit = dquot->dq_dqb.dqb_bsoftlimit; if (dquot->dq_dqb.dqb_bhardlimit && (!limit || dquot->dq_dqb.dqb_bhardlimit < limit)) limit = dquot->dq_dqb.dqb_bhardlimit; @@ -5603,10 +5596,7 @@ static int ext4_statfs_project(struct super_block *sb, (buf->f_blocks - curblock) : 0; } - limit = 0; - if (dquot->dq_dqb.dqb_isoftlimit && - (!limit || dquot->dq_dqb.dqb_isoftlimit < limit)) - limit = dquot->dq_dqb.dqb_isoftlimit; + limit = dquot->dq_dqb.dqb_isoftlimit; if (dquot->dq_dqb.dqb_ihardlimit && (!limit || dquot->dq_dqb.dqb_ihardlimit < limit)) limit = dquot->dq_dqb.dqb_ihardlimit; diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 2494095e0340..27373f5792a4 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -976,29 +976,33 @@ restart_loop: * it. */ /* - * A buffer which has been freed while still being journaled by - * a previous transaction. - */ - if (buffer_freed(bh)) { + * A buffer which has been freed while still being journaled + * by a previous transaction, refile the buffer to BJ_Forget of + * the running transaction. If the just committed transaction + * contains "add to orphan" operation, we can completely + * invalidate the buffer now. We are rather through in that + * since the buffer may be still accessible when blocksize < + * pagesize and it is attached to the last partial page. + */ + if (buffer_freed(bh) && !jh->b_next_transaction) { + struct address_space *mapping; + + clear_buffer_freed(bh); + clear_buffer_jbddirty(bh); + /* - * If the running transaction is the one containing - * "add to orphan" operation (b_next_transaction != - * NULL), we have to wait for that transaction to - * commit before we can really get rid of the buffer. - * So just clear b_modified to not confuse transaction - * credit accounting and refile the buffer to - * BJ_Forget of the running transaction. If the just - * committed transaction contains "add to orphan" - * operation, we can completely invalidate the buffer - * now. We are rather through in that since the - * buffer may be still accessible when blocksize < - * pagesize and it is attached to the last partial - * page. + * Block device buffers need to stay mapped all the + * time, so it is enough to clear buffer_jbddirty and + * buffer_freed bits. For the file mapping buffers (i.e. + * journalled data) we need to unmap buffer and clear + * more bits. We also need to be careful about the check + * because the data page mapping can get cleared under + * out hands, which alse need not to clear more bits + * because the page and buffers will be freed and can + * never be reused once we are done with them. */ - jh->b_modified = 0; - if (!jh->b_next_transaction) { - clear_buffer_freed(bh); - clear_buffer_jbddirty(bh); + mapping = READ_ONCE(bh->b_page->mapping); + if (mapping && !sb_is_blkdev_sb(mapping->host->i_sb)) { clear_buffer_mapped(bh); clear_buffer_new(bh); clear_buffer_req(bh); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index e77a5a0b4e46..2dd848a743ed 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -2329,14 +2329,16 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh, return -EBUSY; } /* - * OK, buffer won't be reachable after truncate. We just set - * j_next_transaction to the running transaction (if there is - * one) and mark buffer as freed so that commit code knows it - * should clear dirty bits when it is done with the buffer. + * OK, buffer won't be reachable after truncate. We just clear + * b_modified to not confuse transaction credit accounting, and + * set j_next_transaction to the running transaction (if there + * is one) and mark buffer as freed so that commit code knows + * it should clear dirty bits when it is done with the buffer. */ set_buffer_freed(bh); if (journal->j_running_transaction && buffer_jbddirty(bh)) jh->b_next_transaction = journal->j_running_transaction; + jh->b_modified = 0; spin_unlock(&journal->j_list_lock); spin_unlock(&jh->b_state_lock); write_unlock(&journal->j_state_lock); diff --git a/fs/pipe.c b/fs/pipe.c index 5a34d6c22d4c..2144507447c5 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -722,9 +722,10 @@ pipe_release(struct inode *inode, struct file *file) if (file->f_mode & FMODE_WRITE) pipe->writers--; - if (pipe->readers || pipe->writers) { - wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLHUP); - wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM | EPOLLERR | EPOLLHUP); + /* Was that the last reader or writer, but not the other side? */ + if (!pipe->readers != !pipe->writers) { + wake_up_interruptible_all(&pipe->rd_wait); + wake_up_interruptible_all(&pipe->wr_wait); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } @@ -1026,8 +1027,8 @@ static int wait_for_partner(struct pipe_inode_info *pipe, unsigned int *cnt) static void wake_up_partner(struct pipe_inode_info *pipe) { - wake_up_interruptible(&pipe->rd_wait); - wake_up_interruptible(&pipe->wr_wait); + wake_up_interruptible_all(&pipe->rd_wait); + wake_up_interruptible_all(&pipe->wr_wait); } static int fifo_open(struct inode *inode, struct file *filp) @@ -1144,7 +1145,7 @@ err_rd: err_wr: if (!--pipe->writers) - wake_up_interruptible(&pipe->rd_wait); + wake_up_interruptible_all(&pipe->rd_wait); ret = -ERESTARTSYS; goto err; @@ -1271,8 +1272,9 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) pipe->max_usage = nr_slots; pipe->tail = tail; pipe->head = head; - wake_up_interruptible_all(&pipe->rd_wait); - wake_up_interruptible_all(&pipe->wr_wait); + + /* This might have made more room for writers */ + wake_up_interruptible(&pipe->wr_wait); return pipe->max_usage * PAGE_SIZE; out_revert_acct: diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 5867777bb7d0..8e8be989c2a6 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -753,6 +753,7 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_disable_all_gpes(void)) ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_runtime_gpes(void)) ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_wakeup_gpes(void)) ACPI_HW_DEPENDENT_RETURN_UINT32(u32 acpi_any_gpe_status_set(void)) +ACPI_HW_DEPENDENT_RETURN_UINT32(u32 acpi_any_fixed_event_status_set(void)) ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_get_gpe_device(u32 gpe_index, diff --git a/include/linux/compat.h b/include/linux/compat.h index 11083d84eb23..df2475be134a 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -248,15 +248,6 @@ typedef struct compat_siginfo { } _sifields; } compat_siginfo_t; -/* - * These functions operate on 32- or 64-bit specs depending on - * COMPAT_USE_64BIT_TIME, hence the void user pointer arguments. - */ -extern int compat_get_timespec(struct timespec *, const void __user *); -extern int compat_put_timespec(const struct timespec *, void __user *); -extern int compat_get_timeval(struct timeval *, const void __user *); -extern int compat_put_timeval(const struct timeval *, void __user *); - struct compat_iovec { compat_uptr_t iov_base; compat_size_t iov_len; @@ -416,26 +407,6 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *to, const kernel_siginf int get_compat_sigevent(struct sigevent *event, const struct compat_sigevent __user *u_event); -static inline int old_timeval32_compare(struct old_timeval32 *lhs, - struct old_timeval32 *rhs) -{ - if (lhs->tv_sec < rhs->tv_sec) - return -1; - if (lhs->tv_sec > rhs->tv_sec) - return 1; - return lhs->tv_usec - rhs->tv_usec; -} - -static inline int old_timespec32_compare(struct old_timespec32 *lhs, - struct old_timespec32 *rhs) -{ - if (lhs->tv_sec < rhs->tv_sec) - return -1; - if (lhs->tv_sec > rhs->tv_sec) - return 1; - return lhs->tv_nsec - rhs->tv_nsec; -} - extern int get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat); /* diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index 94f047a8a845..d7c403d0dd27 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -122,7 +122,7 @@ static inline int intel_svm_unbind_mm(struct device *dev, int pasid) BUG(); } -static int intel_svm_is_pasid_valid(struct device *dev, int pasid) +static inline int intel_svm_is_pasid_valid(struct device *dev, int pasid) { return -EINVAL; } diff --git a/include/linux/ktime.h b/include/linux/ktime.h index b2bb44f87f5a..d1fb05135665 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -66,33 +66,15 @@ static inline ktime_t ktime_set(const s64 secs, const unsigned long nsecs) */ #define ktime_sub_ns(kt, nsval) ((kt) - (nsval)) -/* convert a timespec to ktime_t format: */ -static inline ktime_t timespec_to_ktime(struct timespec ts) -{ - return ktime_set(ts.tv_sec, ts.tv_nsec); -} - /* convert a timespec64 to ktime_t format: */ static inline ktime_t timespec64_to_ktime(struct timespec64 ts) { return ktime_set(ts.tv_sec, ts.tv_nsec); } -/* convert a timeval to ktime_t format: */ -static inline ktime_t timeval_to_ktime(struct timeval tv) -{ - return ktime_set(tv.tv_sec, tv.tv_usec * NSEC_PER_USEC); -} - -/* Map the ktime_t to timespec conversion to ns_to_timespec function */ -#define ktime_to_timespec(kt) ns_to_timespec((kt)) - /* Map the ktime_t to timespec conversion to ns_to_timespec function */ #define ktime_to_timespec64(kt) ns_to_timespec64((kt)) -/* Map the ktime_t to timeval conversion to ns_to_timeval function */ -#define ktime_to_timeval(kt) ns_to_timeval((kt)) - /* Convert ktime_t to nanoseconds */ static inline s64 ktime_to_ns(const ktime_t kt) { @@ -216,25 +198,6 @@ static inline ktime_t ktime_sub_ms(const ktime_t kt, const u64 msec) extern ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs); /** - * ktime_to_timespec_cond - convert a ktime_t variable to timespec - * format only if the variable contains data - * @kt: the ktime_t variable to convert - * @ts: the timespec variable to store the result in - * - * Return: %true if there was a successful conversion, %false if kt was 0. - */ -static inline __must_check bool ktime_to_timespec_cond(const ktime_t kt, - struct timespec *ts) -{ - if (kt) { - *ts = ktime_to_timespec(kt); - return true; - } else { - return false; - } -} - -/** * ktime_to_timespec64_cond - convert a ktime_t variable to timespec64 * format only if the variable contains data * @kt: the ktime_t variable to convert diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ff8c9d527bb4..bfdf41537cf1 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -688,7 +688,10 @@ struct mlx5_ifc_flow_table_nic_cap_bits { u8 nic_rx_multi_path_tirs[0x1]; u8 nic_rx_multi_path_tirs_fts[0x1]; u8 allow_sniffer_and_nic_rx_shared_tir[0x1]; - u8 reserved_at_3[0x1d]; + u8 reserved_at_3[0x4]; + u8 sw_owner_reformat_supported[0x1]; + u8 reserved_at_8[0x18]; + u8 encap_general_header[0x1]; u8 reserved_at_21[0xa]; u8 log_max_packet_reformat_context[0x5]; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9f1f633235f6..6c3f7032e8d9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -72,6 +72,8 @@ void netdev_set_default_ethtool_ops(struct net_device *dev, #define NET_RX_SUCCESS 0 /* keep 'em coming, baby */ #define NET_RX_DROP 1 /* packet dropped */ +#define MAX_NEST_DEV 8 + /* * Transmit return codes: transmit return codes originate from three different * namespaces: @@ -4389,11 +4391,8 @@ void *netdev_lower_get_next(struct net_device *dev, ldev; \ ldev = netdev_lower_get_next(dev, &(iter))) -struct net_device *netdev_all_lower_get_next(struct net_device *dev, +struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter); -struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev, - struct list_head **iter); - int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *lower_dev, void *data), diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index e5b752027a03..9670b54b484a 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -145,6 +145,13 @@ static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n, } } +/* after that hlist_nulls_del will work */ +static inline void hlist_nulls_add_fake(struct hlist_nulls_node *n) +{ + n->pprev = &n->next; + n->next = (struct hlist_nulls_node *)NULLS_MARKER(NULL); +} + /** * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ca8806b69388..5b50278c4bc8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -611,9 +611,15 @@ typedef unsigned char *sk_buff_data_t; * @next: Next buffer in list * @prev: Previous buffer in list * @tstamp: Time we arrived/left + * @skb_mstamp_ns: (aka @tstamp) earliest departure time; start point + * for retransmit timer * @rbnode: RB tree node, alternative to next/prev for netem/tcp + * @list: queue head * @sk: Socket we are owned by + * @ip_defrag_offset: (aka @sk) alternate use of @sk, used in + * fragmentation management * @dev: Device we arrived on/are leaving by + * @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL * @cb: Control buffer. Free for use by every layer. Put private vars here * @_skb_refdst: destination entry (with norefcount bit) * @sp: the security path, used for xfrm @@ -632,6 +638,9 @@ typedef unsigned char *sk_buff_data_t; * @pkt_type: Packet class * @fclone: skbuff clone status * @ipvs_property: skbuff is owned by ipvs + * @inner_protocol_type: whether the inner protocol is + * ENCAP_TYPE_ETHER or ENCAP_TYPE_IPPROTO + * @remcsum_offload: remote checksum offload is enabled * @offload_fwd_mark: Packet was L2-forwarded in hardware * @offload_l3_fwd_mark: Packet was L3-forwarded in hardware * @tc_skip_classify: do not classify packet. set by IFB device @@ -650,6 +659,8 @@ typedef unsigned char *sk_buff_data_t; * @tc_index: Traffic control index * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices + * @head_frag: skb was allocated from page fragments, + * not allocated by kmalloc() or vmalloc(). * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves * @active_extensions: active extensions (skb_ext_id types) * @ndisc_nodetype: router type (from link layer) @@ -660,15 +671,28 @@ typedef unsigned char *sk_buff_data_t; * @wifi_acked_valid: wifi_acked was set * @wifi_acked: whether frame was acked on wifi or not * @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS + * @encapsulation: indicates the inner headers in the skbuff are valid + * @encap_hdr_csum: software checksum is needed + * @csum_valid: checksum is already valid * @csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL + * @csum_complete_sw: checksum was completed by software + * @csum_level: indicates the number of consecutive checksums found in + * the packet minus one that have been verified as + * CHECKSUM_UNNECESSARY (max 3) * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @napi_id: id of the NAPI struct this skb came from + * @sender_cpu: (aka @napi_id) source CPU in XPS * @secmark: security marking * @mark: Generic packet mark + * @reserved_tailroom: (aka @mark) number of bytes of free space available + * at the tail of an sk_buff + * @vlan_present: VLAN tag is present * @vlan_proto: vlan encapsulation protocol * @vlan_tci: vlan tag control information * @inner_protocol: Protocol (encapsulation) + * @inner_ipproto: (aka @inner_protocol) stores ipproto when + * skb->inner_protocol_type == ENCAP_TYPE_IPPROTO; * @inner_transport_header: Inner transport layer header (encapsulation) * @inner_network_header: Network layer header (encapsulation) * @inner_mac_header: Link layer header (encapsulation) @@ -750,7 +774,9 @@ struct sk_buff { #endif #define CLONED_OFFSET() offsetof(struct sk_buff, __cloned_offset) + /* private: */ __u8 __cloned_offset[0]; + /* public: */ __u8 cloned:1, nohdr:1, fclone:2, @@ -775,7 +801,9 @@ struct sk_buff { #endif #define PKT_TYPE_OFFSET() offsetof(struct sk_buff, __pkt_type_offset) + /* private: */ __u8 __pkt_type_offset[0]; + /* public: */ __u8 pkt_type:3; __u8 ignore_df:1; __u8 nf_trace:1; @@ -798,7 +826,9 @@ struct sk_buff { #define PKT_VLAN_PRESENT_BIT 0 #endif #define PKT_VLAN_PRESENT_OFFSET() offsetof(struct sk_buff, __pkt_vlan_present_offset) + /* private: */ __u8 __pkt_vlan_present_offset[0]; + /* public: */ __u8 vlan_present:1; __u8 csum_complete_sw:1; __u8 csum_level:2; diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index cde3dc18e21a..046bb94bd4d6 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -64,6 +64,9 @@ extern void swiotlb_tbl_sync_single(struct device *hwdev, size_t size, enum dma_data_direction dir, enum dma_sync_target target); +dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys, + size_t size, enum dma_data_direction dir, unsigned long attrs); + #ifdef CONFIG_SWIOTLB extern enum swiotlb_force swiotlb_force; extern phys_addr_t io_tlb_start, io_tlb_end; @@ -73,8 +76,6 @@ static inline bool is_swiotlb_buffer(phys_addr_t paddr) return paddr >= io_tlb_start && paddr < io_tlb_end; } -bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr, - size_t size, enum dma_data_direction dir, unsigned long attrs); void __init swiotlb_exit(void); unsigned int swiotlb_max_segment(void); size_t swiotlb_max_mapping_size(struct device *dev); @@ -85,12 +86,6 @@ static inline bool is_swiotlb_buffer(phys_addr_t paddr) { return false; } -static inline bool swiotlb_map(struct device *dev, phys_addr_t *phys, - dma_addr_t *dma_addr, size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - return false; -} static inline void swiotlb_exit(void) { } diff --git a/include/linux/time32.h b/include/linux/time32.h index cad4c3186002..cf9320cd2d0b 100644 --- a/include/linux/time32.h +++ b/include/linux/time32.h @@ -12,8 +12,6 @@ #include <linux/time64.h> #include <linux/timex.h> -#define TIME_T_MAX (__kernel_old_time_t)((1UL << ((sizeof(__kernel_old_time_t) << 3) - 1)) - 1) - typedef s32 old_time32_t; struct old_timespec32 { @@ -73,162 +71,12 @@ struct __kernel_timex; int get_old_timex32(struct __kernel_timex *, const struct old_timex32 __user *); int put_old_timex32(struct old_timex32 __user *, const struct __kernel_timex *); -#if __BITS_PER_LONG == 64 - -/* timespec64 is defined as timespec here */ -static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64) -{ - return *(const struct timespec *)&ts64; -} - -static inline struct timespec64 timespec_to_timespec64(const struct timespec ts) -{ - return *(const struct timespec64 *)&ts; -} - -#else -static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64) -{ - struct timespec ret; - - ret.tv_sec = (time_t)ts64.tv_sec; - ret.tv_nsec = ts64.tv_nsec; - return ret; -} - -static inline struct timespec64 timespec_to_timespec64(const struct timespec ts) -{ - struct timespec64 ret; - - ret.tv_sec = ts.tv_sec; - ret.tv_nsec = ts.tv_nsec; - return ret; -} -#endif - -static inline int timespec_equal(const struct timespec *a, - const struct timespec *b) -{ - return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec); -} - -/* - * lhs < rhs: return <0 - * lhs == rhs: return 0 - * lhs > rhs: return >0 - */ -static inline int timespec_compare(const struct timespec *lhs, const struct timespec *rhs) -{ - if (lhs->tv_sec < rhs->tv_sec) - return -1; - if (lhs->tv_sec > rhs->tv_sec) - return 1; - return lhs->tv_nsec - rhs->tv_nsec; -} - -/* - * Returns true if the timespec is norm, false if denorm: - */ -static inline bool timespec_valid(const struct timespec *ts) -{ - /* Dates before 1970 are bogus */ - if (ts->tv_sec < 0) - return false; - /* Can't have more nanoseconds then a second */ - if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) - return false; - return true; -} - -/** - * timespec_to_ns - Convert timespec to nanoseconds - * @ts: pointer to the timespec variable to be converted - * - * Returns the scalar nanosecond representation of the timespec - * parameter. - */ -static inline s64 timespec_to_ns(const struct timespec *ts) -{ - return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; -} - /** - * ns_to_timespec - Convert nanoseconds to timespec - * @nsec: the nanoseconds value to be converted - * - * Returns the timespec representation of the nsec parameter. - */ -extern struct timespec ns_to_timespec(const s64 nsec); - -/** - * timespec_add_ns - Adds nanoseconds to a timespec - * @a: pointer to timespec to be incremented - * @ns: unsigned nanoseconds value to be added - * - * This must always be inlined because its used from the x86-64 vdso, - * which cannot call other kernel functions. - */ -static __always_inline void timespec_add_ns(struct timespec *a, u64 ns) -{ - a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns); - a->tv_nsec = ns; -} - -static inline unsigned long mktime(const unsigned int year, - const unsigned int mon, const unsigned int day, - const unsigned int hour, const unsigned int min, - const unsigned int sec) -{ - return mktime64(year, mon, day, hour, min, sec); -} - -static inline bool timeval_valid(const struct timeval *tv) -{ - /* Dates before 1970 are bogus */ - if (tv->tv_sec < 0) - return false; - - /* Can't have more microseconds then a second */ - if (tv->tv_usec < 0 || tv->tv_usec >= USEC_PER_SEC) - return false; - - return true; -} - -/** - * timeval_to_ns - Convert timeval to nanoseconds - * @ts: pointer to the timeval variable to be converted - * - * Returns the scalar nanosecond representation of the timeval - * parameter. - */ -static inline s64 timeval_to_ns(const struct timeval *tv) -{ - return ((s64) tv->tv_sec * NSEC_PER_SEC) + - tv->tv_usec * NSEC_PER_USEC; -} - -/** - * ns_to_timeval - Convert nanoseconds to timeval + * ns_to_kernel_old_timeval - Convert nanoseconds to timeval * @nsec: the nanoseconds value to be converted * * Returns the timeval representation of the nsec parameter. */ -extern struct timeval ns_to_timeval(const s64 nsec); extern struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec); -/* - * Old names for the 32-bit time_t interfaces, these will be removed - * when everything uses the new names. - */ -#define compat_time_t old_time32_t -#define compat_timeval old_timeval32 -#define compat_timespec old_timespec32 -#define compat_itimerspec old_itimerspec32 -#define ns_to_compat_timeval ns_to_old_timeval32 -#define get_compat_itimerspec64 get_old_itimerspec32 -#define put_compat_itimerspec64 put_old_itimerspec32 -#define compat_get_timespec64 get_old_timespec32 -#define compat_put_timespec64 put_old_timespec32 - #endif diff --git a/include/linux/timekeeping32.h b/include/linux/timekeeping32.h index cc59cc9e0e84..266017fc9ee9 100644 --- a/include/linux/timekeeping32.h +++ b/include/linux/timekeeping32.h @@ -11,36 +11,4 @@ static inline unsigned long get_seconds(void) return ktime_get_real_seconds(); } -static inline void getnstimeofday(struct timespec *ts) -{ - struct timespec64 ts64; - - ktime_get_real_ts64(&ts64); - *ts = timespec64_to_timespec(ts64); -} - -static inline void ktime_get_ts(struct timespec *ts) -{ - struct timespec64 ts64; - - ktime_get_ts64(&ts64); - *ts = timespec64_to_timespec(ts64); -} - -static inline void getrawmonotonic(struct timespec *ts) -{ - struct timespec64 ts64; - - ktime_get_raw_ts64(&ts64); - *ts = timespec64_to_timespec(ts64); -} - -static inline void getboottime(struct timespec *ts) -{ - struct timespec64 ts64; - - getboottime64(&ts64); - *ts = timespec64_to_timespec(ts64); -} - #endif diff --git a/include/linux/tty.h b/include/linux/tty.h index bfa4e2ee94a9..bd5fe0e907e8 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -225,6 +225,8 @@ struct tty_port_client_operations { void (*write_wakeup)(struct tty_port *port); }; +extern const struct tty_port_client_operations tty_port_default_client_ops; + struct tty_port { struct tty_bufhead buf; /* Locked internally */ struct tty_struct *tty; /* Back pointer */ diff --git a/include/linux/types.h b/include/linux/types.h index eb870ad42919..d3021c879179 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -65,11 +65,6 @@ typedef __kernel_ssize_t ssize_t; typedef __kernel_ptrdiff_t ptrdiff_t; #endif -#ifndef _TIME_T -#define _TIME_T -typedef __kernel_old_time_t time_t; -#endif - #ifndef _CLOCK_T #define _CLOCK_T typedef __kernel_clock_t clock_t; diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index a1be64c9940f..22c1f579afe3 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -69,4 +69,7 @@ /* Hub needs extra delay after resetting its port. */ #define USB_QUIRK_HUB_SLOW_RESET BIT(14) +/* device has blacklisted endpoints */ +#define USB_QUIRK_ENDPOINT_BLACKLIST BIT(15) + #endif /* __LINUX_USB_QUIRKS_H */ diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index e9391e877f9a..628383915827 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -5,6 +5,7 @@ #include <linux/types.h> #include <linux/in6.h> #include <linux/siphash.h> +#include <linux/string.h> #include <uapi/linux/if_ether.h> struct sk_buff; @@ -348,4 +349,12 @@ struct bpf_flow_dissector { void *data_end; }; +static inline void +flow_dissector_init_keys(struct flow_dissector_key_control *key_control, + struct flow_dissector_key_basic *key_basic) +{ + memset(key_control, 0, sizeof(*key_control)); + memset(key_basic, 0, sizeof(*key_basic)); +} + #endif diff --git a/include/net/sock.h b/include/net/sock.h index 02162b0378f7..328564525526 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -117,19 +117,26 @@ typedef __u64 __bitwise __addrpair; * struct sock_common - minimal network layer representation of sockets * @skc_daddr: Foreign IPv4 addr * @skc_rcv_saddr: Bound local IPv4 addr + * @skc_addrpair: 8-byte-aligned __u64 union of @skc_daddr & @skc_rcv_saddr * @skc_hash: hash value used with various protocol lookup tables * @skc_u16hashes: two u16 hash values used by UDP lookup tables * @skc_dport: placeholder for inet_dport/tw_dport * @skc_num: placeholder for inet_num/tw_num + * @skc_portpair: __u32 union of @skc_dport & @skc_num * @skc_family: network address family * @skc_state: Connection state * @skc_reuse: %SO_REUSEADDR setting * @skc_reuseport: %SO_REUSEPORT setting + * @skc_ipv6only: socket is IPV6 only + * @skc_net_refcnt: socket is using net ref counting * @skc_bound_dev_if: bound device index if != 0 * @skc_bind_node: bind hash linkage for various protocol lookup tables * @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol * @skc_prot: protocol handlers inside a network family * @skc_net: reference to the network namespace of this socket + * @skc_v6_daddr: IPV6 destination address + * @skc_v6_rcv_saddr: IPV6 source address + * @skc_cookie: socket's cookie value * @skc_node: main hash linkage for various protocol lookup tables * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol * @skc_tx_queue_mapping: tx queue number for this connection @@ -137,7 +144,15 @@ typedef __u64 __bitwise __addrpair; * @skc_flags: place holder for sk_flags * %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings + * @skc_listener: connection request listener socket (aka rsk_listener) + * [union with @skc_flags] + * @skc_tw_dr: (aka tw_dr) ptr to &struct inet_timewait_death_row + * [union with @skc_flags] * @skc_incoming_cpu: record/match cpu processing incoming packets + * @skc_rcv_wnd: (aka rsk_rcv_wnd) TCP receive window size (possibly scaled) + * [union with @skc_incoming_cpu] + * @skc_tw_rcv_nxt: (aka tw_rcv_nxt) TCP window next expected seq number + * [union with @skc_incoming_cpu] * @skc_refcnt: reference count * * This is the minimal network layer representation of sockets, the header @@ -245,6 +260,7 @@ struct bpf_sk_storage; * @sk_dst_cache: destination cache * @sk_dst_pending_confirm: need to confirm neighbour * @sk_policy: flow policy + * @sk_rx_skb_cache: cache copy of recently accessed RX skb * @sk_receive_queue: incoming packets * @sk_wmem_alloc: transmit queue bytes committed * @sk_tsq_flags: TCP Small Queues flags @@ -265,6 +281,8 @@ struct bpf_sk_storage; * @sk_no_check_rx: allow zero checksum in RX packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) * @sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK) + * @sk_route_forced_caps: static, forced route capabilities + * (set in tcp_init_sock()) * @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4) * @sk_gso_max_size: Maximum GSO segment size to build * @sk_gso_max_segs: Maximum number of GSO segments @@ -303,6 +321,8 @@ struct bpf_sk_storage; * @sk_frag: cached page frag * @sk_peek_off: current peek_offset value * @sk_send_head: front of stuff to transmit + * @tcp_rtx_queue: TCP re-transmit queue [union with @sk_send_head] + * @sk_tx_skb_cache: cache copy of recently accessed TX skb * @sk_security: used by security modules * @sk_mark: generic packet mark * @sk_cgrp_data: cgroup data for this cgroup @@ -313,11 +333,14 @@ struct bpf_sk_storage; * @sk_write_space: callback to indicate there is bf sending space available * @sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE) * @sk_backlog_rcv: callback to process the backlog + * @sk_validate_xmit_skb: ptr to an optional validate function * @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0 * @sk_reuseport_cb: reuseport group container + * @sk_bpf_storage: ptr to cache and control for bpf_sk_storage * @sk_rcu: used during RCU grace period * @sk_clockid: clockid used by time-based scheduling (SO_TXTIME) * @sk_txtime_deadline_mode: set deadline mode for SO_TXTIME + * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags */ struct sock { @@ -393,7 +416,9 @@ struct sock { struct sk_filter __rcu *sk_filter; union { struct socket_wq __rcu *sk_wq; + /* private: */ struct socket_wq *sk_wq_raw; + /* public: */ }; #ifdef CONFIG_XFRM struct xfrm_policy __rcu *sk_policy[2]; @@ -2017,7 +2042,7 @@ static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *fro * sk_wmem_alloc_get - returns write allocations * @sk: socket * - * Returns sk_wmem_alloc minus initial offset of one + * Return: sk_wmem_alloc minus initial offset of one */ static inline int sk_wmem_alloc_get(const struct sock *sk) { @@ -2028,7 +2053,7 @@ static inline int sk_wmem_alloc_get(const struct sock *sk) * sk_rmem_alloc_get - returns read allocations * @sk: socket * - * Returns sk_rmem_alloc + * Return: sk_rmem_alloc */ static inline int sk_rmem_alloc_get(const struct sock *sk) { @@ -2039,7 +2064,7 @@ static inline int sk_rmem_alloc_get(const struct sock *sk) * sk_has_allocations - check if allocations are outstanding * @sk: socket * - * Returns true if socket has write or read allocations + * Return: true if socket has write or read allocations */ static inline bool sk_has_allocations(const struct sock *sk) { @@ -2050,7 +2075,7 @@ static inline bool sk_has_allocations(const struct sock *sk) * skwq_has_sleeper - check if there are any waiting processes * @wq: struct socket_wq * - * Returns true if socket_wq has waiting processes + * Return: true if socket_wq has waiting processes * * The purpose of the skwq_has_sleeper and sock_poll_wait is to wrap the memory * barrier call. They were added due to the race found within the tcp code. @@ -2238,6 +2263,9 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, * gfpflags_allow_blocking() isn't enough here as direct reclaim may nest * inside other socket operations and end up recursing into sk_page_frag() * while it's already in use. + * + * Return: a per task page_frag if context allows that, + * otherwise a per socket one. */ static inline struct page_frag *sk_page_frag(struct sock *sk) { @@ -2432,6 +2460,7 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) &skb_shinfo(skb)->tskey); } +DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key); /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from @@ -2440,7 +2469,6 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) * This routine must be called with interrupts disabled or with the socket * locked so that the sk_buff queue operation is ok. */ -DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key); static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb) { __skb_unlink(skb, &sk->sk_receive_queue); diff --git a/include/scsi/iscsi_proto.h b/include/scsi/iscsi_proto.h index 533f56733ba8..b71b5c4f418c 100644 --- a/include/scsi/iscsi_proto.h +++ b/include/scsi/iscsi_proto.h @@ -627,7 +627,6 @@ struct iscsi_reject { #define ISCSI_REASON_BOOKMARK_INVALID 9 #define ISCSI_REASON_BOOKMARK_NO_RESOURCES 10 #define ISCSI_REASON_NEGOTIATION_RESET 11 -#define ISCSI_REASON_WAITING_FOR_LOGOUT 12 /* Max. number of Key=Value pairs in a text message */ #define MAX_KEY_VALUE_PAIRS 8192 diff --git a/include/sound/rawmidi.h b/include/sound/rawmidi.h index 40ab20439fee..a36b7227a15a 100644 --- a/include/sound/rawmidi.h +++ b/include/sound/rawmidi.h @@ -77,9 +77,9 @@ struct snd_rawmidi_substream { struct list_head list; /* list of all substream for given stream */ int stream; /* direction */ int number; /* substream number */ - unsigned int opened: 1, /* open flag */ - append: 1, /* append flag (merge more streams) */ - active_sensing: 1; /* send active sensing when close */ + bool opened; /* open flag */ + bool append; /* append flag (merge more streams) */ + bool active_sensing; /* send active sensing when close */ int use_count; /* use counter (for output) */ size_t bytes; struct snd_rawmidi *rmidi; diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h index 2a306c6f3fbc..1b6afbc1a4ed 100644 --- a/include/sound/soc-dapm.h +++ b/include/sound/soc-dapm.h @@ -392,8 +392,6 @@ int snd_soc_dapm_get_enum_double(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol); int snd_soc_dapm_put_enum_double(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol); -int snd_soc_dapm_put_enum_double_locked(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol); int snd_soc_dapm_info_pin_switch(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo); int snd_soc_dapm_get_pin_switch(struct snd_kcontrol *kcontrol, diff --git a/include/uapi/asm-generic/posix_types.h b/include/uapi/asm-generic/posix_types.h index 2f9c80595ba7..b5f7594eee7a 100644 --- a/include/uapi/asm-generic/posix_types.h +++ b/include/uapi/asm-generic/posix_types.h @@ -87,7 +87,9 @@ typedef struct { typedef __kernel_long_t __kernel_off_t; typedef long long __kernel_loff_t; typedef __kernel_long_t __kernel_old_time_t; +#ifndef __KERNEL__ typedef __kernel_long_t __kernel_time_t; +#endif typedef long long __kernel_time64_t; typedef __kernel_long_t __kernel_clock_t; typedef int __kernel_timer_t; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f1d74a2bd234..22f235260a3a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1045,9 +1045,9 @@ union bpf_attr { * supports redirection to the egress interface, and accepts no * flag at all. * - * The same effect can be attained with the more generic - * **bpf_redirect_map**\ (), which requires specific maps to be - * used but offers better performance. + * The same effect can also be attained with the more generic + * **bpf_redirect_map**\ (), which uses a BPF map to store the + * redirect target instead of providing it directly to the helper. * Return * For XDP, the helper returns **XDP_REDIRECT** on success or * **XDP_ABORTED** on error. For other program types, the values @@ -1611,13 +1611,11 @@ union bpf_attr { * the caller. Any higher bits in the *flags* argument must be * unset. * - * When used to redirect packets to net devices, this helper - * provides a high performance increase over **bpf_redirect**\ (). - * This is due to various implementation details of the underlying - * mechanisms, one of which is the fact that **bpf_redirect_map**\ - * () tries to send packet as a "bulk" to the device. + * See also bpf_redirect(), which only supports redirecting to an + * ifindex, but doesn't require a map to do so. * Return - * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error. + * **XDP_REDIRECT** on success, or the value of the two lower bits + * of the **flags* argument on error. * * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags) * Description diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h index 336014bf8868..b6f0bb1dc799 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_common.h +++ b/include/uapi/linux/netfilter/nf_conntrack_common.h @@ -97,6 +97,15 @@ enum ip_conntrack_status { IPS_UNTRACKED_BIT = 12, IPS_UNTRACKED = (1 << IPS_UNTRACKED_BIT), +#ifdef __KERNEL__ + /* Re-purposed for in-kernel use: + * Tags a conntrack entry that clashed with an existing entry + * on insert. + */ + IPS_NAT_CLASH_BIT = IPS_UNTRACKED_BIT, + IPS_NAT_CLASH = IPS_UNTRACKED, +#endif + /* Conntrack got a helper explicitly attached via CT target. */ IPS_HELPER_BIT = 13, IPS_HELPER = (1 << IPS_HELPER_BIT), @@ -110,7 +119,8 @@ enum ip_conntrack_status { */ IPS_UNCHANGEABLE_MASK = (IPS_NAT_DONE_MASK | IPS_NAT_MASK | IPS_EXPECTED | IPS_CONFIRMED | IPS_DYING | - IPS_SEQ_ADJUST | IPS_TEMPLATE | IPS_OFFLOAD), + IPS_SEQ_ADJUST | IPS_TEMPLATE | IPS_UNTRACKED | + IPS_OFFLOAD), __IPS_MAX_BIT = 15, }; diff --git a/include/uapi/linux/swab.h b/include/uapi/linux/swab.h index fa7f97da5b76..7272f85d6d6a 100644 --- a/include/uapi/linux/swab.h +++ b/include/uapi/linux/swab.h @@ -135,9 +135,9 @@ static inline __attribute_const__ __u32 __fswahb32(__u32 val) static __always_inline unsigned long __swab(const unsigned long y) { -#if BITS_PER_LONG == 64 +#if __BITS_PER_LONG == 64 return __swab64(y); -#else /* BITS_PER_LONG == 32 */ +#else /* __BITS_PER_LONG == 32 */ return __swab32(y); #endif } diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h index a655aa28dc6e..4f4b6e48e01c 100644 --- a/include/uapi/linux/time.h +++ b/include/uapi/linux/time.h @@ -5,6 +5,7 @@ #include <linux/types.h> #include <linux/time_types.h> +#ifndef __KERNEL__ #ifndef _STRUCT_TIMESPEC #define _STRUCT_TIMESPEC struct timespec { @@ -18,6 +19,17 @@ struct timeval { __kernel_suseconds_t tv_usec; /* microseconds */ }; +struct itimerspec { + struct timespec it_interval;/* timer period */ + struct timespec it_value; /* timer expiration */ +}; + +struct itimerval { + struct timeval it_interval;/* timer interval */ + struct timeval it_value; /* current value */ +}; +#endif + struct timezone { int tz_minuteswest; /* minutes west of Greenwich */ int tz_dsttime; /* type of dst correction */ @@ -31,16 +43,6 @@ struct timezone { #define ITIMER_VIRTUAL 1 #define ITIMER_PROF 2 -struct itimerspec { - struct timespec it_interval; /* timer period */ - struct timespec it_value; /* timer expiration */ -}; - -struct itimerval { - struct timeval it_interval; /* timer interval */ - struct timeval it_value; /* current value */ -}; - /* * The IDs of the various system clocks (for POSIX.1b interval timers): */ diff --git a/include/uapi/linux/usb/charger.h b/include/uapi/linux/usb/charger.h index 5f72af35b3ed..ad22079125bf 100644 --- a/include/uapi/linux/usb/charger.h +++ b/include/uapi/linux/usb/charger.h @@ -14,18 +14,18 @@ * ACA (Accessory Charger Adapters) */ enum usb_charger_type { - UNKNOWN_TYPE, - SDP_TYPE, - DCP_TYPE, - CDP_TYPE, - ACA_TYPE, + UNKNOWN_TYPE = 0, + SDP_TYPE = 1, + DCP_TYPE = 2, + CDP_TYPE = 3, + ACA_TYPE = 4, }; /* USB charger state */ enum usb_charger_state { - USB_CHARGER_DEFAULT, - USB_CHARGER_PRESENT, - USB_CHARGER_ABSENT, + USB_CHARGER_DEFAULT = 0, + USB_CHARGER_PRESENT = 1, + USB_CHARGER_ABSENT = 2, }; #endif /* _UAPI__LINUX_USB_CHARGER_H */ diff --git a/ipc/sem.c b/ipc/sem.c index 4f4303f32077..3687b71151b3 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -2384,11 +2384,9 @@ void exit_sem(struct task_struct *tsk) ipc_assert_locked_object(&sma->sem_perm); list_del(&un->list_id); - /* we are the last process using this ulp, acquiring ulp->lock - * isn't required. Besides that, we are also protected against - * IPC_RMID as we hold sma->sem_perm lock now - */ + spin_lock(&ulp->lock); list_del_rcu(&un->list_proc); + spin_unlock(&ulp->lock); /* perform adjustments registered in un */ for (i = 0; i < sma->sem_nsems; i++) { diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 805c43b083e9..787140095e58 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -4142,9 +4142,9 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, * EFAULT - verifier bug * 0 - 99% match. The last 1% is validated by the verifier. */ -int btf_check_func_type_match(struct bpf_verifier_log *log, - struct btf *btf1, const struct btf_type *t1, - struct btf *btf2, const struct btf_type *t2) +static int btf_check_func_type_match(struct bpf_verifier_log *log, + struct btf *btf1, const struct btf_type *t1, + struct btf *btf2, const struct btf_type *t2) { const struct btf_param *args1, *args2; const char *fn1, *fn2, *s1, *s2; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 2d182c4ee9d9..a1468e3f5af2 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -56,6 +56,7 @@ struct htab_elem { union { struct bpf_htab *htab; struct pcpu_freelist_node fnode; + struct htab_elem *batch_flink; }; }; }; @@ -126,6 +127,17 @@ free_elems: bpf_map_area_free(htab->elems); } +/* The LRU list has a lock (lru_lock). Each htab bucket has a lock + * (bucket_lock). If both locks need to be acquired together, the lock + * order is always lru_lock -> bucket_lock and this only happens in + * bpf_lru_list.c logic. For example, certain code path of + * bpf_lru_pop_free(), which is called by function prealloc_lru_pop(), + * will acquire lru_lock first followed by acquiring bucket_lock. + * + * In hashtab.c, to avoid deadlock, lock acquisition of + * bucket_lock followed by lru_lock is not allowed. In such cases, + * bucket_lock needs to be released first before acquiring lru_lock. + */ static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key, u32 hash) { @@ -1256,10 +1268,12 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map, void __user *ukeys = u64_to_user_ptr(attr->batch.keys); void *ubatch = u64_to_user_ptr(attr->batch.in_batch); u32 batch, max_count, size, bucket_size; + struct htab_elem *node_to_free = NULL; u64 elem_map_flags, map_flags; struct hlist_nulls_head *head; struct hlist_nulls_node *n; - unsigned long flags; + unsigned long flags = 0; + bool locked = false; struct htab_elem *l; struct bucket *b; int ret = 0; @@ -1319,15 +1333,25 @@ again_nocopy: dst_val = values; b = &htab->buckets[batch]; head = &b->head; - raw_spin_lock_irqsave(&b->lock, flags); + /* do not grab the lock unless need it (bucket_cnt > 0). */ + if (locked) + raw_spin_lock_irqsave(&b->lock, flags); bucket_cnt = 0; hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) bucket_cnt++; + if (bucket_cnt && !locked) { + locked = true; + goto again_nocopy; + } + if (bucket_cnt > (max_count - total)) { if (total == 0) ret = -ENOSPC; + /* Note that since bucket_cnt > 0 here, it is implicit + * that the locked was grabbed, so release it. + */ raw_spin_unlock_irqrestore(&b->lock, flags); rcu_read_unlock(); this_cpu_dec(bpf_prog_active); @@ -1337,6 +1361,9 @@ again_nocopy: if (bucket_cnt > bucket_size) { bucket_size = bucket_cnt; + /* Note that since bucket_cnt > 0 here, it is implicit + * that the locked was grabbed, so release it. + */ raw_spin_unlock_irqrestore(&b->lock, flags); rcu_read_unlock(); this_cpu_dec(bpf_prog_active); @@ -1346,6 +1373,10 @@ again_nocopy: goto alloc; } + /* Next block is only safe to run if you have grabbed the lock */ + if (!locked) + goto next_batch; + hlist_nulls_for_each_entry_safe(l, n, head, hash_node) { memcpy(dst_key, l->key, key_size); @@ -1370,16 +1401,33 @@ again_nocopy: } if (do_delete) { hlist_nulls_del_rcu(&l->hash_node); - if (is_lru_map) - bpf_lru_push_free(&htab->lru, &l->lru_node); - else + + /* bpf_lru_push_free() will acquire lru_lock, which + * may cause deadlock. See comments in function + * prealloc_lru_pop(). Let us do bpf_lru_push_free() + * after releasing the bucket lock. + */ + if (is_lru_map) { + l->batch_flink = node_to_free; + node_to_free = l; + } else { free_htab_elem(htab, l); + } } dst_key += key_size; dst_val += value_size; } raw_spin_unlock_irqrestore(&b->lock, flags); + locked = false; + + while (node_to_free) { + l = node_to_free; + node_to_free = node_to_free->batch_flink; + bpf_lru_push_free(&htab->lru, &l->lru_node); + } + +next_batch: /* If we are not copying data, we can go to next bucket and avoid * unlocking the rcu. */ diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 2c5dc6541ece..bd09290e3648 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -321,7 +321,7 @@ int bpf_prog_offload_info_fill(struct bpf_prog_info *info, ulen = info->jited_prog_len; info->jited_prog_len = aux->offload->jited_len; - if (info->jited_prog_len & ulen) { + if (info->jited_prog_len && ulen) { uinsns = u64_to_user_ptr(info->jited_prog_insns); ulen = min_t(u32, info->jited_prog_len, ulen); if (copy_to_user(uinsns, aux->offload->jited_image, ulen)) { diff --git a/kernel/compat.c b/kernel/compat.c index 95005f849c68..843dd17e6078 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -26,70 +26,6 @@ #include <linux/uaccess.h> -static int __compat_get_timeval(struct timeval *tv, const struct old_timeval32 __user *ctv) -{ - return (!access_ok(ctv, sizeof(*ctv)) || - __get_user(tv->tv_sec, &ctv->tv_sec) || - __get_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0; -} - -static int __compat_put_timeval(const struct timeval *tv, struct old_timeval32 __user *ctv) -{ - return (!access_ok(ctv, sizeof(*ctv)) || - __put_user(tv->tv_sec, &ctv->tv_sec) || - __put_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0; -} - -static int __compat_get_timespec(struct timespec *ts, const struct old_timespec32 __user *cts) -{ - return (!access_ok(cts, sizeof(*cts)) || - __get_user(ts->tv_sec, &cts->tv_sec) || - __get_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0; -} - -static int __compat_put_timespec(const struct timespec *ts, struct old_timespec32 __user *cts) -{ - return (!access_ok(cts, sizeof(*cts)) || - __put_user(ts->tv_sec, &cts->tv_sec) || - __put_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0; -} - -int compat_get_timeval(struct timeval *tv, const void __user *utv) -{ - if (COMPAT_USE_64BIT_TIME) - return copy_from_user(tv, utv, sizeof(*tv)) ? -EFAULT : 0; - else - return __compat_get_timeval(tv, utv); -} -EXPORT_SYMBOL_GPL(compat_get_timeval); - -int compat_put_timeval(const struct timeval *tv, void __user *utv) -{ - if (COMPAT_USE_64BIT_TIME) - return copy_to_user(utv, tv, sizeof(*tv)) ? -EFAULT : 0; - else - return __compat_put_timeval(tv, utv); -} -EXPORT_SYMBOL_GPL(compat_put_timeval); - -int compat_get_timespec(struct timespec *ts, const void __user *uts) -{ - if (COMPAT_USE_64BIT_TIME) - return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0; - else - return __compat_get_timespec(ts, uts); -} -EXPORT_SYMBOL_GPL(compat_get_timespec); - -int compat_put_timespec(const struct timespec *ts, void __user *uts) -{ - if (COMPAT_USE_64BIT_TIME) - return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0; - else - return __compat_put_timespec(ts, uts); -} -EXPORT_SYMBOL_GPL(compat_put_timespec); - #ifdef __ARCH_WANT_SYS_SIGPROCMASK /* diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c index daa4e6eefdde..8bc6f2d670f9 100644 --- a/kernel/dma/contiguous.c +++ b/kernel/dma/contiguous.c @@ -302,9 +302,16 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem) phys_addr_t align = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order); phys_addr_t mask = align - 1; unsigned long node = rmem->fdt_node; + bool default_cma = of_get_flat_dt_prop(node, "linux,cma-default", NULL); struct cma *cma; int err; + if (size_cmdline != -1 && default_cma) { + pr_info("Reserved memory: bypass %s node, using cmdline CMA params instead\n", + rmem->name); + return -EBUSY; + } + if (!of_get_flat_dt_prop(node, "reusable", NULL) || of_get_flat_dt_prop(node, "no-map", NULL)) return -EINVAL; @@ -322,7 +329,7 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem) /* Architecture specific contiguous memory fixup. */ dma_contiguous_early_fixup(rmem->base, rmem->size); - if (of_get_flat_dt_prop(node, "linux,cma-default", NULL)) + if (default_cma) dma_contiguous_set_default(cma); rmem->ops = &rmem_cma_ops; diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 6af7ae83c4ad..ac7956c38f69 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -23,18 +23,6 @@ */ unsigned int zone_dma_bits __ro_after_init = 24; -static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size) -{ - if (!dev->dma_mask) { - dev_err_once(dev, "DMA map on device without dma_mask\n"); - } else if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_limit) { - dev_err_once(dev, - "overflow %pad+%zu of DMA mask %llx bus limit %llx\n", - &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); - } - WARN_ON_ONCE(1); -} - static inline dma_addr_t phys_to_dma_direct(struct device *dev, phys_addr_t phys) { @@ -357,13 +345,6 @@ void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, EXPORT_SYMBOL(dma_direct_unmap_sg); #endif -static inline bool dma_direct_possible(struct device *dev, dma_addr_t dma_addr, - size_t size) -{ - return swiotlb_force != SWIOTLB_FORCE && - dma_capable(dev, dma_addr, size, true); -} - dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, unsigned long attrs) @@ -371,9 +352,16 @@ dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, phys_addr_t phys = page_to_phys(page) + offset; dma_addr_t dma_addr = phys_to_dma(dev, phys); - if (unlikely(!dma_direct_possible(dev, dma_addr, size)) && - !swiotlb_map(dev, &phys, &dma_addr, size, dir, attrs)) { - report_addr(dev, dma_addr, size); + if (unlikely(swiotlb_force == SWIOTLB_FORCE)) + return swiotlb_map(dev, phys, size, dir, attrs); + + if (unlikely(!dma_capable(dev, dma_addr, size, true))) { + if (swiotlb_force != SWIOTLB_NO_FORCE) + return swiotlb_map(dev, phys, size, dir, attrs); + + dev_WARN_ONCE(dev, 1, + "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n", + &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); return DMA_MAPPING_ERROR; } @@ -411,7 +399,10 @@ dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr, dma_addr_t dma_addr = paddr; if (unlikely(!dma_capable(dev, dma_addr, size, false))) { - report_addr(dev, dma_addr, size); + dev_err_once(dev, + "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n", + &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); + WARN_ON_ONCE(1); return DMA_MAPPING_ERROR; } @@ -472,28 +463,26 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma, } #endif /* CONFIG_MMU */ -/* - * Because 32-bit DMA masks are so common we expect every architecture to be - * able to satisfy them - either by not supporting more physical memory, or by - * providing a ZONE_DMA32. If neither is the case, the architecture needs to - * use an IOMMU instead of the direct mapping. - */ int dma_direct_supported(struct device *dev, u64 mask) { - u64 min_mask; + u64 min_mask = (max_pfn - 1) << PAGE_SHIFT; - if (IS_ENABLED(CONFIG_ZONE_DMA)) - min_mask = DMA_BIT_MASK(zone_dma_bits); - else - min_mask = DMA_BIT_MASK(32); - - min_mask = min_t(u64, min_mask, (max_pfn - 1) << PAGE_SHIFT); + /* + * Because 32-bit DMA masks are so common we expect every architecture + * to be able to satisfy them - either by not supporting more physical + * memory, or by providing a ZONE_DMA32. If neither is the case, the + * architecture needs to use an IOMMU instead of the direct mapping. + */ + if (mask >= DMA_BIT_MASK(32)) + return 1; /* * This check needs to be against the actual bit mask value, so * use __phys_to_dma() here so that the SME encryption mask isn't * part of the check. */ + if (IS_ENABLED(CONFIG_ZONE_DMA)) + min_mask = min_t(u64, min_mask, DMA_BIT_MASK(zone_dma_bits)); return mask >= __phys_to_dma(dev, min_mask); } diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 9280d6f8271e..c19379fabd20 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -22,6 +22,7 @@ #include <linux/cache.h> #include <linux/dma-direct.h> +#include <linux/dma-noncoherent.h> #include <linux/mm.h> #include <linux/export.h> #include <linux/spinlock.h> @@ -656,35 +657,38 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, } /* - * Create a swiotlb mapping for the buffer at @phys, and in case of DMAing + * Create a swiotlb mapping for the buffer at @paddr, and in case of DMAing * to the device copy the data into it as well. */ -bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr, - size_t size, enum dma_data_direction dir, unsigned long attrs) +dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size, + enum dma_data_direction dir, unsigned long attrs) { - trace_swiotlb_bounced(dev, *dma_addr, size, swiotlb_force); + phys_addr_t swiotlb_addr; + dma_addr_t dma_addr; - if (unlikely(swiotlb_force == SWIOTLB_NO_FORCE)) { - dev_warn_ratelimited(dev, - "Cannot do DMA to address %pa\n", phys); - return false; - } + trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size, + swiotlb_force); - /* Oh well, have to allocate and map a bounce buffer. */ - *phys = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start), - *phys, size, size, dir, attrs); - if (*phys == (phys_addr_t)DMA_MAPPING_ERROR) - return false; + swiotlb_addr = swiotlb_tbl_map_single(dev, + __phys_to_dma(dev, io_tlb_start), + paddr, size, size, dir, attrs); + if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR) + return DMA_MAPPING_ERROR; /* Ensure that the address returned is DMA'ble */ - *dma_addr = __phys_to_dma(dev, *phys); - if (unlikely(!dma_capable(dev, *dma_addr, size, true))) { - swiotlb_tbl_unmap_single(dev, *phys, size, size, dir, + dma_addr = __phys_to_dma(dev, swiotlb_addr); + if (unlikely(!dma_capable(dev, dma_addr, size, true))) { + swiotlb_tbl_unmap_single(dev, swiotlb_addr, size, size, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC); - return false; + dev_WARN_ONCE(dev, 1, + "swiotlb addr %pad+%zu overflow (mask %llx, bus limit %llx).\n", + &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); + return DMA_MAPPING_ERROR; } - return true; + if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + arch_sync_dma_for_device(swiotlb_addr, size, dir); + return dma_addr; } size_t swiotlb_max_mapping_size(struct device *dev) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index d396aaaf19a3..ad5b88a53c5a 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -805,15 +805,6 @@ static struct ctl_table kern_table[] = { .extra2 = &maxolduid, }, #ifdef CONFIG_S390 -#ifdef CONFIG_MATHEMU - { - .procname = "ieee_emulation_warnings", - .data = &sysctl_ieee_emulation_warnings, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif { .procname = "userprocess_debug", .data = &show_unhandled_signals, diff --git a/kernel/time/time.c b/kernel/time/time.c index cdd7386115ff..3985b2b32d08 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -449,49 +449,6 @@ time64_t mktime64(const unsigned int year0, const unsigned int mon0, } EXPORT_SYMBOL(mktime64); -/** - * ns_to_timespec - Convert nanoseconds to timespec - * @nsec: the nanoseconds value to be converted - * - * Returns the timespec representation of the nsec parameter. - */ -struct timespec ns_to_timespec(const s64 nsec) -{ - struct timespec ts; - s32 rem; - - if (!nsec) - return (struct timespec) {0, 0}; - - ts.tv_sec = div_s64_rem(nsec, NSEC_PER_SEC, &rem); - if (unlikely(rem < 0)) { - ts.tv_sec--; - rem += NSEC_PER_SEC; - } - ts.tv_nsec = rem; - - return ts; -} -EXPORT_SYMBOL(ns_to_timespec); - -/** - * ns_to_timeval - Convert nanoseconds to timeval - * @nsec: the nanoseconds value to be converted - * - * Returns the timeval representation of the nsec parameter. - */ -struct timeval ns_to_timeval(const s64 nsec) -{ - struct timespec ts = ns_to_timespec(nsec); - struct timeval tv; - - tv.tv_sec = ts.tv_sec; - tv.tv_usec = (suseconds_t) ts.tv_nsec / 1000; - - return tv; -} -EXPORT_SYMBOL(ns_to_timeval); - struct __kernel_old_timeval ns_to_kernel_old_timeval(const s64 nsec) { struct timespec64 ts = ns_to_timespec64(nsec); diff --git a/lib/stackdepot.c b/lib/stackdepot.c index ed717dd08ff3..81c69c08d1d1 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -83,15 +83,19 @@ static bool init_stack_slab(void **prealloc) return true; if (stack_slabs[depot_index] == NULL) { stack_slabs[depot_index] = *prealloc; + *prealloc = NULL; } else { - stack_slabs[depot_index + 1] = *prealloc; + /* If this is the last depot slab, do not touch the next one. */ + if (depot_index + 1 < STACK_ALLOC_MAX_SLABS) { + stack_slabs[depot_index + 1] = *prealloc; + *prealloc = NULL; + } /* * This smp_store_release pairs with smp_load_acquire() from * |next_slab_inited| above and in stack_depot_save(). */ smp_store_release(&next_slab_inited, 1); } - *prealloc = NULL; return true; } diff --git a/lib/string.c b/lib/string.c index f607b967d978..6012c385fb31 100644 --- a/lib/string.c +++ b/lib/string.c @@ -699,6 +699,14 @@ EXPORT_SYMBOL(sysfs_streq); * @n: number of strings in the array or -1 for NULL terminated arrays * @string: string to match with * + * This routine will look for a string in an array of strings up to the + * n-th element in the array or until the first NULL element. + * + * Historically the value of -1 for @n, was used to search in arrays that + * are NULL terminated. However, the function does not make a distinction + * when finishing the search: either @n elements have been compared OR + * the first NULL element was found. + * * Return: * index of a @string in the @array if matches, or %-EINVAL otherwise. */ @@ -727,6 +735,14 @@ EXPORT_SYMBOL(match_string); * * Returns index of @str in the @array or -EINVAL, just like match_string(). * Uses sysfs_streq instead of strcmp for matching. + * + * This routine will look for a string in an array of strings up to the + * n-th element in the array or until the first NULL element. + * + * Historically the value of -1 for @n, was used to search in arrays that + * are NULL terminated. However, the function does not make a distinction + * when finishing the search: either @n elements have been compared OR + * the first NULL element was found. */ int __sysfs_match_string(const char * const *array, size_t n, const char *str) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6f6dc8712e39..d09776cd6e10 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -409,8 +409,10 @@ int memcg_expand_shrinker_maps(int new_id) if (mem_cgroup_is_root(memcg)) continue; ret = memcg_expand_one_shrinker_map(memcg, size, old_size); - if (ret) + if (ret) { + mem_cgroup_iter_break(NULL, memcg); goto unlock; + } } unlock: if (!ret) diff --git a/mm/mmap.c b/mm/mmap.c index 6756b8bb0033..d681a20eb4ea 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -195,8 +195,6 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) bool downgraded = false; LIST_HEAD(uf); - brk = untagged_addr(brk); - if (down_write_killable(&mm->mmap_sem)) return -EINTR; @@ -1557,8 +1555,6 @@ unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, struct file *file = NULL; unsigned long retval; - addr = untagged_addr(addr); - if (!(flags & MAP_ANONYMOUS)) { audit_mmap_fd(fd, flags); file = fget(fd); diff --git a/mm/mremap.c b/mm/mremap.c index 122938dcec15..af363063ea23 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -607,7 +607,6 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, LIST_HEAD(uf_unmap); addr = untagged_addr(addr); - new_addr = untagged_addr(new_addr); if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE)) return ret; diff --git a/mm/sparse.c b/mm/sparse.c index c184b69460b7..596b2a45b100 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -876,7 +876,7 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn, * Poison uninitialized struct pages in order to catch invalid flags * combinations. */ - page_init_poison(pfn_to_page(start_pfn), sizeof(struct page) * nr_pages); + page_init_poison(memmap, sizeof(struct page) * nr_pages); ms = __nr_to_section(section_nr); set_section_nid(section_nr, nid); diff --git a/mm/swapfile.c b/mm/swapfile.c index 2c33ff456ed5..b2a2e45c9a36 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3157,7 +3157,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) mapping = swap_file->f_mapping; inode = mapping->host; - /* If S_ISREG(inode->i_mode) will do inode_lock(inode); */ + /* will take i_rwsem; */ error = claim_swapfile(p, inode); if (unlikely(error)) goto bad_swap; diff --git a/mm/vmscan.c b/mm/vmscan.c index c05eb9efec07..876370565455 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2415,10 +2415,13 @@ out: /* * Scan types proportional to swappiness and * their relative recent reclaim efficiency. - * Make sure we don't miss the last page - * because of a round-off error. + * Make sure we don't miss the last page on + * the offlined memory cgroups because of a + * round-off error. */ - scan = DIV64_U64_ROUND_UP(scan * fraction[file], + scan = mem_cgroup_online(memcg) ? + div64_u64(scan * fraction[file], denominator) : + DIV64_U64_ROUND_UP(scan * fraction[file], denominator); break; case SCAN_FILE: diff --git a/net/Kconfig b/net/Kconfig index b0937a700f01..2eeb0e55f7c9 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -189,7 +189,6 @@ config BRIDGE_NETFILTER depends on NETFILTER_ADVANCED select NETFILTER_FAMILY_BRIDGE select SKB_EXTENSIONS - default m ---help--- Enabling this option will let arptables resp. iptables see bridged ARP resp. IP traffic. If you want a bridging firewall, you probably diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 6856a6d9282b..1f14b8455345 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -63,7 +63,8 @@ struct net_bridge_port *br_get_port(struct net_bridge *br, u16 port_no) { struct net_bridge_port *p; - list_for_each_entry_rcu(p, &br->port_list, list) { + list_for_each_entry_rcu(p, &br->port_list, list, + lockdep_is_held(&br->lock)) { if (p->port_no == port_no) return p; } diff --git a/net/core/dev.c b/net/core/dev.c index a6316b336128..e10bd680dc03 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -146,7 +146,6 @@ #include "net-sysfs.h" #define MAX_GRO_SKBS 8 -#define MAX_NEST_DEV 8 /* This should be increased if a protocol with a bigger head is added. */ #define GRO_MAX_HEAD (MAX_HEADER + 128) @@ -331,6 +330,12 @@ int netdev_name_node_alt_destroy(struct net_device *dev, const char *name) name_node = netdev_name_node_lookup(net, name); if (!name_node) return -ENOENT; + /* lookup might have found our primary name or a name belonging + * to another device. + */ + if (name_node == dev->name_node || name_node->dev != dev) + return -EINVAL; + __netdev_name_node_alt_destroy(name_node); return 0; @@ -3657,26 +3662,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, qdisc_calculate_pkt_len(skb, q); if (q->flags & TCQ_F_NOLOCK) { - if ((q->flags & TCQ_F_CAN_BYPASS) && READ_ONCE(q->empty) && - qdisc_run_begin(q)) { - if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, - &q->state))) { - __qdisc_drop(skb, &to_free); - rc = NET_XMIT_DROP; - goto end_run; - } - qdisc_bstats_cpu_update(q, skb); - - rc = NET_XMIT_SUCCESS; - if (sch_direct_xmit(skb, q, dev, txq, NULL, true)) - __qdisc_run(q); - -end_run: - qdisc_run_end(q); - } else { - rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; - qdisc_run(q); - } + rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; + qdisc_run(q); if (unlikely(to_free)) kfree_skb_list(to_free); @@ -7201,8 +7188,8 @@ static int __netdev_walk_all_lower_dev(struct net_device *dev, return 0; } -static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, - struct list_head **iter) +struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, + struct list_head **iter) { struct netdev_adjacent *lower; @@ -7214,6 +7201,7 @@ static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, return lower->dev; } +EXPORT_SYMBOL(netdev_next_lower_dev_rcu); static u8 __netdev_upper_depth(struct net_device *dev) { diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 3e7e15278c46..bd7eba9066f8 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -974,7 +974,7 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, frh = nlmsg_data(nlh); frh->family = ops->family; - frh->table = rule->table; + frh->table = rule->table < 256 ? rule->table : RT_TABLE_COMPAT; if (nla_put_u32(skb, FRA_TABLE, rule->table)) goto nla_put_failure; if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen)) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 09c44bf2e1d2..e1152f4ffe33 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3504,27 +3504,25 @@ static int rtnl_alt_ifname(int cmd, struct net_device *dev, struct nlattr *attr, if (err) return err; - alt_ifname = nla_data(attr); + alt_ifname = nla_strdup(attr, GFP_KERNEL); + if (!alt_ifname) + return -ENOMEM; + if (cmd == RTM_NEWLINKPROP) { - alt_ifname = kstrdup(alt_ifname, GFP_KERNEL); - if (!alt_ifname) - return -ENOMEM; err = netdev_name_node_alt_create(dev, alt_ifname); - if (err) { - kfree(alt_ifname); - return err; - } + if (!err) + alt_ifname = NULL; } else if (cmd == RTM_DELLINKPROP) { err = netdev_name_node_alt_destroy(dev, alt_ifname); - if (err) - return err; } else { - WARN_ON(1); - return 0; + WARN_ON_ONCE(1); + err = -EINVAL; } - *changed = true; - return 0; + kfree(alt_ifname); + if (!err) + *changed = true; + return err; } static int rtnl_linkprop(int cmd, struct sk_buff *skb, struct nlmsghdr *nlh, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 864cb9e9622f..e1101a4f90a6 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -467,7 +467,6 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, return NULL; } - /* use OR instead of assignment to avoid clearing of bits in mask */ if (pfmemalloc) skb->pfmemalloc = 1; skb->head_frag = 1; @@ -527,7 +526,6 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, return NULL; } - /* use OR instead of assignment to avoid clearing of bits in mask */ if (nc->page.pfmemalloc) skb->pfmemalloc = 1; skb->head_frag = 1; @@ -4805,9 +4803,9 @@ static __sum16 *skb_checksum_setup_ip(struct sk_buff *skb, typeof(IPPROTO_IP) proto, unsigned int off) { - switch (proto) { - int err; + int err; + switch (proto) { case IPPROTO_TCP: err = skb_maybe_pull_tail(skb, off + sizeof(struct tcphdr), off + MAX_TCP_HDR_LEN); diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c index fce45dac4205..8977fe1f3946 100644 --- a/net/ethtool/bitset.c +++ b/net/ethtool/bitset.c @@ -447,7 +447,10 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits, "mask only allowed in compact bitset"); return -EINVAL; } + no_mask = tb[ETHTOOL_A_BITSET_NOMASK]; + if (no_mask) + ethnl_bitmap32_clear(bitmap, 0, nbits, mod); nla_for_each_nested(bit_attr, tb[ETHTOOL_A_BITSET_BITS], rem) { bool old_val, new_val; diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 364ea2cc028e..3ba7f61be107 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -155,7 +155,8 @@ static struct hsr_node *hsr_add_node(struct hsr_priv *hsr, new_node->seq_out[i] = seq_out; spin_lock_bh(&hsr->list_lock); - list_for_each_entry_rcu(node, node_db, mac_list) { + list_for_each_entry_rcu(node, node_db, mac_list, + lockdep_is_held(&hsr->list_lock)) { if (ether_addr_equal(node->macaddress_A, addr)) goto out; if (ether_addr_equal(node->macaddress_B, addr)) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index db76b9609299..08a41f1e1cd2 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1857,8 +1857,12 @@ int __udp_disconnect(struct sock *sk, int flags) inet->inet_dport = 0; sock_rps_reset_rxhash(sk); sk->sk_bound_dev_if = 0; - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) { inet_reset_saddr(sk); + if (sk->sk_prot->rehash && + (sk->sk_userlocks & SOCK_BINDPORT_LOCK)) + sk->sk_prot->rehash(sk); + } if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) { sk->sk_prot->unhash(sk); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 58fbde244381..72abf892302f 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1102,8 +1102,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, found++; break; } - if (rt_can_ecmp) - fallback_ins = fallback_ins ?: ins; + fallback_ins = fallback_ins ?: ins; goto next_iter; } @@ -1146,7 +1145,9 @@ next_iter: } if (fallback_ins && !found) { - /* No ECMP-able route found, replace first non-ECMP one */ + /* No matching route with same ecmp-able-ness found, replace + * first matching route + */ ins = fallback_ins; iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->fib6_table->tb6_lock)); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 55bfc5149d0c..781ca8c07a0d 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -437,8 +437,6 @@ static int ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return -ENOENT; switch (type) { - struct ipv6_tlv_tnl_enc_lim *tel; - __u32 teli; case ICMPV6_DEST_UNREACH: net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n", t->parms.name); @@ -452,7 +450,10 @@ static int ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, break; } return 0; - case ICMPV6_PARAMPROB: + case ICMPV6_PARAMPROB: { + struct ipv6_tlv_tnl_enc_lim *tel; + __u32 teli; + teli = 0; if (code == ICMPV6_HDR_FIELD) teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data); @@ -468,6 +469,7 @@ static int ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, t->parms.name); } return 0; + } case ICMPV6_PKT_TOOBIG: ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL)); return 0; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 5d65436ad5ad..4703b09808d0 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -517,8 +517,6 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, err = 0; switch (*type) { - struct ipv6_tlv_tnl_enc_lim *tel; - __u32 mtu, teli; case ICMPV6_DEST_UNREACH: net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n", t->parms.name); @@ -531,7 +529,10 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, rel_msg = 1; } break; - case ICMPV6_PARAMPROB: + case ICMPV6_PARAMPROB: { + struct ipv6_tlv_tnl_enc_lim *tel; + __u32 teli; + teli = 0; if ((*code) == ICMPV6_HDR_FIELD) teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data); @@ -548,7 +549,10 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, t->parms.name); } break; - case ICMPV6_PKT_TOOBIG: + } + case ICMPV6_PKT_TOOBIG: { + __u32 mtu; + ip6_update_pmtu(skb, net, htonl(*info), 0, 0, sock_net_uid(net, NULL)); mtu = *info - offset; @@ -562,6 +566,7 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, rel_msg = 1; } break; + } case NDISC_REDIRECT: ip6_redirect(skb, net, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 4fbdc60b4e07..2931224b674e 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5198,6 +5198,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, */ cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | NLM_F_REPLACE); + cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE; nhn++; } diff --git a/net/mptcp/Kconfig b/net/mptcp/Kconfig index 49f6054e7f4e..a9ed3bf1d93f 100644 --- a/net/mptcp/Kconfig +++ b/net/mptcp/Kconfig @@ -4,6 +4,7 @@ config MPTCP depends on INET select SKB_EXTENSIONS select CRYPTO_LIB_SHA256 + select CRYPTO help Multipath TCP (MPTCP) connections send and receive data over multiple subflows in order to utilize multiple network paths. Each subflow diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 030dee668e0a..e9aa6807b5be 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -755,60 +755,50 @@ static int mptcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { struct mptcp_sock *msk = mptcp_sk(sk); - int ret = -EOPNOTSUPP; struct socket *ssock; - struct sock *ssk; pr_debug("msk=%p", msk); /* @@ the meaning of setsockopt() when the socket is connected and - * there are multiple subflows is not defined. + * there are multiple subflows is not yet defined. It is up to the + * MPTCP-level socket to configure the subflows until the subflow + * is in TCP fallback, when TCP socket options are passed through + * to the one remaining subflow. */ lock_sock(sk); - ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE); - if (IS_ERR(ssock)) { - release_sock(sk); - return ret; - } + ssock = __mptcp_tcp_fallback(msk); + if (ssock) + return tcp_setsockopt(ssock->sk, level, optname, optval, + optlen); - ssk = ssock->sk; - sock_hold(ssk); release_sock(sk); - ret = tcp_setsockopt(ssk, level, optname, optval, optlen); - sock_put(ssk); - - return ret; + return -EOPNOTSUPP; } static int mptcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *option) { struct mptcp_sock *msk = mptcp_sk(sk); - int ret = -EOPNOTSUPP; struct socket *ssock; - struct sock *ssk; pr_debug("msk=%p", msk); - /* @@ the meaning of getsockopt() when the socket is connected and - * there are multiple subflows is not defined. + /* @@ the meaning of setsockopt() when the socket is connected and + * there are multiple subflows is not yet defined. It is up to the + * MPTCP-level socket to configure the subflows until the subflow + * is in TCP fallback, when socket options are passed through + * to the one remaining subflow. */ lock_sock(sk); - ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE); - if (IS_ERR(ssock)) { - release_sock(sk); - return ret; - } + ssock = __mptcp_tcp_fallback(msk); + if (ssock) + return tcp_getsockopt(ssock->sk, level, optname, optval, + option); - ssk = ssock->sk; - sock_hold(ssk); release_sock(sk); - ret = tcp_getsockopt(ssk, level, optname, optval, option); - sock_put(ssk); - - return ret; + return -EOPNOTSUPP; } static int mptcp_get_port(struct sock *sk, unsigned short snum) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 8a99a2930284..9f8663b30456 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -56,8 +56,8 @@ #define MPTCP_DSS_FLAG_MASK (0x1F) /* MPTCP socket flags */ -#define MPTCP_DATA_READY BIT(0) -#define MPTCP_SEND_SPACE BIT(1) +#define MPTCP_DATA_READY 0 +#define MPTCP_SEND_SPACE 1 /* MPTCP connection sock */ struct mptcp_sock { diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index d1305423640f..1927fc296f95 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -894,32 +894,175 @@ static void nf_ct_acct_merge(struct nf_conn *ct, enum ip_conntrack_info ctinfo, } } -/* Resolve race on insertion if this protocol allows this. */ +static void __nf_conntrack_insert_prepare(struct nf_conn *ct) +{ + struct nf_conn_tstamp *tstamp; + + atomic_inc(&ct->ct_general.use); + ct->status |= IPS_CONFIRMED; + + /* set conntrack timestamp, if enabled. */ + tstamp = nf_conn_tstamp_find(ct); + if (tstamp) + tstamp->start = ktime_get_real_ns(); +} + +static int __nf_ct_resolve_clash(struct sk_buff *skb, + struct nf_conntrack_tuple_hash *h) +{ + /* This is the conntrack entry already in hashes that won race. */ + struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); + enum ip_conntrack_info ctinfo; + struct nf_conn *loser_ct; + + loser_ct = nf_ct_get(skb, &ctinfo); + + if (nf_ct_is_dying(ct)) + return NF_DROP; + + if (!atomic_inc_not_zero(&ct->ct_general.use)) + return NF_DROP; + + if (((ct->status & IPS_NAT_DONE_MASK) == 0) || + nf_ct_match(ct, loser_ct)) { + struct net *net = nf_ct_net(ct); + + nf_ct_acct_merge(ct, ctinfo, loser_ct); + nf_ct_add_to_dying_list(loser_ct); + nf_conntrack_put(&loser_ct->ct_general); + nf_ct_set(skb, ct, ctinfo); + + NF_CT_STAT_INC(net, insert_failed); + return NF_ACCEPT; + } + + nf_ct_put(ct); + return NF_DROP; +} + +/** + * nf_ct_resolve_clash_harder - attempt to insert clashing conntrack entry + * + * @skb: skb that causes the collision + * @repl_idx: hash slot for reply direction + * + * Called when origin or reply direction had a clash. + * The skb can be handled without packet drop provided the reply direction + * is unique or there the existing entry has the identical tuple in both + * directions. + * + * Caller must hold conntrack table locks to prevent concurrent updates. + * + * Returns NF_DROP if the clash could not be handled. + */ +static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx) +{ + struct nf_conn *loser_ct = (struct nf_conn *)skb_nfct(skb); + const struct nf_conntrack_zone *zone; + struct nf_conntrack_tuple_hash *h; + struct hlist_nulls_node *n; + struct net *net; + + zone = nf_ct_zone(loser_ct); + net = nf_ct_net(loser_ct); + + /* Reply direction must never result in a clash, unless both origin + * and reply tuples are identical. + */ + hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[repl_idx], hnnode) { + if (nf_ct_key_equal(h, + &loser_ct->tuplehash[IP_CT_DIR_REPLY].tuple, + zone, net)) + return __nf_ct_resolve_clash(skb, h); + } + + /* We want the clashing entry to go away real soon: 1 second timeout. */ + loser_ct->timeout = nfct_time_stamp + HZ; + + /* IPS_NAT_CLASH removes the entry automatically on the first + * reply. Also prevents UDP tracker from moving the entry to + * ASSURED state, i.e. the entry can always be evicted under + * pressure. + */ + loser_ct->status |= IPS_FIXED_TIMEOUT | IPS_NAT_CLASH; + + __nf_conntrack_insert_prepare(loser_ct); + + /* fake add for ORIGINAL dir: we want lookups to only find the entry + * already in the table. This also hides the clashing entry from + * ctnetlink iteration, i.e. conntrack -L won't show them. + */ + hlist_nulls_add_fake(&loser_ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); + + hlist_nulls_add_head_rcu(&loser_ct->tuplehash[IP_CT_DIR_REPLY].hnnode, + &nf_conntrack_hash[repl_idx]); + return NF_ACCEPT; +} + +/** + * nf_ct_resolve_clash - attempt to handle clash without packet drop + * + * @skb: skb that causes the clash + * @h: tuplehash of the clashing entry already in table + * @hash_reply: hash slot for reply direction + * + * A conntrack entry can be inserted to the connection tracking table + * if there is no existing entry with an identical tuple. + * + * If there is one, @skb (and the assocated, unconfirmed conntrack) has + * to be dropped. In case @skb is retransmitted, next conntrack lookup + * will find the already-existing entry. + * + * The major problem with such packet drop is the extra delay added by + * the packet loss -- it will take some time for a retransmit to occur + * (or the sender to time out when waiting for a reply). + * + * This function attempts to handle the situation without packet drop. + * + * If @skb has no NAT transformation or if the colliding entries are + * exactly the same, only the to-be-confirmed conntrack entry is discarded + * and @skb is associated with the conntrack entry already in the table. + * + * Failing that, the new, unconfirmed conntrack is still added to the table + * provided that the collision only occurs in the ORIGINAL direction. + * The new entry will be added after the existing one in the hash list, + * so packets in the ORIGINAL direction will continue to match the existing + * entry. The new entry will also have a fixed timeout so it expires -- + * due to the collision, it will not see bidirectional traffic. + * + * Returns NF_DROP if the clash could not be resolved. + */ static __cold noinline int -nf_ct_resolve_clash(struct net *net, struct sk_buff *skb, - enum ip_conntrack_info ctinfo, - struct nf_conntrack_tuple_hash *h) +nf_ct_resolve_clash(struct sk_buff *skb, struct nf_conntrack_tuple_hash *h, + u32 reply_hash) { /* This is the conntrack entry already in hashes that won race. */ struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); const struct nf_conntrack_l4proto *l4proto; - enum ip_conntrack_info oldinfo; - struct nf_conn *loser_ct = nf_ct_get(skb, &oldinfo); + enum ip_conntrack_info ctinfo; + struct nf_conn *loser_ct; + struct net *net; + int ret; + + loser_ct = nf_ct_get(skb, &ctinfo); + net = nf_ct_net(loser_ct); l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); - if (l4proto->allow_clash && - !nf_ct_is_dying(ct) && - atomic_inc_not_zero(&ct->ct_general.use)) { - if (((ct->status & IPS_NAT_DONE_MASK) == 0) || - nf_ct_match(ct, loser_ct)) { - nf_ct_acct_merge(ct, ctinfo, loser_ct); - nf_conntrack_put(&loser_ct->ct_general); - nf_ct_set(skb, ct, oldinfo); - return NF_ACCEPT; - } - nf_ct_put(ct); - } + if (!l4proto->allow_clash) + goto drop; + + ret = __nf_ct_resolve_clash(skb, h); + if (ret == NF_ACCEPT) + return ret; + + ret = nf_ct_resolve_clash_harder(skb, reply_hash); + if (ret == NF_ACCEPT) + return ret; + +drop: + nf_ct_add_to_dying_list(loser_ct); NF_CT_STAT_INC(net, drop); + NF_CT_STAT_INC(net, insert_failed); return NF_DROP; } @@ -932,7 +1075,6 @@ __nf_conntrack_confirm(struct sk_buff *skb) struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct nf_conn_help *help; - struct nf_conn_tstamp *tstamp; struct hlist_nulls_node *n; enum ip_conntrack_info ctinfo; struct net *net; @@ -989,6 +1131,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) if (unlikely(nf_ct_is_dying(ct))) { nf_ct_add_to_dying_list(ct); + NF_CT_STAT_INC(net, insert_failed); goto dying; } @@ -1009,13 +1152,8 @@ __nf_conntrack_confirm(struct sk_buff *skb) setting time, otherwise we'd get timer wrap in weird delay cases. */ ct->timeout += nfct_time_stamp; - atomic_inc(&ct->ct_general.use); - ct->status |= IPS_CONFIRMED; - /* set conntrack timestamp, if enabled. */ - tstamp = nf_conn_tstamp_find(ct); - if (tstamp) - tstamp->start = ktime_get_real_ns(); + __nf_conntrack_insert_prepare(ct); /* Since the lookup is lockless, hash insertion must be done after * starting the timer and setting the CONFIRMED bit. The RCU barriers @@ -1035,11 +1173,9 @@ __nf_conntrack_confirm(struct sk_buff *skb) return NF_ACCEPT; out: - nf_ct_add_to_dying_list(ct); - ret = nf_ct_resolve_clash(net, skb, ctinfo, h); + ret = nf_ct_resolve_clash(skb, h, reply_hash); dying: nf_conntrack_double_unlock(hash, reply_hash); - NF_CT_STAT_INC(net, insert_failed); local_bh_enable(); return ret; } diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 7365b43f8f98..760ca2422816 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -81,6 +81,18 @@ static bool udp_error(struct sk_buff *skb, return false; } +static void nf_conntrack_udp_refresh_unreplied(struct nf_conn *ct, + struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + u32 extra_jiffies) +{ + if (unlikely(ctinfo == IP_CT_ESTABLISHED_REPLY && + ct->status & IPS_NAT_CLASH)) + nf_ct_kill(ct); + else + nf_ct_refresh_acct(ct, ctinfo, skb, extra_jiffies); +} + /* Returns verdict for packet, and may modify conntracktype */ int nf_conntrack_udp_packet(struct nf_conn *ct, struct sk_buff *skb, @@ -116,8 +128,8 @@ int nf_conntrack_udp_packet(struct nf_conn *ct, if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); } else { - nf_ct_refresh_acct(ct, ctinfo, skb, - timeouts[UDP_CT_UNREPLIED]); + nf_conntrack_udp_refresh_unreplied(ct, skb, ctinfo, + timeouts[UDP_CT_UNREPLIED]); } return NF_ACCEPT; } @@ -198,8 +210,8 @@ int nf_conntrack_udplite_packet(struct nf_conn *ct, if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); } else { - nf_ct_refresh_acct(ct, ctinfo, skb, - timeouts[UDP_CT_UNREPLIED]); + nf_conntrack_udp_refresh_unreplied(ct, skb, ctinfo, + timeouts[UDP_CT_UNREPLIED]); } return NF_ACCEPT; } diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 83e1db37c3b0..06f00cdc3891 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -847,9 +847,6 @@ static int nf_flow_table_offload_cmd(struct flow_block_offload *bo, { int err; - if (!nf_flowtable_hw_offload(flowtable)) - return 0; - if (!dev->netdev_ops->ndo_setup_tc) return -EOPNOTSUPP; @@ -876,6 +873,9 @@ int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, struct flow_block_offload bo; int err; + if (!nf_flowtable_hw_offload(flowtable)) + return 0; + err = nf_flow_table_offload_cmd(&bo, flowtable, dev, cmd, &extack); if (err < 0) return err; diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index f0cb1e13af50..feac8553f6d9 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -203,7 +203,7 @@ * :: * * rule indices in last field: 0 1 - * map to elements: 0x42 0x66 + * map to elements: 0x66 0x42 * * * Matching @@ -298,7 +298,7 @@ * :: * * rule indices in last field: 0 1 - * map to elements: 0x42 0x66 + * map to elements: 0x66 0x42 * * the matching element is at 0x42. * @@ -503,7 +503,7 @@ static int pipapo_refill(unsigned long *map, int len, int rules, return -1; } - if (unlikely(match_only)) { + if (match_only) { bitmap_clear(map, i, 1); return i; } diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index bccd47cd7190..7a2c4b8408c4 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -36,6 +36,7 @@ #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/mutex.h> #include <linux/kernel.h> +#include <linux/refcount.h> #include <uapi/linux/netfilter/xt_hashlimit.h> #define XT_HASHLIMIT_ALL (XT_HASHLIMIT_HASH_DIP | XT_HASHLIMIT_HASH_DPT | \ @@ -114,7 +115,7 @@ struct dsthash_ent { struct xt_hashlimit_htable { struct hlist_node node; /* global list of all htables */ - int use; + refcount_t use; u_int8_t family; bool rnd_initialized; @@ -315,7 +316,7 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg, for (i = 0; i < hinfo->cfg.size; i++) INIT_HLIST_HEAD(&hinfo->hash[i]); - hinfo->use = 1; + refcount_set(&hinfo->use, 1); hinfo->count = 0; hinfo->family = family; hinfo->rnd_initialized = false; @@ -420,7 +421,7 @@ static struct xt_hashlimit_htable *htable_find_get(struct net *net, hlist_for_each_entry(hinfo, &hashlimit_net->htables, node) { if (!strcmp(name, hinfo->name) && hinfo->family == family) { - hinfo->use++; + refcount_inc(&hinfo->use); return hinfo; } } @@ -429,12 +430,11 @@ static struct xt_hashlimit_htable *htable_find_get(struct net *net, static void htable_put(struct xt_hashlimit_htable *hinfo) { - mutex_lock(&hashlimit_mutex); - if (--hinfo->use == 0) { + if (refcount_dec_and_mutex_lock(&hinfo->use, &hashlimit_mutex)) { hlist_del(&hinfo->node); + mutex_unlock(&hashlimit_mutex); htable_destroy(hinfo); } - mutex_unlock(&hashlimit_mutex); } /* The algorithm used is the Simple Token Bucket Filter (TBF) @@ -837,6 +837,8 @@ hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) return hashlimit_mt_common(skb, par, hinfo, &info->cfg, 3); } +#define HASHLIMIT_MAX_SIZE 1048576 + static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, struct xt_hashlimit_htable **hinfo, struct hashlimit_cfg3 *cfg, @@ -847,6 +849,14 @@ static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, if (cfg->gc_interval == 0 || cfg->expire == 0) return -EINVAL; + if (cfg->size > HASHLIMIT_MAX_SIZE) { + cfg->size = HASHLIMIT_MAX_SIZE; + pr_info_ratelimited("size too large, truncated to %u\n", cfg->size); + } + if (cfg->max > HASHLIMIT_MAX_SIZE) { + cfg->max = HASHLIMIT_MAX_SIZE; + pr_info_ratelimited("max too large, truncated to %u\n", cfg->max); + } if (par->family == NFPROTO_IPV4) { if (cfg->srcmask > 32 || cfg->dstmask > 32) return -EINVAL; diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index f5d34da0646e..a1f2320ecc16 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -143,7 +143,8 @@ static struct netlbl_dom_map *netlbl_domhsh_search(const char *domain, if (domain != NULL) { bkt = netlbl_domhsh_hash(domain); bkt_list = &netlbl_domhsh_rcu_deref(netlbl_domhsh)->tbl[bkt]; - list_for_each_entry_rcu(iter, bkt_list, list) + list_for_each_entry_rcu(iter, bkt_list, list, + lockdep_is_held(&netlbl_domhsh_lock)) if (iter->valid && netlbl_family_match(iter->family, family) && strcmp(iter->domain, domain) == 0) diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index d2e4ab8d1cb1..77bb1bb22c3b 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -207,7 +207,8 @@ static struct netlbl_unlhsh_iface *netlbl_unlhsh_search_iface(int ifindex) bkt = netlbl_unlhsh_hash(ifindex); bkt_list = &netlbl_unlhsh_rcu_deref(netlbl_unlhsh)->tbl[bkt]; - list_for_each_entry_rcu(iter, bkt_list, list) + list_for_each_entry_rcu(iter, bkt_list, list, + lockdep_is_held(&netlbl_unlhsh_lock)) if (iter->valid && iter->ifindex == ifindex) return iter; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 4e31721e7293..edf3e285e242 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1014,7 +1014,8 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, if (nlk->netlink_bind && groups) { int group; - for (group = 0; group < nlk->ngroups; group++) { + /* nl_groups is a u32, so cap the maximum groups we can bind */ + for (group = 0; group < BITS_PER_TYPE(u32); group++) { if (!test_bit(group, &groups)) continue; err = nlk->netlink_bind(net, group + 1); @@ -1033,7 +1034,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, netlink_insert(sk, nladdr->nl_pid) : netlink_autobind(sock); if (err) { - netlink_undo_bind(nlk->ngroups, groups, sk); + netlink_undo_bind(BITS_PER_TYPE(u32), groups, sk); goto unlock; } } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 659c2a790fe7..c047afd12116 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -179,7 +179,8 @@ struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no) struct hlist_head *head; head = vport_hash_bucket(dp, port_no); - hlist_for_each_entry_rcu(vport, head, dp_hash_node) { + hlist_for_each_entry_rcu(vport, head, dp_hash_node, + lockdep_ovsl_is_held()) { if (vport->port_no == port_no) return vport; } @@ -2042,7 +2043,8 @@ static unsigned int ovs_get_max_headroom(struct datapath *dp) int i; for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { - hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) { + hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node, + lockdep_ovsl_is_held()) { dev = vport->dev; dev_headroom = netdev_get_fwd_headroom(dev); if (dev_headroom > max_headroom) @@ -2061,7 +2063,8 @@ static void ovs_update_headroom(struct datapath *dp, unsigned int new_headroom) dp->max_headroom = new_headroom; for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) - hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) + hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node, + lockdep_ovsl_is_held()) netdev_set_rx_headroom(vport->dev, new_headroom); } diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 7da4230627f5..288122eec7c8 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2708,10 +2708,6 @@ static int validate_set(const struct nlattr *a, return -EINVAL; switch (key_type) { - const struct ovs_key_ipv4 *ipv4_key; - const struct ovs_key_ipv6 *ipv6_key; - int err; - case OVS_KEY_ATTR_PRIORITY: case OVS_KEY_ATTR_SKB_MARK: case OVS_KEY_ATTR_CT_MARK: @@ -2723,7 +2719,9 @@ static int validate_set(const struct nlattr *a, return -EINVAL; break; - case OVS_KEY_ATTR_TUNNEL: + case OVS_KEY_ATTR_TUNNEL: { + int err; + if (masked) return -EINVAL; /* Masked tunnel set not supported. */ @@ -2732,8 +2730,10 @@ static int validate_set(const struct nlattr *a, if (err) return err; break; + } + case OVS_KEY_ATTR_IPV4: { + const struct ovs_key_ipv4 *ipv4_key; - case OVS_KEY_ATTR_IPV4: if (eth_type != htons(ETH_P_IP)) return -EINVAL; @@ -2753,8 +2753,10 @@ static int validate_set(const struct nlattr *a, return -EINVAL; } break; + } + case OVS_KEY_ATTR_IPV6: { + const struct ovs_key_ipv6 *ipv6_key; - case OVS_KEY_ATTR_IPV6: if (eth_type != htons(ETH_P_IPV6)) return -EINVAL; @@ -2781,7 +2783,7 @@ static int validate_set(const struct nlattr *a, return -EINVAL; break; - + } case OVS_KEY_ATTR_TCP: if ((eth_type != htons(ETH_P_IP) && eth_type != htons(ETH_P_IPV6)) || diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index 5904e93e5765..fd8a01ca7a2d 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -585,7 +585,8 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti, head = find_bucket(ti, hash); (*n_mask_hit)++; - hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver]) { + hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver], + lockdep_ovsl_is_held()) { if (flow->mask == mask && flow->flow_table.hash == hash && flow_cmp_masked_key(flow, &masked_key, &mask->range)) return flow; @@ -769,7 +770,8 @@ struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *tbl, hash = ufid_hash(ufid); head = find_bucket(ti, hash); - hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver]) { + hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver], + lockdep_ovsl_is_held()) { if (flow->ufid_table.hash == hash && ovs_flow_cmp_ufid(flow, ufid)) return flow; diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index 3323b79ff548..5010d1ddd4bd 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -61,7 +61,8 @@ static struct dp_meter *lookup_meter(const struct datapath *dp, struct hlist_head *head; head = meter_hash_bucket(dp, meter_id); - hlist_for_each_entry_rcu(meter, head, dp_hash_node) { + hlist_for_each_entry_rcu(meter, head, dp_hash_node, + lockdep_ovsl_is_held()) { if (meter->id == meter_id) return meter; } diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 5da9392b03d6..47febb4504f0 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -96,7 +96,8 @@ struct vport *ovs_vport_locate(const struct net *net, const char *name) struct hlist_head *bucket = hash_bucket(net, name); struct vport *vport; - hlist_for_each_entry_rcu(vport, bucket, hash_node) + hlist_for_each_entry_rcu(vport, bucket, hash_node, + lockdep_ovsl_is_held()) if (!strcmp(name, ovs_vport_name(vport)) && net_eq(ovs_dp_get_net(vport->dp), net)) return vport; diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 3341eee87bf9..585e6b3b69ce 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -162,10 +162,9 @@ static int rds_pin_pages(unsigned long user_addr, unsigned int nr_pages, if (write) gup_flags |= FOLL_WRITE; - ret = get_user_pages_fast(user_addr, nr_pages, gup_flags, pages); + ret = pin_user_pages_fast(user_addr, nr_pages, gup_flags, pages); if (ret >= 0 && ret < nr_pages) { - while (ret--) - put_page(pages[ret]); + unpin_user_pages(pages, ret); ret = -EFAULT; } @@ -300,8 +299,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, * to release anything. */ if (!need_odp) { - for (i = 0 ; i < nents; i++) - put_page(sg_page(&sg[i])); + unpin_user_pages(pages, nr_pages); kfree(sg); } ret = PTR_ERR(trans_private); @@ -325,7 +323,12 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, if (cookie_ret) *cookie_ret = cookie; - if (args->cookie_addr && put_user(cookie, (u64 __user *)(unsigned long) args->cookie_addr)) { + if (args->cookie_addr && + put_user(cookie, (u64 __user *)(unsigned long)args->cookie_addr)) { + if (!need_odp) { + unpin_user_pages(pages, nr_pages); + kfree(sg); + } ret = -EFAULT; goto out; } @@ -496,9 +499,7 @@ void rds_rdma_free_op(struct rm_rdma_op *ro) * is the case for a RDMA_READ which copies from remote * to local memory */ - if (!ro->op_write) - set_page_dirty(page); - put_page(page); + unpin_user_pages_dirty_lock(&page, 1, !ro->op_write); } } @@ -515,8 +516,7 @@ void rds_atomic_free_op(struct rm_atomic_op *ao) /* Mark page dirty if it was possibly modified, which * is the case for a RDMA_READ which copies from remote * to local memory */ - set_page_dirty(page); - put_page(page); + unpin_user_pages_dirty_lock(&page, 1, true); kfree(ao->op_notifier); ao->op_notifier = NULL; @@ -944,7 +944,7 @@ int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm, return ret; err: if (page) - put_page(page); + unpin_user_page(page); rm->atomic.op_active = 0; kfree(rm->atomic.op_notifier); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 7e54d2ab5254..d32d4233d337 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -305,6 +305,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct cls_fl_filter *f; list_for_each_entry_rcu(mask, &head->masks, list) { + flow_dissector_init_keys(&skb_key.control, &skb_key.basic); fl_clear_masked_range(&skb_key, mask); skb_flow_dissect_meta(skb, &mask->dissector, &skb_key); diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 748e3b19ec1d..6a16af4b1ef6 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -170,6 +170,16 @@ static inline bool sctp_chunk_length_valid(struct sctp_chunk *chunk, return true; } +/* Check for format error in an ABORT chunk */ +static inline bool sctp_err_chunk_valid(struct sctp_chunk *chunk) +{ + struct sctp_errhdr *err; + + sctp_walk_errors(err, chunk->chunk_hdr); + + return (void *)err == (void *)chunk->chunk_end; +} + /********************************************************** * These are the state functions for handling chunk events. **********************************************************/ @@ -2255,6 +2265,9 @@ enum sctp_disposition sctp_sf_shutdown_pending_abort( sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + if (!sctp_err_chunk_valid(chunk)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands); } @@ -2298,6 +2311,9 @@ enum sctp_disposition sctp_sf_shutdown_sent_abort( sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + if (!sctp_err_chunk_valid(chunk)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* Stop the T2-shutdown timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN)); @@ -2565,6 +2581,9 @@ enum sctp_disposition sctp_sf_do_9_1_abort( sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + if (!sctp_err_chunk_valid(chunk)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands); } @@ -2582,16 +2601,8 @@ static enum sctp_disposition __sctp_sf_do_9_1_abort( /* See if we have an error cause code in the chunk. */ len = ntohs(chunk->chunk_hdr->length); - if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) { - struct sctp_errhdr *err; - - sctp_walk_errors(err, chunk->chunk_hdr); - if ((void *)err != (void *)chunk->chunk_end) - return sctp_sf_pdiscard(net, ep, asoc, type, arg, - commands); - + if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) error = ((struct sctp_errhdr *)chunk->skb->data)->cause; - } sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNRESET)); /* ASSOC_FAILED will DELETE_TCB. */ diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 1ba5a92832bb..1c5574e2e058 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -593,7 +593,7 @@ struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, u32 seq, u64 *p_record_sn) { u64 record_sn = context->hint_record_sn; - struct tls_record_info *info; + struct tls_record_info *info, *last; info = context->retransmit_hint; if (!info || @@ -605,6 +605,24 @@ struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, struct tls_record_info, list); if (!info) return NULL; + /* send the start_marker record if seq number is before the + * tls offload start marker sequence number. This record is + * required to handle TCP packets which are before TLS offload + * started. + * And if it's not start marker, look if this seq number + * belongs to the list. + */ + if (likely(!tls_record_is_start_marker(info))) { + /* we have the first record, get the last record to see + * if this seq number belongs to the list. + */ + last = list_last_entry(&context->records_list, + struct tls_record_info, list); + + if (!between(seq, tls_record_start_seq(info), + last->end_seq)) + return NULL; + } record_sn = context->unacked_record_sn; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index df600487a68d..356f90e4522b 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -217,6 +217,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) static void xsk_flush(struct xdp_sock *xs) { xskq_prod_submit(xs->rx); + __xskq_cons_release(xs->umem->fq); sock_def_readable(&xs->sk); } @@ -304,6 +305,7 @@ void xsk_umem_consume_tx_done(struct xdp_umem *umem) rcu_read_lock(); list_for_each_entry_rcu(xs, &umem->xsk_list, list) { + __xskq_cons_release(xs->tx); xs->sk.sk_write_space(&xs->sk); } rcu_read_unlock(); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index bec2af11853a..89a01ac4e079 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -271,7 +271,8 @@ static inline void xskq_cons_release(struct xsk_queue *q) { /* To improve performance, only update local state here. * Reflect this to global state when we get new entries - * from the ring in xskq_cons_get_entries(). + * from the ring in xskq_cons_get_entries() and whenever + * Rx or Tx processing are completed in the NAPI loop. */ q->cached_cons++; } diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 34085d146fa2..6cbcd1a3e113 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -932,10 +932,6 @@ sub get_maintainers { } } - foreach my $fix (@fixes) { - vcs_add_commit_signers($fix, "blamed_fixes"); - } - foreach my $email (@email_to, @list_to) { $email->[0] = deduplicate_email($email->[0]); } @@ -974,6 +970,10 @@ sub get_maintainers { } } + foreach my $fix (@fixes) { + vcs_add_commit_signers($fix, "blamed_fixes"); + } + my @to = (); if ($email || $email_list) { if ($email) { @@ -1341,35 +1341,11 @@ sub add_categories { } } } elsif ($ptype eq "M") { - my ($name, $address) = parse_email($pvalue); - if ($name eq "") { - if ($i > 0) { - my $tv = $typevalue[$i - 1]; - if ($tv =~ m/^([A-Z]):\s*(.*)/) { - if ($1 eq "P") { - $name = $2; - $pvalue = format_email($name, $address, $email_usename); - } - } - } - } if ($email_maintainer) { my $role = get_maintainer_role($i); push_email_addresses($pvalue, $role); } } elsif ($ptype eq "R") { - my ($name, $address) = parse_email($pvalue); - if ($name eq "") { - if ($i > 0) { - my $tv = $typevalue[$i - 1]; - if ($tv =~ m/^([A-Z]):\s*(.*)/) { - if ($1 eq "P") { - $name = $2; - $pvalue = format_email($name, $address, $email_usename); - } - } - } - } if ($email_reviewer) { my $subsystem = get_subsystem_name($i); push_email_addresses($pvalue, "reviewer:$subsystem"); diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig index 711ff10fa36e..3f3ee4e2eb0d 100644 --- a/security/integrity/ima/Kconfig +++ b/security/integrity/ima/Kconfig @@ -112,6 +112,10 @@ choice config IMA_DEFAULT_HASH_WP512 bool "WP512" depends on CRYPTO_WP512=y && !IMA_TEMPLATE + + config IMA_DEFAULT_HASH_SM3 + bool "SM3" + depends on CRYPTO_SM3=y && !IMA_TEMPLATE endchoice config IMA_DEFAULT_HASH @@ -121,6 +125,7 @@ config IMA_DEFAULT_HASH default "sha256" if IMA_DEFAULT_HASH_SHA256 default "sha512" if IMA_DEFAULT_HASH_SHA512 default "wp512" if IMA_DEFAULT_HASH_WP512 + default "sm3" if IMA_DEFAULT_HASH_SM3 config IMA_WRITE_POLICY bool "Enable multiple writes to the IMA policy" diff --git a/security/integrity/platform_certs/load_uefi.c b/security/integrity/platform_certs/load_uefi.c index 111898aad56e..f0c908241966 100644 --- a/security/integrity/platform_certs/load_uefi.c +++ b/security/integrity/platform_certs/load_uefi.c @@ -35,16 +35,18 @@ static __init bool uefi_check_ignore_db(void) * Get a certificate list blob from the named EFI variable. */ static __init void *get_cert_list(efi_char16_t *name, efi_guid_t *guid, - unsigned long *size) + unsigned long *size, efi_status_t *status) { - efi_status_t status; unsigned long lsize = 4; unsigned long tmpdb[4]; void *db; - status = efi.get_variable(name, guid, NULL, &lsize, &tmpdb); - if (status != EFI_BUFFER_TOO_SMALL) { - pr_err("Couldn't get size: 0x%lx\n", status); + *status = efi.get_variable(name, guid, NULL, &lsize, &tmpdb); + if (*status == EFI_NOT_FOUND) + return NULL; + + if (*status != EFI_BUFFER_TOO_SMALL) { + pr_err("Couldn't get size: 0x%lx\n", *status); return NULL; } @@ -52,10 +54,10 @@ static __init void *get_cert_list(efi_char16_t *name, efi_guid_t *guid, if (!db) return NULL; - status = efi.get_variable(name, guid, NULL, &lsize, db); - if (status != EFI_SUCCESS) { + *status = efi.get_variable(name, guid, NULL, &lsize, db); + if (*status != EFI_SUCCESS) { kfree(db); - pr_err("Error reading db var: 0x%lx\n", status); + pr_err("Error reading db var: 0x%lx\n", *status); return NULL; } @@ -74,6 +76,7 @@ static int __init load_uefi_certs(void) efi_guid_t mok_var = EFI_SHIM_LOCK_GUID; void *db = NULL, *dbx = NULL, *mok = NULL; unsigned long dbsize = 0, dbxsize = 0, moksize = 0; + efi_status_t status; int rc = 0; if (!efi.get_variable) @@ -83,9 +86,12 @@ static int __init load_uefi_certs(void) * an error if we can't get them. */ if (!uefi_check_ignore_db()) { - db = get_cert_list(L"db", &secure_var, &dbsize); + db = get_cert_list(L"db", &secure_var, &dbsize, &status); if (!db) { - pr_err("MODSIGN: Couldn't get UEFI db list\n"); + if (status == EFI_NOT_FOUND) + pr_debug("MODSIGN: db variable wasn't found\n"); + else + pr_err("MODSIGN: Couldn't get UEFI db list\n"); } else { rc = parse_efi_signature_list("UEFI:db", db, dbsize, get_handler_for_db); @@ -96,9 +102,12 @@ static int __init load_uefi_certs(void) } } - mok = get_cert_list(L"MokListRT", &mok_var, &moksize); + mok = get_cert_list(L"MokListRT", &mok_var, &moksize, &status); if (!mok) { - pr_info("Couldn't get UEFI MokListRT\n"); + if (status == EFI_NOT_FOUND) + pr_debug("MokListRT variable wasn't found\n"); + else + pr_info("Couldn't get UEFI MokListRT\n"); } else { rc = parse_efi_signature_list("UEFI:MokListRT", mok, moksize, get_handler_for_db); @@ -107,9 +116,12 @@ static int __init load_uefi_certs(void) kfree(mok); } - dbx = get_cert_list(L"dbx", &secure_var, &dbxsize); + dbx = get_cert_list(L"dbx", &secure_var, &dbxsize, &status); if (!dbx) { - pr_info("Couldn't get UEFI dbx list\n"); + if (status == EFI_NOT_FOUND) + pr_debug("dbx variable wasn't found\n"); + else + pr_info("Couldn't get UEFI dbx list\n"); } else { rc = parse_efi_signature_list("UEFI:dbx", dbx, dbxsize, diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 6d9592f0ae1d..cc93157fa950 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -580,7 +580,7 @@ static int update_timestamp_of_queue(struct snd_seq_event *event, event->queue = queue; event->flags &= ~SNDRV_SEQ_TIME_STAMP_MASK; if (real_time) { - event->time.time = snd_seq_timer_get_cur_time(q->timer); + event->time.time = snd_seq_timer_get_cur_time(q->timer, true); event->flags |= SNDRV_SEQ_TIME_STAMP_REAL; } else { event->time.tick = snd_seq_timer_get_cur_tick(q->timer); @@ -1659,7 +1659,7 @@ static int snd_seq_ioctl_get_queue_status(struct snd_seq_client *client, tmr = queue->timer; status->events = queue->tickq->cells + queue->timeq->cells; - status->time = snd_seq_timer_get_cur_time(tmr); + status->time = snd_seq_timer_get_cur_time(tmr, true); status->tick = snd_seq_timer_get_cur_tick(tmr); status->running = tmr->running; diff --git a/sound/core/seq/seq_queue.c b/sound/core/seq/seq_queue.c index caf68bf42f13..71a6ea62c3be 100644 --- a/sound/core/seq/seq_queue.c +++ b/sound/core/seq/seq_queue.c @@ -238,6 +238,8 @@ void snd_seq_check_queue(struct snd_seq_queue *q, int atomic, int hop) { unsigned long flags; struct snd_seq_event_cell *cell; + snd_seq_tick_time_t cur_tick; + snd_seq_real_time_t cur_time; if (q == NULL) return; @@ -254,17 +256,18 @@ void snd_seq_check_queue(struct snd_seq_queue *q, int atomic, int hop) __again: /* Process tick queue... */ + cur_tick = snd_seq_timer_get_cur_tick(q->timer); for (;;) { - cell = snd_seq_prioq_cell_out(q->tickq, - &q->timer->tick.cur_tick); + cell = snd_seq_prioq_cell_out(q->tickq, &cur_tick); if (!cell) break; snd_seq_dispatch_event(cell, atomic, hop); } /* Process time queue... */ + cur_time = snd_seq_timer_get_cur_time(q->timer, false); for (;;) { - cell = snd_seq_prioq_cell_out(q->timeq, &q->timer->cur_time); + cell = snd_seq_prioq_cell_out(q->timeq, &cur_time); if (!cell) break; snd_seq_dispatch_event(cell, atomic, hop); @@ -392,6 +395,7 @@ int snd_seq_queue_check_access(int queueid, int client) int snd_seq_queue_set_owner(int queueid, int client, int locked) { struct snd_seq_queue *q = queueptr(queueid); + unsigned long flags; if (q == NULL) return -EINVAL; @@ -401,8 +405,10 @@ int snd_seq_queue_set_owner(int queueid, int client, int locked) return -EPERM; } + spin_lock_irqsave(&q->owner_lock, flags); q->locked = locked ? 1 : 0; q->owner = client; + spin_unlock_irqrestore(&q->owner_lock, flags); queue_access_unlock(q); queuefree(q); @@ -539,15 +545,17 @@ void snd_seq_queue_client_termination(int client) unsigned long flags; int i; struct snd_seq_queue *q; + bool matched; for (i = 0; i < SNDRV_SEQ_MAX_QUEUES; i++) { if ((q = queueptr(i)) == NULL) continue; spin_lock_irqsave(&q->owner_lock, flags); - if (q->owner == client) + matched = (q->owner == client); + if (matched) q->klocked = 1; spin_unlock_irqrestore(&q->owner_lock, flags); - if (q->owner == client) { + if (matched) { if (q->timer->running) snd_seq_timer_stop(q->timer); snd_seq_timer_reset(q->timer); @@ -739,6 +747,8 @@ void snd_seq_info_queues_read(struct snd_info_entry *entry, int i, bpm; struct snd_seq_queue *q; struct snd_seq_timer *tmr; + bool locked; + int owner; for (i = 0; i < SNDRV_SEQ_MAX_QUEUES; i++) { if ((q = queueptr(i)) == NULL) @@ -750,9 +760,14 @@ void snd_seq_info_queues_read(struct snd_info_entry *entry, else bpm = 0; + spin_lock_irq(&q->owner_lock); + locked = q->locked; + owner = q->owner; + spin_unlock_irq(&q->owner_lock); + snd_iprintf(buffer, "queue %d: [%s]\n", q->queue, q->name); - snd_iprintf(buffer, "owned by client : %d\n", q->owner); - snd_iprintf(buffer, "lock status : %s\n", q->locked ? "Locked" : "Free"); + snd_iprintf(buffer, "owned by client : %d\n", owner); + snd_iprintf(buffer, "lock status : %s\n", locked ? "Locked" : "Free"); snd_iprintf(buffer, "queued time events : %d\n", snd_seq_prioq_avail(q->timeq)); snd_iprintf(buffer, "queued tick events : %d\n", snd_seq_prioq_avail(q->tickq)); snd_iprintf(buffer, "timer state : %s\n", tmr->running ? "Running" : "Stopped"); diff --git a/sound/core/seq/seq_timer.c b/sound/core/seq/seq_timer.c index be59b59c9be4..1645e4142e30 100644 --- a/sound/core/seq/seq_timer.c +++ b/sound/core/seq/seq_timer.c @@ -428,14 +428,15 @@ int snd_seq_timer_continue(struct snd_seq_timer *tmr) } /* return current 'real' time. use timeofday() to get better granularity. */ -snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr) +snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr, + bool adjust_ktime) { snd_seq_real_time_t cur_time; unsigned long flags; spin_lock_irqsave(&tmr->lock, flags); cur_time = tmr->cur_time; - if (tmr->running) { + if (adjust_ktime && tmr->running) { struct timespec64 tm; ktime_get_ts64(&tm); @@ -452,7 +453,13 @@ snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr) high PPQ values) */ snd_seq_tick_time_t snd_seq_timer_get_cur_tick(struct snd_seq_timer *tmr) { - return tmr->tick.cur_tick; + snd_seq_tick_time_t cur_tick; + unsigned long flags; + + spin_lock_irqsave(&tmr->lock, flags); + cur_tick = tmr->tick.cur_tick; + spin_unlock_irqrestore(&tmr->lock, flags); + return cur_tick; } diff --git a/sound/core/seq/seq_timer.h b/sound/core/seq/seq_timer.h index 66c3e344eae3..4bec57df8158 100644 --- a/sound/core/seq/seq_timer.h +++ b/sound/core/seq/seq_timer.h @@ -120,7 +120,8 @@ int snd_seq_timer_set_tempo_ppq(struct snd_seq_timer *tmr, int tempo, int ppq); int snd_seq_timer_set_position_tick(struct snd_seq_timer *tmr, snd_seq_tick_time_t position); int snd_seq_timer_set_position_time(struct snd_seq_timer *tmr, snd_seq_real_time_t position); int snd_seq_timer_set_skew(struct snd_seq_timer *tmr, unsigned int skew, unsigned int base); -snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr); +snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr, + bool adjust_ktime); snd_seq_tick_time_t snd_seq_timer_get_cur_tick(struct snd_seq_timer *tmr); extern int seq_default_timer_class; diff --git a/sound/hda/ext/hdac_ext_controller.c b/sound/hda/ext/hdac_ext_controller.c index a684f0520b4b..4d060d5b1db6 100644 --- a/sound/hda/ext/hdac_ext_controller.c +++ b/sound/hda/ext/hdac_ext_controller.c @@ -254,6 +254,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_link_power_down_all); int snd_hdac_ext_bus_link_get(struct hdac_bus *bus, struct hdac_ext_link *link) { + unsigned long codec_mask; int ret = 0; mutex_lock(&bus->lock); @@ -280,9 +281,11 @@ int snd_hdac_ext_bus_link_get(struct hdac_bus *bus, * HDA spec section 4.3 - Codec Discovery */ udelay(521); - bus->codec_mask = snd_hdac_chip_readw(bus, STATESTS); - dev_dbg(bus->dev, "codec_mask = 0x%lx\n", bus->codec_mask); - snd_hdac_chip_writew(bus, STATESTS, bus->codec_mask); + codec_mask = snd_hdac_chip_readw(bus, STATESTS); + dev_dbg(bus->dev, "codec_mask = 0x%lx\n", codec_mask); + snd_hdac_chip_writew(bus, STATESTS, codec_mask); + if (!bus->codec_mask) + bus->codec_mask = codec_mask; } mutex_unlock(&bus->lock); diff --git a/sound/hda/hdmi_chmap.c b/sound/hda/hdmi_chmap.c index 5fd6d575e123..aad5c4bf4d34 100644 --- a/sound/hda/hdmi_chmap.c +++ b/sound/hda/hdmi_chmap.c @@ -250,7 +250,7 @@ void snd_hdac_print_channel_allocation(int spk_alloc, char *buf, int buflen) for (i = 0, j = 0; i < ARRAY_SIZE(cea_speaker_allocation_names); i++) { if (spk_alloc & (1 << i)) - j += snprintf(buf + j, buflen - j, " %s", + j += scnprintf(buf + j, buflen - j, " %s", cea_speaker_allocation_names[i]); } buf[j] = '\0'; /* necessary when j == 0 */ diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index 5dc42f932739..53e7732ef752 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -4022,7 +4022,7 @@ void snd_print_pcm_bits(int pcm, char *buf, int buflen) for (i = 0, j = 0; i < ARRAY_SIZE(bits); i++) if (pcm & (AC_SUPPCM_BITS_8 << i)) - j += snprintf(buf + j, buflen - j, " %d", bits[i]); + j += scnprintf(buf + j, buflen - j, " %d", bits[i]); buf[j] = '\0'; /* necessary when j == 0 */ } diff --git a/sound/pci/hda/hda_eld.c b/sound/pci/hda/hda_eld.c index bb46c89b7f63..136477ed46ae 100644 --- a/sound/pci/hda/hda_eld.c +++ b/sound/pci/hda/hda_eld.c @@ -360,7 +360,7 @@ static void hdmi_print_pcm_rates(int pcm, char *buf, int buflen) for (i = 0, j = 0; i < ARRAY_SIZE(alsa_rates); i++) if (pcm & (1 << i)) - j += snprintf(buf + j, buflen - j, " %d", + j += scnprintf(buf + j, buflen - j, " %d", alsa_rates[i]); buf[j] = '\0'; /* necessary when j == 0 */ diff --git a/sound/pci/hda/hda_sysfs.c b/sound/pci/hda/hda_sysfs.c index 0607ed5d1959..eb8ec109d7ad 100644 --- a/sound/pci/hda/hda_sysfs.c +++ b/sound/pci/hda/hda_sysfs.c @@ -222,7 +222,7 @@ static ssize_t init_verbs_show(struct device *dev, int i, len = 0; mutex_lock(&codec->user_mutex); snd_array_for_each(&codec->init_verbs, i, v) { - len += snprintf(buf + len, PAGE_SIZE - len, + len += scnprintf(buf + len, PAGE_SIZE - len, "0x%02x 0x%03x 0x%04x\n", v->nid, v->verb, v->param); } @@ -272,7 +272,7 @@ static ssize_t hints_show(struct device *dev, int i, len = 0; mutex_lock(&codec->user_mutex); snd_array_for_each(&codec->hints, i, hint) { - len += snprintf(buf + len, PAGE_SIZE - len, + len += scnprintf(buf + len, PAGE_SIZE - len, "%s = %s\n", hint->key, hint->val); } mutex_unlock(&codec->user_mutex); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 6c8cb4ce517e..477589e7ec1d 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2447,7 +2447,9 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1071, 0x8258, "Evesham Voyaeger", ALC882_FIXUP_EAPD), SND_PCI_QUIRK(0x1458, 0xa002, "Gigabyte EP45-DS3/Z87X-UD3H", ALC889_FIXUP_FRONT_HP_NO_PRESENCE), SND_PCI_QUIRK(0x1458, 0xa0b8, "Gigabyte AZ370-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS), + SND_PCI_QUIRK(0x1462, 0x1228, "MSI-GP63", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1462, 0x1276, "MSI-GL73", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1462, 0x1293, "MSI-GP65", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD), SND_PCI_QUIRK(0x1462, 0xda57, "MSI Z270-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS), SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3), diff --git a/sound/soc/amd/raven/acp3x-i2s.c b/sound/soc/amd/raven/acp3x-i2s.c index 31cd4008e33f..91a388184e52 100644 --- a/sound/soc/amd/raven/acp3x-i2s.c +++ b/sound/soc/amd/raven/acp3x-i2s.c @@ -170,6 +170,7 @@ static int acp3x_i2s_trigger(struct snd_pcm_substream *substream, struct snd_soc_card *card; struct acp3x_platform_info *pinfo; u32 ret, val, period_bytes, reg_val, ier_val, water_val; + u32 buf_size, buf_reg; prtd = substream->private_data; rtd = substream->runtime->private_data; @@ -183,6 +184,8 @@ static int acp3x_i2s_trigger(struct snd_pcm_substream *substream, } period_bytes = frames_to_bytes(substream->runtime, substream->runtime->period_size); + buf_size = frames_to_bytes(substream->runtime, + substream->runtime->buffer_size); switch (cmd) { case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_RESUME: @@ -196,6 +199,7 @@ static int acp3x_i2s_trigger(struct snd_pcm_substream *substream, mmACP_BT_TX_INTR_WATERMARK_SIZE; reg_val = mmACP_BTTDM_ITER; ier_val = mmACP_BTTDM_IER; + buf_reg = mmACP_BT_TX_RINGBUFSIZE; break; case I2S_SP_INSTANCE: default: @@ -203,6 +207,7 @@ static int acp3x_i2s_trigger(struct snd_pcm_substream *substream, mmACP_I2S_TX_INTR_WATERMARK_SIZE; reg_val = mmACP_I2STDM_ITER; ier_val = mmACP_I2STDM_IER; + buf_reg = mmACP_I2S_TX_RINGBUFSIZE; } } else { switch (rtd->i2s_instance) { @@ -211,6 +216,7 @@ static int acp3x_i2s_trigger(struct snd_pcm_substream *substream, mmACP_BT_RX_INTR_WATERMARK_SIZE; reg_val = mmACP_BTTDM_IRER; ier_val = mmACP_BTTDM_IER; + buf_reg = mmACP_BT_RX_RINGBUFSIZE; break; case I2S_SP_INSTANCE: default: @@ -218,9 +224,11 @@ static int acp3x_i2s_trigger(struct snd_pcm_substream *substream, mmACP_I2S_RX_INTR_WATERMARK_SIZE; reg_val = mmACP_I2STDM_IRER; ier_val = mmACP_I2STDM_IER; + buf_reg = mmACP_I2S_RX_RINGBUFSIZE; } } rv_writel(period_bytes, rtd->acp3x_base + water_val); + rv_writel(buf_size, rtd->acp3x_base + buf_reg); val = rv_readl(rtd->acp3x_base + reg_val); val = val | BIT(0); rv_writel(val, rtd->acp3x_base + reg_val); diff --git a/sound/soc/amd/raven/acp3x-pcm-dma.c b/sound/soc/amd/raven/acp3x-pcm-dma.c index aecc3c061679..d62c0d90c41e 100644 --- a/sound/soc/amd/raven/acp3x-pcm-dma.c +++ b/sound/soc/amd/raven/acp3x-pcm-dma.c @@ -110,7 +110,7 @@ static void config_acp3x_dma(struct i2s_stream_instance *rtd, int direction) { u16 page_idx; u32 low, high, val, acp_fifo_addr, reg_fifo_addr; - u32 reg_ringbuf_size, reg_dma_size, reg_fifo_size; + u32 reg_dma_size, reg_fifo_size; dma_addr_t addr; addr = rtd->dma_addr; @@ -157,7 +157,6 @@ static void config_acp3x_dma(struct i2s_stream_instance *rtd, int direction) if (direction == SNDRV_PCM_STREAM_PLAYBACK) { switch (rtd->i2s_instance) { case I2S_BT_INSTANCE: - reg_ringbuf_size = mmACP_BT_TX_RINGBUFSIZE; reg_dma_size = mmACP_BT_TX_DMA_SIZE; acp_fifo_addr = ACP_SRAM_PTE_OFFSET + BT_PB_FIFO_ADDR_OFFSET; @@ -169,7 +168,6 @@ static void config_acp3x_dma(struct i2s_stream_instance *rtd, int direction) case I2S_SP_INSTANCE: default: - reg_ringbuf_size = mmACP_I2S_TX_RINGBUFSIZE; reg_dma_size = mmACP_I2S_TX_DMA_SIZE; acp_fifo_addr = ACP_SRAM_PTE_OFFSET + SP_PB_FIFO_ADDR_OFFSET; @@ -181,7 +179,6 @@ static void config_acp3x_dma(struct i2s_stream_instance *rtd, int direction) } else { switch (rtd->i2s_instance) { case I2S_BT_INSTANCE: - reg_ringbuf_size = mmACP_BT_RX_RINGBUFSIZE; reg_dma_size = mmACP_BT_RX_DMA_SIZE; acp_fifo_addr = ACP_SRAM_PTE_OFFSET + BT_CAPT_FIFO_ADDR_OFFSET; @@ -193,7 +190,6 @@ static void config_acp3x_dma(struct i2s_stream_instance *rtd, int direction) case I2S_SP_INSTANCE: default: - reg_ringbuf_size = mmACP_I2S_RX_RINGBUFSIZE; reg_dma_size = mmACP_I2S_RX_DMA_SIZE; acp_fifo_addr = ACP_SRAM_PTE_OFFSET + SP_CAPT_FIFO_ADDR_OFFSET; @@ -203,7 +199,6 @@ static void config_acp3x_dma(struct i2s_stream_instance *rtd, int direction) rtd->acp3x_base + mmACP_I2S_RX_RINGBUFADDR); } } - rv_writel(MAX_BUFFER, rtd->acp3x_base + reg_ringbuf_size); rv_writel(DMA_SIZE, rtd->acp3x_base + reg_dma_size); rv_writel(acp_fifo_addr, rtd->acp3x_base + reg_fifo_addr); rv_writel(FIFO_SIZE, rtd->acp3x_base + reg_fifo_size); diff --git a/sound/soc/amd/raven/pci-acp3x.c b/sound/soc/amd/raven/pci-acp3x.c index 65330bb50e74..da60e2ec5535 100644 --- a/sound/soc/amd/raven/pci-acp3x.c +++ b/sound/soc/amd/raven/pci-acp3x.c @@ -45,23 +45,6 @@ static int acp3x_power_on(void __iomem *acp3x_base) return -ETIMEDOUT; } -static int acp3x_power_off(void __iomem *acp3x_base) -{ - u32 val; - int timeout; - - rv_writel(ACP_PGFSM_CNTL_POWER_OFF_MASK, - acp3x_base + mmACP_PGFSM_CONTROL); - timeout = 0; - while (++timeout < 500) { - val = rv_readl(acp3x_base + mmACP_PGFSM_STATUS); - if ((val & ACP_PGFSM_STATUS_MASK) == ACP_POWERED_OFF) - return 0; - udelay(1); - } - return -ETIMEDOUT; -} - static int acp3x_reset(void __iomem *acp3x_base) { u32 val; @@ -115,12 +98,6 @@ static int acp3x_deinit(void __iomem *acp3x_base) pr_err("ACP3x reset failed\n"); return ret; } - /* power off */ - ret = acp3x_power_off(acp3x_base); - if (ret) { - pr_err("ACP3x power off failed\n"); - return ret; - } return 0; } diff --git a/sound/soc/atmel/Kconfig b/sound/soc/atmel/Kconfig index d1dc8e6366dc..71f2d42188c4 100644 --- a/sound/soc/atmel/Kconfig +++ b/sound/soc/atmel/Kconfig @@ -10,11 +10,11 @@ config SND_ATMEL_SOC if SND_ATMEL_SOC config SND_ATMEL_SOC_PDC - tristate + bool depends on HAS_DMA config SND_ATMEL_SOC_DMA - tristate + bool select SND_SOC_GENERIC_DMAENGINE_PCM config SND_ATMEL_SOC_SSC diff --git a/sound/soc/atmel/Makefile b/sound/soc/atmel/Makefile index 1f6890ed3738..c7d2989791be 100644 --- a/sound/soc/atmel/Makefile +++ b/sound/soc/atmel/Makefile @@ -6,8 +6,14 @@ snd-soc-atmel_ssc_dai-objs := atmel_ssc_dai.o snd-soc-atmel-i2s-objs := atmel-i2s.o snd-soc-mchp-i2s-mcc-objs := mchp-i2s-mcc.o -obj-$(CONFIG_SND_ATMEL_SOC_PDC) += snd-soc-atmel-pcm-pdc.o -obj-$(CONFIG_SND_ATMEL_SOC_DMA) += snd-soc-atmel-pcm-dma.o +# pdc and dma need to both be built-in if any user of +# ssc is built-in. +ifdef CONFIG_SND_ATMEL_SOC_PDC +obj-$(CONFIG_SND_ATMEL_SOC_SSC) += snd-soc-atmel-pcm-pdc.o +endif +ifdef CONFIG_SND_ATMEL_SOC_DMA +obj-$(CONFIG_SND_ATMEL_SOC_SSC) += snd-soc-atmel-pcm-dma.o +endif obj-$(CONFIG_SND_ATMEL_SOC_SSC) += snd-soc-atmel_ssc_dai.o obj-$(CONFIG_SND_ATMEL_SOC_I2S) += snd-soc-atmel-i2s.o obj-$(CONFIG_SND_MCHP_SOC_I2S_MCC) += snd-soc-mchp-i2s-mcc.o diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c index 444cc4e3374e..f005751da2cc 100644 --- a/sound/soc/codecs/hdmi-codec.c +++ b/sound/soc/codecs/hdmi-codec.c @@ -779,7 +779,17 @@ static int hdmi_of_xlate_dai_id(struct snd_soc_component *component, return ret; } +static void hdmi_remove(struct snd_soc_component *component) +{ + struct hdmi_codec_priv *hcp = snd_soc_component_get_drvdata(component); + + if (hcp->hcd.ops->hook_plugged_cb) + hcp->hcd.ops->hook_plugged_cb(component->dev->parent, + hcp->hcd.data, NULL, NULL); +} + static const struct snd_soc_component_driver hdmi_driver = { + .remove = hdmi_remove, .dapm_widgets = hdmi_widgets, .num_dapm_widgets = ARRAY_SIZE(hdmi_widgets), .of_xlate_dai_id = hdmi_of_xlate_dai_id, diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c index 5bc2c6411b33..032adc14562d 100644 --- a/sound/soc/codecs/max98090.c +++ b/sound/soc/codecs/max98090.c @@ -5,150 +5,24 @@ * Copyright 2011-2012 Maxim Integrated Products */ -#include <linux/acpi.h> -#include <linux/clk.h> #include <linux/delay.h> #include <linux/i2c.h> #include <linux/module.h> -#include <linux/mutex.h> #include <linux/of.h> #include <linux/pm.h> #include <linux/pm_runtime.h> #include <linux/regmap.h> #include <linux/slab.h> +#include <linux/acpi.h> +#include <linux/clk.h> #include <sound/jack.h> -#include <sound/max98090.h> #include <sound/pcm.h> #include <sound/pcm_params.h> #include <sound/soc.h> #include <sound/tlv.h> +#include <sound/max98090.h> #include "max98090.h" -static void max98090_shdn_save_locked(struct max98090_priv *max98090) -{ - int shdn = 0; - - /* saved_shdn, saved_count, SHDN are protected by card->dapm_mutex */ - regmap_read(max98090->regmap, M98090_REG_DEVICE_SHUTDOWN, &shdn); - max98090->saved_shdn |= shdn; - ++max98090->saved_count; - - if (shdn) - regmap_write(max98090->regmap, M98090_REG_DEVICE_SHUTDOWN, 0x0); -} - -static void max98090_shdn_restore_locked(struct max98090_priv *max98090) -{ - /* saved_shdn, saved_count, SHDN are protected by card->dapm_mutex */ - if (--max98090->saved_count == 0) { - if (max98090->saved_shdn) { - regmap_write(max98090->regmap, - M98090_REG_DEVICE_SHUTDOWN, - M98090_SHDNN_MASK); - max98090->saved_shdn = 0; - } - } -} - -static void max98090_shdn_save(struct max98090_priv *max98090) -{ - mutex_lock_nested(&max98090->component->card->dapm_mutex, - SND_SOC_DAPM_CLASS_RUNTIME); - max98090_shdn_save_locked(max98090); -} - -static void max98090_shdn_restore(struct max98090_priv *max98090) -{ - max98090_shdn_restore_locked(max98090); - mutex_unlock(&max98090->component->card->dapm_mutex); -} - -static int max98090_put_volsw(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - struct snd_soc_component *component = - snd_soc_kcontrol_component(kcontrol); - struct max98090_priv *max98090 = - snd_soc_component_get_drvdata(component); - int ret; - - max98090_shdn_save(max98090); - ret = snd_soc_put_volsw(kcontrol, ucontrol); - max98090_shdn_restore(max98090); - - return ret; -} - -static int max98090_dapm_put_enum_double(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - struct snd_soc_component *component = - snd_soc_dapm_kcontrol_component(kcontrol); - struct max98090_priv *max98090 = - snd_soc_component_get_drvdata(component); - int ret; - - max98090_shdn_save(max98090); - ret = snd_soc_dapm_put_enum_double_locked(kcontrol, ucontrol); - max98090_shdn_restore(max98090); - - return ret; -} - -static int max98090_put_enum_double(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - struct snd_soc_component *component = - snd_soc_kcontrol_component(kcontrol); - struct max98090_priv *max98090 = - snd_soc_component_get_drvdata(component); - int ret; - - max98090_shdn_save(max98090); - ret = snd_soc_put_enum_double(kcontrol, ucontrol); - max98090_shdn_restore(max98090); - - return ret; -} - -static int max98090_bytes_put(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - struct snd_soc_component *component = - snd_soc_kcontrol_component(kcontrol); - struct max98090_priv *max98090 = - snd_soc_component_get_drvdata(component); - int ret; - - max98090_shdn_save(max98090); - ret = snd_soc_bytes_put(kcontrol, ucontrol); - max98090_shdn_restore(max98090); - - return ret; -} - -static int max98090_dapm_event(struct snd_soc_dapm_widget *w, - struct snd_kcontrol *kcontrol, int event) -{ - struct snd_soc_component *component = - snd_soc_dapm_to_component(w->dapm); - struct max98090_priv *max98090 = - snd_soc_component_get_drvdata(component); - - switch (event) { - case SND_SOC_DAPM_PRE_PMU: - case SND_SOC_DAPM_PRE_PMD: - max98090_shdn_save_locked(max98090); - break; - case SND_SOC_DAPM_POST_PMU: - case SND_SOC_DAPM_POST_PMD: - max98090_shdn_restore_locked(max98090); - break; - } - - return 0; -} - /* Allows for sparsely populated register maps */ static const struct reg_default max98090_reg[] = { { 0x00, 0x00 }, /* 00 Software Reset */ @@ -632,13 +506,10 @@ static SOC_ENUM_SINGLE_DECL(max98090_adchp_enum, max98090_pwr_perf_text); static const struct snd_kcontrol_new max98090_snd_controls[] = { - SOC_ENUM_EXT("MIC Bias VCM Bandgap", max98090_vcmbandgap_enum, - snd_soc_get_enum_double, max98090_put_enum_double), + SOC_ENUM("MIC Bias VCM Bandgap", max98090_vcmbandgap_enum), - SOC_SINGLE_EXT("DMIC MIC Comp Filter Config", - M98090_REG_DIGITAL_MIC_CONFIG, - M98090_DMIC_COMP_SHIFT, M98090_DMIC_COMP_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), + SOC_SINGLE("DMIC MIC Comp Filter Config", M98090_REG_DIGITAL_MIC_CONFIG, + M98090_DMIC_COMP_SHIFT, M98090_DMIC_COMP_NUM - 1, 0), SOC_SINGLE_EXT_TLV("MIC1 Boost Volume", M98090_REG_MIC1_INPUT_LEVEL, M98090_MIC_PA1EN_SHIFT, @@ -693,34 +564,24 @@ static const struct snd_kcontrol_new max98090_snd_controls[] = { M98090_AVR_SHIFT, M98090_AVR_NUM - 1, 1, max98090_av_tlv), - SOC_ENUM_EXT("ADC Oversampling Rate", max98090_osr128_enum, - snd_soc_get_enum_double, max98090_put_enum_double), - SOC_SINGLE_EXT("ADC Quantizer Dither", M98090_REG_ADC_CONTROL, - M98090_ADCDITHER_SHIFT, M98090_ADCDITHER_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), - SOC_ENUM_EXT("ADC High Performance Mode", max98090_adchp_enum, - snd_soc_get_enum_double, max98090_put_enum_double), - - SOC_SINGLE_EXT("DAC Mono Mode", M98090_REG_IO_CONFIGURATION, - M98090_DMONO_SHIFT, M98090_DMONO_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), - SOC_SINGLE_EXT("SDIN Mode", M98090_REG_IO_CONFIGURATION, - M98090_SDIEN_SHIFT, M98090_SDIEN_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), - SOC_SINGLE_EXT("SDOUT Mode", M98090_REG_IO_CONFIGURATION, - M98090_SDOEN_SHIFT, M98090_SDOEN_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), - SOC_SINGLE_EXT("SDOUT Hi-Z Mode", M98090_REG_IO_CONFIGURATION, - M98090_HIZOFF_SHIFT, M98090_HIZOFF_NUM - 1, 1, - snd_soc_get_volsw, max98090_put_volsw), - SOC_ENUM_EXT("Filter Mode", max98090_mode_enum, - snd_soc_get_enum_double, max98090_put_enum_double), - SOC_SINGLE_EXT("Record Path DC Blocking", M98090_REG_FILTER_CONFIG, - M98090_AHPF_SHIFT, M98090_AHPF_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), - SOC_SINGLE_EXT("Playback Path DC Blocking", M98090_REG_FILTER_CONFIG, - M98090_DHPF_SHIFT, M98090_DHPF_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), + SOC_ENUM("ADC Oversampling Rate", max98090_osr128_enum), + SOC_SINGLE("ADC Quantizer Dither", M98090_REG_ADC_CONTROL, + M98090_ADCDITHER_SHIFT, M98090_ADCDITHER_NUM - 1, 0), + SOC_ENUM("ADC High Performance Mode", max98090_adchp_enum), + + SOC_SINGLE("DAC Mono Mode", M98090_REG_IO_CONFIGURATION, + M98090_DMONO_SHIFT, M98090_DMONO_NUM - 1, 0), + SOC_SINGLE("SDIN Mode", M98090_REG_IO_CONFIGURATION, + M98090_SDIEN_SHIFT, M98090_SDIEN_NUM - 1, 0), + SOC_SINGLE("SDOUT Mode", M98090_REG_IO_CONFIGURATION, + M98090_SDOEN_SHIFT, M98090_SDOEN_NUM - 1, 0), + SOC_SINGLE("SDOUT Hi-Z Mode", M98090_REG_IO_CONFIGURATION, + M98090_HIZOFF_SHIFT, M98090_HIZOFF_NUM - 1, 1), + SOC_ENUM("Filter Mode", max98090_mode_enum), + SOC_SINGLE("Record Path DC Blocking", M98090_REG_FILTER_CONFIG, + M98090_AHPF_SHIFT, M98090_AHPF_NUM - 1, 0), + SOC_SINGLE("Playback Path DC Blocking", M98090_REG_FILTER_CONFIG, + M98090_DHPF_SHIFT, M98090_DHPF_NUM - 1, 0), SOC_SINGLE_TLV("Digital BQ Volume", M98090_REG_ADC_BIQUAD_LEVEL, M98090_AVBQ_SHIFT, M98090_AVBQ_NUM - 1, 1, max98090_dv_tlv), SOC_SINGLE_EXT_TLV("Digital Sidetone Volume", @@ -733,17 +594,13 @@ static const struct snd_kcontrol_new max98090_snd_controls[] = { SOC_SINGLE_TLV("Digital Volume", M98090_REG_DAI_PLAYBACK_LEVEL, M98090_DV_SHIFT, M98090_DV_NUM - 1, 1, max98090_dv_tlv), - SND_SOC_BYTES_E("EQ Coefficients", M98090_REG_EQUALIZER_BASE, 105, - snd_soc_bytes_get, max98090_bytes_put), - SOC_SINGLE_EXT("Digital EQ 3 Band Switch", M98090_REG_DSP_FILTER_ENABLE, - M98090_EQ3BANDEN_SHIFT, M98090_EQ3BANDEN_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), - SOC_SINGLE_EXT("Digital EQ 5 Band Switch", M98090_REG_DSP_FILTER_ENABLE, - M98090_EQ5BANDEN_SHIFT, M98090_EQ5BANDEN_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), - SOC_SINGLE_EXT("Digital EQ 7 Band Switch", M98090_REG_DSP_FILTER_ENABLE, - M98090_EQ7BANDEN_SHIFT, M98090_EQ7BANDEN_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), + SND_SOC_BYTES("EQ Coefficients", M98090_REG_EQUALIZER_BASE, 105), + SOC_SINGLE("Digital EQ 3 Band Switch", M98090_REG_DSP_FILTER_ENABLE, + M98090_EQ3BANDEN_SHIFT, M98090_EQ3BANDEN_NUM - 1, 0), + SOC_SINGLE("Digital EQ 5 Band Switch", M98090_REG_DSP_FILTER_ENABLE, + M98090_EQ5BANDEN_SHIFT, M98090_EQ5BANDEN_NUM - 1, 0), + SOC_SINGLE("Digital EQ 7 Band Switch", M98090_REG_DSP_FILTER_ENABLE, + M98090_EQ7BANDEN_SHIFT, M98090_EQ7BANDEN_NUM - 1, 0), SOC_SINGLE("Digital EQ Clipping Detection", M98090_REG_DAI_PLAYBACK_LEVEL_EQ, M98090_EQCLPN_SHIFT, M98090_EQCLPN_NUM - 1, 1), @@ -751,34 +608,25 @@ static const struct snd_kcontrol_new max98090_snd_controls[] = { M98090_DVEQ_SHIFT, M98090_DVEQ_NUM - 1, 1, max98090_dv_tlv), - SOC_SINGLE_EXT("ALC Enable", M98090_REG_DRC_TIMING, - M98090_DRCEN_SHIFT, M98090_DRCEN_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), - SOC_ENUM_EXT("ALC Attack Time", max98090_drcatk_enum, - snd_soc_get_enum_double, max98090_put_enum_double), - SOC_ENUM_EXT("ALC Release Time", max98090_drcrls_enum, - snd_soc_get_enum_double, max98090_put_enum_double), + SOC_SINGLE("ALC Enable", M98090_REG_DRC_TIMING, + M98090_DRCEN_SHIFT, M98090_DRCEN_NUM - 1, 0), + SOC_ENUM("ALC Attack Time", max98090_drcatk_enum), + SOC_ENUM("ALC Release Time", max98090_drcrls_enum), SOC_SINGLE_TLV("ALC Make Up Volume", M98090_REG_DRC_GAIN, M98090_DRCG_SHIFT, M98090_DRCG_NUM - 1, 0, max98090_alcmakeup_tlv), - SOC_ENUM_EXT("ALC Compression Ratio", max98090_alccmp_enum, - snd_soc_get_enum_double, max98090_put_enum_double), - SOC_ENUM_EXT("ALC Expansion Ratio", max98090_drcexp_enum, - snd_soc_get_enum_double, max98090_put_enum_double), - SOC_SINGLE_EXT_TLV("ALC Compression Threshold Volume", + SOC_ENUM("ALC Compression Ratio", max98090_alccmp_enum), + SOC_ENUM("ALC Expansion Ratio", max98090_drcexp_enum), + SOC_SINGLE_TLV("ALC Compression Threshold Volume", M98090_REG_DRC_COMPRESSOR, M98090_DRCTHC_SHIFT, - M98090_DRCTHC_NUM - 1, 1, - snd_soc_get_volsw, max98090_put_volsw, max98090_alccomp_tlv), - SOC_SINGLE_EXT_TLV("ALC Expansion Threshold Volume", + M98090_DRCTHC_NUM - 1, 1, max98090_alccomp_tlv), + SOC_SINGLE_TLV("ALC Expansion Threshold Volume", M98090_REG_DRC_EXPANDER, M98090_DRCTHE_SHIFT, - M98090_DRCTHE_NUM - 1, 1, - snd_soc_get_volsw, max98090_put_volsw, max98090_drcexp_tlv), + M98090_DRCTHE_NUM - 1, 1, max98090_drcexp_tlv), - SOC_ENUM_EXT("DAC HP Playback Performance Mode", - max98090_dac_perfmode_enum, - snd_soc_get_enum_double, max98090_put_enum_double), - SOC_ENUM_EXT("DAC High Performance Mode", max98090_dachp_enum, - snd_soc_get_enum_double, max98090_put_enum_double), + SOC_ENUM("DAC HP Playback Performance Mode", + max98090_dac_perfmode_enum), + SOC_ENUM("DAC High Performance Mode", max98090_dachp_enum), SOC_SINGLE_TLV("Headphone Left Mixer Volume", M98090_REG_HP_CONTROL, M98090_MIXHPLG_SHIFT, @@ -836,12 +684,9 @@ static const struct snd_kcontrol_new max98090_snd_controls[] = { SOC_SINGLE("Volume Adjustment Smoothing", M98090_REG_LEVEL_CONTROL, M98090_VSENN_SHIFT, M98090_VSENN_NUM - 1, 1), - SND_SOC_BYTES_E("Biquad Coefficients", - M98090_REG_RECORD_BIQUAD_BASE, 15, - snd_soc_bytes_get, max98090_bytes_put), - SOC_SINGLE_EXT("Biquad Switch", M98090_REG_DSP_FILTER_ENABLE, - M98090_ADCBQEN_SHIFT, M98090_ADCBQEN_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), + SND_SOC_BYTES("Biquad Coefficients", M98090_REG_RECORD_BIQUAD_BASE, 15), + SOC_SINGLE("Biquad Switch", M98090_REG_DSP_FILTER_ENABLE, + M98090_ADCBQEN_SHIFT, M98090_ADCBQEN_NUM - 1, 0), }; static const struct snd_kcontrol_new max98091_snd_controls[] = { @@ -850,12 +695,10 @@ static const struct snd_kcontrol_new max98091_snd_controls[] = { M98090_DMIC34_ZEROPAD_SHIFT, M98090_DMIC34_ZEROPAD_NUM - 1, 0), - SOC_ENUM_EXT("Filter DMIC34 Mode", max98090_filter_dmic34mode_enum, - snd_soc_get_enum_double, max98090_put_enum_double), - SOC_SINGLE_EXT("DMIC34 DC Blocking", M98090_REG_FILTER_CONFIG, + SOC_ENUM("Filter DMIC34 Mode", max98090_filter_dmic34mode_enum), + SOC_SINGLE("DMIC34 DC Blocking", M98090_REG_FILTER_CONFIG, M98090_FLT_DMIC34HPF_SHIFT, - M98090_FLT_DMIC34HPF_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), + M98090_FLT_DMIC34HPF_NUM - 1, 0), SOC_SINGLE_TLV("DMIC3 Boost Volume", M98090_REG_DMIC3_VOLUME, M98090_DMIC_AV3G_SHIFT, M98090_DMIC_AV3G_NUM - 1, 0, @@ -873,9 +716,8 @@ static const struct snd_kcontrol_new max98091_snd_controls[] = { SND_SOC_BYTES("DMIC34 Biquad Coefficients", M98090_REG_DMIC34_BIQUAD_BASE, 15), - SOC_SINGLE_EXT("DMIC34 Biquad Switch", M98090_REG_DSP_FILTER_ENABLE, - M98090_DMIC34BQEN_SHIFT, M98090_DMIC34BQEN_NUM - 1, 0, - snd_soc_get_volsw, max98090_put_volsw), + SOC_SINGLE("DMIC34 Biquad Switch", M98090_REG_DSP_FILTER_ENABLE, + M98090_DMIC34BQEN_SHIFT, M98090_DMIC34BQEN_NUM - 1, 0), SOC_SINGLE_TLV("DMIC34 BQ PreAttenuation Volume", M98090_REG_DMIC34_BQ_PREATTEN, M98090_AV34BQ_SHIFT, @@ -929,6 +771,19 @@ static int max98090_micinput_event(struct snd_soc_dapm_widget *w, return 0; } +static int max98090_shdn_event(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *kcontrol, int event) +{ + struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm); + struct max98090_priv *max98090 = snd_soc_component_get_drvdata(component); + + if (event & SND_SOC_DAPM_POST_PMU) + max98090->shdn_pending = true; + + return 0; + +} + static const char *mic1_mux_text[] = { "IN12", "IN56" }; static SOC_ENUM_SINGLE_DECL(mic1_mux_enum, @@ -1029,14 +884,10 @@ static SOC_ENUM_SINGLE_DECL(ltenr_mux_enum, lten_mux_text); static const struct snd_kcontrol_new max98090_ltenl_mux = - SOC_DAPM_ENUM_EXT("LTENL Mux", ltenl_mux_enum, - snd_soc_dapm_get_enum_double, - max98090_dapm_put_enum_double); + SOC_DAPM_ENUM("LTENL Mux", ltenl_mux_enum); static const struct snd_kcontrol_new max98090_ltenr_mux = - SOC_DAPM_ENUM_EXT("LTENR Mux", ltenr_mux_enum, - snd_soc_dapm_get_enum_double, - max98090_dapm_put_enum_double); + SOC_DAPM_ENUM("LTENR Mux", ltenr_mux_enum); static const char *lben_mux_text[] = { "Normal", "Loopback" }; @@ -1051,14 +902,10 @@ static SOC_ENUM_SINGLE_DECL(lbenr_mux_enum, lben_mux_text); static const struct snd_kcontrol_new max98090_lbenl_mux = - SOC_DAPM_ENUM_EXT("LBENL Mux", lbenl_mux_enum, - snd_soc_dapm_get_enum_double, - max98090_dapm_put_enum_double); + SOC_DAPM_ENUM("LBENL Mux", lbenl_mux_enum); static const struct snd_kcontrol_new max98090_lbenr_mux = - SOC_DAPM_ENUM_EXT("LBENR Mux", lbenr_mux_enum, - snd_soc_dapm_get_enum_double, - max98090_dapm_put_enum_double); + SOC_DAPM_ENUM("LBENR Mux", lbenr_mux_enum); static const char *stenl_mux_text[] = { "Normal", "Sidetone Left" }; @@ -1225,25 +1072,21 @@ static const struct snd_soc_dapm_widget max98090_dapm_widgets[] = { SND_SOC_DAPM_INPUT("IN56"), SND_SOC_DAPM_SUPPLY("MICBIAS", M98090_REG_INPUT_ENABLE, - M98090_MBEN_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + M98090_MBEN_SHIFT, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("SHDN", M98090_REG_DEVICE_SHUTDOWN, M98090_SHDNN_SHIFT, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("SDIEN", M98090_REG_IO_CONFIGURATION, - M98090_SDIEN_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + M98090_SDIEN_SHIFT, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("SDOEN", M98090_REG_IO_CONFIGURATION, - M98090_SDOEN_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + M98090_SDOEN_SHIFT, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("DMICL_ENA", M98090_REG_DIGITAL_MIC_ENABLE, - M98090_DIGMICL_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + M98090_DIGMICL_SHIFT, 0, max98090_shdn_event, + SND_SOC_DAPM_POST_PMU), SND_SOC_DAPM_SUPPLY("DMICR_ENA", M98090_REG_DIGITAL_MIC_ENABLE, - M98090_DIGMICR_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + M98090_DIGMICR_SHIFT, 0, max98090_shdn_event, + SND_SOC_DAPM_POST_PMU), SND_SOC_DAPM_SUPPLY("AHPF", M98090_REG_FILTER_CONFIG, - M98090_AHPF_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + M98090_AHPF_SHIFT, 0, NULL, 0), /* * Note: Sysclk and misc power supplies are taken care of by SHDN @@ -1273,12 +1116,10 @@ static const struct snd_soc_dapm_widget max98090_dapm_widgets[] = { &max98090_lineb_mixer_controls[0], ARRAY_SIZE(max98090_lineb_mixer_controls)), - SND_SOC_DAPM_PGA_E("LINEA Input", M98090_REG_INPUT_ENABLE, - M98090_LINEAEN_SHIFT, 0, NULL, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), - SND_SOC_DAPM_PGA_E("LINEB Input", M98090_REG_INPUT_ENABLE, - M98090_LINEBEN_SHIFT, 0, NULL, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + SND_SOC_DAPM_PGA("LINEA Input", M98090_REG_INPUT_ENABLE, + M98090_LINEAEN_SHIFT, 0, NULL, 0), + SND_SOC_DAPM_PGA("LINEB Input", M98090_REG_INPUT_ENABLE, + M98090_LINEBEN_SHIFT, 0, NULL, 0), SND_SOC_DAPM_MIXER("Left ADC Mixer", SND_SOC_NOPM, 0, 0, &max98090_left_adc_mixer_controls[0], @@ -1289,11 +1130,11 @@ static const struct snd_soc_dapm_widget max98090_dapm_widgets[] = { ARRAY_SIZE(max98090_right_adc_mixer_controls)), SND_SOC_DAPM_ADC_E("ADCL", NULL, M98090_REG_INPUT_ENABLE, - M98090_ADLEN_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + M98090_ADLEN_SHIFT, 0, max98090_shdn_event, + SND_SOC_DAPM_POST_PMU), SND_SOC_DAPM_ADC_E("ADCR", NULL, M98090_REG_INPUT_ENABLE, - M98090_ADREN_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + M98090_ADREN_SHIFT, 0, max98090_shdn_event, + SND_SOC_DAPM_POST_PMU), SND_SOC_DAPM_AIF_OUT("AIFOUTL", "HiFi Capture", 0, SND_SOC_NOPM, 0, 0), @@ -1321,12 +1162,10 @@ static const struct snd_soc_dapm_widget max98090_dapm_widgets[] = { SND_SOC_DAPM_AIF_IN("AIFINL", "HiFi Playback", 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("AIFINR", "HiFi Playback", 1, SND_SOC_NOPM, 0, 0), - SND_SOC_DAPM_DAC_E("DACL", NULL, M98090_REG_OUTPUT_ENABLE, - M98090_DALEN_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), - SND_SOC_DAPM_DAC_E("DACR", NULL, M98090_REG_OUTPUT_ENABLE, - M98090_DAREN_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + SND_SOC_DAPM_DAC("DACL", NULL, M98090_REG_OUTPUT_ENABLE, + M98090_DALEN_SHIFT, 0), + SND_SOC_DAPM_DAC("DACR", NULL, M98090_REG_OUTPUT_ENABLE, + M98090_DAREN_SHIFT, 0), SND_SOC_DAPM_MIXER("Left Headphone Mixer", SND_SOC_NOPM, 0, 0, &max98090_left_hp_mixer_controls[0], @@ -1361,26 +1200,20 @@ static const struct snd_soc_dapm_widget max98090_dapm_widgets[] = { SND_SOC_DAPM_MUX("MIXHPRSEL Mux", SND_SOC_NOPM, 0, 0, &max98090_mixhprsel_mux), - SND_SOC_DAPM_PGA_E("HP Left Out", M98090_REG_OUTPUT_ENABLE, - M98090_HPLEN_SHIFT, 0, NULL, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), - SND_SOC_DAPM_PGA_E("HP Right Out", M98090_REG_OUTPUT_ENABLE, - M98090_HPREN_SHIFT, 0, NULL, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), - - SND_SOC_DAPM_PGA_E("SPK Left Out", M98090_REG_OUTPUT_ENABLE, - M98090_SPLEN_SHIFT, 0, NULL, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), - SND_SOC_DAPM_PGA_E("SPK Right Out", M98090_REG_OUTPUT_ENABLE, - M98090_SPREN_SHIFT, 0, NULL, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), - - SND_SOC_DAPM_PGA_E("RCV Left Out", M98090_REG_OUTPUT_ENABLE, - M98090_RCVLEN_SHIFT, 0, NULL, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), - SND_SOC_DAPM_PGA_E("RCV Right Out", M98090_REG_OUTPUT_ENABLE, - M98090_RCVREN_SHIFT, 0, NULL, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + SND_SOC_DAPM_PGA("HP Left Out", M98090_REG_OUTPUT_ENABLE, + M98090_HPLEN_SHIFT, 0, NULL, 0), + SND_SOC_DAPM_PGA("HP Right Out", M98090_REG_OUTPUT_ENABLE, + M98090_HPREN_SHIFT, 0, NULL, 0), + + SND_SOC_DAPM_PGA("SPK Left Out", M98090_REG_OUTPUT_ENABLE, + M98090_SPLEN_SHIFT, 0, NULL, 0), + SND_SOC_DAPM_PGA("SPK Right Out", M98090_REG_OUTPUT_ENABLE, + M98090_SPREN_SHIFT, 0, NULL, 0), + + SND_SOC_DAPM_PGA("RCV Left Out", M98090_REG_OUTPUT_ENABLE, + M98090_RCVLEN_SHIFT, 0, NULL, 0), + SND_SOC_DAPM_PGA("RCV Right Out", M98090_REG_OUTPUT_ENABLE, + M98090_RCVREN_SHIFT, 0, NULL, 0), SND_SOC_DAPM_OUTPUT("HPL"), SND_SOC_DAPM_OUTPUT("HPR"), @@ -1395,11 +1228,9 @@ static const struct snd_soc_dapm_widget max98091_dapm_widgets[] = { SND_SOC_DAPM_INPUT("DMIC4"), SND_SOC_DAPM_SUPPLY("DMIC3_ENA", M98090_REG_DIGITAL_MIC_ENABLE, - M98090_DIGMIC3_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + M98090_DIGMIC3_SHIFT, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("DMIC4_ENA", M98090_REG_DIGITAL_MIC_ENABLE, - M98090_DIGMIC4_SHIFT, 0, max98090_dapm_event, - SND_SOC_DAPM_PRE_POST_PMU | SND_SOC_DAPM_PRE_POST_PMD), + M98090_DIGMIC4_SHIFT, 0, NULL, 0), }; static const struct snd_soc_dapm_route max98090_dapm_routes[] = { @@ -1670,11 +1501,6 @@ static void max98090_configure_bclk(struct snd_soc_component *component) return; } - /* - * Master mode: no need to save and restore SHDN for the following - * sensitive registers. - */ - /* Check for supported PCLK to LRCLK ratios */ for (i = 0; i < ARRAY_SIZE(pclk_rates); i++) { if ((pclk_rates[i] == max98090->sysclk) && @@ -1761,14 +1587,12 @@ static int max98090_dai_set_fmt(struct snd_soc_dai *codec_dai, switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) { case SND_SOC_DAIFMT_CBS_CFS: /* Set to slave mode PLL - MAS mode off */ - max98090_shdn_save(max98090); snd_soc_component_write(component, M98090_REG_CLOCK_RATIO_NI_MSB, 0x00); snd_soc_component_write(component, M98090_REG_CLOCK_RATIO_NI_LSB, 0x00); snd_soc_component_update_bits(component, M98090_REG_CLOCK_MODE, M98090_USE_M1_MASK, 0); - max98090_shdn_restore(max98090); max98090->master = false; break; case SND_SOC_DAIFMT_CBM_CFM: @@ -1794,9 +1618,7 @@ static int max98090_dai_set_fmt(struct snd_soc_dai *codec_dai, dev_err(component->dev, "DAI clock mode unsupported"); return -EINVAL; } - max98090_shdn_save(max98090); snd_soc_component_write(component, M98090_REG_MASTER_MODE, regval); - max98090_shdn_restore(max98090); regval = 0; switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) { @@ -1841,10 +1663,8 @@ static int max98090_dai_set_fmt(struct snd_soc_dai *codec_dai, if (max98090->tdm_slots > 1) regval ^= M98090_BCI_MASK; - max98090_shdn_save(max98090); snd_soc_component_write(component, M98090_REG_INTERFACE_FORMAT, regval); - max98090_shdn_restore(max98090); } return 0; @@ -1856,7 +1676,6 @@ static int max98090_set_tdm_slot(struct snd_soc_dai *codec_dai, struct snd_soc_component *component = codec_dai->component; struct max98090_priv *max98090 = snd_soc_component_get_drvdata(component); struct max98090_cdata *cdata; - cdata = &max98090->dai[0]; if (slots < 0 || slots > 4) @@ -1866,7 +1685,6 @@ static int max98090_set_tdm_slot(struct snd_soc_dai *codec_dai, max98090->tdm_width = slot_width; if (max98090->tdm_slots > 1) { - max98090_shdn_save(max98090); /* SLOTL SLOTR SLOTDLY */ snd_soc_component_write(component, M98090_REG_TDM_FORMAT, 0 << M98090_TDM_SLOTL_SHIFT | @@ -1877,7 +1695,6 @@ static int max98090_set_tdm_slot(struct snd_soc_dai *codec_dai, snd_soc_component_update_bits(component, M98090_REG_TDM_CONTROL, M98090_TDM_MASK, M98090_TDM_MASK); - max98090_shdn_restore(max98090); } /* @@ -2077,7 +1894,6 @@ static int max98090_configure_dmic(struct max98090_priv *max98090, dmic_freq = dmic_table[pclk_index].settings[micclk_index].freq; dmic_comp = dmic_table[pclk_index].settings[micclk_index].comp[i]; - max98090_shdn_save(max98090); regmap_update_bits(max98090->regmap, M98090_REG_DIGITAL_MIC_ENABLE, M98090_MICCLK_MASK, micclk_index << M98090_MICCLK_SHIFT); @@ -2086,7 +1902,6 @@ static int max98090_configure_dmic(struct max98090_priv *max98090, M98090_DMIC_COMP_MASK | M98090_DMIC_FREQ_MASK, dmic_comp << M98090_DMIC_COMP_SHIFT | dmic_freq << M98090_DMIC_FREQ_SHIFT); - max98090_shdn_restore(max98090); return 0; } @@ -2123,10 +1938,8 @@ static int max98090_dai_hw_params(struct snd_pcm_substream *substream, switch (params_width(params)) { case 16: - max98090_shdn_save(max98090); snd_soc_component_update_bits(component, M98090_REG_INTERFACE_FORMAT, M98090_WS_MASK, 0); - max98090_shdn_restore(max98090); break; default: return -EINVAL; @@ -2137,7 +1950,6 @@ static int max98090_dai_hw_params(struct snd_pcm_substream *substream, cdata->rate = max98090->lrclk; - max98090_shdn_save(max98090); /* Update filter mode */ if (max98090->lrclk < 24000) snd_soc_component_update_bits(component, M98090_REG_FILTER_CONFIG, @@ -2153,7 +1965,6 @@ static int max98090_dai_hw_params(struct snd_pcm_substream *substream, else snd_soc_component_update_bits(component, M98090_REG_FILTER_CONFIG, M98090_DHF_MASK, M98090_DHF_MASK); - max98090_shdn_restore(max98090); max98090_configure_dmic(max98090, max98090->dmic_freq, max98090->pclk, max98090->lrclk); @@ -2184,7 +1995,6 @@ static int max98090_dai_set_sysclk(struct snd_soc_dai *dai, * 0x02 (when master clk is 20MHz to 40MHz).. * 0x03 (when master clk is 40MHz to 60MHz).. */ - max98090_shdn_save(max98090); if ((freq >= 10000000) && (freq <= 20000000)) { snd_soc_component_write(component, M98090_REG_SYSTEM_CLOCK, M98090_PSCLK_DIV1); @@ -2199,10 +2009,8 @@ static int max98090_dai_set_sysclk(struct snd_soc_dai *dai, max98090->pclk = freq >> 2; } else { dev_err(component->dev, "Invalid master clock frequency\n"); - max98090_shdn_restore(max98090); return -EINVAL; } - max98090_shdn_restore(max98090); max98090->sysclk = freq; @@ -2314,12 +2122,10 @@ static void max98090_pll_work(struct max98090_priv *max98090) */ /* Toggle shutdown OFF then ON */ - mutex_lock(&component->card->dapm_mutex); snd_soc_component_update_bits(component, M98090_REG_DEVICE_SHUTDOWN, M98090_SHDNN_MASK, 0); snd_soc_component_update_bits(component, M98090_REG_DEVICE_SHUTDOWN, M98090_SHDNN_MASK, M98090_SHDNN_MASK); - mutex_unlock(&component->card->dapm_mutex); for (i = 0; i < 10; ++i) { /* Give PLL time to lock */ @@ -2642,12 +2448,7 @@ static int max98090_probe(struct snd_soc_component *component) */ snd_soc_component_read32(component, M98090_REG_DEVICE_STATUS); - /* - * SHDN should be 0 at the point, no need to save/restore for the - * following registers. - * - * High Performance is default - */ + /* High Performance is default */ snd_soc_component_update_bits(component, M98090_REG_DAC_CONTROL, M98090_DACHP_MASK, 1 << M98090_DACHP_SHIFT); @@ -2658,12 +2459,7 @@ static int max98090_probe(struct snd_soc_component *component) M98090_ADCHP_MASK, 1 << M98090_ADCHP_SHIFT); - /* - * SHDN should be 0 at the point, no need to save/restore for the - * following registers. - * - * Turn on VCM bandgap reference - */ + /* Turn on VCM bandgap reference */ snd_soc_component_write(component, M98090_REG_BIAS_CONTROL, M98090_VCM_MODE_MASK); @@ -2695,9 +2491,25 @@ static void max98090_remove(struct snd_soc_component *component) max98090->component = NULL; } +static void max98090_seq_notifier(struct snd_soc_component *component, + enum snd_soc_dapm_type event, int subseq) +{ + struct max98090_priv *max98090 = snd_soc_component_get_drvdata(component); + + if (max98090->shdn_pending) { + snd_soc_component_update_bits(component, M98090_REG_DEVICE_SHUTDOWN, + M98090_SHDNN_MASK, 0); + msleep(40); + snd_soc_component_update_bits(component, M98090_REG_DEVICE_SHUTDOWN, + M98090_SHDNN_MASK, M98090_SHDNN_MASK); + max98090->shdn_pending = false; + } +} + static const struct snd_soc_component_driver soc_component_dev_max98090 = { .probe = max98090_probe, .remove = max98090_remove, + .seq_notifier = max98090_seq_notifier, .set_bias_level = max98090_set_bias_level, .idle_bias_on = 1, .use_pmdown_time = 1, diff --git a/sound/soc/codecs/max98090.h b/sound/soc/codecs/max98090.h index 0a31708b7df7..a197114b0dad 100644 --- a/sound/soc/codecs/max98090.h +++ b/sound/soc/codecs/max98090.h @@ -1539,8 +1539,7 @@ struct max98090_priv { unsigned int pa2en; unsigned int sidetone; bool master; - int saved_count; - int saved_shdn; + bool shdn_pending; }; int max98090_mic_detect(struct snd_soc_component *component, diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index 8c3ea7300972..9d436b0c5718 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -1020,12 +1020,24 @@ static int fsl_sai_probe(struct platform_device *pdev) ret = devm_snd_soc_register_component(&pdev->dev, &fsl_component, &fsl_sai_dai, 1); if (ret) - return ret; + goto err_pm_disable; - if (sai->soc_data->use_imx_pcm) - return imx_pcm_dma_init(pdev, IMX_SAI_DMABUF_SIZE); - else - return devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0); + if (sai->soc_data->use_imx_pcm) { + ret = imx_pcm_dma_init(pdev, IMX_SAI_DMABUF_SIZE); + if (ret) + goto err_pm_disable; + } else { + ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0); + if (ret) + goto err_pm_disable; + } + + return ret; + +err_pm_disable: + pm_runtime_disable(&pdev->dev); + + return ret; } static int fsl_sai_remove(struct platform_device *pdev) diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index bc20ad9abf8b..9b130561d562 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -3441,8 +3441,17 @@ int snd_soc_dapm_get_enum_double(struct snd_kcontrol *kcontrol, } EXPORT_SYMBOL_GPL(snd_soc_dapm_get_enum_double); -static int __snd_soc_dapm_put_enum_double(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol, int locked) +/** + * snd_soc_dapm_put_enum_double - dapm enumerated double mixer set callback + * @kcontrol: mixer control + * @ucontrol: control element information + * + * Callback to set the value of a dapm enumerated double mixer control. + * + * Returns 0 for success. + */ +int snd_soc_dapm_put_enum_double(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) { struct snd_soc_dapm_context *dapm = snd_soc_dapm_kcontrol_dapm(kcontrol); struct snd_soc_card *card = dapm->card; @@ -3465,9 +3474,7 @@ static int __snd_soc_dapm_put_enum_double(struct snd_kcontrol *kcontrol, mask |= e->mask << e->shift_r; } - if (!locked) - mutex_lock_nested(&card->dapm_mutex, - SND_SOC_DAPM_CLASS_RUNTIME); + mutex_lock_nested(&card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); change = dapm_kcontrol_set_value(kcontrol, val); @@ -3489,51 +3496,16 @@ static int __snd_soc_dapm_put_enum_double(struct snd_kcontrol *kcontrol, card->update = NULL; } - if (!locked) - mutex_unlock(&card->dapm_mutex); + mutex_unlock(&card->dapm_mutex); if (ret > 0) soc_dpcm_runtime_update(card); return change; } - -/** - * snd_soc_dapm_put_enum_double - dapm enumerated double mixer set callback - * @kcontrol: mixer control - * @ucontrol: control element information - * - * Callback to set the value of a dapm enumerated double mixer control. - * - * Returns 0 for success. - */ -int snd_soc_dapm_put_enum_double(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - return __snd_soc_dapm_put_enum_double(kcontrol, ucontrol, 0); -} EXPORT_SYMBOL_GPL(snd_soc_dapm_put_enum_double); /** - * snd_soc_dapm_put_enum_double_locked - dapm enumerated double mixer set - * callback - * @kcontrol: mixer control - * @ucontrol: control element information - * - * Callback to set the value of a dapm enumerated double mixer control. - * Must acquire dapm_mutex before calling the function. - * - * Returns 0 for success. - */ -int snd_soc_dapm_put_enum_double_locked(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - dapm_assert_locked(snd_soc_dapm_kcontrol_dapm(kcontrol)); - return __snd_soc_dapm_put_enum_double(kcontrol, ucontrol, 1); -} -EXPORT_SYMBOL_GPL(snd_soc_dapm_put_enum_double_locked); - -/** * snd_soc_dapm_info_pin_switch - Info for a pin switch * * @kcontrol: mixer control @@ -3916,9 +3888,6 @@ snd_soc_dai_link_event_pre_pmu(struct snd_soc_dapm_widget *w, runtime->rate = params_rate(params); out: - if (ret < 0) - kfree(runtime); - kfree(params); return ret; } diff --git a/sound/soc/sof/intel/hda-codec.c b/sound/soc/sof/intel/hda-codec.c index 9106ab8dac6f..ff45075ef720 100644 --- a/sound/soc/sof/intel/hda-codec.c +++ b/sound/soc/sof/intel/hda-codec.c @@ -174,8 +174,10 @@ void hda_codec_i915_display_power(struct snd_sof_dev *sdev, bool enable) { struct hdac_bus *bus = sof_to_bus(sdev); - dev_dbg(bus->dev, "Turning i915 HDAC power %d\n", enable); - snd_hdac_display_power(bus, HDA_CODEC_IDX_CONTROLLER, enable); + if (HDA_IDISP_CODEC(bus->codec_mask)) { + dev_dbg(bus->dev, "Turning i915 HDAC power %d\n", enable); + snd_hdac_display_power(bus, HDA_CODEC_IDX_CONTROLLER, enable); + } } EXPORT_SYMBOL_NS(hda_codec_i915_display_power, SND_SOC_SOF_HDA_AUDIO_CODEC_I915); @@ -189,7 +191,8 @@ int hda_codec_i915_init(struct snd_sof_dev *sdev) if (ret < 0) return ret; - hda_codec_i915_display_power(sdev, true); + /* codec_mask not yet known, power up for probe */ + snd_hdac_display_power(bus, HDA_CODEC_IDX_CONTROLLER, true); return 0; } @@ -200,7 +203,8 @@ int hda_codec_i915_exit(struct snd_sof_dev *sdev) struct hdac_bus *bus = sof_to_bus(sdev); int ret; - hda_codec_i915_display_power(sdev, false); + /* power down unconditionally */ + snd_hdac_display_power(bus, HDA_CODEC_IDX_CONTROLLER, false); ret = snd_hdac_i915_exit(bus); diff --git a/sound/soc/sof/intel/hda-dsp.c b/sound/soc/sof/intel/hda-dsp.c index 4a4d318f97ff..0848b79967a9 100644 --- a/sound/soc/sof/intel/hda-dsp.c +++ b/sound/soc/sof/intel/hda-dsp.c @@ -428,6 +428,9 @@ static int hda_suspend(struct snd_sof_dev *sdev, bool runtime_suspend) return ret; } + /* display codec can powered off after link reset */ + hda_codec_i915_display_power(sdev, false); + return 0; } @@ -439,6 +442,9 @@ static int hda_resume(struct snd_sof_dev *sdev, bool runtime_resume) #endif int ret; + /* display codec must be powered before link reset */ + hda_codec_i915_display_power(sdev, true); + /* * clear TCSEL to clear playback on some HD Audio * codecs. PCI TCSEL is defined in the Intel manuals. @@ -482,6 +488,8 @@ int hda_dsp_resume(struct snd_sof_dev *sdev) struct pci_dev *pci = to_pci_dev(sdev->dev); if (sdev->s0_suspend) { + hda_codec_i915_display_power(sdev, true); + /* restore L1SEN bit */ if (hda->l1_support_changed) snd_sof_dsp_update_bits(sdev, HDA_DSP_HDA_BAR, @@ -531,6 +539,9 @@ int hda_dsp_suspend(struct snd_sof_dev *sdev) int ret; if (sdev->s0_suspend) { + /* we can't keep a wakeref to display driver at suspend */ + hda_codec_i915_display_power(sdev, false); + /* enable L1SEN to make sure the system can enter S0Ix */ hda->l1_support_changed = snd_sof_dsp_update_bits(sdev, HDA_DSP_HDA_BAR, diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c index 65b86dd044f1..25946a1c2822 100644 --- a/sound/soc/sof/intel/hda.c +++ b/sound/soc/sof/intel/hda.c @@ -286,6 +286,13 @@ static int hda_init(struct snd_sof_dev *sdev) /* HDA base */ sdev->bar[HDA_DSP_HDA_BAR] = bus->remap_addr; + /* init i915 and HDMI codecs */ + ret = hda_codec_i915_init(sdev); + if (ret < 0) { + dev_err(sdev->dev, "error: init i915 and HDMI codec failed\n"); + return ret; + } + /* get controller capabilities */ ret = hda_dsp_ctrl_get_caps(sdev); if (ret < 0) @@ -353,15 +360,6 @@ static int hda_init_caps(struct snd_sof_dev *sdev) if (bus->ppcap) dev_dbg(sdev->dev, "PP capability, will probe DSP later.\n"); -#if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA) - /* init i915 and HDMI codecs */ - ret = hda_codec_i915_init(sdev); - if (ret < 0) { - dev_err(sdev->dev, "error: init i915 and HDMI codec failed\n"); - return ret; - } -#endif - /* Init HDA controller after i915 init */ ret = hda_dsp_ctrl_init_chip(sdev, true); if (ret < 0) { @@ -381,7 +379,7 @@ static int hda_init_caps(struct snd_sof_dev *sdev) hda_codec_probe_bus(sdev, hda_codec_use_common_hdmi); if (!HDA_IDISP_CODEC(bus->codec_mask)) - hda_codec_i915_display_power(sdev, false); + hda_codec_i915_exit(sdev); /* * we are done probing so decrement link counts @@ -611,6 +609,7 @@ free_streams: iounmap(sdev->bar[HDA_DSP_BAR]); hdac_bus_unmap: iounmap(bus->remap_addr); + hda_codec_i915_exit(sdev); err: return ret; } diff --git a/sound/soc/sunxi/sun8i-codec.c b/sound/soc/sunxi/sun8i-codec.c index 55798bc8eae2..686561df8e13 100644 --- a/sound/soc/sunxi/sun8i-codec.c +++ b/sound/soc/sunxi/sun8i-codec.c @@ -80,6 +80,7 @@ #define SUN8I_SYS_SR_CTRL_AIF1_FS_MASK GENMASK(15, 12) #define SUN8I_SYS_SR_CTRL_AIF2_FS_MASK GENMASK(11, 8) +#define SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT_MASK GENMASK(3, 2) #define SUN8I_AIF1CLK_CTRL_AIF1_WORD_SIZ_MASK GENMASK(5, 4) #define SUN8I_AIF1CLK_CTRL_AIF1_LRCK_DIV_MASK GENMASK(8, 6) #define SUN8I_AIF1CLK_CTRL_AIF1_BCLK_DIV_MASK GENMASK(12, 9) @@ -241,7 +242,7 @@ static int sun8i_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) return -EINVAL; } regmap_update_bits(scodec->regmap, SUN8I_AIF1CLK_CTRL, - BIT(SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT), + SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT_MASK, value << SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT); return 0; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index f1d74a2bd234..22f235260a3a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1045,9 +1045,9 @@ union bpf_attr { * supports redirection to the egress interface, and accepts no * flag at all. * - * The same effect can be attained with the more generic - * **bpf_redirect_map**\ (), which requires specific maps to be - * used but offers better performance. + * The same effect can also be attained with the more generic + * **bpf_redirect_map**\ (), which uses a BPF map to store the + * redirect target instead of providing it directly to the helper. * Return * For XDP, the helper returns **XDP_REDIRECT** on success or * **XDP_ABORTED** on error. For other program types, the values @@ -1611,13 +1611,11 @@ union bpf_attr { * the caller. Any higher bits in the *flags* argument must be * unset. * - * When used to redirect packets to net devices, this helper - * provides a high performance increase over **bpf_redirect**\ (). - * This is due to various implementation details of the underlying - * mechanisms, one of which is the fact that **bpf_redirect_map**\ - * () tries to send packet as a "bulk" to the device. + * See also bpf_redirect(), which only supports redirecting to an + * ifindex, but doesn't require a map to do so. * Return - * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error. + * **XDP_REDIRECT** on success, or the value of the two lower bits + * of the **flags* argument on error. * * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags) * Description diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 514b1a524abb..7469c7dcc15e 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -24,6 +24,7 @@ #include <endian.h> #include <fcntl.h> #include <errno.h> +#include <ctype.h> #include <asm/unistd.h> #include <linux/err.h> #include <linux/kernel.h> @@ -1283,7 +1284,7 @@ static size_t bpf_map_mmap_sz(const struct bpf_map *map) static char *internal_map_name(struct bpf_object *obj, enum libbpf_map_type type) { - char map_name[BPF_OBJ_NAME_LEN]; + char map_name[BPF_OBJ_NAME_LEN], *p; const char *sfx = libbpf_type_to_btf_name[type]; int sfx_len = max((size_t)7, strlen(sfx)); int pfx_len = min((size_t)BPF_OBJ_NAME_LEN - sfx_len - 1, @@ -1292,6 +1293,11 @@ static char *internal_map_name(struct bpf_object *obj, snprintf(map_name, sizeof(map_name), "%.*s%.*s", pfx_len, obj->name, sfx_len, libbpf_type_to_btf_name[type]); + /* sanitise map name to characters allowed by kernel */ + for (p = map_name; *p && p < map_name + sizeof(map_name); p++) + if (!isalnum(*p) && *p != '_' && *p != '.') + *p = '_'; + return strdup(map_name); } diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 63430e2664c2..6ec503912bea 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -77,6 +77,12 @@ ifneq ($(SKIP_TARGETS),) override TARGETS := $(TMP) endif +# User can set FORCE_TARGETS to 1 to require all targets to be successfully +# built; make will fail if any of the targets cannot be built. If +# FORCE_TARGETS is not set (the default), make will succeed if at least one +# of the targets gets built. +FORCE_TARGETS ?= + # Clear LDFLAGS and MAKEFLAGS if called from main # Makefile to avoid test build failures when test # Makefile doesn't have explicit build rules. @@ -151,7 +157,8 @@ all: khdr for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ mkdir $$BUILD_TARGET -p; \ - $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET \ + $(if $(FORCE_TARGETS),|| exit); \ ret=$$((ret * $$?)); \ done; exit $$ret; @@ -205,7 +212,8 @@ ifdef INSTALL_PATH @ret=1; \ for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ - $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install \ + $(if $(FORCE_TARGETS),|| exit); \ ret=$$((ret * $$?)); \ done; exit $$ret; diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c index 098bcae5f827..0800036ed654 100644 --- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c +++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c @@ -506,8 +506,10 @@ static void test_syncookie(int type, sa_family_t family) .pass_on_failure = 0, }; - if (type != SOCK_STREAM) + if (type != SOCK_STREAM) { + test__skip(); return; + } /* * +1 for TCP-SYN and @@ -822,8 +824,10 @@ void test_select_reuseport(void) goto out; saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL); + if (saved_tcp_fo < 0) + goto out; saved_tcp_syncookie = read_int_sysctl(TCP_SYNCOOKIE_SYSCTL); - if (saved_tcp_syncookie < 0 || saved_tcp_syncookie < 0) + if (saved_tcp_syncookie < 0) goto out; if (enable_fastopen()) diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 07f5b462c2ef..aa43e0bd210c 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -3,6 +3,11 @@ #include "test_progs.h" +#define TCP_REPAIR 19 /* TCP sock is under repair right now */ + +#define TCP_REPAIR_ON 1 +#define TCP_REPAIR_OFF_NO_WP -1 /* Turn off without window probes */ + static int connected_socket_v4(void) { struct sockaddr_in addr = { diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc index 64cfcc75e3c1..f2ee1e889e13 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc @@ -1,6 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: ftrace - function pid filters +# flags: instance # Make sure that function pid matching filter works. # Also test it on an instance directory @@ -96,13 +97,6 @@ do_test() { } do_test - -mkdir instances/foo -cd instances/foo -do_test -cd ../../ -rmdir instances/foo - do_reset exit 0 diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile index 30996306cabc..23207829ec75 100644 --- a/tools/testing/selftests/futex/functional/Makefile +++ b/tools/testing/selftests/futex/functional/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 INCLUDES := -I../include -I../../ CFLAGS := $(CFLAGS) -g -O2 -Wall -D_GNU_SOURCE -pthread $(INCLUDES) -LDFLAGS := $(LDFLAGS) -pthread -lrt +LDLIBS := -lpthread -lrt HEADERS := \ ../include/futextest.h \ diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 67abc1dd50ee..d91c53b726e6 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -8,7 +8,7 @@ KSFT_KHDR_INSTALL := 1 UNAME_M := $(shell uname -m) LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c -LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/ucall.c +LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c @@ -26,6 +26,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test +TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test TEST_GEN_PROGS_x86_64 += clear_dirty_log_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index aa6451b3f740..7428513a4c68 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -36,24 +36,24 @@ #define X86_CR4_SMAP (1ul << 21) #define X86_CR4_PKE (1ul << 22) -/* The enum values match the intruction encoding of each register */ -enum x86_register { - RAX = 0, - RCX, - RDX, - RBX, - RSP, - RBP, - RSI, - RDI, - R8, - R9, - R10, - R11, - R12, - R13, - R14, - R15, +/* General Registers in 64-Bit Mode */ +struct gpr64_regs { + u64 rax; + u64 rcx; + u64 rdx; + u64 rbx; + u64 rsp; + u64 rbp; + u64 rsi; + u64 rdi; + u64 r8; + u64 r9; + u64 r10; + u64 r11; + u64 r12; + u64 r13; + u64 r14; + u64 r15; }; struct desc64 { @@ -220,20 +220,20 @@ static inline void set_cr4(uint64_t val) __asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory"); } -static inline uint64_t get_gdt_base(void) +static inline struct desc_ptr get_gdt(void) { struct desc_ptr gdt; __asm__ __volatile__("sgdt %[gdt]" : /* output */ [gdt]"=m"(gdt)); - return gdt.address; + return gdt; } -static inline uint64_t get_idt_base(void) +static inline struct desc_ptr get_idt(void) { struct desc_ptr idt; __asm__ __volatile__("sidt %[idt]" : /* output */ [idt]"=m"(idt)); - return idt.address; + return idt; } #define SET_XMM(__var, __xmm) \ diff --git a/tools/testing/selftests/kvm/include/x86_64/svm.h b/tools/testing/selftests/kvm/include/x86_64/svm.h new file mode 100644 index 000000000000..f4ea2355dbc2 --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/svm.h @@ -0,0 +1,297 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * tools/testing/selftests/kvm/include/x86_64/svm.h + * This is a copy of arch/x86/include/asm/svm.h + * + */ + +#ifndef SELFTEST_KVM_SVM_H +#define SELFTEST_KVM_SVM_H + +enum { + INTERCEPT_INTR, + INTERCEPT_NMI, + INTERCEPT_SMI, + INTERCEPT_INIT, + INTERCEPT_VINTR, + INTERCEPT_SELECTIVE_CR0, + INTERCEPT_STORE_IDTR, + INTERCEPT_STORE_GDTR, + INTERCEPT_STORE_LDTR, + INTERCEPT_STORE_TR, + INTERCEPT_LOAD_IDTR, + INTERCEPT_LOAD_GDTR, + INTERCEPT_LOAD_LDTR, + INTERCEPT_LOAD_TR, + INTERCEPT_RDTSC, + INTERCEPT_RDPMC, + INTERCEPT_PUSHF, + INTERCEPT_POPF, + INTERCEPT_CPUID, + INTERCEPT_RSM, + INTERCEPT_IRET, + INTERCEPT_INTn, + INTERCEPT_INVD, + INTERCEPT_PAUSE, + INTERCEPT_HLT, + INTERCEPT_INVLPG, + INTERCEPT_INVLPGA, + INTERCEPT_IOIO_PROT, + INTERCEPT_MSR_PROT, + INTERCEPT_TASK_SWITCH, + INTERCEPT_FERR_FREEZE, + INTERCEPT_SHUTDOWN, + INTERCEPT_VMRUN, + INTERCEPT_VMMCALL, + INTERCEPT_VMLOAD, + INTERCEPT_VMSAVE, + INTERCEPT_STGI, + INTERCEPT_CLGI, + INTERCEPT_SKINIT, + INTERCEPT_RDTSCP, + INTERCEPT_ICEBP, + INTERCEPT_WBINVD, + INTERCEPT_MONITOR, + INTERCEPT_MWAIT, + INTERCEPT_MWAIT_COND, + INTERCEPT_XSETBV, + INTERCEPT_RDPRU, +}; + + +struct __attribute__ ((__packed__)) vmcb_control_area { + u32 intercept_cr; + u32 intercept_dr; + u32 intercept_exceptions; + u64 intercept; + u8 reserved_1[40]; + u16 pause_filter_thresh; + u16 pause_filter_count; + u64 iopm_base_pa; + u64 msrpm_base_pa; + u64 tsc_offset; + u32 asid; + u8 tlb_ctl; + u8 reserved_2[3]; + u32 int_ctl; + u32 int_vector; + u32 int_state; + u8 reserved_3[4]; + u32 exit_code; + u32 exit_code_hi; + u64 exit_info_1; + u64 exit_info_2; + u32 exit_int_info; + u32 exit_int_info_err; + u64 nested_ctl; + u64 avic_vapic_bar; + u8 reserved_4[8]; + u32 event_inj; + u32 event_inj_err; + u64 nested_cr3; + u64 virt_ext; + u32 clean; + u32 reserved_5; + u64 next_rip; + u8 insn_len; + u8 insn_bytes[15]; + u64 avic_backing_page; /* Offset 0xe0 */ + u8 reserved_6[8]; /* Offset 0xe8 */ + u64 avic_logical_id; /* Offset 0xf0 */ + u64 avic_physical_id; /* Offset 0xf8 */ + u8 reserved_7[768]; +}; + + +#define TLB_CONTROL_DO_NOTHING 0 +#define TLB_CONTROL_FLUSH_ALL_ASID 1 +#define TLB_CONTROL_FLUSH_ASID 3 +#define TLB_CONTROL_FLUSH_ASID_LOCAL 7 + +#define V_TPR_MASK 0x0f + +#define V_IRQ_SHIFT 8 +#define V_IRQ_MASK (1 << V_IRQ_SHIFT) + +#define V_GIF_SHIFT 9 +#define V_GIF_MASK (1 << V_GIF_SHIFT) + +#define V_INTR_PRIO_SHIFT 16 +#define V_INTR_PRIO_MASK (0x0f << V_INTR_PRIO_SHIFT) + +#define V_IGN_TPR_SHIFT 20 +#define V_IGN_TPR_MASK (1 << V_IGN_TPR_SHIFT) + +#define V_INTR_MASKING_SHIFT 24 +#define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT) + +#define V_GIF_ENABLE_SHIFT 25 +#define V_GIF_ENABLE_MASK (1 << V_GIF_ENABLE_SHIFT) + +#define AVIC_ENABLE_SHIFT 31 +#define AVIC_ENABLE_MASK (1 << AVIC_ENABLE_SHIFT) + +#define LBR_CTL_ENABLE_MASK BIT_ULL(0) +#define VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK BIT_ULL(1) + +#define SVM_INTERRUPT_SHADOW_MASK 1 + +#define SVM_IOIO_STR_SHIFT 2 +#define SVM_IOIO_REP_SHIFT 3 +#define SVM_IOIO_SIZE_SHIFT 4 +#define SVM_IOIO_ASIZE_SHIFT 7 + +#define SVM_IOIO_TYPE_MASK 1 +#define SVM_IOIO_STR_MASK (1 << SVM_IOIO_STR_SHIFT) +#define SVM_IOIO_REP_MASK (1 << SVM_IOIO_REP_SHIFT) +#define SVM_IOIO_SIZE_MASK (7 << SVM_IOIO_SIZE_SHIFT) +#define SVM_IOIO_ASIZE_MASK (7 << SVM_IOIO_ASIZE_SHIFT) + +#define SVM_VM_CR_VALID_MASK 0x001fULL +#define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL +#define SVM_VM_CR_SVM_DIS_MASK 0x0010ULL + +#define SVM_NESTED_CTL_NP_ENABLE BIT(0) +#define SVM_NESTED_CTL_SEV_ENABLE BIT(1) + +struct __attribute__ ((__packed__)) vmcb_seg { + u16 selector; + u16 attrib; + u32 limit; + u64 base; +}; + +struct __attribute__ ((__packed__)) vmcb_save_area { + struct vmcb_seg es; + struct vmcb_seg cs; + struct vmcb_seg ss; + struct vmcb_seg ds; + struct vmcb_seg fs; + struct vmcb_seg gs; + struct vmcb_seg gdtr; + struct vmcb_seg ldtr; + struct vmcb_seg idtr; + struct vmcb_seg tr; + u8 reserved_1[43]; + u8 cpl; + u8 reserved_2[4]; + u64 efer; + u8 reserved_3[112]; + u64 cr4; + u64 cr3; + u64 cr0; + u64 dr7; + u64 dr6; + u64 rflags; + u64 rip; + u8 reserved_4[88]; + u64 rsp; + u8 reserved_5[24]; + u64 rax; + u64 star; + u64 lstar; + u64 cstar; + u64 sfmask; + u64 kernel_gs_base; + u64 sysenter_cs; + u64 sysenter_esp; + u64 sysenter_eip; + u64 cr2; + u8 reserved_6[32]; + u64 g_pat; + u64 dbgctl; + u64 br_from; + u64 br_to; + u64 last_excp_from; + u64 last_excp_to; +}; + +struct __attribute__ ((__packed__)) vmcb { + struct vmcb_control_area control; + struct vmcb_save_area save; +}; + +#define SVM_CPUID_FUNC 0x8000000a + +#define SVM_VM_CR_SVM_DISABLE 4 + +#define SVM_SELECTOR_S_SHIFT 4 +#define SVM_SELECTOR_DPL_SHIFT 5 +#define SVM_SELECTOR_P_SHIFT 7 +#define SVM_SELECTOR_AVL_SHIFT 8 +#define SVM_SELECTOR_L_SHIFT 9 +#define SVM_SELECTOR_DB_SHIFT 10 +#define SVM_SELECTOR_G_SHIFT 11 + +#define SVM_SELECTOR_TYPE_MASK (0xf) +#define SVM_SELECTOR_S_MASK (1 << SVM_SELECTOR_S_SHIFT) +#define SVM_SELECTOR_DPL_MASK (3 << SVM_SELECTOR_DPL_SHIFT) +#define SVM_SELECTOR_P_MASK (1 << SVM_SELECTOR_P_SHIFT) +#define SVM_SELECTOR_AVL_MASK (1 << SVM_SELECTOR_AVL_SHIFT) +#define SVM_SELECTOR_L_MASK (1 << SVM_SELECTOR_L_SHIFT) +#define SVM_SELECTOR_DB_MASK (1 << SVM_SELECTOR_DB_SHIFT) +#define SVM_SELECTOR_G_MASK (1 << SVM_SELECTOR_G_SHIFT) + +#define SVM_SELECTOR_WRITE_MASK (1 << 1) +#define SVM_SELECTOR_READ_MASK SVM_SELECTOR_WRITE_MASK +#define SVM_SELECTOR_CODE_MASK (1 << 3) + +#define INTERCEPT_CR0_READ 0 +#define INTERCEPT_CR3_READ 3 +#define INTERCEPT_CR4_READ 4 +#define INTERCEPT_CR8_READ 8 +#define INTERCEPT_CR0_WRITE (16 + 0) +#define INTERCEPT_CR3_WRITE (16 + 3) +#define INTERCEPT_CR4_WRITE (16 + 4) +#define INTERCEPT_CR8_WRITE (16 + 8) + +#define INTERCEPT_DR0_READ 0 +#define INTERCEPT_DR1_READ 1 +#define INTERCEPT_DR2_READ 2 +#define INTERCEPT_DR3_READ 3 +#define INTERCEPT_DR4_READ 4 +#define INTERCEPT_DR5_READ 5 +#define INTERCEPT_DR6_READ 6 +#define INTERCEPT_DR7_READ 7 +#define INTERCEPT_DR0_WRITE (16 + 0) +#define INTERCEPT_DR1_WRITE (16 + 1) +#define INTERCEPT_DR2_WRITE (16 + 2) +#define INTERCEPT_DR3_WRITE (16 + 3) +#define INTERCEPT_DR4_WRITE (16 + 4) +#define INTERCEPT_DR5_WRITE (16 + 5) +#define INTERCEPT_DR6_WRITE (16 + 6) +#define INTERCEPT_DR7_WRITE (16 + 7) + +#define SVM_EVTINJ_VEC_MASK 0xff + +#define SVM_EVTINJ_TYPE_SHIFT 8 +#define SVM_EVTINJ_TYPE_MASK (7 << SVM_EVTINJ_TYPE_SHIFT) + +#define SVM_EVTINJ_TYPE_INTR (0 << SVM_EVTINJ_TYPE_SHIFT) +#define SVM_EVTINJ_TYPE_NMI (2 << SVM_EVTINJ_TYPE_SHIFT) +#define SVM_EVTINJ_TYPE_EXEPT (3 << SVM_EVTINJ_TYPE_SHIFT) +#define SVM_EVTINJ_TYPE_SOFT (4 << SVM_EVTINJ_TYPE_SHIFT) + +#define SVM_EVTINJ_VALID (1 << 31) +#define SVM_EVTINJ_VALID_ERR (1 << 11) + +#define SVM_EXITINTINFO_VEC_MASK SVM_EVTINJ_VEC_MASK +#define SVM_EXITINTINFO_TYPE_MASK SVM_EVTINJ_TYPE_MASK + +#define SVM_EXITINTINFO_TYPE_INTR SVM_EVTINJ_TYPE_INTR +#define SVM_EXITINTINFO_TYPE_NMI SVM_EVTINJ_TYPE_NMI +#define SVM_EXITINTINFO_TYPE_EXEPT SVM_EVTINJ_TYPE_EXEPT +#define SVM_EXITINTINFO_TYPE_SOFT SVM_EVTINJ_TYPE_SOFT + +#define SVM_EXITINTINFO_VALID SVM_EVTINJ_VALID +#define SVM_EXITINTINFO_VALID_ERR SVM_EVTINJ_VALID_ERR + +#define SVM_EXITINFOSHIFT_TS_REASON_IRET 36 +#define SVM_EXITINFOSHIFT_TS_REASON_JMP 38 +#define SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE 44 + +#define SVM_EXITINFO_REG_MASK 0x0F + +#define SVM_CR0_SELECTIVE_MASK (X86_CR0_TS | X86_CR0_MP) + +#endif /* SELFTEST_KVM_SVM_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/svm_util.h b/tools/testing/selftests/kvm/include/x86_64/svm_util.h new file mode 100644 index 000000000000..cd037917fece --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/svm_util.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * tools/testing/selftests/kvm/include/x86_64/svm_utils.h + * Header for nested SVM testing + * + * Copyright (C) 2020, Red Hat, Inc. + */ + +#ifndef SELFTEST_KVM_SVM_UTILS_H +#define SELFTEST_KVM_SVM_UTILS_H + +#include <stdint.h> +#include "svm.h" +#include "processor.h" + +#define CPUID_SVM_BIT 2 +#define CPUID_SVM BIT_ULL(CPUID_SVM_BIT) + +#define SVM_EXIT_VMMCALL 0x081 + +struct svm_test_data { + /* VMCB */ + struct vmcb *vmcb; /* gva */ + void *vmcb_hva; + uint64_t vmcb_gpa; + + /* host state-save area */ + struct vmcb_save_area *save_area; /* gva */ + void *save_area_hva; + uint64_t save_area_gpa; +}; + +struct svm_test_data *vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva); +void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_rsp); +void run_guest(struct vmcb *vmcb, uint64_t vmcb_gpa); +void nested_svm_check_supported(void); + +#endif /* SELFTEST_KVM_SVM_UTILS_H */ diff --git a/tools/testing/selftests/kvm/lib/x86_64/svm.c b/tools/testing/selftests/kvm/lib/x86_64/svm.c new file mode 100644 index 000000000000..6e05a8fc3fe0 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86_64/svm.c @@ -0,0 +1,161 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * tools/testing/selftests/kvm/lib/x86_64/svm.c + * Helpers used for nested SVM testing + * Largely inspired from KVM unit test svm.c + * + * Copyright (C) 2020, Red Hat, Inc. + */ + +#include "test_util.h" +#include "kvm_util.h" +#include "../kvm_util_internal.h" +#include "processor.h" +#include "svm_util.h" + +struct gpr64_regs guest_regs; +u64 rflags; + +/* Allocate memory regions for nested SVM tests. + * + * Input Args: + * vm - The VM to allocate guest-virtual addresses in. + * + * Output Args: + * p_svm_gva - The guest virtual address for the struct svm_test_data. + * + * Return: + * Pointer to structure with the addresses of the SVM areas. + */ +struct svm_test_data * +vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva) +{ + vm_vaddr_t svm_gva = vm_vaddr_alloc(vm, getpagesize(), + 0x10000, 0, 0); + struct svm_test_data *svm = addr_gva2hva(vm, svm_gva); + + svm->vmcb = (void *)vm_vaddr_alloc(vm, getpagesize(), + 0x10000, 0, 0); + svm->vmcb_hva = addr_gva2hva(vm, (uintptr_t)svm->vmcb); + svm->vmcb_gpa = addr_gva2gpa(vm, (uintptr_t)svm->vmcb); + + svm->save_area = (void *)vm_vaddr_alloc(vm, getpagesize(), + 0x10000, 0, 0); + svm->save_area_hva = addr_gva2hva(vm, (uintptr_t)svm->save_area); + svm->save_area_gpa = addr_gva2gpa(vm, (uintptr_t)svm->save_area); + + *p_svm_gva = svm_gva; + return svm; +} + +static void vmcb_set_seg(struct vmcb_seg *seg, u16 selector, + u64 base, u32 limit, u32 attr) +{ + seg->selector = selector; + seg->attrib = attr; + seg->limit = limit; + seg->base = base; +} + +void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_rsp) +{ + struct vmcb *vmcb = svm->vmcb; + uint64_t vmcb_gpa = svm->vmcb_gpa; + struct vmcb_save_area *save = &vmcb->save; + struct vmcb_control_area *ctrl = &vmcb->control; + u32 data_seg_attr = 3 | SVM_SELECTOR_S_MASK | SVM_SELECTOR_P_MASK + | SVM_SELECTOR_DB_MASK | SVM_SELECTOR_G_MASK; + u32 code_seg_attr = 9 | SVM_SELECTOR_S_MASK | SVM_SELECTOR_P_MASK + | SVM_SELECTOR_L_MASK | SVM_SELECTOR_G_MASK; + uint64_t efer; + + efer = rdmsr(MSR_EFER); + wrmsr(MSR_EFER, efer | EFER_SVME); + wrmsr(MSR_VM_HSAVE_PA, svm->save_area_gpa); + + memset(vmcb, 0, sizeof(*vmcb)); + asm volatile ("vmsave\n\t" : : "a" (vmcb_gpa) : "memory"); + vmcb_set_seg(&save->es, get_es(), 0, -1U, data_seg_attr); + vmcb_set_seg(&save->cs, get_cs(), 0, -1U, code_seg_attr); + vmcb_set_seg(&save->ss, get_ss(), 0, -1U, data_seg_attr); + vmcb_set_seg(&save->ds, get_ds(), 0, -1U, data_seg_attr); + vmcb_set_seg(&save->gdtr, 0, get_gdt().address, get_gdt().size, 0); + vmcb_set_seg(&save->idtr, 0, get_idt().address, get_idt().size, 0); + + ctrl->asid = 1; + save->cpl = 0; + save->efer = rdmsr(MSR_EFER); + asm volatile ("mov %%cr4, %0" : "=r"(save->cr4) : : "memory"); + asm volatile ("mov %%cr3, %0" : "=r"(save->cr3) : : "memory"); + asm volatile ("mov %%cr0, %0" : "=r"(save->cr0) : : "memory"); + asm volatile ("mov %%dr7, %0" : "=r"(save->dr7) : : "memory"); + asm volatile ("mov %%dr6, %0" : "=r"(save->dr6) : : "memory"); + asm volatile ("mov %%cr2, %0" : "=r"(save->cr2) : : "memory"); + save->g_pat = rdmsr(MSR_IA32_CR_PAT); + save->dbgctl = rdmsr(MSR_IA32_DEBUGCTLMSR); + ctrl->intercept = (1ULL << INTERCEPT_VMRUN) | + (1ULL << INTERCEPT_VMMCALL); + + vmcb->save.rip = (u64)guest_rip; + vmcb->save.rsp = (u64)guest_rsp; + guest_regs.rdi = (u64)svm; +} + +/* + * save/restore 64-bit general registers except rax, rip, rsp + * which are directly handed through the VMCB guest processor state + */ +#define SAVE_GPR_C \ + "xchg %%rbx, guest_regs+0x20\n\t" \ + "xchg %%rcx, guest_regs+0x10\n\t" \ + "xchg %%rdx, guest_regs+0x18\n\t" \ + "xchg %%rbp, guest_regs+0x30\n\t" \ + "xchg %%rsi, guest_regs+0x38\n\t" \ + "xchg %%rdi, guest_regs+0x40\n\t" \ + "xchg %%r8, guest_regs+0x48\n\t" \ + "xchg %%r9, guest_regs+0x50\n\t" \ + "xchg %%r10, guest_regs+0x58\n\t" \ + "xchg %%r11, guest_regs+0x60\n\t" \ + "xchg %%r12, guest_regs+0x68\n\t" \ + "xchg %%r13, guest_regs+0x70\n\t" \ + "xchg %%r14, guest_regs+0x78\n\t" \ + "xchg %%r15, guest_regs+0x80\n\t" + +#define LOAD_GPR_C SAVE_GPR_C + +/* + * selftests do not use interrupts so we dropped clgi/sti/cli/stgi + * for now. registers involved in LOAD/SAVE_GPR_C are eventually + * unmodified so they do not need to be in the clobber list. + */ +void run_guest(struct vmcb *vmcb, uint64_t vmcb_gpa) +{ + asm volatile ( + "vmload\n\t" + "mov rflags, %%r15\n\t" // rflags + "mov %%r15, 0x170(%[vmcb])\n\t" + "mov guest_regs, %%r15\n\t" // rax + "mov %%r15, 0x1f8(%[vmcb])\n\t" + LOAD_GPR_C + "vmrun\n\t" + SAVE_GPR_C + "mov 0x170(%[vmcb]), %%r15\n\t" // rflags + "mov %%r15, rflags\n\t" + "mov 0x1f8(%[vmcb]), %%r15\n\t" // rax + "mov %%r15, guest_regs\n\t" + "vmsave\n\t" + : : [vmcb] "r" (vmcb), [vmcb_gpa] "a" (vmcb_gpa) + : "r15", "memory"); +} + +void nested_svm_check_supported(void) +{ + struct kvm_cpuid_entry2 *entry = + kvm_get_supported_cpuid_entry(0x80000001); + + if (!(entry->ecx & CPUID_SVM)) { + fprintf(stderr, "nested SVM not enabled, skipping test\n"); + exit(KSFT_SKIP); + } +} + diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c index 85064baf5e97..7aaa99ca4dbc 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c @@ -288,9 +288,9 @@ static inline void init_vmcs_host_state(void) vmwrite(HOST_FS_BASE, rdmsr(MSR_FS_BASE)); vmwrite(HOST_GS_BASE, rdmsr(MSR_GS_BASE)); vmwrite(HOST_TR_BASE, - get_desc64_base((struct desc64 *)(get_gdt_base() + get_tr()))); - vmwrite(HOST_GDTR_BASE, get_gdt_base()); - vmwrite(HOST_IDTR_BASE, get_idt_base()); + get_desc64_base((struct desc64 *)(get_gdt().address + get_tr()))); + vmwrite(HOST_GDTR_BASE, get_gdt().address); + vmwrite(HOST_IDTR_BASE, get_idt().address); vmwrite(HOST_IA32_SYSENTER_ESP, rdmsr(MSR_IA32_SYSENTER_ESP)); vmwrite(HOST_IA32_SYSENTER_EIP, rdmsr(MSR_IA32_SYSENTER_EIP)); } diff --git a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c new file mode 100644 index 000000000000..e280f68f6365 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * svm_vmcall_test + * + * Copyright (C) 2020, Red Hat, Inc. + * + * Nested SVM testing: VMCALL + */ + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" + +#define VCPU_ID 5 + +static struct kvm_vm *vm; + +static void l2_guest_code(struct svm_test_data *svm) +{ + __asm__ __volatile__("vmcall"); +} + +static void l1_guest_code(struct svm_test_data *svm) +{ + #define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + struct vmcb *vmcb = svm->vmcb; + + /* Prepare for L2 execution. */ + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + run_guest(vmcb, svm->vmcb_gpa); + + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL); + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + vm_vaddr_t svm_gva; + + nested_svm_check_supported(); + + vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + + vcpu_alloc_svm(vm, &svm_gva); + vcpu_args_set(vm, VCPU_ID, 1, svm_gva); + + for (;;) { + volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc; + + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_ABORT: + TEST_ASSERT(false, "%s", + (const char *)uc.args[0]); + /* NOT REACHED */ + case UCALL_SYNC: + break; + case UCALL_DONE: + goto done; + default: + TEST_ASSERT(false, + "Unknown ucall 0x%x.", uc.cmd); + } + } +done: + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 1c8a1963d03f..3ed0134a764d 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -83,17 +83,20 @@ else $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS)) endif +define INSTALL_SINGLE_RULE + $(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH)) + $(if $(INSTALL_LIST),@echo rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/) + $(if $(INSTALL_LIST),@rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/) +endef + define INSTALL_RULE - @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \ - mkdir -p ${INSTALL_PATH}; \ - echo "rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/"; \ - rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/; \ - fi - @if [ "X$(TEST_GEN_PROGS)$(TEST_CUSTOM_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then \ - mkdir -p ${INSTALL_PATH}; \ - echo "rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/"; \ - rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/; \ - fi + $(eval INSTALL_LIST = $(TEST_PROGS)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_FILES)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_GEN_PROGS)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_CUSTOM_PROGS)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_GEN_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_GEN_FILES)) $(INSTALL_SINGLE_RULE) endef install: all diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index b5694196430a..287ae916ec0b 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -27,5 +27,5 @@ KSFT_KHDR_INSTALL := 1 include ../lib.mk $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma -$(OUTPUT)/tcp_mmap: LDFLAGS += -lpthread -$(OUTPUT)/tcp_inq: LDFLAGS += -lpthread +$(OUTPUT)/tcp_mmap: LDLIBS += -lpthread +$(OUTPUT)/tcp_inq: LDLIBS += -lpthread diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 6dd403103800..60273f1bc7d9 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -910,6 +910,12 @@ ipv6_rt_replace_mpath() check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024" log_test $? 0 "Multipath with single path via multipath attribute" + # multipath with dev-only + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 dev veth1" + check_route6 "2001:db8:104::/64 dev veth1 metric 1024" + log_test $? 0 "Multipath with dev-only" + # route replace fails - invalid nexthop 1 add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3" diff --git a/tools/testing/selftests/net/forwarding/mirror_gre.sh b/tools/testing/selftests/net/forwarding/mirror_gre.sh index e6fd7a18c655..0266443601bc 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre.sh @@ -63,22 +63,23 @@ test_span_gre_mac() { local tundev=$1; shift local direction=$1; shift - local prot=$1; shift local what=$1; shift - local swp3mac=$(mac_get $swp3) - local h3mac=$(mac_get $h3) + case "$direction" in + ingress) local src_mac=$(mac_get $h1); local dst_mac=$(mac_get $h2) + ;; + egress) local src_mac=$(mac_get $h2); local dst_mac=$(mac_get $h1) + ;; + esac RET=0 mirror_install $swp1 $direction $tundev "matchall $tcflags" - tc filter add dev $h3 ingress pref 77 prot $prot \ - flower ip_proto 0x2f src_mac $swp3mac dst_mac $h3mac \ - action pass + icmp_capture_install h3-${tundev} "src_mac $src_mac dst_mac $dst_mac" - mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10 + mirror_test v$h1 192.0.2.1 192.0.2.2 h3-${tundev} 100 10 - tc filter del dev $h3 ingress pref 77 + icmp_capture_uninstall h3-${tundev} mirror_uninstall $swp1 $direction log_test "$direction $what: envelope MAC ($tcflags)" @@ -120,14 +121,14 @@ test_ip6gretap() test_gretap_mac() { - test_span_gre_mac gt4 ingress ip "mirror to gretap" - test_span_gre_mac gt4 egress ip "mirror to gretap" + test_span_gre_mac gt4 ingress "mirror to gretap" + test_span_gre_mac gt4 egress "mirror to gretap" } test_ip6gretap_mac() { - test_span_gre_mac gt6 ingress ipv6 "mirror to ip6gretap" - test_span_gre_mac gt6 egress ipv6 "mirror to ip6gretap" + test_span_gre_mac gt6 ingress "mirror to ip6gretap" + test_span_gre_mac gt6 egress "mirror to ip6gretap" } test_all() diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh index bb10e33690b2..ce6bea9675c0 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh @@ -516,9 +516,9 @@ test_tos() RET=0 tc filter add dev v1 egress pref 77 prot ip \ - flower ip_tos 0x40 action pass - vxlan_ping_test $h1 192.0.2.3 "-Q 0x40" v1 egress 77 10 - vxlan_ping_test $h1 192.0.2.3 "-Q 0x30" v1 egress 77 0 + flower ip_tos 0x14 action pass + vxlan_ping_test $h1 192.0.2.3 "-Q 0x14" v1 egress 77 10 + vxlan_ping_test $h1 192.0.2.3 "-Q 0x18" v1 egress 77 0 tc filter del dev v1 egress pref 77 prot ip log_test "VXLAN: envelope TOS inheritance" diff --git a/tools/testing/selftests/openat2/helpers.c b/tools/testing/selftests/openat2/helpers.c index e9a6557ab16f..5074681ffdc9 100644 --- a/tools/testing/selftests/openat2/helpers.c +++ b/tools/testing/selftests/openat2/helpers.c @@ -46,7 +46,7 @@ int sys_renameat2(int olddirfd, const char *oldpath, int touchat(int dfd, const char *path) { - int fd = openat(dfd, path, O_CREAT); + int fd = openat(dfd, path, O_CREAT, 0700); if (fd >= 0) close(fd); return fd; diff --git a/tools/testing/selftests/openat2/resolve_test.c b/tools/testing/selftests/openat2/resolve_test.c index 7a94b1da8e7b..bbafad440893 100644 --- a/tools/testing/selftests/openat2/resolve_test.c +++ b/tools/testing/selftests/openat2/resolve_test.c @@ -230,7 +230,7 @@ void test_openat2_opath_tests(void) { .name = "[in_root] garbage link to /root", .path = "cheeky/garbageself", .how.resolve = RESOLVE_IN_ROOT, .out.path = "root", .pass = true }, - { .name = "[in_root] chainged garbage links to /root", + { .name = "[in_root] chained garbage links to /root", .path = "abscheeky/garbageself", .how.resolve = RESOLVE_IN_ROOT, .out.path = "root", .pass = true }, { .name = "[in_root] relative path to 'root'", diff --git a/tools/testing/selftests/rtc/Makefile b/tools/testing/selftests/rtc/Makefile index de9c8566672a..2d93d65723c9 100644 --- a/tools/testing/selftests/rtc/Makefile +++ b/tools/testing/selftests/rtc/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -O3 -Wl,-no-as-needed -Wall -LDFLAGS += -lrt -lpthread -lm +LDLIBS += -lrt -lpthread -lm TEST_GEN_PROGS = rtctest diff --git a/tools/testing/selftests/timens/Makefile b/tools/testing/selftests/timens/Makefile index e9fb30bd8aeb..b4fd9a934654 100644 --- a/tools/testing/selftests/timens/Makefile +++ b/tools/testing/selftests/timens/Makefile @@ -2,6 +2,6 @@ TEST_GEN_PROGS := timens timerfd timer clock_nanosleep procfs exec TEST_GEN_PROGS_EXTENDED := gettime_perf CFLAGS := -Wall -Werror -pthread -LDFLAGS := -lrt -ldl +LDLIBS := -lrt -ldl include ../lib.mk diff --git a/tools/testing/selftests/tpm2/test_smoke.sh b/tools/testing/selftests/tpm2/test_smoke.sh index 8155c2ea7ccb..b630c7b5950a 100755 --- a/tools/testing/selftests/tpm2/test_smoke.sh +++ b/tools/testing/selftests/tpm2/test_smoke.sh @@ -1,8 +1,17 @@ #!/bin/bash # SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) +self.flags = flags -python -m unittest -v tpm2_tests.SmokeTest -python -m unittest -v tpm2_tests.AsyncTest +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + + +if [ -f /dev/tpm0 ] ; then + python -m unittest -v tpm2_tests.SmokeTest + python -m unittest -v tpm2_tests.AsyncTest +else + exit $ksft_skip +fi CLEAR_CMD=$(which tpm2_clear) if [ -n $CLEAR_CMD ]; then diff --git a/tools/testing/selftests/tpm2/test_space.sh b/tools/testing/selftests/tpm2/test_space.sh index a6f5e346635e..180b469c53b4 100755 --- a/tools/testing/selftests/tpm2/test_space.sh +++ b/tools/testing/selftests/tpm2/test_space.sh @@ -1,4 +1,11 @@ #!/bin/bash # SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) -python -m unittest -v tpm2_tests.SpaceTest +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +if [ -f /dev/tpmrm0 ] ; then + python -m unittest -v tpm2_tests.SpaceTest +else + exit $ksft_skip +fi diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests index a692ea828317..f33714843198 100755 --- a/tools/testing/selftests/vm/run_vmtests +++ b/tools/testing/selftests/vm/run_vmtests @@ -112,6 +112,17 @@ echo "NOTE: The above hugetlb tests provide minimal coverage. Use" echo " https://github.com/libhugetlbfs/libhugetlbfs.git for" echo " hugetlb regression testing." +echo "---------------------------" +echo "running map_fixed_noreplace" +echo "---------------------------" +./map_fixed_noreplace +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi + echo "-------------------" echo "running userfaultfd" echo "-------------------" @@ -186,6 +197,17 @@ else echo "[PASS]" fi +echo "-------------------------" +echo "running mlock-random-test" +echo "-------------------------" +./mlock-random-test +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi + echo "--------------------" echo "running mlock2-tests" echo "--------------------" @@ -197,6 +219,17 @@ else echo "[PASS]" fi +echo "-----------------" +echo "running thuge-gen" +echo "-----------------" +./thuge-gen +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi + if [ $VADDR64 -ne 0 ]; then echo "-----------------------------" echo "running virtual_address_range" diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile index f10aa3590adc..28d477683e8a 100644 --- a/tools/testing/selftests/wireguard/qemu/Makefile +++ b/tools/testing/selftests/wireguard/qemu/Makefile @@ -38,19 +38,17 @@ endef define file_download = $(DISTFILES_PATH)/$(1): mkdir -p $(DISTFILES_PATH) - flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp' - if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi + flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp; [ -f $$@.tmp ] || exit 1; if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi' endef $(eval $(call tar_download,MUSL,musl,1.1.24,.tar.gz,https://www.musl-libc.org/releases/,1370c9a812b2cf2a7d92802510cca0058cc37e66a7bedd70051f0a34015022a3)) -$(eval $(call tar_download,LIBMNL,libmnl,1.0.4,.tar.bz2,https://www.netfilter.org/projects/libmnl/files/,171f89699f286a5854b72b91d06e8f8e3683064c5901fb09d954a9ab6f551f81)) $(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c)) $(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d)) $(eval $(call tar_download,IPROUTE2,iproute2,5.4.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,fe97aa60a0d4c5ac830be18937e18dc3400ca713a33a89ad896ff1e3d46086ae)) $(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c)) $(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa)) $(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a)) -$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20191226,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,aa8af0fdc9872d369d8c890a84dbc2a2466b55795dccd5b47721b2d97644b04f)) +$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20200206,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,f5207248c6a3c3e3bfc9ab30b91c1897b00802ed861e1f9faaed873366078c64)) KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug) rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d)) @@ -295,21 +293,13 @@ $(IPERF_PATH)/src/iperf3: | $(IPERF_PATH)/.installed $(USERSPACE_DEPS) $(MAKE) -C $(IPERF_PATH) $(STRIP) -s $@ -$(LIBMNL_PATH)/.installed: $(LIBMNL_TAR) - flock -s $<.lock tar -C $(BUILD_PATH) -xf $< - touch $@ - -$(LIBMNL_PATH)/src/.libs/libmnl.a: | $(LIBMNL_PATH)/.installed $(USERSPACE_DEPS) - cd $(LIBMNL_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared - $(MAKE) -C $(LIBMNL_PATH) - sed -i 's:prefix=.*:prefix=$(LIBMNL_PATH):' $(LIBMNL_PATH)/libmnl.pc - $(WIREGUARD_TOOLS_PATH)/.installed: $(WIREGUARD_TOOLS_TAR) + mkdir -p $(BUILD_PATH) flock -s $<.lock tar -C $(BUILD_PATH) -xf $< touch $@ -$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) - LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg +$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(USERSPACE_DEPS) + $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src wg $(STRIP) -s $@ $(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS) @@ -340,17 +330,17 @@ $(BASH_PATH)/bash: | $(BASH_PATH)/.installed $(USERSPACE_DEPS) $(IPROUTE2_PATH)/.installed: $(IPROUTE2_TAR) mkdir -p $(BUILD_PATH) flock -s $<.lock tar -C $(BUILD_PATH) -xf $< - printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=y\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS -DHAVE_LIBMNL -I$(LIBMNL_PATH)/include\nLDLIBS+=-lmnl' > $(IPROUTE2_PATH)/config.mk + printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=n\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS\n' > $(IPROUTE2_PATH)/config.mk printf 'lib: snapshot\n\t$$(MAKE) -C lib\nip/ip: lib\n\t$$(MAKE) -C ip ip\nmisc/ss: lib\n\t$$(MAKE) -C misc ss\n' >> $(IPROUTE2_PATH)/Makefile touch $@ -$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) - LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip - $(STRIP) -s $(IPROUTE2_PATH)/ip/ip +$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS) + $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip + $(STRIP) -s $@ -$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) - LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss - $(STRIP) -s $(IPROUTE2_PATH)/misc/ss +$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS) + $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss + $(STRIP) -s $@ $(IPTABLES_PATH)/.installed: $(IPTABLES_TAR) mkdir -p $(BUILD_PATH) @@ -358,8 +348,8 @@ $(IPTABLES_PATH)/.installed: $(IPTABLES_TAR) sed -i -e "/nfnetlink=[01]/s:=[01]:=0:" -e "/nfconntrack=[01]/s:=[01]:=0:" $(IPTABLES_PATH)/configure touch $@ -$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) - cd $(IPTABLES_PATH) && PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --with-kernel=$(BUILD_PATH)/include +$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(USERSPACE_DEPS) + cd $(IPTABLES_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --disable-connlabel --with-kernel=$(BUILD_PATH)/include $(MAKE) -C $(IPTABLES_PATH) $(STRIP) -s $@ diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c index d656ebd5f9d4..97fb2a40e6ba 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.c +++ b/virt/kvm/arm/vgic/vgic-mmio.c @@ -179,18 +179,6 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, return value; } -/* - * This function will return the VCPU that performed the MMIO access and - * trapped from within the VM, and will return NULL if this is a userspace - * access. - * - * We can disable preemption locally around accessing the per-CPU variable, - * and use the resolved vcpu pointer after enabling preemption again, because - * even if the current thread is migrated to another CPU, reading the per-CPU - * value later will give us the same value as we update the per-CPU variable - * in the preempt notifier handlers. - */ - /* Must be called with irq->irq_lock held */ static void vgic_hw_irq_spending(struct kvm_vcpu *vcpu, struct vgic_irq *irq, bool is_uaccess) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 67ae2d5c37b2..70f03ce0e5c1 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -4409,12 +4409,22 @@ static void kvm_sched_out(struct preempt_notifier *pn, /** * kvm_get_running_vcpu - get the vcpu running on the current CPU. - * Thanks to preempt notifiers, this can also be called from - * preemptible context. + * + * We can disable preemption locally around accessing the per-CPU variable, + * and use the resolved vcpu pointer after enabling preemption again, + * because even if the current thread is migrated to another CPU, reading + * the per-CPU value later will give us the same value as we update the + * per-CPU variable in the preempt notifier handlers. */ struct kvm_vcpu *kvm_get_running_vcpu(void) { - return __this_cpu_read(kvm_running_vcpu); + struct kvm_vcpu *vcpu; + + preempt_disable(); + vcpu = __this_cpu_read(kvm_running_vcpu); + preempt_enable(); + + return vcpu; } /** |