diff options
686 files changed, 9752 insertions, 4148 deletions
diff --git a/Documentation/ABI/testing/sysfs-fs-erofs b/Documentation/ABI/testing/sysfs-fs-erofs index 05482374a741..bb4681a01811 100644 --- a/Documentation/ABI/testing/sysfs-fs-erofs +++ b/Documentation/ABI/testing/sysfs-fs-erofs @@ -9,8 +9,9 @@ Description: Shows all enabled kernel features. What: /sys/fs/erofs/<disk>/sync_decompress Date: November 2021 Contact: "Huang Jianan" <huangjianan@oppo.com> -Description: Control strategy of sync decompression +Description: Control strategy of sync decompression: + - 0 (default, auto): enable for readpage, and enable for - readahead on atomic contexts only, + readahead on atomic contexts only. - 1 (force on): enable for readpage and readahead. - 2 (force off): disable for all situations. diff --git a/Documentation/arm64/cpu-feature-registers.rst b/Documentation/arm64/cpu-feature-registers.rst index 749ae970c319..04ba83e1965f 100644 --- a/Documentation/arm64/cpu-feature-registers.rst +++ b/Documentation/arm64/cpu-feature-registers.rst @@ -290,6 +290,8 @@ infrastructure: +------------------------------+---------+---------+ | RPRES | [7-4] | y | +------------------------------+---------+---------+ + | WFXT | [3-0] | y | + +------------------------------+---------+---------+ Appendix I: Example diff --git a/Documentation/arm64/elf_hwcaps.rst b/Documentation/arm64/elf_hwcaps.rst index a8f30963e550..3d116fb536c5 100644 --- a/Documentation/arm64/elf_hwcaps.rst +++ b/Documentation/arm64/elf_hwcaps.rst @@ -264,6 +264,43 @@ HWCAP2_MTE3 Functionality implied by ID_AA64PFR1_EL1.MTE == 0b0011, as described by Documentation/arm64/memory-tagging-extension.rst. +HWCAP2_SME + + Functionality implied by ID_AA64PFR1_EL1.SME == 0b0001, as described + by Documentation/arm64/sme.rst. + +HWCAP2_SME_I16I64 + + Functionality implied by ID_AA64SMFR0_EL1.I16I64 == 0b1111. + +HWCAP2_SME_F64F64 + + Functionality implied by ID_AA64SMFR0_EL1.F64F64 == 0b1. + +HWCAP2_SME_I8I32 + + Functionality implied by ID_AA64SMFR0_EL1.I8I32 == 0b1111. + +HWCAP2_SME_F16F32 + + Functionality implied by ID_AA64SMFR0_EL1.F16F32 == 0b1. + +HWCAP2_SME_B16F32 + + Functionality implied by ID_AA64SMFR0_EL1.B16F32 == 0b1. + +HWCAP2_SME_F32F32 + + Functionality implied by ID_AA64SMFR0_EL1.F32F32 == 0b1. + +HWCAP2_SME_FA64 + + Functionality implied by ID_AA64SMFR0_EL1.FA64 == 0b1. + +HWCAP2_WFXT + + Functionality implied by ID_AA64ISAR2_EL1.WFXT == 0b0010. + 4. Unused AT_HWCAP bits ----------------------- diff --git a/Documentation/arm64/index.rst b/Documentation/arm64/index.rst index 4f840bac083e..ae21f8118830 100644 --- a/Documentation/arm64/index.rst +++ b/Documentation/arm64/index.rst @@ -21,6 +21,7 @@ ARM64 Architecture perf pointer-authentication silicon-errata + sme sve tagged-address-abi tagged-pointers diff --git a/Documentation/arm64/memory-tagging-extension.rst b/Documentation/arm64/memory-tagging-extension.rst index dd27f78d7608..dbae47bba25e 100644 --- a/Documentation/arm64/memory-tagging-extension.rst +++ b/Documentation/arm64/memory-tagging-extension.rst @@ -228,10 +228,10 @@ Core dump support ----------------- The allocation tags for user memory mapped with ``PROT_MTE`` are dumped -in the core file as additional ``PT_ARM_MEMTAG_MTE`` segments. The +in the core file as additional ``PT_AARCH64_MEMTAG_MTE`` segments. The program header for such segment is defined as: -:``p_type``: ``PT_ARM_MEMTAG_MTE`` +:``p_type``: ``PT_AARCH64_MEMTAG_MTE`` :``p_flags``: 0 :``p_offset``: segment file offset :``p_vaddr``: segment virtual address, same as the corresponding diff --git a/Documentation/arm64/sme.rst b/Documentation/arm64/sme.rst new file mode 100644 index 000000000000..8ba677b87e90 --- /dev/null +++ b/Documentation/arm64/sme.rst @@ -0,0 +1,428 @@ +=================================================== +Scalable Matrix Extension support for AArch64 Linux +=================================================== + +This document outlines briefly the interface provided to userspace by Linux in +order to support use of the ARM Scalable Matrix Extension (SME). + +This is an outline of the most important features and issues only and not +intended to be exhaustive. It should be read in conjunction with the SVE +documentation in sve.rst which provides details on the Streaming SVE mode +included in SME. + +This document does not aim to describe the SME architecture or programmer's +model. To aid understanding, a minimal description of relevant programmer's +model features for SME is included in Appendix A. + + +1. General +----------- + +* PSTATE.SM, PSTATE.ZA, the streaming mode vector length, the ZA + register state and TPIDR2_EL0 are tracked per thread. + +* The presence of SME is reported to userspace via HWCAP2_SME in the aux vector + AT_HWCAP2 entry. Presence of this flag implies the presence of the SME + instructions and registers, and the Linux-specific system interfaces + described in this document. SME is reported in /proc/cpuinfo as "sme". + +* Support for the execution of SME instructions in userspace can also be + detected by reading the CPU ID register ID_AA64PFR1_EL1 using an MRS + instruction, and checking that the value of the SME field is nonzero. [3] + + It does not guarantee the presence of the system interfaces described in the + following sections: software that needs to verify that those interfaces are + present must check for HWCAP2_SME instead. + +* There are a number of optional SME features, presence of these is reported + through AT_HWCAP2 through: + + HWCAP2_SME_I16I64 + HWCAP2_SME_F64F64 + HWCAP2_SME_I8I32 + HWCAP2_SME_F16F32 + HWCAP2_SME_B16F32 + HWCAP2_SME_F32F32 + HWCAP2_SME_FA64 + + This list may be extended over time as the SME architecture evolves. + + These extensions are also reported via the CPU ID register ID_AA64SMFR0_EL1, + which userspace can read using an MRS instruction. See elf_hwcaps.txt and + cpu-feature-registers.txt for details. + +* Debuggers should restrict themselves to interacting with the target via the + NT_ARM_SVE, NT_ARM_SSVE and NT_ARM_ZA regsets. The recommended way + of detecting support for these regsets is to connect to a target process + first and then attempt a + + ptrace(PTRACE_GETREGSET, pid, NT_ARM_<regset>, &iov). + +* Whenever ZA register values are exchanged in memory between userspace and + the kernel, the register value is encoded in memory as a series of horizontal + vectors from 0 to VL/8-1 stored in the same endianness invariant format as is + used for SVE vectors. + +* On thread creation TPIDR2_EL0 is preserved unless CLONE_SETTLS is specified, + in which case it is set to 0. + +2. Vector lengths +------------------ + +SME defines a second vector length similar to the SVE vector length which is +controls the size of the streaming mode SVE vectors and the ZA matrix array. +The ZA matrix is square with each side having as many bytes as a streaming +mode SVE vector. + + +3. Sharing of streaming and non-streaming mode SVE state +--------------------------------------------------------- + +It is implementation defined which if any parts of the SVE state are shared +between streaming and non-streaming modes. When switching between modes +via software interfaces such as ptrace if no register content is provided as +part of switching no state will be assumed to be shared and everything will +be zeroed. + + +4. System call behaviour +------------------------- + +* On syscall PSTATE.ZA is preserved, if PSTATE.ZA==1 then the contents of the + ZA matrix are preserved. + +* On syscall PSTATE.SM will be cleared and the SVE registers will be handled + as per the standard SVE ABI. + +* Neither the SVE registers nor ZA are used to pass arguments to or receive + results from any syscall. + +* On process creation (eg, clone()) the newly created process will have + PSTATE.SM cleared. + +* All other SME state of a thread, including the currently configured vector + length, the state of the PR_SME_VL_INHERIT flag, and the deferred vector + length (if any), is preserved across all syscalls, subject to the specific + exceptions for execve() described in section 6. + + +5. Signal handling +------------------- + +* Signal handlers are invoked with streaming mode and ZA disabled. + +* A new signal frame record za_context encodes the ZA register contents on + signal delivery. [1] + +* The signal frame record for ZA always contains basic metadata, in particular + the thread's vector length (in za_context.vl). + +* The ZA matrix may or may not be included in the record, depending on + the value of PSTATE.ZA. The registers are present if and only if: + za_context.head.size >= ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za_context.vl)) + in which case PSTATE.ZA == 1. + +* If matrix data is present, the remainder of the record has a vl-dependent + size and layout. Macros ZA_SIG_* are defined [1] to facilitate access to + them. + +* The matrix is stored as a series of horizontal vectors in the same format as + is used for SVE vectors. + +* If the ZA context is too big to fit in sigcontext.__reserved[], then extra + space is allocated on the stack, an extra_context record is written in + __reserved[] referencing this space. za_context is then written in the + extra space. Refer to [1] for further details about this mechanism. + + +5. Signal return +----------------- + +When returning from a signal handler: + +* If there is no za_context record in the signal frame, or if the record is + present but contains no register data as described in the previous section, + then ZA is disabled. + +* If za_context is present in the signal frame and contains matrix data then + PSTATE.ZA is set to 1 and ZA is populated with the specified data. + +* The vector length cannot be changed via signal return. If za_context.vl in + the signal frame does not match the current vector length, the signal return + attempt is treated as illegal, resulting in a forced SIGSEGV. + + +6. prctl extensions +-------------------- + +Some new prctl() calls are added to allow programs to manage the SME vector +length: + +prctl(PR_SME_SET_VL, unsigned long arg) + + Sets the vector length of the calling thread and related flags, where + arg == vl | flags. Other threads of the calling process are unaffected. + + vl is the desired vector length, where sve_vl_valid(vl) must be true. + + flags: + + PR_SME_VL_INHERIT + + Inherit the current vector length across execve(). Otherwise, the + vector length is reset to the system default at execve(). (See + Section 9.) + + PR_SME_SET_VL_ONEXEC + + Defer the requested vector length change until the next execve() + performed by this thread. + + The effect is equivalent to implicit execution of the following + call immediately after the next execve() (if any) by the thread: + + prctl(PR_SME_SET_VL, arg & ~PR_SME_SET_VL_ONEXEC) + + This allows launching of a new program with a different vector + length, while avoiding runtime side effects in the caller. + + Without PR_SME_SET_VL_ONEXEC, the requested change takes effect + immediately. + + + Return value: a nonnegative on success, or a negative value on error: + EINVAL: SME not supported, invalid vector length requested, or + invalid flags. + + + On success: + + * Either the calling thread's vector length or the deferred vector length + to be applied at the next execve() by the thread (dependent on whether + PR_SME_SET_VL_ONEXEC is present in arg), is set to the largest value + supported by the system that is less than or equal to vl. If vl == + SVE_VL_MAX, the value set will be the largest value supported by the + system. + + * Any previously outstanding deferred vector length change in the calling + thread is cancelled. + + * The returned value describes the resulting configuration, encoded as for + PR_SME_GET_VL. The vector length reported in this value is the new + current vector length for this thread if PR_SME_SET_VL_ONEXEC was not + present in arg; otherwise, the reported vector length is the deferred + vector length that will be applied at the next execve() by the calling + thread. + + * Changing the vector length causes all of ZA, P0..P15, FFR and all bits of + Z0..Z31 except for Z0 bits [127:0] .. Z31 bits [127:0] to become + unspecified, including both streaming and non-streaming SVE state. + Calling PR_SME_SET_VL with vl equal to the thread's current vector + length, or calling PR_SME_SET_VL with the PR_SVE_SET_VL_ONEXEC flag, + does not constitute a change to the vector length for this purpose. + + * Changing the vector length causes PSTATE.ZA and PSTATE.SM to be cleared. + Calling PR_SME_SET_VL with vl equal to the thread's current vector + length, or calling PR_SME_SET_VL with the PR_SVE_SET_VL_ONEXEC flag, + does not constitute a change to the vector length for this purpose. + + +prctl(PR_SME_GET_VL) + + Gets the vector length of the calling thread. + + The following flag may be OR-ed into the result: + + PR_SME_VL_INHERIT + + Vector length will be inherited across execve(). + + There is no way to determine whether there is an outstanding deferred + vector length change (which would only normally be the case between a + fork() or vfork() and the corresponding execve() in typical use). + + To extract the vector length from the result, bitwise and it with + PR_SME_VL_LEN_MASK. + + Return value: a nonnegative value on success, or a negative value on error: + EINVAL: SME not supported. + + +7. ptrace extensions +--------------------- + +* A new regset NT_ARM_SSVE is defined for access to streaming mode SVE + state via PTRACE_GETREGSET and PTRACE_SETREGSET, this is documented in + sve.rst. + +* A new regset NT_ARM_ZA is defined for ZA state for access to ZA state via + PTRACE_GETREGSET and PTRACE_SETREGSET. + + Refer to [2] for definitions. + +The regset data starts with struct user_za_header, containing: + + size + + Size of the complete regset, in bytes. + This depends on vl and possibly on other things in the future. + + If a call to PTRACE_GETREGSET requests less data than the value of + size, the caller can allocate a larger buffer and retry in order to + read the complete regset. + + max_size + + Maximum size in bytes that the regset can grow to for the target + thread. The regset won't grow bigger than this even if the target + thread changes its vector length etc. + + vl + + Target thread's current streaming vector length, in bytes. + + max_vl + + Maximum possible streaming vector length for the target thread. + + flags + + Zero or more of the following flags, which have the same + meaning and behaviour as the corresponding PR_SET_VL_* flags: + + SME_PT_VL_INHERIT + + SME_PT_VL_ONEXEC (SETREGSET only). + +* The effects of changing the vector length and/or flags are equivalent to + those documented for PR_SME_SET_VL. + + The caller must make a further GETREGSET call if it needs to know what VL is + actually set by SETREGSET, unless is it known in advance that the requested + VL is supported. + +* The size and layout of the payload depends on the header fields. The + SME_PT_ZA_*() macros are provided to facilitate access to the data. + +* In either case, for SETREGSET it is permissible to omit the payload, in which + case the vector length and flags are changed and PSTATE.ZA is set to 0 + (along with any consequences of those changes). If a payload is provided + then PSTATE.ZA will be set to 1. + +* For SETREGSET, if the requested VL is not supported, the effect will be the + same as if the payload were omitted, except that an EIO error is reported. + No attempt is made to translate the payload data to the correct layout + for the vector length actually set. It is up to the caller to translate the + payload layout for the actual VL and retry. + +* The effect of writing a partial, incomplete payload is unspecified. + + +8. ELF coredump extensions +--------------------------- + +* NT_ARM_SSVE notes will be added to each coredump for + each thread of the dumped process. The contents will be equivalent to the + data that would have been read if a PTRACE_GETREGSET of the corresponding + type were executed for each thread when the coredump was generated. + +* A NT_ARM_ZA note will be added to each coredump for each thread of the + dumped process. The contents will be equivalent to the data that would have + been read if a PTRACE_GETREGSET of NT_ARM_ZA were executed for each thread + when the coredump was generated. + + +9. System runtime configuration +-------------------------------- + +* To mitigate the ABI impact of expansion of the signal frame, a policy + mechanism is provided for administrators, distro maintainers and developers + to set the default vector length for userspace processes: + +/proc/sys/abi/sme_default_vector_length + + Writing the text representation of an integer to this file sets the system + default vector length to the specified value, unless the value is greater + than the maximum vector length supported by the system in which case the + default vector length is set to that maximum. + + The result can be determined by reopening the file and reading its + contents. + + At boot, the default vector length is initially set to 32 or the maximum + supported vector length, whichever is smaller and supported. This + determines the initial vector length of the init process (PID 1). + + Reading this file returns the current system default vector length. + +* At every execve() call, the new vector length of the new process is set to + the system default vector length, unless + + * PR_SME_VL_INHERIT (or equivalently SME_PT_VL_INHERIT) is set for the + calling thread, or + + * a deferred vector length change is pending, established via the + PR_SME_SET_VL_ONEXEC flag (or SME_PT_VL_ONEXEC). + +* Modifying the system default vector length does not affect the vector length + of any existing process or thread that does not make an execve() call. + + +Appendix A. SME programmer's model (informative) +================================================= + +This section provides a minimal description of the additions made by SVE to the +ARMv8-A programmer's model that are relevant to this document. + +Note: This section is for information only and not intended to be complete or +to replace any architectural specification. + +A.1. Registers +--------------- + +In A64 state, SME adds the following: + +* A new mode, streaming mode, in which a subset of the normal FPSIMD and SVE + features are available. When supported EL0 software may enter and leave + streaming mode at any time. + + For best system performance it is strongly encouraged for software to enable + streaming mode only when it is actively being used. + +* A new vector length controlling the size of ZA and the Z registers when in + streaming mode, separately to the vector length used for SVE when not in + streaming mode. There is no requirement that either the currently selected + vector length or the set of vector lengths supported for the two modes in + a given system have any relationship. The streaming mode vector length + is referred to as SVL. + +* A new ZA matrix register. This is a square matrix of SVLxSVL bits. Most + operations on ZA require that streaming mode be enabled but ZA can be + enabled without streaming mode in order to load, save and retain data. + + For best system performance it is strongly encouraged for software to enable + ZA only when it is actively being used. + +* Two new 1 bit fields in PSTATE which may be controlled via the SMSTART and + SMSTOP instructions or by access to the SVCR system register: + + * PSTATE.ZA, if this is 1 then the ZA matrix is accessible and has valid + data while if it is 0 then ZA can not be accessed. When PSTATE.ZA is + changed from 0 to 1 all bits in ZA are cleared. + + * PSTATE.SM, if this is 1 then the PE is in streaming mode. When the value + of PSTATE.SM is changed then it is implementation defined if the subset + of the floating point register bits valid in both modes may be retained. + Any other bits will be cleared. + + +References +========== + +[1] arch/arm64/include/uapi/asm/sigcontext.h + AArch64 Linux signal ABI definitions + +[2] arch/arm64/include/uapi/asm/ptrace.h + AArch64 Linux ptrace ABI definitions + +[3] Documentation/arm64/cpu-feature-registers.rst diff --git a/Documentation/arm64/sve.rst b/Documentation/arm64/sve.rst index 9d9a4de5bc34..93c2c2990584 100644 --- a/Documentation/arm64/sve.rst +++ b/Documentation/arm64/sve.rst @@ -7,7 +7,9 @@ Author: Dave Martin <Dave.Martin@arm.com> Date: 4 August 2017 This document outlines briefly the interface provided to userspace by Linux in -order to support use of the ARM Scalable Vector Extension (SVE). +order to support use of the ARM Scalable Vector Extension (SVE), including +interactions with Streaming SVE mode added by the Scalable Matrix Extension +(SME). This is an outline of the most important features and issues only and not intended to be exhaustive. @@ -23,6 +25,10 @@ model features for SVE is included in Appendix A. * SVE registers Z0..Z31, P0..P15 and FFR and the current vector length VL, are tracked per-thread. +* In streaming mode FFR is not accessible unless HWCAP2_SME_FA64 is present + in the system, when it is not supported and these interfaces are used to + access streaming mode FFR is read and written as zero. + * The presence of SVE is reported to userspace via HWCAP_SVE in the aux vector AT_HWCAP entry. Presence of this flag implies the presence of the SVE instructions and registers, and the Linux-specific system interfaces @@ -53,10 +59,19 @@ model features for SVE is included in Appendix A. which userspace can read using an MRS instruction. See elf_hwcaps.txt and cpu-feature-registers.txt for details. +* On hardware that supports the SME extensions, HWCAP2_SME will also be + reported in the AT_HWCAP2 aux vector entry. Among other things SME adds + streaming mode which provides a subset of the SVE feature set using a + separate SME vector length and the same Z/V registers. See sme.rst + for more details. + * Debuggers should restrict themselves to interacting with the target via the NT_ARM_SVE regset. The recommended way of detecting support for this regset is to connect to a target process first and then attempt a - ptrace(PTRACE_GETREGSET, pid, NT_ARM_SVE, &iov). + ptrace(PTRACE_GETREGSET, pid, NT_ARM_SVE, &iov). Note that when SME is + present and streaming SVE mode is in use the FPSIMD subset of registers + will be read via NT_ARM_SVE and NT_ARM_SVE writes will exit streaming mode + in the target. * Whenever SVE scalable register values (Zn, Pn, FFR) are exchanged in memory between userspace and the kernel, the register value is encoded in memory in @@ -126,6 +141,11 @@ the SVE instruction set architecture. are only present in fpsimd_context. For convenience, the content of V0..V31 is duplicated between sve_context and fpsimd_context. +* The record contains a flag field which includes a flag SVE_SIG_FLAG_SM which + if set indicates that the thread is in streaming mode and the vector length + and register data (if present) describe the streaming SVE data and vector + length. + * The signal frame record for SVE always contains basic metadata, in particular the thread's vector length (in sve_context.vl). @@ -170,6 +190,11 @@ When returning from a signal handler: the signal frame does not match the current vector length, the signal return attempt is treated as illegal, resulting in a forced SIGSEGV. +* It is permitted to enter or leave streaming mode by setting or clearing + the SVE_SIG_FLAG_SM flag but applications should take care to ensure that + when doing so sve_context.vl and any register data are appropriate for the + vector length in the new mode. + 6. prctl extensions -------------------- @@ -265,8 +290,14 @@ prctl(PR_SVE_GET_VL) 7. ptrace extensions --------------------- -* A new regset NT_ARM_SVE is defined for use with PTRACE_GETREGSET and - PTRACE_SETREGSET. +* New regsets NT_ARM_SVE and NT_ARM_SSVE are defined for use with + PTRACE_GETREGSET and PTRACE_SETREGSET. NT_ARM_SSVE describes the + streaming mode SVE registers and NT_ARM_SVE describes the + non-streaming mode SVE registers. + + In this description a register set is referred to as being "live" when + the target is in the appropriate streaming or non-streaming mode and is + using data beyond the subset shared with the FPSIMD Vn registers. Refer to [2] for definitions. @@ -297,7 +328,7 @@ The regset data starts with struct user_sve_header, containing: flags - either + at most one of SVE_PT_REGS_FPSIMD @@ -331,6 +362,10 @@ The regset data starts with struct user_sve_header, containing: SVE_PT_VL_ONEXEC (SETREGSET only). + If neither FPSIMD nor SVE flags are provided then no register + payload is available, this is only possible when SME is implemented. + + * The effects of changing the vector length and/or flags are equivalent to those documented for PR_SVE_SET_VL. @@ -346,6 +381,13 @@ The regset data starts with struct user_sve_header, containing: case only the vector length and flags are changed (along with any consequences of those changes). +* In systems supporting SME when in streaming mode a GETREGSET for + NT_REG_SVE will return only the user_sve_header with no register data, + similarly a GETREGSET for NT_REG_SSVE will not return any register data + when not in streaming mode. + +* A GETREGSET for NT_ARM_SSVE will never return SVE_PT_REGS_FPSIMD. + * For SETREGSET, if an SVE_PT_REGS_SVE payload is present and the requested VL is not supported, the effect will be the same as if the payload were omitted, except that an EIO error is reported. No @@ -355,17 +397,25 @@ The regset data starts with struct user_sve_header, containing: unspecified. It is up to the caller to translate the payload layout for the actual VL and retry. +* Where SME is implemented it is not possible to GETREGSET the register + state for normal SVE when in streaming mode, nor the streaming mode + register state when in normal mode, regardless of the implementation defined + behaviour of the hardware for sharing data between the two modes. + +* Any SETREGSET of NT_ARM_SVE will exit streaming mode if the target was in + streaming mode and any SETREGSET of NT_ARM_SSVE will enter streaming mode + if the target was not in streaming mode. + * The effect of writing a partial, incomplete payload is unspecified. 8. ELF coredump extensions --------------------------- -* A NT_ARM_SVE note will be added to each coredump for each thread of the - dumped process. The contents will be equivalent to the data that would have - been read if a PTRACE_GETREGSET of NT_ARM_SVE were executed for each thread - when the coredump was generated. - +* NT_ARM_SVE and NT_ARM_SSVE notes will be added to each coredump for + each thread of the dumped process. The contents will be equivalent to the + data that would have been read if a PTRACE_GETREGSET of the corresponding + type were executed for each thread when the coredump was generated. 9. System runtime configuration -------------------------------- diff --git a/Documentation/devicetree/bindings/clock/microchip,mpfs.yaml b/Documentation/devicetree/bindings/clock/microchip,mpfs.yaml index 0c15afa2214c..016a4f378b9b 100644 --- a/Documentation/devicetree/bindings/clock/microchip,mpfs.yaml +++ b/Documentation/devicetree/bindings/clock/microchip,mpfs.yaml @@ -22,7 +22,16 @@ properties: const: microchip,mpfs-clkcfg reg: - maxItems: 1 + items: + - description: | + clock config registers: + These registers contain enable, reset & divider tables for the, cpu, + axi, ahb and rtc/mtimer reference clocks as well as enable and reset + for the peripheral clocks. + - description: | + mss pll dri registers: + Block of registers responsible for dynamic reconfiguration of the mss + pll clocks: maxItems: 1 @@ -51,7 +60,7 @@ examples: #size-cells = <2>; clkcfg: clock-controller@20002000 { compatible = "microchip,mpfs-clkcfg"; - reg = <0x0 0x20002000 0x0 0x1000>; + reg = <0x0 0x20002000 0x0 0x1000>, <0x0 0x3E001000 0x0 0x1000>; clocks = <&ref>; #clock-cells = <1>; }; diff --git a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml index e614fe3187bb..d09d79d7406a 100644 --- a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml +++ b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml @@ -29,6 +29,7 @@ properties: interrupts: description: Interrupt lines for each GPI instance + minItems: 1 maxItems: 13 "#dma-cells": diff --git a/Documentation/devicetree/bindings/mfd/atmel-flexcom.txt b/Documentation/devicetree/bindings/mfd/atmel-flexcom.txt index 692300117c64..9d837535637b 100644 --- a/Documentation/devicetree/bindings/mfd/atmel-flexcom.txt +++ b/Documentation/devicetree/bindings/mfd/atmel-flexcom.txt @@ -54,7 +54,7 @@ flexcom@f8034000 { clock-names = "spi_clk"; atmel,fifo-size = <32>; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at25f512b"; reg = <0>; spi-max-frequency = <20000000>; diff --git a/Documentation/devicetree/bindings/net/dsa/realtek.yaml b/Documentation/devicetree/bindings/net/dsa/realtek.yaml index 8756060895a8..99ee4b5b9346 100644 --- a/Documentation/devicetree/bindings/net/dsa/realtek.yaml +++ b/Documentation/devicetree/bindings/net/dsa/realtek.yaml @@ -27,32 +27,25 @@ description: The realtek-mdio driver is an MDIO driver and it must be inserted inside an MDIO node. + The compatible string is only used to identify which (silicon) family the + switch belongs to. Roughly speaking, a family is any set of Realtek switches + whose chip identification register(s) have a common location and semantics. + The different models in a given family can be automatically disambiguated by + parsing the chip identification register(s) according to the given family, + avoiding the need for a unique compatible string for each model. + properties: compatible: enum: - realtek,rtl8365mb - - realtek,rtl8366 - realtek,rtl8366rb - - realtek,rtl8366s - - realtek,rtl8367 - - realtek,rtl8367b - - realtek,rtl8367rb - - realtek,rtl8367s - - realtek,rtl8368s - - realtek,rtl8369 - - realtek,rtl8370 description: | - realtek,rtl8365mb: 4+1 ports - realtek,rtl8366: 5+1 ports - realtek,rtl8366rb: 5+1 ports - realtek,rtl8366s: 5+1 ports - realtek,rtl8367: - realtek,rtl8367b: - realtek,rtl8367rb: 5+2 ports - realtek,rtl8367s: 5+2 ports - realtek,rtl8368s: 8 ports - realtek,rtl8369: 8+1 ports - realtek,rtl8370: 8+2 ports + realtek,rtl8365mb: + Use with models RTL8363NB, RTL8363NB-VB, RTL8363SC, RTL8363SC-VB, + RTL8364NB, RTL8364NB-VB, RTL8365MB, RTL8366SC, RTL8367RB-VB, RTL8367S, + RTL8367SB, RTL8370MB, RTL8310SR + realtek,rtl8366rb: + Use with models RTL8366RB, RTL8366S mdc-gpios: description: GPIO line for the MDC clock line. @@ -335,7 +328,7 @@ examples: #size-cells = <0>; switch@29 { - compatible = "realtek,rtl8367s"; + compatible = "realtek,rtl8365mb"; reg = <29>; reset-gpios = <&gpio2 20 GPIO_ACTIVE_LOW>; diff --git a/Documentation/devicetree/bindings/regulator/richtek,rt5190a-regulator.yaml b/Documentation/devicetree/bindings/regulator/richtek,rt5190a-regulator.yaml index 28725c5467fc..edb411be0390 100644 --- a/Documentation/devicetree/bindings/regulator/richtek,rt5190a-regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/richtek,rt5190a-regulator.yaml @@ -58,7 +58,7 @@ properties: type: object $ref: regulator.yaml# description: | - regulator description for buck1 and buck4. + regulator description for buck1 to buck4, and ldo. properties: regulator-allowed-modes: diff --git a/Documentation/devicetree/bindings/rtc/microchip,mfps-rtc.yaml b/Documentation/devicetree/bindings/rtc/microchip,mfps-rtc.yaml index a2e984ea3553..500c62becd6b 100644 --- a/Documentation/devicetree/bindings/rtc/microchip,mfps-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/microchip,mfps-rtc.yaml @@ -31,11 +31,19 @@ properties: to that of the RTC's count register. clocks: - maxItems: 1 + items: + - description: | + AHB clock + - description: | + Reference clock: divided by the prescaler to create a time-based + strobe (typically 1 Hz) for the calendar counter. By default, the rtc + on the PolarFire SoC shares it's reference with MTIMER so this will + be a 1 MHz clock. clock-names: items: - const: rtc + - const: rtcref required: - compatible @@ -48,11 +56,12 @@ additionalProperties: false examples: - | + #include "dt-bindings/clock/microchip,mpfs-clock.h" rtc@20124000 { compatible = "microchip,mpfs-rtc"; reg = <0x20124000 0x1000>; - clocks = <&clkcfg 21>; - clock-names = "rtc"; + clocks = <&clkcfg CLK_RTC>, <&clkcfg CLK_RTCREF>; + clock-names = "rtc", "rtcref"; interrupts = <80>, <81>; }; ... diff --git a/Documentation/devicetree/bindings/usb/samsung,exynos-usb2.yaml b/Documentation/devicetree/bindings/usb/samsung,exynos-usb2.yaml index 340dff8d19c3..9c92defbba01 100644 --- a/Documentation/devicetree/bindings/usb/samsung,exynos-usb2.yaml +++ b/Documentation/devicetree/bindings/usb/samsung,exynos-usb2.yaml @@ -62,6 +62,7 @@ required: - interrupts - phys - phy-names + - reg allOf: - if: diff --git a/Documentation/filesystems/ext4/attributes.rst b/Documentation/filesystems/ext4/attributes.rst index 54386a010a8d..871d2da7a0a9 100644 --- a/Documentation/filesystems/ext4/attributes.rst +++ b/Documentation/filesystems/ext4/attributes.rst @@ -76,7 +76,7 @@ The beginning of an extended attribute block is in - Checksum of the extended attribute block. * - 0x14 - \_\_u32 - - h\_reserved[2] + - h\_reserved[3] - Zero. The checksum is calculated against the FS UUID, the 64-bit block number diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst index 4a2426f0485a..ad8dc8c040a2 100644 --- a/Documentation/filesystems/f2fs.rst +++ b/Documentation/filesystems/f2fs.rst @@ -235,12 +235,6 @@ offgrpjquota Turn off group journalled quota. offprjjquota Turn off project journalled quota. quota Enable plain user disk quota accounting. noquota Disable all plain disk quota option. -whint_mode=%s Control which write hints are passed down to block - layer. This supports "off", "user-based", and - "fs-based". In "off" mode (default), f2fs does not pass - down hints. In "user-based" mode, f2fs tries to pass - down hints given by users. And in "fs-based" mode, f2fs - passes down hints with its policy. alloc_mode=%s Adjust block allocation policy, which supports "reuse" and "default". fsync_mode=%s Control the policy of fsync. Currently supports "posix", @@ -751,70 +745,6 @@ In order to identify whether the data in the victim segment are valid or not, F2FS manages a bitmap. Each bit represents the validity of a block, and the bitmap is composed of a bit stream covering whole blocks in main area. -Write-hint Policy ------------------ - -1) whint_mode=off. F2FS only passes down WRITE_LIFE_NOT_SET. - -2) whint_mode=user-based. F2FS tries to pass down hints given by -users. - -===================== ======================== =================== -User F2FS Block -===================== ======================== =================== -N/A META WRITE_LIFE_NOT_SET -N/A HOT_NODE " -N/A WARM_NODE " -N/A COLD_NODE " -ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME -extension list " " - --- buffered io -WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME -WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT -WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET -WRITE_LIFE_NONE " " -WRITE_LIFE_MEDIUM " " -WRITE_LIFE_LONG " " - --- direct io -WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME -WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT -WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET -WRITE_LIFE_NONE " WRITE_LIFE_NONE -WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM -WRITE_LIFE_LONG " WRITE_LIFE_LONG -===================== ======================== =================== - -3) whint_mode=fs-based. F2FS passes down hints with its policy. - -===================== ======================== =================== -User F2FS Block -===================== ======================== =================== -N/A META WRITE_LIFE_MEDIUM; -N/A HOT_NODE WRITE_LIFE_NOT_SET -N/A WARM_NODE " -N/A COLD_NODE WRITE_LIFE_NONE -ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME -extension list " " - --- buffered io -WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME -WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT -WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_LONG -WRITE_LIFE_NONE " " -WRITE_LIFE_MEDIUM " " -WRITE_LIFE_LONG " " - --- direct io -WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME -WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT -WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET -WRITE_LIFE_NONE " WRITE_LIFE_NONE -WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM -WRITE_LIFE_LONG " WRITE_LIFE_LONG -===================== ======================== =================== - Fallocate(2) Policy ------------------- diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index b0024aa7b051..66828293d9cb 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -267,6 +267,13 @@ ipfrag_max_dist - INTEGER from different IP datagrams, which could result in data corruption. Default: 64 +bc_forwarding - INTEGER + bc_forwarding enables the feature described in rfc1812#section-5.3.5.2 + and rfc2644. It allows the router to forward directed broadcast. + To enable this feature, the 'all' entry and the input interface entry + should be set to 1. + Default: 0 + INET peer storage ================= diff --git a/Documentation/security/siphash.rst b/Documentation/security/siphash.rst index bd9363025fcb..a10380cb78e5 100644 --- a/Documentation/security/siphash.rst +++ b/Documentation/security/siphash.rst @@ -121,26 +121,36 @@ even scarier, uses an easily brute-forcable 64-bit key (with a 32-bit output) instead of SipHash's 128-bit key. However, this may appeal to some high-performance `jhash` users. -Danger! - -Do not ever use HalfSipHash except for as a hashtable key function, and only -then when you can be absolutely certain that the outputs will never be -transmitted out of the kernel. This is only remotely useful over `jhash` as a -means of mitigating hashtable flooding denial of service attacks. - -Generating a HalfSipHash key -============================ +HalfSipHash support is provided through the "hsiphash" family of functions. + +.. warning:: + Do not ever use the hsiphash functions except for as a hashtable key + function, and only then when you can be absolutely certain that the outputs + will never be transmitted out of the kernel. This is only remotely useful + over `jhash` as a means of mitigating hashtable flooding denial of service + attacks. + +On 64-bit kernels, the hsiphash functions actually implement SipHash-1-3, a +reduced-round variant of SipHash, instead of HalfSipHash-1-3. This is because in +64-bit code, SipHash-1-3 is no slower than HalfSipHash-1-3, and can be faster. +Note, this does *not* mean that in 64-bit kernels the hsiphash functions are the +same as the siphash ones, or that they are secure; the hsiphash functions still +use a less secure reduced-round algorithm and truncate their outputs to 32 +bits. + +Generating a hsiphash key +========================= Keys should always be generated from a cryptographically secure source of -random numbers, either using get_random_bytes or get_random_once: +random numbers, either using get_random_bytes or get_random_once:: -hsiphash_key_t key; -get_random_bytes(&key, sizeof(key)); + hsiphash_key_t key; + get_random_bytes(&key, sizeof(key)); If you're not deriving your key from here, you're doing it wrong. -Using the HalfSipHash functions -=============================== +Using the hsiphash functions +============================ There are two variants of the function, one that takes a list of integers, and one that takes a buffer:: @@ -183,7 +193,7 @@ You may then iterate like usual over the returned hash bucket. Performance =========== -HalfSipHash is roughly 3 times slower than JenkinsHash. For many replacements, -this will not be a problem, as the hashtable lookup isn't the bottleneck. And -in general, this is probably a good sacrifice to make for the security and DoS -resistance of HalfSipHash. +hsiphash() is roughly 3 times slower than jhash(). For many replacements, this +will not be a problem, as the hashtable lookup isn't the bottleneck. And in +general, this is probably a good sacrifice to make for the security and DoS +resistance of hsiphash(). diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 85c7abc51af5..47c483d440f3 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -1476,14 +1476,43 @@ Possible values are: [s390] KVM_MP_STATE_LOAD the vcpu is in a special load/startup state [s390] + KVM_MP_STATE_SUSPENDED the vcpu is in a suspend state and is waiting + for a wakeup event [arm64] ========================== =============================================== 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 arm64/riscv: -^^^^^^^^^^^^^^^^ +For arm64: +^^^^^^^^^^ + +If a vCPU is in the KVM_MP_STATE_SUSPENDED state, KVM will emulate the +architectural execution of a WFI instruction. + +If a wakeup event is recognized, KVM will exit to userspace with a +KVM_SYSTEM_EVENT exit, where the event type is KVM_SYSTEM_EVENT_WAKEUP. If +userspace wants to honor the wakeup, it must set the vCPU's MP state to +KVM_MP_STATE_RUNNABLE. If it does not, KVM will continue to await a wakeup +event in subsequent calls to KVM_RUN. + +.. warning:: + + If userspace intends to keep the vCPU in a SUSPENDED state, it is + strongly recommended that userspace take action to suppress the + wakeup event (such as masking an interrupt). Otherwise, subsequent + calls to KVM_RUN will immediately exit with a KVM_SYSTEM_EVENT_WAKEUP + event and inadvertently waste CPU cycles. + + Additionally, if userspace takes action to suppress a wakeup event, + it is strongly recommended that it also restores the vCPU to its + original state when the vCPU is made RUNNABLE again. For example, + if userspace masked a pending interrupt to suppress the wakeup, + the interrupt should be unmasked before returning control to the + guest. + +For riscv: +^^^^^^^^^^ 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. @@ -2601,6 +2630,24 @@ EINVAL. After the vcpu's SVE configuration is finalized, further attempts to write this register will fail with EPERM. +arm64 bitmap feature firmware pseudo-registers have the following bit pattern:: + + 0x6030 0000 0016 <regno:16> + +The bitmap feature firmware registers exposes the hypercall services that +are available for userspace to configure. The set bits corresponds to the +services that are available for the guests to access. By default, KVM +sets all the supported bits during VM initialization. The userspace can +discover the available services via KVM_GET_ONE_REG, and write back the +bitmap corresponding to the features that it wishes guests to see via +KVM_SET_ONE_REG. + +Note: These registers are immutable once any of the vCPUs of the VM has +run at least once. A KVM_SET_ONE_REG in such a scenario will return +a -EBUSY to userspace. + +(See Documentation/virt/kvm/arm/hypercalls.rst for more details.) + MIPS registers are mapped using the lower 32 bits. The upper 16 of that is the register group type: @@ -5985,17 +6032,19 @@ should put the acknowledged interrupt vector into the 'epr' field. #define KVM_SYSTEM_EVENT_SHUTDOWN 1 #define KVM_SYSTEM_EVENT_RESET 2 #define KVM_SYSTEM_EVENT_CRASH 3 + #define KVM_SYSTEM_EVENT_WAKEUP 4 + #define KVM_SYSTEM_EVENT_SUSPEND 5 __u32 type; - __u64 flags; + __u32 ndata; + __u64 data[16]; } system_event; If exit_reason is KVM_EXIT_SYSTEM_EVENT then the vcpu has triggered a system-level event using some architecture specific mechanism (hypercall or some special instruction). In case of ARM64, this is triggered using -HVC instruction based PSCI call from the vcpu. The 'type' field describes -the system-level event type. The 'flags' field describes architecture -specific flags for the system-level event. +HVC instruction based PSCI call from the vcpu. +The 'type' field describes the system-level event type. Valid values for 'type' are: - KVM_SYSTEM_EVENT_SHUTDOWN -- the guest has requested a shutdown of the @@ -6009,11 +6058,52 @@ Valid values for 'type' are: 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_SYSTEM_EVENT_WAKEUP -- the exiting vCPU is in a suspended state and + KVM has recognized a wakeup event. Userspace may honor this event by + marking the exiting vCPU as runnable, or deny it and call KVM_RUN again. + - KVM_SYSTEM_EVENT_SUSPEND -- the guest has requested a suspension of + the VM. -Valid flags are: +For arm/arm64: +-------------- - - KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2 (arm64 only) -- the guest issued - a SYSTEM_RESET2 call according to v1.1 of the PSCI specification. + KVM_SYSTEM_EVENT_SUSPEND exits are enabled with the + KVM_CAP_ARM_SYSTEM_SUSPEND VM capability. If a guest invokes the PSCI + SYSTEM_SUSPEND function, KVM will exit to userspace with this event + type. + + It is the sole responsibility of userspace to implement the PSCI + SYSTEM_SUSPEND call according to ARM DEN0022D.b 5.19 "SYSTEM_SUSPEND". + KVM does not change the vCPU's state before exiting to userspace, so + the call parameters are left in-place in the vCPU registers. + + Userspace is _required_ to take action for such an exit. It must + either: + + - Honor the guest request to suspend the VM. Userspace can request + in-kernel emulation of suspension by setting the calling vCPU's + state to KVM_MP_STATE_SUSPENDED. Userspace must configure the vCPU's + state according to the parameters passed to the PSCI function when + the calling vCPU is resumed. See ARM DEN0022D.b 5.19.1 "Intended use" + for details on the function parameters. + + - Deny the guest request to suspend the VM. See ARM DEN0022D.b 5.19.2 + "Caller responsibilities" for possible return values. + +If KVM_CAP_SYSTEM_EVENT_DATA is present, the 'data' field can contain +architecture specific information for the system-level event. Only +the first `ndata` items (possibly zero) of the data array are valid. + + - for arm64, data[0] is set to KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2 if + the guest issued a SYSTEM_RESET2 call according to v1.1 of the PSCI + specification. + + - for RISC-V, data[0] is set to the value of the second argument of the + ``sbi_system_reset`` call. + +Previous versions of Linux defined a `flags` member in this struct. The +field is now aliased to `data[0]`. Userspace can assume that it is only +written if ndata is greater than 0. :: @@ -7724,6 +7814,16 @@ At this time, KVM_PMU_CAP_DISABLE is the only capability. Setting this capability will disable PMU virtualization for that VM. Usermode should adjust CPUID leaf 0xA to reflect that the PMU is disabled. +8.36 KVM_CAP_ARM_SYSTEM_SUSPEND +------------------------------- + +:Capability: KVM_CAP_ARM_SYSTEM_SUSPEND +:Architectures: arm64 +:Type: vm + +When enabled, KVM will exit to userspace with KVM_EXIT_SYSTEM_EVENT of +type KVM_SYSTEM_EVENT_SUSPEND to process the guest suspend request. + 9. Known KVM API problems ========================= diff --git a/Documentation/virt/kvm/arm/hypercalls.rst b/Documentation/virt/kvm/arm/hypercalls.rst new file mode 100644 index 000000000000..3e23084644ba --- /dev/null +++ b/Documentation/virt/kvm/arm/hypercalls.rst @@ -0,0 +1,138 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================= +ARM Hypercall Interface +======================= + +KVM handles the hypercall services as requested by the guests. New hypercall +services are regularly made available by the ARM specification or by KVM (as +vendor services) if they make sense from a virtualization point of view. + +This means that a guest booted on two different versions of KVM can observe +two different "firmware" revisions. This could cause issues if a given guest +is tied to a particular version of a hypercall service, or if a migration +causes a different version to be exposed out of the blue to an unsuspecting +guest. + +In order to remedy this situation, KVM exposes a set of "firmware +pseudo-registers" that can be manipulated using the GET/SET_ONE_REG +interface. These registers can be saved/restored by userspace, and set +to a convenient value as required. + +The following registers are defined: + +* KVM_REG_ARM_PSCI_VERSION: + + 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. + + - Only valid if the vcpu has the KVM_ARM_VCPU_PSCI_0_2 feature set + (and thus has already been initialized) + - Returns the current PSCI version on GET_ONE_REG (defaulting to the + highest PSCI version implemented by KVM and compatible with v0.2) + - Allows any PSCI version implemented by KVM and compatible with + v0.2 to be set with SET_ONE_REG + - 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]. + + Accepted values are: + + 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 + available to the guest and required for the mitigation. + 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]_. + + Accepted values are: + + 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 + unknown. KVM does not offer firmware support for the workaround. + 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. + + +Bitmap Feature Firmware Registers +--------------------------------- + +Contrary to the above registers, the following registers exposes the +hypercall services in the form of a feature-bitmap to the userspace. This +bitmap is translated to the services that are available to the guest. +There is a register defined per service call owner and can be accessed via +GET/SET_ONE_REG interface. + +By default, these registers are set with the upper limit of the features +that are supported. This way userspace can discover all the usable +hypercall services via GET_ONE_REG. The user-space can write-back the +desired bitmap back via SET_ONE_REG. The features for the registers that +are untouched, probably because userspace isn't aware of them, will be +exposed as is to the guest. + +Note that KVM will not allow the userspace to configure the registers +anymore once any of the vCPUs has run at least once. Instead, it will +return a -EBUSY. + +The pseudo-firmware bitmap register are as follows: + +* KVM_REG_ARM_STD_BMAP: + Controls the bitmap of the ARM Standard Secure Service Calls. + + The following bits are accepted: + + Bit-0: KVM_REG_ARM_STD_BIT_TRNG_V1_0: + The bit represents the services offered under v1.0 of ARM True Random + Number Generator (TRNG) specification, ARM DEN0098. + +* KVM_REG_ARM_STD_HYP_BMAP: + Controls the bitmap of the ARM Standard Hypervisor Service Calls. + + The following bits are accepted: + + Bit-0: KVM_REG_ARM_STD_HYP_BIT_PV_TIME: + The bit represents the Paravirtualized Time service as represented by + ARM DEN0057A. + +* KVM_REG_ARM_VENDOR_HYP_BMAP: + Controls the bitmap of the Vendor specific Hypervisor Service Calls. + + The following bits are accepted: + + Bit-0: KVM_REG_ARM_VENDOR_HYP_BIT_FUNC_FEAT + The bit represents the ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID + and ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID function-ids. + + Bit-1: KVM_REG_ARM_VENDOR_HYP_BIT_PTP: + The bit represents the Precision Time Protocol KVM service. + +Errors: + + ======= ============================================================= + -ENOENT Unknown register accessed. + -EBUSY Attempt a 'write' to the register after the VM has started. + -EINVAL Invalid bitmap written to the register. + ======= ============================================================= + +.. [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/arm/index.rst b/Documentation/virt/kvm/arm/index.rst index 78a9b670aafe..e84848432158 100644 --- a/Documentation/virt/kvm/arm/index.rst +++ b/Documentation/virt/kvm/arm/index.rst @@ -8,6 +8,6 @@ ARM :maxdepth: 2 hyp-abi - psci + hypercalls pvtime ptp_kvm diff --git a/Documentation/virt/kvm/arm/psci.rst b/Documentation/virt/kvm/arm/psci.rst deleted file mode 100644 index d52c2e83b5b8..000000000000 --- a/Documentation/virt/kvm/arm/psci.rst +++ /dev/null @@ -1,77 +0,0 @@ -.. 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. - -The PSCI specification is regularly updated to provide new features, -and KVM implements these updates if they make sense from a virtualization -point of view. - -This means that a guest booted on two different versions of KVM can -observe two different "firmware" revisions. This could cause issues if -a given guest is tied to a particular PSCI revision (unlikely), or if -a migration causes a different PSCI version to be exposed out of the -blue to an unsuspecting guest. - -In order to remedy this situation, KVM exposes a set of "firmware -pseudo-registers" that can be manipulated using the GET/SET_ONE_REG -interface. These registers can be saved/restored by userspace, and set -to a convenient value if required. - -The following register is defined: - -* KVM_REG_ARM_PSCI_VERSION: - - - Only valid if the vcpu has the KVM_ARM_VCPU_PSCI_0_2 feature set - (and thus has already been initialized) - - Returns the current PSCI version on GET_ONE_REG (defaulting to the - highest PSCI version implemented by KVM and compatible with v0.2) - - Allows any PSCI version implemented by KVM and compatible with - v0.2 to be set with SET_ONE_REG - - 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]. - - Accepted values are: - - 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 - available to the guest and required for the mitigation. - 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]_. - - Accepted values are: - - 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 - unknown. KVM does not offer firmware support for the workaround. - 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. - -.. [1] https://developer.arm.com/-/media/developer/pdf/ARM_DEN_0070A_Firmware_interfaces_for_mitigating_CVE-2017-5715.pdf diff --git a/Documentation/vm/page_owner.rst b/Documentation/vm/page_owner.rst index 65204d7f004f..7e0c3f574e78 100644 --- a/Documentation/vm/page_owner.rst +++ b/Documentation/vm/page_owner.rst @@ -110,7 +110,7 @@ Usage If you want to sort by the page nums of buf, use the ``-m`` parameter. The detailed parameters are: - fundamental function: + fundamental function:: Sort: -a Sort by memory allocation time. @@ -122,7 +122,7 @@ Usage -s Sort by stack trace. -t Sort by times (default). - additional function: + additional function:: Cull: --cull <rules> @@ -153,6 +153,7 @@ Usage STANDARD FORMAT SPECIFIERS ========================== +:: KEY LONG DESCRIPTION p pid process ID diff --git a/MAINTAINERS b/MAINTAINERS index 40fa1955ca3f..edc96cdb85e8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2644,6 +2644,7 @@ L: linux-samsung-soc@vger.kernel.org S: Maintained C: irc://irc.libera.chat/linux-exynos Q: https://patchwork.kernel.org/project/linux-samsung-soc/list/ +B: mailto:linux-samsung-soc@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/krzk/linux.git F: Documentation/arm/samsung/ F: Documentation/devicetree/bindings/arm/samsung/ @@ -3913,7 +3914,9 @@ BROADCOM BNXT_EN 50 GIGABIT ETHERNET DRIVER M: Michael Chan <michael.chan@broadcom.com> L: netdev@vger.kernel.org S: Supported +F: drivers/firmware/broadcom/tee_bnxt_fw.c F: drivers/net/ethernet/broadcom/bnxt/ +F: include/linux/firmware/broadcom/tee_bnxt_fw.h BROADCOM BRCM80211 IEEE802.11n WIRELESS DRIVER M: Arend van Spriel <aspriel@gmail.com> @@ -9337,14 +9340,12 @@ F: drivers/pci/hotplug/rpaphp* IBM Power SRIOV Virtual NIC Device Driver M: Dany Madden <drt@linux.ibm.com> -M: Sukadev Bhattiprolu <sukadev@linux.ibm.com> R: Thomas Falcon <tlfalcon@linux.ibm.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/ibm/ibmvnic.* IBM Power Virtual Accelerator Switchboard -M: Sukadev Bhattiprolu <sukadev@linux.ibm.com> L: linuxppc-dev@lists.ozlabs.org S: Supported F: arch/powerpc/include/asm/vas.h @@ -10239,8 +10240,6 @@ F: drivers/net/ethernet/sgi/ioc3-eth.c IOMAP FILESYSTEM LIBRARY M: Christoph Hellwig <hch@infradead.org> M: Darrick J. Wong <djwong@kernel.org> -M: linux-xfs@vger.kernel.org -M: linux-fsdevel@vger.kernel.org L: linux-xfs@vger.kernel.org L: linux-fsdevel@vger.kernel.org S: Supported @@ -10549,6 +10548,7 @@ M: Andrey Ryabinin <ryabinin.a.a@gmail.com> R: Alexander Potapenko <glider@google.com> R: Andrey Konovalov <andreyknvl@gmail.com> R: Dmitry Vyukov <dvyukov@google.com> +R: Vincenzo Frascino <vincenzo.frascino@arm.com> L: kasan-dev@googlegroups.com S: Maintained F: Documentation/dev-tools/kasan.rst @@ -11974,6 +11974,7 @@ M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> L: linux-pm@vger.kernel.org S: Supported +B: mailto:linux-samsung-soc@vger.kernel.org F: Documentation/devicetree/bindings/power/supply/maxim,max14577.yaml F: Documentation/devicetree/bindings/power/supply/maxim,max77693.yaml F: drivers/power/supply/max14577_charger.c @@ -11985,6 +11986,7 @@ M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> L: linux-kernel@vger.kernel.org S: Supported +B: mailto:linux-samsung-soc@vger.kernel.org F: Documentation/devicetree/bindings/*/maxim,max14577.yaml F: Documentation/devicetree/bindings/*/maxim,max77686.yaml F: Documentation/devicetree/bindings/*/maxim,max77693.yaml @@ -12678,6 +12680,7 @@ MEMORY CONTROLLER DRIVERS M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> L: linux-kernel@vger.kernel.org S: Maintained +B: mailto:krzysztof.kozlowski@linaro.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/krzk/linux-mem-ctrl.git F: Documentation/devicetree/bindings/memory-controllers/ F: drivers/memory/ @@ -13626,6 +13629,7 @@ F: net/core/drop_monitor.c NETWORKING DRIVERS M: "David S. Miller" <davem@davemloft.net> +M: Eric Dumazet <edumazet@google.com> M: Jakub Kicinski <kuba@kernel.org> M: Paolo Abeni <pabeni@redhat.com> L: netdev@vger.kernel.org @@ -13673,6 +13677,7 @@ F: tools/testing/selftests/drivers/net/dsa/ NETWORKING [GENERAL] M: "David S. Miller" <davem@davemloft.net> +M: Eric Dumazet <edumazet@google.com> M: Jakub Kicinski <kuba@kernel.org> M: Paolo Abeni <pabeni@redhat.com> L: netdev@vger.kernel.org @@ -13823,6 +13828,7 @@ M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> L: linux-nfc@lists.01.org (subscribers-only) L: netdev@vger.kernel.org S: Maintained +B: mailto:linux-nfc@lists.01.org F: Documentation/devicetree/bindings/net/nfc/ F: drivers/nfc/ F: include/linux/platform_data/nfcmrvl.h @@ -15609,6 +15615,7 @@ L: linux-samsung-soc@vger.kernel.org S: Maintained C: irc://irc.libera.chat/linux-exynos Q: https://patchwork.kernel.org/project/linux-samsung-soc/list/ +B: mailto:linux-samsung-soc@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/pinctrl/samsung.git F: Documentation/devicetree/bindings/pinctrl/samsung,pinctrl*yaml F: drivers/pinctrl/samsung/ @@ -17325,6 +17332,7 @@ M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Sylwester Nawrocki <s.nawrocki@samsung.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Supported +B: mailto:linux-samsung-soc@vger.kernel.org F: Documentation/devicetree/bindings/sound/samsung* F: sound/soc/samsung/ @@ -17369,6 +17377,7 @@ M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> L: linux-kernel@vger.kernel.org L: linux-samsung-soc@vger.kernel.org S: Supported +B: mailto:linux-samsung-soc@vger.kernel.org F: Documentation/devicetree/bindings/clock/samsung,s2mps11.yaml F: Documentation/devicetree/bindings/mfd/samsung,s2m*.yaml F: Documentation/devicetree/bindings/mfd/samsung,s5m*.yaml @@ -21434,6 +21443,15 @@ F: arch/x86/include/asm/uv/ F: arch/x86/kernel/apic/x2apic_uv_x.c F: arch/x86/platform/uv/ +X86 STACK UNWINDING +M: Josh Poimboeuf <jpoimboe@redhat.com> +M: Peter Zijlstra <peterz@infradead.org> +S: Supported +F: arch/x86/include/asm/unwind*.h +F: arch/x86/kernel/dumpstack.c +F: arch/x86/kernel/stacktrace.c +F: arch/x86/kernel/unwind_*.c + X86 VDSO M: Andy Lutomirski <luto@kernel.org> L: linux-kernel@vger.kernel.org @@ -21596,7 +21614,6 @@ F: drivers/xen/*swiotlb* XFS FILESYSTEM C: irc://irc.oftc.net/xfs M: Darrick J. Wong <djwong@kernel.org> -M: linux-xfs@vger.kernel.org L: linux-xfs@vger.kernel.org S: Supported W: http://xfs.org/ @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 18 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc5 NAME = Superb Owl # *DOCUMENTATION* diff --git a/arch/Kconfig b/arch/Kconfig index 29b0167c088b..31c4fdc4a4ba 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -854,10 +854,8 @@ config HAVE_ARCH_HUGE_VMAP # # Archs that select this would be capable of PMD-sized vmaps (i.e., -# arch_vmap_pmd_supported() returns true), and they must make no assumptions -# that vmalloc memory is mapped with PAGE_SIZE ptes. The VM_NO_HUGE_VMAP flag -# can be used to prohibit arch-specific allocations from using hugepages to -# help with this (e.g., modules may require it). +# arch_vmap_pmd_supported() returns true). The VM_ALLOW_HUGE_VMAP flag +# must be used to enable allocations to use hugepages. # config HAVE_ARCH_HUGE_VMALLOC depends on HAVE_ARCH_HUGE_VMAP diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index dcaa44e408ac..f48ba03e9b5e 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -275,7 +275,7 @@ cs-gpios = <&creg_gpio 0 GPIO_ACTIVE_LOW>, <&creg_gpio 1 GPIO_ACTIVE_LOW>; - spi-flash@0 { + flash@0 { compatible = "sst26wf016b", "jedec,spi-nor"; reg = <0>; #address-cells = <1>; diff --git a/arch/arc/include/asm/atomic-llsc.h b/arch/arc/include/asm/atomic-llsc.h index 088d348781c1..1b0ffaeee16d 100644 --- a/arch/arc/include/asm/atomic-llsc.h +++ b/arch/arc/include/asm/atomic-llsc.h @@ -5,7 +5,7 @@ #define arch_atomic_set(v, i) WRITE_ONCE(((v)->counter), (i)) -#define ATOMIC_OP(op, c_op, asm_op) \ +#define ATOMIC_OP(op, asm_op) \ static inline void arch_atomic_##op(int i, atomic_t *v) \ { \ unsigned int val; \ @@ -21,7 +21,7 @@ static inline void arch_atomic_##op(int i, atomic_t *v) \ : "cc"); \ } \ -#define ATOMIC_OP_RETURN(op, c_op, asm_op) \ +#define ATOMIC_OP_RETURN(op, asm_op) \ static inline int arch_atomic_##op##_return_relaxed(int i, atomic_t *v) \ { \ unsigned int val; \ @@ -42,7 +42,7 @@ static inline int arch_atomic_##op##_return_relaxed(int i, atomic_t *v) \ #define arch_atomic_add_return_relaxed arch_atomic_add_return_relaxed #define arch_atomic_sub_return_relaxed arch_atomic_sub_return_relaxed -#define ATOMIC_FETCH_OP(op, c_op, asm_op) \ +#define ATOMIC_FETCH_OP(op, asm_op) \ static inline int arch_atomic_fetch_##op##_relaxed(int i, atomic_t *v) \ { \ unsigned int val, orig; \ @@ -69,23 +69,23 @@ static inline int arch_atomic_fetch_##op##_relaxed(int i, atomic_t *v) \ #define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or_relaxed #define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor_relaxed -#define ATOMIC_OPS(op, c_op, asm_op) \ - ATOMIC_OP(op, c_op, asm_op) \ - ATOMIC_OP_RETURN(op, c_op, asm_op) \ - ATOMIC_FETCH_OP(op, c_op, asm_op) +#define ATOMIC_OPS(op, asm_op) \ + ATOMIC_OP(op, asm_op) \ + ATOMIC_OP_RETURN(op, asm_op) \ + ATOMIC_FETCH_OP(op, asm_op) -ATOMIC_OPS(add, +=, add) -ATOMIC_OPS(sub, -=, sub) +ATOMIC_OPS(add, add) +ATOMIC_OPS(sub, sub) #undef ATOMIC_OPS -#define ATOMIC_OPS(op, c_op, asm_op) \ - ATOMIC_OP(op, c_op, asm_op) \ - ATOMIC_FETCH_OP(op, c_op, asm_op) +#define ATOMIC_OPS(op, asm_op) \ + ATOMIC_OP(op, asm_op) \ + ATOMIC_FETCH_OP(op, asm_op) -ATOMIC_OPS(and, &=, and) -ATOMIC_OPS(andnot, &= ~, bic) -ATOMIC_OPS(or, |=, or) -ATOMIC_OPS(xor, ^=, xor) +ATOMIC_OPS(and, and) +ATOMIC_OPS(andnot, bic) +ATOMIC_OPS(or, or) +ATOMIC_OPS(xor, xor) #define arch_atomic_andnot arch_atomic_andnot diff --git a/arch/arc/include/asm/pgtable-levels.h b/arch/arc/include/asm/pgtable-levels.h index 7848348719b2..64ca25d199be 100644 --- a/arch/arc/include/asm/pgtable-levels.h +++ b/arch/arc/include/asm/pgtable-levels.h @@ -98,9 +98,6 @@ /* * 1st level paging: pgd */ -#define pgd_index(addr) ((addr) >> PGDIR_SHIFT) -#define pgd_offset(mm, addr) (((mm)->pgd) + pgd_index(addr)) -#define pgd_offset_k(addr) pgd_offset(&init_mm, addr) #define pgd_ERROR(e) \ pr_crit("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) diff --git a/arch/arc/kernel/disasm.c b/arch/arc/kernel/disasm.c index 03f8b1be0c3a..1e1db51b6941 100644 --- a/arch/arc/kernel/disasm.c +++ b/arch/arc/kernel/disasm.c @@ -366,7 +366,7 @@ void __kprobes disasm_instr(unsigned long addr, struct disasm_state *state, case op_SP: /* LD_S|LDB_S b,[sp,u7], ST_S|STB_S b,[sp,u7] */ /* note: we are ignoring possibility of: * ADD_S, SUB_S, PUSH_S, POP_S as these should not - * cause unaliged exception anyway */ + * cause unaligned exception anyway */ state->write = BITS(state->words[0], 6, 6); state->zz = BITS(state->words[0], 5, 5); if (state->zz) @@ -503,7 +503,6 @@ int __kprobes disasm_next_pc(unsigned long pc, struct pt_regs *regs, { struct disasm_state instr; - memset(&instr, 0, sizeof(struct disasm_state)); disasm_instr(pc, &instr, 0, regs, cregs); *next_pc = pc + instr.instr_len; diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index dd77a0c8f740..66ba549b520f 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -196,6 +196,7 @@ tracesys_exit: st r0, [sp, PT_r0] ; sys call return value in pt_regs ;POST Sys Call Ptrace Hook + mov r0, sp ; pt_regs needed bl @syscall_trace_exit b ret_from_exception ; NOT ret_from_system_call at is saves r0 which ; we'd done before calling post hook above diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index f748483628f2..3c1590c27fae 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -319,7 +319,7 @@ setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) regs->ret = (unsigned long)ksig->ka.sa.sa_handler; /* - * handler returns using sigreturn stub provided already by userpsace + * handler returns using sigreturn stub provided already by userspace * If not, nuke the process right away */ if(!(ksig->ka.sa.sa_flags & SA_RESTORER)) diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index 78e6d069b1c1..d947473f1e6d 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -35,7 +35,7 @@ EXPORT_SYMBOL_GPL(smp_atomic_ops_lock); struct plat_smp_ops __weak plat_smp_ops; -/* XXX: per cpu ? Only needed once in early seconday boot */ +/* XXX: per cpu ? Only needed once in early secondary boot */ struct task_struct *secondary_idle_tsk; /* Called from start_kernel */ @@ -274,7 +274,7 @@ static void ipi_send_msg_one(int cpu, enum ipi_msg_type msg) * and read back old value */ do { - new = old = READ_ONCE(*ipi_data_ptr); + new = old = *ipi_data_ptr; new |= 1U << msg; } while (cmpxchg(ipi_data_ptr, old, new) != old); diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c index d63ebd81f1c6..99a9b92ed98d 100644 --- a/arch/arc/kernel/unaligned.c +++ b/arch/arc/kernel/unaligned.c @@ -237,7 +237,7 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs, if (state.fault) goto fault; - /* clear any remanants of delay slot */ + /* clear any remnants of delay slot */ if (delay_mode(regs)) { regs->ret = regs->bta & ~1U; regs->status32 &= ~STATUS_DE_MASK; diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 8aa1231865d1..5446967ea98d 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -401,7 +401,7 @@ static inline void __before_dc_op(const int op) { if (op == OP_FLUSH_N_INV) { /* Dcache provides 2 cmd: FLUSH or INV - * INV inturn has sub-modes: DISCARD or FLUSH-BEFORE + * INV in turn has sub-modes: DISCARD or FLUSH-BEFORE * flush-n-inv is achieved by INV cmd but with IM=1 * So toggle INV sub-mode depending on op request and default */ diff --git a/arch/arm/boot/dts/am33xx-l4.dtsi b/arch/arm/boot/dts/am33xx-l4.dtsi index c9629cb5ccd1..7da42a5b959c 100644 --- a/arch/arm/boot/dts/am33xx-l4.dtsi +++ b/arch/arm/boot/dts/am33xx-l4.dtsi @@ -263,6 +263,8 @@ compatible = "ti,am3359-tscadc"; reg = <0x0 0x1000>; interrupts = <16>; + clocks = <&adc_tsc_fck>; + clock-names = "fck"; status = "disabled"; dmas = <&edma 53 0>, <&edma 57 0>; dma-names = "fifo0", "fifo1"; diff --git a/arch/arm/boot/dts/am3517-evm.dts b/arch/arm/boot/dts/am3517-evm.dts index 0d2fac98ce7d..c8b80f156ec9 100644 --- a/arch/arm/boot/dts/am3517-evm.dts +++ b/arch/arm/boot/dts/am3517-evm.dts @@ -161,6 +161,8 @@ /* HS USB Host PHY on PORT 1 */ hsusb1_phy: hsusb1_phy { + pinctrl-names = "default"; + pinctrl-0 = <&hsusb1_rst_pins>; compatible = "usb-nop-xceiv"; reset-gpios = <&gpio2 25 GPIO_ACTIVE_LOW>; /* gpio_57 */ #phy-cells = <0>; @@ -168,7 +170,9 @@ }; &davinci_emac { - status = "okay"; + pinctrl-names = "default"; + pinctrl-0 = <ðernet_pins>; + status = "okay"; }; &davinci_mdio { @@ -193,6 +197,8 @@ }; &i2c2 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c2_pins>; clock-frequency = <400000>; /* User DIP swithes [1:8] / User LEDS [1:2] */ tca6416: gpio@21 { @@ -205,6 +211,8 @@ }; &i2c3 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c3_pins>; clock-frequency = <400000>; }; @@ -223,6 +231,8 @@ }; &usbhshost { + pinctrl-names = "default"; + pinctrl-0 = <&hsusb1_pins>; port1-mode = "ehci-phy"; }; @@ -231,8 +241,35 @@ }; &omap3_pmx_core { - pinctrl-names = "default"; - pinctrl-0 = <&hsusb1_rst_pins>; + + ethernet_pins: pinmux_ethernet_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21fe, PIN_INPUT | MUX_MODE0) /* rmii_mdio_data */ + OMAP3_CORE1_IOPAD(0x2200, MUX_MODE0) /* rmii_mdio_clk */ + OMAP3_CORE1_IOPAD(0x2202, PIN_INPUT_PULLDOWN | MUX_MODE0) /* rmii_rxd0 */ + OMAP3_CORE1_IOPAD(0x2204, PIN_INPUT_PULLDOWN | MUX_MODE0) /* rmii_rxd1 */ + OMAP3_CORE1_IOPAD(0x2206, PIN_INPUT_PULLDOWN | MUX_MODE0) /* rmii_crs_dv */ + OMAP3_CORE1_IOPAD(0x2208, PIN_OUTPUT_PULLDOWN | MUX_MODE0) /* rmii_rxer */ + OMAP3_CORE1_IOPAD(0x220a, PIN_OUTPUT_PULLDOWN | MUX_MODE0) /* rmii_txd0 */ + OMAP3_CORE1_IOPAD(0x220c, PIN_OUTPUT_PULLDOWN | MUX_MODE0) /* rmii_txd1 */ + OMAP3_CORE1_IOPAD(0x220e, PIN_OUTPUT_PULLDOWN |MUX_MODE0) /* rmii_txen */ + OMAP3_CORE1_IOPAD(0x2210, PIN_INPUT_PULLDOWN | MUX_MODE0) /* rmii_50mhz_clk */ + >; + }; + + i2c2_pins: pinmux_i2c2_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21be, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c2_scl */ + OMAP3_CORE1_IOPAD(0x21c0, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c2_sda */ + >; + }; + + i2c3_pins: pinmux_i2c3_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21c2, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c3_scl */ + OMAP3_CORE1_IOPAD(0x21c4, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c3_sda */ + >; + }; leds_pins: pinmux_leds_pins { pinctrl-single,pins = < @@ -300,8 +337,6 @@ }; &omap3_pmx_core2 { - pinctrl-names = "default"; - pinctrl-0 = <&hsusb1_pins>; hsusb1_pins: pinmux_hsusb1_pins { pinctrl-single,pins = < diff --git a/arch/arm/boot/dts/am3517-som.dtsi b/arch/arm/boot/dts/am3517-som.dtsi index 8b669e2eafec..f7b680f6c48a 100644 --- a/arch/arm/boot/dts/am3517-som.dtsi +++ b/arch/arm/boot/dts/am3517-som.dtsi @@ -69,6 +69,8 @@ }; &i2c1 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_pins>; clock-frequency = <400000>; s35390a: s35390a@30 { @@ -179,6 +181,13 @@ &omap3_pmx_core { + i2c1_pins: pinmux_i2c1_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c1_scl */ + OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c1_sda */ + >; + }; + wl12xx_buffer_pins: pinmux_wl12xx_buffer_pins { pinctrl-single,pins = < OMAP3_CORE1_IOPAD(0x2156, PIN_OUTPUT | MUX_MODE4) /* mmc1_dat7.gpio_129 */ diff --git a/arch/arm/boot/dts/at91-dvk_su60_somc.dtsi b/arch/arm/boot/dts/at91-dvk_su60_somc.dtsi index c1c8650dafce..3542ad8a243e 100644 --- a/arch/arm/boot/dts/at91-dvk_su60_somc.dtsi +++ b/arch/arm/boot/dts/at91-dvk_su60_somc.dtsi @@ -44,7 +44,7 @@ status = "okay"; /* spi0.0: 4M Flash Macronix MX25R4035FM1IL0 */ - spi-flash@0 { + flash@0 { compatible = "mxicy,mx25u4035", "jedec,spi-nor"; spi-max-frequency = <33000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91-kizbox3-hs.dts b/arch/arm/boot/dts/at91-kizbox3-hs.dts index f7d90cf1bb77..2799b2a1f4d2 100644 --- a/arch/arm/boot/dts/at91-kizbox3-hs.dts +++ b/arch/arm/boot/dts/at91-kizbox3-hs.dts @@ -225,7 +225,7 @@ pinctrl_pio_io_reset: gpio_io_reset { pinmux = <PIN_PB30__GPIO>; bias-disable; - drive-open-drain; + drive-open-drain = <1>; output-low; }; pinctrl_pio_input: gpio_input { diff --git a/arch/arm/boot/dts/at91-kizbox3_common.dtsi b/arch/arm/boot/dts/at91-kizbox3_common.dtsi index 465664628419..abe27adfa4d6 100644 --- a/arch/arm/boot/dts/at91-kizbox3_common.dtsi +++ b/arch/arm/boot/dts/at91-kizbox3_common.dtsi @@ -211,7 +211,7 @@ pinmux = <PIN_PD12__FLEXCOM4_IO0>, //DATA <PIN_PD13__FLEXCOM4_IO1>; //CLK bias-disable; - drive-open-drain; + drive-open-drain = <1>; }; pinctrl_pwm0 { diff --git a/arch/arm/boot/dts/at91-q5xr5.dts b/arch/arm/boot/dts/at91-q5xr5.dts index 47a00062f01f..9cf60b6f695c 100644 --- a/arch/arm/boot/dts/at91-q5xr5.dts +++ b/arch/arm/boot/dts/at91-q5xr5.dts @@ -125,7 +125,7 @@ cs-gpios = <&pioA 3 GPIO_ACTIVE_HIGH>, <&pioC 11 GPIO_ACTIVE_LOW>, <0>, <0>; status = "okay"; - m25p80@0 { + flash@0 { compatible = "jedec,spi-nor"; spi-max-frequency = <20000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi b/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi index 21c86171e462..ba621783acdb 100644 --- a/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi +++ b/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi @@ -214,7 +214,7 @@ pinctrl-0 = <&pinctrl_qspi1_default>; status = "disabled"; - qspi1_flash: spi_flash@0 { + qspi1_flash: flash@0 { #address-cells = <1>; #size-cells = <1>; compatible = "jedec,spi-nor"; diff --git a/arch/arm/boot/dts/at91-sama5d27_wlsom1_ek.dts b/arch/arm/boot/dts/at91-sama5d27_wlsom1_ek.dts index c145c4e5ef58..5e8755f22784 100644 --- a/arch/arm/boot/dts/at91-sama5d27_wlsom1_ek.dts +++ b/arch/arm/boot/dts/at91-sama5d27_wlsom1_ek.dts @@ -191,7 +191,7 @@ &qspi1 { status = "okay"; - qspi1_flash: spi_flash@0 { + qspi1_flash: flash@0 { status = "okay"; }; }; diff --git a/arch/arm/boot/dts/at91-sama5d2_xplained.dts b/arch/arm/boot/dts/at91-sama5d2_xplained.dts index 9bf2ec0ba3e2..cdfe891f9a9e 100644 --- a/arch/arm/boot/dts/at91-sama5d2_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d2_xplained.dts @@ -137,7 +137,7 @@ pinctrl-0 = <&pinctrl_spi0_default>; status = "okay"; - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; reg = <0>; spi-max-frequency = <50000000>; diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts index d72c042f2850..a49c2966b41e 100644 --- a/arch/arm/boot/dts/at91-sama5d3_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts @@ -57,8 +57,8 @@ }; spi0: spi@f0004000 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_spi0_cs>; + pinctrl-names = "default", "cs"; + pinctrl-1 = <&pinctrl_spi0_cs>; cs-gpios = <&pioD 13 0>, <0>, <0>, <&pioD 16 0>; status = "okay"; }; @@ -171,8 +171,8 @@ }; spi1: spi@f8008000 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_spi1_cs>; + pinctrl-names = "default", "cs"; + pinctrl-1 = <&pinctrl_spi1_cs>; cs-gpios = <&pioC 25 0>; status = "okay"; }; diff --git a/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi b/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi index 710cb72bda5a..fd1086f52b40 100644 --- a/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi +++ b/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi @@ -49,7 +49,7 @@ cs-gpios = <&pioC 3 0>, <0>, <0>, <0>; status = "okay"; - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts index d241c24f0d83..e519d2747936 100644 --- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts @@ -81,8 +81,8 @@ }; spi1: spi@fc018000 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_spi0_cs>; + pinctrl-names = "default", "cs"; + pinctrl-1 = <&pinctrl_spi1_cs>; cs-gpios = <&pioB 21 0>; status = "okay"; }; @@ -140,7 +140,7 @@ atmel,pins = <AT91_PIOE 1 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>; }; - pinctrl_spi0_cs: spi0_cs_default { + pinctrl_spi1_cs: spi1_cs_default { atmel,pins = <AT91_PIOB 21 AT91_PERIPH_GPIO AT91_PINCTRL_NONE>; }; diff --git a/arch/arm/boot/dts/at91-sama5d4ek.dts b/arch/arm/boot/dts/at91-sama5d4ek.dts index fe432b6b7e95..7017f626f362 100644 --- a/arch/arm/boot/dts/at91-sama5d4ek.dts +++ b/arch/arm/boot/dts/at91-sama5d4ek.dts @@ -65,7 +65,7 @@ spi0: spi@f8010000 { cs-gpios = <&pioC 3 0>, <0>, <0>, <0>; status = "okay"; - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91-sama7g5ek.dts b/arch/arm/boot/dts/at91-sama7g5ek.dts index 08685a10eda1..d83f76a6cd6a 100644 --- a/arch/arm/boot/dts/at91-sama7g5ek.dts +++ b/arch/arm/boot/dts/at91-sama7g5ek.dts @@ -495,7 +495,7 @@ pinctrl_flx3_default: flx3_default { pinmux = <PIN_PD16__FLEXCOM3_IO0>, <PIN_PD17__FLEXCOM3_IO1>; - bias-disable; + bias-pull-up; }; pinctrl_flx4_default: flx4_default { @@ -655,7 +655,7 @@ <PIN_PB21__QSPI0_INT>; bias-disable; slew-rate = <0>; - atmel,drive-strength = <ATMEL_PIO_DRVSTR_HI>; + atmel,drive-strength = <ATMEL_PIO_DRVSTR_ME>; }; pinctrl_sdmmc0_default: sdmmc0_default { diff --git a/arch/arm/boot/dts/at91-vinco.dts b/arch/arm/boot/dts/at91-vinco.dts index a51a3372afa1..ebeaa6ab500e 100644 --- a/arch/arm/boot/dts/at91-vinco.dts +++ b/arch/arm/boot/dts/at91-vinco.dts @@ -59,7 +59,7 @@ spi0: spi@f8010000 { cs-gpios = <&pioC 3 0>, <0>, <0>, <0>; status = "okay"; - m25p80@0 { + flash@0 { compatible = "n25q32b", "jedec,spi-nor"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91rm9200ek.dts b/arch/arm/boot/dts/at91rm9200ek.dts index e1ef4e44e663..4624a6f076f8 100644 --- a/arch/arm/boot/dts/at91rm9200ek.dts +++ b/arch/arm/boot/dts/at91rm9200ek.dts @@ -73,7 +73,7 @@ spi0: spi@fffe0000 { status = "okay"; cs-gpios = <&pioA 3 0>, <0>, <0>, <0>; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <15000000>; reg = <0>; @@ -94,7 +94,7 @@ status = "okay"; }; - nor_flash@10000000 { + flash@10000000 { compatible = "cfi-flash"; reg = <0x10000000 0x800000>; linux,mtd-name = "physmap-flash.0"; diff --git a/arch/arm/boot/dts/at91sam9260ek.dts b/arch/arm/boot/dts/at91sam9260ek.dts index ce96345d28a3..6381088ba24f 100644 --- a/arch/arm/boot/dts/at91sam9260ek.dts +++ b/arch/arm/boot/dts/at91sam9260ek.dts @@ -92,7 +92,7 @@ spi0: spi@fffc8000 { cs-gpios = <0>, <&pioC 11 0>, <0>, <0>; - mtd_dataflash@1 { + flash@1 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <50000000>; reg = <1>; diff --git a/arch/arm/boot/dts/at91sam9261ek.dts b/arch/arm/boot/dts/at91sam9261ek.dts index beed819609e8..8f11c0b7d76d 100644 --- a/arch/arm/boot/dts/at91sam9261ek.dts +++ b/arch/arm/boot/dts/at91sam9261ek.dts @@ -145,7 +145,7 @@ cs-gpios = <&pioA 3 0>, <0>, <&pioA 28 0>, <0>; status = "okay"; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; reg = <0>; spi-max-frequency = <15000000>; diff --git a/arch/arm/boot/dts/at91sam9263ek.dts b/arch/arm/boot/dts/at91sam9263ek.dts index 71f60576761a..42e734020235 100644 --- a/arch/arm/boot/dts/at91sam9263ek.dts +++ b/arch/arm/boot/dts/at91sam9263ek.dts @@ -95,7 +95,7 @@ spi0: spi@fffa4000 { status = "okay"; cs-gpios = <&pioA 5 0>, <0>, <0>, <0>; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi index 87bb39060e8b..85c17dd1c8d5 100644 --- a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi +++ b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi @@ -110,7 +110,7 @@ spi0: spi@fffc8000 { cs-gpios = <0>, <&pioC 11 0>, <0>, <0>; - mtd_dataflash@1 { + flash@1 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <50000000>; reg = <1>; @@ -214,11 +214,23 @@ 24c512@50 { compatible = "atmel,24c512"; reg = <0x50>; + vcc-supply = <®_3v3>; }; wm8731: wm8731@1b { compatible = "wm8731"; reg = <0x1b>; + + /* PCK0 at 12MHz */ + clocks = <&pmc PMC_TYPE_SYSTEM 8>; + clock-names = "mclk"; + assigned-clocks = <&pmc PMC_TYPE_SYSTEM 8>; + assigned-clock-rates = <12000000>; + + HPVDD-supply = <&vcc_dac>; + AVDD-supply = <&vcc_dac>; + DCVDD-supply = <®_3v3>; + DBVDD-supply = <®_3v3>; }; }; @@ -254,4 +266,35 @@ atmel,ssc-controller = <&ssc0>; atmel,audio-codec = <&wm8731>; }; + + reg_5v: fixedregulator0 { + compatible = "regulator-fixed"; + regulator-name = "5V"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + + reg_3v3: fixedregulator1 { + compatible = "regulator-fixed"; + regulator-name = "3V3"; + vin-supply = <®_5v>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + reg_1v: fixedregulator2 { + compatible = "regulator-fixed"; + regulator-name = "1V"; + vin-supply = <®_5v>; + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <1000000>; + }; + + vcc_dac: fixedregulator3 { + compatible = "regulator-fixed"; + regulator-name = "VCC_DAC"; + vin-supply = <®_3v3>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; }; diff --git a/arch/arm/boot/dts/at91sam9m10g45ek.dts b/arch/arm/boot/dts/at91sam9m10g45ek.dts index b6256a20fbc7..e5db198a87a8 100644 --- a/arch/arm/boot/dts/at91sam9m10g45ek.dts +++ b/arch/arm/boot/dts/at91sam9m10g45ek.dts @@ -167,7 +167,7 @@ spi0: spi@fffa4000{ status = "okay"; cs-gpios = <&pioB 3 0>, <0>, <0>, <0>; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <13000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts index 2bc4e6e0a923..c905d7bfc771 100644 --- a/arch/arm/boot/dts/at91sam9n12ek.dts +++ b/arch/arm/boot/dts/at91sam9n12ek.dts @@ -119,7 +119,7 @@ spi0: spi@f0000000 { status = "okay"; cs-gpios = <&pioA 14 0>, <0>, <0>, <0>; - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91sam9rlek.dts b/arch/arm/boot/dts/at91sam9rlek.dts index 62981b39c815..d74b8d9d84aa 100644 --- a/arch/arm/boot/dts/at91sam9rlek.dts +++ b/arch/arm/boot/dts/at91sam9rlek.dts @@ -180,7 +180,7 @@ spi0: spi@fffcc000 { status = "okay"; cs-gpios = <&pioA 28 0>, <0>, <0>, <0>; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <15000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91sam9x5ek.dtsi b/arch/arm/boot/dts/at91sam9x5ek.dtsi index 6d1264de6060..5f4eaa618ab4 100644 --- a/arch/arm/boot/dts/at91sam9x5ek.dtsi +++ b/arch/arm/boot/dts/at91sam9x5ek.dtsi @@ -125,7 +125,7 @@ cs-gpios = <&pioA 14 0>, <0>, <0>, <0>; status = "disabled"; /* conflicts with mmc1 */ - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/dra7-l4.dtsi b/arch/arm/boot/dts/dra7-l4.dtsi index 0a11bacffc1f..5733e3a4ea8e 100644 --- a/arch/arm/boot/dts/dra7-l4.dtsi +++ b/arch/arm/boot/dts/dra7-l4.dtsi @@ -4188,11 +4188,11 @@ reg = <0x1d0010 0x4>; reg-names = "sysc"; ti,sysc-midle = <SYSC_IDLE_FORCE>, - <SYSC_IDLE_NO>, - <SYSC_IDLE_SMART>; + <SYSC_IDLE_NO>; ti,sysc-sidle = <SYSC_IDLE_FORCE>, <SYSC_IDLE_NO>, <SYSC_IDLE_SMART>; + power-domains = <&prm_vpe>; clocks = <&vpe_clkctrl DRA7_VPE_VPE_CLKCTRL 0>; clock-names = "fck"; #address-cells = <1>; diff --git a/arch/arm/boot/dts/imx6qdl-apalis.dtsi b/arch/arm/boot/dts/imx6qdl-apalis.dtsi index ed2739e39085..bd763bae596b 100644 --- a/arch/arm/boot/dts/imx6qdl-apalis.dtsi +++ b/arch/arm/boot/dts/imx6qdl-apalis.dtsi @@ -286,6 +286,8 @@ codec: sgtl5000@a { compatible = "fsl,sgtl5000"; reg = <0x0a>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_sgtl5000>; clocks = <&clks IMX6QDL_CLK_CKO>; VDDA-supply = <®_module_3v3_audio>; VDDIO-supply = <®_module_3v3>; @@ -517,8 +519,6 @@ MX6QDL_PAD_DISP0_DAT21__AUD4_TXD 0x130b0 MX6QDL_PAD_DISP0_DAT22__AUD4_TXFS 0x130b0 MX6QDL_PAD_DISP0_DAT23__AUD4_RXD 0x130b0 - /* SGTL5000 sys_mclk */ - MX6QDL_PAD_GPIO_5__CCM_CLKO1 0x130b0 >; }; @@ -811,6 +811,12 @@ >; }; + pinctrl_sgtl5000: sgtl5000grp { + fsl,pins = < + MX6QDL_PAD_GPIO_5__CCM_CLKO1 0x130b0 + >; + }; + pinctrl_spdif: spdifgrp { fsl,pins = < MX6QDL_PAD_GPIO_16__SPDIF_IN 0x1b0b0 diff --git a/arch/arm/boot/dts/imx6ull-colibri.dtsi b/arch/arm/boot/dts/imx6ull-colibri.dtsi index 7f35a06dff95..951a2a6c5a65 100644 --- a/arch/arm/boot/dts/imx6ull-colibri.dtsi +++ b/arch/arm/boot/dts/imx6ull-colibri.dtsi @@ -37,7 +37,7 @@ reg_sd1_vmmc: regulator-sd1-vmmc { compatible = "regulator-gpio"; - gpio = <&gpio5 9 GPIO_ACTIVE_HIGH>; + gpios = <&gpio5 9 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_snvs_reg_sd>; regulator-always-on; diff --git a/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts b/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts index 2a0a98fe67f0..3240c67e0c39 100644 --- a/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts +++ b/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts @@ -11,3 +11,18 @@ model = "LogicPD Zoom OMAP35xx SOM-LV Development Kit"; compatible = "logicpd,dm3730-som-lv-devkit", "ti,omap3430", "ti,omap3"; }; + +&omap3_pmx_core2 { + pinctrl-names = "default"; + pinctrl-0 = <&hsusb2_2_pins>; + hsusb2_2_pins: pinmux_hsusb2_2_pins { + pinctrl-single,pins = < + OMAP3430_CORE2_IOPAD(0x25f0, PIN_OUTPUT | MUX_MODE3) /* etk_d10.hsusb2_clk */ + OMAP3430_CORE2_IOPAD(0x25f2, PIN_OUTPUT | MUX_MODE3) /* etk_d11.hsusb2_stp */ + OMAP3430_CORE2_IOPAD(0x25f4, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d12.hsusb2_dir */ + OMAP3430_CORE2_IOPAD(0x25f6, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d13.hsusb2_nxt */ + OMAP3430_CORE2_IOPAD(0x25f8, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d14.hsusb2_data0 */ + OMAP3430_CORE2_IOPAD(0x25fa, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d15.hsusb2_data1 */ + >; + }; +}; diff --git a/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts b/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts index a604d92221a4..c757f0d7781c 100644 --- a/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts +++ b/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts @@ -11,3 +11,18 @@ model = "LogicPD Zoom DM3730 SOM-LV Development Kit"; compatible = "logicpd,dm3730-som-lv-devkit", "ti,omap3630", "ti,omap3"; }; + +&omap3_pmx_core2 { + pinctrl-names = "default"; + pinctrl-0 = <&hsusb2_2_pins>; + hsusb2_2_pins: pinmux_hsusb2_2_pins { + pinctrl-single,pins = < + OMAP3630_CORE2_IOPAD(0x25f0, PIN_OUTPUT | MUX_MODE3) /* etk_d10.hsusb2_clk */ + OMAP3630_CORE2_IOPAD(0x25f2, PIN_OUTPUT | MUX_MODE3) /* etk_d11.hsusb2_stp */ + OMAP3630_CORE2_IOPAD(0x25f4, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d12.hsusb2_dir */ + OMAP3630_CORE2_IOPAD(0x25f6, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d13.hsusb2_nxt */ + OMAP3630_CORE2_IOPAD(0x25f8, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d14.hsusb2_data0 */ + OMAP3630_CORE2_IOPAD(0x25fa, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d15.hsusb2_data1 */ + >; + }; +}; diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi index b56524cc7fe2..55b619c99e24 100644 --- a/arch/arm/boot/dts/logicpd-som-lv.dtsi +++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi @@ -265,21 +265,6 @@ }; }; -&omap3_pmx_core2 { - pinctrl-names = "default"; - pinctrl-0 = <&hsusb2_2_pins>; - hsusb2_2_pins: pinmux_hsusb2_2_pins { - pinctrl-single,pins = < - OMAP3630_CORE2_IOPAD(0x25f0, PIN_OUTPUT | MUX_MODE3) /* etk_d10.hsusb2_clk */ - OMAP3630_CORE2_IOPAD(0x25f2, PIN_OUTPUT | MUX_MODE3) /* etk_d11.hsusb2_stp */ - OMAP3630_CORE2_IOPAD(0x25f4, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d12.hsusb2_dir */ - OMAP3630_CORE2_IOPAD(0x25f6, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d13.hsusb2_nxt */ - OMAP3630_CORE2_IOPAD(0x25f8, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d14.hsusb2_data0 */ - OMAP3630_CORE2_IOPAD(0x25fa, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d15.hsusb2_data1 */ - >; - }; -}; - &uart2 { interrupts-extended = <&intc 73 &omap3_pmx_core OMAP3_UART2_RX>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi index 7e3d8147e2c1..0365f06165e9 100644 --- a/arch/arm/boot/dts/omap3-gta04.dtsi +++ b/arch/arm/boot/dts/omap3-gta04.dtsi @@ -31,6 +31,8 @@ aliases { display0 = &lcd; display1 = &tv0; + /delete-property/ mmc2; + /delete-property/ mmc3; }; ldo_3v3: fixedregulator { diff --git a/arch/arm/boot/dts/sama5d3xmb.dtsi b/arch/arm/boot/dts/sama5d3xmb.dtsi index a499de8a7a64..3652c9e24124 100644 --- a/arch/arm/boot/dts/sama5d3xmb.dtsi +++ b/arch/arm/boot/dts/sama5d3xmb.dtsi @@ -26,7 +26,7 @@ spi0: spi@f0004000 { dmas = <0>, <0>; /* Do not use DMA for spi0 */ - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/sama5d3xmb_cmp.dtsi b/arch/arm/boot/dts/sama5d3xmb_cmp.dtsi index fa9e5e2a745d..5d9e97fecf83 100644 --- a/arch/arm/boot/dts/sama5d3xmb_cmp.dtsi +++ b/arch/arm/boot/dts/sama5d3xmb_cmp.dtsi @@ -25,7 +25,7 @@ spi0: spi@f0004000 { dmas = <0>, <0>; /* Do not use DMA for spi0 */ - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/sama7g5.dtsi b/arch/arm/boot/dts/sama7g5.dtsi index 4decd3a91a76..f691c8f08d04 100644 --- a/arch/arm/boot/dts/sama7g5.dtsi +++ b/arch/arm/boot/dts/sama7g5.dtsi @@ -601,9 +601,9 @@ #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 39>; atmel,fifo-size = <32>; - dmas = <&dma0 AT91_XDMAC_DT_PERID(7)>, - <&dma0 AT91_XDMAC_DT_PERID(8)>; - dma-names = "rx", "tx"; + dmas = <&dma0 AT91_XDMAC_DT_PERID(8)>, + <&dma0 AT91_XDMAC_DT_PERID(7)>; + dma-names = "tx", "rx"; status = "disabled"; }; }; @@ -786,9 +786,9 @@ #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 46>; atmel,fifo-size = <32>; - dmas = <&dma0 AT91_XDMAC_DT_PERID(21)>, - <&dma0 AT91_XDMAC_DT_PERID(22)>; - dma-names = "rx", "tx"; + dmas = <&dma0 AT91_XDMAC_DT_PERID(22)>, + <&dma0 AT91_XDMAC_DT_PERID(21)>; + dma-names = "tx", "rx"; status = "disabled"; }; }; @@ -810,9 +810,9 @@ #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 47>; atmel,fifo-size = <32>; - dmas = <&dma0 AT91_XDMAC_DT_PERID(23)>, - <&dma0 AT91_XDMAC_DT_PERID(24)>; - dma-names = "rx", "tx"; + dmas = <&dma0 AT91_XDMAC_DT_PERID(24)>, + <&dma0 AT91_XDMAC_DT_PERID(23)>; + dma-names = "tx", "rx"; status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/usb_a9263.dts b/arch/arm/boot/dts/usb_a9263.dts index 8a0cfbfd0c45..b6cb9cdf8197 100644 --- a/arch/arm/boot/dts/usb_a9263.dts +++ b/arch/arm/boot/dts/usb_a9263.dts @@ -60,7 +60,7 @@ spi0: spi@fffa4000 { cs-gpios = <&pioB 15 GPIO_ACTIVE_HIGH>; status = "okay"; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; reg = <0>; spi-max-frequency = <15000000>; diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 6e0c8c19b35c..d6a6811f0539 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -673,6 +673,7 @@ CONFIG_VIDEO_STI_DELTA=m CONFIG_VIDEO_RENESAS_FDP1=m CONFIG_VIDEO_RENESAS_JPU=m CONFIG_VIDEO_RENESAS_VSP1=m +CONFIG_VIDEO_TEGRA_VDE=m CONFIG_V4L_TEST_DRIVERS=y CONFIG_VIDEO_VIVID=m CONFIG_VIDEO_ADV7180=m diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig index 289d022acc4b..c209722399d7 100644 --- a/arch/arm/configs/tegra_defconfig +++ b/arch/arm/configs/tegra_defconfig @@ -286,7 +286,8 @@ CONFIG_SERIO_NVEC_PS2=y CONFIG_NVEC_POWER=y CONFIG_NVEC_PAZ00=y CONFIG_STAGING_MEDIA=y -CONFIG_TEGRA_VDE=y +CONFIG_V4L_MEM2MEM_DRIVERS=y +CONFIG_VIDEO_TEGRA_VDE=y CONFIG_CHROME_PLATFORMS=y CONFIG_CROS_EC=y CONFIG_CROS_EC_I2C=m diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig index f7d993628cb7..a9c1efcf7c9c 100644 --- a/arch/arm/mach-exynos/Kconfig +++ b/arch/arm/mach-exynos/Kconfig @@ -17,7 +17,6 @@ menuconfig ARCH_EXYNOS select EXYNOS_PMU select EXYNOS_SROM select EXYNOS_PM_DOMAINS if PM_GENERIC_DOMAINS - select GPIOLIB select HAVE_ARM_ARCH_TIMER if ARCH_EXYNOS5 select HAVE_ARM_SCU if SMP select PINCTRL diff --git a/arch/arm/mach-omap2/omap4-common.c b/arch/arm/mach-omap2/omap4-common.c index 5c3845730dbf..0b80f8bcd304 100644 --- a/arch/arm/mach-omap2/omap4-common.c +++ b/arch/arm/mach-omap2/omap4-common.c @@ -314,10 +314,12 @@ void __init omap_gic_of_init(void) np = of_find_compatible_node(NULL, NULL, "arm,cortex-a9-gic"); gic_dist_base_addr = of_iomap(np, 0); + of_node_put(np); WARN_ON(!gic_dist_base_addr); np = of_find_compatible_node(NULL, NULL, "arm,cortex-a9-twd-timer"); twd_base = of_iomap(np, 0); + of_node_put(np); WARN_ON(!twd_base); skip_errata_init: diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index ec5b082f3de6..07eb69f9e7df 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -337,12 +337,15 @@ int __init arch_xen_unpopulated_init(struct resource **res) if (!nr_reg) { pr_err("No extended regions are found\n"); + of_node_put(np); return -EINVAL; } regs = kcalloc(nr_reg, sizeof(*regs), GFP_KERNEL); - if (!regs) + if (!regs) { + of_node_put(np); return -ENOMEM; + } /* * Create resource from extended regions provided by the hypervisor to be @@ -403,8 +406,8 @@ int __init arch_xen_unpopulated_init(struct resource **res) *res = &xen_resource; err: + of_node_put(np); kfree(regs); - return rc; } #endif @@ -424,8 +427,10 @@ static void __init xen_dt_guest_init(void) if (of_address_to_resource(xen_node, GRANT_TABLE_INDEX, &res)) { pr_err("Xen grant table region is not found\n"); + of_node_put(xen_node); return; } + of_node_put(xen_node); xen_grant_frames = res.start; } diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 57c4c995965f..0dbae092c9b9 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -175,8 +175,6 @@ config ARM64 select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE - select HAVE_DYNAMIC_FTRACE_WITH_REGS \ - if $(cc-option,-fpatchable-function-entry=2) select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \ if DYNAMIC_FTRACE_WITH_REGS select HAVE_EFFICIENT_UNALIGNED_ACCESS @@ -228,6 +226,17 @@ config ARM64 help ARM 64-bit (AArch64) Linux support. +config CLANG_SUPPORTS_DYNAMIC_FTRACE_WITH_REGS + def_bool CC_IS_CLANG + # https://github.com/ClangBuiltLinux/linux/issues/1507 + depends on AS_IS_GNU || (AS_IS_LLVM && (LD_IS_LLD || LD_VERSION >= 23600)) + select HAVE_DYNAMIC_FTRACE_WITH_REGS + +config GCC_SUPPORTS_DYNAMIC_FTRACE_WITH_REGS + def_bool CC_IS_GCC + depends on $(cc-option,-fpatchable-function-entry=2) + select HAVE_DYNAMIC_FTRACE_WITH_REGS + config 64BIT def_bool y @@ -678,7 +687,7 @@ config ARM64_ERRATUM_2051678 default y help This options adds the workaround for ARM Cortex-A510 erratum ARM64_ERRATUM_2051678. - Affected Coretex-A510 might not respect the ordering rules for + Affected Cortex-A510 might not respect the ordering rules for hardware update of the page table's dirty bit. The workaround is to not enable the feature on affected CPUs. @@ -1939,6 +1948,17 @@ config ARM64_SVE booting the kernel. If unsure and you are not observing these symptoms, you should assume that it is safe to say Y. +config ARM64_SME + bool "ARM Scalable Matrix Extension support" + default y + depends on ARM64_SVE + help + The Scalable Matrix Extension (SME) is an extension to the AArch64 + execution state which utilises a substantial subset of the SVE + instruction set, together with the addition of new architectural + register state capable of holding two dimensional matrix tiles to + enable various matrix operations. + config ARM64_MODULE_PLTS bool "Use PLTs to allow module memory to spill over into vmalloc area" depends on MODULES diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-a311d.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-a311d.dtsi index d61f43052a34..8e9ad1e51d66 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12b-a311d.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12b-a311d.dtsi @@ -11,26 +11,6 @@ compatible = "operating-points-v2"; opp-shared; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <731000>; - }; - - opp-250000000 { - opp-hz = /bits/ 64 <250000000>; - opp-microvolt = <731000>; - }; - - opp-500000000 { - opp-hz = /bits/ 64 <500000000>; - opp-microvolt = <731000>; - }; - - opp-667000000 { - opp-hz = /bits/ 64 <667000000>; - opp-microvolt = <731000>; - }; - opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <761000>; @@ -71,26 +51,6 @@ compatible = "operating-points-v2"; opp-shared; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <731000>; - }; - - opp-250000000 { - opp-hz = /bits/ 64 <250000000>; - opp-microvolt = <731000>; - }; - - opp-500000000 { - opp-hz = /bits/ 64 <500000000>; - opp-microvolt = <731000>; - }; - - opp-667000000 { - opp-hz = /bits/ 64 <667000000>; - opp-microvolt = <731000>; - }; - opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <731000>; diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-s922x.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-s922x.dtsi index 1e5d0ee5d541..44c23c984034 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12b-s922x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12b-s922x.dtsi @@ -11,26 +11,6 @@ compatible = "operating-points-v2"; opp-shared; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <731000>; - }; - - opp-250000000 { - opp-hz = /bits/ 64 <250000000>; - opp-microvolt = <731000>; - }; - - opp-500000000 { - opp-hz = /bits/ 64 <500000000>; - opp-microvolt = <731000>; - }; - - opp-667000000 { - opp-hz = /bits/ 64 <667000000>; - opp-microvolt = <731000>; - }; - opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <731000>; @@ -76,26 +56,6 @@ compatible = "operating-points-v2"; opp-shared; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <751000>; - }; - - opp-250000000 { - opp-hz = /bits/ 64 <250000000>; - opp-microvolt = <751000>; - }; - - opp-500000000 { - opp-hz = /bits/ 64 <500000000>; - opp-microvolt = <751000>; - }; - - opp-667000000 { - opp-hz = /bits/ 64 <667000000>; - opp-microvolt = <751000>; - }; - opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <771000>; diff --git a/arch/arm64/boot/dts/amlogic/meson-s4.dtsi b/arch/arm64/boot/dts/amlogic/meson-s4.dtsi index bf9ae1e1016b..480afa2cc61f 100644 --- a/arch/arm64/boot/dts/amlogic/meson-s4.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-s4.dtsi @@ -13,28 +13,28 @@ cpu0: cpu@0 { device_type = "cpu"; - compatible = "arm,cortex-a35","arm,armv8"; + compatible = "arm,cortex-a35"; reg = <0x0 0x0>; enable-method = "psci"; }; cpu1: cpu@1 { device_type = "cpu"; - compatible = "arm,cortex-a35","arm,armv8"; + compatible = "arm,cortex-a35"; reg = <0x0 0x1>; enable-method = "psci"; }; cpu2: cpu@2 { device_type = "cpu"; - compatible = "arm,cortex-a35","arm,armv8"; + compatible = "arm,cortex-a35"; reg = <0x0 0x2>; enable-method = "psci"; }; cpu3: cpu@3 { device_type = "cpu"; - compatible = "arm,cortex-a35","arm,armv8"; + compatible = "arm,cortex-a35"; reg = <0x0 0x3>; enable-method = "psci"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi-m5.dts b/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi-m5.dts index 5751c48620ed..cadba194b149 100644 --- a/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi-m5.dts +++ b/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi-m5.dts @@ -437,6 +437,7 @@ "", "eMMC_RST#", /* BOOT_12 */ "eMMC_DS", /* BOOT_13 */ + "", "", /* GPIOC */ "SD_D0_B", /* GPIOC_0 */ "SD_D1_B", /* GPIOC_1 */ diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi b/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi index 3c07a89bfd27..80737731af3f 100644 --- a/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi @@ -95,26 +95,6 @@ compatible = "operating-points-v2"; opp-shared; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <730000>; - }; - - opp-250000000 { - opp-hz = /bits/ 64 <250000000>; - opp-microvolt = <730000>; - }; - - opp-500000000 { - opp-hz = /bits/ 64 <500000000>; - opp-microvolt = <730000>; - }; - - opp-667000000 { - opp-hz = /bits/ 64 <666666666>; - opp-microvolt = <750000>; - }; - opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <770000>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi index 73addc0b8e57..cce55c3c5df0 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi @@ -146,12 +146,14 @@ &usbotg1 { dr_mode = "otg"; + over-current-active-low; vbus-supply = <®_usb_otg1_vbus>; status = "okay"; }; &usbotg2 { dr_mode = "host"; + disable-over-current; status = "okay"; }; @@ -215,7 +217,7 @@ fsl,pins = < MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 MX8MM_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI 0xd6 - MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 + MX8MM_IOMUXC_ECSPI2_MISO_ECSPI2_MISO 0xd6 MX8MM_IOMUXC_ECSPI2_SS0_GPIO5_IO13 0xd6 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi index 1e7badb2a82e..f61e4847fa49 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi @@ -211,12 +211,14 @@ &usbotg1 { dr_mode = "otg"; + over-current-active-low; vbus-supply = <®_usb_otg1_vbus>; status = "okay"; }; &usbotg2 { dr_mode = "host"; + disable-over-current; vbus-supply = <®_usb_otg2_vbus>; status = "okay"; }; @@ -309,7 +311,7 @@ fsl,pins = < MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 MX8MM_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI 0xd6 - MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 + MX8MM_IOMUXC_ECSPI2_MISO_ECSPI2_MISO 0xd6 MX8MM_IOMUXC_ECSPI2_SS0_GPIO5_IO13 0xd6 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi index 426483ec1f88..023619648966 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi @@ -238,12 +238,14 @@ &usbotg1 { dr_mode = "otg"; + over-current-active-low; vbus-supply = <®_usb_otg1_vbus>; status = "okay"; }; &usbotg2 { dr_mode = "host"; + disable-over-current; vbus-supply = <®_usb_otg2_vbus>; status = "okay"; }; @@ -358,7 +360,7 @@ fsl,pins = < MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 MX8MM_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI 0xd6 - MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 + MX8MM_IOMUXC_ECSPI2_MISO_ECSPI2_MISO 0xd6 MX8MM_IOMUXC_ECSPI2_SS0_GPIO5_IO13 0xd6 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts index 7dfee715a2c4..d8ce217c6016 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts @@ -59,6 +59,10 @@ interrupts = <3 IRQ_TYPE_LEVEL_LOW>; rohm,reset-snvs-powered; + #clock-cells = <0>; + clocks = <&osc_32k 0>; + clock-output-names = "clk-32k-out"; + regulators { buck1_reg: BUCK1 { regulator-name = "buck1"; diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index 99f0f5026674..5c0ca2490561 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -293,7 +293,7 @@ ranges; sai2: sai@30020000 { - compatible = "fsl,imx8mm-sai", "fsl,imx8mq-sai"; + compatible = "fsl,imx8mn-sai", "fsl,imx8mq-sai"; reg = <0x30020000 0x10000>; interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SAI2_IPG>, @@ -307,7 +307,7 @@ }; sai3: sai@30030000 { - compatible = "fsl,imx8mm-sai", "fsl,imx8mq-sai"; + compatible = "fsl,imx8mn-sai", "fsl,imx8mq-sai"; reg = <0x30030000 0x10000>; interrupts = <GIC_SPI 50 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SAI3_IPG>, @@ -321,7 +321,7 @@ }; sai5: sai@30050000 { - compatible = "fsl,imx8mm-sai", "fsl,imx8mq-sai"; + compatible = "fsl,imx8mn-sai", "fsl,imx8mq-sai"; reg = <0x30050000 0x10000>; interrupts = <GIC_SPI 90 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SAI5_IPG>, @@ -337,7 +337,7 @@ }; sai6: sai@30060000 { - compatible = "fsl,imx8mm-sai", "fsl,imx8mq-sai"; + compatible = "fsl,imx8mn-sai", "fsl,imx8mq-sai"; reg = <0x30060000 0x10000>; interrupts = <GIC_SPI 90 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SAI6_IPG>, @@ -394,7 +394,7 @@ }; sai7: sai@300b0000 { - compatible = "fsl,imx8mm-sai", "fsl,imx8mq-sai"; + compatible = "fsl,imx8mn-sai", "fsl,imx8mq-sai"; reg = <0x300b0000 0x10000>; interrupts = <GIC_SPI 111 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SAI7_IPG>, diff --git a/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi index 38ffcd145b33..899e8e7dbc24 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi @@ -253,7 +253,7 @@ #address-cells = <1>; #size-cells = <1>; spi-max-frequency = <84000000>; - spi-tx-bus-width = <4>; + spi-tx-bus-width = <1>; spi-rx-bus-width = <4>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8qm.dtsi b/arch/arm64/boot/dts/freescale/imx8qm.dtsi index be8c76a0554c..4f767012f1f5 100644 --- a/arch/arm64/boot/dts/freescale/imx8qm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8qm.dtsi @@ -196,7 +196,7 @@ }; clk: clock-controller { - compatible = "fsl,imx8qxp-clk", "fsl,scu-clk"; + compatible = "fsl,imx8qm-clk", "fsl,scu-clk"; #clock-cells = <2>; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi b/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi index 1df84335925b..aff857df25cf 100644 --- a/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi @@ -262,25 +262,25 @@ gpio4 { pins = "gpio4"; function = "32k-out1"; - drive-push-pull; + drive-push-pull = <1>; }; gpio5 { pins = "gpio5"; function = "gpio"; - drive-push-pull; + drive-push-pull = <0>; }; gpio6 { pins = "gpio6"; function = "gpio"; - drive-push-pull; + drive-push-pull = <1>; }; gpio7 { pins = "gpio7"; function = "gpio"; - drive-push-pull; + drive-push-pull = <0>; }; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra186-p3509-0000+p3636-0001.dts b/arch/arm64/boot/dts/nvidia/tegra186-p3509-0000+p3636-0001.dts index 1ab132c152bb..4631504c3c7a 100644 --- a/arch/arm64/boot/dts/nvidia/tegra186-p3509-0000+p3636-0001.dts +++ b/arch/arm64/boot/dts/nvidia/tegra186-p3509-0000+p3636-0001.dts @@ -462,25 +462,25 @@ gpio4 { pins = "gpio4"; function = "32k-out1"; - drive-push-pull; + drive-push-pull = <1>; }; gpio5 { pins = "gpio5"; function = "gpio"; - drive-push-pull; + drive-push-pull = <0>; }; gpio6 { pins = "gpio6"; function = "gpio"; - drive-push-pull; + drive-push-pull = <1>; }; gpio7 { pins = "gpio7"; function = "gpio"; - drive-push-pull; + drive-push-pull = <1>; }; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi b/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi index 634d0f493c2e..a7d7cfd66379 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi @@ -174,19 +174,19 @@ gpio4 { pins = "gpio4"; function = "32k-out1"; - drive-push-pull; + drive-push-pull = <1>; }; gpio6 { pins = "gpio6"; function = "gpio"; - drive-push-pull; + drive-push-pull = <1>; }; gpio7 { pins = "gpio7"; function = "gpio"; - drive-push-pull; + drive-push-pull = <0>; }; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p3668.dtsi b/arch/arm64/boot/dts/nvidia/tegra194-p3668.dtsi index 0b219e72765e..0bd66f9c620b 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194-p3668.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194-p3668.dtsi @@ -148,19 +148,19 @@ gpio4 { pins = "gpio4"; function = "32k-out1"; - drive-push-pull; + drive-push-pull = <1>; }; gpio6 { pins = "gpio6"; function = "gpio"; - drive-push-pull; + drive-push-pull = <1>; }; gpio7 { pins = "gpio7"; function = "gpio"; - drive-push-pull; + drive-push-pull = <0>; }; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi b/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi index 0fe772b04bd0..75eb743a7242 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra210-p2180.dtsi @@ -59,7 +59,7 @@ gpio1 { pins = "gpio1"; function = "fps-out"; - drive-push-pull; + drive-push-pull = <1>; maxim,active-fps-source = <MAX77620_FPS_SRC_0>; maxim,active-fps-power-up-slot = <7>; maxim,active-fps-power-down-slot = <0>; @@ -68,7 +68,7 @@ gpio2_3 { pins = "gpio2", "gpio3"; function = "fps-out"; - drive-open-drain; + drive-open-drain = <1>; maxim,active-fps-source = <MAX77620_FPS_SRC_0>; }; @@ -80,7 +80,7 @@ gpio5_6_7 { pins = "gpio5", "gpio6", "gpio7"; function = "gpio"; - drive-push-pull; + drive-push-pull = <1>; }; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra210-p2894.dtsi b/arch/arm64/boot/dts/nvidia/tegra210-p2894.dtsi index 936a309e288c..10347b6e6e84 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210-p2894.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra210-p2894.dtsi @@ -1351,7 +1351,7 @@ gpio1 { pins = "gpio1"; function = "fps-out"; - drive-push-pull; + drive-push-pull = <1>; maxim,active-fps-source = <MAX77620_FPS_SRC_0>; maxim,active-fps-power-up-slot = <7>; maxim,active-fps-power-down-slot = <0>; @@ -1360,14 +1360,14 @@ gpio2 { pins = "gpio2"; function = "fps-out"; - drive-open-drain; + drive-open-drain = <1>; maxim,active-fps-source = <MAX77620_FPS_SRC_0>; }; gpio3 { pins = "gpio3"; function = "fps-out"; - drive-open-drain; + drive-open-drain = <1>; maxim,active-fps-source = <MAX77620_FPS_SRC_0>; }; @@ -1379,7 +1379,7 @@ gpio5_6_7 { pins = "gpio5", "gpio6", "gpio7"; function = "gpio"; - drive-push-pull; + drive-push-pull = <1>; }; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra210-p3450-0000.dts b/arch/arm64/boot/dts/nvidia/tegra210-p3450-0000.dts index f6446120c267..72c2dc3c14ea 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210-p3450-0000.dts +++ b/arch/arm64/boot/dts/nvidia/tegra210-p3450-0000.dts @@ -195,7 +195,7 @@ gpio1 { pins = "gpio1"; function = "fps-out"; - drive-push-pull; + drive-push-pull = <1>; maxim,active-fps-source = <MAX77620_FPS_SRC_NONE>; maxim,active-fps-power-up-slot = <0>; maxim,active-fps-power-down-slot = <7>; @@ -204,7 +204,7 @@ gpio2 { pins = "gpio2"; function = "fps-out"; - drive-open-drain; + drive-open-drain = <1>; maxim,active-fps-source = <MAX77620_FPS_SRC_0>; maxim,active-fps-power-up-slot = <0>; maxim,active-fps-power-down-slot = <7>; @@ -213,7 +213,7 @@ gpio3 { pins = "gpio3"; function = "fps-out"; - drive-open-drain; + drive-open-drain = <1>; maxim,active-fps-source = <MAX77620_FPS_SRC_0>; maxim,active-fps-power-up-slot = <4>; maxim,active-fps-power-down-slot = <3>; @@ -227,7 +227,7 @@ gpio5_6_7 { pins = "gpio5", "gpio6", "gpio7"; function = "gpio"; - drive-push-pull; + drive-push-pull = <1>; }; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra210-smaug.dts b/arch/arm64/boot/dts/nvidia/tegra210-smaug.dts index e42384f097d6..a263d51882ee 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210-smaug.dts +++ b/arch/arm64/boot/dts/nvidia/tegra210-smaug.dts @@ -1386,7 +1386,7 @@ gpio3 { pins = "gpio3"; function = "fps-out"; - drive-open-drain; + drive-open-drain = <1>; maxim,active-fps-source = <MAX77620_FPS_SRC_0>; maxim,active-fps-power-up-slot = <4>; maxim,active-fps-power-down-slot = <2>; @@ -1395,7 +1395,7 @@ gpio5_6 { pins = "gpio5", "gpio6"; function = "gpio"; - drive-push-pull; + drive-push-pull = <1>; }; gpio4 { diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 62217be36217..9f3e2c3d2ca0 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -16,7 +16,11 @@ #define sev() asm volatile("sev" : : : "memory") #define wfe() asm volatile("wfe" : : : "memory") +#define wfet(val) asm volatile("msr s0_3_c1_c0_0, %0" \ + : : "r" (val) : "memory") #define wfi() asm volatile("wfi" : : : "memory") +#define wfit(val) asm volatile("msr s0_3_c1_c0_1, %0" \ + : : "r" (val) : "memory") #define isb() asm volatile("isb" : : : "memory") #define dmb(opt) asm volatile("dmb " #opt : : : "memory") diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h index a58e366f0b07..115cdec1ae87 100644 --- a/arch/arm64/include/asm/cpu.h +++ b/arch/arm64/include/asm/cpu.h @@ -58,11 +58,15 @@ struct cpuinfo_arm64 { u64 reg_id_aa64pfr0; u64 reg_id_aa64pfr1; u64 reg_id_aa64zfr0; + u64 reg_id_aa64smfr0; struct cpuinfo_32bit aarch32; /* pseudo-ZCR for recording maximum ZCR_EL1 LEN value: */ u64 reg_zcr; + + /* pseudo-SMCR for recording maximum SMCR_EL1 LEN value: */ + u64 reg_smcr; }; DECLARE_PER_CPU(struct cpuinfo_arm64, cpu_data); diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index c62e7e5e2f0c..14a8f3d93add 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -622,6 +622,13 @@ static inline bool id_aa64pfr0_sve(u64 pfr0) return val > 0; } +static inline bool id_aa64pfr1_sme(u64 pfr1) +{ + u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_SME_SHIFT); + + return val > 0; +} + static inline bool id_aa64pfr1_mte(u64 pfr1) { u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_MTE_SHIFT); @@ -759,6 +766,23 @@ static __always_inline bool system_supports_sve(void) cpus_have_const_cap(ARM64_SVE); } +static __always_inline bool system_supports_sme(void) +{ + return IS_ENABLED(CONFIG_ARM64_SME) && + cpus_have_const_cap(ARM64_SME); +} + +static __always_inline bool system_supports_fa64(void) +{ + return IS_ENABLED(CONFIG_ARM64_SME) && + cpus_have_const_cap(ARM64_SME_FA64); +} + +static __always_inline bool system_supports_tpidr2(void) +{ + return system_supports_sme(); +} + static __always_inline bool system_supports_cnp(void) { return IS_ENABLED(CONFIG_ARM64_CNP) && diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index c31be7eda9df..fabdbde0fe02 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -143,6 +143,50 @@ .Lskip_sve_\@: .endm +/* SME register access and priority mapping */ +.macro __init_el2_nvhe_sme + mrs x1, id_aa64pfr1_el1 + ubfx x1, x1, #ID_AA64PFR1_SME_SHIFT, #4 + cbz x1, .Lskip_sme_\@ + + bic x0, x0, #CPTR_EL2_TSM // Also disable SME traps + msr cptr_el2, x0 // Disable copro. traps to EL2 + isb + + mrs x1, sctlr_el2 + orr x1, x1, #SCTLR_ELx_ENTP2 // Disable TPIDR2 traps + msr sctlr_el2, x1 + isb + + mov x1, #0 // SMCR controls + + mrs_s x2, SYS_ID_AA64SMFR0_EL1 + ubfx x2, x2, #ID_AA64SMFR0_FA64_SHIFT, #1 // Full FP in SM? + cbz x2, .Lskip_sme_fa64_\@ + + orr x1, x1, SMCR_ELx_FA64_MASK +.Lskip_sme_fa64_\@: + + orr x1, x1, #SMCR_ELx_LEN_MASK // Enable full SME vector + msr_s SYS_SMCR_EL2, x1 // length for EL1. + + mrs_s x1, SYS_SMIDR_EL1 // Priority mapping supported? + ubfx x1, x1, #SYS_SMIDR_EL1_SMPS_SHIFT, #1 + cbz x1, .Lskip_sme_\@ + + msr_s SYS_SMPRIMAP_EL2, xzr // Make all priorities equal + + mrs x1, id_aa64mmfr1_el1 // HCRX_EL2 present? + ubfx x1, x1, #ID_AA64MMFR1_HCX_SHIFT, #4 + cbz x1, .Lskip_sme_\@ + + mrs_s x1, SYS_HCRX_EL2 + orr x1, x1, #HCRX_EL2_SMPME_MASK // Enable priority mapping + msr_s SYS_HCRX_EL2, x1 + +.Lskip_sme_\@: +.endm + /* Disable any fine grained traps */ .macro __init_el2_fgt mrs x1, id_aa64mmfr0_el1 @@ -153,15 +197,26 @@ mrs x1, id_aa64dfr0_el1 ubfx x1, x1, #ID_AA64DFR0_PMSVER_SHIFT, #4 cmp x1, #3 - b.lt .Lset_fgt_\@ + b.lt .Lset_debug_fgt_\@ /* Disable PMSNEVFR_EL1 read and write traps */ orr x0, x0, #(1 << 62) -.Lset_fgt_\@: +.Lset_debug_fgt_\@: msr_s SYS_HDFGRTR_EL2, x0 msr_s SYS_HDFGWTR_EL2, x0 - msr_s SYS_HFGRTR_EL2, xzr - msr_s SYS_HFGWTR_EL2, xzr + + mov x0, xzr + mrs x1, id_aa64pfr1_el1 + ubfx x1, x1, #ID_AA64PFR1_SME_SHIFT, #4 + cbz x1, .Lset_fgt_\@ + + /* Disable nVHE traps of TPIDR2 and SMPRI */ + orr x0, x0, #HFGxTR_EL2_nSMPRI_EL1_MASK + orr x0, x0, #HFGxTR_EL2_nTPIDR2_EL0_MASK + +.Lset_fgt_\@: + msr_s SYS_HFGRTR_EL2, x0 + msr_s SYS_HFGWTR_EL2, x0 msr_s SYS_HFGITR_EL2, xzr mrs x1, id_aa64pfr0_el1 // AMU traps UNDEF without AMU @@ -196,6 +251,7 @@ __init_el2_nvhe_idregs __init_el2_nvhe_cptr __init_el2_nvhe_sve + __init_el2_nvhe_sme __init_el2_fgt __init_el2_nvhe_prepare_eret .endm diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index d52a0b269ee8..0bc9941b412e 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -37,7 +37,8 @@ #define ESR_ELx_EC_ERET (0x1a) /* EL2 only */ /* Unallocated EC: 0x1B */ #define ESR_ELx_EC_FPAC (0x1C) /* EL1 and above */ -/* Unallocated EC: 0x1D - 0x1E */ +#define ESR_ELx_EC_SME (0x1D) +/* Unallocated EC: 0x1E */ #define ESR_ELx_EC_IMP_DEF (0x1f) /* EL3 only */ #define ESR_ELx_EC_IABT_LOW (0x20) #define ESR_ELx_EC_IABT_CUR (0x21) @@ -75,6 +76,7 @@ #define ESR_ELx_IL_SHIFT (25) #define ESR_ELx_IL (UL(1) << ESR_ELx_IL_SHIFT) #define ESR_ELx_ISS_MASK (ESR_ELx_IL - 1) +#define ESR_ELx_ISS(esr) ((esr) & ESR_ELx_ISS_MASK) /* ISS field definitions shared by different classes */ #define ESR_ELx_WNR_SHIFT (6) @@ -133,7 +135,10 @@ #define ESR_ELx_CV (UL(1) << 24) #define ESR_ELx_COND_SHIFT (20) #define ESR_ELx_COND_MASK (UL(0xF) << ESR_ELx_COND_SHIFT) -#define ESR_ELx_WFx_ISS_TI (UL(1) << 0) +#define ESR_ELx_WFx_ISS_RN (UL(0x1F) << 5) +#define ESR_ELx_WFx_ISS_RV (UL(1) << 2) +#define ESR_ELx_WFx_ISS_TI (UL(3) << 0) +#define ESR_ELx_WFx_ISS_WFxT (UL(2) << 0) #define ESR_ELx_WFx_ISS_WFI (UL(0) << 0) #define ESR_ELx_WFx_ISS_WFE (UL(1) << 0) #define ESR_ELx_xVC_IMM_MASK ((1UL << 16) - 1) @@ -146,7 +151,8 @@ #define DISR_EL1_ESR_MASK (ESR_ELx_AET | ESR_ELx_EA | ESR_ELx_FSC) /* ESR value templates for specific events */ -#define ESR_ELx_WFx_MASK (ESR_ELx_EC_MASK | ESR_ELx_WFx_ISS_TI) +#define ESR_ELx_WFx_MASK (ESR_ELx_EC_MASK | \ + (ESR_ELx_WFx_ISS_TI & ~ESR_ELx_WFx_ISS_WFxT)) #define ESR_ELx_WFx_WFI_VAL ((ESR_ELx_EC_WFx << ESR_ELx_EC_SHIFT) | \ ESR_ELx_WFx_ISS_WFI) @@ -327,6 +333,15 @@ #define ESR_ELx_CP15_32_ISS_SYS_CNTFRQ (ESR_ELx_CP15_32_ISS_SYS_VAL(0, 0, 14, 0) |\ ESR_ELx_CP15_32_ISS_DIR_READ) +/* + * ISS values for SME traps + */ + +#define ESR_ELx_SME_ISS_SME_DISABLED 0 +#define ESR_ELx_SME_ISS_ILL 1 +#define ESR_ELx_SME_ISS_SM_DISABLED 2 +#define ESR_ELx_SME_ISS_ZA_DISABLED 3 + #ifndef __ASSEMBLY__ #include <asm/types.h> diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index 339477dca551..2add7f33b7c2 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -64,6 +64,7 @@ void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr, struct pt_regs *regs); void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs); void do_sve_acc(unsigned int esr, struct pt_regs *regs); +void do_sme_acc(unsigned int esr, struct pt_regs *regs); void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs); void do_sysinstr(unsigned int esr, struct pt_regs *regs); void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index cb24385e3632..5afcd0709aae 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -46,11 +46,23 @@ extern void fpsimd_restore_current_state(void); extern void fpsimd_update_current_state(struct user_fpsimd_state const *state); extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state, - void *sve_state, unsigned int sve_vl); + void *sve_state, unsigned int sve_vl, + void *za_state, unsigned int sme_vl, + u64 *svcr); extern void fpsimd_flush_task_state(struct task_struct *target); extern void fpsimd_save_and_flush_cpu_state(void); +static inline bool thread_sm_enabled(struct thread_struct *thread) +{ + return system_supports_sme() && (thread->svcr & SYS_SVCR_EL0_SM_MASK); +} + +static inline bool thread_za_enabled(struct thread_struct *thread) +{ + return system_supports_sme() && (thread->svcr & SYS_SVCR_EL0_ZA_MASK); +} + /* Maximum VL that SVE/SME VL-agnostic software can transparently support */ #define VL_ARCH_MAX 0x100 @@ -62,7 +74,14 @@ static inline size_t sve_ffr_offset(int vl) static inline void *sve_pffr(struct thread_struct *thread) { - return (char *)thread->sve_state + sve_ffr_offset(thread_get_sve_vl(thread)); + unsigned int vl; + + if (system_supports_sme() && thread_sm_enabled(thread)) + vl = thread_get_sme_vl(thread); + else + vl = thread_get_sve_vl(thread); + + return (char *)thread->sve_state + sve_ffr_offset(vl); } extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr); @@ -71,11 +90,17 @@ extern void sve_load_state(void const *state, u32 const *pfpsr, extern void sve_flush_live(bool flush_ffr, unsigned long vq_minus_1); extern unsigned int sve_get_vl(void); extern void sve_set_vq(unsigned long vq_minus_1); +extern void sme_set_vq(unsigned long vq_minus_1); +extern void za_save_state(void *state); +extern void za_load_state(void const *state); struct arm64_cpu_capabilities; extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused); +extern void sme_kernel_enable(const struct arm64_cpu_capabilities *__unused); +extern void fa64_kernel_enable(const struct arm64_cpu_capabilities *__unused); extern u64 read_zcr_features(void); +extern u64 read_smcr_features(void); /* * Helpers to translate bit indices in sve_vq_map to VQ values (and @@ -119,6 +144,7 @@ struct vl_info { extern void sve_alloc(struct task_struct *task); extern void fpsimd_release_task(struct task_struct *task); extern void fpsimd_sync_to_sve(struct task_struct *task); +extern void fpsimd_force_sync_to_sve(struct task_struct *task); extern void sve_sync_to_fpsimd(struct task_struct *task); extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task); @@ -171,6 +197,12 @@ static inline void write_vl(enum vec_type type, u64 val) write_sysreg_s(tmp | val, SYS_ZCR_EL1); break; #endif +#ifdef CONFIG_ARM64_SME + case ARM64_VEC_SME: + tmp = read_sysreg_s(SYS_SMCR_EL1) & ~SMCR_ELx_LEN_MASK; + write_sysreg_s(tmp | val, SYS_SMCR_EL1); + break; +#endif default: WARN_ON_ONCE(1); break; @@ -208,6 +240,8 @@ static inline bool sve_vq_available(unsigned int vq) return vq_available(ARM64_VEC_SVE, vq); } +size_t sve_state_size(struct task_struct const *task); + #else /* ! CONFIG_ARM64_SVE */ static inline void sve_alloc(struct task_struct *task) { } @@ -247,8 +281,93 @@ static inline void vec_update_vq_map(enum vec_type t) { } static inline int vec_verify_vq_map(enum vec_type t) { return 0; } static inline void sve_setup(void) { } +static inline size_t sve_state_size(struct task_struct const *task) +{ + return 0; +} + #endif /* ! CONFIG_ARM64_SVE */ +#ifdef CONFIG_ARM64_SME + +static inline void sme_user_disable(void) +{ + sysreg_clear_set(cpacr_el1, CPACR_EL1_SMEN_EL0EN, 0); +} + +static inline void sme_user_enable(void) +{ + sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_SMEN_EL0EN); +} + +static inline void sme_smstart_sm(void) +{ + asm volatile(__msr_s(SYS_SVCR_SMSTART_SM_EL0, "xzr")); +} + +static inline void sme_smstop_sm(void) +{ + asm volatile(__msr_s(SYS_SVCR_SMSTOP_SM_EL0, "xzr")); +} + +static inline void sme_smstop(void) +{ + asm volatile(__msr_s(SYS_SVCR_SMSTOP_SMZA_EL0, "xzr")); +} + +extern void __init sme_setup(void); + +static inline int sme_max_vl(void) +{ + return vec_max_vl(ARM64_VEC_SME); +} + +static inline int sme_max_virtualisable_vl(void) +{ + return vec_max_virtualisable_vl(ARM64_VEC_SME); +} + +extern void sme_alloc(struct task_struct *task); +extern unsigned int sme_get_vl(void); +extern int sme_set_current_vl(unsigned long arg); +extern int sme_get_current_vl(void); + +/* + * Return how many bytes of memory are required to store the full SME + * specific state (currently just ZA) for task, given task's currently + * configured vector length. + */ +static inline size_t za_state_size(struct task_struct const *task) +{ + unsigned int vl = task_get_sme_vl(task); + + return ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl)); +} + +#else + +static inline void sme_user_disable(void) { BUILD_BUG(); } +static inline void sme_user_enable(void) { BUILD_BUG(); } + +static inline void sme_smstart_sm(void) { } +static inline void sme_smstop_sm(void) { } +static inline void sme_smstop(void) { } + +static inline void sme_alloc(struct task_struct *task) { } +static inline void sme_setup(void) { } +static inline unsigned int sme_get_vl(void) { return 0; } +static inline int sme_max_vl(void) { return 0; } +static inline int sme_max_virtualisable_vl(void) { return 0; } +static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; } +static inline int sme_get_current_vl(void) { return -EINVAL; } + +static inline size_t za_state_size(struct task_struct const *task) +{ + return 0; +} + +#endif /* ! CONFIG_ARM64_SME */ + /* For use by EFI runtime services calls only */ extern void __efi_fpsimd_begin(void); extern void __efi_fpsimd_end(void); diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h index 2509d7dde55a..5e0910cf4832 100644 --- a/arch/arm64/include/asm/fpsimdmacros.h +++ b/arch/arm64/include/asm/fpsimdmacros.h @@ -93,6 +93,12 @@ .endif .endm +.macro _sme_check_wv v + .if (\v) < 12 || (\v) > 15 + .error "Bad vector select register \v." + .endif +.endm + /* SVE instruction encodings for non-SVE-capable assemblers */ /* (pre binutils 2.28, all kernel capable clang versions support SVE) */ @@ -174,6 +180,54 @@ | (\np) .endm +/* SME instruction encodings for non-SME-capable assemblers */ +/* (pre binutils 2.38/LLVM 13) */ + +/* RDSVL X\nx, #\imm */ +.macro _sme_rdsvl nx, imm + _check_general_reg \nx + _check_num (\imm), -0x20, 0x1f + .inst 0x04bf5800 \ + | (\nx) \ + | (((\imm) & 0x3f) << 5) +.endm + +/* + * STR (vector from ZA array): + * STR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL] + */ +.macro _sme_str_zav nw, nxbase, offset=0 + _sme_check_wv \nw + _check_general_reg \nxbase + _check_num (\offset), -0x100, 0xff + .inst 0xe1200000 \ + | (((\nw) & 3) << 13) \ + | ((\nxbase) << 5) \ + | ((\offset) & 7) +.endm + +/* + * LDR (vector to ZA array): + * LDR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL] + */ +.macro _sme_ldr_zav nw, nxbase, offset=0 + _sme_check_wv \nw + _check_general_reg \nxbase + _check_num (\offset), -0x100, 0xff + .inst 0xe1000000 \ + | (((\nw) & 3) << 13) \ + | ((\nxbase) << 5) \ + | ((\offset) & 7) +.endm + +/* + * Zero the entire ZA array + * ZERO ZA + */ +.macro zero_za + .inst 0xc00800ff +.endm + .macro __for from:req, to:req .if (\from) == (\to) _for__body %\from @@ -208,6 +262,17 @@ 921: .endm +/* Update SMCR_EL1.LEN with the new VQ */ +.macro sme_load_vq xvqminus1, xtmp, xtmp2 + mrs_s \xtmp, SYS_SMCR_EL1 + bic \xtmp2, \xtmp, SMCR_ELx_LEN_MASK + orr \xtmp2, \xtmp2, \xvqminus1 + cmp \xtmp2, \xtmp + b.eq 921f + msr_s SYS_SMCR_EL1, \xtmp2 //self-synchronising +921: +.endm + /* Preserve the first 128-bits of Znz and zero the rest. */ .macro _sve_flush_z nz _sve_check_zreg \nz @@ -254,3 +319,25 @@ ldr w\nxtmp, [\xpfpsr, #4] msr fpcr, x\nxtmp .endm + +.macro sme_save_za nxbase, xvl, nw + mov w\nw, #0 + +423: + _sme_str_zav \nw, \nxbase + add x\nxbase, x\nxbase, \xvl + add x\nw, x\nw, #1 + cmp \xvl, x\nw + bne 423b +.endm + +.macro sme_load_za nxbase, xvl, nw + mov w\nw, #0 + +423: + _sme_ldr_zav \nw, \nxbase + add x\nxbase, x\nxbase, \xvl + add x\nw, x\nw, #1 + cmp \xvl, x\nw + bne 423b +.endm diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index 8db5ec0089db..aa443d8f8cfb 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -109,6 +109,15 @@ #define KERNEL_HWCAP_AFP __khwcap2_feature(AFP) #define KERNEL_HWCAP_RPRES __khwcap2_feature(RPRES) #define KERNEL_HWCAP_MTE3 __khwcap2_feature(MTE3) +#define KERNEL_HWCAP_SME __khwcap2_feature(SME) +#define KERNEL_HWCAP_SME_I16I64 __khwcap2_feature(SME_I16I64) +#define KERNEL_HWCAP_SME_F64F64 __khwcap2_feature(SME_F64F64) +#define KERNEL_HWCAP_SME_I8I32 __khwcap2_feature(SME_I8I32) +#define KERNEL_HWCAP_SME_F16F32 __khwcap2_feature(SME_F16F32) +#define KERNEL_HWCAP_SME_B16F32 __khwcap2_feature(SME_B16F32) +#define KERNEL_HWCAP_SME_F32F32 __khwcap2_feature(SME_F32F32) +#define KERNEL_HWCAP_SME_FA64 __khwcap2_feature(SME_FA64) +#define KERNEL_HWCAP_WFXT __khwcap2_feature(WFXT) /* * This yields a mask that user programs can use to figure out what diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 1767ded83888..8aa8492dafc0 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -80,11 +80,12 @@ * FMO: Override CPSR.F and enable signaling with VF * SWIO: Turn set/way invalidates into set/way clean+invalidate * PTW: Take a stage2 fault if a stage1 walk steps in device memory + * TID3: Trap EL1 reads of group 3 ID registers */ #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \ HCR_BSU_IS | HCR_FB | HCR_TACR | \ HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \ - HCR_FMO | HCR_IMO | HCR_PTW ) + HCR_FMO | HCR_IMO | HCR_PTW | HCR_TID3 ) #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF) #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK | HCR_ATA) #define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC) @@ -279,6 +280,7 @@ #define CPTR_EL2_TCPAC (1U << 31) #define CPTR_EL2_TAM (1 << 30) #define CPTR_EL2_TTA (1 << 20) +#define CPTR_EL2_TSM (1 << 12) #define CPTR_EL2_TFP (1 << CPTR_EL2_TFP_SHIFT) #define CPTR_EL2_TZ (1 << 8) #define CPTR_NVHE_EL2_RES1 0x000032ff /* known RES1 bits in CPTR_EL2 (nVHE) */ diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index d5b0386ef765..2e277f2ed671 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -169,6 +169,7 @@ struct kvm_nvhe_init_params { unsigned long tcr_el2; unsigned long tpidr_el2; unsigned long stack_hyp_va; + unsigned long stack_pa; phys_addr_t pgd_pa; unsigned long hcr_el2; unsigned long vttbr; diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 7496deab025a..07812680fcaf 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -40,6 +40,7 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu); void kvm_inject_vabt(struct kvm_vcpu *vcpu); void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr); +void kvm_inject_size_fault(struct kvm_vcpu *vcpu); void kvm_vcpu_wfi(struct kvm_vcpu *vcpu); @@ -86,13 +87,6 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) if (vcpu_el1_is_32bit(vcpu)) vcpu->arch.hcr_el2 &= ~HCR_RW; - else - /* - * TID3: trap feature register accesses that we virtualise. - * For now this is conditional, since no AArch32 feature regs - * are currently virtualised. - */ - vcpu->arch.hcr_el2 |= HCR_TID3; if (cpus_have_const_cap(ARM64_MISMATCHED_CACHE_TYPE) || vcpu_el1_is_32bit(vcpu)) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 94a27a7520f4..89a26e2e8c4f 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -46,6 +46,7 @@ #define KVM_REQ_RECORD_STEAL KVM_ARCH_REQ(3) #define KVM_REQ_RELOAD_GICv4 KVM_ARCH_REQ(4) #define KVM_REQ_RELOAD_PMU KVM_ARCH_REQ(5) +#define KVM_REQ_SUSPEND KVM_ARCH_REQ(6) #define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ KVM_DIRTY_LOG_INITIALLY_SET) @@ -101,6 +102,19 @@ struct kvm_s2_mmu { struct kvm_arch_memory_slot { }; +/** + * struct kvm_smccc_features: Descriptor of the hypercall services exposed to the guests + * + * @std_bmap: Bitmap of standard secure service calls + * @std_hyp_bmap: Bitmap of standard hypervisor service calls + * @vendor_hyp_bmap: Bitmap of vendor specific hypervisor service calls + */ +struct kvm_smccc_features { + unsigned long std_bmap; + unsigned long std_hyp_bmap; + unsigned long vendor_hyp_bmap; +}; + struct kvm_arch { struct kvm_s2_mmu mmu; @@ -136,6 +150,8 @@ struct kvm_arch { */ #define KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED 3 #define KVM_ARCH_FLAG_EL1_32BIT 4 + /* PSCI SYSTEM_SUSPEND enabled for the guest */ +#define KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED 5 unsigned long flags; @@ -150,6 +166,9 @@ struct kvm_arch { u8 pfr0_csv2; u8 pfr0_csv3; + + /* Hypercall features firmware registers' descriptor */ + struct kvm_smccc_features smccc_feat; }; struct kvm_vcpu_fault_info { @@ -295,8 +314,11 @@ struct vcpu_reset_state { struct kvm_vcpu_arch { struct kvm_cpu_context ctxt; + + /* Guest floating point state */ void *sve_state; unsigned int sve_max_vl; + u64 svcr; /* Stage 2 paging state used by the hardware on next switch */ struct kvm_s2_mmu *hw_mmu; @@ -365,8 +387,8 @@ struct kvm_vcpu_arch { u32 mdscr_el1; } guest_debug_preserved; - /* vcpu power-off state */ - bool power_off; + /* vcpu power state */ + struct kvm_mp_state mp_state; /* Don't run the guest (internal implementation need) */ bool pause; @@ -451,6 +473,8 @@ struct kvm_vcpu_arch { #define KVM_ARM64_DEBUG_STATE_SAVE_TRBE (1 << 13) /* Save TRBE context if active */ #define KVM_ARM64_FP_FOREIGN_FPSTATE (1 << 14) #define KVM_ARM64_ON_UNSUPPORTED_CPU (1 << 15) /* Physical CPU not in supported_cpus */ +#define KVM_ARM64_HOST_SME_ENABLED (1 << 16) /* SME enabled for EL0 */ +#define KVM_ARM64_WFIT (1 << 17) /* WFIT instruction trapped */ #define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \ KVM_GUESTDBG_USE_SW_BP | \ @@ -683,6 +707,7 @@ int kvm_handle_cp14_64(struct kvm_vcpu *vcpu); int kvm_handle_cp15_32(struct kvm_vcpu *vcpu); int kvm_handle_cp15_64(struct kvm_vcpu *vcpu); int kvm_handle_sys_reg(struct kvm_vcpu *vcpu); +int kvm_handle_cp10_id(struct kvm_vcpu *vcpu); void kvm_reset_sys_regs(struct kvm_vcpu *vcpu); @@ -841,4 +866,7 @@ void __init kvm_hyp_reserve(void); static inline void kvm_hyp_reserve(void) { } #endif +void kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu); +bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu); + #endif /* __ARM64_KVM_HOST_H__ */ diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 74735a864eee..b208da3bebec 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -154,6 +154,9 @@ static __always_inline unsigned long __kern_hyp_va(unsigned long v) int kvm_share_hyp(void *from, void *to); void kvm_unshare_hyp(void *from, void *to); int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot); +int __create_hyp_mappings(unsigned long start, unsigned long size, + unsigned long phys, enum kvm_pgtable_prot prot); +int hyp_alloc_private_va_range(size_t size, unsigned long *haddr); int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size, void __iomem **kaddr, void __iomem **haddr); diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 94e147e5456c..dff2b483ea50 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -535,7 +535,7 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, PMD_TYPE_TABLE) #define pmd_sect(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \ PMD_TYPE_SECT) -#define pmd_leaf(pmd) pmd_sect(pmd) +#define pmd_leaf(pmd) (pmd_present(pmd) && !pmd_table(pmd)) #define pmd_bad(pmd) (!pmd_table(pmd)) #define pmd_leaf_size(pmd) (pmd_cont(pmd) ? CONT_PMD_SIZE : PMD_SIZE) @@ -625,7 +625,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) #define pud_none(pud) (!pud_val(pud)) #define pud_bad(pud) (!pud_table(pud)) #define pud_present(pud) pte_present(pud_pte(pud)) -#define pud_leaf(pud) pud_sect(pud) +#define pud_leaf(pud) (pud_present(pud) && !pud_table(pud)) #define pud_valid(pud) pte_valid(pud_pte(pud)) static inline void set_pud(pud_t *pudp, pud_t pud) diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 73e38d9a540c..1d2ca4870b84 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -118,6 +118,7 @@ struct debug_info { enum vec_type { ARM64_VEC_SVE = 0, + ARM64_VEC_SME, ARM64_VEC_MAX, }; @@ -153,6 +154,7 @@ struct thread_struct { unsigned int fpsimd_cpu; void *sve_state; /* SVE registers, if any */ + void *za_state; /* ZA register, if any */ unsigned int vl[ARM64_VEC_MAX]; /* vector length */ unsigned int vl_onexec[ARM64_VEC_MAX]; /* vl after next exec */ unsigned long fault_address; /* fault info */ @@ -168,6 +170,8 @@ struct thread_struct { u64 mte_ctrl; #endif u64 sctlr_user; + u64 svcr; + u64 tpidr2_el0; }; static inline unsigned int thread_get_vl(struct thread_struct *thread, @@ -181,6 +185,19 @@ static inline unsigned int thread_get_sve_vl(struct thread_struct *thread) return thread_get_vl(thread, ARM64_VEC_SVE); } +static inline unsigned int thread_get_sme_vl(struct thread_struct *thread) +{ + return thread_get_vl(thread, ARM64_VEC_SME); +} + +static inline unsigned int thread_get_cur_vl(struct thread_struct *thread) +{ + if (system_supports_sme() && (thread->svcr & SYS_SVCR_EL0_SM_MASK)) + return thread_get_sme_vl(thread); + else + return thread_get_sve_vl(thread); +} + unsigned int task_get_vl(const struct task_struct *task, enum vec_type type); void task_set_vl(struct task_struct *task, enum vec_type type, unsigned long vl); @@ -194,6 +211,11 @@ static inline unsigned int task_get_sve_vl(const struct task_struct *task) return task_get_vl(task, ARM64_VEC_SVE); } +static inline unsigned int task_get_sme_vl(const struct task_struct *task) +{ + return task_get_vl(task, ARM64_VEC_SME); +} + static inline void task_set_sve_vl(struct task_struct *task, unsigned long vl) { task_set_vl(task, ARM64_VEC_SVE, vl); @@ -354,9 +376,11 @@ extern void __init minsigstksz_setup(void); */ #include <asm/fpsimd.h> -/* Userspace interface for PR_SVE_{SET,GET}_VL prctl()s: */ +/* Userspace interface for PR_S[MV]E_{SET,GET}_VL prctl()s: */ #define SVE_SET_VL(arg) sve_set_current_vl(arg) #define SVE_GET_VL() sve_get_current_vl() +#define SME_SET_VL(arg) sme_set_current_vl(arg) +#define SME_GET_VL() sme_get_current_vl() /* PR_PAC_RESET_KEYS prctl */ #define PAC_RESET_KEYS(tsk, arg) ptrauth_prctl_reset_keys(tsk, arg) diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index fbf5f8bb9055..bebfdd27296a 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -118,6 +118,10 @@ * System registers, organised loosely by encoding but grouped together * where the architected name contains an index. e.g. ID_MMFR<n>_EL1. */ +#define SYS_SVCR_SMSTOP_SM_EL0 sys_reg(0, 3, 4, 2, 3) +#define SYS_SVCR_SMSTART_SM_EL0 sys_reg(0, 3, 4, 3, 3) +#define SYS_SVCR_SMSTOP_SMZA_EL0 sys_reg(0, 3, 4, 6, 3) + #define SYS_OSDTRRX_EL1 sys_reg(2, 0, 0, 0, 2) #define SYS_MDCCINT_EL1 sys_reg(2, 0, 0, 2, 0) #define SYS_MDSCR_EL1 sys_reg(2, 0, 0, 2, 2) @@ -181,6 +185,7 @@ #define SYS_ID_AA64PFR0_EL1 sys_reg(3, 0, 0, 4, 0) #define SYS_ID_AA64PFR1_EL1 sys_reg(3, 0, 0, 4, 1) #define SYS_ID_AA64ZFR0_EL1 sys_reg(3, 0, 0, 4, 4) +#define SYS_ID_AA64SMFR0_EL1 sys_reg(3, 0, 0, 4, 5) #define SYS_ID_AA64DFR0_EL1 sys_reg(3, 0, 0, 5, 0) #define SYS_ID_AA64DFR1_EL1 sys_reg(3, 0, 0, 5, 1) @@ -204,6 +209,8 @@ #define SYS_ZCR_EL1 sys_reg(3, 0, 1, 2, 0) #define SYS_TRFCR_EL1 sys_reg(3, 0, 1, 2, 1) +#define SYS_SMPRI_EL1 sys_reg(3, 0, 1, 2, 4) +#define SYS_SMCR_EL1 sys_reg(3, 0, 1, 2, 6) #define SYS_TTBR0_EL1 sys_reg(3, 0, 2, 0, 0) #define SYS_TTBR1_EL1 sys_reg(3, 0, 2, 0, 1) @@ -396,6 +403,8 @@ #define TRBIDR_ALIGN_MASK GENMASK(3, 0) #define TRBIDR_ALIGN_SHIFT 0 +#define SMPRI_EL1_PRIORITY_MASK 0xf + #define SYS_PMINTENSET_EL1 sys_reg(3, 0, 9, 14, 1) #define SYS_PMINTENCLR_EL1 sys_reg(3, 0, 9, 14, 2) @@ -451,8 +460,13 @@ #define SYS_CCSIDR_EL1 sys_reg(3, 1, 0, 0, 0) #define SYS_CLIDR_EL1 sys_reg(3, 1, 0, 0, 1) #define SYS_GMID_EL1 sys_reg(3, 1, 0, 0, 4) +#define SYS_SMIDR_EL1 sys_reg(3, 1, 0, 0, 6) #define SYS_AIDR_EL1 sys_reg(3, 1, 0, 0, 7) +#define SYS_SMIDR_EL1_IMPLEMENTER_SHIFT 24 +#define SYS_SMIDR_EL1_SMPS_SHIFT 15 +#define SYS_SMIDR_EL1_AFFINITY_SHIFT 0 + #define SYS_CSSELR_EL1 sys_reg(3, 2, 0, 0, 0) #define SYS_CTR_EL0 sys_reg(3, 3, 0, 0, 1) @@ -461,6 +475,10 @@ #define SYS_RNDR_EL0 sys_reg(3, 3, 2, 4, 0) #define SYS_RNDRRS_EL0 sys_reg(3, 3, 2, 4, 1) +#define SYS_SVCR_EL0 sys_reg(3, 3, 4, 2, 2) +#define SYS_SVCR_EL0_ZA_MASK 2 +#define SYS_SVCR_EL0_SM_MASK 1 + #define SYS_PMCR_EL0 sys_reg(3, 3, 9, 12, 0) #define SYS_PMCNTENSET_EL0 sys_reg(3, 3, 9, 12, 1) #define SYS_PMCNTENCLR_EL0 sys_reg(3, 3, 9, 12, 2) @@ -477,6 +495,7 @@ #define SYS_TPIDR_EL0 sys_reg(3, 3, 13, 0, 2) #define SYS_TPIDRRO_EL0 sys_reg(3, 3, 13, 0, 3) +#define SYS_TPIDR2_EL0 sys_reg(3, 3, 13, 0, 5) #define SYS_SCXTNUM_EL0 sys_reg(3, 3, 13, 0, 7) @@ -546,6 +565,9 @@ #define SYS_HFGITR_EL2 sys_reg(3, 4, 1, 1, 6) #define SYS_ZCR_EL2 sys_reg(3, 4, 1, 2, 0) #define SYS_TRFCR_EL2 sys_reg(3, 4, 1, 2, 1) +#define SYS_HCRX_EL2 sys_reg(3, 4, 1, 2, 2) +#define SYS_SMPRIMAP_EL2 sys_reg(3, 4, 1, 2, 5) +#define SYS_SMCR_EL2 sys_reg(3, 4, 1, 2, 6) #define SYS_DACR32_EL2 sys_reg(3, 4, 3, 0, 0) #define SYS_HDFGRTR_EL2 sys_reg(3, 4, 3, 1, 4) #define SYS_HDFGWTR_EL2 sys_reg(3, 4, 3, 1, 5) @@ -605,6 +627,7 @@ #define SYS_SCTLR_EL12 sys_reg(3, 5, 1, 0, 0) #define SYS_CPACR_EL12 sys_reg(3, 5, 1, 0, 2) #define SYS_ZCR_EL12 sys_reg(3, 5, 1, 2, 0) +#define SYS_SMCR_EL12 sys_reg(3, 5, 1, 2, 6) #define SYS_TTBR0_EL12 sys_reg(3, 5, 2, 0, 0) #define SYS_TTBR1_EL12 sys_reg(3, 5, 2, 0, 1) #define SYS_TCR_EL12 sys_reg(3, 5, 2, 0, 2) @@ -628,6 +651,7 @@ #define SYS_CNTV_CVAL_EL02 sys_reg(3, 5, 14, 3, 2) /* Common SCTLR_ELx flags. */ +#define SCTLR_ELx_ENTP2 (BIT(60)) #define SCTLR_ELx_DSSBS (BIT(44)) #define SCTLR_ELx_ATA (BIT(43)) @@ -836,6 +860,7 @@ #define ID_AA64PFR0_ELx_32BIT_64BIT 0x2 /* id_aa64pfr1 */ +#define ID_AA64PFR1_SME_SHIFT 24 #define ID_AA64PFR1_MPAMFRAC_SHIFT 16 #define ID_AA64PFR1_RASFRAC_SHIFT 12 #define ID_AA64PFR1_MTE_SHIFT 8 @@ -846,6 +871,7 @@ #define ID_AA64PFR1_SSBS_PSTATE_ONLY 1 #define ID_AA64PFR1_SSBS_PSTATE_INSNS 2 #define ID_AA64PFR1_BT_BTI 0x1 +#define ID_AA64PFR1_SME 1 #define ID_AA64PFR1_MTE_NI 0x0 #define ID_AA64PFR1_MTE_EL0 0x1 @@ -874,6 +900,23 @@ #define ID_AA64ZFR0_AES_PMULL 0x2 #define ID_AA64ZFR0_SVEVER_SVE2 0x1 +/* id_aa64smfr0 */ +#define ID_AA64SMFR0_FA64_SHIFT 63 +#define ID_AA64SMFR0_I16I64_SHIFT 52 +#define ID_AA64SMFR0_F64F64_SHIFT 48 +#define ID_AA64SMFR0_I8I32_SHIFT 36 +#define ID_AA64SMFR0_F16F32_SHIFT 35 +#define ID_AA64SMFR0_B16F32_SHIFT 34 +#define ID_AA64SMFR0_F32F32_SHIFT 32 + +#define ID_AA64SMFR0_FA64 0x1 +#define ID_AA64SMFR0_I16I64 0x4 +#define ID_AA64SMFR0_F64F64 0x1 +#define ID_AA64SMFR0_I8I32 0x4 +#define ID_AA64SMFR0_F16F32 0x1 +#define ID_AA64SMFR0_B16F32 0x1 +#define ID_AA64SMFR0_F32F32 0x1 + /* id_aa64mmfr0 */ #define ID_AA64MMFR0_ECV_SHIFT 60 #define ID_AA64MMFR0_FGT_SHIFT 56 @@ -926,6 +969,7 @@ /* id_aa64mmfr1 */ #define ID_AA64MMFR1_ECBHB_SHIFT 60 +#define ID_AA64MMFR1_HCX_SHIFT 40 #define ID_AA64MMFR1_AFP_SHIFT 44 #define ID_AA64MMFR1_ETS_SHIFT 36 #define ID_AA64MMFR1_TWED_SHIFT 32 @@ -1119,9 +1163,24 @@ #define ZCR_ELx_LEN_SIZE 9 #define ZCR_ELx_LEN_MASK 0x1ff +#define SMCR_ELx_FA64_SHIFT 31 +#define SMCR_ELx_FA64_MASK (1 << SMCR_ELx_FA64_SHIFT) + +/* + * The SMCR_ELx_LEN_* definitions intentionally include bits [8:4] which + * are reserved by the SME architecture for future expansion of the LEN + * field, with compatible semantics. + */ +#define SMCR_ELx_LEN_SHIFT 0 +#define SMCR_ELx_LEN_SIZE 9 +#define SMCR_ELx_LEN_MASK 0x1ff + #define CPACR_EL1_FPEN_EL1EN (BIT(20)) /* enable EL1 access */ #define CPACR_EL1_FPEN_EL0EN (BIT(21)) /* enable EL0 access, if EL1EN set */ +#define CPACR_EL1_SMEN_EL1EN (BIT(24)) /* enable EL1 access */ +#define CPACR_EL1_SMEN_EL0EN (BIT(25)) /* enable EL0 access, if EL1EN set */ + #define CPACR_EL1_ZEN_EL1EN (BIT(16)) /* enable EL1 access */ #define CPACR_EL1_ZEN_EL0EN (BIT(17)) /* enable EL0 access, if EL1EN set */ @@ -1170,6 +1229,8 @@ #define TRFCR_ELx_ExTRE BIT(1) #define TRFCR_ELx_E0TRE BIT(0) +/* HCRX_EL2 definitions */ +#define HCRX_EL2_SMPME_MASK (1 << 5) /* GIC Hypervisor interface registers */ /* ICH_MISR_EL2 bit definitions */ @@ -1233,6 +1294,12 @@ #define ICH_VTR_TDS_SHIFT 19 #define ICH_VTR_TDS_MASK (1 << ICH_VTR_TDS_SHIFT) +/* HFG[WR]TR_EL2 bit definitions */ +#define HFGxTR_EL2_nTPIDR2_EL0_SHIFT 55 +#define HFGxTR_EL2_nTPIDR2_EL0_MASK BIT_MASK(HFGxTR_EL2_nTPIDR2_EL0_SHIFT) +#define HFGxTR_EL2_nSMPRI_EL1_SHIFT 54 +#define HFGxTR_EL2_nSMPRI_EL1_MASK BIT_MASK(HFGxTR_EL2_nSMPRI_EL1_SHIFT) + #define ARM64_FEATURE_FIELD_BITS 4 /* Create a mask for the feature bits of the specified feature. */ diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index e1317b7c4525..848739c15de8 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -82,6 +82,8 @@ int arch_dup_task_struct(struct task_struct *dst, #define TIF_SVE_VL_INHERIT 24 /* Inherit SVE vl_onexec across exec */ #define TIF_SSBD 25 /* Wants SSB mitigation */ #define TIF_TAGGED_ADDR 26 /* Allow tagged user addresses */ +#define TIF_SME 27 /* SME in use */ +#define TIF_SME_VL_INHERIT 28 /* Inherit SME vl_onexec across exec */ #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index 99cb5d383048..4bb2cc8ac446 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -79,5 +79,14 @@ #define HWCAP2_AFP (1 << 20) #define HWCAP2_RPRES (1 << 21) #define HWCAP2_MTE3 (1 << 22) +#define HWCAP2_SME (1 << 23) +#define HWCAP2_SME_I16I64 (1 << 24) +#define HWCAP2_SME_F64F64 (1 << 25) +#define HWCAP2_SME_I8I32 (1 << 26) +#define HWCAP2_SME_F16F32 (1 << 27) +#define HWCAP2_SME_B16F32 (1 << 28) +#define HWCAP2_SME_F32F32 (1 << 29) +#define HWCAP2_SME_FA64 (1 << 30) +#define HWCAP2_WFXT (1UL << 31) #endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index c1b6ddc02d2f..d4722b08f0d4 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -332,6 +332,40 @@ struct kvm_arm_copy_mte_tags { #define KVM_ARM64_SVE_VLS_WORDS \ ((KVM_ARM64_SVE_VQ_MAX - KVM_ARM64_SVE_VQ_MIN) / 64 + 1) +/* Bitmap feature firmware registers */ +#define KVM_REG_ARM_FW_FEAT_BMAP (0x0016 << KVM_REG_ARM_COPROC_SHIFT) +#define KVM_REG_ARM_FW_FEAT_BMAP_REG(r) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \ + KVM_REG_ARM_FW_FEAT_BMAP | \ + ((r) & 0xffff)) + +#define KVM_REG_ARM_STD_BMAP KVM_REG_ARM_FW_FEAT_BMAP_REG(0) + +enum { + KVM_REG_ARM_STD_BIT_TRNG_V1_0 = 0, +#ifdef __KERNEL__ + KVM_REG_ARM_STD_BMAP_BIT_COUNT, +#endif +}; + +#define KVM_REG_ARM_STD_HYP_BMAP KVM_REG_ARM_FW_FEAT_BMAP_REG(1) + +enum { + KVM_REG_ARM_STD_HYP_BIT_PV_TIME = 0, +#ifdef __KERNEL__ + KVM_REG_ARM_STD_HYP_BMAP_BIT_COUNT, +#endif +}; + +#define KVM_REG_ARM_VENDOR_HYP_BMAP KVM_REG_ARM_FW_FEAT_BMAP_REG(2) + +enum { + KVM_REG_ARM_VENDOR_HYP_BIT_FUNC_FEAT = 0, + KVM_REG_ARM_VENDOR_HYP_BIT_PTP = 1, +#ifdef __KERNEL__ + KVM_REG_ARM_VENDOR_HYP_BMAP_BIT_COUNT, +#endif +}; + /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h index 758ae984ff97..7fa2f7036aa7 100644 --- a/arch/arm64/include/uapi/asm/ptrace.h +++ b/arch/arm64/include/uapi/asm/ptrace.h @@ -109,7 +109,7 @@ struct user_hwdebug_state { } dbg_regs[16]; }; -/* SVE/FP/SIMD state (NT_ARM_SVE) */ +/* SVE/FP/SIMD state (NT_ARM_SVE & NT_ARM_SSVE) */ struct user_sve_header { __u32 size; /* total meaningful regset content in bytes */ @@ -220,6 +220,7 @@ struct user_sve_header { (SVE_PT_SVE_PREG_OFFSET(vq, __SVE_NUM_PREGS) - \ SVE_PT_SVE_PREGS_OFFSET(vq)) +/* For streaming mode SVE (SSVE) FFR must be read and written as zero */ #define SVE_PT_SVE_FFR_OFFSET(vq) \ (SVE_PT_REGS_OFFSET + __SVE_FFR_OFFSET(vq)) @@ -240,10 +241,12 @@ struct user_sve_header { - SVE_PT_SVE_OFFSET + (__SVE_VQ_BYTES - 1)) \ / __SVE_VQ_BYTES * __SVE_VQ_BYTES) -#define SVE_PT_SIZE(vq, flags) \ - (((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE ? \ - SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, flags) \ - : SVE_PT_FPSIMD_OFFSET + SVE_PT_FPSIMD_SIZE(vq, flags)) +#define SVE_PT_SIZE(vq, flags) \ + (((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE ? \ + SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, flags) \ + : ((((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD ? \ + SVE_PT_FPSIMD_OFFSET + SVE_PT_FPSIMD_SIZE(vq, flags) \ + : SVE_PT_REGS_OFFSET))) /* pointer authentication masks (NT_ARM_PAC_MASK) */ @@ -265,6 +268,62 @@ struct user_pac_generic_keys { __uint128_t apgakey; }; +/* ZA state (NT_ARM_ZA) */ + +struct user_za_header { + __u32 size; /* total meaningful regset content in bytes */ + __u32 max_size; /* maxmium possible size for this thread */ + __u16 vl; /* current vector length */ + __u16 max_vl; /* maximum possible vector length */ + __u16 flags; + __u16 __reserved; +}; + +/* + * Common ZA_PT_* flags: + * These must be kept in sync with prctl interface in <linux/prctl.h> + */ +#define ZA_PT_VL_INHERIT ((1 << 17) /* PR_SME_VL_INHERIT */ >> 16) +#define ZA_PT_VL_ONEXEC ((1 << 18) /* PR_SME_SET_VL_ONEXEC */ >> 16) + + +/* + * The remainder of the ZA state follows struct user_za_header. The + * total size of the ZA state (including header) depends on the + * metadata in the header: ZA_PT_SIZE(vq, flags) gives the total size + * of the state in bytes, including the header. + * + * Refer to <asm/sigcontext.h> for details of how to pass the correct + * "vq" argument to these macros. + */ + +/* Offset from the start of struct user_za_header to the register data */ +#define ZA_PT_ZA_OFFSET \ + ((sizeof(struct user_za_header) + (__SVE_VQ_BYTES - 1)) \ + / __SVE_VQ_BYTES * __SVE_VQ_BYTES) + +/* + * The payload starts at offset ZA_PT_ZA_OFFSET, and is of size + * ZA_PT_ZA_SIZE(vq, flags). + * + * The ZA array is stored as a sequence of horizontal vectors ZAV of SVL/8 + * bytes each, starting from vector 0. + * + * Additional data might be appended in the future. + * + * The ZA matrix is represented in memory in an endianness-invariant layout + * which differs from the layout used for the FPSIMD V-registers on big-endian + * systems: see sigcontext.h for more explanation. + */ + +#define ZA_PT_ZAV_OFFSET(vq, n) \ + (ZA_PT_ZA_OFFSET + ((vq * __SVE_VQ_BYTES) * n)) + +#define ZA_PT_ZA_SIZE(vq) ((vq * __SVE_VQ_BYTES) * (vq * __SVE_VQ_BYTES)) + +#define ZA_PT_SIZE(vq) \ + (ZA_PT_ZA_OFFSET + ZA_PT_ZA_SIZE(vq)) + #endif /* __ASSEMBLY__ */ #endif /* _UAPI__ASM_PTRACE_H */ diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h index 0c796c795dbe..4aaf31e3bf16 100644 --- a/arch/arm64/include/uapi/asm/sigcontext.h +++ b/arch/arm64/include/uapi/asm/sigcontext.h @@ -134,6 +134,17 @@ struct extra_context { struct sve_context { struct _aarch64_ctx head; __u16 vl; + __u16 flags; + __u16 __reserved[2]; +}; + +#define SVE_SIG_FLAG_SM 0x1 /* Context describes streaming mode */ + +#define ZA_MAGIC 0x54366345 + +struct za_context { + struct _aarch64_ctx head; + __u16 vl; __u16 __reserved[3]; }; @@ -186,9 +197,16 @@ struct sve_context { * sve_context.vl must equal the thread's current vector length when * doing a sigreturn. * + * On systems with support for SME the SVE register state may reflect either + * streaming or non-streaming mode. In streaming mode the streaming mode + * vector length will be used and the flag SVE_SIG_FLAG_SM will be set in + * the flags field. It is permitted to enter or leave streaming mode in + * a signal return, applications should take care to ensure that any difference + * in vector length between the two modes is handled, including any resizing + * and movement of context blocks. * - * Note: for all these macros, the "vq" argument denotes the SVE - * vector length in quadwords (i.e., units of 128 bits). + * Note: for all these macros, the "vq" argument denotes the vector length + * in quadwords (i.e., units of 128 bits). * * The correct way to obtain vq is to use sve_vq_from_vl(vl). The * result is valid if and only if sve_vl_valid(vl) is true. This is @@ -249,4 +267,37 @@ struct sve_context { #define SVE_SIG_CONTEXT_SIZE(vq) \ (SVE_SIG_REGS_OFFSET + SVE_SIG_REGS_SIZE(vq)) +/* + * If the ZA register is enabled for the thread at signal delivery then, + * za_context.head.size >= ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za_context.vl)) + * and the register data may be accessed using the ZA_SIG_*() macros. + * + * If za_context.head.size < ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za_context.vl)) + * then ZA was not enabled and no register data was included in which case + * ZA register was not enabled for the thread and no register data + * the ZA_SIG_*() macros should not be used except for this check. + * + * The same convention applies when returning from a signal: a caller + * will need to remove or resize the za_context block if it wants to + * enable the ZA register when it was previously non-live or vice-versa. + * This may require the caller to allocate fresh memory and/or move other + * context blocks in the signal frame. + * + * Changing the vector length during signal return is not permitted: + * za_context.vl must equal the thread's current SME vector length when + * doing a sigreturn. + */ + +#define ZA_SIG_REGS_OFFSET \ + ((sizeof(struct za_context) + (__SVE_VQ_BYTES - 1)) \ + / __SVE_VQ_BYTES * __SVE_VQ_BYTES) + +#define ZA_SIG_REGS_SIZE(vq) ((vq * __SVE_VQ_BYTES) * (vq * __SVE_VQ_BYTES)) + +#define ZA_SIG_ZAV_OFFSET(vq, n) (ZA_SIG_REGS_OFFSET + \ + (SVE_SIG_ZREG_SIZE(vq) * n)) + +#define ZA_SIG_CONTEXT_SIZE(vq) \ + (ZA_SIG_REGS_OFFSET + ZA_SIG_REGS_SIZE(vq)) + #endif /* _UAPI__ASM_SIGCONTEXT_H */ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index d72c4b4d389c..78ed5fc762eb 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -237,6 +237,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_GPA3_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_RPRES_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_WFXT_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -261,6 +262,8 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { }; static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = { + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_SME_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_MPAMFRAC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_RASFRAC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_MTE), @@ -293,6 +296,24 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { ARM64_FTR_END, }; +static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = { + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_FA64_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_I16I64_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_F64F64_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_I8I32_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_F16F32_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_B16F32_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_F32F32_SHIFT, 1, 0), + ARM64_FTR_END, +}; + static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_ECV_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_FGT_SHIFT, 4, 0), @@ -561,6 +582,12 @@ static const struct arm64_ftr_bits ftr_zcr[] = { ARM64_FTR_END, }; +static const struct arm64_ftr_bits ftr_smcr[] = { + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, + SMCR_ELx_LEN_SHIFT, SMCR_ELx_LEN_SIZE, 0), /* LEN */ + ARM64_FTR_END, +}; + /* * Common ftr bits for a 32bit register with all hidden, strict * attributes, with 4bit feature fields and a default safe value of @@ -645,6 +672,7 @@ static const struct __ftr_reg_entry { ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1, &id_aa64pfr1_override), ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_id_aa64zfr0), + ARM64_FTR_REG(SYS_ID_AA64SMFR0_EL1, ftr_id_aa64smfr0), /* Op1 = 0, CRn = 0, CRm = 5 */ ARM64_FTR_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0), @@ -666,6 +694,7 @@ static const struct __ftr_reg_entry { /* Op1 = 0, CRn = 1, CRm = 2 */ ARM64_FTR_REG(SYS_ZCR_EL1, ftr_zcr), + ARM64_FTR_REG(SYS_SMCR_EL1, ftr_smcr), /* Op1 = 1, CRn = 0, CRm = 0 */ ARM64_FTR_REG(SYS_GMID_EL1, ftr_gmid), @@ -960,6 +989,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) init_cpu_ftr_reg(SYS_ID_AA64PFR0_EL1, info->reg_id_aa64pfr0); init_cpu_ftr_reg(SYS_ID_AA64PFR1_EL1, info->reg_id_aa64pfr1); init_cpu_ftr_reg(SYS_ID_AA64ZFR0_EL1, info->reg_id_aa64zfr0); + init_cpu_ftr_reg(SYS_ID_AA64SMFR0_EL1, info->reg_id_aa64smfr0); if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) init_32bit_cpu_features(&info->aarch32); @@ -969,6 +999,12 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) vec_init_vq_map(ARM64_VEC_SVE); } + if (id_aa64pfr1_sme(info->reg_id_aa64pfr1)) { + init_cpu_ftr_reg(SYS_SMCR_EL1, info->reg_smcr); + if (IS_ENABLED(CONFIG_ARM64_SME)) + vec_init_vq_map(ARM64_VEC_SME); + } + if (id_aa64pfr1_mte(info->reg_id_aa64pfr1)) init_cpu_ftr_reg(SYS_GMID_EL1, info->reg_gmid); @@ -1195,6 +1231,9 @@ void update_cpu_features(int cpu, taint |= check_update_ftr_reg(SYS_ID_AA64ZFR0_EL1, cpu, info->reg_id_aa64zfr0, boot->reg_id_aa64zfr0); + taint |= check_update_ftr_reg(SYS_ID_AA64SMFR0_EL1, cpu, + info->reg_id_aa64smfr0, boot->reg_id_aa64smfr0); + if (id_aa64pfr0_sve(info->reg_id_aa64pfr0)) { taint |= check_update_ftr_reg(SYS_ZCR_EL1, cpu, info->reg_zcr, boot->reg_zcr); @@ -1205,6 +1244,16 @@ void update_cpu_features(int cpu, vec_update_vq_map(ARM64_VEC_SVE); } + if (id_aa64pfr1_sme(info->reg_id_aa64pfr1)) { + taint |= check_update_ftr_reg(SYS_SMCR_EL1, cpu, + info->reg_smcr, boot->reg_smcr); + + /* Probe vector lengths, unless we already gave up on SME */ + if (id_aa64pfr1_sme(read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1)) && + !system_capabilities_finalized()) + vec_update_vq_map(ARM64_VEC_SME); + } + /* * The kernel uses the LDGM/STGM instructions and the number of tags * they read/write depends on the GMID_EL1.BS field. Check that the @@ -1288,6 +1337,7 @@ u64 __read_sysreg_by_encoding(u32 sys_id) read_sysreg_case(SYS_ID_AA64PFR0_EL1); read_sysreg_case(SYS_ID_AA64PFR1_EL1); read_sysreg_case(SYS_ID_AA64ZFR0_EL1); + read_sysreg_case(SYS_ID_AA64SMFR0_EL1); read_sysreg_case(SYS_ID_AA64DFR0_EL1); read_sysreg_case(SYS_ID_AA64DFR1_EL1); read_sysreg_case(SYS_ID_AA64MMFR0_EL1); @@ -2442,6 +2492,44 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, .min_field_value = 1, }, +#ifdef CONFIG_ARM64_SME + { + .desc = "Scalable Matrix Extension", + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .capability = ARM64_SME, + .sys_reg = SYS_ID_AA64PFR1_EL1, + .sign = FTR_UNSIGNED, + .field_pos = ID_AA64PFR1_SME_SHIFT, + .field_width = 4, + .min_field_value = ID_AA64PFR1_SME, + .matches = has_cpuid_feature, + .cpu_enable = sme_kernel_enable, + }, + /* FA64 should be sorted after the base SME capability */ + { + .desc = "FA64", + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .capability = ARM64_SME_FA64, + .sys_reg = SYS_ID_AA64SMFR0_EL1, + .sign = FTR_UNSIGNED, + .field_pos = ID_AA64SMFR0_FA64_SHIFT, + .field_width = 1, + .min_field_value = ID_AA64SMFR0_FA64, + .matches = has_cpuid_feature, + .cpu_enable = fa64_kernel_enable, + }, +#endif /* CONFIG_ARM64_SME */ + { + .desc = "WFx with timeout", + .capability = ARM64_HAS_WFXT, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .sys_reg = SYS_ID_AA64ISAR2_EL1, + .sign = FTR_UNSIGNED, + .field_pos = ID_AA64ISAR2_WFXT_SHIFT, + .field_width = 4, + .matches = has_cpuid_feature, + .min_field_value = ID_AA64ISAR2_WFXT_SUPPORTED, + }, {}, }; @@ -2575,6 +2663,17 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(SYS_ID_AA64MMFR0_EL1, ID_AA64MMFR0_ECV_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ECV), HWCAP_CAP(SYS_ID_AA64MMFR1_EL1, ID_AA64MMFR1_AFP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AFP), HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_RPRES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RPRES), + HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_WFXT_SHIFT, 4, FTR_UNSIGNED, ID_AA64ISAR2_WFXT_SUPPORTED, CAP_HWCAP, KERNEL_HWCAP_WFXT), +#ifdef CONFIG_ARM64_SME + HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SME_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_SME, CAP_HWCAP, KERNEL_HWCAP_SME), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_FA64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_FA64, CAP_HWCAP, KERNEL_HWCAP_SME_FA64), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_I16I64_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_I16I64, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_F64F64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_F64F64, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_I8I32_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_I8I32, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_F16F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_F16F32, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_B16F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_B16F32, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_F32F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_F32F32, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32), +#endif /* CONFIG_ARM64_SME */ {}, }; @@ -2872,6 +2971,23 @@ static void verify_sve_features(void) /* Add checks on other ZCR bits here if necessary */ } +static void verify_sme_features(void) +{ + u64 safe_smcr = read_sanitised_ftr_reg(SYS_SMCR_EL1); + u64 smcr = read_smcr_features(); + + unsigned int safe_len = safe_smcr & SMCR_ELx_LEN_MASK; + unsigned int len = smcr & SMCR_ELx_LEN_MASK; + + if (len < safe_len || vec_verify_vq_map(ARM64_VEC_SME)) { + pr_crit("CPU%d: SME: vector length support mismatch\n", + smp_processor_id()); + cpu_die_early(); + } + + /* Add checks on other SMCR bits here if necessary */ +} + static void verify_hyp_capabilities(void) { u64 safe_mmfr1, mmfr0, mmfr1; @@ -2924,6 +3040,9 @@ static void verify_local_cpu_capabilities(void) if (system_supports_sve()) verify_sve_features(); + if (system_supports_sme()) + verify_sme_features(); + if (is_hyp_mode_available()) verify_hyp_capabilities(); } @@ -3041,6 +3160,7 @@ void __init setup_cpu_features(void) pr_info("emulated: Privileged Access Never (PAN) using TTBR0_EL1 switching\n"); sve_setup(); + sme_setup(); minsigstksz_setup(); /* Advertise that we have computed the system capabilities */ diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 330b92ea863a..8eff0a34ffd4 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -98,6 +98,15 @@ static const char *const hwcap_str[] = { [KERNEL_HWCAP_AFP] = "afp", [KERNEL_HWCAP_RPRES] = "rpres", [KERNEL_HWCAP_MTE3] = "mte3", + [KERNEL_HWCAP_SME] = "sme", + [KERNEL_HWCAP_SME_I16I64] = "smei16i64", + [KERNEL_HWCAP_SME_F64F64] = "smef64f64", + [KERNEL_HWCAP_SME_I8I32] = "smei8i32", + [KERNEL_HWCAP_SME_F16F32] = "smef16f32", + [KERNEL_HWCAP_SME_B16F32] = "smeb16f32", + [KERNEL_HWCAP_SME_F32F32] = "smef32f32", + [KERNEL_HWCAP_SME_FA64] = "smefa64", + [KERNEL_HWCAP_WFXT] = "wfxt", }; #ifdef CONFIG_COMPAT @@ -401,6 +410,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) info->reg_id_aa64pfr0 = read_cpuid(ID_AA64PFR0_EL1); info->reg_id_aa64pfr1 = read_cpuid(ID_AA64PFR1_EL1); info->reg_id_aa64zfr0 = read_cpuid(ID_AA64ZFR0_EL1); + info->reg_id_aa64smfr0 = read_cpuid(ID_AA64SMFR0_EL1); if (id_aa64pfr1_mte(info->reg_id_aa64pfr1)) info->reg_gmid = read_cpuid(GMID_EL1); @@ -412,6 +422,10 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) id_aa64pfr0_sve(info->reg_id_aa64pfr0)) info->reg_zcr = read_zcr_features(); + if (IS_ENABLED(CONFIG_ARM64_SME) && + id_aa64pfr1_sme(info->reg_id_aa64pfr1)) + info->reg_smcr = read_smcr_features(); + cpuinfo_detect_icache_policy(info); } diff --git a/arch/arm64/kernel/elfcore.c b/arch/arm64/kernel/elfcore.c index 2b3f3d0544b9..98d67444a5b6 100644 --- a/arch/arm64/kernel/elfcore.c +++ b/arch/arm64/kernel/elfcore.c @@ -95,7 +95,7 @@ int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) for_each_mte_vma(current, vma) { struct elf_phdr phdr; - phdr.p_type = PT_ARM_MEMTAG_MTE; + phdr.p_type = PT_AARCH64_MEMTAG_MTE; phdr.p_offset = offset; phdr.p_vaddr = vma->vm_start; phdr.p_paddr = 0; diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 878c65aa7206..29139e9a1517 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -537,6 +537,14 @@ static void noinstr el0_sve_acc(struct pt_regs *regs, unsigned long esr) exit_to_user_mode(regs); } +static void noinstr el0_sme_acc(struct pt_regs *regs, unsigned long esr) +{ + enter_from_user_mode(regs); + local_daif_restore(DAIF_PROCCTX); + do_sme_acc(esr, regs); + exit_to_user_mode(regs); +} + static void noinstr el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr) { enter_from_user_mode(regs); @@ -645,6 +653,9 @@ asmlinkage void noinstr el0t_64_sync_handler(struct pt_regs *regs) case ESR_ELx_EC_SVE: el0_sve_acc(regs, esr); break; + case ESR_ELx_EC_SME: + el0_sme_acc(regs, esr); + break; case ESR_ELx_EC_FP_EXC64: el0_fpsimd_exc(regs, esr); break; diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S index dc242e269f9a..229436f33df5 100644 --- a/arch/arm64/kernel/entry-fpsimd.S +++ b/arch/arm64/kernel/entry-fpsimd.S @@ -86,3 +86,39 @@ SYM_FUNC_START(sve_flush_live) SYM_FUNC_END(sve_flush_live) #endif /* CONFIG_ARM64_SVE */ + +#ifdef CONFIG_ARM64_SME + +SYM_FUNC_START(sme_get_vl) + _sme_rdsvl 0, 1 + ret +SYM_FUNC_END(sme_get_vl) + +SYM_FUNC_START(sme_set_vq) + sme_load_vq x0, x1, x2 + ret +SYM_FUNC_END(sme_set_vq) + +/* + * Save the SME state + * + * x0 - pointer to buffer for state + */ +SYM_FUNC_START(za_save_state) + _sme_rdsvl 1, 1 // x1 = VL/8 + sme_save_za 0, x1, 12 + ret +SYM_FUNC_END(za_save_state) + +/* + * Load the SME state + * + * x0 - pointer to buffer for state + */ +SYM_FUNC_START(za_load_state) + _sme_rdsvl 1, 1 // x1 = VL/8 + sme_load_za 0, x1, 12 + ret +SYM_FUNC_END(za_load_state) + +#endif /* CONFIG_ARM64_SME */ diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 47af76e53221..64431bc62472 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -121,7 +121,10 @@ struct fpsimd_last_state_struct { struct user_fpsimd_state *st; void *sve_state; + void *za_state; + u64 *svcr; unsigned int sve_vl; + unsigned int sme_vl; }; static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state); @@ -136,6 +139,12 @@ __ro_after_init struct vl_info vl_info[ARM64_VEC_MAX] = { .max_virtualisable_vl = SVE_VL_MIN, }, #endif +#ifdef CONFIG_ARM64_SME + [ARM64_VEC_SME] = { + .type = ARM64_VEC_SME, + .name = "SME", + }, +#endif }; static unsigned int vec_vl_inherit_flag(enum vec_type type) @@ -143,6 +152,8 @@ static unsigned int vec_vl_inherit_flag(enum vec_type type) switch (type) { case ARM64_VEC_SVE: return TIF_SVE_VL_INHERIT; + case ARM64_VEC_SME: + return TIF_SME_VL_INHERIT; default: WARN_ON_ONCE(1); return 0; @@ -186,6 +197,26 @@ extern void __percpu *efi_sve_state; #endif /* ! CONFIG_ARM64_SVE */ +#ifdef CONFIG_ARM64_SME + +static int get_sme_default_vl(void) +{ + return get_default_vl(ARM64_VEC_SME); +} + +static void set_sme_default_vl(int val) +{ + set_default_vl(ARM64_VEC_SME, val); +} + +static void sme_free(struct task_struct *); + +#else + +static inline void sme_free(struct task_struct *t) { } + +#endif + DEFINE_PER_CPU(bool, fpsimd_context_busy); EXPORT_PER_CPU_SYMBOL(fpsimd_context_busy); @@ -279,16 +310,27 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type, } /* + * TIF_SME controls whether a task can use SME without trapping while + * in userspace, when TIF_SME is set then we must have storage + * alocated in sve_state and za_state to store the contents of both ZA + * and the SVE registers for both streaming and non-streaming modes. + * + * If both SVCR.ZA and SVCR.SM are disabled then at any point we + * may disable TIF_SME and reenable traps. + */ + + +/* * TIF_SVE controls whether a task can use SVE without trapping while - * in userspace, and also the way a task's FPSIMD/SVE state is stored - * in thread_struct. + * in userspace, and also (together with TIF_SME) the way a task's + * FPSIMD/SVE state is stored in thread_struct. * * The kernel uses this flag to track whether a user task is actively * using SVE, and therefore whether full SVE register state needs to * be tracked. If not, the cheaper FPSIMD context handling code can * be used instead of the more costly SVE equivalents. * - * * TIF_SVE set: + * * TIF_SVE or SVCR.SM set: * * The task can execute SVE instructions while in userspace without * trapping to the kernel. @@ -296,7 +338,8 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type, * When stored, Z0-Z31 (incorporating Vn in bits[127:0] or the * corresponding Zn), P0-P15 and FFR are encoded in in * task->thread.sve_state, formatted appropriately for vector - * length task->thread.sve_vl. + * length task->thread.sve_vl or, if SVCR.SM is set, + * task->thread.sme_vl. * * task->thread.sve_state must point to a valid buffer at least * sve_state_size(task) bytes in size. @@ -334,16 +377,44 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type, */ static void task_fpsimd_load(void) { + bool restore_sve_regs = false; + bool restore_ffr; + WARN_ON(!system_supports_fpsimd()); WARN_ON(!have_cpu_fpsimd_context()); + /* Check if we should restore SVE first */ if (IS_ENABLED(CONFIG_ARM64_SVE) && test_thread_flag(TIF_SVE)) { sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1); + restore_sve_regs = true; + restore_ffr = true; + } + + /* Restore SME, override SVE register configuration if needed */ + if (system_supports_sme()) { + unsigned long sme_vl = task_get_sme_vl(current); + + /* Ensure VL is set up for restoring data */ + if (test_thread_flag(TIF_SME)) + sme_set_vq(sve_vq_from_vl(sme_vl) - 1); + + write_sysreg_s(current->thread.svcr, SYS_SVCR_EL0); + + if (thread_za_enabled(¤t->thread)) + za_load_state(current->thread.za_state); + + if (thread_sm_enabled(¤t->thread)) { + restore_sve_regs = true; + restore_ffr = system_supports_fa64(); + } + } + + if (restore_sve_regs) sve_load_state(sve_pffr(¤t->thread), - ¤t->thread.uw.fpsimd_state.fpsr, true); - } else { + ¤t->thread.uw.fpsimd_state.fpsr, + restore_ffr); + else fpsimd_load_state(¤t->thread.uw.fpsimd_state); - } } /* @@ -361,6 +432,9 @@ static void fpsimd_save(void) struct fpsimd_last_state_struct const *last = this_cpu_ptr(&fpsimd_last_state); /* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */ + bool save_sve_regs = false; + bool save_ffr; + unsigned int vl; WARN_ON(!system_supports_fpsimd()); WARN_ON(!have_cpu_fpsimd_context()); @@ -368,9 +442,32 @@ static void fpsimd_save(void) if (test_thread_flag(TIF_FOREIGN_FPSTATE)) return; - if (IS_ENABLED(CONFIG_ARM64_SVE) && - test_thread_flag(TIF_SVE)) { - if (WARN_ON(sve_get_vl() != last->sve_vl)) { + if (test_thread_flag(TIF_SVE)) { + save_sve_regs = true; + save_ffr = true; + vl = last->sve_vl; + } + + if (system_supports_sme()) { + u64 *svcr = last->svcr; + *svcr = read_sysreg_s(SYS_SVCR_EL0); + + *svcr = read_sysreg_s(SYS_SVCR_EL0); + + if (*svcr & SYS_SVCR_EL0_ZA_MASK) + za_save_state(last->za_state); + + /* If we are in streaming mode override regular SVE. */ + if (*svcr & SYS_SVCR_EL0_SM_MASK) { + save_sve_regs = true; + save_ffr = system_supports_fa64(); + vl = last->sme_vl; + } + } + + if (IS_ENABLED(CONFIG_ARM64_SVE) && save_sve_regs) { + /* Get the configured VL from RDVL, will account for SM */ + if (WARN_ON(sve_get_vl() != vl)) { /* * Can't save the user regs, so current would * re-enter user with corrupt state. @@ -381,8 +478,8 @@ static void fpsimd_save(void) } sve_save_state((char *)last->sve_state + - sve_ffr_offset(last->sve_vl), - &last->st->fpsr, true); + sve_ffr_offset(vl), + &last->st->fpsr, save_ffr); } else { fpsimd_save_state(last->st); } @@ -409,6 +506,8 @@ static unsigned int find_supported_vector_length(enum vec_type type, if (vl > max_vl) vl = max_vl; + if (vl < info->min_vl) + vl = info->min_vl; bit = find_next_bit(info->vq_map, SVE_VQ_MAX, __vq_to_bit(sve_vq_from_vl(vl))); @@ -467,6 +566,30 @@ static int __init sve_sysctl_init(void) static int __init sve_sysctl_init(void) { return 0; } #endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */ +#if defined(CONFIG_ARM64_SME) && defined(CONFIG_SYSCTL) +static struct ctl_table sme_default_vl_table[] = { + { + .procname = "sme_default_vector_length", + .mode = 0644, + .proc_handler = vec_proc_do_default_vl, + .extra1 = &vl_info[ARM64_VEC_SME], + }, + { } +}; + +static int __init sme_sysctl_init(void) +{ + if (system_supports_sme()) + if (!register_sysctl("abi", sme_default_vl_table)) + return -EINVAL; + + return 0; +} + +#else /* ! (CONFIG_ARM64_SME && CONFIG_SYSCTL) */ +static int __init sme_sysctl_init(void) { return 0; } +#endif /* ! (CONFIG_ARM64_SME && CONFIG_SYSCTL) */ + #define ZREG(sve_state, vq, n) ((char *)(sve_state) + \ (SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET)) @@ -520,7 +643,7 @@ static void fpsimd_to_sve(struct task_struct *task) if (!system_supports_sve()) return; - vq = sve_vq_from_vl(task_get_sve_vl(task)); + vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread)); __fpsimd_to_sve(sst, fst, vq); } @@ -537,7 +660,7 @@ static void fpsimd_to_sve(struct task_struct *task) */ static void sve_to_fpsimd(struct task_struct *task) { - unsigned int vq; + unsigned int vq, vl; void const *sst = task->thread.sve_state; struct user_fpsimd_state *fst = &task->thread.uw.fpsimd_state; unsigned int i; @@ -546,7 +669,8 @@ static void sve_to_fpsimd(struct task_struct *task) if (!system_supports_sve()) return; - vq = sve_vq_from_vl(task_get_sve_vl(task)); + vl = thread_get_cur_vl(&task->thread); + vq = sve_vq_from_vl(vl); for (i = 0; i < SVE_NUM_ZREGS; ++i) { p = (__uint128_t const *)ZREG(sst, vq, i); fst->vregs[i] = arm64_le128_to_cpu(*p); @@ -559,9 +683,16 @@ static void sve_to_fpsimd(struct task_struct *task) * Return how many bytes of memory are required to store the full SVE * state for task, given task's currently configured vector length. */ -static size_t sve_state_size(struct task_struct const *task) +size_t sve_state_size(struct task_struct const *task) { - return SVE_SIG_REGS_SIZE(sve_vq_from_vl(task_get_sve_vl(task))); + unsigned int vl = 0; + + if (system_supports_sve()) + vl = task_get_sve_vl(task); + if (system_supports_sme()) + vl = max(vl, task_get_sme_vl(task)); + + return SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl)); } /* @@ -588,6 +719,19 @@ void sve_alloc(struct task_struct *task) /* + * Force the FPSIMD state shared with SVE to be updated in the SVE state + * even if the SVE state is the current active state. + * + * This should only be called by ptrace. task must be non-runnable. + * task->thread.sve_state must point to at least sve_state_size(task) + * bytes of allocated kernel memory. + */ +void fpsimd_force_sync_to_sve(struct task_struct *task) +{ + fpsimd_to_sve(task); +} + +/* * Ensure that task->thread.sve_state is up to date with respect to * the user task, irrespective of when SVE is in use or not. * @@ -597,7 +741,8 @@ void sve_alloc(struct task_struct *task) */ void fpsimd_sync_to_sve(struct task_struct *task) { - if (!test_tsk_thread_flag(task, TIF_SVE)) + if (!test_tsk_thread_flag(task, TIF_SVE) && + !thread_sm_enabled(&task->thread)) fpsimd_to_sve(task); } @@ -611,7 +756,8 @@ void fpsimd_sync_to_sve(struct task_struct *task) */ void sve_sync_to_fpsimd(struct task_struct *task) { - if (test_tsk_thread_flag(task, TIF_SVE)) + if (test_tsk_thread_flag(task, TIF_SVE) || + thread_sm_enabled(&task->thread)) sve_to_fpsimd(task); } @@ -636,7 +782,7 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task) if (!test_tsk_thread_flag(task, TIF_SVE)) return; - vq = sve_vq_from_vl(task_get_sve_vl(task)); + vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread)); memset(sst, 0, SVE_SIG_REGS_SIZE(vq)); __fpsimd_to_sve(sst, fst, vq); @@ -680,8 +826,7 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type, /* * To ensure the FPSIMD bits of the SVE vector registers are preserved, * write any live register state back to task_struct, and convert to a - * regular FPSIMD thread. Since the vector length can only be changed - * with a syscall we can't be in streaming mode while reconfiguring. + * regular FPSIMD thread. */ if (task == current) { get_cpu_fpsimd_context(); @@ -690,17 +835,26 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type, } fpsimd_flush_task_state(task); - if (test_and_clear_tsk_thread_flag(task, TIF_SVE)) + if (test_and_clear_tsk_thread_flag(task, TIF_SVE) || + thread_sm_enabled(&task->thread)) sve_to_fpsimd(task); + if (system_supports_sme() && type == ARM64_VEC_SME) { + task->thread.svcr &= ~(SYS_SVCR_EL0_SM_MASK | + SYS_SVCR_EL0_ZA_MASK); + clear_thread_flag(TIF_SME); + } + if (task == current) put_cpu_fpsimd_context(); /* - * Force reallocation of task SVE state to the correct size - * on next use: + * Force reallocation of task SVE and SME state to the correct + * size on next use: */ sve_free(task); + if (system_supports_sme() && type == ARM64_VEC_SME) + sme_free(task); task_set_vl(task, type, vl); @@ -761,6 +915,36 @@ int sve_get_current_vl(void) return vec_prctl_status(ARM64_VEC_SVE, 0); } +#ifdef CONFIG_ARM64_SME +/* PR_SME_SET_VL */ +int sme_set_current_vl(unsigned long arg) +{ + unsigned long vl, flags; + int ret; + + vl = arg & PR_SME_VL_LEN_MASK; + flags = arg & ~vl; + + if (!system_supports_sme() || is_compat_task()) + return -EINVAL; + + ret = vec_set_vector_length(current, ARM64_VEC_SME, vl, flags); + if (ret) + return ret; + + return vec_prctl_status(ARM64_VEC_SME, flags); +} + +/* PR_SME_GET_VL */ +int sme_get_current_vl(void) +{ + if (!system_supports_sme() || is_compat_task()) + return -EINVAL; + + return vec_prctl_status(ARM64_VEC_SME, 0); +} +#endif /* CONFIG_ARM64_SME */ + static void vec_probe_vqs(struct vl_info *info, DECLARE_BITMAP(map, SVE_VQ_MAX)) { @@ -770,7 +954,23 @@ static void vec_probe_vqs(struct vl_info *info, for (vq = SVE_VQ_MAX; vq >= SVE_VQ_MIN; --vq) { write_vl(info->type, vq - 1); /* self-syncing */ - vl = sve_get_vl(); + + switch (info->type) { + case ARM64_VEC_SVE: + vl = sve_get_vl(); + break; + case ARM64_VEC_SME: + vl = sme_get_vl(); + break; + default: + vl = 0; + break; + } + + /* Minimum VL identified? */ + if (sve_vq_from_vl(vl) > vq) + break; + vq = sve_vq_from_vl(vl); /* skip intervening lengths */ set_bit(__vq_to_bit(vq), map); } @@ -856,21 +1056,25 @@ int vec_verify_vq_map(enum vec_type type) static void __init sve_efi_setup(void) { - struct vl_info *info = &vl_info[ARM64_VEC_SVE]; + int max_vl = 0; + int i; if (!IS_ENABLED(CONFIG_EFI)) return; + for (i = 0; i < ARRAY_SIZE(vl_info); i++) + max_vl = max(vl_info[i].max_vl, max_vl); + /* * alloc_percpu() warns and prints a backtrace if this goes wrong. * This is evidence of a crippled system and we are returning void, * so no attempt is made to handle this situation here. */ - if (!sve_vl_valid(info->max_vl)) + if (!sve_vl_valid(max_vl)) goto fail; efi_sve_state = __alloc_percpu( - SVE_SIG_REGS_SIZE(sve_vq_from_vl(info->max_vl)), SVE_VQ_BYTES); + SVE_SIG_REGS_SIZE(sve_vq_from_vl(max_vl)), SVE_VQ_BYTES); if (!efi_sve_state) goto fail; @@ -989,10 +1193,172 @@ void __init sve_setup(void) void fpsimd_release_task(struct task_struct *dead_task) { __sve_free(dead_task); + sme_free(dead_task); } #endif /* CONFIG_ARM64_SVE */ +#ifdef CONFIG_ARM64_SME + +/* + * Ensure that task->thread.za_state is allocated and sufficiently large. + * + * This function should be used only in preparation for replacing + * task->thread.za_state with new data. The memory is always zeroed + * here to prevent stale data from showing through: this is done in + * the interest of testability and predictability, the architecture + * guarantees that when ZA is enabled it will be zeroed. + */ +void sme_alloc(struct task_struct *task) +{ + if (task->thread.za_state) { + memset(task->thread.za_state, 0, za_state_size(task)); + return; + } + + /* This could potentially be up to 64K. */ + task->thread.za_state = + kzalloc(za_state_size(task), GFP_KERNEL); +} + +static void sme_free(struct task_struct *task) +{ + kfree(task->thread.za_state); + task->thread.za_state = NULL; +} + +void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p) +{ + /* Set priority for all PEs to architecturally defined minimum */ + write_sysreg_s(read_sysreg_s(SYS_SMPRI_EL1) & ~SMPRI_EL1_PRIORITY_MASK, + SYS_SMPRI_EL1); + + /* Allow SME in kernel */ + write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_SMEN_EL1EN, CPACR_EL1); + isb(); + + /* Allow EL0 to access TPIDR2 */ + write_sysreg(read_sysreg(SCTLR_EL1) | SCTLR_ELx_ENTP2, SCTLR_EL1); + isb(); +} + +/* + * This must be called after sme_kernel_enable(), we rely on the + * feature table being sorted to ensure this. + */ +void fa64_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p) +{ + /* Allow use of FA64 */ + write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_FA64_MASK, + SYS_SMCR_EL1); +} + +/* + * Read the pseudo-SMCR used by cpufeatures to identify the supported + * vector length. + * + * Use only if SME is present. + * This function clobbers the SME vector length. + */ +u64 read_smcr_features(void) +{ + u64 smcr; + unsigned int vq_max; + + sme_kernel_enable(NULL); + sme_smstart_sm(); + + /* + * Set the maximum possible VL. + */ + write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_LEN_MASK, + SYS_SMCR_EL1); + + smcr = read_sysreg_s(SYS_SMCR_EL1); + smcr &= ~(u64)SMCR_ELx_LEN_MASK; /* Only the LEN field */ + vq_max = sve_vq_from_vl(sve_get_vl()); + smcr |= vq_max - 1; /* set LEN field to maximum effective value */ + + sme_smstop_sm(); + + return smcr; +} + +void __init sme_setup(void) +{ + struct vl_info *info = &vl_info[ARM64_VEC_SME]; + u64 smcr; + int min_bit; + + if (!system_supports_sme()) + return; + + /* + * SME doesn't require any particular vector length be + * supported but it does require at least one. We should have + * disabled the feature entirely while bringing up CPUs but + * let's double check here. + */ + WARN_ON(bitmap_empty(info->vq_map, SVE_VQ_MAX)); + + min_bit = find_last_bit(info->vq_map, SVE_VQ_MAX); + info->min_vl = sve_vl_from_vq(__bit_to_vq(min_bit)); + + smcr = read_sanitised_ftr_reg(SYS_SMCR_EL1); + info->max_vl = sve_vl_from_vq((smcr & SMCR_ELx_LEN_MASK) + 1); + + /* + * Sanity-check that the max VL we determined through CPU features + * corresponds properly to sme_vq_map. If not, do our best: + */ + if (WARN_ON(info->max_vl != find_supported_vector_length(ARM64_VEC_SME, + info->max_vl))) + info->max_vl = find_supported_vector_length(ARM64_VEC_SME, + info->max_vl); + + WARN_ON(info->min_vl > info->max_vl); + + /* + * For the default VL, pick the maximum supported value <= 32 + * (256 bits) if there is one since this is guaranteed not to + * grow the signal frame when in streaming mode, otherwise the + * minimum available VL will be used. + */ + set_sme_default_vl(find_supported_vector_length(ARM64_VEC_SME, 32)); + + pr_info("SME: minimum available vector length %u bytes per vector\n", + info->min_vl); + pr_info("SME: maximum available vector length %u bytes per vector\n", + info->max_vl); + pr_info("SME: default vector length %u bytes per vector\n", + get_sme_default_vl()); +} + +#endif /* CONFIG_ARM64_SME */ + +static void sve_init_regs(void) +{ + /* + * Convert the FPSIMD state to SVE, zeroing all the state that + * is not shared with FPSIMD. If (as is likely) the current + * state is live in the registers then do this there and + * update our metadata for the current task including + * disabling the trap, otherwise update our in-memory copy. + * We are guaranteed to not be in streaming mode, we can only + * take a SVE trap when not in streaming mode and we can't be + * in streaming mode when taking a SME trap. + */ + if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) { + unsigned long vq_minus_one = + sve_vq_from_vl(task_get_sve_vl(current)) - 1; + sve_set_vq(vq_minus_one); + sve_flush_live(true, vq_minus_one); + fpsimd_bind_task_to_cpu(); + } else { + fpsimd_to_sve(current); + } +} + /* * Trapped SVE access * @@ -1024,22 +1390,77 @@ void do_sve_acc(unsigned int esr, struct pt_regs *regs) WARN_ON(1); /* SVE access shouldn't have trapped */ /* - * Convert the FPSIMD state to SVE, zeroing all the state that - * is not shared with FPSIMD. If (as is likely) the current - * state is live in the registers then do this there and - * update our metadata for the current task including - * disabling the trap, otherwise update our in-memory copy. + * Even if the task can have used streaming mode we can only + * generate SVE access traps in normal SVE mode and + * transitioning out of streaming mode may discard any + * streaming mode state. Always clear the high bits to avoid + * any potential errors tracking what is properly initialised. */ + sve_init_regs(); + + put_cpu_fpsimd_context(); +} + +/* + * Trapped SME access + * + * Storage is allocated for the full SVE and SME state, the current + * FPSIMD register contents are migrated to SVE if SVE is not already + * active, and the access trap is disabled. + * + * TIF_SME should be clear on entry: otherwise, fpsimd_restore_current_state() + * would have disabled the SME access trap for userspace during + * ret_to_user, making an SVE access trap impossible in that case. + */ +void do_sme_acc(unsigned int esr, struct pt_regs *regs) +{ + /* Even if we chose not to use SME, the hardware could still trap: */ + if (unlikely(!system_supports_sme()) || WARN_ON(is_compat_task())) { + force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); + return; + } + + /* + * If this not a trap due to SME being disabled then something + * is being used in the wrong mode, report as SIGILL. + */ + if (ESR_ELx_ISS(esr) != ESR_ELx_SME_ISS_SME_DISABLED) { + force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); + return; + } + + sve_alloc(current); + sme_alloc(current); + if (!current->thread.sve_state || !current->thread.za_state) { + force_sig(SIGKILL); + return; + } + + get_cpu_fpsimd_context(); + + /* With TIF_SME userspace shouldn't generate any traps */ + if (test_and_set_thread_flag(TIF_SME)) + WARN_ON(1); + if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) { unsigned long vq_minus_one = - sve_vq_from_vl(task_get_sve_vl(current)) - 1; - sve_set_vq(vq_minus_one); - sve_flush_live(true, vq_minus_one); + sve_vq_from_vl(task_get_sme_vl(current)) - 1; + sme_set_vq(vq_minus_one); + fpsimd_bind_task_to_cpu(); - } else { - fpsimd_to_sve(current); } + /* + * If SVE was not already active initialise the SVE registers, + * any non-shared state between the streaming and regular SVE + * registers is architecturally guaranteed to be zeroed when + * we enter streaming mode. We do not need to initialize ZA + * since ZA must be disabled at this point and enabling ZA is + * architecturally defined to zero ZA. + */ + if (system_supports_sve() && !test_thread_flag(TIF_SVE)) + sve_init_regs(); + put_cpu_fpsimd_context(); } @@ -1156,6 +1577,13 @@ void fpsimd_flush_thread(void) fpsimd_flush_thread_vl(ARM64_VEC_SVE); } + if (system_supports_sme()) { + clear_thread_flag(TIF_SME); + sme_free(current); + fpsimd_flush_thread_vl(ARM64_VEC_SME); + current->thread.svcr = 0; + } + put_cpu_fpsimd_context(); } @@ -1198,22 +1626,34 @@ static void fpsimd_bind_task_to_cpu(void) WARN_ON(!system_supports_fpsimd()); last->st = ¤t->thread.uw.fpsimd_state; last->sve_state = current->thread.sve_state; + last->za_state = current->thread.za_state; last->sve_vl = task_get_sve_vl(current); + last->sme_vl = task_get_sme_vl(current); + last->svcr = ¤t->thread.svcr; current->thread.fpsimd_cpu = smp_processor_id(); + /* + * Toggle SVE and SME trapping for userspace if needed, these + * are serialsied by ret_to_user(). + */ + if (system_supports_sme()) { + if (test_thread_flag(TIF_SME)) + sme_user_enable(); + else + sme_user_disable(); + } + if (system_supports_sve()) { - /* Toggle SVE trapping for userspace if needed */ if (test_thread_flag(TIF_SVE)) sve_user_enable(); else sve_user_disable(); - - /* Serialised by exception return to user */ } } void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state, - unsigned int sve_vl) + unsigned int sve_vl, void *za_state, + unsigned int sme_vl, u64 *svcr) { struct fpsimd_last_state_struct *last = this_cpu_ptr(&fpsimd_last_state); @@ -1222,8 +1662,11 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state, WARN_ON(!in_softirq() && !irqs_disabled()); last->st = st; + last->svcr = svcr; last->sve_state = sve_state; + last->za_state = za_state; last->sve_vl = sve_vl; + last->sme_vl = sme_vl; } /* @@ -1320,6 +1763,15 @@ static void fpsimd_flush_cpu_state(void) { WARN_ON(!system_supports_fpsimd()); __this_cpu_write(fpsimd_last_state.st, NULL); + + /* + * Leaving streaming mode enabled will cause issues for any kernel + * NEON and leaving streaming mode or ZA enabled may increase power + * consumption. + */ + if (system_supports_sme()) + sme_smstop(); + set_thread_flag(TIF_FOREIGN_FPSTATE); } @@ -1397,6 +1849,7 @@ EXPORT_SYMBOL(kernel_neon_end); static DEFINE_PER_CPU(struct user_fpsimd_state, efi_fpsimd_state); static DEFINE_PER_CPU(bool, efi_fpsimd_state_used); static DEFINE_PER_CPU(bool, efi_sve_state_used); +static DEFINE_PER_CPU(bool, efi_sm_state); /* * EFI runtime services support functions @@ -1431,12 +1884,28 @@ void __efi_fpsimd_begin(void) */ if (system_supports_sve() && likely(efi_sve_state)) { char *sve_state = this_cpu_ptr(efi_sve_state); + bool ffr = true; + u64 svcr; __this_cpu_write(efi_sve_state_used, true); + if (system_supports_sme()) { + svcr = read_sysreg_s(SYS_SVCR_EL0); + + if (!system_supports_fa64()) + ffr = svcr & SYS_SVCR_EL0_SM_MASK; + + __this_cpu_write(efi_sm_state, ffr); + } + sve_save_state(sve_state + sve_ffr_offset(sve_max_vl()), &this_cpu_ptr(&efi_fpsimd_state)->fpsr, - true); + ffr); + + if (system_supports_sme()) + sysreg_clear_set_s(SYS_SVCR_EL0, + SYS_SVCR_EL0_SM_MASK, 0); + } else { fpsimd_save_state(this_cpu_ptr(&efi_fpsimd_state)); } @@ -1459,11 +1928,26 @@ void __efi_fpsimd_end(void) if (system_supports_sve() && likely(__this_cpu_read(efi_sve_state_used))) { char const *sve_state = this_cpu_ptr(efi_sve_state); + bool ffr = true; + + /* + * Restore streaming mode; EFI calls are + * normal function calls so should not return in + * streaming mode. + */ + if (system_supports_sme()) { + if (__this_cpu_read(efi_sm_state)) { + sysreg_clear_set_s(SYS_SVCR_EL0, + 0, + SYS_SVCR_EL0_SM_MASK); + if (!system_supports_fa64()) + ffr = efi_sm_state; + } + } - sve_set_vq(sve_vq_from_vl(sve_get_vl()) - 1); sve_load_state(sve_state + sve_ffr_offset(sve_max_vl()), &this_cpu_ptr(&efi_fpsimd_state)->fpsr, - true); + ffr); __this_cpu_write(efi_sve_state_used, false); } else { @@ -1538,6 +2022,13 @@ static int __init fpsimd_init(void) if (!cpu_have_named_feature(ASIMD)) pr_notice("Advanced SIMD is not implemented\n"); - return sve_sysctl_init(); + + if (cpu_have_named_feature(SME) && !cpu_have_named_feature(SVE)) + pr_notice("SME is implemented but not SVE\n"); + + sve_sysctl_init(); + sme_sysctl_init(); + + return 0; } core_initcall(fpsimd_init); diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 7fa97df55e3a..9734c9fb1a32 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -250,6 +250,8 @@ void show_regs(struct pt_regs *regs) static void tls_thread_flush(void) { write_sysreg(0, tpidr_el0); + if (system_supports_tpidr2()) + write_sysreg_s(0, SYS_TPIDR2_EL0); if (is_compat_task()) { current->thread.uw.tp_value = 0; @@ -298,16 +300,42 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) /* * Detach src's sve_state (if any) from dst so that it does not - * get erroneously used or freed prematurely. dst's sve_state + * get erroneously used or freed prematurely. dst's copies * will be allocated on demand later on if dst uses SVE. * For consistency, also clear TIF_SVE here: this could be done * later in copy_process(), but to avoid tripping up future - * maintainers it is best not to leave TIF_SVE and sve_state in + * maintainers it is best not to leave TIF flags and buffers in * an inconsistent state, even temporarily. */ dst->thread.sve_state = NULL; clear_tsk_thread_flag(dst, TIF_SVE); + /* + * In the unlikely event that we create a new thread with ZA + * enabled we should retain the ZA state so duplicate it here. + * This may be shortly freed if we exec() or if CLONE_SETTLS + * but it's simpler to do it here. To avoid confusing the rest + * of the code ensure that we have a sve_state allocated + * whenever za_state is allocated. + */ + if (thread_za_enabled(&src->thread)) { + dst->thread.sve_state = kzalloc(sve_state_size(src), + GFP_KERNEL); + if (!dst->thread.sve_state) + return -ENOMEM; + dst->thread.za_state = kmemdup(src->thread.za_state, + za_state_size(src), + GFP_KERNEL); + if (!dst->thread.za_state) { + kfree(dst->thread.sve_state); + dst->thread.sve_state = NULL; + return -ENOMEM; + } + } else { + dst->thread.za_state = NULL; + clear_tsk_thread_flag(dst, TIF_SME); + } + /* clear any pending asynchronous tag fault raised by the parent */ clear_tsk_thread_flag(dst, TIF_MTE_ASYNC_FAULT); @@ -343,6 +371,8 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, * out-of-sync with the saved value. */ *task_user_tls(p) = read_sysreg(tpidr_el0); + if (system_supports_tpidr2()) + p->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0); if (stack_start) { if (is_compat_thread(task_thread_info(p))) @@ -353,10 +383,12 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, /* * If a TLS pointer was passed to clone, use it for the new - * thread. + * thread. We also reset TPIDR2 if it's in use. */ - if (clone_flags & CLONE_SETTLS) + if (clone_flags & CLONE_SETTLS) { p->thread.uw.tp_value = tls; + p->thread.tpidr2_el0 = 0; + } } else { /* * A kthread has no context to ERET to, so ensure any buggy @@ -387,6 +419,8 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, void tls_preserve_current_state(void) { *task_user_tls(current) = read_sysreg(tpidr_el0); + if (system_supports_tpidr2() && !is_compat_task()) + current->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0); } static void tls_thread_switch(struct task_struct *next) @@ -399,6 +433,8 @@ static void tls_thread_switch(struct task_struct *next) write_sysreg(0, tpidrro_el0); write_sysreg(*task_user_tls(next), tpidr_el0); + if (system_supports_tpidr2()) + write_sysreg_s(next->thread.tpidr2_el0, SYS_TPIDR2_EL0); } /* diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 230a47b9189e..47d8a7472171 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -713,21 +713,51 @@ static int system_call_set(struct task_struct *target, #ifdef CONFIG_ARM64_SVE static void sve_init_header_from_task(struct user_sve_header *header, - struct task_struct *target) + struct task_struct *target, + enum vec_type type) { unsigned int vq; + bool active; + bool fpsimd_only; + enum vec_type task_type; memset(header, 0, sizeof(*header)); - header->flags = test_tsk_thread_flag(target, TIF_SVE) ? - SVE_PT_REGS_SVE : SVE_PT_REGS_FPSIMD; - if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT)) - header->flags |= SVE_PT_VL_INHERIT; + /* Check if the requested registers are active for the task */ + if (thread_sm_enabled(&target->thread)) + task_type = ARM64_VEC_SME; + else + task_type = ARM64_VEC_SVE; + active = (task_type == type); + + switch (type) { + case ARM64_VEC_SVE: + if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT)) + header->flags |= SVE_PT_VL_INHERIT; + fpsimd_only = !test_tsk_thread_flag(target, TIF_SVE); + break; + case ARM64_VEC_SME: + if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT)) + header->flags |= SVE_PT_VL_INHERIT; + fpsimd_only = false; + break; + default: + WARN_ON_ONCE(1); + return; + } - header->vl = task_get_sve_vl(target); + if (active) { + if (fpsimd_only) { + header->flags |= SVE_PT_REGS_FPSIMD; + } else { + header->flags |= SVE_PT_REGS_SVE; + } + } + + header->vl = task_get_vl(target, type); vq = sve_vq_from_vl(header->vl); - header->max_vl = sve_max_vl(); + header->max_vl = vec_max_vl(type); header->size = SVE_PT_SIZE(vq, header->flags); header->max_size = SVE_PT_SIZE(sve_vq_from_vl(header->max_vl), SVE_PT_REGS_SVE); @@ -738,19 +768,17 @@ static unsigned int sve_size_from_header(struct user_sve_header const *header) return ALIGN(header->size, SVE_VQ_BYTES); } -static int sve_get(struct task_struct *target, - const struct user_regset *regset, - struct membuf to) +static int sve_get_common(struct task_struct *target, + const struct user_regset *regset, + struct membuf to, + enum vec_type type) { struct user_sve_header header; unsigned int vq; unsigned long start, end; - if (!system_supports_sve()) - return -EINVAL; - /* Header */ - sve_init_header_from_task(&header, target); + sve_init_header_from_task(&header, target, type); vq = sve_vq_from_vl(header.vl); membuf_write(&to, &header, sizeof(header)); @@ -758,49 +786,61 @@ static int sve_get(struct task_struct *target, if (target == current) fpsimd_preserve_current_state(); - /* Registers: FPSIMD-only case */ - BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header)); - if ((header.flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD) + BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); + + switch ((header.flags & SVE_PT_REGS_MASK)) { + case SVE_PT_REGS_FPSIMD: return __fpr_get(target, regset, to); - /* Otherwise: full SVE case */ + case SVE_PT_REGS_SVE: + start = SVE_PT_SVE_OFFSET; + end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq); + membuf_write(&to, target->thread.sve_state, end - start); - BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); - start = SVE_PT_SVE_OFFSET; - end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq); - membuf_write(&to, target->thread.sve_state, end - start); + start = end; + end = SVE_PT_SVE_FPSR_OFFSET(vq); + membuf_zero(&to, end - start); - start = end; - end = SVE_PT_SVE_FPSR_OFFSET(vq); - membuf_zero(&to, end - start); + /* + * Copy fpsr, and fpcr which must follow contiguously in + * struct fpsimd_state: + */ + start = end; + end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE; + membuf_write(&to, &target->thread.uw.fpsimd_state.fpsr, + end - start); - /* - * Copy fpsr, and fpcr which must follow contiguously in - * struct fpsimd_state: - */ - start = end; - end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE; - membuf_write(&to, &target->thread.uw.fpsimd_state.fpsr, end - start); + start = end; + end = sve_size_from_header(&header); + return membuf_zero(&to, end - start); - start = end; - end = sve_size_from_header(&header); - return membuf_zero(&to, end - start); + default: + return 0; + } } -static int sve_set(struct task_struct *target, +static int sve_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) + struct membuf to) +{ + if (!system_supports_sve()) + return -EINVAL; + + return sve_get_common(target, regset, to, ARM64_VEC_SVE); +} + +static int sve_set_common(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf, + enum vec_type type) { int ret; struct user_sve_header header; unsigned int vq; unsigned long start, end; - if (!system_supports_sve()) - return -EINVAL; - /* Header */ if (count < sizeof(header)) return -EINVAL; @@ -813,13 +853,37 @@ static int sve_set(struct task_struct *target, * Apart from SVE_PT_REGS_MASK, all SVE_PT_* flags are consumed by * vec_set_vector_length(), which will also validate them for us: */ - ret = vec_set_vector_length(target, ARM64_VEC_SVE, header.vl, + ret = vec_set_vector_length(target, type, header.vl, ((unsigned long)header.flags & ~SVE_PT_REGS_MASK) << 16); if (ret) goto out; /* Actual VL set may be less than the user asked for: */ - vq = sve_vq_from_vl(task_get_sve_vl(target)); + vq = sve_vq_from_vl(task_get_vl(target, type)); + + /* Enter/exit streaming mode */ + if (system_supports_sme()) { + u64 old_svcr = target->thread.svcr; + + switch (type) { + case ARM64_VEC_SVE: + target->thread.svcr &= ~SYS_SVCR_EL0_SM_MASK; + break; + case ARM64_VEC_SME: + target->thread.svcr |= SYS_SVCR_EL0_SM_MASK; + break; + default: + WARN_ON_ONCE(1); + return -EINVAL; + } + + /* + * If we switched then invalidate any existing SVE + * state and ensure there's storage. + */ + if (target->thread.svcr != old_svcr) + sve_alloc(target); + } /* Registers: FPSIMD-only case */ @@ -828,10 +892,15 @@ static int sve_set(struct task_struct *target, ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, SVE_PT_FPSIMD_OFFSET); clear_tsk_thread_flag(target, TIF_SVE); + if (type == ARM64_VEC_SME) + fpsimd_force_sync_to_sve(target); goto out; } - /* Otherwise: full SVE case */ + /* + * Otherwise: no registers or full SVE case. For backwards + * compatibility reasons we treat empty flags as SVE registers. + */ /* * If setting a different VL from the requested VL and there is @@ -852,8 +921,9 @@ static int sve_set(struct task_struct *target, /* * Ensure target->thread.sve_state is up to date with target's - * FPSIMD regs, so that a short copyin leaves trailing registers - * unmodified. + * FPSIMD regs, so that a short copyin leaves trailing + * registers unmodified. Always enable SVE even if going into + * streaming mode. */ fpsimd_sync_to_sve(target); set_tsk_thread_flag(target, TIF_SVE); @@ -889,8 +959,181 @@ out: return ret; } +static int sve_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + if (!system_supports_sve()) + return -EINVAL; + + return sve_set_common(target, regset, pos, count, kbuf, ubuf, + ARM64_VEC_SVE); +} + #endif /* CONFIG_ARM64_SVE */ +#ifdef CONFIG_ARM64_SME + +static int ssve_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + if (!system_supports_sme()) + return -EINVAL; + + return sve_get_common(target, regset, to, ARM64_VEC_SME); +} + +static int ssve_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + if (!system_supports_sme()) + return -EINVAL; + + return sve_set_common(target, regset, pos, count, kbuf, ubuf, + ARM64_VEC_SME); +} + +static int za_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + struct user_za_header header; + unsigned int vq; + unsigned long start, end; + + if (!system_supports_sme()) + return -EINVAL; + + /* Header */ + memset(&header, 0, sizeof(header)); + + if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT)) + header.flags |= ZA_PT_VL_INHERIT; + + header.vl = task_get_sme_vl(target); + vq = sve_vq_from_vl(header.vl); + header.max_vl = sme_max_vl(); + header.max_size = ZA_PT_SIZE(vq); + + /* If ZA is not active there is only the header */ + if (thread_za_enabled(&target->thread)) + header.size = ZA_PT_SIZE(vq); + else + header.size = ZA_PT_ZA_OFFSET; + + membuf_write(&to, &header, sizeof(header)); + + BUILD_BUG_ON(ZA_PT_ZA_OFFSET != sizeof(header)); + end = ZA_PT_ZA_OFFSET; + + if (target == current) + fpsimd_preserve_current_state(); + + /* Any register data to include? */ + if (thread_za_enabled(&target->thread)) { + start = end; + end = ZA_PT_SIZE(vq); + membuf_write(&to, target->thread.za_state, end - start); + } + + /* Zero any trailing padding */ + start = end; + end = ALIGN(header.size, SVE_VQ_BYTES); + return membuf_zero(&to, end - start); +} + +static int za_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + struct user_za_header header; + unsigned int vq; + unsigned long start, end; + + if (!system_supports_sme()) + return -EINVAL; + + /* Header */ + if (count < sizeof(header)) + return -EINVAL; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &header, + 0, sizeof(header)); + if (ret) + goto out; + + /* + * All current ZA_PT_* flags are consumed by + * vec_set_vector_length(), which will also validate them for + * us: + */ + ret = vec_set_vector_length(target, ARM64_VEC_SME, header.vl, + ((unsigned long)header.flags) << 16); + if (ret) + goto out; + + /* Actual VL set may be less than the user asked for: */ + vq = sve_vq_from_vl(task_get_sme_vl(target)); + + /* Ensure there is some SVE storage for streaming mode */ + if (!target->thread.sve_state) { + sve_alloc(target); + if (!target->thread.sve_state) { + clear_thread_flag(TIF_SME); + ret = -ENOMEM; + goto out; + } + } + + /* Allocate/reinit ZA storage */ + sme_alloc(target); + if (!target->thread.za_state) { + ret = -ENOMEM; + clear_tsk_thread_flag(target, TIF_SME); + goto out; + } + + /* If there is no data then disable ZA */ + if (!count) { + target->thread.svcr &= ~SYS_SVCR_EL0_ZA_MASK; + goto out; + } + + /* + * If setting a different VL from the requested VL and there is + * register data, the data layout will be wrong: don't even + * try to set the registers in this case. + */ + if (vq != sve_vq_from_vl(header.vl)) { + ret = -EIO; + goto out; + } + + BUILD_BUG_ON(ZA_PT_ZA_OFFSET != sizeof(header)); + start = ZA_PT_ZA_OFFSET; + end = ZA_PT_SIZE(vq); + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + target->thread.za_state, + start, end); + if (ret) + goto out; + + /* Mark ZA as active and let userspace use it */ + set_tsk_thread_flag(target, TIF_SME); + target->thread.svcr |= SYS_SVCR_EL0_ZA_MASK; + +out: + fpsimd_flush_task_state(target); + return ret; +} + +#endif /* CONFIG_ARM64_SME */ + #ifdef CONFIG_ARM64_PTR_AUTH static int pac_mask_get(struct task_struct *target, const struct user_regset *regset, @@ -1108,6 +1351,10 @@ enum aarch64_regset { #ifdef CONFIG_ARM64_SVE REGSET_SVE, #endif +#ifdef CONFIG_ARM64_SVE + REGSET_SSVE, + REGSET_ZA, +#endif #ifdef CONFIG_ARM64_PTR_AUTH REGSET_PAC_MASK, REGSET_PAC_ENABLED_KEYS, @@ -1188,6 +1435,25 @@ static const struct user_regset aarch64_regsets[] = { .set = sve_set, }, #endif +#ifdef CONFIG_ARM64_SME + [REGSET_SSVE] = { /* Streaming mode SVE */ + .core_note_type = NT_ARM_SSVE, + .n = DIV_ROUND_UP(SVE_PT_SIZE(SVE_VQ_MAX, SVE_PT_REGS_SVE), + SVE_VQ_BYTES), + .size = SVE_VQ_BYTES, + .align = SVE_VQ_BYTES, + .regset_get = ssve_get, + .set = ssve_set, + }, + [REGSET_ZA] = { /* SME ZA */ + .core_note_type = NT_ARM_ZA, + .n = DIV_ROUND_UP(ZA_PT_ZA_SIZE(SVE_VQ_MAX), SVE_VQ_BYTES), + .size = SVE_VQ_BYTES, + .align = SVE_VQ_BYTES, + .regset_get = za_get, + .set = za_set, + }, +#endif #ifdef CONFIG_ARM64_PTR_AUTH [REGSET_PAC_MASK] = { .core_note_type = NT_ARM_PAC_MASK, diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 4a4122ef6f39..2295948d97fd 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -56,6 +56,7 @@ struct rt_sigframe_user_layout { unsigned long fpsimd_offset; unsigned long esr_offset; unsigned long sve_offset; + unsigned long za_offset; unsigned long extra_offset; unsigned long end_offset; }; @@ -218,6 +219,7 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx) struct user_ctxs { struct fpsimd_context __user *fpsimd; struct sve_context __user *sve; + struct za_context __user *za; }; #ifdef CONFIG_ARM64_SVE @@ -226,11 +228,17 @@ static int preserve_sve_context(struct sve_context __user *ctx) { int err = 0; u16 reserved[ARRAY_SIZE(ctx->__reserved)]; + u16 flags = 0; unsigned int vl = task_get_sve_vl(current); unsigned int vq = 0; - if (test_thread_flag(TIF_SVE)) + if (thread_sm_enabled(¤t->thread)) { + vl = task_get_sme_vl(current); vq = sve_vq_from_vl(vl); + flags |= SVE_SIG_FLAG_SM; + } else if (test_thread_flag(TIF_SVE)) { + vq = sve_vq_from_vl(vl); + } memset(reserved, 0, sizeof(reserved)); @@ -238,6 +246,7 @@ static int preserve_sve_context(struct sve_context __user *ctx) __put_user_error(round_up(SVE_SIG_CONTEXT_SIZE(vq), 16), &ctx->head.size, err); __put_user_error(vl, &ctx->vl, err); + __put_user_error(flags, &ctx->flags, err); BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved)); err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved)); @@ -258,18 +267,28 @@ static int preserve_sve_context(struct sve_context __user *ctx) static int restore_sve_fpsimd_context(struct user_ctxs *user) { int err; - unsigned int vq; + unsigned int vl, vq; struct user_fpsimd_state fpsimd; struct sve_context sve; if (__copy_from_user(&sve, user->sve, sizeof(sve))) return -EFAULT; - if (sve.vl != task_get_sve_vl(current)) + if (sve.flags & SVE_SIG_FLAG_SM) { + if (!system_supports_sme()) + return -EINVAL; + + vl = task_get_sme_vl(current); + } else { + vl = task_get_sve_vl(current); + } + + if (sve.vl != vl) return -EINVAL; if (sve.head.size <= sizeof(*user->sve)) { clear_thread_flag(TIF_SVE); + current->thread.svcr &= ~SYS_SVCR_EL0_SM_MASK; goto fpsimd_only; } @@ -301,7 +320,10 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user) if (err) return -EFAULT; - set_thread_flag(TIF_SVE); + if (sve.flags & SVE_SIG_FLAG_SM) + current->thread.svcr |= SYS_SVCR_EL0_SM_MASK; + else + set_thread_flag(TIF_SVE); fpsimd_only: /* copy the FP and status/control registers */ @@ -326,6 +348,101 @@ extern int restore_sve_fpsimd_context(struct user_ctxs *user); #endif /* ! CONFIG_ARM64_SVE */ +#ifdef CONFIG_ARM64_SME + +static int preserve_za_context(struct za_context __user *ctx) +{ + int err = 0; + u16 reserved[ARRAY_SIZE(ctx->__reserved)]; + unsigned int vl = task_get_sme_vl(current); + unsigned int vq; + + if (thread_za_enabled(¤t->thread)) + vq = sve_vq_from_vl(vl); + else + vq = 0; + + memset(reserved, 0, sizeof(reserved)); + + __put_user_error(ZA_MAGIC, &ctx->head.magic, err); + __put_user_error(round_up(ZA_SIG_CONTEXT_SIZE(vq), 16), + &ctx->head.size, err); + __put_user_error(vl, &ctx->vl, err); + BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved)); + err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved)); + + if (vq) { + /* + * This assumes that the ZA state has already been saved to + * the task struct by calling the function + * fpsimd_signal_preserve_current_state(). + */ + err |= __copy_to_user((char __user *)ctx + ZA_SIG_REGS_OFFSET, + current->thread.za_state, + ZA_SIG_REGS_SIZE(vq)); + } + + return err ? -EFAULT : 0; +} + +static int restore_za_context(struct user_ctxs __user *user) +{ + int err; + unsigned int vq; + struct za_context za; + + if (__copy_from_user(&za, user->za, sizeof(za))) + return -EFAULT; + + if (za.vl != task_get_sme_vl(current)) + return -EINVAL; + + if (za.head.size <= sizeof(*user->za)) { + current->thread.svcr &= ~SYS_SVCR_EL0_ZA_MASK; + return 0; + } + + vq = sve_vq_from_vl(za.vl); + + if (za.head.size < ZA_SIG_CONTEXT_SIZE(vq)) + return -EINVAL; + + /* + * Careful: we are about __copy_from_user() directly into + * thread.za_state with preemption enabled, so protection is + * needed to prevent a racing context switch from writing stale + * registers back over the new data. + */ + + fpsimd_flush_task_state(current); + /* From now, fpsimd_thread_switch() won't touch thread.sve_state */ + + sme_alloc(current); + if (!current->thread.za_state) { + current->thread.svcr &= ~SYS_SVCR_EL0_ZA_MASK; + clear_thread_flag(TIF_SME); + return -ENOMEM; + } + + err = __copy_from_user(current->thread.za_state, + (char __user const *)user->za + + ZA_SIG_REGS_OFFSET, + ZA_SIG_REGS_SIZE(vq)); + if (err) + return -EFAULT; + + set_thread_flag(TIF_SME); + current->thread.svcr |= SYS_SVCR_EL0_ZA_MASK; + + return 0; +} +#else /* ! CONFIG_ARM64_SME */ + +/* Turn any non-optimised out attempts to use these into a link error: */ +extern int preserve_za_context(void __user *ctx); +extern int restore_za_context(struct user_ctxs *user); + +#endif /* ! CONFIG_ARM64_SME */ static int parse_user_sigframe(struct user_ctxs *user, struct rt_sigframe __user *sf) @@ -340,6 +457,7 @@ static int parse_user_sigframe(struct user_ctxs *user, user->fpsimd = NULL; user->sve = NULL; + user->za = NULL; if (!IS_ALIGNED((unsigned long)base, 16)) goto invalid; @@ -393,7 +511,7 @@ static int parse_user_sigframe(struct user_ctxs *user, break; case SVE_MAGIC: - if (!system_supports_sve()) + if (!system_supports_sve() && !system_supports_sme()) goto invalid; if (user->sve) @@ -405,6 +523,19 @@ static int parse_user_sigframe(struct user_ctxs *user, user->sve = (struct sve_context __user *)head; break; + case ZA_MAGIC: + if (!system_supports_sme()) + goto invalid; + + if (user->za) + goto invalid; + + if (size < sizeof(*user->za)) + goto invalid; + + user->za = (struct za_context __user *)head; + break; + case EXTRA_MAGIC: if (have_extra_context) goto invalid; @@ -528,6 +659,9 @@ static int restore_sigframe(struct pt_regs *regs, } } + if (err == 0 && system_supports_sme() && user.za) + err = restore_za_context(&user); + return err; } @@ -594,11 +728,12 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, if (system_supports_sve()) { unsigned int vq = 0; - if (add_all || test_thread_flag(TIF_SVE)) { - int vl = sve_max_vl(); + if (add_all || test_thread_flag(TIF_SVE) || + thread_sm_enabled(¤t->thread)) { + int vl = max(sve_max_vl(), sme_max_vl()); if (!add_all) - vl = task_get_sve_vl(current); + vl = thread_get_cur_vl(¤t->thread); vq = sve_vq_from_vl(vl); } @@ -609,6 +744,24 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, return err; } + if (system_supports_sme()) { + unsigned int vl; + unsigned int vq = 0; + + if (add_all) + vl = sme_max_vl(); + else + vl = task_get_sme_vl(current); + + if (thread_za_enabled(¤t->thread)) + vq = sve_vq_from_vl(vl); + + err = sigframe_alloc(user, &user->za_offset, + ZA_SIG_CONTEXT_SIZE(vq)); + if (err) + return err; + } + return sigframe_alloc_end(user); } @@ -649,13 +802,21 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user, __put_user_error(current->thread.fault_code, &esr_ctx->esr, err); } - /* Scalable Vector Extension state, if present */ - if (system_supports_sve() && err == 0 && user->sve_offset) { + /* Scalable Vector Extension state (including streaming), if present */ + if ((system_supports_sve() || system_supports_sme()) && + err == 0 && user->sve_offset) { struct sve_context __user *sve_ctx = apply_user_offset(user, user->sve_offset); err |= preserve_sve_context(sve_ctx); } + /* ZA state if present */ + if (system_supports_sme() && err == 0 && user->za_offset) { + struct za_context __user *za_ctx = + apply_user_offset(user, user->za_offset); + err |= preserve_za_context(za_ctx); + } + if (err == 0 && user->extra_offset) { char __user *sfp = (char __user *)user->sigframe; char __user *userp = @@ -759,6 +920,13 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka, /* TCO (Tag Check Override) always cleared for signal handlers */ regs->pstate &= ~PSR_TCO_BIT; + /* Signal handlers are invoked with ZA and streaming mode disabled */ + if (system_supports_sme()) { + current->thread.svcr &= ~(SYS_SVCR_EL0_ZA_MASK | + SYS_SVCR_EL0_SM_MASK); + sme_smstop(); + } + if (ka->sa.sa_flags & SA_RESTORER) sigtramp = ka->sa.sa_restorer; else diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index c938603b3ba0..92c69e5ac269 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -158,11 +158,36 @@ trace_exit: syscall_trace_exit(regs); } -static inline void sve_user_discard(void) +/* + * As per the ABI exit SME streaming mode and clear the SVE state not + * shared with FPSIMD on syscall entry. + */ +static inline void fp_user_discard(void) { + /* + * If SME is active then exit streaming mode. If ZA is active + * then flush the SVE registers but leave userspace access to + * both SVE and SME enabled, otherwise disable SME for the + * task and fall through to disabling SVE too. This means + * that after a syscall we never have any streaming mode + * register state to track, if this changes the KVM code will + * need updating. + */ + if (system_supports_sme() && test_thread_flag(TIF_SME)) { + u64 svcr = read_sysreg_s(SYS_SVCR_EL0); + + if (svcr & SYS_SVCR_EL0_SM_MASK) + sme_smstop_sm(); + } + if (!system_supports_sve()) return; + /* + * If SME is not active then disable SVE, the registers will + * be cleared when userspace next attempts to access them and + * we do not need to track the SVE register state until then. + */ clear_thread_flag(TIF_SVE); /* @@ -177,7 +202,7 @@ static inline void sve_user_discard(void) void do_el0_svc(struct pt_regs *regs) { - sve_user_discard(); + fp_user_discard(); el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table); } diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 0529fd57567e..6751621e5bea 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -821,6 +821,7 @@ static const char *esr_class_str[] = { [ESR_ELx_EC_SVE] = "SVE", [ESR_ELx_EC_ERET] = "ERET/ERETAA/ERETAB", [ESR_ELx_EC_FPAC] = "FPAC", + [ESR_ELx_EC_SME] = "SME", [ESR_ELx_EC_IMP_DEF] = "EL3 IMP DEF", [ESR_ELx_EC_IABT_LOW] = "IABT (lower EL)", [ESR_ELx_EC_IABT_CUR] = "IABT (current EL)", diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 6e542e2eae32..4e39ace073af 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -208,18 +208,16 @@ static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id) return IRQ_HANDLED; } -static u64 kvm_timer_compute_delta(struct arch_timer_context *timer_ctx) +static u64 kvm_counter_compute_delta(struct arch_timer_context *timer_ctx, + u64 val) { - u64 cval, now; - - cval = timer_get_cval(timer_ctx); - now = kvm_phys_timer_read() - timer_get_offset(timer_ctx); + u64 now = kvm_phys_timer_read() - timer_get_offset(timer_ctx); - if (now < cval) { + if (now < val) { u64 ns; ns = cyclecounter_cyc2ns(timecounter->cc, - cval - now, + val - now, timecounter->mask, &timecounter->frac); return ns; @@ -228,6 +226,11 @@ static u64 kvm_timer_compute_delta(struct arch_timer_context *timer_ctx) return 0; } +static u64 kvm_timer_compute_delta(struct arch_timer_context *timer_ctx) +{ + return kvm_counter_compute_delta(timer_ctx, timer_get_cval(timer_ctx)); +} + static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx) { WARN_ON(timer_ctx && timer_ctx->loaded); @@ -236,6 +239,20 @@ static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx) (ARCH_TIMER_CTRL_IT_MASK | ARCH_TIMER_CTRL_ENABLE)) == ARCH_TIMER_CTRL_ENABLE); } +static bool vcpu_has_wfit_active(struct kvm_vcpu *vcpu) +{ + return (cpus_have_final_cap(ARM64_HAS_WFXT) && + (vcpu->arch.flags & KVM_ARM64_WFIT)); +} + +static u64 wfit_delay_ns(struct kvm_vcpu *vcpu) +{ + struct arch_timer_context *ctx = vcpu_vtimer(vcpu); + u64 val = vcpu_get_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu)); + + return kvm_counter_compute_delta(ctx, val); +} + /* * Returns the earliest expiration time in ns among guest timers. * Note that it will return 0 if none of timers can fire. @@ -253,6 +270,9 @@ static u64 kvm_timer_earliest_exp(struct kvm_vcpu *vcpu) min_delta = min(min_delta, kvm_timer_compute_delta(ctx)); } + if (vcpu_has_wfit_active(vcpu)) + min_delta = min(min_delta, wfit_delay_ns(vcpu)); + /* If none of timers can fire, then return 0 */ if (min_delta == ULLONG_MAX) return 0; @@ -350,15 +370,9 @@ static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx) return cval <= now; } -bool kvm_timer_is_pending(struct kvm_vcpu *vcpu) +int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) { - struct timer_map map; - - get_timer_map(vcpu, &map); - - return kvm_timer_should_fire(map.direct_vtimer) || - kvm_timer_should_fire(map.direct_ptimer) || - kvm_timer_should_fire(map.emul_ptimer); + return vcpu_has_wfit_active(vcpu) && wfit_delay_ns(vcpu) == 0; } /* @@ -484,7 +498,8 @@ static void kvm_timer_blocking(struct kvm_vcpu *vcpu) */ if (!kvm_timer_irq_can_fire(map.direct_vtimer) && !kvm_timer_irq_can_fire(map.direct_ptimer) && - !kvm_timer_irq_can_fire(map.emul_ptimer)) + !kvm_timer_irq_can_fire(map.emul_ptimer) && + !vcpu_has_wfit_active(vcpu)) return; /* diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 523bc934fe2f..114184781bba 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -97,6 +97,10 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, } mutex_unlock(&kvm->lock); break; + case KVM_CAP_ARM_SYSTEM_SUSPEND: + r = 0; + set_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags); + break; default: r = -EINVAL; break; @@ -156,6 +160,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.max_vcpus = kvm_arm_default_max_vcpus(); set_default_spectre(kvm); + kvm_arm_init_hypercalls(kvm); return ret; out_free_stage2_pgd: @@ -210,6 +215,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SET_GUEST_DEBUG: case KVM_CAP_VCPU_ATTRIBUTES: case KVM_CAP_PTP_KVM: + case KVM_CAP_ARM_SYSTEM_SUSPEND: r = 1; break; case KVM_CAP_SET_GUEST_DEBUG2: @@ -356,11 +362,6 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvm_arm_vcpu_destroy(vcpu); } -int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) -{ - return kvm_timer_is_pending(vcpu); -} - void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) { @@ -432,20 +433,34 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) vcpu->cpu = -1; } -static void vcpu_power_off(struct kvm_vcpu *vcpu) +void kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu) { - vcpu->arch.power_off = true; + vcpu->arch.mp_state.mp_state = KVM_MP_STATE_STOPPED; kvm_make_request(KVM_REQ_SLEEP, vcpu); kvm_vcpu_kick(vcpu); } +bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.mp_state.mp_state == KVM_MP_STATE_STOPPED; +} + +static void kvm_arm_vcpu_suspend(struct kvm_vcpu *vcpu) +{ + vcpu->arch.mp_state.mp_state = KVM_MP_STATE_SUSPENDED; + kvm_make_request(KVM_REQ_SUSPEND, vcpu); + kvm_vcpu_kick(vcpu); +} + +static bool kvm_arm_vcpu_suspended(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.mp_state.mp_state == KVM_MP_STATE_SUSPENDED; +} + int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { - if (vcpu->arch.power_off) - mp_state->mp_state = KVM_MP_STATE_STOPPED; - else - mp_state->mp_state = KVM_MP_STATE_RUNNABLE; + *mp_state = vcpu->arch.mp_state; return 0; } @@ -457,10 +472,13 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, switch (mp_state->mp_state) { case KVM_MP_STATE_RUNNABLE: - vcpu->arch.power_off = false; + vcpu->arch.mp_state = *mp_state; break; case KVM_MP_STATE_STOPPED: - vcpu_power_off(vcpu); + kvm_arm_vcpu_power_off(vcpu); + break; + case KVM_MP_STATE_SUSPENDED: + kvm_arm_vcpu_suspend(vcpu); break; default: ret = -EINVAL; @@ -480,7 +498,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v) { bool irq_lines = *vcpu_hcr(v) & (HCR_VI | HCR_VF); return ((irq_lines || kvm_vgic_vcpu_pending_irq(v)) - && !v->arch.power_off && !v->arch.pause); + && !kvm_arm_vcpu_stopped(v) && !v->arch.pause); } bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) @@ -592,15 +610,15 @@ void kvm_arm_resume_guest(struct kvm *kvm) } } -static void vcpu_req_sleep(struct kvm_vcpu *vcpu) +static void kvm_vcpu_sleep(struct kvm_vcpu *vcpu) { struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); rcuwait_wait_event(wait, - (!vcpu->arch.power_off) &&(!vcpu->arch.pause), + (!kvm_arm_vcpu_stopped(vcpu)) && (!vcpu->arch.pause), TASK_INTERRUPTIBLE); - if (vcpu->arch.power_off || vcpu->arch.pause) { + if (kvm_arm_vcpu_stopped(vcpu) || vcpu->arch.pause) { /* Awaken to handle a signal, request we sleep again later. */ kvm_make_request(KVM_REQ_SLEEP, vcpu); } @@ -639,6 +657,7 @@ void kvm_vcpu_wfi(struct kvm_vcpu *vcpu) preempt_enable(); kvm_vcpu_halt(vcpu); + vcpu->arch.flags &= ~KVM_ARM64_WFIT; kvm_clear_request(KVM_REQ_UNHALT, vcpu); preempt_disable(); @@ -646,11 +665,53 @@ void kvm_vcpu_wfi(struct kvm_vcpu *vcpu) preempt_enable(); } -static void check_vcpu_requests(struct kvm_vcpu *vcpu) +static int kvm_vcpu_suspend(struct kvm_vcpu *vcpu) +{ + if (!kvm_arm_vcpu_suspended(vcpu)) + return 1; + + kvm_vcpu_wfi(vcpu); + + /* + * The suspend state is sticky; we do not leave it until userspace + * explicitly marks the vCPU as runnable. Request that we suspend again + * later. + */ + kvm_make_request(KVM_REQ_SUSPEND, vcpu); + + /* + * Check to make sure the vCPU is actually runnable. If so, exit to + * userspace informing it of the wakeup condition. + */ + if (kvm_arch_vcpu_runnable(vcpu)) { + memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event)); + vcpu->run->system_event.type = KVM_SYSTEM_EVENT_WAKEUP; + vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; + return 0; + } + + /* + * Otherwise, we were unblocked to process a different event, such as a + * pending signal. Return 1 and allow kvm_arch_vcpu_ioctl_run() to + * process the event. + */ + return 1; +} + +/** + * check_vcpu_requests - check and handle pending vCPU requests + * @vcpu: the VCPU pointer + * + * Return: 1 if we should enter the guest + * 0 if we should exit to userspace + * < 0 if we should exit to userspace, where the return value indicates + * an error + */ +static int check_vcpu_requests(struct kvm_vcpu *vcpu) { if (kvm_request_pending(vcpu)) { if (kvm_check_request(KVM_REQ_SLEEP, vcpu)) - vcpu_req_sleep(vcpu); + kvm_vcpu_sleep(vcpu); if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu)) kvm_reset_vcpu(vcpu); @@ -675,7 +736,12 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_RELOAD_PMU, vcpu)) kvm_pmu_handle_pmcr(vcpu, __vcpu_sys_reg(vcpu, PMCR_EL0)); + + if (kvm_check_request(KVM_REQ_SUSPEND, vcpu)) + return kvm_vcpu_suspend(vcpu); } + + return 1; } static bool vcpu_mode_is_bad_32bit(struct kvm_vcpu *vcpu) @@ -791,7 +857,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) if (!ret) ret = 1; - check_vcpu_requests(vcpu); + if (ret > 0) + ret = check_vcpu_requests(vcpu); /* * Preparing the interrupts to be injected also @@ -1124,9 +1191,9 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu, * Handle the "start in power-off" case. */ if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features)) - vcpu_power_off(vcpu); + kvm_arm_vcpu_power_off(vcpu); else - vcpu->arch.power_off = false; + vcpu->arch.mp_state.mp_state = KVM_MP_STATE_RUNNABLE; return 0; } @@ -1483,7 +1550,6 @@ static void cpu_prepare_hyp_mode(int cpu) tcr |= (idmap_t0sz & GENMASK(TCR_TxSZ_WIDTH - 1, 0)) << TCR_T0SZ_OFFSET; params->tcr_el2 = tcr; - params->stack_hyp_va = kern_hyp_va(per_cpu(kvm_arm_hyp_stack_page, cpu) + PAGE_SIZE); params->pgd_pa = kvm_mmu_get_httbr(); if (is_protected_kvm_enabled()) params->hcr_el2 = HCR_HOST_NVHE_PROTECTED_FLAGS; @@ -1933,14 +1999,46 @@ static int init_hyp_mode(void) * Map the Hyp stack pages */ for_each_possible_cpu(cpu) { + struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu); char *stack_page = (char *)per_cpu(kvm_arm_hyp_stack_page, cpu); - err = create_hyp_mappings(stack_page, stack_page + PAGE_SIZE, - PAGE_HYP); + unsigned long hyp_addr; + /* + * Allocate a contiguous HYP private VA range for the stack + * and guard page. The allocation is also aligned based on + * the order of its size. + */ + err = hyp_alloc_private_va_range(PAGE_SIZE * 2, &hyp_addr); + if (err) { + kvm_err("Cannot allocate hyp stack guard page\n"); + goto out_err; + } + + /* + * Since the stack grows downwards, map the stack to the page + * at the higher address and leave the lower guard page + * unbacked. + * + * Any valid stack address now has the PAGE_SHIFT bit as 1 + * and addresses corresponding to the guard page have the + * PAGE_SHIFT bit as 0 - this is used for overflow detection. + */ + err = __create_hyp_mappings(hyp_addr + PAGE_SIZE, PAGE_SIZE, + __pa(stack_page), PAGE_HYP); if (err) { kvm_err("Cannot map hyp stack\n"); goto out_err; } + + /* + * Save the stack PA in nvhe_init_params. This will be needed + * to recreate the stack mapping in protected nVHE mode. + * __hyp_pa() won't do the right thing there, since the stack + * has been mapped in the flexible private VA space. + */ + params->stack_pa = __pa(stack_page); + + params->stack_hyp_va = hyp_addr + (2 * PAGE_SIZE); } for_each_possible_cpu(cpu) { diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 397fdac75cb1..441edb9c398c 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -82,6 +82,26 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) vcpu->arch.flags |= KVM_ARM64_HOST_SVE_ENABLED; + + /* + * We don't currently support SME guests but if we leave + * things in streaming mode then when the guest starts running + * FPSIMD or SVE code it may generate SME traps so as a + * special case if we are in streaming mode we force the host + * state to be saved now and exit streaming mode so that we + * don't have to handle any SME traps for valid guest + * operations. Do this for ZA as well for now for simplicity. + */ + if (system_supports_sme()) { + if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN) + vcpu->arch.flags |= KVM_ARM64_HOST_SME_ENABLED; + + if (read_sysreg_s(SYS_SVCR_EL0) & + (SYS_SVCR_EL0_SM_MASK | SYS_SVCR_EL0_ZA_MASK)) { + vcpu->arch.flags &= ~KVM_ARM64_FP_HOST; + fpsimd_save_and_flush_cpu_state(); + } + } } /* @@ -109,9 +129,14 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) WARN_ON_ONCE(!irqs_disabled()); if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) { + /* + * Currently we do not support SME guests so SVCR is + * always 0 and we just need a variable to point to. + */ fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.fp_regs, vcpu->arch.sve_state, - vcpu->arch.sve_max_vl); + vcpu->arch.sve_max_vl, + NULL, 0, &vcpu->arch.svcr); clear_thread_flag(TIF_FOREIGN_FPSTATE); update_thread_flag(TIF_SVE, vcpu_has_sve(vcpu)); @@ -130,6 +155,22 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) local_irq_save(flags); + /* + * If we have VHE then the Hyp code will reset CPACR_EL1 to + * CPACR_EL1_DEFAULT and we need to reenable SME. + */ + if (has_vhe() && system_supports_sme()) { + /* Also restore EL0 state seen on entry */ + if (vcpu->arch.flags & KVM_ARM64_HOST_SME_ENABLED) + sysreg_clear_set(CPACR_EL1, 0, + CPACR_EL1_SMEN_EL0EN | + CPACR_EL1_SMEN_EL1EN); + else + sysreg_clear_set(CPACR_EL1, + CPACR_EL1_SMEN_EL0EN, + CPACR_EL1_SMEN_EL1EN); + } + if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) { if (vcpu_has_sve(vcpu)) { __vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_el1(SYS_ZCR); diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 7e15b03fbdf8..8c607199cad1 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -18,7 +18,7 @@ #include <linux/string.h> #include <linux/vmalloc.h> #include <linux/fs.h> -#include <kvm/arm_psci.h> +#include <kvm/arm_hypercalls.h> #include <asm/cputype.h> #include <linux/uaccess.h> #include <asm/fpsimd.h> @@ -756,7 +756,9 @@ int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) switch (reg->id & KVM_REG_ARM_COPROC_MASK) { case KVM_REG_ARM_CORE: return get_core_reg(vcpu, reg); - case KVM_REG_ARM_FW: return kvm_arm_get_fw_reg(vcpu, reg); + case KVM_REG_ARM_FW: + case KVM_REG_ARM_FW_FEAT_BMAP: + return kvm_arm_get_fw_reg(vcpu, reg); case KVM_REG_ARM64_SVE: return get_sve_reg(vcpu, reg); } @@ -774,7 +776,9 @@ int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) switch (reg->id & KVM_REG_ARM_COPROC_MASK) { case KVM_REG_ARM_CORE: return set_core_reg(vcpu, reg); - case KVM_REG_ARM_FW: return kvm_arm_set_fw_reg(vcpu, reg); + case KVM_REG_ARM_FW: + case KVM_REG_ARM_FW_FEAT_BMAP: + return kvm_arm_set_fw_reg(vcpu, reg); case KVM_REG_ARM64_SVE: return set_sve_reg(vcpu, reg); } diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 97fe14aab1a3..2ebebd3efaee 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -80,24 +80,51 @@ static int handle_no_fpsimd(struct kvm_vcpu *vcpu) * * @vcpu: the vcpu pointer * - * WFE: Yield the CPU and come back to this vcpu when the scheduler + * WFE[T]: Yield the CPU and come back to this vcpu when the scheduler * decides to. * WFI: Simply call kvm_vcpu_halt(), which will halt execution of * world-switches and schedule other host processes until there is an * incoming IRQ or FIQ to the VM. + * WFIT: Same as WFI, with a timed wakeup implemented as a background timer + * + * WF{I,E}T can immediately return if the deadline has already expired. */ static int kvm_handle_wfx(struct kvm_vcpu *vcpu) { - if (kvm_vcpu_get_esr(vcpu) & ESR_ELx_WFx_ISS_WFE) { + u64 esr = kvm_vcpu_get_esr(vcpu); + + if (esr & ESR_ELx_WFx_ISS_WFE) { trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true); vcpu->stat.wfe_exit_stat++; - kvm_vcpu_on_spin(vcpu, vcpu_mode_priv(vcpu)); } else { trace_kvm_wfx_arm64(*vcpu_pc(vcpu), false); vcpu->stat.wfi_exit_stat++; - kvm_vcpu_wfi(vcpu); } + if (esr & ESR_ELx_WFx_ISS_WFxT) { + if (esr & ESR_ELx_WFx_ISS_RV) { + u64 val, now; + + now = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_TIMER_CNT); + val = vcpu_get_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu)); + + if (now >= val) + goto out; + } else { + /* Treat WFxT as WFx if RN is invalid */ + esr &= ~ESR_ELx_WFx_ISS_WFxT; + } + } + + if (esr & ESR_ELx_WFx_ISS_WFE) { + kvm_vcpu_on_spin(vcpu, vcpu_mode_priv(vcpu)); + } else { + if (esr & ESR_ELx_WFx_ISS_WFxT) + vcpu->arch.flags |= KVM_ARM64_WFIT; + + kvm_vcpu_wfi(vcpu); + } +out: kvm_incr_pc(vcpu); return 1; @@ -167,6 +194,7 @@ static exit_handle_fn arm_exit_handlers[] = { [ESR_ELx_EC_CP15_64] = kvm_handle_cp15_64, [ESR_ELx_EC_CP14_MR] = kvm_handle_cp14_32, [ESR_ELx_EC_CP14_LS] = kvm_handle_cp14_load_store, + [ESR_ELx_EC_CP10_ID] = kvm_handle_cp10_id, [ESR_ELx_EC_CP14_64] = kvm_handle_cp14_64, [ESR_ELx_EC_HVC32] = handle_hvc, [ESR_ELx_EC_SMC32] = handle_smc, @@ -295,13 +323,8 @@ void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr, u64 elr_in_kimg = __phys_to_kimg(elr_phys); u64 hyp_offset = elr_in_kimg - kaslr_offset() - elr_virt; u64 mode = spsr & PSR_MODE_MASK; + u64 panic_addr = elr_virt + hyp_offset; - /* - * The nVHE hyp symbols are not included by kallsyms to avoid issues - * with aliasing. That means that the symbols cannot be printed with the - * "%pS" format specifier, so fall back to the vmlinux address if - * there's no better option. - */ if (mode != PSR_MODE_EL2t && mode != PSR_MODE_EL2h) { kvm_err("Invalid host exception to nVHE hyp!\n"); } else if (ESR_ELx_EC(esr) == ESR_ELx_EC_BRK64 && @@ -321,9 +344,11 @@ void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr, if (file) kvm_err("nVHE hyp BUG at: %s:%u!\n", file, line); else - kvm_err("nVHE hyp BUG at: %016llx!\n", elr_virt + hyp_offset); + kvm_err("nVHE hyp BUG at: [<%016llx>] %pB!\n", panic_addr, + (void *)panic_addr); } else { - kvm_err("nVHE hyp panic at: %016llx!\n", elr_virt + hyp_offset); + kvm_err("nVHE hyp panic at: [<%016llx>] %pB!\n", panic_addr, + (void *)panic_addr); } /* diff --git a/arch/arm64/kvm/hyp/include/nvhe/mm.h b/arch/arm64/kvm/hyp/include/nvhe/mm.h index 2d08510c6cc1..42d8eb9bfe72 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/mm.h +++ b/arch/arm64/kvm/hyp/include/nvhe/mm.h @@ -19,8 +19,10 @@ int hyp_back_vmemmap(phys_addr_t phys, unsigned long size, phys_addr_t back); int pkvm_cpu_set_vector(enum arm64_hyp_spectre_vector slot); int pkvm_create_mappings(void *from, void *to, enum kvm_pgtable_prot prot); int pkvm_create_mappings_locked(void *from, void *to, enum kvm_pgtable_prot prot); -unsigned long __pkvm_create_private_mapping(phys_addr_t phys, size_t size, - enum kvm_pgtable_prot prot); +int __pkvm_create_private_mapping(phys_addr_t phys, size_t size, + enum kvm_pgtable_prot prot, + unsigned long *haddr); +int pkvm_alloc_private_va_range(size_t size, unsigned long *haddr); static inline void hyp_vmemmap_range(phys_addr_t phys, unsigned long size, unsigned long *start, unsigned long *end) diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S index 3d613e721a75..20bf1327e6b9 100644 --- a/arch/arm64/kvm/hyp/nvhe/host.S +++ b/arch/arm64/kvm/hyp/nvhe/host.S @@ -153,6 +153,18 @@ SYM_FUNC_END(__host_hvc) .macro invalid_host_el2_vect .align 7 + + /* + * Test whether the SP has overflowed, without corrupting a GPR. + * nVHE hypervisor stacks are aligned so that the PAGE_SHIFT bit + * of SP should always be 1. + */ + add sp, sp, x0 // sp' = sp + x0 + sub x0, sp, x0 // x0' = sp' - x0 = (sp + x0) - x0 = sp + tbz x0, #PAGE_SHIFT, .L__hyp_sp_overflow\@ + sub x0, sp, x0 // x0'' = sp' - x0' = (sp + x0) - sp = x0 + sub sp, sp, x0 // sp'' = sp' - x0 = (sp + x0) - x0 = sp + /* If a guest is loaded, panic out of it. */ stp x0, x1, [sp, #-16]! get_loaded_vcpu x0, x1 @@ -165,6 +177,18 @@ SYM_FUNC_END(__host_hvc) * been partially clobbered by __host_enter. */ b hyp_panic + +.L__hyp_sp_overflow\@: + /* + * Reset SP to the top of the stack, to allow handling the hyp_panic. + * This corrupts the stack but is ok, since we won't be attempting + * any unwinding here. + */ + ldr_this_cpu x0, kvm_init_params + NVHE_INIT_STACK_HYP_VA, x1 + mov sp, x0 + + b hyp_panic_bad_stack + ASM_BUG() .endm .macro invalid_host_el1_vect @@ -198,15 +222,15 @@ SYM_CODE_START(__kvm_hyp_host_vector) invalid_host_el2_vect // FIQ EL2h invalid_host_el2_vect // Error EL2h - host_el1_sync_vect // Synchronous 64-bit EL1 - invalid_host_el1_vect // IRQ 64-bit EL1 - invalid_host_el1_vect // FIQ 64-bit EL1 - invalid_host_el1_vect // Error 64-bit EL1 + host_el1_sync_vect // Synchronous 64-bit EL1/EL0 + invalid_host_el1_vect // IRQ 64-bit EL1/EL0 + invalid_host_el1_vect // FIQ 64-bit EL1/EL0 + invalid_host_el1_vect // Error 64-bit EL1/EL0 - invalid_host_el1_vect // Synchronous 32-bit EL1 - invalid_host_el1_vect // IRQ 32-bit EL1 - invalid_host_el1_vect // FIQ 32-bit EL1 - invalid_host_el1_vect // Error 32-bit EL1 + host_el1_sync_vect // Synchronous 32-bit EL1/EL0 + invalid_host_el1_vect // IRQ 32-bit EL1/EL0 + invalid_host_el1_vect // FIQ 32-bit EL1/EL0 + invalid_host_el1_vect // Error 32-bit EL1/EL0 SYM_CODE_END(__kvm_hyp_host_vector) /* diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 5e2197db0d32..3cea4b6ac23e 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -160,7 +160,23 @@ static void handle___pkvm_create_private_mapping(struct kvm_cpu_context *host_ct DECLARE_REG(size_t, size, host_ctxt, 2); DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 3); - cpu_reg(host_ctxt, 1) = __pkvm_create_private_mapping(phys, size, prot); + /* + * __pkvm_create_private_mapping() populates a pointer with the + * hypervisor start address of the allocation. + * + * However, handle___pkvm_create_private_mapping() hypercall crosses the + * EL1/EL2 boundary so the pointer would not be valid in this context. + * + * Instead pass the allocation address as the return value (or return + * ERR_PTR() on failure). + */ + unsigned long haddr; + int err = __pkvm_create_private_mapping(phys, size, prot, &haddr); + + if (err) + haddr = (unsigned long)ERR_PTR(err); + + cpu_reg(host_ctxt, 1) = haddr; } static void handle___pkvm_prot_finalize(struct kvm_cpu_context *host_ctxt) diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c index cdbe8e246418..96193cb31a39 100644 --- a/arch/arm64/kvm/hyp/nvhe/mm.c +++ b/arch/arm64/kvm/hyp/nvhe/mm.c @@ -37,36 +37,60 @@ static int __pkvm_create_mappings(unsigned long start, unsigned long size, return err; } -unsigned long __pkvm_create_private_mapping(phys_addr_t phys, size_t size, - enum kvm_pgtable_prot prot) +/** + * pkvm_alloc_private_va_range - Allocates a private VA range. + * @size: The size of the VA range to reserve. + * @haddr: The hypervisor virtual start address of the allocation. + * + * The private virtual address (VA) range is allocated above __io_map_base + * and aligned based on the order of @size. + * + * Return: 0 on success or negative error code on failure. + */ +int pkvm_alloc_private_va_range(size_t size, unsigned long *haddr) { - unsigned long addr; - int err; + unsigned long base, addr; + int ret = 0; hyp_spin_lock(&pkvm_pgd_lock); - size = PAGE_ALIGN(size + offset_in_page(phys)); - addr = __io_map_base; - __io_map_base += size; + /* Align the allocation based on the order of its size */ + addr = ALIGN(__io_map_base, PAGE_SIZE << get_order(size)); - /* Are we overflowing on the vmemmap ? */ - if (__io_map_base > __hyp_vmemmap) { - __io_map_base -= size; - addr = (unsigned long)ERR_PTR(-ENOMEM); - goto out; - } + /* The allocated size is always a multiple of PAGE_SIZE */ + base = addr + PAGE_ALIGN(size); - err = kvm_pgtable_hyp_map(&pkvm_pgtable, addr, size, phys, prot); - if (err) { - addr = (unsigned long)ERR_PTR(err); - goto out; + /* Are we overflowing on the vmemmap ? */ + if (!addr || base > __hyp_vmemmap) + ret = -ENOMEM; + else { + __io_map_base = base; + *haddr = addr; } - addr = addr + offset_in_page(phys); -out: hyp_spin_unlock(&pkvm_pgd_lock); - return addr; + return ret; +} + +int __pkvm_create_private_mapping(phys_addr_t phys, size_t size, + enum kvm_pgtable_prot prot, + unsigned long *haddr) +{ + unsigned long addr; + int err; + + size = PAGE_ALIGN(size + offset_in_page(phys)); + err = pkvm_alloc_private_va_range(size, &addr); + if (err) + return err; + + err = __pkvm_create_mappings(addr, size, phys, prot); + if (err) + return err; + + *haddr = addr + offset_in_page(phys); + return err; } int pkvm_create_mappings_locked(void *from, void *to, enum kvm_pgtable_prot prot) @@ -146,7 +170,8 @@ int pkvm_cpu_set_vector(enum arm64_hyp_spectre_vector slot) int hyp_map_vectors(void) { phys_addr_t phys; - void *bp_base; + unsigned long bp_base; + int ret; if (!kvm_system_needs_idmapped_vectors()) { __hyp_bp_vect_base = __bp_harden_hyp_vecs; @@ -154,13 +179,12 @@ int hyp_map_vectors(void) } phys = __hyp_pa(__bp_harden_hyp_vecs); - bp_base = (void *)__pkvm_create_private_mapping(phys, - __BP_HARDEN_HYP_VECS_SZ, - PAGE_HYP_EXEC); - if (IS_ERR_OR_NULL(bp_base)) - return PTR_ERR(bp_base); + ret = __pkvm_create_private_mapping(phys, __BP_HARDEN_HYP_VECS_SZ, + PAGE_HYP_EXEC, &bp_base); + if (ret) + return ret; - __hyp_bp_vect_base = bp_base; + __hyp_bp_vect_base = (void *)bp_base; return 0; } diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c index 27af337f9fea..e8d4ea2fcfa0 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -99,17 +99,42 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size, return ret; for (i = 0; i < hyp_nr_cpus; i++) { + struct kvm_nvhe_init_params *params = per_cpu_ptr(&kvm_init_params, i); + unsigned long hyp_addr; + start = (void *)kern_hyp_va(per_cpu_base[i]); end = start + PAGE_ALIGN(hyp_percpu_size); ret = pkvm_create_mappings(start, end, PAGE_HYP); if (ret) return ret; - end = (void *)per_cpu_ptr(&kvm_init_params, i)->stack_hyp_va; - start = end - PAGE_SIZE; - ret = pkvm_create_mappings(start, end, PAGE_HYP); + /* + * Allocate a contiguous HYP private VA range for the stack + * and guard page. The allocation is also aligned based on + * the order of its size. + */ + ret = pkvm_alloc_private_va_range(PAGE_SIZE * 2, &hyp_addr); + if (ret) + return ret; + + /* + * Since the stack grows downwards, map the stack to the page + * at the higher address and leave the lower guard page + * unbacked. + * + * Any valid stack address now has the PAGE_SHIFT bit as 1 + * and addresses corresponding to the guard page have the + * PAGE_SHIFT bit as 0 - this is used for overflow detection. + */ + hyp_spin_lock(&pkvm_pgd_lock); + ret = kvm_pgtable_hyp_map(&pkvm_pgtable, hyp_addr + PAGE_SIZE, + PAGE_SIZE, params->stack_pa, PAGE_HYP); + hyp_spin_unlock(&pkvm_pgd_lock); if (ret) return ret; + + /* Update stack_hyp_va to end of the stack's private VA range */ + params->stack_hyp_va = hyp_addr + (2 * PAGE_SIZE); } /* diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 6410d21d8695..978f1b94fb25 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -47,10 +47,24 @@ static void __activate_traps(struct kvm_vcpu *vcpu) val |= CPTR_EL2_TFP | CPTR_EL2_TZ; __activate_traps_fpsimd32(vcpu); } + if (cpus_have_final_cap(ARM64_SME)) + val |= CPTR_EL2_TSM; write_sysreg(val, cptr_el2); write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el2); + if (cpus_have_final_cap(ARM64_SME)) { + val = read_sysreg_s(SYS_HFGRTR_EL2); + val &= ~(HFGxTR_EL2_nTPIDR2_EL0_MASK | + HFGxTR_EL2_nSMPRI_EL1_MASK); + write_sysreg_s(val, SYS_HFGRTR_EL2); + + val = read_sysreg_s(SYS_HFGWTR_EL2); + val &= ~(HFGxTR_EL2_nTPIDR2_EL0_MASK | + HFGxTR_EL2_nSMPRI_EL1_MASK); + write_sysreg_s(val, SYS_HFGWTR_EL2); + } + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt; @@ -94,9 +108,25 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2); + if (cpus_have_final_cap(ARM64_SME)) { + u64 val; + + val = read_sysreg_s(SYS_HFGRTR_EL2); + val |= HFGxTR_EL2_nTPIDR2_EL0_MASK | + HFGxTR_EL2_nSMPRI_EL1_MASK; + write_sysreg_s(val, SYS_HFGRTR_EL2); + + val = read_sysreg_s(SYS_HFGWTR_EL2); + val |= HFGxTR_EL2_nTPIDR2_EL0_MASK | + HFGxTR_EL2_nSMPRI_EL1_MASK; + write_sysreg_s(val, SYS_HFGWTR_EL2); + } + cptr = CPTR_EL2_DEFAULT; if (vcpu_has_sve(vcpu) && (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)) cptr |= CPTR_EL2_TZ; + if (cpus_have_final_cap(ARM64_SME)) + cptr &= ~CPTR_EL2_TSM; write_sysreg(cptr, cptr_el2); write_sysreg(__kvm_hyp_host_vector, vbar_el2); @@ -347,7 +377,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu) return exit_code; } -void __noreturn hyp_panic(void) +asmlinkage void __noreturn hyp_panic(void) { u64 spsr = read_sysreg_el2(SYS_SPSR); u64 elr = read_sysreg_el2(SYS_ELR); @@ -369,6 +399,11 @@ void __noreturn hyp_panic(void) unreachable(); } +asmlinkage void __noreturn hyp_panic_bad_stack(void) +{ + hyp_panic(); +} + asmlinkage void kvm_unexpected_el2_exception(void) { return __kvm_unexpected_el2_exception(); diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 262dfe03134d..969f20daf97a 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -41,7 +41,8 @@ static void __activate_traps(struct kvm_vcpu *vcpu) val = read_sysreg(cpacr_el1); val |= CPACR_EL1_TTA; - val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN); + val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN | + CPACR_EL1_SMEN_EL0EN | CPACR_EL1_SMEN_EL1EN); /* * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to @@ -62,6 +63,10 @@ static void __activate_traps(struct kvm_vcpu *vcpu) __activate_traps_fpsimd32(vcpu); } + if (cpus_have_final_cap(ARM64_SME)) + write_sysreg(read_sysreg(sctlr_el2) & ~SCTLR_ELx_ENTP2, + sctlr_el2); + write_sysreg(val, cpacr_el1); write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el1); @@ -83,6 +88,10 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) */ asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT)); + if (cpus_have_final_cap(ARM64_SME)) + write_sysreg(read_sysreg(sctlr_el2) | SCTLR_ELx_ENTP2, + sctlr_el2); + write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1); if (!arm64_kernel_unmapped_at_el0()) diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index 202b8c455724..c9f401fa01a9 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -9,6 +9,13 @@ #include <kvm/arm_hypercalls.h> #include <kvm/arm_psci.h> +#define KVM_ARM_SMCCC_STD_FEATURES \ + GENMASK(KVM_REG_ARM_STD_BMAP_BIT_COUNT - 1, 0) +#define KVM_ARM_SMCCC_STD_HYP_FEATURES \ + GENMASK(KVM_REG_ARM_STD_HYP_BMAP_BIT_COUNT - 1, 0) +#define KVM_ARM_SMCCC_VENDOR_HYP_FEATURES \ + GENMASK(KVM_REG_ARM_VENDOR_HYP_BMAP_BIT_COUNT - 1, 0) + static void kvm_ptp_get_time(struct kvm_vcpu *vcpu, u64 *val) { struct system_time_snapshot systime_snapshot; @@ -58,13 +65,73 @@ static void kvm_ptp_get_time(struct kvm_vcpu *vcpu, u64 *val) val[3] = lower_32_bits(cycles); } +static bool kvm_hvc_call_default_allowed(u32 func_id) +{ + switch (func_id) { + /* + * List of function-ids that are not gated with the bitmapped + * feature firmware registers, and are to be allowed for + * servicing the call by default. + */ + case ARM_SMCCC_VERSION_FUNC_ID: + case ARM_SMCCC_ARCH_FEATURES_FUNC_ID: + return true; + default: + /* PSCI 0.2 and up is in the 0:0x1f range */ + if (ARM_SMCCC_OWNER_NUM(func_id) == ARM_SMCCC_OWNER_STANDARD && + ARM_SMCCC_FUNC_NUM(func_id) <= 0x1f) + return true; + + /* + * KVM's PSCI 0.1 doesn't comply with SMCCC, and has + * its own function-id base and range + */ + if (func_id >= KVM_PSCI_FN(0) && func_id <= KVM_PSCI_FN(3)) + return true; + + return false; + } +} + +static bool kvm_hvc_call_allowed(struct kvm_vcpu *vcpu, u32 func_id) +{ + struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat; + + switch (func_id) { + case ARM_SMCCC_TRNG_VERSION: + case ARM_SMCCC_TRNG_FEATURES: + case ARM_SMCCC_TRNG_GET_UUID: + case ARM_SMCCC_TRNG_RND32: + case ARM_SMCCC_TRNG_RND64: + return test_bit(KVM_REG_ARM_STD_BIT_TRNG_V1_0, + &smccc_feat->std_bmap); + case ARM_SMCCC_HV_PV_TIME_FEATURES: + case ARM_SMCCC_HV_PV_TIME_ST: + return test_bit(KVM_REG_ARM_STD_HYP_BIT_PV_TIME, + &smccc_feat->std_hyp_bmap); + case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID: + case ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID: + return test_bit(KVM_REG_ARM_VENDOR_HYP_BIT_FUNC_FEAT, + &smccc_feat->vendor_hyp_bmap); + case ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID: + return test_bit(KVM_REG_ARM_VENDOR_HYP_BIT_PTP, + &smccc_feat->vendor_hyp_bmap); + default: + return kvm_hvc_call_default_allowed(func_id); + } +} + int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) { + struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat; u32 func_id = smccc_get_function(vcpu); u64 val[4] = {SMCCC_RET_NOT_SUPPORTED}; u32 feature; gpa_t gpa; + if (!kvm_hvc_call_allowed(vcpu, func_id)) + goto out; + switch (func_id) { case ARM_SMCCC_VERSION_FUNC_ID: val[0] = ARM_SMCCC_VERSION_1_1; @@ -120,7 +187,9 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) } break; case ARM_SMCCC_HV_PV_TIME_FEATURES: - val[0] = SMCCC_RET_SUCCESS; + if (test_bit(KVM_REG_ARM_STD_HYP_BIT_PV_TIME, + &smccc_feat->std_hyp_bmap)) + val[0] = SMCCC_RET_SUCCESS; break; } break; @@ -139,8 +208,7 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) val[3] = ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3; break; case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID: - val[0] = BIT(ARM_SMCCC_KVM_FUNC_FEATURES); - val[0] |= BIT(ARM_SMCCC_KVM_FUNC_PTP); + val[0] = smccc_feat->vendor_hyp_bmap; break; case ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID: kvm_ptp_get_time(vcpu, val); @@ -155,6 +223,259 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) return kvm_psci_call(vcpu); } +out: smccc_set_retval(vcpu, val[0], val[1], val[2], val[3]); return 1; } + +static const u64 kvm_arm_fw_reg_ids[] = { + KVM_REG_ARM_PSCI_VERSION, + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1, + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2, + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3, + KVM_REG_ARM_STD_BMAP, + KVM_REG_ARM_STD_HYP_BMAP, + KVM_REG_ARM_VENDOR_HYP_BMAP, +}; + +void kvm_arm_init_hypercalls(struct kvm *kvm) +{ + struct kvm_smccc_features *smccc_feat = &kvm->arch.smccc_feat; + + smccc_feat->std_bmap = KVM_ARM_SMCCC_STD_FEATURES; + smccc_feat->std_hyp_bmap = KVM_ARM_SMCCC_STD_HYP_FEATURES; + smccc_feat->vendor_hyp_bmap = KVM_ARM_SMCCC_VENDOR_HYP_FEATURES; +} + +int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu) +{ + return ARRAY_SIZE(kvm_arm_fw_reg_ids); +} + +int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(kvm_arm_fw_reg_ids); i++) { + if (put_user(kvm_arm_fw_reg_ids[i], uindices++)) + return -EFAULT; + } + + return 0; +} + +#define KVM_REG_FEATURE_LEVEL_MASK GENMASK(3, 0) + +/* + * Convert the workaround level into an easy-to-compare number, where higher + * values mean better protection. + */ +static int get_kernel_wa_level(u64 regid) +{ + switch (regid) { + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: + switch (arm64_get_spectre_v2_state()) { + case SPECTRE_VULNERABLE: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL; + case SPECTRE_MITIGATED: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL; + case SPECTRE_UNAFFECTED: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED; + } + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL; + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: + switch (arm64_get_spectre_v4_state()) { + case SPECTRE_MITIGATED: + /* + * As for the hypercall discovery, we pretend we + * don't have any FW mitigation if SSBS is there at + * all times. + */ + if (cpus_have_final_cap(ARM64_SSBS)) + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; + fallthrough; + case SPECTRE_UNAFFECTED: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED; + case SPECTRE_VULNERABLE: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; + } + break; + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: + switch (arm64_get_spectre_bhb_state()) { + case SPECTRE_VULNERABLE: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL; + case SPECTRE_MITIGATED: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL; + case SPECTRE_UNAFFECTED: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED; + } + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL; + } + + return -EINVAL; +} + +int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) +{ + struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat; + void __user *uaddr = (void __user *)(long)reg->addr; + u64 val; + + switch (reg->id) { + case KVM_REG_ARM_PSCI_VERSION: + val = kvm_psci_version(vcpu); + break; + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: + val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK; + break; + case KVM_REG_ARM_STD_BMAP: + val = READ_ONCE(smccc_feat->std_bmap); + break; + case KVM_REG_ARM_STD_HYP_BMAP: + val = READ_ONCE(smccc_feat->std_hyp_bmap); + break; + case KVM_REG_ARM_VENDOR_HYP_BMAP: + val = READ_ONCE(smccc_feat->vendor_hyp_bmap); + break; + default: + return -ENOENT; + } + + if (copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + return 0; +} + +static int kvm_arm_set_fw_reg_bmap(struct kvm_vcpu *vcpu, u64 reg_id, u64 val) +{ + int ret = 0; + struct kvm *kvm = vcpu->kvm; + struct kvm_smccc_features *smccc_feat = &kvm->arch.smccc_feat; + unsigned long *fw_reg_bmap, fw_reg_features; + + switch (reg_id) { + case KVM_REG_ARM_STD_BMAP: + fw_reg_bmap = &smccc_feat->std_bmap; + fw_reg_features = KVM_ARM_SMCCC_STD_FEATURES; + break; + case KVM_REG_ARM_STD_HYP_BMAP: + fw_reg_bmap = &smccc_feat->std_hyp_bmap; + fw_reg_features = KVM_ARM_SMCCC_STD_HYP_FEATURES; + break; + case KVM_REG_ARM_VENDOR_HYP_BMAP: + fw_reg_bmap = &smccc_feat->vendor_hyp_bmap; + fw_reg_features = KVM_ARM_SMCCC_VENDOR_HYP_FEATURES; + break; + default: + return -ENOENT; + } + + /* Check for unsupported bit */ + if (val & ~fw_reg_features) + return -EINVAL; + + mutex_lock(&kvm->lock); + + if (test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &kvm->arch.flags) && + val != *fw_reg_bmap) { + ret = -EBUSY; + goto out; + } + + WRITE_ONCE(*fw_reg_bmap, val); +out: + mutex_unlock(&kvm->lock); + return ret; +} + +int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) +{ + void __user *uaddr = (void __user *)(long)reg->addr; + u64 val; + int wa_level; + + if (copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + switch (reg->id) { + case KVM_REG_ARM_PSCI_VERSION: + { + bool wants_02; + + wants_02 = test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features); + + switch (val) { + case KVM_ARM_PSCI_0_1: + if (wants_02) + return -EINVAL; + vcpu->kvm->arch.psci_version = val; + return 0; + case KVM_ARM_PSCI_0_2: + case KVM_ARM_PSCI_1_0: + case KVM_ARM_PSCI_1_1: + if (!wants_02) + return -EINVAL; + vcpu->kvm->arch.psci_version = val; + return 0; + } + break; + } + + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: + if (val & ~KVM_REG_FEATURE_LEVEL_MASK) + return -EINVAL; + + if (get_kernel_wa_level(reg->id) < val) + return -EINVAL; + + return 0; + + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: + if (val & ~(KVM_REG_FEATURE_LEVEL_MASK | + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED)) + return -EINVAL; + + /* The enabled bit must not be set unless the level is AVAIL. */ + if ((val & KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED) && + (val & KVM_REG_FEATURE_LEVEL_MASK) != KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL) + return -EINVAL; + + /* + * Map all the possible incoming states to the only two we + * really want to deal with. + */ + switch (val & KVM_REG_FEATURE_LEVEL_MASK) { + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL: + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN: + wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; + break; + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL: + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED: + wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED; + break; + default: + return -EINVAL; + } + + /* + * We can deal with NOT_AVAIL on NOT_REQUIRED, but not the + * other way around. + */ + if (get_kernel_wa_level(reg->id) < wa_level) + return -EINVAL; + + return 0; + case KVM_REG_ARM_STD_BMAP: + case KVM_REG_ARM_STD_HYP_BMAP: + case KVM_REG_ARM_VENDOR_HYP_BMAP: + return kvm_arm_set_fw_reg_bmap(vcpu, reg->id, val); + default: + return -ENOENT; + } + + return -EINVAL; +} diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index b47df73e98d7..ba20405d2dc2 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -145,6 +145,34 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr) inject_abt64(vcpu, true, addr); } +void kvm_inject_size_fault(struct kvm_vcpu *vcpu) +{ + unsigned long addr, esr; + + addr = kvm_vcpu_get_fault_ipa(vcpu); + addr |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0); + + if (kvm_vcpu_trap_is_iabt(vcpu)) + kvm_inject_pabt(vcpu, addr); + else + kvm_inject_dabt(vcpu, addr); + + /* + * If AArch64 or LPAE, set FSC to 0 to indicate an Address + * Size Fault at level 0, as if exceeding PARange. + * + * Non-LPAE guests will only get the external abort, as there + * is no way to to describe the ASF. + */ + if (vcpu_el1_is_32bit(vcpu) && + !(vcpu_read_sys_reg(vcpu, TCR_EL1) & TTBCR_EAE)) + return; + + esr = vcpu_read_sys_reg(vcpu, ESR_EL1); + esr &= ~GENMASK_ULL(5, 0); + vcpu_write_sys_reg(vcpu, esr, ESR_EL1); +} + /** * kvm_inject_undefined - inject an undefined instruction into the guest * @vcpu: The vCPU in which to inject the exception diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 53ae2c0640bc..f5651a05b6a8 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -258,8 +258,8 @@ static bool kvm_host_owns_hyp_mappings(void) return true; } -static int __create_hyp_mappings(unsigned long start, unsigned long size, - unsigned long phys, enum kvm_pgtable_prot prot) +int __create_hyp_mappings(unsigned long start, unsigned long size, + unsigned long phys, enum kvm_pgtable_prot prot) { int err; @@ -457,23 +457,22 @@ int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot) return 0; } -static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size, - unsigned long *haddr, - enum kvm_pgtable_prot prot) + +/** + * hyp_alloc_private_va_range - Allocates a private VA range. + * @size: The size of the VA range to reserve. + * @haddr: The hypervisor virtual start address of the allocation. + * + * The private virtual address (VA) range is allocated below io_map_base + * and aligned based on the order of @size. + * + * Return: 0 on success or negative error code on failure. + */ +int hyp_alloc_private_va_range(size_t size, unsigned long *haddr) { unsigned long base; int ret = 0; - if (!kvm_host_owns_hyp_mappings()) { - base = kvm_call_hyp_nvhe(__pkvm_create_private_mapping, - phys_addr, size, prot); - if (IS_ERR_OR_NULL((void *)base)) - return PTR_ERR((void *)base); - *haddr = base; - - return 0; - } - mutex_lock(&kvm_hyp_pgd_mutex); /* @@ -484,8 +483,10 @@ static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size, * * The allocated size is always a multiple of PAGE_SIZE. */ - size = PAGE_ALIGN(size + offset_in_page(phys_addr)); - base = io_map_base - size; + base = io_map_base - PAGE_ALIGN(size); + + /* Align the allocation based on the order of its size */ + base = ALIGN_DOWN(base, PAGE_SIZE << get_order(size)); /* * Verify that BIT(VA_BITS - 1) hasn't been flipped by @@ -495,19 +496,40 @@ static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size, if ((base ^ io_map_base) & BIT(VA_BITS - 1)) ret = -ENOMEM; else - io_map_base = base; + *haddr = io_map_base = base; mutex_unlock(&kvm_hyp_pgd_mutex); + return ret; +} + +static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size, + unsigned long *haddr, + enum kvm_pgtable_prot prot) +{ + unsigned long addr; + int ret = 0; + + if (!kvm_host_owns_hyp_mappings()) { + addr = kvm_call_hyp_nvhe(__pkvm_create_private_mapping, + phys_addr, size, prot); + if (IS_ERR_VALUE(addr)) + return addr; + *haddr = addr; + + return 0; + } + + size = PAGE_ALIGN(size + offset_in_page(phys_addr)); + ret = hyp_alloc_private_va_range(size, &addr); if (ret) - goto out; + return ret; - ret = __create_hyp_mappings(base, size, phys_addr, prot); + ret = __create_hyp_mappings(addr, size, phys_addr, prot); if (ret) - goto out; + return ret; - *haddr = base + offset_in_page(phys_addr); -out: + *haddr = addr + offset_in_page(phys_addr); return ret; } @@ -1337,6 +1359,25 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) fault_ipa = kvm_vcpu_get_fault_ipa(vcpu); is_iabt = kvm_vcpu_trap_is_iabt(vcpu); + if (fault_status == FSC_FAULT) { + /* Beyond sanitised PARange (which is the IPA limit) */ + if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) { + kvm_inject_size_fault(vcpu); + return 1; + } + + /* Falls between the IPA range and the PARange? */ + if (fault_ipa >= BIT_ULL(vcpu->arch.hw_mmu->pgt->ia_bits)) { + fault_ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0); + + if (is_iabt) + kvm_inject_pabt(vcpu, fault_ipa); + else + kvm_inject_dabt(vcpu, fault_ipa); + return 1; + } + } + /* Synchronous External Abort? */ if (kvm_vcpu_abt_issea(vcpu)) { /* diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 78fdc443adc7..3dc990ac4f44 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -177,6 +177,9 @@ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx) struct kvm_pmu *pmu = &vcpu->arch.pmu; struct kvm_pmc *pmc = &pmu->pmc[select_idx]; + if (!kvm_vcpu_has_pmu(vcpu)) + return 0; + counter = kvm_pmu_get_pair_counter_value(vcpu, pmc); if (kvm_pmu_pmc_is_chained(pmc) && @@ -198,6 +201,9 @@ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val) { u64 reg; + if (!kvm_vcpu_has_pmu(vcpu)) + return; + reg = (select_idx == ARMV8_PMU_CYCLE_IDX) ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + select_idx; __vcpu_sys_reg(vcpu, reg) += (s64)val - kvm_pmu_get_counter_value(vcpu, select_idx); @@ -322,6 +328,9 @@ void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) struct kvm_pmu *pmu = &vcpu->arch.pmu; struct kvm_pmc *pmc; + if (!kvm_vcpu_has_pmu(vcpu)) + return; + if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E) || !val) return; @@ -357,7 +366,7 @@ void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) struct kvm_pmu *pmu = &vcpu->arch.pmu; struct kvm_pmc *pmc; - if (!val) + if (!kvm_vcpu_has_pmu(vcpu) || !val) return; for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) { @@ -527,6 +536,9 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val) struct kvm_pmu *pmu = &vcpu->arch.pmu; int i; + if (!kvm_vcpu_has_pmu(vcpu)) + return; + if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E)) return; @@ -576,6 +588,9 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) { int i; + if (!kvm_vcpu_has_pmu(vcpu)) + return; + if (val & ARMV8_PMU_PMCR_E) { kvm_pmu_enable_counter_mask(vcpu, __vcpu_sys_reg(vcpu, PMCNTENSET_EL0)); @@ -739,6 +754,9 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, { u64 reg, mask; + if (!kvm_vcpu_has_pmu(vcpu)) + return; + mask = ARMV8_PMU_EVTYPE_MASK; mask &= ~ARMV8_PMU_EVTYPE_EVENT; mask |= kvm_pmu_event_mask(vcpu->kvm); @@ -827,6 +845,9 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) u64 val, mask = 0; int base, i, nr_events; + if (!kvm_vcpu_has_pmu(vcpu)) + return 0; + if (!pmceid1) { val = read_sysreg(pmceid0_el0); base = 0; diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c index baac2b405f23..7fbc4c1b9df0 100644 --- a/arch/arm64/kvm/psci.c +++ b/arch/arm64/kvm/psci.c @@ -51,13 +51,6 @@ static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu) return PSCI_RET_SUCCESS; } -static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu) -{ - vcpu->arch.power_off = true; - kvm_make_request(KVM_REQ_SLEEP, vcpu); - kvm_vcpu_kick(vcpu); -} - static inline bool kvm_psci_valid_affinity(struct kvm_vcpu *vcpu, unsigned long affinity) { @@ -83,7 +76,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) */ if (!vcpu) return PSCI_RET_INVALID_PARAMS; - if (!vcpu->arch.power_off) { + if (!kvm_arm_vcpu_stopped(vcpu)) { if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1) return PSCI_RET_ALREADY_ON; else @@ -107,12 +100,12 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) kvm_make_request(KVM_REQ_VCPU_RESET, vcpu); /* - * Make sure the reset request is observed if the change to - * power_off is observed. + * Make sure the reset request is observed if the RUNNABLE mp_state is + * observed. */ smp_wmb(); - vcpu->arch.power_off = false; + vcpu->arch.mp_state.mp_state = KVM_MP_STATE_RUNNABLE; kvm_vcpu_wake_up(vcpu); return PSCI_RET_SUCCESS; @@ -150,7 +143,7 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) mpidr = kvm_vcpu_get_mpidr_aff(tmp); if ((mpidr & target_affinity_mask) == target_affinity) { matching_cpus++; - if (!tmp->arch.power_off) + if (!kvm_arm_vcpu_stopped(tmp)) return PSCI_0_2_AFFINITY_LEVEL_ON; } } @@ -176,12 +169,13 @@ static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type, u64 flags) * re-initialized. */ kvm_for_each_vcpu(i, tmp, vcpu->kvm) - tmp->arch.power_off = true; + tmp->arch.mp_state.mp_state = KVM_MP_STATE_STOPPED; kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_SLEEP); memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event)); vcpu->run->system_event.type = type; - vcpu->run->system_event.flags = flags; + vcpu->run->system_event.ndata = 1; + vcpu->run->system_event.data[0] = flags; vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; } @@ -201,6 +195,15 @@ static void kvm_psci_system_reset2(struct kvm_vcpu *vcpu) KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2); } +static void kvm_psci_system_suspend(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + + memset(&run->system_event, 0, sizeof(vcpu->run->system_event)); + run->system_event.type = KVM_SYSTEM_EVENT_SUSPEND; + run->exit_reason = KVM_EXIT_SYSTEM_EVENT; +} + static void kvm_psci_narrow_to_32bit(struct kvm_vcpu *vcpu) { int i; @@ -244,7 +247,7 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) val = kvm_psci_vcpu_suspend(vcpu); break; case PSCI_0_2_FN_CPU_OFF: - kvm_psci_vcpu_off(vcpu); + kvm_arm_vcpu_power_off(vcpu); val = PSCI_RET_SUCCESS; break; case PSCI_0_2_FN_CPU_ON: @@ -304,9 +307,10 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor) { + unsigned long val = PSCI_RET_NOT_SUPPORTED; u32 psci_fn = smccc_get_function(vcpu); + struct kvm *kvm = vcpu->kvm; u32 arg; - unsigned long val; int ret = 1; switch(psci_fn) { @@ -319,6 +323,8 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor) if (val) break; + val = PSCI_RET_NOT_SUPPORTED; + switch(arg) { case PSCI_0_2_FN_PSCI_VERSION: case PSCI_0_2_FN_CPU_SUSPEND: @@ -335,18 +341,32 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor) case ARM_SMCCC_VERSION_FUNC_ID: val = 0; break; + case PSCI_1_0_FN_SYSTEM_SUSPEND: + case PSCI_1_0_FN64_SYSTEM_SUSPEND: + if (test_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags)) + val = 0; + break; case PSCI_1_1_FN_SYSTEM_RESET2: case PSCI_1_1_FN64_SYSTEM_RESET2: - if (minor >= 1) { + if (minor >= 1) val = 0; - break; - } - fallthrough; - default: - val = PSCI_RET_NOT_SUPPORTED; break; } break; + case PSCI_1_0_FN_SYSTEM_SUSPEND: + kvm_psci_narrow_to_32bit(vcpu); + fallthrough; + case PSCI_1_0_FN64_SYSTEM_SUSPEND: + /* + * Return directly to userspace without changing the vCPU's + * registers. Userspace depends on reading the SMCCC parameters + * to implement SYSTEM_SUSPEND. + */ + if (test_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags)) { + kvm_psci_system_suspend(vcpu); + return 0; + } + break; case PSCI_1_1_FN_SYSTEM_RESET2: kvm_psci_narrow_to_32bit(vcpu); fallthrough; @@ -364,7 +384,7 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor) val = PSCI_RET_INVALID_PARAMS; break; } - fallthrough; + break; default: return kvm_psci_0_2_call(vcpu); } @@ -381,7 +401,7 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) switch (psci_fn) { case KVM_PSCI_FN_CPU_OFF: - kvm_psci_vcpu_off(vcpu); + kvm_arm_vcpu_power_off(vcpu); val = PSCI_RET_SUCCESS; break; case KVM_PSCI_FN_CPU_ON: @@ -436,186 +456,3 @@ int kvm_psci_call(struct kvm_vcpu *vcpu) return -EINVAL; } } - -int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu) -{ - return 4; /* PSCI version and three workaround registers */ -} - -int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) -{ - if (put_user(KVM_REG_ARM_PSCI_VERSION, uindices++)) - return -EFAULT; - - if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1, uindices++)) - return -EFAULT; - - if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2, uindices++)) - return -EFAULT; - - if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3, uindices++)) - return -EFAULT; - - return 0; -} - -#define KVM_REG_FEATURE_LEVEL_WIDTH 4 -#define KVM_REG_FEATURE_LEVEL_MASK (BIT(KVM_REG_FEATURE_LEVEL_WIDTH) - 1) - -/* - * Convert the workaround level into an easy-to-compare number, where higher - * values mean better protection. - */ -static int get_kernel_wa_level(u64 regid) -{ - switch (regid) { - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: - switch (arm64_get_spectre_v2_state()) { - case SPECTRE_VULNERABLE: - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL; - case SPECTRE_MITIGATED: - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL; - case SPECTRE_UNAFFECTED: - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED; - } - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL; - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: - switch (arm64_get_spectre_v4_state()) { - case SPECTRE_MITIGATED: - /* - * As for the hypercall discovery, we pretend we - * don't have any FW mitigation if SSBS is there at - * all times. - */ - if (cpus_have_final_cap(ARM64_SSBS)) - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; - fallthrough; - case SPECTRE_UNAFFECTED: - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED; - case SPECTRE_VULNERABLE: - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; - } - break; - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: - switch (arm64_get_spectre_bhb_state()) { - case SPECTRE_VULNERABLE: - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL; - case SPECTRE_MITIGATED: - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL; - case SPECTRE_UNAFFECTED: - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED; - } - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL; - } - - return -EINVAL; -} - -int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) -{ - void __user *uaddr = (void __user *)(long)reg->addr; - u64 val; - - switch (reg->id) { - case KVM_REG_ARM_PSCI_VERSION: - val = kvm_psci_version(vcpu); - break; - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: - val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK; - break; - default: - return -ENOENT; - } - - if (copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id))) - return -EFAULT; - - return 0; -} - -int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) -{ - void __user *uaddr = (void __user *)(long)reg->addr; - u64 val; - int wa_level; - - if (copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id))) - return -EFAULT; - - switch (reg->id) { - case KVM_REG_ARM_PSCI_VERSION: - { - bool wants_02; - - wants_02 = test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features); - - switch (val) { - case KVM_ARM_PSCI_0_1: - if (wants_02) - return -EINVAL; - vcpu->kvm->arch.psci_version = val; - return 0; - case KVM_ARM_PSCI_0_2: - case KVM_ARM_PSCI_1_0: - case KVM_ARM_PSCI_1_1: - if (!wants_02) - return -EINVAL; - vcpu->kvm->arch.psci_version = val; - return 0; - } - break; - } - - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: - if (val & ~KVM_REG_FEATURE_LEVEL_MASK) - return -EINVAL; - - if (get_kernel_wa_level(reg->id) < val) - return -EINVAL; - - return 0; - - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: - if (val & ~(KVM_REG_FEATURE_LEVEL_MASK | - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED)) - return -EINVAL; - - /* The enabled bit must not be set unless the level is AVAIL. */ - if ((val & KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED) && - (val & KVM_REG_FEATURE_LEVEL_MASK) != KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL) - return -EINVAL; - - /* - * Map all the possible incoming states to the only two we - * really want to deal with. - */ - switch (val & KVM_REG_FEATURE_LEVEL_MASK) { - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL: - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN: - wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; - break; - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL: - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED: - wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED; - break; - default: - return -EINVAL; - } - - /* - * We can deal with NOT_AVAIL on NOT_REQUIRED, but not the - * other way around. - */ - if (get_kernel_wa_level(reg->id) < wa_level) - return -EINVAL; - - return 0; - default: - return -ENOENT; - } - - return -EINVAL; -} diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 7b45c040cc27..181db62bcfdc 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1132,6 +1132,8 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, case SYS_ID_AA64PFR1_EL1: if (!kvm_has_mte(vcpu->kvm)) val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_MTE); + + val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_SME); break; case SYS_ID_AA64ISAR1_EL1: if (!vcpu_has_ptrauth(vcpu)) @@ -1144,6 +1146,8 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, if (!vcpu_has_ptrauth(vcpu)) val &= ~(ARM64_FEATURE_MASK(ID_AA64ISAR2_APA3) | ARM64_FEATURE_MASK(ID_AA64ISAR2_GPA3)); + if (!cpus_have_final_cap(ARM64_HAS_WFXT)) + val &= ~ARM64_FEATURE_MASK(ID_AA64ISAR2_WFXT); break; case SYS_ID_AA64DFR0_EL1: /* Limit debug to ARMv8.0 */ @@ -1553,7 +1557,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_UNALLOCATED(4,2), ID_UNALLOCATED(4,3), ID_SANITISED(ID_AA64ZFR0_EL1), - ID_UNALLOCATED(4,5), + ID_HIDDEN(ID_AA64SMFR0_EL1), ID_UNALLOCATED(4,6), ID_UNALLOCATED(4,7), @@ -1596,6 +1600,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility }, { SYS_DESC(SYS_TRFCR_EL1), undef_access }, + { SYS_DESC(SYS_SMPRI_EL1), undef_access }, + { SYS_DESC(SYS_SMCR_EL1), undef_access }, { SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 }, { SYS_DESC(SYS_TTBR1_EL1), access_vm_reg, reset_unknown, TTBR1_EL1 }, { SYS_DESC(SYS_TCR_EL1), access_vm_reg, reset_val, TCR_EL1, 0 }, @@ -1678,8 +1684,10 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr }, { SYS_DESC(SYS_CLIDR_EL1), access_clidr }, + { SYS_DESC(SYS_SMIDR_EL1), undef_access }, { SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 }, { SYS_DESC(SYS_CTR_EL0), access_ctr }, + { SYS_DESC(SYS_SVCR_EL0), undef_access }, { PMU_SYS_REG(SYS_PMCR_EL0), .access = access_pmcr, .reset = reset_pmcr, .reg = PMCR_EL0 }, @@ -1719,6 +1727,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 }, { SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 }, + { SYS_DESC(SYS_TPIDR2_EL0), undef_access }, { SYS_DESC(SYS_SCXTNUM_EL0), undef_access }, @@ -2014,20 +2023,22 @@ static const struct sys_reg_desc cp14_64_regs[] = { { Op1( 0), CRm( 2), .access = trap_raz_wi }, }; +#define CP15_PMU_SYS_REG(_map, _Op1, _CRn, _CRm, _Op2) \ + AA32(_map), \ + Op1(_Op1), CRn(_CRn), CRm(_CRm), Op2(_Op2), \ + .visibility = pmu_visibility + /* Macro to expand the PMEVCNTRn register */ #define PMU_PMEVCNTR(n) \ - /* PMEVCNTRn */ \ - { Op1(0), CRn(0b1110), \ - CRm((0b1000 | (((n) >> 3) & 0x3))), Op2(((n) & 0x7)), \ - access_pmu_evcntr } + { CP15_PMU_SYS_REG(DIRECT, 0, 0b1110, \ + (0b1000 | (((n) >> 3) & 0x3)), ((n) & 0x7)), \ + .access = access_pmu_evcntr } /* Macro to expand the PMEVTYPERn register */ #define PMU_PMEVTYPER(n) \ - /* PMEVTYPERn */ \ - { Op1(0), CRn(0b1110), \ - CRm((0b1100 | (((n) >> 3) & 0x3))), Op2(((n) & 0x7)), \ - access_pmu_evtyper } - + { CP15_PMU_SYS_REG(DIRECT, 0, 0b1110, \ + (0b1100 | (((n) >> 3) & 0x3)), ((n) & 0x7)), \ + .access = access_pmu_evtyper } /* * Trapped cp15 registers. TTBR0/TTBR1 get a double encoding, * depending on the way they are accessed (as a 32bit or a 64bit @@ -2067,25 +2078,25 @@ static const struct sys_reg_desc cp15_regs[] = { { Op1( 0), CRn( 7), CRm(14), Op2( 2), access_dcsw }, /* PMU */ - { Op1( 0), CRn( 9), CRm(12), Op2( 0), access_pmcr }, - { Op1( 0), CRn( 9), CRm(12), Op2( 1), access_pmcnten }, - { Op1( 0), CRn( 9), CRm(12), Op2( 2), access_pmcnten }, - { Op1( 0), CRn( 9), CRm(12), Op2( 3), access_pmovs }, - { Op1( 0), CRn( 9), CRm(12), Op2( 4), access_pmswinc }, - { Op1( 0), CRn( 9), CRm(12), Op2( 5), access_pmselr }, - { AA32(LO), Op1( 0), CRn( 9), CRm(12), Op2( 6), access_pmceid }, - { AA32(LO), Op1( 0), CRn( 9), CRm(12), Op2( 7), access_pmceid }, - { Op1( 0), CRn( 9), CRm(13), Op2( 0), access_pmu_evcntr }, - { Op1( 0), CRn( 9), CRm(13), Op2( 1), access_pmu_evtyper }, - { Op1( 0), CRn( 9), CRm(13), Op2( 2), access_pmu_evcntr }, - { Op1( 0), CRn( 9), CRm(14), Op2( 0), access_pmuserenr }, - { Op1( 0), CRn( 9), CRm(14), Op2( 1), access_pminten }, - { Op1( 0), CRn( 9), CRm(14), Op2( 2), access_pminten }, - { Op1( 0), CRn( 9), CRm(14), Op2( 3), access_pmovs }, - { AA32(HI), Op1( 0), CRn( 9), CRm(14), Op2( 4), access_pmceid }, - { AA32(HI), Op1( 0), CRn( 9), CRm(14), Op2( 5), access_pmceid }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 12, 0), .access = access_pmcr }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 12, 1), .access = access_pmcnten }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 12, 2), .access = access_pmcnten }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 12, 3), .access = access_pmovs }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 12, 4), .access = access_pmswinc }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 12, 5), .access = access_pmselr }, + { CP15_PMU_SYS_REG(LO, 0, 9, 12, 6), .access = access_pmceid }, + { CP15_PMU_SYS_REG(LO, 0, 9, 12, 7), .access = access_pmceid }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 13, 0), .access = access_pmu_evcntr }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 13, 1), .access = access_pmu_evtyper }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 13, 2), .access = access_pmu_evcntr }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 14, 0), .access = access_pmuserenr }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 14, 1), .access = access_pminten }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 14, 2), .access = access_pminten }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 14, 3), .access = access_pmovs }, + { CP15_PMU_SYS_REG(HI, 0, 9, 14, 4), .access = access_pmceid }, + { CP15_PMU_SYS_REG(HI, 0, 9, 14, 5), .access = access_pmceid }, /* PMMIR */ - { Op1( 0), CRn( 9), CRm(14), Op2( 6), trap_raz_wi }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 14, 6), .access = trap_raz_wi }, /* PRRR/MAIR0 */ { AA32(LO), Op1( 0), CRn(10), CRm( 2), Op2( 0), access_vm_reg, NULL, MAIR_EL1 }, @@ -2170,7 +2181,7 @@ static const struct sys_reg_desc cp15_regs[] = { PMU_PMEVTYPER(29), PMU_PMEVTYPER(30), /* PMCCFILTR */ - { Op1(0), CRn(14), CRm(15), Op2(7), access_pmu_evtyper }, + { CP15_PMU_SYS_REG(DIRECT, 0, 14, 15, 7), .access = access_pmu_evtyper }, { Op1(1), CRn( 0), CRm( 0), Op2(0), access_ccsidr }, { Op1(1), CRn( 0), CRm( 0), Op2(1), access_clidr }, @@ -2179,7 +2190,7 @@ static const struct sys_reg_desc cp15_regs[] = { static const struct sys_reg_desc cp15_64_regs[] = { { Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, TTBR0_EL1 }, - { Op1( 0), CRn( 0), CRm( 9), Op2( 0), access_pmu_evcntr }, + { CP15_PMU_SYS_REG(DIRECT, 0, 0, 9, 0), .access = access_pmu_evcntr }, { Op1( 0), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_SGI1R */ { Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, TTBR1_EL1 }, { Op1( 1), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_ASGI1R */ @@ -2246,27 +2257,27 @@ static void perform_access(struct kvm_vcpu *vcpu, * @table: array of trap descriptors * @num: size of the trap descriptor array * - * Return 0 if the access has been handled, and -1 if not. + * Return true if the access has been handled, false if not. */ -static int emulate_cp(struct kvm_vcpu *vcpu, - struct sys_reg_params *params, - const struct sys_reg_desc *table, - size_t num) +static bool emulate_cp(struct kvm_vcpu *vcpu, + struct sys_reg_params *params, + const struct sys_reg_desc *table, + size_t num) { const struct sys_reg_desc *r; if (!table) - return -1; /* Not handled */ + return false; /* Not handled */ r = find_reg(params, table, num); if (r) { perform_access(vcpu, params, r); - return 0; + return true; } /* Not handled */ - return -1; + return false; } static void unhandled_cp_access(struct kvm_vcpu *vcpu, @@ -2304,7 +2315,7 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu, size_t nr_global) { struct sys_reg_params params; - u32 esr = kvm_vcpu_get_esr(vcpu); + u64 esr = kvm_vcpu_get_esr(vcpu); int Rt = kvm_vcpu_sys_get_rt(vcpu); int Rt2 = (esr >> 10) & 0x1f; @@ -2330,7 +2341,7 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu, * potential register operation in the case of a read and return * with success. */ - if (!emulate_cp(vcpu, ¶ms, global, nr_global)) { + if (emulate_cp(vcpu, ¶ms, global, nr_global)) { /* Split up the value between registers for the read side */ if (!params.is_write) { vcpu_set_reg(vcpu, Rt, lower_32_bits(params.regval)); @@ -2344,34 +2355,144 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu, return 1; } +static bool emulate_sys_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *params); + +/* + * The CP10 ID registers are architecturally mapped to AArch64 feature + * registers. Abuse that fact so we can rely on the AArch64 handler for accesses + * from AArch32. + */ +static bool kvm_esr_cp10_id_to_sys64(u64 esr, struct sys_reg_params *params) +{ + u8 reg_id = (esr >> 10) & 0xf; + bool valid; + + params->is_write = ((esr & 1) == 0); + params->Op0 = 3; + params->Op1 = 0; + params->CRn = 0; + params->CRm = 3; + + /* CP10 ID registers are read-only */ + valid = !params->is_write; + + switch (reg_id) { + /* MVFR0 */ + case 0b0111: + params->Op2 = 0; + break; + /* MVFR1 */ + case 0b0110: + params->Op2 = 1; + break; + /* MVFR2 */ + case 0b0101: + params->Op2 = 2; + break; + default: + valid = false; + } + + if (valid) + return true; + + kvm_pr_unimpl("Unhandled cp10 register %s: %u\n", + params->is_write ? "write" : "read", reg_id); + return false; +} + +/** + * kvm_handle_cp10_id() - Handles a VMRS trap on guest access to a 'Media and + * VFP Register' from AArch32. + * @vcpu: The vCPU pointer + * + * MVFR{0-2} are architecturally mapped to the AArch64 MVFR{0-2}_EL1 registers. + * Work out the correct AArch64 system register encoding and reroute to the + * AArch64 system register emulation. + */ +int kvm_handle_cp10_id(struct kvm_vcpu *vcpu) +{ + int Rt = kvm_vcpu_sys_get_rt(vcpu); + u64 esr = kvm_vcpu_get_esr(vcpu); + struct sys_reg_params params; + + /* UNDEF on any unhandled register access */ + if (!kvm_esr_cp10_id_to_sys64(esr, ¶ms)) { + kvm_inject_undefined(vcpu); + return 1; + } + + if (emulate_sys_reg(vcpu, ¶ms)) + vcpu_set_reg(vcpu, Rt, params.regval); + + return 1; +} + +/** + * kvm_emulate_cp15_id_reg() - Handles an MRC trap on a guest CP15 access where + * CRn=0, which corresponds to the AArch32 feature + * registers. + * @vcpu: the vCPU pointer + * @params: the system register access parameters. + * + * Our cp15 system register tables do not enumerate the AArch32 feature + * registers. Conveniently, our AArch64 table does, and the AArch32 system + * register encoding can be trivially remapped into the AArch64 for the feature + * registers: Append op0=3, leaving op1, CRn, CRm, and op2 the same. + * + * According to DDI0487G.b G7.3.1, paragraph "Behavior of VMSAv8-32 32-bit + * System registers with (coproc=0b1111, CRn==c0)", read accesses from this + * range are either UNKNOWN or RES0. Rerouting remains architectural as we + * treat undefined registers in this range as RAZ. + */ +static int kvm_emulate_cp15_id_reg(struct kvm_vcpu *vcpu, + struct sys_reg_params *params) +{ + int Rt = kvm_vcpu_sys_get_rt(vcpu); + + /* Treat impossible writes to RO registers as UNDEFINED */ + if (params->is_write) { + unhandled_cp_access(vcpu, params); + return 1; + } + + params->Op0 = 3; + + /* + * All registers where CRm > 3 are known to be UNKNOWN/RAZ from AArch32. + * Avoid conflicting with future expansion of AArch64 feature registers + * and simply treat them as RAZ here. + */ + if (params->CRm > 3) + params->regval = 0; + else if (!emulate_sys_reg(vcpu, params)) + return 1; + + vcpu_set_reg(vcpu, Rt, params->regval); + return 1; +} + /** * kvm_handle_cp_32 -- handles a mrc/mcr trap on a guest CP14/CP15 access * @vcpu: The VCPU pointer * @run: The kvm_run struct */ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu, + struct sys_reg_params *params, const struct sys_reg_desc *global, size_t nr_global) { - struct sys_reg_params params; - u32 esr = kvm_vcpu_get_esr(vcpu); int Rt = kvm_vcpu_sys_get_rt(vcpu); - params.CRm = (esr >> 1) & 0xf; - params.regval = vcpu_get_reg(vcpu, Rt); - params.is_write = ((esr & 1) == 0); - params.CRn = (esr >> 10) & 0xf; - params.Op0 = 0; - params.Op1 = (esr >> 14) & 0x7; - params.Op2 = (esr >> 17) & 0x7; + params->regval = vcpu_get_reg(vcpu, Rt); - if (!emulate_cp(vcpu, ¶ms, global, nr_global)) { - if (!params.is_write) - vcpu_set_reg(vcpu, Rt, params.regval); + if (emulate_cp(vcpu, params, global, nr_global)) { + if (!params->is_write) + vcpu_set_reg(vcpu, Rt, params->regval); return 1; } - unhandled_cp_access(vcpu, ¶ms); + unhandled_cp_access(vcpu, params); return 1; } @@ -2382,7 +2503,20 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu) int kvm_handle_cp15_32(struct kvm_vcpu *vcpu) { - return kvm_handle_cp_32(vcpu, cp15_regs, ARRAY_SIZE(cp15_regs)); + struct sys_reg_params params; + + params = esr_cp1x_32_to_params(kvm_vcpu_get_esr(vcpu)); + + /* + * Certain AArch32 ID registers are handled by rerouting to the AArch64 + * system register table. Registers in the ID range where CRm=0 are + * excluded from this scheme as they do not trivially map into AArch64 + * system register encodings. + */ + if (params.Op1 == 0 && params.CRn == 0 && params.CRm) + return kvm_emulate_cp15_id_reg(vcpu, ¶ms); + + return kvm_handle_cp_32(vcpu, ¶ms, cp15_regs, ARRAY_SIZE(cp15_regs)); } int kvm_handle_cp14_64(struct kvm_vcpu *vcpu) @@ -2392,7 +2526,11 @@ int kvm_handle_cp14_64(struct kvm_vcpu *vcpu) int kvm_handle_cp14_32(struct kvm_vcpu *vcpu) { - return kvm_handle_cp_32(vcpu, cp14_regs, ARRAY_SIZE(cp14_regs)); + struct sys_reg_params params; + + params = esr_cp1x_32_to_params(kvm_vcpu_get_esr(vcpu)); + + return kvm_handle_cp_32(vcpu, ¶ms, cp14_regs, ARRAY_SIZE(cp14_regs)); } static bool is_imp_def_sys_reg(struct sys_reg_params *params) @@ -2401,7 +2539,14 @@ static bool is_imp_def_sys_reg(struct sys_reg_params *params) return params->Op0 == 3 && (params->CRn & 0b1011) == 0b1011; } -static int emulate_sys_reg(struct kvm_vcpu *vcpu, +/** + * emulate_sys_reg - Emulate a guest access to an AArch64 system register + * @vcpu: The VCPU pointer + * @params: Decoded system register parameters + * + * Return: true if the system register access was successful, false otherwise. + */ +static bool emulate_sys_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *params) { const struct sys_reg_desc *r; @@ -2410,7 +2555,10 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu, if (likely(r)) { perform_access(vcpu, params, r); - } else if (is_imp_def_sys_reg(params)) { + return true; + } + + if (is_imp_def_sys_reg(params)) { kvm_inject_undefined(vcpu); } else { print_sys_reg_msg(params, @@ -2418,7 +2566,7 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu, *vcpu_pc(vcpu), *vcpu_cpsr(vcpu)); kvm_inject_undefined(vcpu); } - return 1; + return false; } /** @@ -2446,18 +2594,18 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu) struct sys_reg_params params; unsigned long esr = kvm_vcpu_get_esr(vcpu); int Rt = kvm_vcpu_sys_get_rt(vcpu); - int ret; trace_kvm_handle_sys_reg(esr); params = esr_sys64_to_params(esr); params.regval = vcpu_get_reg(vcpu, Rt); - ret = emulate_sys_reg(vcpu, ¶ms); + if (!emulate_sys_reg(vcpu, ¶ms)) + return 1; if (!params.is_write) vcpu_set_reg(vcpu, Rt, params.regval); - return ret; + return 1; } /****************************************************************************** diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h index cc0cc95a0280..aee8ea054f0d 100644 --- a/arch/arm64/kvm/sys_regs.h +++ b/arch/arm64/kvm/sys_regs.h @@ -35,12 +35,19 @@ struct sys_reg_params { .Op2 = ((esr) >> 17) & 0x7, \ .is_write = !((esr) & 1) }) +#define esr_cp1x_32_to_params(esr) \ + ((struct sys_reg_params){ .Op1 = ((esr) >> 14) & 0x7, \ + .CRn = ((esr) >> 10) & 0xf, \ + .CRm = ((esr) >> 1) & 0xf, \ + .Op2 = ((esr) >> 17) & 0x7, \ + .is_write = !((esr) & 1) }) + struct sys_reg_desc { /* Sysreg string for debug */ const char *name; enum { - AA32_ZEROHIGH, + AA32_DIRECT, AA32_LO, AA32_HI, } aarch32_map; diff --git a/arch/arm64/lib/delay.c b/arch/arm64/lib/delay.c index 1688af0a4c97..5b7890139bc2 100644 --- a/arch/arm64/lib/delay.c +++ b/arch/arm64/lib/delay.c @@ -27,7 +27,17 @@ void __delay(unsigned long cycles) { cycles_t start = get_cycles(); - if (arch_timer_evtstrm_available()) { + if (cpus_have_const_cap(ARM64_HAS_WFXT)) { + u64 end = start + cycles; + + /* + * Start with WFIT. If an interrupt makes us resume + * early, use a WFET loop to complete the delay. + */ + wfit(end); + while ((get_cycles() - start) < cycles) + wfet(end); + } else if (arch_timer_evtstrm_available()) { const cycles_t timer_evt_period = USECS_TO_CYCLES(ARCH_TIMER_EVT_STREAM_PERIOD_US); diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index 3ed418f70e3b..507b20373953 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -38,11 +38,14 @@ HAS_STAGE2_FWB HAS_SYSREG_GIC_CPUIF HAS_TLB_RANGE HAS_VIRT_HOST_EXTN +HAS_WFXT HW_DBM KVM_PROTECTED_MODE MISMATCHED_CACHE_TYPE MTE MTE_ASYMM +SME +SME_FA64 SPECTRE_V2 SPECTRE_V3A SPECTRE_V4 diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index 40a583e9d3c7..97a76a8619fb 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -101,7 +101,7 @@ __module_alloc(unsigned long size, unsigned long start, unsigned long end, bool * too. */ return __vmalloc_node_range(size, 1, start, end, gfp, prot, - VM_FLUSH_RESET_PERMS | VM_NO_HUGE_VMAP, + VM_FLUSH_RESET_PERMS, NUMA_NO_NODE, __builtin_return_address(0)); } diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index f5cbfe5efd25..f80cce0e3899 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -615,23 +615,22 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) return; } - /* Conditionally hard-enable interrupts. */ - if (should_hard_irq_enable()) { - /* - * Ensure a positive value is written to the decrementer, or - * else some CPUs will continue to take decrementer exceptions. - * When the PPC_WATCHDOG (decrementer based) is configured, - * keep this at most 31 bits, which is about 4 seconds on most - * systems, which gives the watchdog a chance of catching timer - * interrupt hard lockups. - */ - if (IS_ENABLED(CONFIG_PPC_WATCHDOG)) - set_dec(0x7fffffff); - else - set_dec(decrementer_max); + /* + * Ensure a positive value is written to the decrementer, or + * else some CPUs will continue to take decrementer exceptions. + * When the PPC_WATCHDOG (decrementer based) is configured, + * keep this at most 31 bits, which is about 4 seconds on most + * systems, which gives the watchdog a chance of catching timer + * interrupt hard lockups. + */ + if (IS_ENABLED(CONFIG_PPC_WATCHDOG)) + set_dec(0x7fffffff); + else + set_dec(decrementer_max); + /* Conditionally hard-enable interrupts. */ + if (should_hard_irq_enable()) do_hard_irq_enable(); - } #if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC) if (atomic_read(&ppc_n_lost_interrupts) != 0) diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index e4ce2a35483f..42851c32ff3b 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -168,9 +168,10 @@ int kvmppc_mmu_walk_radix_tree(struct kvm_vcpu *vcpu, gva_t eaddr, return -EINVAL; /* Read the entry from guest memory */ addr = base + (index * sizeof(rpte)); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + + kvm_vcpu_srcu_read_lock(vcpu); ret = kvm_read_guest(kvm, addr, &rpte, sizeof(rpte)); - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (ret) { if (pte_ret_p) *pte_ret_p = addr; @@ -246,9 +247,9 @@ int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr, /* Read the table to find the root of the radix tree */ ptbl = (table & PRTB_MASK) + (table_index * sizeof(entry)); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); ret = kvm_read_guest(kvm, ptbl, &entry, sizeof(entry)); - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (ret) return ret; diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index d42b4b6d4a79..85cfa6328222 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -420,13 +420,19 @@ static void kvmppc_tce_put(struct kvmppc_spapr_tce_table *stt, tbl[idx % TCES_PER_PAGE] = tce; } -static void kvmppc_clear_tce(struct mm_struct *mm, struct iommu_table *tbl, - unsigned long entry) +static void kvmppc_clear_tce(struct mm_struct *mm, struct kvmppc_spapr_tce_table *stt, + struct iommu_table *tbl, unsigned long entry) { - unsigned long hpa = 0; - enum dma_data_direction dir = DMA_NONE; + unsigned long i; + unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift); + unsigned long io_entry = entry << (stt->page_shift - tbl->it_page_shift); + + for (i = 0; i < subpages; ++i) { + unsigned long hpa = 0; + enum dma_data_direction dir = DMA_NONE; - iommu_tce_xchg_no_kill(mm, tbl, entry, &hpa, &dir); + iommu_tce_xchg_no_kill(mm, tbl, io_entry + i, &hpa, &dir); + } } static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm, @@ -485,6 +491,8 @@ static long kvmppc_tce_iommu_unmap(struct kvm *kvm, break; } + iommu_tce_kill(tbl, io_entry, subpages); + return ret; } @@ -544,6 +552,8 @@ static long kvmppc_tce_iommu_map(struct kvm *kvm, break; } + iommu_tce_kill(tbl, io_entry, subpages); + return ret; } @@ -590,10 +600,9 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, ret = kvmppc_tce_iommu_map(vcpu->kvm, stt, stit->tbl, entry, ua, dir); - iommu_tce_kill(stit->tbl, entry, 1); if (ret != H_SUCCESS) { - kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, entry); + kvmppc_clear_tce(vcpu->kvm->mm, stt, stit->tbl, entry); goto unlock_exit; } } @@ -669,13 +678,13 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu, */ if (get_user(tce, tces + i)) { ret = H_TOO_HARD; - goto invalidate_exit; + goto unlock_exit; } tce = be64_to_cpu(tce); if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua)) { ret = H_PARAMETER; - goto invalidate_exit; + goto unlock_exit; } list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { @@ -684,19 +693,15 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu, iommu_tce_direction(tce)); if (ret != H_SUCCESS) { - kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, - entry); - goto invalidate_exit; + kvmppc_clear_tce(vcpu->kvm->mm, stt, stit->tbl, + entry + i); + goto unlock_exit; } } kvmppc_tce_put(stt, entry + i, tce); } -invalidate_exit: - list_for_each_entry_lockless(stit, &stt->iommu_tables, next) - iommu_tce_kill(stit->tbl, entry, npages); - unlock_exit: srcu_read_unlock(&vcpu->kvm->srcu, idx); @@ -735,20 +740,16 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu, continue; if (ret == H_TOO_HARD) - goto invalidate_exit; + return ret; WARN_ON_ONCE(1); - kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, entry); + kvmppc_clear_tce(vcpu->kvm->mm, stt, stit->tbl, entry + i); } } for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift)) kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value); -invalidate_exit: - list_for_each_entry_lockless(stit, &stt->iommu_tables, next) - iommu_tce_kill(stit->tbl, ioba >> stt->page_shift, npages); - return ret; } EXPORT_SYMBOL_GPL(kvmppc_h_stuff_tce); diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index 870b7f0c7ea5..fdeda6a9cff4 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -247,13 +247,19 @@ static void iommu_tce_kill_rm(struct iommu_table *tbl, tbl->it_ops->tce_kill(tbl, entry, pages, true); } -static void kvmppc_rm_clear_tce(struct kvm *kvm, struct iommu_table *tbl, - unsigned long entry) +static void kvmppc_rm_clear_tce(struct kvm *kvm, struct kvmppc_spapr_tce_table *stt, + struct iommu_table *tbl, unsigned long entry) { - unsigned long hpa = 0; - enum dma_data_direction dir = DMA_NONE; + unsigned long i; + unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift); + unsigned long io_entry = entry << (stt->page_shift - tbl->it_page_shift); + + for (i = 0; i < subpages; ++i) { + unsigned long hpa = 0; + enum dma_data_direction dir = DMA_NONE; - iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir); + iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, io_entry + i, &hpa, &dir); + } } static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm, @@ -316,6 +322,8 @@ static long kvmppc_rm_tce_iommu_unmap(struct kvm *kvm, break; } + iommu_tce_kill_rm(tbl, io_entry, subpages); + return ret; } @@ -379,6 +387,8 @@ static long kvmppc_rm_tce_iommu_map(struct kvm *kvm, break; } + iommu_tce_kill_rm(tbl, io_entry, subpages); + return ret; } @@ -420,10 +430,8 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, stt, stit->tbl, entry, ua, dir); - iommu_tce_kill_rm(stit->tbl, entry, 1); - if (ret != H_SUCCESS) { - kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); + kvmppc_rm_clear_tce(vcpu->kvm, stt, stit->tbl, entry); return ret; } } @@ -561,7 +569,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, ua = 0; if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua)) { ret = H_PARAMETER; - goto invalidate_exit; + goto unlock_exit; } list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { @@ -570,19 +578,15 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, iommu_tce_direction(tce)); if (ret != H_SUCCESS) { - kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, - entry); - goto invalidate_exit; + kvmppc_rm_clear_tce(vcpu->kvm, stt, stit->tbl, + entry + i); + goto unlock_exit; } } kvmppc_rm_tce_put(stt, entry + i, tce); } -invalidate_exit: - list_for_each_entry_lockless(stit, &stt->iommu_tables, next) - iommu_tce_kill_rm(stit->tbl, entry, npages); - unlock_exit: if (!prereg) arch_spin_unlock(&kvm->mmu_lock.rlock.raw_lock); @@ -620,20 +624,16 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu, continue; if (ret == H_TOO_HARD) - goto invalidate_exit; + return ret; WARN_ON_ONCE_RM(1); - kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); + kvmppc_rm_clear_tce(vcpu->kvm, stt, stit->tbl, entry + i); } } for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift)) kvmppc_rm_tce_put(stt, ioba >> stt->page_shift, tce_value); -invalidate_exit: - list_for_each_entry_lockless(stit, &stt->iommu_tables, next) - iommu_tce_kill_rm(stit->tbl, ioba >> stt->page_shift, npages); - return ret; } diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 9d373f8963ee..c943a051c6e7 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -306,10 +306,10 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) /* copy parameters in */ hv_ptr = kvmppc_get_gpr(vcpu, 4); regs_ptr = kvmppc_get_gpr(vcpu, 5); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); err = kvmhv_read_guest_state_and_regs(vcpu, &l2_hv, &l2_regs, hv_ptr, regs_ptr); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (err) return H_PARAMETER; @@ -410,10 +410,10 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) byteswap_hv_regs(&l2_hv); byteswap_pt_regs(&l2_regs); } - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); err = kvmhv_write_guest_state_and_regs(vcpu, &l2_hv, &l2_regs, hv_ptr, regs_ptr); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (err) return H_AUTHORITY; @@ -600,16 +600,16 @@ long kvmhv_copy_tofrom_guest_nested(struct kvm_vcpu *vcpu) goto not_found; /* Write what was loaded into our buffer back to the L1 guest */ - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); rc = kvm_vcpu_write_guest(vcpu, gp_to, buf, n); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (rc) goto not_found; } else { /* Load the data to be stored from the L1 guest into our buf */ - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); rc = kvm_vcpu_read_guest(vcpu, gp_from, buf, n); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (rc) goto not_found; diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c index 0f847f1e5ddd..6808bda0dbc1 100644 --- a/arch/powerpc/kvm/book3s_rtas.c +++ b/arch/powerpc/kvm/book3s_rtas.c @@ -229,9 +229,9 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu) */ args_phys = kvmppc_get_gpr(vcpu, 4) & KVM_PAM; - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); rc = kvm_read_guest(vcpu->kvm, args_phys, &args, sizeof(args)); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (rc) goto fail; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 875c30c12db0..533c4232e5ab 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -425,9 +425,9 @@ int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, return EMULATE_DONE; } - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); rc = kvm_read_guest(vcpu->kvm, pte.raddr, ptr, size); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (rc) return EMULATE_DO_MMIO; diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile index 2f46e31c7612..4f53d0b97539 100644 --- a/arch/powerpc/perf/Makefile +++ b/arch/powerpc/perf/Makefile @@ -3,11 +3,11 @@ obj-y += callchain.o callchain_$(BITS).o perf_regs.o obj-$(CONFIG_COMPAT) += callchain_32.o -obj-$(CONFIG_PPC_PERF_CTRS) += core-book3s.o bhrb.o +obj-$(CONFIG_PPC_PERF_CTRS) += core-book3s.o obj64-$(CONFIG_PPC_PERF_CTRS) += ppc970-pmu.o power5-pmu.o \ power5+-pmu.o power6-pmu.o power7-pmu.o \ isa207-common.o power8-pmu.o power9-pmu.o \ - generic-compat-pmu.o power10-pmu.o + generic-compat-pmu.o power10-pmu.o bhrb.o obj32-$(CONFIG_PPC_PERF_CTRS) += mpc7450-pmu.o obj-$(CONFIG_PPC_POWERNV) += imc-pmu.o diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c index d3398100a60f..c6d51e7093cf 100644 --- a/arch/powerpc/perf/power10-pmu.c +++ b/arch/powerpc/perf/power10-pmu.c @@ -91,8 +91,8 @@ extern u64 PERF_REG_EXTENDED_MASK; /* Table of alternatives, sorted by column 0 */ static const unsigned int power10_event_alternatives[][MAX_ALT] = { - { PM_CYC_ALT, PM_CYC }, { PM_INST_CMPL_ALT, PM_INST_CMPL }, + { PM_CYC_ALT, PM_CYC }, }; static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[]) diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index c9eb5232e68b..c393e837648e 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -133,11 +133,11 @@ int p9_dd22_bl_ev[] = { /* Table of alternatives, sorted by column 0 */ static const unsigned int power9_event_alternatives[][MAX_ALT] = { - { PM_INST_DISP, PM_INST_DISP_ALT }, - { PM_RUN_CYC_ALT, PM_RUN_CYC }, - { PM_RUN_INST_CMPL_ALT, PM_RUN_INST_CMPL }, - { PM_LD_MISS_L1, PM_LD_MISS_L1_ALT }, { PM_BR_2PATH, PM_BR_2PATH_ALT }, + { PM_INST_DISP, PM_INST_DISP_ALT }, + { PM_RUN_CYC_ALT, PM_RUN_CYC }, + { PM_LD_MISS_L1, PM_LD_MISS_L1_ALT }, + { PM_RUN_INST_CMPL_ALT, PM_RUN_INST_CMPL }, }; static int power9_get_alternatives(u64 event, unsigned int flags, u64 alt[]) diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index 34592d00dde8..f6ef358d8a2c 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -38,7 +38,7 @@ config SOC_VIRT select SIFIVE_PLIC select PM_GENERIC_DOMAINS if PM select PM_GENERIC_DOMAINS_OF if PM && OF - select RISCV_SBI_CPUIDLE if CPU_IDLE + select RISCV_SBI_CPUIDLE if CPU_IDLE && RISCV_SBI help This enables support for QEMU Virt Machine. diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs-fabric.dtsi b/arch/riscv/boot/dts/microchip/microchip-mpfs-fabric.dtsi index 854320e17b28..ccaac3371cf9 100644 --- a/arch/riscv/boot/dts/microchip/microchip-mpfs-fabric.dtsi +++ b/arch/riscv/boot/dts/microchip/microchip-mpfs-fabric.dtsi @@ -7,7 +7,7 @@ reg = <0x0 0x41000000 0x0 0xF0>; microchip,sync-update-mask = /bits/ 32 <0>; #pwm-cells = <2>; - clocks = <&clkcfg CLK_FIC3>; + clocks = <&fabric_clk3>; status = "disabled"; }; @@ -16,10 +16,22 @@ reg = <0x0 0x44000000 0x0 0x1000>; #address-cells = <1>; #size-cells = <0>; - clocks = <&clkcfg CLK_FIC3>; + clocks = <&fabric_clk3>; interrupt-parent = <&plic>; interrupts = <122>; clock-frequency = <100000>; status = "disabled"; }; + + fabric_clk3: fabric-clk3 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <62500000>; + }; + + fabric_clk1: fabric-clk1 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <125000000>; + }; }; diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts index cd2fe80fa81a..3392153dd0f1 100644 --- a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts +++ b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts @@ -45,7 +45,7 @@ }; &refclk { - clock-frequency = <600000000>; + clock-frequency = <125000000>; }; &mmuart1 { diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi index c5c9d1360de0..746c4d4e7686 100644 --- a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi +++ b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi @@ -141,7 +141,7 @@ }; }; - refclk: msspllclk { + refclk: mssrefclk { compatible = "fixed-clock"; #clock-cells = <0>; }; @@ -190,7 +190,7 @@ clkcfg: clkcfg@20002000 { compatible = "microchip,mpfs-clkcfg"; - reg = <0x0 0x20002000 0x0 0x1000>; + reg = <0x0 0x20002000 0x0 0x1000>, <0x0 0x3E001000 0x0 0x1000>; clocks = <&refclk>; #clock-cells = <1>; }; @@ -393,8 +393,8 @@ reg = <0x0 0x20124000 0x0 0x1000>; interrupt-parent = <&plic>; interrupts = <80>, <81>; - clocks = <&clkcfg CLK_RTC>; - clock-names = "rtc"; + clocks = <&clkcfg CLK_RTC>, <&clkcfg CLK_RTCREF>; + clock-names = "rtc", "rtcref"; status = "disabled"; }; @@ -424,7 +424,7 @@ <0 0 0 3 &pcie_intc 2>, <0 0 0 4 &pcie_intc 3>; interrupt-map-mask = <0 0 0 7>; - clocks = <&clkcfg CLK_FIC0>, <&clkcfg CLK_FIC1>, <&clkcfg CLK_FIC3>; + clocks = <&fabric_clk1>, <&fabric_clk1>, <&fabric_clk3>; clock-names = "fic0", "fic1", "fic3"; ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>; msi-parent = <&pcie>; diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 30e3017f22bc..0cc17db8aaba 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -101,6 +101,7 @@ CONFIG_VIRTIO_BALLOON=y CONFIG_VIRTIO_INPUT=y CONFIG_VIRTIO_MMIO=y CONFIG_RPMSG_CHAR=y +CONFIG_RPMSG_CTRL=y CONFIG_RPMSG_VIRTIO=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig index 7e5efdc3829d..6cd9d84d3e13 100644 --- a/arch/riscv/configs/rv32_defconfig +++ b/arch/riscv/configs/rv32_defconfig @@ -93,6 +93,7 @@ CONFIG_VIRTIO_BALLOON=y CONFIG_VIRTIO_INPUT=y CONFIG_VIRTIO_MMIO=y CONFIG_RPMSG_CHAR=y +CONFIG_RPMSG_CTRL=y CONFIG_RPMSG_VIRTIO=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 78da839657e5..cd4bbcecb0fb 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -193,9 +193,6 @@ struct kvm_vcpu_arch { /* Don't run the VCPU (blocked) */ bool pause; - - /* SRCU lock index for in-kernel run loop */ - int srcu_idx; }; static inline void kvm_arch_hardware_unsetup(void) {} diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c index 0b552873a577..765004b60513 100644 --- a/arch/riscv/kernel/patch.c +++ b/arch/riscv/kernel/patch.c @@ -104,7 +104,7 @@ static int patch_text_cb(void *data) struct patch_insn *patch = data; int ret = 0; - if (atomic_inc_return(&patch->cpu_count) == 1) { + if (atomic_inc_return(&patch->cpu_count) == num_online_cpus()) { ret = patch_text_nosync(patch->addr, &patch->insn, GET_INSN_LENGTH(patch->insn)); diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 6785aef4cbd4..7461f964d20a 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -38,14 +38,16 @@ const struct kvm_stats_header kvm_vcpu_stats_header = { sizeof(kvm_vcpu_stats_desc), }; -#define KVM_RISCV_ISA_ALLOWED (riscv_isa_extension_mask(a) | \ - riscv_isa_extension_mask(c) | \ - riscv_isa_extension_mask(d) | \ - riscv_isa_extension_mask(f) | \ - riscv_isa_extension_mask(i) | \ - riscv_isa_extension_mask(m) | \ - riscv_isa_extension_mask(s) | \ - riscv_isa_extension_mask(u)) +#define KVM_RISCV_ISA_DISABLE_ALLOWED (riscv_isa_extension_mask(d) | \ + riscv_isa_extension_mask(f)) + +#define KVM_RISCV_ISA_DISABLE_NOT_ALLOWED (riscv_isa_extension_mask(a) | \ + riscv_isa_extension_mask(c) | \ + riscv_isa_extension_mask(i) | \ + riscv_isa_extension_mask(m)) + +#define KVM_RISCV_ISA_ALLOWED (KVM_RISCV_ISA_DISABLE_ALLOWED | \ + KVM_RISCV_ISA_DISABLE_NOT_ALLOWED) static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu) { @@ -219,7 +221,8 @@ static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu, switch (reg_num) { case KVM_REG_RISCV_CONFIG_REG(isa): if (!vcpu->arch.ran_atleast_once) { - vcpu->arch.isa = reg_val; + /* Ignore the disable request for these extensions */ + vcpu->arch.isa = reg_val | KVM_RISCV_ISA_DISABLE_NOT_ALLOWED; vcpu->arch.isa &= riscv_isa_extension_base(NULL); vcpu->arch.isa &= KVM_RISCV_ISA_ALLOWED; kvm_riscv_vcpu_fp_reset(vcpu); @@ -724,13 +727,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) /* Mark this VCPU ran at least once */ vcpu->arch.ran_atleast_once = true; - vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); /* Process MMIO value returned from user-space */ if (run->exit_reason == KVM_EXIT_MMIO) { ret = kvm_riscv_vcpu_mmio_return(vcpu, vcpu->run); if (ret) { - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); return ret; } } @@ -739,13 +742,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) if (run->exit_reason == KVM_EXIT_RISCV_SBI) { ret = kvm_riscv_vcpu_sbi_return(vcpu, vcpu->run); if (ret) { - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); return ret; } } if (run->immediate_exit) { - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); return -EINTR; } @@ -784,7 +787,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) */ vcpu->mode = IN_GUEST_MODE; - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); smp_mb__after_srcu_read_unlock(); /* @@ -802,7 +805,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; local_irq_enable(); preempt_enable(); - vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); continue; } @@ -846,7 +849,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) preempt_enable(); - vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); ret = kvm_riscv_vcpu_exit(vcpu, run, &trap); } @@ -855,7 +858,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) vcpu_put(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); return ret; } diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c index aa8af129e4bb..a72c15d4b42a 100644 --- a/arch/riscv/kvm/vcpu_exit.c +++ b/arch/riscv/kvm/vcpu_exit.c @@ -456,9 +456,9 @@ static int stage2_page_fault(struct kvm_vcpu *vcpu, struct kvm_run *run, void kvm_riscv_vcpu_wfi(struct kvm_vcpu *vcpu) { if (!kvm_arch_vcpu_runnable(vcpu)) { - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); kvm_vcpu_halt(vcpu); - vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); } } diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index a09ecb97b890..d45e7da3f0d3 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -83,7 +83,7 @@ void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run) void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu, struct kvm_run *run, - u32 type, u64 flags) + u32 type, u64 reason) { unsigned long i; struct kvm_vcpu *tmp; @@ -94,7 +94,8 @@ void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu, memset(&run->system_event, 0, sizeof(run->system_event)); run->system_event.type = type; - run->system_event.flags = flags; + run->system_event.ndata = 1; + run->system_event.data[0] = reason; run->exit_reason = KVM_EXIT_SYSTEM_EVENT; } diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 9535bea8688c..b0793dc0c291 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -718,6 +718,7 @@ retry: if (!check_l4) { disable_pgtable_l5(); check_l4 = true; + memset(early_pg_dir, 0, PAGE_SIZE); goto retry; } disable_pgtable_l4(); diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 9b30beac904d..af96dc0549a4 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1334,11 +1334,11 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) hrtimer_start(&vcpu->arch.ckc_timer, sltime, HRTIMER_MODE_REL); VCPU_EVENT(vcpu, 4, "enabled wait: %llu ns", sltime); no_timer: - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); kvm_vcpu_halt(vcpu); vcpu->valid_wakeup = false; __unset_cpu_idle(vcpu); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); hrtimer_cancel(&vcpu->arch.ckc_timer); return 0; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 156d1c25a3c1..da3dabda1a12 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4237,14 +4237,14 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) * We try to hold kvm->srcu during most of vcpu_run (except when run- * ning the guest), so that memslots (and other stuff) are protected */ - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); do { rc = vcpu_pre_run(vcpu); if (rc) break; - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); /* * As PF_VCPU will be used in fault handler, between * guest_enter and guest_exit should be no uaccess. @@ -4281,12 +4281,12 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) __enable_cpu_timer_accounting(vcpu); guest_exit_irqoff(); local_irq_enable(); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); rc = vcpu_post_run(vcpu, exit_reason); } while (!signal_pending(current) && !guestdbg_exit_pending(vcpu) && !rc); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); return rc; } diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index 7f7c0d6af2ce..cc7c9599f43e 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -137,12 +137,7 @@ static int kvm_s390_pv_alloc_vm(struct kvm *kvm) /* Allocate variable storage */ vlen = ALIGN(virt * ((npages * PAGE_SIZE) / HPAGE_SIZE), PAGE_SIZE); vlen += uv_info.guest_virt_base_stor_len; - /* - * The Create Secure Configuration Ultravisor Call does not support - * using large pages for the virtual memory area. - * This is a hardware limitation. - */ - kvm->arch.pv.stor_var = vmalloc_no_huge(vlen); + kvm->arch.pv.stor_var = vzalloc(vlen); if (!kvm->arch.pv.stor_var) goto out_err; return 0; diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index acda4b6fc851..dada78b92691 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -1091,7 +1091,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) handle_last_fault(vcpu, vsie_page); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); /* save current guest state of bp isolation override */ guest_bp_isolation = test_thread_flag(TIF_ISOLATE_BP_GUEST); @@ -1133,7 +1133,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) if (!guest_bp_isolation) clear_thread_flag(TIF_ISOLATE_BP_GUEST); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); if (rc == -EINTR) { VCPU_EVENT(vcpu, 3, "%s", "machine check"); diff --git a/arch/sparc/include/asm/cacheflush_32.h b/arch/sparc/include/asm/cacheflush_32.h index 41c6d734a474..adb6991d0455 100644 --- a/arch/sparc/include/asm/cacheflush_32.h +++ b/arch/sparc/include/asm/cacheflush_32.h @@ -35,6 +35,7 @@ #define flush_page_for_dma(addr) \ sparc32_cachetlb_ops->page_for_dma(addr) +struct page; void sparc_flush_page_to_ram(struct page *page); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index b0142e01002e..4bed3abf444d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1866,7 +1866,7 @@ config X86_KERNEL_IBT code with them to make this happen. In addition to building the kernel with IBT, seal all functions that - are not indirect call targets, avoiding them ever becomming one. + are not indirect call targets, avoiding them ever becoming one. This requires LTO like objtool runs and will slow down the build. It does significantly reduce the number of ENDBR instructions in the diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 4faac48ebec5..73d958522b6a 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -337,6 +337,9 @@ SYM_CODE_END(ret_from_fork) call \cfunc + /* For some configurations \cfunc ends up being a noreturn. */ + REACHABLE + jmp error_return .endm diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 5d7762288a24..48e5db21142c 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -51,7 +51,7 @@ * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL,RPL + * TGL,TNT,RKL,ADL,RPL,SPR * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 @@ -62,7 +62,7 @@ * perf code: 0x00 * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL, * KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL, - * RPL + * RPL,SPR * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01 @@ -74,7 +74,7 @@ * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL,RPL + * TGL,TNT,RKL,ADL,RPL,SPR * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 @@ -675,6 +675,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &icx_cstates), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &icx_cstates), + X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &icx_cstates), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &icl_cstates), diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 048b6d5aff50..def6ca121111 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -26,6 +26,7 @@ * _G - parts with extra graphics on * _X - regular server parts * _D - micro server parts + * _N,_P - other mobile parts * * Historical OPTDIFFs: * @@ -107,8 +108,10 @@ #define INTEL_FAM6_ALDERLAKE 0x97 /* Golden Cove / Gracemont */ #define INTEL_FAM6_ALDERLAKE_L 0x9A /* Golden Cove / Gracemont */ +#define INTEL_FAM6_ALDERLAKE_N 0xBE #define INTEL_FAM6_RAPTORLAKE 0xB7 +#define INTEL_FAM6_RAPTORLAKE_P 0xBA /* "Small Core" Processors (Atom) */ diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 3c368b639c04..1a6d7e3f6c32 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -118,6 +118,7 @@ KVM_X86_OP_OPTIONAL(mem_enc_register_region) KVM_X86_OP_OPTIONAL(mem_enc_unregister_region) KVM_X86_OP_OPTIONAL(vm_copy_enc_context_from) KVM_X86_OP_OPTIONAL(vm_move_enc_context_from) +KVM_X86_OP_OPTIONAL(guest_memory_reclaimed) KVM_X86_OP(get_msr_feature) KVM_X86_OP(can_emulate_instruction) KVM_X86_OP(apic_init_signal_blocked) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index e0c0f0e1f754..4ff36610af6a 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1484,6 +1484,7 @@ struct kvm_x86_ops { int (*mem_enc_unregister_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd); int (*vm_move_enc_context_from)(struct kvm *kvm, unsigned int source_fd); + void (*guest_memory_reclaimed)(struct kvm *kvm); int (*get_msr_feature)(struct kvm_msr_entry *entry); diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index d6bfdfb0f0af..0c3d3440fe27 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -131,10 +131,12 @@ extern void __init load_ucode_bsp(void); extern void load_ucode_ap(void); void reload_early_microcode(void); extern bool initrd_gone; +void microcode_bsp_resume(void); #else static inline void __init load_ucode_bsp(void) { } static inline void load_ucode_ap(void) { } static inline void reload_early_microcode(void) { } +static inline void microcode_bsp_resume(void) { } #endif #endif /* _ASM_X86_MICROCODE_H */ diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 40497a9020c6..407084d9fd99 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -559,10 +559,6 @@ static inline void update_page_count(int level, unsigned long pages) { } extern pte_t *lookup_address(unsigned long address, unsigned int *level); extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, unsigned int *level); - -struct mm_struct; -extern pte_t *lookup_address_in_mm(struct mm_struct *mm, unsigned long address, - unsigned int *level); extern pmd_t *lookup_pmd_address(unsigned long address); extern phys_addr_t slow_virt_to_phys(void *__address); extern int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index 2455d721503e..2d8dacd02643 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -26,6 +26,7 @@ ".align 4 \n" \ ".globl " STATIC_CALL_TRAMP_STR(name) " \n" \ STATIC_CALL_TRAMP_STR(name) ": \n" \ + ANNOTATE_NOENDBR \ insns " \n" \ ".byte 0x53, 0x43, 0x54 \n" \ ".type " STATIC_CALL_TRAMP_STR(name) ", @function \n" \ diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index f955d25076ba..239ff5fcec6a 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -758,9 +758,9 @@ static struct subsys_interface mc_cpu_interface = { }; /** - * mc_bp_resume - Update boot CPU microcode during resume. + * microcode_bsp_resume - Update boot CPU microcode during resume. */ -static void mc_bp_resume(void) +void microcode_bsp_resume(void) { int cpu = smp_processor_id(); struct ucode_cpu_info *uci = ucode_cpu_info + cpu; @@ -772,7 +772,7 @@ static void mc_bp_resume(void) } static struct syscore_ops mc_syscore_ops = { - .resume = mc_bp_resume, + .resume = microcode_bsp_resume, }; static int mc_cpu_starting(unsigned int cpu) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index a22deb58f86d..8b1c45c9cda8 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -69,6 +69,7 @@ static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __align DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64) __visible; static int has_steal_clock = 0; +static int has_guest_poll = 0; /* * No need for any "IO delay" on KVM */ @@ -706,14 +707,26 @@ static int kvm_cpu_down_prepare(unsigned int cpu) static int kvm_suspend(void) { + u64 val = 0; + kvm_guest_cpu_offline(false); +#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL + if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL)) + rdmsrl(MSR_KVM_POLL_CONTROL, val); + has_guest_poll = !(val & 1); +#endif return 0; } static void kvm_resume(void) { kvm_cpu_online(raw_smp_processor_id()); + +#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL + if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL) && has_guest_poll) + wrmsrl(MSR_KVM_POLL_CONTROL, 0); +#endif } static struct syscore_ops kvm_syscore_ops = { diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 794fdef2501a..38185aedf7d1 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -339,11 +339,11 @@ static bool stack_access_ok(struct unwind_state *state, unsigned long _addr, struct stack_info *info = &state->stack_info; void *addr = (void *)_addr; - if (!on_stack(info, addr, len) && - (get_stack_info(addr, state->task, info, &state->stack_mask))) - return false; + if (on_stack(info, addr, len)) + return true; - return true; + return !get_stack_info(addr, state->task, info, &state->stack_mask) && + on_stack(info, addr, len); } static bool deref_stack_reg(struct unwind_state *state, unsigned long addr, diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index b24ca7f4ed7c..598334ed5fbc 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -1085,12 +1085,21 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) case 0x80000000: entry->eax = min(entry->eax, 0x80000021); /* - * Serializing LFENCE is reported in a multitude of ways, - * and NullSegClearsBase is not reported in CPUID on Zen2; - * help userspace by providing the CPUID leaf ourselves. + * Serializing LFENCE is reported in a multitude of ways, and + * NullSegClearsBase is not reported in CPUID on Zen2; help + * userspace by providing the CPUID leaf ourselves. + * + * However, only do it if the host has CPUID leaf 0x8000001d. + * QEMU thinks that it can query the host blindly for that + * CPUID leaf if KVM reports that it supports 0x8000001d or + * above. The processor merrily returns values from the + * highest Intel leaf which QEMU tries to use as the guest's + * 0x8000001d. Even worse, this can result in an infinite + * loop if said highest leaf has no subleaves indexed by ECX. */ - if (static_cpu_has(X86_FEATURE_LFENCE_RDTSC) - || !static_cpu_has_bug(X86_BUG_NULL_SEG)) + if (entry->eax >= 0x8000001d && + (static_cpu_has(X86_FEATURE_LFENCE_RDTSC) + || !static_cpu_has_bug(X86_BUG_NULL_SEG))) entry->eax = max(entry->eax, 0x80000021); break; case 0x80000001: diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index e6cae6f22683..a335e7f1f69e 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -65,6 +65,30 @@ static __always_inline u64 rsvd_bits(int s, int e) return ((2ULL << (e - s)) - 1) << s; } +/* + * The number of non-reserved physical address bits irrespective of features + * that repurpose legal bits, e.g. MKTME. + */ +extern u8 __read_mostly shadow_phys_bits; + +static inline gfn_t kvm_mmu_max_gfn(void) +{ + /* + * Note that this uses the host MAXPHYADDR, not the guest's. + * EPT/NPT cannot support GPAs that would exceed host.MAXPHYADDR; + * assuming KVM is running on bare metal, guest accesses beyond + * host.MAXPHYADDR will hit a #PF(RSVD) and never cause a vmexit + * (either EPT Violation/Misconfig or #NPF), and so KVM will never + * install a SPTE for such addresses. If KVM is running as a VM + * itself, on the other hand, it might see a MAXPHYADDR that is less + * than hardware's real MAXPHYADDR. Using the host MAXPHYADDR + * disallows such SPTEs entirely and simplifies the TDP MMU. + */ + int max_gpa_bits = likely(tdp_enabled) ? shadow_phys_bits : 52; + + return (1ULL << (max_gpa_bits - PAGE_SHIFT)) - 1; +} + void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask); void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index f9080ee50ffa..64a2a7e2be90 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2804,8 +2804,12 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, const struct kvm_memory_slot *slot) { unsigned long hva; - pte_t *pte; - int level; + unsigned long flags; + int level = PG_LEVEL_4K; + pgd_t pgd; + p4d_t p4d; + pud_t pud; + pmd_t pmd; if (!PageCompound(pfn_to_page(pfn)) && !kvm_is_zone_device_pfn(pfn)) return PG_LEVEL_4K; @@ -2820,10 +2824,43 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, */ hva = __gfn_to_hva_memslot(slot, gfn); - pte = lookup_address_in_mm(kvm->mm, hva, &level); - if (unlikely(!pte)) - return PG_LEVEL_4K; + /* + * Lookup the mapping level in the current mm. The information + * may become stale soon, but it is safe to use as long as + * 1) mmu_notifier_retry was checked after taking mmu_lock, and + * 2) mmu_lock is taken now. + * + * We still need to disable IRQs to prevent concurrent tear down + * of page tables. + */ + local_irq_save(flags); + + pgd = READ_ONCE(*pgd_offset(kvm->mm, hva)); + if (pgd_none(pgd)) + goto out; + + p4d = READ_ONCE(*p4d_offset(&pgd, hva)); + if (p4d_none(p4d) || !p4d_present(p4d)) + goto out; + pud = READ_ONCE(*pud_offset(&p4d, hva)); + if (pud_none(pud) || !pud_present(pud)) + goto out; + + if (pud_large(pud)) { + level = PG_LEVEL_1G; + goto out; + } + + pmd = READ_ONCE(*pmd_offset(&pud, hva)); + if (pmd_none(pmd) || !pmd_present(pmd)) + goto out; + + if (pmd_large(pmd)) + level = PG_LEVEL_2M; + +out: + local_irq_restore(flags); return level; } @@ -2992,9 +3029,15 @@ static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fa /* * If MMIO caching is disabled, emulate immediately without * touching the shadow page tables as attempting to install an - * MMIO SPTE will just be an expensive nop. + * MMIO SPTE will just be an expensive nop. Do not cache MMIO + * whose gfn is greater than host.MAXPHYADDR, any guest that + * generates such gfns is running nested and is being tricked + * by L0 userspace (you can observe gfn > L1.MAXPHYADDR if + * and only if L1's MAXPHYADDR is inaccurate with respect to + * the hardware's). */ - if (unlikely(!shadow_mmio_value)) { + if (unlikely(!shadow_mmio_value) || + unlikely(fault->gfn > kvm_mmu_max_gfn())) { *ret_val = RET_PF_EMULATE; return true; } diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 73f12615416f..e4abeb5df1b1 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -201,12 +201,6 @@ static inline bool is_removed_spte(u64 spte) */ extern u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; -/* - * The number of non-reserved physical address bits irrespective of features - * that repurpose legal bits, e.g. MKTME. - */ -extern u8 __read_mostly shadow_phys_bits; - static inline bool is_mmio_spte(u64 spte) { return (spte & shadow_mmio_mask) == shadow_mmio_value && diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index c472769e0300..edc68538819b 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -815,14 +815,15 @@ static inline bool __must_check tdp_mmu_iter_cond_resched(struct kvm *kvm, return iter->yielded; } -static inline gfn_t tdp_mmu_max_gfn_host(void) +static inline gfn_t tdp_mmu_max_gfn_exclusive(void) { /* - * Bound TDP MMU walks at host.MAXPHYADDR, guest accesses beyond that - * will hit a #PF(RSVD) and never hit an EPT Violation/Misconfig / #NPF, - * and so KVM will never install a SPTE for such addresses. + * Bound TDP MMU walks at host.MAXPHYADDR. KVM disallows memslots with + * a gpa range that would exceed the max gfn, and KVM does not create + * MMIO SPTEs for "impossible" gfns, instead sending such accesses down + * the slow emulation path every time. */ - return 1ULL << (shadow_phys_bits - PAGE_SHIFT); + return kvm_mmu_max_gfn() + 1; } static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, @@ -830,7 +831,7 @@ static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, { struct tdp_iter iter; - gfn_t end = tdp_mmu_max_gfn_host(); + gfn_t end = tdp_mmu_max_gfn_exclusive(); gfn_t start = 0; for_each_tdp_pte_min_level(iter, root, zap_level, start, end) { @@ -923,7 +924,7 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, { struct tdp_iter iter; - end = min(end, tdp_mmu_max_gfn_host()); + end = min(end, tdp_mmu_max_gfn_exclusive()); lockdep_assert_held_write(&kvm->mmu_lock); diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 9e66fba1d6a3..22992b049d38 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -138,6 +138,15 @@ static inline u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value) return sample_period; } +static inline void pmc_update_sample_period(struct kvm_pmc *pmc) +{ + if (!pmc->perf_event || pmc->is_paused) + return; + + perf_event_period(pmc->perf_event, + get_sample_period(pmc, pmc->counter)); +} + void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel); void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int fixed_idx); void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx); diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 24eb935b6f85..b14860863c39 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -257,6 +257,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER); if (pmc) { pmc->counter += data - pmc_read_counter(pmc); + pmc_update_sample_period(pmc); return 0; } /* MSR_EVNTSELn */ diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 537aaddc852f..0ad70c12c7c3 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2226,51 +2226,47 @@ int sev_cpu_init(struct svm_cpu_data *sd) * Pages used by hardware to hold guest encrypted state must be flushed before * returning them to the system. */ -static void sev_flush_guest_memory(struct vcpu_svm *svm, void *va, - unsigned long len) +static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va) { + int asid = to_kvm_svm(vcpu->kvm)->sev_info.asid; + /* - * If hardware enforced cache coherency for encrypted mappings of the - * same physical page is supported, nothing to do. + * Note! The address must be a kernel address, as regular page walk + * checks are performed by VM_PAGE_FLUSH, i.e. operating on a user + * address is non-deterministic and unsafe. This function deliberately + * takes a pointer to deter passing in a user address. */ - if (boot_cpu_has(X86_FEATURE_SME_COHERENT)) - return; + unsigned long addr = (unsigned long)va; /* - * If the VM Page Flush MSR is supported, use it to flush the page - * (using the page virtual address and the guest ASID). + * If CPU enforced cache coherency for encrypted mappings of the + * same physical page is supported, use CLFLUSHOPT instead. NOTE: cache + * flush is still needed in order to work properly with DMA devices. */ - if (boot_cpu_has(X86_FEATURE_VM_PAGE_FLUSH)) { - struct kvm_sev_info *sev; - unsigned long va_start; - u64 start, stop; - - /* Align start and stop to page boundaries. */ - va_start = (unsigned long)va; - start = (u64)va_start & PAGE_MASK; - stop = PAGE_ALIGN((u64)va_start + len); - - if (start < stop) { - sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info; + if (boot_cpu_has(X86_FEATURE_SME_COHERENT)) { + clflush_cache_range(va, PAGE_SIZE); + return; + } - while (start < stop) { - wrmsrl(MSR_AMD64_VM_PAGE_FLUSH, - start | sev->asid); + /* + * VM Page Flush takes a host virtual address and a guest ASID. Fall + * back to WBINVD if this faults so as not to make any problems worse + * by leaving stale encrypted data in the cache. + */ + if (WARN_ON_ONCE(wrmsrl_safe(MSR_AMD64_VM_PAGE_FLUSH, addr | asid))) + goto do_wbinvd; - start += PAGE_SIZE; - } + return; - return; - } +do_wbinvd: + wbinvd_on_all_cpus(); +} - WARN(1, "Address overflow, using WBINVD\n"); - } +void sev_guest_memory_reclaimed(struct kvm *kvm) +{ + if (!sev_guest(kvm)) + return; - /* - * Hardware should always have one of the above features, - * but if not, use WBINVD and issue a warning. - */ - WARN_ONCE(1, "Using WBINVD to flush guest memory\n"); wbinvd_on_all_cpus(); } @@ -2284,7 +2280,8 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu) svm = to_svm(vcpu); if (vcpu->arch.guest_state_protected) - sev_flush_guest_memory(svm, svm->sev_es.vmsa, PAGE_SIZE); + sev_flush_encrypted_page(vcpu, svm->sev_es.vmsa); + __free_page(virt_to_page(svm->sev_es.vmsa)); if (svm->sev_es.ghcb_sa_free) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index bd4c64b362d2..7e45d03cd018 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4620,6 +4620,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .mem_enc_ioctl = sev_mem_enc_ioctl, .mem_enc_register_region = sev_mem_enc_register_region, .mem_enc_unregister_region = sev_mem_enc_unregister_region, + .guest_memory_reclaimed = sev_guest_memory_reclaimed, .vm_copy_enc_context_from = sev_vm_copy_enc_context_from, .vm_move_enc_context_from = sev_vm_move_enc_context_from, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index f77a7d2d39dd..f76deff71002 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -609,6 +609,8 @@ int sev_mem_enc_unregister_region(struct kvm *kvm, struct kvm_enc_region *range); int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd); int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd); +void sev_guest_memory_reclaimed(struct kvm *kvm); + void pre_sev_run(struct vcpu_svm *svm, int cpu); void __init sev_set_cpu_caps(void); void __init sev_hardware_setup(void); diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index f18744f7ff82..856c87563883 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4618,6 +4618,11 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); } + if (vmx->nested.update_vmcs01_apicv_status) { + vmx->nested.update_vmcs01_apicv_status = false; + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); + } + if ((vm_exit_reason != -1) && (enable_shadow_vmcs || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))) vmx->nested.need_vmcs12_to_shadow_sync = true; diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index bc3f8512bb64..b82b6709d7a8 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -431,15 +431,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !(msr & MSR_PMC_FULL_WIDTH_BIT)) data = (s64)(s32)data; pmc->counter += data - pmc_read_counter(pmc); - if (pmc->perf_event && !pmc->is_paused) - perf_event_period(pmc->perf_event, - get_sample_period(pmc, data)); + pmc_update_sample_period(pmc); return 0; } else if ((pmc = get_fixed_pmc(pmu, msr))) { pmc->counter += data - pmc_read_counter(pmc); - if (pmc->perf_event && !pmc->is_paused) - perf_event_period(pmc->perf_event, - get_sample_period(pmc, data)); + pmc_update_sample_period(pmc); return 0; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { if (data == pmc->eventsel) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 04d170c4b61e..d58b763df855 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4174,6 +4174,11 @@ static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + if (is_guest_mode(vcpu)) { + vmx->nested.update_vmcs01_apicv_status = true; + return; + } + pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx)); if (cpu_has_secondary_exec_ctrls()) { if (kvm_vcpu_apicv_active(vcpu)) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 9c6bfcd84008..b98c7e96697a 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -183,6 +183,7 @@ struct nested_vmx { bool change_vmcs01_virtual_apic_mode; bool reload_vmcs01_apic_access_page; bool update_vmcs01_cpu_dirty_logging; + bool update_vmcs01_apicv_status; /* * Enlightened VMCS has been enabled. It does not mean that L1 has to diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 547ba00ef64f..4790f0d7d40b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9111,7 +9111,7 @@ static void kvm_apicv_init(struct kvm *kvm) if (!enable_apicv) set_or_clear_apicv_inhibit(inhibits, - APICV_INHIBIT_REASON_ABSENT, true); + APICV_INHIBIT_REASON_DISABLE, true); } static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id) @@ -9889,6 +9889,11 @@ void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); } +void kvm_arch_guest_memory_reclaimed(struct kvm *kvm) +{ + static_call_cond(kvm_x86_guest_memory_reclaimed)(kvm); +} + static void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) { if (!lapic_in_kernel(vcpu)) @@ -10015,12 +10020,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_HV_CRASH, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; vcpu->run->system_event.type = KVM_SYSTEM_EVENT_CRASH; + vcpu->run->system_event.ndata = 0; r = 0; goto out; } if (kvm_check_request(KVM_REQ_HV_RESET, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; vcpu->run->system_event.type = KVM_SYSTEM_EVENT_RESET; + vcpu->run->system_event.ndata = 0; r = 0; goto out; } @@ -10097,7 +10104,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) /* Store vcpu->apicv_active before vcpu->mode. */ smp_store_release(&vcpu->mode, IN_GUEST_MODE); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); /* * 1) We should set ->mode before checking ->requests. Please see @@ -10128,7 +10135,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) smp_wmb(); local_irq_enable(); preempt_enable(); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); r = 1; goto cancel_injection; } @@ -10254,7 +10261,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) local_irq_enable(); preempt_enable(); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); /* * Profile KVM exit RIPs: @@ -10284,7 +10291,7 @@ out: } /* Called within kvm->srcu read side. */ -static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) +static inline int vcpu_block(struct kvm_vcpu *vcpu) { bool hv_timer; @@ -10300,12 +10307,12 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) if (hv_timer) kvm_lapic_switch_to_sw_timer(vcpu); - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) kvm_vcpu_halt(vcpu); else kvm_vcpu_block(vcpu); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); if (hv_timer) kvm_lapic_switch_to_hv_timer(vcpu); @@ -10347,7 +10354,6 @@ static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) static int vcpu_run(struct kvm_vcpu *vcpu) { int r; - struct kvm *kvm = vcpu->kvm; vcpu->arch.l1tf_flush_l1d = true; @@ -10355,7 +10361,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu) if (kvm_vcpu_running(vcpu)) { r = vcpu_enter_guest(vcpu); } else { - r = vcpu_block(kvm, vcpu); + r = vcpu_block(vcpu); } if (r <= 0) @@ -10374,9 +10380,9 @@ static int vcpu_run(struct kvm_vcpu *vcpu) } if (__xfer_to_guest_mode_work_pending()) { - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); r = xfer_to_guest_mode_handle_work(vcpu); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); if (r) return r; } @@ -10387,12 +10393,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu) static inline int complete_emulated_io(struct kvm_vcpu *vcpu) { - int r; - - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); - r = kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - return r; + return kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE); } static int complete_emulated_pio(struct kvm_vcpu *vcpu) @@ -10484,7 +10485,6 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; - struct kvm *kvm = vcpu->kvm; int r; vcpu_load(vcpu); @@ -10492,7 +10492,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_run->flags = 0; kvm_load_guest_fpu(vcpu); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) { if (kvm_run->immediate_exit) { r = -EINTR; @@ -10504,9 +10504,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) */ WARN_ON_ONCE(kvm_lapic_hv_timer_in_use(vcpu)); - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); kvm_vcpu_block(vcpu); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); if (kvm_apic_accept_events(vcpu) < 0) { r = 0; @@ -10567,7 +10567,7 @@ out: if (kvm_run->kvm_valid_regs) store_regs(vcpu); post_kvm_run_save(vcpu); - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); kvm_sigset_deactivate(vcpu); vcpu_put(vcpu); @@ -10985,6 +10985,9 @@ static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm) struct kvm_vcpu *vcpu; unsigned long i; + if (!enable_apicv) + return; + down_write(&kvm->arch.apicv_update_lock); kvm_for_each_vcpu(i, vcpu, kvm) { @@ -11196,8 +11199,21 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) r = kvm_create_lapic(vcpu, lapic_timer_advance_ns); if (r < 0) goto fail_mmu_destroy; - if (kvm_apicv_activated(vcpu->kvm)) + + /* + * Defer evaluating inhibits until the vCPU is first run, as + * this vCPU will not get notified of any changes until this + * vCPU is visible to other vCPUs (marked online and added to + * the set of vCPUs). Opportunistically mark APICv active as + * VMX in particularly is highly unlikely to have inhibits. + * Ignore the current per-VM APICv state so that vCPU creation + * is guaranteed to run with a deterministic value, the request + * will ensure the vCPU gets the correct state before VM-Entry. + */ + if (enable_apicv) { vcpu->arch.apicv_active = true; + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); + } } else static_branch_inc(&kvm_has_noapic_vcpu); @@ -11995,8 +12011,12 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *new, enum kvm_mr_change change) { - if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) + if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) { + if ((new->base_gfn + new->npages - 1) > kvm_mmu_max_gfn()) + return -EINVAL; + return kvm_alloc_memslot_metadata(kvm, new); + } if (change == KVM_MR_FLAGS_ONLY) memcpy(&new->arch, &old->arch, sizeof(old->arch)); diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 8ca5ecf16dc4..9dec1b38a98f 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -53,12 +53,12 @@ SYM_FUNC_START(copy_user_generic_unrolled) ASM_STAC cmpl $8,%edx - jb 20f /* less then 8 bytes, go to byte copy loop */ + jb .Lcopy_user_short_string_bytes ALIGN_DESTINATION movl %edx,%ecx andl $63,%edx shrl $6,%ecx - jz .L_copy_short_string + jz copy_user_short_string 1: movq (%rsi),%r8 2: movq 1*8(%rsi),%r9 3: movq 2*8(%rsi),%r10 @@ -79,37 +79,11 @@ SYM_FUNC_START(copy_user_generic_unrolled) leaq 64(%rdi),%rdi decl %ecx jnz 1b -.L_copy_short_string: - movl %edx,%ecx - andl $7,%edx - shrl $3,%ecx - jz 20f -18: movq (%rsi),%r8 -19: movq %r8,(%rdi) - leaq 8(%rsi),%rsi - leaq 8(%rdi),%rdi - decl %ecx - jnz 18b -20: andl %edx,%edx - jz 23f - movl %edx,%ecx -21: movb (%rsi),%al -22: movb %al,(%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz 21b -23: xor %eax,%eax - ASM_CLAC - RET + jmp copy_user_short_string 30: shll $6,%ecx addl %ecx,%edx - jmp 60f -40: leal (%rdx,%rcx,8),%edx - jmp 60f -50: movl %ecx,%edx -60: jmp .Lcopy_user_handle_tail /* ecx is zerorest also */ + jmp .Lcopy_user_handle_tail _ASM_EXTABLE_CPY(1b, 30b) _ASM_EXTABLE_CPY(2b, 30b) @@ -127,10 +101,6 @@ SYM_FUNC_START(copy_user_generic_unrolled) _ASM_EXTABLE_CPY(14b, 30b) _ASM_EXTABLE_CPY(15b, 30b) _ASM_EXTABLE_CPY(16b, 30b) - _ASM_EXTABLE_CPY(18b, 40b) - _ASM_EXTABLE_CPY(19b, 40b) - _ASM_EXTABLE_CPY(21b, 50b) - _ASM_EXTABLE_CPY(22b, 50b) SYM_FUNC_END(copy_user_generic_unrolled) EXPORT_SYMBOL(copy_user_generic_unrolled) @@ -191,7 +161,7 @@ EXPORT_SYMBOL(copy_user_generic_string) SYM_FUNC_START(copy_user_enhanced_fast_string) ASM_STAC /* CPUs without FSRM should avoid rep movsb for short copies */ - ALTERNATIVE "cmpl $64, %edx; jb .L_copy_short_string", "", X86_FEATURE_FSRM + ALTERNATIVE "cmpl $64, %edx; jb copy_user_short_string", "", X86_FEATURE_FSRM movl %edx,%ecx 1: rep movsb xorl %eax,%eax @@ -244,6 +214,53 @@ SYM_CODE_START_LOCAL(.Lcopy_user_handle_tail) SYM_CODE_END(.Lcopy_user_handle_tail) /* + * Finish memcpy of less than 64 bytes. #AC should already be set. + * + * Input: + * rdi destination + * rsi source + * rdx count (< 64) + * + * Output: + * eax uncopied bytes or 0 if successful. + */ +SYM_CODE_START_LOCAL(copy_user_short_string) + movl %edx,%ecx + andl $7,%edx + shrl $3,%ecx + jz .Lcopy_user_short_string_bytes +18: movq (%rsi),%r8 +19: movq %r8,(%rdi) + leaq 8(%rsi),%rsi + leaq 8(%rdi),%rdi + decl %ecx + jnz 18b +.Lcopy_user_short_string_bytes: + andl %edx,%edx + jz 23f + movl %edx,%ecx +21: movb (%rsi),%al +22: movb %al,(%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz 21b +23: xor %eax,%eax + ASM_CLAC + RET + +40: leal (%rdx,%rcx,8),%edx + jmp 60f +50: movl %ecx,%edx /* ecx is zerorest also */ +60: jmp .Lcopy_user_handle_tail + + _ASM_EXTABLE_CPY(18b, 40b) + _ASM_EXTABLE_CPY(19b, 40b) + _ASM_EXTABLE_CPY(21b, 50b) + _ASM_EXTABLE_CPY(22b, 50b) +SYM_CODE_END(copy_user_short_string) + +/* * copy_user_nocache - Uncached memory copy with exception handling * This will force destination out of cache for more performance. * diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S index ecb2049c1273..b7dfd60243b7 100644 --- a/arch/x86/lib/putuser.S +++ b/arch/x86/lib/putuser.S @@ -48,6 +48,7 @@ SYM_FUNC_START(__put_user_1) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user SYM_INNER_LABEL(__put_user_nocheck_1, SYM_L_GLOBAL) + ENDBR ASM_STAC 1: movb %al,(%_ASM_CX) xor %ecx,%ecx @@ -62,6 +63,7 @@ SYM_FUNC_START(__put_user_2) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user SYM_INNER_LABEL(__put_user_nocheck_2, SYM_L_GLOBAL) + ENDBR ASM_STAC 2: movw %ax,(%_ASM_CX) xor %ecx,%ecx @@ -76,6 +78,7 @@ SYM_FUNC_START(__put_user_4) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user SYM_INNER_LABEL(__put_user_nocheck_4, SYM_L_GLOBAL) + ENDBR ASM_STAC 3: movl %eax,(%_ASM_CX) xor %ecx,%ecx @@ -90,6 +93,7 @@ SYM_FUNC_START(__put_user_8) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user SYM_INNER_LABEL(__put_user_nocheck_8, SYM_L_GLOBAL) + ENDBR ASM_STAC 4: mov %_ASM_AX,(%_ASM_CX) #ifdef CONFIG_X86_32 diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 5f87bab4fb8d..b2b2366885a2 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -31,6 +31,7 @@ .align RETPOLINE_THUNK_SIZE SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL) UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \ __stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \ @@ -55,7 +56,6 @@ SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL) .align RETPOLINE_THUNK_SIZE SYM_CODE_START(__x86_indirect_thunk_array) - ANNOTATE_NOENDBR // apply_retpolines #define GEN(reg) THUNK reg #include <asm/GEN-for-each-reg.h> diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index 0402a749f3a0..0ae6cf804197 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -119,7 +119,7 @@ void __memcpy_flushcache(void *_dst, const void *_src, size_t size) /* cache copy and flush to align dest */ if (!IS_ALIGNED(dest, 8)) { - unsigned len = min_t(unsigned, size, ALIGN(dest, 8) - dest); + size_t len = min_t(size_t, size, ALIGN(dest, 8) - dest); memcpy((void *) dest, (void *) source, len); clean_cache_range((void *) dest, len); diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index abf5ed76e4b7..0656db33574d 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -638,17 +638,6 @@ pte_t *lookup_address(unsigned long address, unsigned int *level) } EXPORT_SYMBOL_GPL(lookup_address); -/* - * Lookup the page table entry for a virtual address in a given mm. Return a - * pointer to the entry and the level of the mapping. - */ -pte_t *lookup_address_in_mm(struct mm_struct *mm, unsigned long address, - unsigned int *level) -{ - return lookup_address_in_pgd(pgd_offset(mm, address), address, level); -} -EXPORT_SYMBOL_GPL(lookup_address_in_mm); - static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address, unsigned int *level) { diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 9bb1e2941179..b94f727251b6 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -467,7 +467,6 @@ static __init void xen_setup_pci_msi(void) else xen_msi_ops.setup_msi_irqs = xen_setup_msi_irqs; xen_msi_ops.teardown_msi_irqs = xen_pv_teardown_msi_irqs; - pci_msi_ignore_mask = 1; } else if (xen_hvm_domain()) { xen_msi_ops.setup_msi_irqs = xen_hvm_setup_msi_irqs; xen_msi_ops.teardown_msi_irqs = xen_teardown_msi_irqs; @@ -481,6 +480,11 @@ static __init void xen_setup_pci_msi(void) * in allocating the native domain and never use it. */ x86_init.irqs.create_pci_msi_domain = xen_create_pci_msi_domain; + /* + * With XEN PIRQ/Eventchannels in use PCI/MSI[-X] masking is solely + * controlled by the hypervisor. + */ + pci_msi_ignore_mask = 1; } #else /* CONFIG_PCI_MSI */ diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S index 72c1e42d121d..7fe564eaf228 100644 --- a/arch/x86/platform/pvh/head.S +++ b/arch/x86/platform/pvh/head.S @@ -50,6 +50,7 @@ #define PVH_DS_SEL (PVH_GDT_ENTRY_DS * 8) SYM_CODE_START_LOCAL(pvh_start_xen) + UNWIND_HINT_EMPTY cld lgdt (_pa(gdt)) diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 3822666fb73d..bb176c72891c 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -25,6 +25,7 @@ #include <asm/cpu.h> #include <asm/mmu_context.h> #include <asm/cpu_device_id.h> +#include <asm/microcode.h> #ifdef CONFIG_X86_32 __visible unsigned long saved_context_ebx; @@ -262,11 +263,18 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) x86_platform.restore_sched_clock_state(); mtrr_bp_restore(); perf_restore_debug_store(); - msr_restore_context(ctxt); c = &cpu_data(smp_processor_id()); if (cpu_has(c, X86_FEATURE_MSR_IA32_FEAT_CTL)) init_ia32_feat_ctl(c); + + microcode_bsp_resume(); + + /* + * This needs to happen after the microcode has been updated upon resume + * because some of the MSRs are "emulated" in microcode. + */ + msr_restore_context(ctxt); } /* Needed by apm.c */ diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index ac17196e2518..3a2cd93bf059 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -45,6 +45,7 @@ SYM_CODE_END(hypercall_page) __INIT SYM_CODE_START(startup_xen) UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR cld /* Clear .bss */ diff --git a/arch/xtensa/kernel/coprocessor.S b/arch/xtensa/kernel/coprocessor.S index 45cc0ae0af6f..c7b9f12896f2 100644 --- a/arch/xtensa/kernel/coprocessor.S +++ b/arch/xtensa/kernel/coprocessor.S @@ -29,7 +29,7 @@ .if XTENSA_HAVE_COPROCESSOR(x); \ .align 4; \ .Lsave_cp_regs_cp##x: \ - xchal_cp##x##_store a2 a4 a5 a6 a7; \ + xchal_cp##x##_store a2 a3 a4 a5 a6; \ jx a0; \ .endif @@ -46,7 +46,7 @@ .if XTENSA_HAVE_COPROCESSOR(x); \ .align 4; \ .Lload_cp_regs_cp##x: \ - xchal_cp##x##_load a2 a4 a5 a6 a7; \ + xchal_cp##x##_load a2 a3 a4 a5 a6; \ jx a0; \ .endif diff --git a/arch/xtensa/kernel/jump_label.c b/arch/xtensa/kernel/jump_label.c index 0dde21e0d3de..ad1841cecdfb 100644 --- a/arch/xtensa/kernel/jump_label.c +++ b/arch/xtensa/kernel/jump_label.c @@ -40,7 +40,7 @@ static int patch_text_stop_machine(void *data) { struct patch *patch = data; - if (atomic_inc_return(&patch->cpu_count) == 1) { + if (atomic_inc_return(&patch->cpu_count) == num_online_cpus()) { local_patch_text(patch->addr, patch->data, patch->sz); atomic_inc(&patch->cpu_count); } else { diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c index 81d7c7e8f7e9..10b79d3c74e0 100644 --- a/arch/xtensa/platforms/iss/console.c +++ b/arch/xtensa/platforms/iss/console.c @@ -36,24 +36,19 @@ static void rs_poll(struct timer_list *); static struct tty_driver *serial_driver; static struct tty_port serial_port; static DEFINE_TIMER(serial_timer, rs_poll); -static DEFINE_SPINLOCK(timer_lock); static int rs_open(struct tty_struct *tty, struct file * filp) { - spin_lock_bh(&timer_lock); if (tty->count == 1) mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE); - spin_unlock_bh(&timer_lock); return 0; } static void rs_close(struct tty_struct *tty, struct file * filp) { - spin_lock_bh(&timer_lock); if (tty->count == 1) del_timer_sync(&serial_timer); - spin_unlock_bh(&timer_lock); } @@ -73,8 +68,6 @@ static void rs_poll(struct timer_list *unused) int rd = 1; unsigned char c; - spin_lock(&timer_lock); - while (simc_poll(0)) { rd = simc_read(0, &c, 1); if (rd <= 0) @@ -87,7 +80,6 @@ static void rs_poll(struct timer_list *unused) tty_flip_buffer_push(port); if (rd) mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE); - spin_unlock(&timer_lock); } diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 2e0dd68a3cbe..1f62dbdc521f 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -569,7 +569,7 @@ static bool bfqq_request_over_limit(struct bfq_queue *bfqq, int limit) struct bfq_entity *entity = &bfqq->entity; struct bfq_entity *inline_entities[BFQ_LIMIT_INLINE_DEPTH]; struct bfq_entity **entities = inline_entities; - int depth, level; + int depth, level, alloc_depth = BFQ_LIMIT_INLINE_DEPTH; int class_idx = bfqq->ioprio_class - 1; struct bfq_sched_data *sched_data; unsigned long wsum; @@ -578,15 +578,21 @@ static bool bfqq_request_over_limit(struct bfq_queue *bfqq, int limit) if (!entity->on_st_or_in_serv) return false; +retry: + spin_lock_irq(&bfqd->lock); /* +1 for bfqq entity, root cgroup not included */ depth = bfqg_to_blkg(bfqq_group(bfqq))->blkcg->css.cgroup->level + 1; - if (depth > BFQ_LIMIT_INLINE_DEPTH) { + if (depth > alloc_depth) { + spin_unlock_irq(&bfqd->lock); + if (entities != inline_entities) + kfree(entities); entities = kmalloc_array(depth, sizeof(*entities), GFP_NOIO); if (!entities) return false; + alloc_depth = depth; + goto retry; } - spin_lock_irq(&bfqd->lock); sched_data = entity->sched_data; /* Gather our ancestors as we need to traverse them in reverse order */ level = 0; diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 70a0a3d680a3..9bd670999d0a 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -2322,7 +2322,17 @@ static void ioc_timer_fn(struct timer_list *timer) iocg->hweight_donating = hwa; iocg->hweight_after_donation = new_hwi; list_add(&iocg->surplus_list, &surpluses); - } else { + } else if (!iocg->abs_vdebt) { + /* + * @iocg doesn't have enough to donate. Reset + * its inuse to active. + * + * Don't reset debtors as their inuse's are + * owned by debt handling. This shouldn't affect + * donation calculuation in any meaningful way + * as @iocg doesn't have a meaningful amount of + * share anyway. + */ TRACE_IOCG_PATH(inuse_shortage, iocg, &now, iocg->inuse, iocg->active, iocg->hweight_inuse, new_hwi); diff --git a/block/blk-mq.c b/block/blk-mq.c index c4370d276170..84d749511f55 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1131,14 +1131,7 @@ void blk_mq_start_request(struct request *rq) trace_block_rq_issue(rq); if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) { - u64 start_time; -#ifdef CONFIG_BLK_CGROUP - if (rq->bio) - start_time = bio_issue_time(&rq->bio->bi_issue); - else -#endif - start_time = ktime_get_ns(); - rq->io_start_time_ns = start_time; + rq->io_start_time_ns = ktime_get_ns(); rq->stats_sectors = blk_rq_sectors(rq); rq->rq_flags |= RQF_STATS; rq_qos_issue(q, rq); diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 4556c86c3465..eb95e188d62b 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -96,11 +96,6 @@ static const struct dmi_system_id processor_power_dmi_table[] = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."), DMI_MATCH(DMI_PRODUCT_NAME,"L8400B series Notebook PC")}, (void *)1}, - /* T40 can not handle C3 idle state */ - { set_max_cstate, "IBM ThinkPad T40", { - DMI_MATCH(DMI_SYS_VENDOR, "IBM"), - DMI_MATCH(DMI_PRODUCT_NAME, "23737CU")}, - (void *)2}, {}, }; @@ -795,7 +790,8 @@ static int acpi_processor_setup_cstates(struct acpi_processor *pr) if (cx->type == ACPI_STATE_C1 || cx->type == ACPI_STATE_C2 || cx->type == ACPI_STATE_C3) { state->enter_dead = acpi_idle_play_dead; - drv->safe_state_index = count; + if (cx->type != ACPI_STATE_C3) + drv->safe_state_index = count; } /* * Halt-induced C1 is not good for ->enter_s2idle, because it diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 8351c5638880..f3b639e89dd8 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2295,6 +2295,7 @@ static int binder_do_deferred_txn_copies(struct binder_alloc *alloc, { int ret = 0; struct binder_sg_copy *sgc, *tmpsgc; + struct binder_ptr_fixup *tmppf; struct binder_ptr_fixup *pf = list_first_entry_or_null(pf_head, struct binder_ptr_fixup, node); @@ -2349,7 +2350,11 @@ static int binder_do_deferred_txn_copies(struct binder_alloc *alloc, list_del(&sgc->node); kfree(sgc); } - BUG_ON(!list_empty(pf_head)); + list_for_each_entry_safe(pf, tmppf, pf_head, node) { + BUG_ON(pf->skip_size == 0); + list_del(&pf->node); + kfree(pf); + } BUG_ON(!list_empty(sgc_head)); return ret > 0 ? -EINVAL : ret; @@ -2486,6 +2491,9 @@ static int binder_translate_fd_array(struct list_head *pf_head, struct binder_proc *proc = thread->proc; int ret; + if (fda->num_fds == 0) + return 0; + fd_buf_size = sizeof(u32) * fda->num_fds; if (fda->num_fds >= SIZE_MAX / sizeof(u32)) { binder_user_error("%d:%d got transaction with invalid number of fds (%lld)\n", diff --git a/drivers/ata/pata_marvell.c b/drivers/ata/pata_marvell.c index 0c5a51970fbf..014ccb0f45dc 100644 --- a/drivers/ata/pata_marvell.c +++ b/drivers/ata/pata_marvell.c @@ -77,6 +77,8 @@ static int marvell_cable_detect(struct ata_port *ap) switch(ap->port_no) { case 0: + if (!ap->ioaddr.bmdma_addr) + return ATA_CBL_PATA_UNK; if (ioread8(ap->ioaddr.bmdma_addr + 1) & 1) return ATA_CBL_PATA40; return ATA_CBL_PATA80; diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 1d6636ebaac5..f73b836047cf 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -667,6 +667,15 @@ const struct cpumask *cpu_coregroup_mask(int cpu) core_mask = &cpu_topology[cpu].llc_sibling; } + /* + * For systems with no shared cpu-side LLC but with clusters defined, + * extend core_mask to cluster_siblings. The sched domain builder will + * then remove MC as redundant with CLS if SCHED_CLUSTER is enabled. + */ + if (IS_ENABLED(CONFIG_SCHED_CLUSTER) && + cpumask_subset(core_mask, &cpu_topology[cpu].cluster_sibling)) + core_mask = &cpu_topology[cpu].cluster_sibling; + return core_mask; } @@ -684,7 +693,7 @@ void update_siblings_masks(unsigned int cpuid) for_each_online_cpu(cpu) { cpu_topo = &cpu_topology[cpu]; - if (cpuid_topo->llc_id == cpu_topo->llc_id) { + if (cpu_topo->llc_id != -1 && cpuid_topo->llc_id == cpu_topo->llc_id) { cpumask_set_cpu(cpu, &cpuid_topo->llc_sibling); cpumask_set_cpu(cpuid, &cpu_topo->llc_sibling); } diff --git a/drivers/base/topology.c b/drivers/base/topology.c index e9d1efcda89b..ac6ad9ab67f9 100644 --- a/drivers/base/topology.c +++ b/drivers/base/topology.c @@ -152,9 +152,19 @@ static struct attribute *default_attrs[] = { NULL }; +static umode_t topology_is_visible(struct kobject *kobj, + struct attribute *attr, int unused) +{ + if (attr == &dev_attr_ppin.attr && !topology_ppin(kobj_to_dev(kobj)->id)) + return 0; + + return attr->mode; +} + static const struct attribute_group topology_attr_group = { .attrs = default_attrs, .bin_attrs = bin_attrs, + .is_visible = topology_is_visible, .name = "topology" }; diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 519b6d38d4df..fdb81f2794cd 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -33,6 +33,22 @@ config BLK_DEV_FD To compile this driver as a module, choose M here: the module will be called floppy. +config BLK_DEV_FD_RAWCMD + bool "Support for raw floppy disk commands (DEPRECATED)" + depends on BLK_DEV_FD + help + If you want to use actual physical floppies and expect to do + special low-level hardware accesses to them (access and use + non-standard formats, for example), then enable this. + + Note that the code enabled by this option is rarely used and + might be unstable or insecure, and distros should not enable it. + + Note: FDRAWCMD is deprecated and will be removed from the kernel + in the near future. + + If unsure, say N. + config AMIGA_FLOPPY tristate "Amiga floppy support" depends on AMIGA diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 8c647532e3ce..d5b9ff9bcbb2 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -2982,6 +2982,8 @@ static const char *drive_name(int type, int drive) return "(null)"; } +#ifdef CONFIG_BLK_DEV_FD_RAWCMD + /* raw commands */ static void raw_cmd_done(int flag) { @@ -3181,6 +3183,35 @@ static int raw_cmd_ioctl(int cmd, void __user *param) return ret; } +static int floppy_raw_cmd_ioctl(int type, int drive, int cmd, + void __user *param) +{ + int ret; + + pr_warn_once("Note: FDRAWCMD is deprecated and will be removed from the kernel in the near future.\n"); + + if (type) + return -EINVAL; + if (lock_fdc(drive)) + return -EINTR; + set_floppy(drive); + ret = raw_cmd_ioctl(cmd, param); + if (ret == -EINTR) + return -EINTR; + process_fd_request(); + return ret; +} + +#else /* CONFIG_BLK_DEV_FD_RAWCMD */ + +static int floppy_raw_cmd_ioctl(int type, int drive, int cmd, + void __user *param) +{ + return -EOPNOTSUPP; +} + +#endif + static int invalidate_drive(struct block_device *bdev) { /* invalidate the buffer track to force a reread */ @@ -3369,7 +3400,6 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int { int drive = (long)bdev->bd_disk->private_data; int type = ITYPE(drive_state[drive].fd_device); - int i; int ret; int size; union inparam { @@ -3520,16 +3550,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int outparam = &write_errors[drive]; break; case FDRAWCMD: - if (type) - return -EINVAL; - if (lock_fdc(drive)) - return -EINTR; - set_floppy(drive); - i = raw_cmd_ioctl(cmd, (void __user *)param); - if (i == -EINTR) - return -EINTR; - process_fd_request(); - return i; + return floppy_raw_cmd_ioctl(type, drive, cmd, (void __user *)param); case FDTWADDLE: if (lock_fdc(drive)) return -EINTR; diff --git a/drivers/bus/fsl-mc/fsl-mc-msi.c b/drivers/bus/fsl-mc/fsl-mc-msi.c index 5e0e4393ce4d..0cfe859a4ac4 100644 --- a/drivers/bus/fsl-mc/fsl-mc-msi.c +++ b/drivers/bus/fsl-mc/fsl-mc-msi.c @@ -224,8 +224,12 @@ int fsl_mc_msi_domain_alloc_irqs(struct device *dev, unsigned int irq_count) if (error) return error; + msi_lock_descs(dev); if (msi_first_desc(dev, MSI_DESC_ALL)) - return -EINVAL; + error = -EINVAL; + msi_unlock_descs(dev); + if (error) + return error; /* * NOTE: Calling this function will trigger the invocation of the diff --git a/drivers/bus/imx-weim.c b/drivers/bus/imx-weim.c index 60fbd42041dd..828c66bbaa67 100644 --- a/drivers/bus/imx-weim.c +++ b/drivers/bus/imx-weim.c @@ -352,8 +352,7 @@ static int of_weim_notify(struct notifier_block *nb, unsigned long action, pdev = of_find_device_by_node(rd->dn); if (!pdev) { - dev_err(&pdev->dev, - "Could not find platform device for '%pOF'\n", + pr_err("Could not find platform device for '%pOF'\n", rd->dn); ret = notifier_from_errno(-EINVAL); @@ -370,7 +369,7 @@ static int of_weim_notify(struct notifier_block *nb, unsigned long action, return ret; } -struct notifier_block weim_of_notifier = { +static struct notifier_block weim_of_notifier = { .notifier_call = of_weim_notify, }; #endif /* IS_ENABLED(CONFIG_OF_DYNAMIC) */ diff --git a/drivers/bus/mhi/host/pci_generic.c b/drivers/bus/mhi/host/pci_generic.c index 9527b7d63840..541ced27d941 100644 --- a/drivers/bus/mhi/host/pci_generic.c +++ b/drivers/bus/mhi/host/pci_generic.c @@ -1060,6 +1060,7 @@ static int __maybe_unused mhi_pci_freeze(struct device *dev) * the intermediate restore kernel reinitializes MHI device with new * context. */ + flush_work(&mhi_pdev->recovery_work); if (test_and_clear_bit(MHI_PCI_DEV_STARTED, &mhi_pdev->status)) { mhi_power_down(mhi_cntrl, true); mhi_unprepare_after_power_down(mhi_cntrl); @@ -1085,6 +1086,7 @@ static const struct dev_pm_ops mhi_pci_pm_ops = { .resume = mhi_pci_resume, .freeze = mhi_pci_freeze, .thaw = mhi_pci_restore, + .poweroff = mhi_pci_freeze, .restore = mhi_pci_restore, #endif }; diff --git a/drivers/bus/sunxi-rsb.c b/drivers/bus/sunxi-rsb.c index 4566e730ef2b..60b082fe2ed0 100644 --- a/drivers/bus/sunxi-rsb.c +++ b/drivers/bus/sunxi-rsb.c @@ -227,6 +227,8 @@ static struct sunxi_rsb_device *sunxi_rsb_device_create(struct sunxi_rsb *rsb, dev_dbg(&rdev->dev, "device %s registered\n", dev_name(&rdev->dev)); + return rdev; + err_device_add: put_device(&rdev->dev); diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 54c0ee6dda30..7a1b1f9e4933 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -3232,13 +3232,27 @@ static int sysc_check_disabled_devices(struct sysc *ddata) */ static int sysc_check_active_timer(struct sysc *ddata) { + int error; + if (ddata->cap->type != TI_SYSC_OMAP2_TIMER && ddata->cap->type != TI_SYSC_OMAP4_TIMER) return 0; + /* + * Quirk for omap3 beagleboard revision A to B4 to use gpt12. + * Revision C and later are fixed with commit 23885389dbbb ("ARM: + * dts: Fix timer regression for beagleboard revision c"). This all + * can be dropped if we stop supporting old beagleboard revisions + * A to B4 at some point. + */ + if (sysc_soc->soc == SOC_3430) + error = -ENXIO; + else + error = -EBUSY; + if ((ddata->cfg.quirks & SYSC_QUIRK_NO_RESET_ON_INIT) && (ddata->cfg.quirks & SYSC_QUIRK_NO_IDLE)) - return -ENXIO; + return error; return 0; } diff --git a/drivers/char/random.c b/drivers/char/random.c index 3a293f919af9..4c9adb4f3d5d 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -318,6 +318,13 @@ static void crng_reseed(bool force) * the resultant ChaCha state to the user, along with the second * half of the block containing 32 bytes of random data that may * be used; random_data_len may not be greater than 32. + * + * The returned ChaCha state contains within it a copy of the old + * key value, at index 4, so the state should always be zeroed out + * immediately after using in order to maintain forward secrecy. + * If the state cannot be erased in a timely manner, then it is + * safer to set the random_data parameter to &chacha_state[4] so + * that this function overwrites it before returning. */ static void crng_fast_key_erasure(u8 key[CHACHA_KEY_SIZE], u32 chacha_state[CHACHA_STATE_WORDS], @@ -333,7 +340,7 @@ static void crng_fast_key_erasure(u8 key[CHACHA_KEY_SIZE], chacha20_block(chacha_state, first_block); memcpy(key, first_block, CHACHA_KEY_SIZE); - memmove(random_data, first_block + CHACHA_KEY_SIZE, random_data_len); + memcpy(random_data, first_block + CHACHA_KEY_SIZE, random_data_len); memzero_explicit(first_block, sizeof(first_block)); } diff --git a/drivers/clk/microchip/clk-mpfs.c b/drivers/clk/microchip/clk-mpfs.c index aa1561b773d6..070c3b896559 100644 --- a/drivers/clk/microchip/clk-mpfs.c +++ b/drivers/clk/microchip/clk-mpfs.c @@ -11,20 +11,48 @@ #include <dt-bindings/clock/microchip,mpfs-clock.h> /* address offset of control registers */ +#define REG_MSSPLL_REF_CR 0x08u +#define REG_MSSPLL_POSTDIV_CR 0x10u +#define REG_MSSPLL_SSCG_2_CR 0x2Cu #define REG_CLOCK_CONFIG_CR 0x08u +#define REG_RTC_CLOCK_CR 0x0Cu #define REG_SUBBLK_CLOCK_CR 0x84u #define REG_SUBBLK_RESET_CR 0x88u +#define MSSPLL_FBDIV_SHIFT 0x00u +#define MSSPLL_FBDIV_WIDTH 0x0Cu +#define MSSPLL_REFDIV_SHIFT 0x08u +#define MSSPLL_REFDIV_WIDTH 0x06u +#define MSSPLL_POSTDIV_SHIFT 0x08u +#define MSSPLL_POSTDIV_WIDTH 0x07u +#define MSSPLL_FIXED_DIV 4u + struct mpfs_clock_data { void __iomem *base; + void __iomem *msspll_base; struct clk_hw_onecell_data hw_data; }; +struct mpfs_msspll_hw_clock { + void __iomem *base; + unsigned int id; + u32 reg_offset; + u32 shift; + u32 width; + u32 flags; + struct clk_hw hw; + struct clk_init_data init; +}; + +#define to_mpfs_msspll_clk(_hw) container_of(_hw, struct mpfs_msspll_hw_clock, hw) + struct mpfs_cfg_clock { const struct clk_div_table *table; unsigned int id; + u32 reg_offset; u8 shift; u8 width; + u8 flags; }; struct mpfs_cfg_hw_clock { @@ -55,7 +83,7 @@ struct mpfs_periph_hw_clock { */ static DEFINE_SPINLOCK(mpfs_clk_lock); -static const struct clk_parent_data mpfs_cfg_parent[] = { +static const struct clk_parent_data mpfs_ext_ref[] = { { .index = 0 }, }; @@ -69,6 +97,86 @@ static const struct clk_div_table mpfs_div_ahb_table[] = { { 0, 0 } }; +/* + * The only two supported reference clock frequencies for the PolarFire SoC are + * 100 and 125 MHz, as the rtc reference is required to be 1 MHz. + * It therefore only needs to have divider table entries corresponding to + * divide by 100 and 125. + */ +static const struct clk_div_table mpfs_div_rtcref_table[] = { + { 100, 100 }, { 125, 125 }, + { 0, 0 } +}; + +static unsigned long mpfs_clk_msspll_recalc_rate(struct clk_hw *hw, unsigned long prate) +{ + struct mpfs_msspll_hw_clock *msspll_hw = to_mpfs_msspll_clk(hw); + void __iomem *mult_addr = msspll_hw->base + msspll_hw->reg_offset; + void __iomem *ref_div_addr = msspll_hw->base + REG_MSSPLL_REF_CR; + void __iomem *postdiv_addr = msspll_hw->base + REG_MSSPLL_POSTDIV_CR; + u32 mult, ref_div, postdiv; + + mult = readl_relaxed(mult_addr) >> MSSPLL_FBDIV_SHIFT; + mult &= clk_div_mask(MSSPLL_FBDIV_WIDTH); + ref_div = readl_relaxed(ref_div_addr) >> MSSPLL_REFDIV_SHIFT; + ref_div &= clk_div_mask(MSSPLL_REFDIV_WIDTH); + postdiv = readl_relaxed(postdiv_addr) >> MSSPLL_POSTDIV_SHIFT; + postdiv &= clk_div_mask(MSSPLL_POSTDIV_WIDTH); + + return prate * mult / (ref_div * MSSPLL_FIXED_DIV * postdiv); +} + +static const struct clk_ops mpfs_clk_msspll_ops = { + .recalc_rate = mpfs_clk_msspll_recalc_rate, +}; + +#define CLK_PLL(_id, _name, _parent, _shift, _width, _flags, _offset) { \ + .id = _id, \ + .shift = _shift, \ + .width = _width, \ + .reg_offset = _offset, \ + .flags = _flags, \ + .hw.init = CLK_HW_INIT_PARENTS_DATA(_name, _parent, &mpfs_clk_msspll_ops, 0), \ +} + +static struct mpfs_msspll_hw_clock mpfs_msspll_clks[] = { + CLK_PLL(CLK_MSSPLL, "clk_msspll", mpfs_ext_ref, MSSPLL_FBDIV_SHIFT, + MSSPLL_FBDIV_WIDTH, 0, REG_MSSPLL_SSCG_2_CR), +}; + +static int mpfs_clk_register_msspll(struct device *dev, struct mpfs_msspll_hw_clock *msspll_hw, + void __iomem *base) +{ + msspll_hw->base = base; + + return devm_clk_hw_register(dev, &msspll_hw->hw); +} + +static int mpfs_clk_register_mssplls(struct device *dev, struct mpfs_msspll_hw_clock *msspll_hws, + unsigned int num_clks, struct mpfs_clock_data *data) +{ + void __iomem *base = data->msspll_base; + unsigned int i; + int ret; + + for (i = 0; i < num_clks; i++) { + struct mpfs_msspll_hw_clock *msspll_hw = &msspll_hws[i]; + + ret = mpfs_clk_register_msspll(dev, msspll_hw, base); + if (ret) + return dev_err_probe(dev, ret, "failed to register msspll id: %d\n", + CLK_MSSPLL); + + data->hw_data.hws[msspll_hw->id] = &msspll_hw->hw; + } + + return 0; +} + +/* + * "CFG" clocks + */ + static unsigned long mpfs_cfg_clk_recalc_rate(struct clk_hw *hw, unsigned long prate) { struct mpfs_cfg_hw_clock *cfg_hw = to_mpfs_cfg_clk(hw); @@ -76,10 +184,10 @@ static unsigned long mpfs_cfg_clk_recalc_rate(struct clk_hw *hw, unsigned long p void __iomem *base_addr = cfg_hw->sys_base; u32 val; - val = readl_relaxed(base_addr + REG_CLOCK_CONFIG_CR) >> cfg->shift; + val = readl_relaxed(base_addr + cfg->reg_offset) >> cfg->shift; val &= clk_div_mask(cfg->width); - return prate / (1u << val); + return divider_recalc_rate(hw, prate, val, cfg->table, cfg->flags, cfg->width); } static long mpfs_cfg_clk_round_rate(struct clk_hw *hw, unsigned long rate, unsigned long *prate) @@ -105,11 +213,10 @@ static int mpfs_cfg_clk_set_rate(struct clk_hw *hw, unsigned long rate, unsigned return divider_setting; spin_lock_irqsave(&mpfs_clk_lock, flags); - - val = readl_relaxed(base_addr + REG_CLOCK_CONFIG_CR); + val = readl_relaxed(base_addr + cfg->reg_offset); val &= ~(clk_div_mask(cfg->width) << cfg_hw->cfg.shift); val |= divider_setting << cfg->shift; - writel_relaxed(val, base_addr + REG_CLOCK_CONFIG_CR); + writel_relaxed(val, base_addr + cfg->reg_offset); spin_unlock_irqrestore(&mpfs_clk_lock, flags); @@ -122,19 +229,33 @@ static const struct clk_ops mpfs_clk_cfg_ops = { .set_rate = mpfs_cfg_clk_set_rate, }; -#define CLK_CFG(_id, _name, _parent, _shift, _width, _table, _flags) { \ - .cfg.id = _id, \ - .cfg.shift = _shift, \ - .cfg.width = _width, \ - .cfg.table = _table, \ - .hw.init = CLK_HW_INIT_PARENTS_DATA(_name, _parent, &mpfs_clk_cfg_ops, \ - _flags), \ +#define CLK_CFG(_id, _name, _parent, _shift, _width, _table, _flags, _offset) { \ + .cfg.id = _id, \ + .cfg.shift = _shift, \ + .cfg.width = _width, \ + .cfg.table = _table, \ + .cfg.reg_offset = _offset, \ + .cfg.flags = _flags, \ + .hw.init = CLK_HW_INIT(_name, _parent, &mpfs_clk_cfg_ops, 0), \ } static struct mpfs_cfg_hw_clock mpfs_cfg_clks[] = { - CLK_CFG(CLK_CPU, "clk_cpu", mpfs_cfg_parent, 0, 2, mpfs_div_cpu_axi_table, 0), - CLK_CFG(CLK_AXI, "clk_axi", mpfs_cfg_parent, 2, 2, mpfs_div_cpu_axi_table, 0), - CLK_CFG(CLK_AHB, "clk_ahb", mpfs_cfg_parent, 4, 2, mpfs_div_ahb_table, 0), + CLK_CFG(CLK_CPU, "clk_cpu", "clk_msspll", 0, 2, mpfs_div_cpu_axi_table, 0, + REG_CLOCK_CONFIG_CR), + CLK_CFG(CLK_AXI, "clk_axi", "clk_msspll", 2, 2, mpfs_div_cpu_axi_table, 0, + REG_CLOCK_CONFIG_CR), + CLK_CFG(CLK_AHB, "clk_ahb", "clk_msspll", 4, 2, mpfs_div_ahb_table, 0, + REG_CLOCK_CONFIG_CR), + { + .cfg.id = CLK_RTCREF, + .cfg.shift = 0, + .cfg.width = 12, + .cfg.table = mpfs_div_rtcref_table, + .cfg.reg_offset = REG_RTC_CLOCK_CR, + .cfg.flags = CLK_DIVIDER_ONE_BASED, + .hw.init = + CLK_HW_INIT_PARENTS_DATA("clk_rtcref", mpfs_ext_ref, &mpfs_clk_cfg_ops, 0), + } }; static int mpfs_clk_register_cfg(struct device *dev, struct mpfs_cfg_hw_clock *cfg_hw, @@ -160,13 +281,17 @@ static int mpfs_clk_register_cfgs(struct device *dev, struct mpfs_cfg_hw_clock * return dev_err_probe(dev, ret, "failed to register clock id: %d\n", cfg_hw->cfg.id); - id = cfg_hws[i].cfg.id; + id = cfg_hw->cfg.id; data->hw_data.hws[id] = &cfg_hw->hw; } return 0; } +/* + * peripheral clocks - devices connected to axi or ahb buses. + */ + static int mpfs_periph_clk_enable(struct clk_hw *hw) { struct mpfs_periph_hw_clock *periph_hw = to_mpfs_periph_clk(hw); @@ -200,10 +325,6 @@ static void mpfs_periph_clk_disable(struct clk_hw *hw) spin_lock_irqsave(&mpfs_clk_lock, flags); - reg = readl_relaxed(base_addr + REG_SUBBLK_RESET_CR); - val = reg | (1u << periph->shift); - writel_relaxed(val, base_addr + REG_SUBBLK_RESET_CR); - reg = readl_relaxed(base_addr + REG_SUBBLK_CLOCK_CR); val = reg & ~(1u << periph->shift); writel_relaxed(val, base_addr + REG_SUBBLK_CLOCK_CR); @@ -249,8 +370,10 @@ static const struct clk_ops mpfs_periph_clk_ops = { * trap handler * - CLK_MMUART0: reserved by the hss * - CLK_DDRC: provides clock to the ddr subsystem - * - CLK_FICx: these provide clocks for sections of the fpga fabric, disabling them would - * cause the fabric to go into reset + * - CLK_FICx: these provide the processor side clocks to the "FIC" (Fabric InterConnect) + * clock domain crossers which provide the interface to the FPGA fabric. Disabling them + * causes the FPGA fabric to go into reset. + * - CLK_ATHENA: The athena clock is FIC4, which is reserved for the Athena TeraFire. */ static struct mpfs_periph_hw_clock mpfs_periph_clks[] = { @@ -258,7 +381,7 @@ static struct mpfs_periph_hw_clock mpfs_periph_clks[] = { CLK_PERIPH(CLK_MAC0, "clk_periph_mac0", PARENT_CLK(AHB), 1, 0), CLK_PERIPH(CLK_MAC1, "clk_periph_mac1", PARENT_CLK(AHB), 2, 0), CLK_PERIPH(CLK_MMC, "clk_periph_mmc", PARENT_CLK(AHB), 3, 0), - CLK_PERIPH(CLK_TIMER, "clk_periph_timer", PARENT_CLK(AHB), 4, 0), + CLK_PERIPH(CLK_TIMER, "clk_periph_timer", PARENT_CLK(RTCREF), 4, 0), CLK_PERIPH(CLK_MMUART0, "clk_periph_mmuart0", PARENT_CLK(AHB), 5, CLK_IS_CRITICAL), CLK_PERIPH(CLK_MMUART1, "clk_periph_mmuart1", PARENT_CLK(AHB), 6, 0), CLK_PERIPH(CLK_MMUART2, "clk_periph_mmuart2", PARENT_CLK(AHB), 7, 0), @@ -277,11 +400,11 @@ static struct mpfs_periph_hw_clock mpfs_periph_clks[] = { CLK_PERIPH(CLK_GPIO1, "clk_periph_gpio1", PARENT_CLK(AHB), 21, 0), CLK_PERIPH(CLK_GPIO2, "clk_periph_gpio2", PARENT_CLK(AHB), 22, 0), CLK_PERIPH(CLK_DDRC, "clk_periph_ddrc", PARENT_CLK(AHB), 23, CLK_IS_CRITICAL), - CLK_PERIPH(CLK_FIC0, "clk_periph_fic0", PARENT_CLK(AHB), 24, CLK_IS_CRITICAL), - CLK_PERIPH(CLK_FIC1, "clk_periph_fic1", PARENT_CLK(AHB), 25, CLK_IS_CRITICAL), - CLK_PERIPH(CLK_FIC2, "clk_periph_fic2", PARENT_CLK(AHB), 26, CLK_IS_CRITICAL), - CLK_PERIPH(CLK_FIC3, "clk_periph_fic3", PARENT_CLK(AHB), 27, CLK_IS_CRITICAL), - CLK_PERIPH(CLK_ATHENA, "clk_periph_athena", PARENT_CLK(AHB), 28, 0), + CLK_PERIPH(CLK_FIC0, "clk_periph_fic0", PARENT_CLK(AXI), 24, CLK_IS_CRITICAL), + CLK_PERIPH(CLK_FIC1, "clk_periph_fic1", PARENT_CLK(AXI), 25, CLK_IS_CRITICAL), + CLK_PERIPH(CLK_FIC2, "clk_periph_fic2", PARENT_CLK(AXI), 26, CLK_IS_CRITICAL), + CLK_PERIPH(CLK_FIC3, "clk_periph_fic3", PARENT_CLK(AXI), 27, CLK_IS_CRITICAL), + CLK_PERIPH(CLK_ATHENA, "clk_periph_athena", PARENT_CLK(AXI), 28, CLK_IS_CRITICAL), CLK_PERIPH(CLK_CFM, "clk_periph_cfm", PARENT_CLK(AHB), 29, 0), }; @@ -322,8 +445,9 @@ static int mpfs_clk_probe(struct platform_device *pdev) unsigned int num_clks; int ret; - /* CLK_RESERVED is not part of cfg_clks nor periph_clks, so add 1 */ - num_clks = ARRAY_SIZE(mpfs_cfg_clks) + ARRAY_SIZE(mpfs_periph_clks) + 1; + /* CLK_RESERVED is not part of clock arrays, so add 1 */ + num_clks = ARRAY_SIZE(mpfs_msspll_clks) + ARRAY_SIZE(mpfs_cfg_clks) + + ARRAY_SIZE(mpfs_periph_clks) + 1; clk_data = devm_kzalloc(dev, struct_size(clk_data, hw_data.hws, num_clks), GFP_KERNEL); if (!clk_data) @@ -333,8 +457,17 @@ static int mpfs_clk_probe(struct platform_device *pdev) if (IS_ERR(clk_data->base)) return PTR_ERR(clk_data->base); + clk_data->msspll_base = devm_platform_ioremap_resource(pdev, 1); + if (IS_ERR(clk_data->msspll_base)) + return PTR_ERR(clk_data->msspll_base); + clk_data->hw_data.num = num_clks; + ret = mpfs_clk_register_mssplls(dev, mpfs_msspll_clks, ARRAY_SIZE(mpfs_msspll_clks), + clk_data); + if (ret) + return ret; + ret = mpfs_clk_register_cfgs(dev, mpfs_cfg_clks, ARRAY_SIZE(mpfs_cfg_clks), clk_data); if (ret) return ret; diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c index f675fd969c4d..e9c357309fd9 100644 --- a/drivers/clk/qcom/clk-rcg2.c +++ b/drivers/clk/qcom/clk-rcg2.c @@ -818,7 +818,7 @@ EXPORT_SYMBOL_GPL(clk_pixel_ops); static int clk_gfx3d_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) { - struct clk_rate_request parent_req = { }; + struct clk_rate_request parent_req = { .min_rate = 0, .max_rate = ULONG_MAX }; struct clk_rcg2_gfx3d *cgfx = to_clk_rcg2_gfx3d(hw); struct clk_hw *xo, *p0, *p1, *p2; unsigned long p0_rate; diff --git a/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c index 8a10bade7e0d..2f3ddc908ebd 100644 --- a/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c +++ b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c @@ -241,6 +241,7 @@ static struct clk_init_data rtc_32k_init_data = { .ops = &ccu_mux_ops, .parent_hws = rtc_32k_parents, .num_parents = ARRAY_SIZE(rtc_32k_parents), /* updated during probe */ + .flags = CLK_IS_CRITICAL, }; static struct ccu_mux rtc_32k_clk = { @@ -346,6 +347,7 @@ static const struct of_device_id sun6i_rtc_ccu_match[] = { .compatible = "allwinner,sun50i-r329-rtc", .data = &sun50i_r329_rtc_ccu_data, }, + {}, }; int sun6i_rtc_ccu_probe(struct device *dev, void __iomem *reg) diff --git a/drivers/clk/sunxi/clk-sun9i-mmc.c b/drivers/clk/sunxi/clk-sun9i-mmc.c index 542b31d6e96d..636bcf2439ef 100644 --- a/drivers/clk/sunxi/clk-sun9i-mmc.c +++ b/drivers/clk/sunxi/clk-sun9i-mmc.c @@ -109,6 +109,8 @@ static int sun9i_a80_mmc_config_clk_probe(struct platform_device *pdev) spin_lock_init(&data->lock); r = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!r) + return -EINVAL; /* one clock/reset pair per word */ count = DIV_ROUND_UP((resource_size(r)), SUN9I_MMC_WIDTH); data->membase = devm_ioremap_resource(&pdev->dev, r); diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c index f9d593ff4718..0253731d6d25 100644 --- a/drivers/cpufreq/qcom-cpufreq-hw.c +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -24,13 +24,17 @@ #define CLK_HW_DIV 2 #define LUT_TURBO_IND 1 +#define GT_IRQ_STATUS BIT(2) + #define HZ_PER_KHZ 1000 struct qcom_cpufreq_soc_data { u32 reg_enable; + u32 reg_domain_state; u32 reg_dcvs_ctrl; u32 reg_freq_lut; u32 reg_volt_lut; + u32 reg_intr_clr; u32 reg_current_vote; u32 reg_perf_state; u8 lut_row_size; @@ -280,37 +284,46 @@ static void qcom_get_related_cpus(int index, struct cpumask *m) } } -static unsigned int qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data) +static unsigned long qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data) { - unsigned int val = readl_relaxed(data->base + data->soc_data->reg_current_vote); + unsigned int lval; + + if (data->soc_data->reg_current_vote) + lval = readl_relaxed(data->base + data->soc_data->reg_current_vote) & 0x3ff; + else + lval = readl_relaxed(data->base + data->soc_data->reg_domain_state) & 0xff; - return (val & 0x3FF) * 19200; + return lval * xo_rate; } static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data) { struct cpufreq_policy *policy = data->policy; - int cpu = cpumask_first(policy->cpus); + int cpu = cpumask_first(policy->related_cpus); struct device *dev = get_cpu_device(cpu); unsigned long freq_hz, throttled_freq; struct dev_pm_opp *opp; - unsigned int freq; /* * Get the h/w throttled frequency, normalize it using the * registered opp table and use it to calculate thermal pressure. */ - freq = qcom_lmh_get_throttle_freq(data); - freq_hz = freq * HZ_PER_KHZ; + freq_hz = qcom_lmh_get_throttle_freq(data); opp = dev_pm_opp_find_freq_floor(dev, &freq_hz); if (IS_ERR(opp) && PTR_ERR(opp) == -ERANGE) - dev_pm_opp_find_freq_ceil(dev, &freq_hz); + opp = dev_pm_opp_find_freq_ceil(dev, &freq_hz); + + if (IS_ERR(opp)) { + dev_warn(dev, "Can't find the OPP for throttling: %pe!\n", opp); + } else { + throttled_freq = freq_hz / HZ_PER_KHZ; - throttled_freq = freq_hz / HZ_PER_KHZ; + /* Update thermal pressure (the boost frequencies are accepted) */ + arch_update_thermal_pressure(policy->related_cpus, throttled_freq); - /* Update thermal pressure (the boost frequencies are accepted) */ - arch_update_thermal_pressure(policy->related_cpus, throttled_freq); + dev_pm_opp_put(opp); + } /* * In the unlikely case policy is unregistered do not enable @@ -350,6 +363,10 @@ static irqreturn_t qcom_lmh_dcvs_handle_irq(int irq, void *data) disable_irq_nosync(c_data->throttle_irq); schedule_delayed_work(&c_data->throttle_work, 0); + if (c_data->soc_data->reg_intr_clr) + writel_relaxed(GT_IRQ_STATUS, + c_data->base + c_data->soc_data->reg_intr_clr); + return IRQ_HANDLED; } @@ -365,9 +382,11 @@ static const struct qcom_cpufreq_soc_data qcom_soc_data = { static const struct qcom_cpufreq_soc_data epss_soc_data = { .reg_enable = 0x0, + .reg_domain_state = 0x20, .reg_dcvs_ctrl = 0xb0, .reg_freq_lut = 0x100, .reg_volt_lut = 0x200, + .reg_intr_clr = 0x308, .reg_perf_state = 0x320, .lut_row_size = 4, }; @@ -417,16 +436,39 @@ static int qcom_cpufreq_hw_lmh_init(struct cpufreq_policy *policy, int index) return 0; } -static void qcom_cpufreq_hw_lmh_exit(struct qcom_cpufreq_data *data) +static int qcom_cpufreq_hw_cpu_online(struct cpufreq_policy *policy) +{ + struct qcom_cpufreq_data *data = policy->driver_data; + struct platform_device *pdev = cpufreq_get_driver_data(); + int ret; + + ret = irq_set_affinity_hint(data->throttle_irq, policy->cpus); + if (ret) + dev_err(&pdev->dev, "Failed to set CPU affinity of %s[%d]\n", + data->irq_name, data->throttle_irq); + + return ret; +} + +static int qcom_cpufreq_hw_cpu_offline(struct cpufreq_policy *policy) { + struct qcom_cpufreq_data *data = policy->driver_data; + if (data->throttle_irq <= 0) - return; + return 0; mutex_lock(&data->throttle_lock); data->cancel_throttle = true; mutex_unlock(&data->throttle_lock); cancel_delayed_work_sync(&data->throttle_work); + irq_set_affinity_hint(data->throttle_irq, NULL); + + return 0; +} + +static void qcom_cpufreq_hw_lmh_exit(struct qcom_cpufreq_data *data) +{ free_irq(data->throttle_irq, data); } @@ -583,6 +625,8 @@ static struct cpufreq_driver cpufreq_qcom_hw_driver = { .get = qcom_cpufreq_hw_get, .init = qcom_cpufreq_hw_cpu_init, .exit = qcom_cpufreq_hw_cpu_exit, + .online = qcom_cpufreq_hw_cpu_online, + .offline = qcom_cpufreq_hw_cpu_offline, .register_em = cpufreq_register_em_with_opp, .fast_switch = qcom_cpufreq_hw_fast_switch, .name = "qcom-cpufreq-hw", diff --git a/drivers/cpufreq/sun50i-cpufreq-nvmem.c b/drivers/cpufreq/sun50i-cpufreq-nvmem.c index 2deed8d8773f..75e1bf3a08f7 100644 --- a/drivers/cpufreq/sun50i-cpufreq-nvmem.c +++ b/drivers/cpufreq/sun50i-cpufreq-nvmem.c @@ -98,8 +98,10 @@ static int sun50i_cpufreq_nvmem_probe(struct platform_device *pdev) return -ENOMEM; ret = sun50i_cpufreq_get_efuse(&speed); - if (ret) + if (ret) { + kfree(opp_tables); return ret; + } snprintf(name, MAX_NAME_LEN, "speed%d", speed); diff --git a/drivers/cpuidle/cpuidle-riscv-sbi.c b/drivers/cpuidle/cpuidle-riscv-sbi.c index b459eda2cd37..5c852e671992 100644 --- a/drivers/cpuidle/cpuidle-riscv-sbi.c +++ b/drivers/cpuidle/cpuidle-riscv-sbi.c @@ -22,6 +22,7 @@ #include <linux/pm_runtime.h> #include <asm/cpuidle.h> #include <asm/sbi.h> +#include <asm/smp.h> #include <asm/suspend.h> #include "dt_idle_states.h" diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 1476156af74b..def564d1e8fa 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -1453,7 +1453,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, { struct at_xdmac_chan *atchan = to_at_xdmac_chan(chan); struct at_xdmac *atxdmac = to_at_xdmac(atchan->chan.device); - struct at_xdmac_desc *desc, *_desc; + struct at_xdmac_desc *desc, *_desc, *iter; struct list_head *descs_list; enum dma_status ret; int residue, retry; @@ -1568,11 +1568,13 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, * microblock. */ descs_list = &desc->descs_list; - list_for_each_entry_safe(desc, _desc, descs_list, desc_node) { - dwidth = at_xdmac_get_dwidth(desc->lld.mbr_cfg); - residue -= (desc->lld.mbr_ubc & 0xffffff) << dwidth; - if ((desc->lld.mbr_nda & 0xfffffffc) == cur_nda) + list_for_each_entry_safe(iter, _desc, descs_list, desc_node) { + dwidth = at_xdmac_get_dwidth(iter->lld.mbr_cfg); + residue -= (iter->lld.mbr_ubc & 0xffffff) << dwidth; + if ((iter->lld.mbr_nda & 0xfffffffc) == cur_nda) { + desc = iter; break; + } } residue += cur_ubc << dwidth; diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.c b/drivers/dma/dw-edma/dw-edma-v0-core.c index 329fc2e57b70..33bc1e6c4cf2 100644 --- a/drivers/dma/dw-edma/dw-edma-v0-core.c +++ b/drivers/dma/dw-edma/dw-edma-v0-core.c @@ -414,14 +414,18 @@ void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first) SET_CH_32(dw, chan->dir, chan->id, ch_control1, (DW_EDMA_V0_CCS | DW_EDMA_V0_LLE)); /* Linked list */ + #ifdef CONFIG_64BIT - SET_CH_64(dw, chan->dir, chan->id, llp.reg, - chunk->ll_region.paddr); + /* llp is not aligned on 64bit -> keep 32bit accesses */ + SET_CH_32(dw, chan->dir, chan->id, llp.lsb, + lower_32_bits(chunk->ll_region.paddr)); + SET_CH_32(dw, chan->dir, chan->id, llp.msb, + upper_32_bits(chunk->ll_region.paddr)); #else /* CONFIG_64BIT */ - SET_CH_32(dw, chan->dir, chan->id, llp.lsb, - lower_32_bits(chunk->ll_region.paddr)); - SET_CH_32(dw, chan->dir, chan->id, llp.msb, - upper_32_bits(chunk->ll_region.paddr)); + SET_CH_32(dw, chan->dir, chan->id, llp.lsb, + lower_32_bits(chunk->ll_region.paddr)); + SET_CH_32(dw, chan->dir, chan->id, llp.msb, + upper_32_bits(chunk->ll_region.paddr)); #endif /* CONFIG_64BIT */ } /* Doorbell */ diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index 3061fe857d69..f652da6ab47d 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -373,7 +373,6 @@ static void idxd_wq_device_reset_cleanup(struct idxd_wq *wq) { lockdep_assert_held(&wq->wq_lock); - idxd_wq_disable_cleanup(wq); wq->size = 0; wq->group = NULL; } @@ -701,14 +700,17 @@ static void idxd_device_wqs_clear_state(struct idxd_device *idxd) if (wq->state == IDXD_WQ_ENABLED) { idxd_wq_disable_cleanup(wq); - idxd_wq_device_reset_cleanup(wq); wq->state = IDXD_WQ_DISABLED; } + idxd_wq_device_reset_cleanup(wq); } } void idxd_device_clear_state(struct idxd_device *idxd) { + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return; + idxd_groups_clear_state(idxd); idxd_engines_clear_state(idxd); idxd_device_wqs_clear_state(idxd); diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c index e289fd48711a..c01db23e3333 100644 --- a/drivers/dma/idxd/submit.c +++ b/drivers/dma/idxd/submit.c @@ -150,14 +150,15 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie, */ int idxd_enqcmds(struct idxd_wq *wq, void __iomem *portal, const void *desc) { - int rc, retries = 0; + unsigned int retries = wq->enqcmds_retries; + int rc; do { rc = enqcmds(portal, desc); if (rc == 0) break; cpu_relax(); - } while (retries++ < wq->enqcmds_retries); + } while (retries--); return rc; } diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index 7e19ab92b61a..dfd549685c46 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -905,6 +905,9 @@ static ssize_t wq_max_transfer_size_store(struct device *dev, struct device_attr u64 xfer_size; int rc; + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return -EPERM; + if (wq->state != IDXD_WQ_DISABLED) return -EPERM; @@ -939,6 +942,9 @@ static ssize_t wq_max_batch_size_store(struct device *dev, struct device_attribu u64 batch_size; int rc; + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return -EPERM; + if (wq->state != IDXD_WQ_DISABLED) return -EPERM; diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index 70c0aa931ddf..6196a7b3956b 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -198,12 +198,12 @@ struct sdma_script_start_addrs { s32 per_2_firi_addr; s32 mcu_2_firi_addr; s32 uart_2_per_addr; - s32 uart_2_mcu_ram_addr; + s32 uart_2_mcu_addr; s32 per_2_app_addr; s32 mcu_2_app_addr; s32 per_2_per_addr; s32 uartsh_2_per_addr; - s32 uartsh_2_mcu_ram_addr; + s32 uartsh_2_mcu_addr; s32 per_2_shp_addr; s32 mcu_2_shp_addr; s32 ata_2_mcu_addr; @@ -232,8 +232,8 @@ struct sdma_script_start_addrs { s32 mcu_2_ecspi_addr; s32 mcu_2_sai_addr; s32 sai_2_mcu_addr; - s32 uart_2_mcu_addr; - s32 uartsh_2_mcu_addr; + s32 uart_2_mcu_rom_addr; + s32 uartsh_2_mcu_rom_addr; /* End of v3 array */ s32 mcu_2_zqspi_addr; /* End of v4 array */ @@ -1796,17 +1796,17 @@ static void sdma_add_scripts(struct sdma_engine *sdma, saddr_arr[i] = addr_arr[i]; /* - * get uart_2_mcu_addr/uartsh_2_mcu_addr rom script specially because - * they are now replaced by uart_2_mcu_ram_addr/uartsh_2_mcu_ram_addr - * to be compatible with legacy freescale/nxp sdma firmware, and they - * are located in the bottom part of sdma_script_start_addrs which are - * beyond the SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V1. + * For compatibility with NXP internal legacy kernel before 4.19 which + * is based on uart ram script and mainline kernel based on uart rom + * script, both uart ram/rom scripts are present in newer sdma + * firmware. Use the rom versions if they are present (V3 or newer). */ - if (addr->uart_2_mcu_addr) - sdma->script_addrs->uart_2_mcu_addr = addr->uart_2_mcu_addr; - if (addr->uartsh_2_mcu_addr) - sdma->script_addrs->uartsh_2_mcu_addr = addr->uartsh_2_mcu_addr; - + if (sdma->script_number >= SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V3) { + if (addr->uart_2_mcu_rom_addr) + sdma->script_addrs->uart_2_mcu_addr = addr->uart_2_mcu_rom_addr; + if (addr->uartsh_2_mcu_rom_addr) + sdma->script_addrs->uartsh_2_mcu_addr = addr->uartsh_2_mcu_rom_addr; + } } static void sdma_load_firmware(const struct firmware *fw, void *context) @@ -1885,7 +1885,7 @@ static int sdma_event_remap(struct sdma_engine *sdma) u32 reg, val, shift, num_map, i; int ret = 0; - if (IS_ERR(np) || IS_ERR(gpr_np)) + if (IS_ERR(np) || !gpr_np) goto out; event_remap = of_find_property(np, propname, NULL); @@ -1933,7 +1933,7 @@ static int sdma_event_remap(struct sdma_engine *sdma) } out: - if (!IS_ERR(gpr_np)) + if (gpr_np) of_node_put(gpr_np); return ret; diff --git a/drivers/dma/mediatek/mtk-uart-apdma.c b/drivers/dma/mediatek/mtk-uart-apdma.c index 375e7e647df6..a1517ef1f4a0 100644 --- a/drivers/dma/mediatek/mtk-uart-apdma.c +++ b/drivers/dma/mediatek/mtk-uart-apdma.c @@ -274,7 +274,7 @@ static int mtk_uart_apdma_alloc_chan_resources(struct dma_chan *chan) unsigned int status; int ret; - ret = pm_runtime_get_sync(mtkd->ddev.dev); + ret = pm_runtime_resume_and_get(mtkd->ddev.dev); if (ret < 0) { pm_runtime_put_noidle(chan->device->dev); return ret; @@ -288,18 +288,21 @@ static int mtk_uart_apdma_alloc_chan_resources(struct dma_chan *chan) ret = readx_poll_timeout(readl, c->base + VFF_EN, status, !status, 10, 100); if (ret) - return ret; + goto err_pm; ret = request_irq(c->irq, mtk_uart_apdma_irq_handler, IRQF_TRIGGER_NONE, KBUILD_MODNAME, chan); if (ret < 0) { dev_err(chan->device->dev, "Can't request dma IRQ\n"); - return -EINVAL; + ret = -EINVAL; + goto err_pm; } if (mtkd->support_33bits) mtk_uart_apdma_write(c, VFF_4G_SUPPORT, VFF_4G_SUPPORT_CLR_B); +err_pm: + pm_runtime_put_noidle(mtkd->ddev.dev); return ret; } diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c index f05ff02c0656..40b1abeca856 100644 --- a/drivers/edac/synopsys_edac.c +++ b/drivers/edac/synopsys_edac.c @@ -164,6 +164,11 @@ #define ECC_STAT_CECNT_SHIFT 8 #define ECC_STAT_BITNUM_MASK 0x7F +/* ECC error count register definitions */ +#define ECC_ERRCNT_UECNT_MASK 0xFFFF0000 +#define ECC_ERRCNT_UECNT_SHIFT 16 +#define ECC_ERRCNT_CECNT_MASK 0xFFFF + /* DDR QOS Interrupt register definitions */ #define DDR_QOS_IRQ_STAT_OFST 0x20200 #define DDR_QOSUE_MASK 0x4 @@ -423,15 +428,16 @@ static int zynqmp_get_error_info(struct synps_edac_priv *priv) base = priv->baseaddr; p = &priv->stat; + regval = readl(base + ECC_ERRCNT_OFST); + p->ce_cnt = regval & ECC_ERRCNT_CECNT_MASK; + p->ue_cnt = (regval & ECC_ERRCNT_UECNT_MASK) >> ECC_ERRCNT_UECNT_SHIFT; + if (!p->ce_cnt) + goto ue_err; + regval = readl(base + ECC_STAT_OFST); if (!regval) return 1; - p->ce_cnt = (regval & ECC_STAT_CECNT_MASK) >> ECC_STAT_CECNT_SHIFT; - p->ue_cnt = (regval & ECC_STAT_UECNT_MASK) >> ECC_STAT_UECNT_SHIFT; - if (!p->ce_cnt) - goto ue_err; - p->ceinfo.bitpos = (regval & ECC_STAT_BITNUM_MASK); regval = readl(base + ECC_CEADDR0_OFST); diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c index e48108e694f8..7dad6f57d970 100644 --- a/drivers/firmware/cirrus/cs_dsp.c +++ b/drivers/firmware/cirrus/cs_dsp.c @@ -955,8 +955,7 @@ static int cs_dsp_create_control(struct cs_dsp *dsp, ctl->alg_region = *alg_region; if (subname && dsp->fw_ver >= 2) { ctl->subname_len = subname_len; - ctl->subname = kmemdup(subname, - strlen(subname) + 1, GFP_KERNEL); + ctl->subname = kasprintf(GFP_KERNEL, "%.*s", subname_len, subname); if (!ctl->subname) { ret = -ENOMEM; goto err_ctl; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 085348e08986..b7694171655c 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1601,8 +1601,6 @@ static int gpiochip_add_irqchip(struct gpio_chip *gc, gpiochip_set_irq_hooks(gc); - acpi_gpiochip_request_interrupts(gc); - /* * Using barrier() here to prevent compiler from reordering * gc->irq.initialized before initialization of above @@ -1612,6 +1610,8 @@ static int gpiochip_add_irqchip(struct gpio_chip *gc, gc->irq.initialized = true; + acpi_gpiochip_request_interrupts(gc); + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 970b065e9a6b..d0d0ea565e3d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -128,6 +128,8 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs goto free_chunk; } + mutex_lock(&p->ctx->lock); + /* skip guilty context job */ if (atomic_read(&p->ctx->guilty) == 1) { ret = -ECANCELED; @@ -709,6 +711,7 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, dma_fence_put(parser->fence); if (parser->ctx) { + mutex_unlock(&parser->ctx->lock); amdgpu_ctx_put(parser->ctx); } if (parser->bo_list) @@ -1157,6 +1160,9 @@ static int amdgpu_cs_dependencies(struct amdgpu_device *adev, { int i, r; + /* TODO: Investigate why we still need the context lock */ + mutex_unlock(&p->ctx->lock); + for (i = 0; i < p->nchunks; ++i) { struct amdgpu_cs_chunk *chunk; @@ -1167,32 +1173,34 @@ static int amdgpu_cs_dependencies(struct amdgpu_device *adev, case AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES: r = amdgpu_cs_process_fence_dep(p, chunk); if (r) - return r; + goto out; break; case AMDGPU_CHUNK_ID_SYNCOBJ_IN: r = amdgpu_cs_process_syncobj_in_dep(p, chunk); if (r) - return r; + goto out; break; case AMDGPU_CHUNK_ID_SYNCOBJ_OUT: r = amdgpu_cs_process_syncobj_out_dep(p, chunk); if (r) - return r; + goto out; break; case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT: r = amdgpu_cs_process_syncobj_timeline_in_dep(p, chunk); if (r) - return r; + goto out; break; case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL: r = amdgpu_cs_process_syncobj_timeline_out_dep(p, chunk); if (r) - return r; + goto out; break; } } - return 0; +out: + mutex_lock(&p->ctx->lock); + return r; } static void amdgpu_cs_post_dependencies(struct amdgpu_cs_parser *p) @@ -1368,6 +1376,7 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) goto out; r = amdgpu_cs_submit(&parser, cs); + out: amdgpu_cs_parser_fini(&parser, r, reserved_buffers); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 5981c7d9bd48..8f0e6d93bb9c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -237,6 +237,7 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev, kref_init(&ctx->refcount); spin_lock_init(&ctx->ring_lock); + mutex_init(&ctx->lock); ctx->reset_counter = atomic_read(&adev->gpu_reset_counter); ctx->reset_counter_query = ctx->reset_counter; @@ -357,6 +358,7 @@ static void amdgpu_ctx_fini(struct kref *ref) drm_dev_exit(idx); } + mutex_destroy(&ctx->lock); kfree(ctx); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h index d0cbfcea90f7..142f2f87d44c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h @@ -49,6 +49,7 @@ struct amdgpu_ctx { bool preamble_presented; int32_t init_priority; int32_t override_priority; + struct mutex lock; atomic_t guilty; unsigned long ras_counter_ce; unsigned long ras_counter_ue; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 29e9419a914b..7fd0277b2805 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2395,6 +2395,71 @@ static int amdgpu_pmops_restore(struct device *dev) return amdgpu_device_resume(drm_dev, true); } +static int amdgpu_runtime_idle_check_display(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct drm_device *drm_dev = pci_get_drvdata(pdev); + struct amdgpu_device *adev = drm_to_adev(drm_dev); + + if (adev->mode_info.num_crtc) { + struct drm_connector *list_connector; + struct drm_connector_list_iter iter; + int ret = 0; + + /* XXX: Return busy if any displays are connected to avoid + * possible display wakeups after runtime resume due to + * hotplug events in case any displays were connected while + * the GPU was in suspend. Remove this once that is fixed. + */ + mutex_lock(&drm_dev->mode_config.mutex); + drm_connector_list_iter_begin(drm_dev, &iter); + drm_for_each_connector_iter(list_connector, &iter) { + if (list_connector->status == connector_status_connected) { + ret = -EBUSY; + break; + } + } + drm_connector_list_iter_end(&iter); + mutex_unlock(&drm_dev->mode_config.mutex); + + if (ret) + return ret; + + if (amdgpu_device_has_dc_support(adev)) { + struct drm_crtc *crtc; + + drm_for_each_crtc(crtc, drm_dev) { + drm_modeset_lock(&crtc->mutex, NULL); + if (crtc->state->active) + ret = -EBUSY; + drm_modeset_unlock(&crtc->mutex); + if (ret < 0) + break; + } + } else { + mutex_lock(&drm_dev->mode_config.mutex); + drm_modeset_lock(&drm_dev->mode_config.connection_mutex, NULL); + + drm_connector_list_iter_begin(drm_dev, &iter); + drm_for_each_connector_iter(list_connector, &iter) { + if (list_connector->dpms == DRM_MODE_DPMS_ON) { + ret = -EBUSY; + break; + } + } + + drm_connector_list_iter_end(&iter); + + drm_modeset_unlock(&drm_dev->mode_config.connection_mutex); + mutex_unlock(&drm_dev->mode_config.mutex); + } + if (ret) + return ret; + } + + return 0; +} + static int amdgpu_pmops_runtime_suspend(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); @@ -2407,6 +2472,10 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev) return -EBUSY; } + ret = amdgpu_runtime_idle_check_display(dev); + if (ret) + return ret; + /* wait for all rings to drain before suspending */ for (i = 0; i < AMDGPU_MAX_RINGS; i++) { struct amdgpu_ring *ring = adev->rings[i]; @@ -2516,41 +2585,7 @@ static int amdgpu_pmops_runtime_idle(struct device *dev) return -EBUSY; } - if (amdgpu_device_has_dc_support(adev)) { - struct drm_crtc *crtc; - - drm_for_each_crtc(crtc, drm_dev) { - drm_modeset_lock(&crtc->mutex, NULL); - if (crtc->state->active) - ret = -EBUSY; - drm_modeset_unlock(&crtc->mutex); - if (ret < 0) - break; - } - - } else { - struct drm_connector *list_connector; - struct drm_connector_list_iter iter; - - mutex_lock(&drm_dev->mode_config.mutex); - drm_modeset_lock(&drm_dev->mode_config.connection_mutex, NULL); - - drm_connector_list_iter_begin(drm_dev, &iter); - drm_for_each_connector_iter(list_connector, &iter) { - if (list_connector->dpms == DRM_MODE_DPMS_ON) { - ret = -EBUSY; - break; - } - } - - drm_connector_list_iter_end(&iter); - - drm_modeset_unlock(&drm_dev->mode_config.connection_mutex); - mutex_unlock(&drm_dev->mode_config.mutex); - } - - if (ret == -EBUSY) - DRM_DEBUG_DRIVER("failing to power off - crtc active\n"); + ret = amdgpu_runtime_idle_check_display(dev); pm_runtime_mark_last_busy(dev); pm_runtime_autosuspend(dev); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 5228421b0f72..7c956cf21bc7 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -1151,6 +1151,16 @@ static int gmc_v10_0_set_clockgating_state(void *handle, int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; + /* + * The issue mmhub can't disconnect from DF with MMHUB clock gating being disabled + * is a new problem observed at DF 3.0.3, however with the same suspend sequence not + * seen any issue on the DF 3.0.2 series platform. + */ + if (adev->in_s0ix && adev->ip_versions[DF_HWIP][0] > IP_VERSION(3, 0, 2)) { + dev_dbg(adev->dev, "keep mmhub clock gating being enabled for s0ix\n"); + return 0; + } + r = adev->mmhub.funcs->set_clockgating(adev, state); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index acf4f7975850..198672264492 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -130,19 +130,33 @@ void program_sh_mem_settings(struct device_queue_manager *dqm, } static void increment_queue_count(struct device_queue_manager *dqm, - enum kfd_queue_type type) + struct qcm_process_device *qpd, + struct queue *q) { dqm->active_queue_count++; - if (type == KFD_QUEUE_TYPE_COMPUTE || type == KFD_QUEUE_TYPE_DIQ) + if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE || + q->properties.type == KFD_QUEUE_TYPE_DIQ) dqm->active_cp_queue_count++; + + if (q->properties.is_gws) { + dqm->gws_queue_count++; + qpd->mapped_gws_queue = true; + } } static void decrement_queue_count(struct device_queue_manager *dqm, - enum kfd_queue_type type) + struct qcm_process_device *qpd, + struct queue *q) { dqm->active_queue_count--; - if (type == KFD_QUEUE_TYPE_COMPUTE || type == KFD_QUEUE_TYPE_DIQ) + if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE || + q->properties.type == KFD_QUEUE_TYPE_DIQ) dqm->active_cp_queue_count--; + + if (q->properties.is_gws) { + dqm->gws_queue_count--; + qpd->mapped_gws_queue = false; + } } /* @@ -412,7 +426,7 @@ add_queue_to_list: list_add(&q->list, &qpd->queues_list); qpd->queue_count++; if (q->properties.is_active) - increment_queue_count(dqm, q->properties.type); + increment_queue_count(dqm, qpd, q); /* * Unconditionally increment this counter, regardless of the queue's @@ -601,13 +615,8 @@ static int destroy_queue_nocpsch_locked(struct device_queue_manager *dqm, deallocate_vmid(dqm, qpd, q); } qpd->queue_count--; - if (q->properties.is_active) { - decrement_queue_count(dqm, q->properties.type); - if (q->properties.is_gws) { - dqm->gws_queue_count--; - qpd->mapped_gws_queue = false; - } - } + if (q->properties.is_active) + decrement_queue_count(dqm, qpd, q); return retval; } @@ -700,12 +709,11 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q, * dqm->active_queue_count to determine whether a new runlist must be * uploaded. */ - if (q->properties.is_active && !prev_active) - increment_queue_count(dqm, q->properties.type); - else if (!q->properties.is_active && prev_active) - decrement_queue_count(dqm, q->properties.type); - - if (q->gws && !q->properties.is_gws) { + if (q->properties.is_active && !prev_active) { + increment_queue_count(dqm, &pdd->qpd, q); + } else if (!q->properties.is_active && prev_active) { + decrement_queue_count(dqm, &pdd->qpd, q); + } else if (q->gws && !q->properties.is_gws) { if (q->properties.is_active) { dqm->gws_queue_count++; pdd->qpd.mapped_gws_queue = true; @@ -767,11 +775,7 @@ static int evict_process_queues_nocpsch(struct device_queue_manager *dqm, mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type( q->properties.type)]; q->properties.is_active = false; - decrement_queue_count(dqm, q->properties.type); - if (q->properties.is_gws) { - dqm->gws_queue_count--; - qpd->mapped_gws_queue = false; - } + decrement_queue_count(dqm, qpd, q); if (WARN_ONCE(!dqm->sched_running, "Evict when stopped\n")) continue; @@ -817,7 +821,7 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm, continue; q->properties.is_active = false; - decrement_queue_count(dqm, q->properties.type); + decrement_queue_count(dqm, qpd, q); } pdd->last_evict_timestamp = get_jiffies_64(); retval = execute_queues_cpsch(dqm, @@ -888,11 +892,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm, mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type( q->properties.type)]; q->properties.is_active = true; - increment_queue_count(dqm, q->properties.type); - if (q->properties.is_gws) { - dqm->gws_queue_count++; - qpd->mapped_gws_queue = true; - } + increment_queue_count(dqm, qpd, q); if (WARN_ONCE(!dqm->sched_running, "Restore when stopped\n")) continue; @@ -950,7 +950,7 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm, continue; q->properties.is_active = true; - increment_queue_count(dqm, q->properties.type); + increment_queue_count(dqm, &pdd->qpd, q); } retval = execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); @@ -1378,7 +1378,7 @@ static int create_kernel_queue_cpsch(struct device_queue_manager *dqm, dqm->total_queue_count); list_add(&kq->list, &qpd->priv_queue_list); - increment_queue_count(dqm, kq->queue->properties.type); + increment_queue_count(dqm, qpd, kq->queue); qpd->is_debug = true; execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); dqm_unlock(dqm); @@ -1392,7 +1392,7 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm, { dqm_lock(dqm); list_del(&kq->list); - decrement_queue_count(dqm, kq->queue->properties.type); + decrement_queue_count(dqm, qpd, kq->queue); qpd->is_debug = false; execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0); /* @@ -1467,7 +1467,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, qpd->queue_count++; if (q->properties.is_active) { - increment_queue_count(dqm, q->properties.type); + increment_queue_count(dqm, qpd, q); execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); @@ -1683,15 +1683,11 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm, list_del(&q->list); qpd->queue_count--; if (q->properties.is_active) { - decrement_queue_count(dqm, q->properties.type); + decrement_queue_count(dqm, qpd, q); retval = execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); if (retval == -ETIME) qpd->reset_wavefronts = true; - if (q->properties.is_gws) { - dqm->gws_queue_count--; - qpd->mapped_gws_queue = false; - } } /* @@ -1932,7 +1928,7 @@ static int process_termination_cpsch(struct device_queue_manager *dqm, /* Clean all kernel queues */ list_for_each_entry_safe(kq, kq_next, &qpd->priv_queue_list, list) { list_del(&kq->list); - decrement_queue_count(dqm, kq->queue->properties.type); + decrement_queue_count(dqm, qpd, kq->queue); qpd->is_debug = false; dqm->total_queue_count--; filter = KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES; @@ -1945,13 +1941,8 @@ static int process_termination_cpsch(struct device_queue_manager *dqm, else if (q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) deallocate_sdma_queue(dqm, q); - if (q->properties.is_active) { - decrement_queue_count(dqm, q->properties.type); - if (q->properties.is_gws) { - dqm->gws_queue_count--; - qpd->mapped_gws_queue = false; - } - } + if (q->properties.is_active) + decrement_queue_count(dqm, qpd, q); dqm->total_queue_count--; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 9967a73d5b0f..8f58fc491b28 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -1103,7 +1103,7 @@ struct kfd_criu_queue_priv_data { uint32_t priority; uint32_t q_percent; uint32_t doorbell_id; - uint32_t is_gws; + uint32_t gws; uint32_t sdma_id; uint32_t eop_ring_buffer_size; uint32_t ctx_save_restore_area_size; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index 6eca9509f2e3..4f58e671d39b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -636,6 +636,8 @@ static int criu_checkpoint_queue(struct kfd_process_device *pdd, q_data->ctx_save_restore_area_size = q->properties.ctx_save_restore_area_size; + q_data->gws = !!q->gws; + ret = pqm_checkpoint_mqd(&pdd->process->pqm, q->properties.queue_id, mqd, ctl_stack); if (ret) { pr_err("Failed checkpoint queue_mqd (%d)\n", ret); @@ -743,7 +745,6 @@ static void set_queue_properties_from_criu(struct queue_properties *qp, struct kfd_criu_queue_priv_data *q_data) { qp->is_interop = false; - qp->is_gws = q_data->is_gws; qp->queue_percent = q_data->q_percent; qp->priority = q_data->priority; qp->queue_address = q_data->q_address; @@ -826,12 +827,15 @@ int kfd_criu_restore_queue(struct kfd_process *p, NULL); if (ret) { pr_err("Failed to create new queue err:%d\n", ret); - ret = -EINVAL; + goto exit; } + if (q_data->gws) + ret = pqm_set_gws(&p->pqm, q_data->q_id, pdd->dev->gws); + exit: if (ret) - pr_err("Failed to create queue (%d)\n", ret); + pr_err("Failed to restore queue (%d)\n", ret); else pr_debug("Queue id %d was restored successfully\n", queue_id); diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index 3fe4bfbb98a0..faab59508d82 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -997,6 +997,7 @@ static struct clock_source *dcn21_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index 5504d81c77b7..72e7b5d40af6 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -427,6 +427,7 @@ int amdgpu_dpm_read_sensor(struct amdgpu_device *adev, enum amd_pp_sensors senso void amdgpu_dpm_compute_clocks(struct amdgpu_device *adev) { const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; + int i; if (!adev->pm.dpm_enabled) return; @@ -434,6 +435,15 @@ void amdgpu_dpm_compute_clocks(struct amdgpu_device *adev) if (!pp_funcs->pm_compute_clocks) return; + if (adev->mode_info.num_crtc) + amdgpu_display_bandwidth_update(adev); + + for (i = 0; i < AMDGPU_MAX_RINGS; i++) { + struct amdgpu_ring *ring = adev->rings[i]; + if (ring && ring->sched.ready) + amdgpu_fence_wait_empty(ring); + } + mutex_lock(&adev->pm.mutex); pp_funcs->pm_compute_clocks(adev->powerplay.pp_handle); mutex_unlock(&adev->pm.mutex); @@ -443,6 +453,20 @@ void amdgpu_dpm_enable_uvd(struct amdgpu_device *adev, bool enable) { int ret = 0; + if (adev->family == AMDGPU_FAMILY_SI) { + mutex_lock(&adev->pm.mutex); + if (enable) { + adev->pm.dpm.uvd_active = true; + adev->pm.dpm.state = POWER_STATE_TYPE_INTERNAL_UVD; + } else { + adev->pm.dpm.uvd_active = false; + } + mutex_unlock(&adev->pm.mutex); + + amdgpu_dpm_compute_clocks(adev); + return; + } + ret = amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_UVD, !enable); if (ret) DRM_ERROR("Dpm %s uvd failed, ret = %d. \n", @@ -453,6 +477,21 @@ void amdgpu_dpm_enable_vce(struct amdgpu_device *adev, bool enable) { int ret = 0; + if (adev->family == AMDGPU_FAMILY_SI) { + mutex_lock(&adev->pm.mutex); + if (enable) { + adev->pm.dpm.vce_active = true; + /* XXX select vce level based on ring/task */ + adev->pm.dpm.vce_level = AMD_VCE_LEVEL_AC_ALL; + } else { + adev->pm.dpm.vce_active = false; + } + mutex_unlock(&adev->pm.mutex); + + amdgpu_dpm_compute_clocks(adev); + return; + } + ret = amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_VCE, !enable); if (ret) DRM_ERROR("Dpm %s vce failed, ret = %d. \n", diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c index 9613c6181c17..d3fe149d8476 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c @@ -1028,16 +1028,6 @@ static int amdgpu_dpm_change_power_state_locked(struct amdgpu_device *adev) void amdgpu_legacy_dpm_compute_clocks(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - int i = 0; - - if (adev->mode_info.num_crtc) - amdgpu_display_bandwidth_update(adev); - - for (i = 0; i < AMDGPU_MAX_RINGS; i++) { - struct amdgpu_ring *ring = adev->rings[i]; - if (ring && ring->sched.ready) - amdgpu_fence_wait_empty(ring); - } amdgpu_dpm_get_active_displays(adev); diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c index caae54487f9c..633dab14f51c 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c @@ -3892,40 +3892,6 @@ static int si_set_boot_state(struct amdgpu_device *adev) } #endif -static int si_set_powergating_by_smu(void *handle, - uint32_t block_type, - bool gate) -{ - struct amdgpu_device *adev = (struct amdgpu_device *)handle; - - switch (block_type) { - case AMD_IP_BLOCK_TYPE_UVD: - if (!gate) { - adev->pm.dpm.uvd_active = true; - adev->pm.dpm.state = POWER_STATE_TYPE_INTERNAL_UVD; - } else { - adev->pm.dpm.uvd_active = false; - } - - amdgpu_legacy_dpm_compute_clocks(handle); - break; - case AMD_IP_BLOCK_TYPE_VCE: - if (!gate) { - adev->pm.dpm.vce_active = true; - /* XXX select vce level based on ring/task */ - adev->pm.dpm.vce_level = AMD_VCE_LEVEL_AC_ALL; - } else { - adev->pm.dpm.vce_active = false; - } - - amdgpu_legacy_dpm_compute_clocks(handle); - break; - default: - break; - } - return 0; -} - static int si_set_sw_state(struct amdgpu_device *adev) { return (amdgpu_si_send_msg_to_smc(adev, PPSMC_MSG_SwitchToSwState) == PPSMC_Result_OK) ? @@ -8125,7 +8091,6 @@ static const struct amd_pm_funcs si_dpm_funcs = { .print_power_state = &si_dpm_print_power_state, .debugfs_print_current_performance_level = &si_dpm_debugfs_print_current_performance_level, .force_performance_level = &si_dpm_force_performance_level, - .set_powergating_by_smu = &si_set_powergating_by_smu, .vblank_too_short = &si_dpm_vblank_too_short, .set_fan_control_mode = &si_dpm_set_fan_control_mode, .get_fan_control_mode = &si_dpm_get_fan_control_mode, diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c index a2da46bf3985..71e9c6ce6b1a 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c @@ -1487,16 +1487,6 @@ static void pp_pm_compute_clocks(void *handle) { struct pp_hwmgr *hwmgr = handle; struct amdgpu_device *adev = hwmgr->adev; - int i = 0; - - if (adev->mode_info.num_crtc) - amdgpu_display_bandwidth_update(adev); - - for (i = 0; i < AMDGPU_MAX_RINGS; i++) { - struct amdgpu_ring *ring = adev->rings[i]; - if (ring && ring->sched.ready) - amdgpu_fence_wait_empty(ring); - } if (!amdgpu_device_has_dc_support(adev)) { amdgpu_dpm_get_active_displays(adev); diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c index f4df344509a8..9a2cfab3a177 100644 --- a/drivers/gpu/drm/drm_of.c +++ b/drivers/gpu/drm/drm_of.c @@ -214,29 +214,6 @@ int drm_of_encoder_active_endpoint(struct device_node *node, } EXPORT_SYMBOL_GPL(drm_of_encoder_active_endpoint); -static int find_panel_or_bridge(struct device_node *node, - struct drm_panel **panel, - struct drm_bridge **bridge) -{ - if (panel) { - *panel = of_drm_find_panel(node); - if (!IS_ERR(*panel)) - return 0; - - /* Clear the panel pointer in case of error. */ - *panel = NULL; - } - - /* No panel found yet, check for a bridge next. */ - if (bridge) { - *bridge = of_drm_find_bridge(node); - if (*bridge) - return 0; - } - - return -EPROBE_DEFER; -} - /** * drm_of_find_panel_or_bridge - return connected panel or bridge device * @np: device tree node containing encoder output ports @@ -259,44 +236,49 @@ int drm_of_find_panel_or_bridge(const struct device_node *np, struct drm_panel **panel, struct drm_bridge **bridge) { - struct device_node *node; - int ret; + int ret = -EPROBE_DEFER; + struct device_node *remote; if (!panel && !bridge) return -EINVAL; - if (panel) *panel = NULL; - if (bridge) - *bridge = NULL; - - /* Check for a graph on the device node first. */ - if (of_graph_is_present(np)) { - node = of_graph_get_remote_node(np, port, endpoint); - if (node) { - ret = find_panel_or_bridge(node, panel, bridge); - of_node_put(node); - - if (!ret) - return 0; - } - } - /* Otherwise check for any child node other than port/ports. */ - for_each_available_child_of_node(np, node) { - if (of_node_name_eq(node, "port") || - of_node_name_eq(node, "ports")) - continue; + /* + * of_graph_get_remote_node() produces a noisy error message if port + * node isn't found and the absence of the port is a legit case here, + * so at first we silently check whether graph presents in the + * device-tree node. + */ + if (!of_graph_is_present(np)) + return -ENODEV; - ret = find_panel_or_bridge(node, panel, bridge); - of_node_put(node); + remote = of_graph_get_remote_node(np, port, endpoint); + if (!remote) + return -ENODEV; + + if (panel) { + *panel = of_drm_find_panel(remote); + if (!IS_ERR(*panel)) + ret = 0; + else + *panel = NULL; + } + + /* No panel found yet, check for a bridge next. */ + if (bridge) { + if (ret) { + *bridge = of_drm_find_bridge(remote); + if (*bridge) + ret = 0; + } else { + *bridge = NULL; + } - /* Stop at the first found occurrence. */ - if (!ret) - return 0; } - return -EPROBE_DEFER; + of_node_put(remote); + return ret; } EXPORT_SYMBOL_GPL(drm_of_find_panel_or_bridge); diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index d667657e3606..f868db8be02a 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -4383,13 +4383,20 @@ intel_dp_update_420(struct intel_dp *intel_dp) static void intel_dp_set_edid(struct intel_dp *intel_dp) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); struct intel_connector *connector = intel_dp->attached_connector; struct edid *edid; + bool vrr_capable; intel_dp_unset_edid(intel_dp); edid = intel_dp_get_edid(intel_dp); connector->detect_edid = edid; + vrr_capable = intel_vrr_is_capable(&connector->base); + drm_dbg_kms(&i915->drm, "[CONNECTOR:%d:%s] VRR capable: %s\n", + connector->base.base.id, connector->base.name, str_yes_no(vrr_capable)); + drm_connector_set_vrr_capable_property(&connector->base, vrr_capable); + intel_dp_update_dfp(intel_dp, edid); intel_dp_update_420(intel_dp); @@ -4422,6 +4429,9 @@ intel_dp_unset_edid(struct intel_dp *intel_dp) intel_dp->dfp.ycbcr_444_to_420 = false; connector->base.ycbcr_420_allowed = false; + + drm_connector_set_vrr_capable_property(&connector->base, + false); } static int @@ -4572,14 +4582,9 @@ static int intel_dp_get_modes(struct drm_connector *connector) int num_modes = 0; edid = intel_connector->detect_edid; - if (edid) { + if (edid) num_modes = intel_connector_update_modes(connector, edid); - if (intel_vrr_is_capable(connector)) - drm_connector_set_vrr_capable_property(connector, - true); - } - /* Also add fixed mode, which may or may not be present in EDID */ if (intel_dp_is_edp(intel_attached_dp(intel_connector)) && intel_connector->panel.fixed_mode) { diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c index 97cf3cac0105..fb6cf30ee628 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c @@ -97,6 +97,14 @@ #define INTEL_EDP_BRIGHTNESS_OPTIMIZATION_1 0x359 +enum intel_dp_aux_backlight_modparam { + INTEL_DP_AUX_BACKLIGHT_AUTO = -1, + INTEL_DP_AUX_BACKLIGHT_OFF = 0, + INTEL_DP_AUX_BACKLIGHT_ON = 1, + INTEL_DP_AUX_BACKLIGHT_FORCE_VESA = 2, + INTEL_DP_AUX_BACKLIGHT_FORCE_INTEL = 3, +}; + /* Intel EDP backlight callbacks */ static bool intel_dp_aux_supports_hdr_backlight(struct intel_connector *connector) @@ -126,6 +134,24 @@ intel_dp_aux_supports_hdr_backlight(struct intel_connector *connector) return false; } + /* + * If we don't have HDR static metadata there is no way to + * runtime detect used range for nits based control. For now + * do not use Intel proprietary eDP backlight control if we + * don't have this data in panel EDID. In case we find panel + * which supports only nits based control, but doesn't provide + * HDR static metadata we need to start maintaining table of + * ranges for such panels. + */ + if (i915->params.enable_dpcd_backlight != INTEL_DP_AUX_BACKLIGHT_FORCE_INTEL && + !(connector->base.hdr_sink_metadata.hdmi_type1.metadata_type & + BIT(HDMI_STATIC_METADATA_TYPE1))) { + drm_info(&i915->drm, + "Panel is missing HDR static metadata. Possible support for Intel HDR backlight interface is not used. If your backlight controls don't work try booting with i915.enable_dpcd_backlight=%d. needs this, please file a _new_ bug report on drm/i915, see " FDO_BUG_URL " for details.\n", + INTEL_DP_AUX_BACKLIGHT_FORCE_INTEL); + return false; + } + panel->backlight.edp.intel.sdr_uses_aux = tcon_cap[2] & INTEL_EDP_SDR_TCON_BRIGHTNESS_AUX_CAP; @@ -413,14 +439,6 @@ static const struct intel_panel_bl_funcs intel_dp_vesa_bl_funcs = { .get = intel_dp_aux_vesa_get_backlight, }; -enum intel_dp_aux_backlight_modparam { - INTEL_DP_AUX_BACKLIGHT_AUTO = -1, - INTEL_DP_AUX_BACKLIGHT_OFF = 0, - INTEL_DP_AUX_BACKLIGHT_ON = 1, - INTEL_DP_AUX_BACKLIGHT_FORCE_VESA = 2, - INTEL_DP_AUX_BACKLIGHT_FORCE_INTEL = 3, -}; - int intel_dp_aux_init_backlight_funcs(struct intel_connector *connector) { struct drm_device *dev = connector->base.dev; diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c index 87f4af3fd523..3e61a8936245 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.c +++ b/drivers/gpu/drm/i915/display/intel_fbc.c @@ -1037,7 +1037,7 @@ static int intel_fbc_check_plane(struct intel_atomic_state *state, struct intel_plane_state *plane_state = intel_atomic_get_new_plane_state(state, plane); const struct drm_framebuffer *fb = plane_state->hw.fb; - struct intel_crtc *crtc = to_intel_crtc(plane_state->uapi.crtc); + struct intel_crtc *crtc = to_intel_crtc(plane_state->hw.crtc); const struct intel_crtc_state *crtc_state; struct intel_fbc *fbc = plane->fbc; diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index bff8c2d73cdf..6c9e6e7f0afd 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -887,6 +887,20 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp, return false; } + /* Wa_16011303918:adl-p */ + if (crtc_state->vrr.enable && + IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0)) { + drm_dbg_kms(&dev_priv->drm, + "PSR2 not enabled, not compatible with HW stepping + VRR\n"); + return false; + } + + if (!_compute_psr2_sdp_prior_scanline_indication(intel_dp, crtc_state)) { + drm_dbg_kms(&dev_priv->drm, + "PSR2 not enabled, PSR2 SDP indication do not fit in hblank\n"); + return false; + } + if (HAS_PSR2_SEL_FETCH(dev_priv)) { if (!intel_psr2_sel_fetch_config_valid(intel_dp, crtc_state) && !HAS_PSR_HW_TRACKING(dev_priv)) { @@ -900,12 +914,12 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp, if (!crtc_state->enable_psr2_sel_fetch && IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_C0)) { drm_dbg_kms(&dev_priv->drm, "PSR2 HW tracking is not supported this Display stepping\n"); - return false; + goto unsupported; } if (!psr2_granularity_check(intel_dp, crtc_state)) { drm_dbg_kms(&dev_priv->drm, "PSR2 not enabled, SU granularity not compatible\n"); - return false; + goto unsupported; } if (!crtc_state->enable_psr2_sel_fetch && @@ -914,25 +928,15 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp, "PSR2 not enabled, resolution %dx%d > max supported %dx%d\n", crtc_hdisplay, crtc_vdisplay, psr_max_h, psr_max_v); - return false; - } - - if (!_compute_psr2_sdp_prior_scanline_indication(intel_dp, crtc_state)) { - drm_dbg_kms(&dev_priv->drm, - "PSR2 not enabled, PSR2 SDP indication do not fit in hblank\n"); - return false; - } - - /* Wa_16011303918:adl-p */ - if (crtc_state->vrr.enable && - IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0)) { - drm_dbg_kms(&dev_priv->drm, - "PSR2 not enabled, not compatible with HW stepping + VRR\n"); - return false; + goto unsupported; } tgl_dc3co_exitline_compute_config(intel_dp, crtc_state); return true; + +unsupported: + crtc_state->enable_psr2_sel_fetch = false; + return false; } void intel_psr_compute_config(struct intel_dp *intel_dp, diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 3c87d77d2cf6..a9354f8f110d 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -4345,12 +4345,12 @@ #define _DSPAADDR 0x70184 #define _DSPASTRIDE 0x70188 #define _DSPAPOS 0x7018C /* reserved */ -#define DISP_POS_Y_MASK REG_GENMASK(31, 0) +#define DISP_POS_Y_MASK REG_GENMASK(31, 16) #define DISP_POS_Y(y) REG_FIELD_PREP(DISP_POS_Y_MASK, (y)) #define DISP_POS_X_MASK REG_GENMASK(15, 0) #define DISP_POS_X(x) REG_FIELD_PREP(DISP_POS_X_MASK, (x)) #define _DSPASIZE 0x70190 -#define DISP_HEIGHT_MASK REG_GENMASK(31, 0) +#define DISP_HEIGHT_MASK REG_GENMASK(31, 16) #define DISP_HEIGHT(h) REG_FIELD_PREP(DISP_HEIGHT_MASK, (h)) #define DISP_WIDTH_MASK REG_GENMASK(15, 0) #define DISP_WIDTH(w) REG_FIELD_PREP(DISP_WIDTH_MASK, (w)) @@ -5152,7 +5152,7 @@ #define _SEL_FETCH_PLANE_BASE_6_A 0x70940 #define _SEL_FETCH_PLANE_BASE_7_A 0x70960 #define _SEL_FETCH_PLANE_BASE_CUR_A 0x70880 -#define _SEL_FETCH_PLANE_BASE_1_B 0x70990 +#define _SEL_FETCH_PLANE_BASE_1_B 0x71890 #define _SEL_FETCH_PLANE_BASE_A(plane) _PICK(plane, \ _SEL_FETCH_PLANE_BASE_1_A, \ diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 9c36b505daab..affa95eb05fc 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -274,7 +274,7 @@ bool msm_use_mmu(struct drm_device *dev) struct msm_drm_private *priv = dev->dev_private; /* a2xx comes with its own MMU */ - return priv->is_a2xx || device_iommu_mapped(dev->dev); + return priv->is_a2xx || iommu_present(&platform_bus_type); } static int msm_init_vram(struct drm_device *dev) diff --git a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c index 46029c5610c8..145047e19394 100644 --- a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c +++ b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c @@ -229,7 +229,7 @@ static void rpi_touchscreen_i2c_write(struct rpi_touchscreen *ts, ret = i2c_smbus_write_byte_data(ts->i2c, reg, val); if (ret) - dev_err(&ts->dsi->dev, "I2C write failed: %d\n", ret); + dev_err(&ts->i2c->dev, "I2C write failed: %d\n", ret); } static int rpi_touchscreen_write(struct rpi_touchscreen *ts, u16 reg, u32 val) @@ -265,7 +265,7 @@ static int rpi_touchscreen_noop(struct drm_panel *panel) return 0; } -static int rpi_touchscreen_enable(struct drm_panel *panel) +static int rpi_touchscreen_prepare(struct drm_panel *panel) { struct rpi_touchscreen *ts = panel_to_ts(panel); int i; @@ -295,6 +295,13 @@ static int rpi_touchscreen_enable(struct drm_panel *panel) rpi_touchscreen_write(ts, DSI_STARTDSI, 0x01); msleep(100); + return 0; +} + +static int rpi_touchscreen_enable(struct drm_panel *panel) +{ + struct rpi_touchscreen *ts = panel_to_ts(panel); + /* Turn on the backlight. */ rpi_touchscreen_i2c_write(ts, REG_PWM, 255); @@ -349,7 +356,7 @@ static int rpi_touchscreen_get_modes(struct drm_panel *panel, static const struct drm_panel_funcs rpi_touchscreen_funcs = { .disable = rpi_touchscreen_disable, .unprepare = rpi_touchscreen_noop, - .prepare = rpi_touchscreen_noop, + .prepare = rpi_touchscreen_prepare, .enable = rpi_touchscreen_enable, .get_modes = rpi_touchscreen_get_modes, }; diff --git a/drivers/gpu/drm/radeon/radeon_sync.c b/drivers/gpu/drm/radeon/radeon_sync.c index b991ba1bcd51..f63efd8d5e52 100644 --- a/drivers/gpu/drm/radeon/radeon_sync.c +++ b/drivers/gpu/drm/radeon/radeon_sync.c @@ -96,7 +96,7 @@ int radeon_sync_resv(struct radeon_device *rdev, struct dma_fence *f; int r = 0; - dma_resv_for_each_fence(&cursor, resv, shared, f) { + dma_resv_for_each_fence(&cursor, resv, !shared, f) { fence = to_radeon_fence(f); if (fence && fence->rdev == rdev) radeon_sync_fence(sync, fence); diff --git a/drivers/gpu/drm/sun4i/sun4i_frontend.c b/drivers/gpu/drm/sun4i/sun4i_frontend.c index 56ae38389db0..462fae73eae9 100644 --- a/drivers/gpu/drm/sun4i/sun4i_frontend.c +++ b/drivers/gpu/drm/sun4i/sun4i_frontend.c @@ -222,13 +222,11 @@ void sun4i_frontend_update_buffer(struct sun4i_frontend *frontend, /* Set the physical address of the buffer in memory */ paddr = drm_fb_cma_get_gem_addr(fb, state, 0); - paddr -= PHYS_OFFSET; DRM_DEBUG_DRIVER("Setting buffer #0 address to %pad\n", &paddr); regmap_write(frontend->regs, SUN4I_FRONTEND_BUF_ADDR0_REG, paddr); if (fb->format->num_planes > 1) { paddr = drm_fb_cma_get_gem_addr(fb, state, swap ? 2 : 1); - paddr -= PHYS_OFFSET; DRM_DEBUG_DRIVER("Setting buffer #1 address to %pad\n", &paddr); regmap_write(frontend->regs, SUN4I_FRONTEND_BUF_ADDR1_REG, paddr); @@ -236,7 +234,6 @@ void sun4i_frontend_update_buffer(struct sun4i_frontend *frontend, if (fb->format->num_planes > 2) { paddr = drm_fb_cma_get_gem_addr(fb, state, swap ? 1 : 2); - paddr -= PHYS_OFFSET; DRM_DEBUG_DRIVER("Setting buffer #2 address to %pad\n", &paddr); regmap_write(frontend->regs, SUN4I_FRONTEND_BUF_ADDR2_REG, paddr); diff --git a/drivers/gpu/drm/vc4/Kconfig b/drivers/gpu/drm/vc4/Kconfig index de3424fed2fc..6cf2621786e6 100644 --- a/drivers/gpu/drm/vc4/Kconfig +++ b/drivers/gpu/drm/vc4/Kconfig @@ -2,6 +2,9 @@ config DRM_VC4 tristate "Broadcom VC4 Graphics" depends on ARCH_BCM || ARCH_BCM2835 || COMPILE_TEST + # Make sure not 'y' when RASPBERRYPI_FIRMWARE is 'm'. This can only + # happen when COMPILE_TEST=y, hence the added !RASPBERRYPI_FIRMWARE. + depends on RASPBERRYPI_FIRMWARE || (COMPILE_TEST && !RASPBERRYPI_FIRMWARE) depends on DRM depends on SND && SND_SOC depends on COMMON_CLK diff --git a/drivers/gpu/drm/vc4/vc4_dsi.c b/drivers/gpu/drm/vc4/vc4_dsi.c index 752f921735c6..98308a17e4ed 100644 --- a/drivers/gpu/drm/vc4/vc4_dsi.c +++ b/drivers/gpu/drm/vc4/vc4_dsi.c @@ -846,7 +846,7 @@ static void vc4_dsi_encoder_enable(struct drm_encoder *encoder) unsigned long phy_clock; int ret; - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret) { DRM_ERROR("Failed to runtime PM enable on DSI%d\n", dsi->variant->port); return; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index 31aecc46624b..04c8a378aeed 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -46,6 +46,21 @@ vmw_buffer_object(struct ttm_buffer_object *bo) return container_of(bo, struct vmw_buffer_object, base); } +/** + * bo_is_vmw - check if the buffer object is a &vmw_buffer_object + * @bo: ttm buffer object to be checked + * + * Uses destroy function associated with the object to determine if this is + * a &vmw_buffer_object. + * + * Returns: + * true if the object is of &vmw_buffer_object type, false if not. + */ +static bool bo_is_vmw(struct ttm_buffer_object *bo) +{ + return bo->destroy == &vmw_bo_bo_free || + bo->destroy == &vmw_gem_destroy; +} /** * vmw_bo_pin_in_placement - Validate a buffer to placement. @@ -615,8 +630,9 @@ int vmw_user_bo_synccpu_ioctl(struct drm_device *dev, void *data, ret = vmw_user_bo_synccpu_grab(vbo, arg->flags); vmw_bo_unreference(&vbo); - if (unlikely(ret != 0 && ret != -ERESTARTSYS && - ret != -EBUSY)) { + if (unlikely(ret != 0)) { + if (ret == -ERESTARTSYS || ret == -EBUSY) + return -EBUSY; DRM_ERROR("Failed synccpu grab on handle 0x%08x.\n", (unsigned int) arg->handle); return ret; @@ -798,7 +814,7 @@ int vmw_dumb_create(struct drm_file *file_priv, void vmw_bo_swap_notify(struct ttm_buffer_object *bo) { /* Is @bo embedded in a struct vmw_buffer_object? */ - if (vmw_bo_is_vmw_bo(bo)) + if (!bo_is_vmw(bo)) return; /* Kill any cached kernel maps before swapout */ @@ -822,7 +838,7 @@ void vmw_bo_move_notify(struct ttm_buffer_object *bo, struct vmw_buffer_object *vbo; /* Make sure @bo is embedded in a struct vmw_buffer_object? */ - if (vmw_bo_is_vmw_bo(bo)) + if (!bo_is_vmw(bo)) return; vbo = container_of(bo, struct vmw_buffer_object, base); @@ -843,22 +859,3 @@ void vmw_bo_move_notify(struct ttm_buffer_object *bo, if (mem->mem_type != VMW_PL_MOB && bo->resource->mem_type == VMW_PL_MOB) vmw_resource_unbind_list(vbo); } - -/** - * vmw_bo_is_vmw_bo - check if the buffer object is a &vmw_buffer_object - * @bo: buffer object to be checked - * - * Uses destroy function associated with the object to determine if this is - * a &vmw_buffer_object. - * - * Returns: - * true if the object is of &vmw_buffer_object type, false if not. - */ -bool vmw_bo_is_vmw_bo(struct ttm_buffer_object *bo) -{ - if (bo->destroy == &vmw_bo_bo_free || - bo->destroy == &vmw_gem_destroy) - return true; - - return false; -} diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 26eb5478394a..163c00793eb1 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -998,13 +998,10 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) goto out_no_fman; } - drm_vma_offset_manager_init(&dev_priv->vma_manager, - DRM_FILE_PAGE_OFFSET_START, - DRM_FILE_PAGE_OFFSET_SIZE); ret = ttm_device_init(&dev_priv->bdev, &vmw_bo_driver, dev_priv->drm.dev, dev_priv->drm.anon_inode->i_mapping, - &dev_priv->vma_manager, + dev_priv->drm.vma_offset_manager, dev_priv->map_mode == vmw_dma_alloc_coherent, false); if (unlikely(ret != 0)) { @@ -1174,7 +1171,6 @@ static void vmw_driver_unload(struct drm_device *dev) vmw_devcaps_destroy(dev_priv); vmw_vram_manager_fini(dev_priv); ttm_device_fini(&dev_priv->bdev); - drm_vma_offset_manager_destroy(&dev_priv->vma_manager); vmw_release_device_late(dev_priv); vmw_fence_manager_takedown(dev_priv->fman); if (dev_priv->capabilities & SVGA_CAP_IRQMASK) @@ -1398,7 +1394,7 @@ vmw_get_unmapped_area(struct file *file, unsigned long uaddr, struct vmw_private *dev_priv = vmw_priv(file_priv->minor->dev); return drm_get_unmapped_area(file, uaddr, len, pgoff, flags, - &dev_priv->vma_manager); + dev_priv->drm.vma_offset_manager); } static int vmwgfx_pm_notifier(struct notifier_block *nb, unsigned long val, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index 00e8e27e4884..ace7ca150b03 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -683,6 +683,9 @@ static void vmw_user_surface_base_release(struct ttm_base_object **p_base) container_of(base, struct vmw_user_surface, prime.base); struct vmw_resource *res = &user_srf->srf.res; + if (base->shareable && res && res->backup) + drm_gem_object_put(&res->backup->base.base); + *p_base = NULL; vmw_resource_unreference(&res); } @@ -857,6 +860,7 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data, goto out_unlock; } vmw_bo_reference(res->backup); + drm_gem_object_get(&res->backup->base.base); } tmp = vmw_resource_reference(&srf->res); @@ -1513,7 +1517,6 @@ vmw_gb_surface_define_internal(struct drm_device *dev, &res->backup); if (ret == 0) vmw_bo_reference(res->backup); - } if (unlikely(ret != 0)) { @@ -1561,6 +1564,8 @@ vmw_gb_surface_define_internal(struct drm_device *dev, drm_vma_node_offset_addr(&res->backup->base.base.vma_node); rep->buffer_size = res->backup->base.base.size; rep->buffer_handle = backup_handle; + if (user_srf->prime.base.shareable) + drm_gem_object_get(&res->backup->base.base); } else { rep->buffer_map_handle = 0; rep->buffer_size = 0; diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index b7640cfe0020..47551ab73ca8 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -69,7 +69,12 @@ static unsigned int preferred_states_mask; static struct cpuidle_device __percpu *intel_idle_cpuidle_devices; static unsigned long auto_demotion_disable_flags; -static bool disable_promotion_to_c1e; + +static enum { + C1E_PROMOTION_PRESERVE, + C1E_PROMOTION_ENABLE, + C1E_PROMOTION_DISABLE +} c1e_promotion = C1E_PROMOTION_PRESERVE; struct idle_cpu { struct cpuidle_state *state_table; @@ -1398,8 +1403,6 @@ static inline void intel_idle_init_cstates_acpi(struct cpuidle_driver *drv) { } static inline bool intel_idle_off_by_default(u32 mwait_hint) { return false; } #endif /* !CONFIG_ACPI_PROCESSOR_CSTATE */ -static void c1e_promotion_enable(void); - /** * ivt_idle_state_table_update - Tune the idle states table for Ivy Town. * @@ -1578,17 +1581,14 @@ static void __init spr_idle_state_table_update(void) unsigned long long msr; /* Check if user prefers C1E over C1. */ - if (preferred_states_mask & BIT(2)) { - if (preferred_states_mask & BIT(1)) - /* Both can't be enabled, stick to the defaults. */ - return; - + if ((preferred_states_mask & BIT(2)) && + !(preferred_states_mask & BIT(1))) { + /* Disable C1 and enable C1E. */ spr_cstates[0].flags |= CPUIDLE_FLAG_UNUSABLE; spr_cstates[1].flags &= ~CPUIDLE_FLAG_UNUSABLE; /* Enable C1E using the "C1E promotion" bit. */ - c1e_promotion_enable(); - disable_promotion_to_c1e = false; + c1e_promotion = C1E_PROMOTION_ENABLE; } /* @@ -1754,7 +1754,9 @@ static int intel_idle_cpu_init(unsigned int cpu) if (auto_demotion_disable_flags) auto_demotion_disable(); - if (disable_promotion_to_c1e) + if (c1e_promotion == C1E_PROMOTION_ENABLE) + c1e_promotion_enable(); + else if (c1e_promotion == C1E_PROMOTION_DISABLE) c1e_promotion_disable(); return 0; @@ -1833,7 +1835,8 @@ static int __init intel_idle_init(void) if (icpu) { cpuidle_state_table = icpu->state_table; auto_demotion_disable_flags = icpu->auto_demotion_disable_flags; - disable_promotion_to_c1e = icpu->disable_promotion_to_c1e; + if (icpu->disable_promotion_to_c1e) + c1e_promotion = C1E_PROMOTION_DISABLE; if (icpu->use_acpi || force_use_acpi) intel_idle_acpi_cst_extract(); } else if (!intel_idle_acpi_cst_extract()) { diff --git a/drivers/iio/adc/ad7280a.c b/drivers/iio/adc/ad7280a.c index ef9d27759961..ec9acbf12b9a 100644 --- a/drivers/iio/adc/ad7280a.c +++ b/drivers/iio/adc/ad7280a.c @@ -745,7 +745,7 @@ static int ad7280a_write_thresh(struct iio_dev *indio_dev, case IIO_EV_DIR_RISING: addr = AD7280A_CELL_OVERVOLTAGE_REG; ret = ad7280_write(st, AD7280A_DEVADDR_MASTER, addr, - 1, val); + 1, value); if (ret) break; st->cell_threshhigh = value; @@ -753,7 +753,7 @@ static int ad7280a_write_thresh(struct iio_dev *indio_dev, case IIO_EV_DIR_FALLING: addr = AD7280A_CELL_UNDERVOLTAGE_REG; ret = ad7280_write(st, AD7280A_DEVADDR_MASTER, addr, - 1, val); + 1, value); if (ret) break; st->cell_threshlow = value; @@ -770,18 +770,18 @@ static int ad7280a_write_thresh(struct iio_dev *indio_dev, case IIO_EV_DIR_RISING: addr = AD7280A_AUX_ADC_OVERVOLTAGE_REG; ret = ad7280_write(st, AD7280A_DEVADDR_MASTER, addr, - 1, val); + 1, value); if (ret) break; - st->aux_threshhigh = val; + st->aux_threshhigh = value; break; case IIO_EV_DIR_FALLING: addr = AD7280A_AUX_ADC_UNDERVOLTAGE_REG; ret = ad7280_write(st, AD7280A_DEVADDR_MASTER, addr, - 1, val); + 1, value); if (ret) break; - st->aux_threshlow = val; + st->aux_threshlow = value; break; default: ret = -EINVAL; diff --git a/drivers/iio/chemical/scd4x.c b/drivers/iio/chemical/scd4x.c index 20d4e7584e92..37143b5526ee 100644 --- a/drivers/iio/chemical/scd4x.c +++ b/drivers/iio/chemical/scd4x.c @@ -471,12 +471,15 @@ static ssize_t calibration_forced_value_store(struct device *dev, ret = scd4x_write_and_fetch(state, CMD_FRC, arg, &val, sizeof(val)); mutex_unlock(&state->lock); + if (ret) + return ret; + if (val == 0xff) { dev_err(dev, "forced calibration has failed"); return -EINVAL; } - return ret ?: len; + return len; } static IIO_DEVICE_ATTR_RW(calibration_auto_enable, 0); diff --git a/drivers/iio/dac/ad3552r.c b/drivers/iio/dac/ad3552r.c index 97f13c0b9631..d5ea1a1be122 100644 --- a/drivers/iio/dac/ad3552r.c +++ b/drivers/iio/dac/ad3552r.c @@ -656,7 +656,7 @@ static int ad3552r_reset(struct ad3552r_desc *dac) { struct reg_addr_pool addr; int ret; - u16 val; + int val; dac->gpio_reset = devm_gpiod_get_optional(&dac->spi->dev, "reset", GPIOD_OUT_LOW); @@ -809,10 +809,10 @@ static int ad3552r_configure_custom_gain(struct ad3552r_desc *dac, gain_child = fwnode_get_named_child_node(child, "custom-output-range-config"); - if (IS_ERR(gain_child)) { + if (!gain_child) { dev_err(dev, "mandatory custom-output-range-config property missing\n"); - return PTR_ERR(gain_child); + return -EINVAL; } dac->ch_data[ch].range_override = 1; diff --git a/drivers/iio/dac/ad5446.c b/drivers/iio/dac/ad5446.c index 14cfabacbea5..fdf824041497 100644 --- a/drivers/iio/dac/ad5446.c +++ b/drivers/iio/dac/ad5446.c @@ -178,7 +178,7 @@ static int ad5446_read_raw(struct iio_dev *indio_dev, switch (m) { case IIO_CHAN_INFO_RAW: - *val = st->cached_val; + *val = st->cached_val >> chan->scan_type.shift; return IIO_VAL_INT; case IIO_CHAN_INFO_SCALE: *val = st->vref_mv; diff --git a/drivers/iio/dac/ad5592r-base.c b/drivers/iio/dac/ad5592r-base.c index a424b7220b61..4434c1b2a322 100644 --- a/drivers/iio/dac/ad5592r-base.c +++ b/drivers/iio/dac/ad5592r-base.c @@ -522,7 +522,7 @@ static int ad5592r_alloc_channels(struct iio_dev *iio_dev) if (!ret) st->channel_modes[reg] = tmp; - fwnode_property_read_u32(child, "adi,off-state", &tmp); + ret = fwnode_property_read_u32(child, "adi,off-state", &tmp); if (!ret) st->channel_offstate[reg] = tmp; } diff --git a/drivers/iio/dac/ltc2688.c b/drivers/iio/dac/ltc2688.c index e41861d29767..2f9c384885f4 100644 --- a/drivers/iio/dac/ltc2688.c +++ b/drivers/iio/dac/ltc2688.c @@ -298,7 +298,7 @@ static int ltc2688_read_raw(struct iio_dev *indio_dev, if (ret) return ret; - *val = 16; + *val2 = 16; return IIO_VAL_FRACTIONAL_LOG2; case IIO_CHAN_INFO_CALIBBIAS: ret = regmap_read(st->regmap, diff --git a/drivers/iio/dac/ti-dac5571.c b/drivers/iio/dac/ti-dac5571.c index 4a3b8d875518..0b775f943db3 100644 --- a/drivers/iio/dac/ti-dac5571.c +++ b/drivers/iio/dac/ti-dac5571.c @@ -19,6 +19,7 @@ #include <linux/i2c.h> #include <linux/module.h> #include <linux/mod_devicetable.h> +#include <linux/property.h> #include <linux/regulator/consumer.h> enum chip_id { @@ -311,6 +312,7 @@ static int dac5571_probe(struct i2c_client *client, const struct dac5571_spec *spec; struct dac5571_data *data; struct iio_dev *indio_dev; + enum chip_id chip_id; int ret, i; indio_dev = devm_iio_device_alloc(dev, sizeof(*data)); @@ -326,7 +328,13 @@ static int dac5571_probe(struct i2c_client *client, indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->channels = dac5571_channels; - spec = &dac5571_spec[id->driver_data]; + if (dev_fwnode(dev)) + chip_id = (uintptr_t)device_get_match_data(dev); + else + chip_id = id->driver_data; + + spec = &dac5571_spec[chip_id]; + indio_dev->num_channels = spec->num_channels; data->spec = spec; @@ -385,15 +393,15 @@ static int dac5571_remove(struct i2c_client *i2c) } static const struct of_device_id dac5571_of_id[] = { - {.compatible = "ti,dac5571"}, - {.compatible = "ti,dac6571"}, - {.compatible = "ti,dac7571"}, - {.compatible = "ti,dac5574"}, - {.compatible = "ti,dac6574"}, - {.compatible = "ti,dac7574"}, - {.compatible = "ti,dac5573"}, - {.compatible = "ti,dac6573"}, - {.compatible = "ti,dac7573"}, + {.compatible = "ti,dac5571", .data = (void *)single_8bit}, + {.compatible = "ti,dac6571", .data = (void *)single_10bit}, + {.compatible = "ti,dac7571", .data = (void *)single_12bit}, + {.compatible = "ti,dac5574", .data = (void *)quad_8bit}, + {.compatible = "ti,dac6574", .data = (void *)quad_10bit}, + {.compatible = "ti,dac7574", .data = (void *)quad_12bit}, + {.compatible = "ti,dac5573", .data = (void *)quad_8bit}, + {.compatible = "ti,dac6573", .data = (void *)quad_10bit}, + {.compatible = "ti,dac7573", .data = (void *)quad_12bit}, {} }; MODULE_DEVICE_TABLE(of, dac5571_of_id); diff --git a/drivers/iio/filter/Kconfig b/drivers/iio/filter/Kconfig index 3ae35817ad82..a85b345ea14e 100644 --- a/drivers/iio/filter/Kconfig +++ b/drivers/iio/filter/Kconfig @@ -8,6 +8,7 @@ menu "Filters" config ADMV8818 tristate "Analog Devices ADMV8818 High-Pass and Low-Pass Filter" depends on SPI && COMMON_CLK && 64BIT + select REGMAP_SPI help Say yes here to build support for Analog Devices ADMV8818 2 GHz to 18 GHz, Digitally Tunable, High-Pass and Low-Pass Filter. diff --git a/drivers/iio/imu/bmi160/bmi160_core.c b/drivers/iio/imu/bmi160/bmi160_core.c index 824b5124a5f5..01336105792e 100644 --- a/drivers/iio/imu/bmi160/bmi160_core.c +++ b/drivers/iio/imu/bmi160/bmi160_core.c @@ -730,7 +730,7 @@ static int bmi160_chip_init(struct bmi160_data *data, bool use_spi) ret = regmap_write(data->regmap, BMI160_REG_CMD, BMI160_CMD_SOFTRESET); if (ret) - return ret; + goto disable_regulator; usleep_range(BMI160_SOFTRESET_USLEEP, BMI160_SOFTRESET_USLEEP + 1); @@ -741,29 +741,37 @@ static int bmi160_chip_init(struct bmi160_data *data, bool use_spi) if (use_spi) { ret = regmap_read(data->regmap, BMI160_REG_DUMMY, &val); if (ret) - return ret; + goto disable_regulator; } ret = regmap_read(data->regmap, BMI160_REG_CHIP_ID, &val); if (ret) { dev_err(dev, "Error reading chip id\n"); - return ret; + goto disable_regulator; } if (val != BMI160_CHIP_ID_VAL) { dev_err(dev, "Wrong chip id, got %x expected %x\n", val, BMI160_CHIP_ID_VAL); - return -ENODEV; + ret = -ENODEV; + goto disable_regulator; } ret = bmi160_set_mode(data, BMI160_ACCEL, true); if (ret) - return ret; + goto disable_regulator; ret = bmi160_set_mode(data, BMI160_GYRO, true); if (ret) - return ret; + goto disable_accel; return 0; + +disable_accel: + bmi160_set_mode(data, BMI160_ACCEL, false); + +disable_regulator: + regulator_bulk_disable(ARRAY_SIZE(data->supplies), data->supplies); + return ret; } static int bmi160_data_rdy_trigger_set_state(struct iio_trigger *trig, diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_i2c.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_i2c.c index 33d9afb1ba91..d4a692b838d0 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_i2c.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_i2c.c @@ -18,12 +18,15 @@ static int inv_icm42600_i2c_bus_setup(struct inv_icm42600_state *st) unsigned int mask, val; int ret; - /* setup interface registers */ - ret = regmap_update_bits(st->map, INV_ICM42600_REG_INTF_CONFIG6, - INV_ICM42600_INTF_CONFIG6_MASK, - INV_ICM42600_INTF_CONFIG6_I3C_EN); - if (ret) - return ret; + /* + * setup interface registers + * This register write to REG_INTF_CONFIG6 enables a spike filter that + * is impacting the line and can prevent the I2C ACK to be seen by the + * controller. So we don't test the return value. + */ + regmap_update_bits(st->map, INV_ICM42600_REG_INTF_CONFIG6, + INV_ICM42600_INTF_CONFIG6_MASK, + INV_ICM42600_INTF_CONFIG6_I3C_EN); ret = regmap_update_bits(st->map, INV_ICM42600_REG_INTF_CONFIG4, INV_ICM42600_INTF_CONFIG4_I3C_BUS_ONLY, 0); diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c index 088f748b683e..2432e697150c 100644 --- a/drivers/iio/magnetometer/ak8975.c +++ b/drivers/iio/magnetometer/ak8975.c @@ -416,6 +416,7 @@ static int ak8975_power_on(const struct ak8975_data *data) if (ret) { dev_warn(&data->client->dev, "Failed to enable specified Vid supply\n"); + regulator_disable(data->vdd); return ret; } diff --git a/drivers/iio/proximity/sx9324.c b/drivers/iio/proximity/sx9324.c index 0d9bbbb50cb4..70c37f664f6d 100644 --- a/drivers/iio/proximity/sx9324.c +++ b/drivers/iio/proximity/sx9324.c @@ -70,13 +70,17 @@ #define SX9324_REG_AFE_PH2 0x2a #define SX9324_REG_AFE_PH3 0x2b #define SX9324_REG_AFE_CTRL8 0x2c -#define SX9324_REG_AFE_CTRL8_RESFILTN_4KOHM 0x02 +#define SX9324_REG_AFE_CTRL8_RESERVED 0x10 +#define SX9324_REG_AFE_CTRL8_RESFILTIN_4KOHM 0x02 #define SX9324_REG_AFE_CTRL9 0x2d #define SX9324_REG_AFE_CTRL9_AGAIN_1 0x08 #define SX9324_REG_PROX_CTRL0 0x30 #define SX9324_REG_PROX_CTRL0_GAIN_MASK GENMASK(5, 3) -#define SX9324_REG_PROX_CTRL0_GAIN_1 0x80 +#define SX9324_REG_PROX_CTRL0_GAIN_SHIFT 3 +#define SX9324_REG_PROX_CTRL0_GAIN_RSVD 0x0 +#define SX9324_REG_PROX_CTRL0_GAIN_1 0x1 +#define SX9324_REG_PROX_CTRL0_GAIN_8 0x4 #define SX9324_REG_PROX_CTRL0_RAWFILT_MASK GENMASK(2, 0) #define SX9324_REG_PROX_CTRL0_RAWFILT_1P50 0x01 #define SX9324_REG_PROX_CTRL1 0x31 @@ -379,7 +383,14 @@ static int sx9324_read_gain(struct sx_common_data *data, if (ret) return ret; - *val = 1 << FIELD_GET(SX9324_REG_PROX_CTRL0_GAIN_MASK, regval); + regval = FIELD_GET(SX9324_REG_PROX_CTRL0_GAIN_MASK, regval); + if (regval) + regval--; + else if (regval == SX9324_REG_PROX_CTRL0_GAIN_RSVD || + regval > SX9324_REG_PROX_CTRL0_GAIN_8) + return -EINVAL; + + *val = 1 << regval; return IIO_VAL_INT; } @@ -725,8 +736,12 @@ static int sx9324_write_gain(struct sx_common_data *data, unsigned int gain, reg; int ret; - gain = ilog2(val); reg = SX9324_REG_PROX_CTRL0 + chan->channel / 2; + + gain = ilog2(val) + 1; + if (val <= 0 || gain > SX9324_REG_PROX_CTRL0_GAIN_8) + return -EINVAL; + gain = FIELD_PREP(SX9324_REG_PROX_CTRL0_GAIN_MASK, gain); mutex_lock(&data->mutex); @@ -781,12 +796,15 @@ static const struct sx_common_reg_default sx9324_default_regs[] = { { SX9324_REG_AFE_PH2, 0x1a }, { SX9324_REG_AFE_PH3, 0x16 }, - { SX9324_REG_AFE_CTRL8, SX9324_REG_AFE_CTRL8_RESFILTN_4KOHM }, + { SX9324_REG_AFE_CTRL8, SX9324_REG_AFE_CTRL8_RESERVED | + SX9324_REG_AFE_CTRL8_RESFILTIN_4KOHM }, { SX9324_REG_AFE_CTRL9, SX9324_REG_AFE_CTRL9_AGAIN_1 }, - { SX9324_REG_PROX_CTRL0, SX9324_REG_PROX_CTRL0_GAIN_1 | + { SX9324_REG_PROX_CTRL0, + SX9324_REG_PROX_CTRL0_GAIN_1 << SX9324_REG_PROX_CTRL0_GAIN_SHIFT | SX9324_REG_PROX_CTRL0_RAWFILT_1P50 }, - { SX9324_REG_PROX_CTRL1, SX9324_REG_PROX_CTRL0_GAIN_1 | + { SX9324_REG_PROX_CTRL1, + SX9324_REG_PROX_CTRL0_GAIN_1 << SX9324_REG_PROX_CTRL0_GAIN_SHIFT | SX9324_REG_PROX_CTRL0_RAWFILT_1P50 }, { SX9324_REG_PROX_CTRL2, SX9324_REG_PROX_CTRL2_AVGNEG_THRESH_16K }, { SX9324_REG_PROX_CTRL3, SX9324_REG_PROX_CTRL3_AVGDEB_2SAMPLES | diff --git a/drivers/iio/proximity/sx_common.c b/drivers/iio/proximity/sx_common.c index a7c07316a0a9..8ad814d96b7e 100644 --- a/drivers/iio/proximity/sx_common.c +++ b/drivers/iio/proximity/sx_common.c @@ -521,6 +521,7 @@ int sx_common_probe(struct i2c_client *client, return dev_err_probe(dev, ret, "error reading WHOAMI\n"); ACPI_COMPANION_SET(&indio_dev->dev, ACPI_COMPANION(dev)); + indio_dev->dev.of_node = client->dev.of_node; indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->channels = data->chip_info->iio_channels; diff --git a/drivers/input/keyboard/cypress-sf.c b/drivers/input/keyboard/cypress-sf.c index c28996028e80..9a23eed6a4f4 100644 --- a/drivers/input/keyboard/cypress-sf.c +++ b/drivers/input/keyboard/cypress-sf.c @@ -61,6 +61,14 @@ static irqreturn_t cypress_sf_irq_handler(int irq, void *devid) return IRQ_HANDLED; } +static void cypress_sf_disable_regulators(void *arg) +{ + struct cypress_sf_data *touchkey = arg; + + regulator_bulk_disable(ARRAY_SIZE(touchkey->regulators), + touchkey->regulators); +} + static int cypress_sf_probe(struct i2c_client *client) { struct cypress_sf_data *touchkey; @@ -121,6 +129,12 @@ static int cypress_sf_probe(struct i2c_client *client) return error; } + error = devm_add_action_or_reset(&client->dev, + cypress_sf_disable_regulators, + touchkey); + if (error) + return error; + touchkey->input_dev = devm_input_allocate_device(&client->dev); if (!touchkey->input_dev) { dev_err(&client->dev, "Failed to allocate input device\n"); diff --git a/drivers/input/keyboard/omap4-keypad.c b/drivers/input/keyboard/omap4-keypad.c index 43375b38ee59..8a7ce41b8c56 100644 --- a/drivers/input/keyboard/omap4-keypad.c +++ b/drivers/input/keyboard/omap4-keypad.c @@ -393,7 +393,7 @@ static int omap4_keypad_probe(struct platform_device *pdev) * revision register. */ error = pm_runtime_get_sync(dev); - if (error) { + if (error < 0) { dev_err(dev, "pm_runtime_get_sync() failed\n"); pm_runtime_put_noidle(dev); return error; diff --git a/drivers/interconnect/qcom/sc7180.c b/drivers/interconnect/qcom/sc7180.c index 12d59c36df53..5f7c0f85fa8e 100644 --- a/drivers/interconnect/qcom/sc7180.c +++ b/drivers/interconnect/qcom/sc7180.c @@ -47,7 +47,6 @@ DEFINE_QNODE(qnm_mnoc_sf, SC7180_MASTER_MNOC_SF_MEM_NOC, 1, 32, SC7180_SLAVE_GEM DEFINE_QNODE(qnm_snoc_gc, SC7180_MASTER_SNOC_GC_MEM_NOC, 1, 8, SC7180_SLAVE_LLCC); DEFINE_QNODE(qnm_snoc_sf, SC7180_MASTER_SNOC_SF_MEM_NOC, 1, 16, SC7180_SLAVE_LLCC); DEFINE_QNODE(qxm_gpu, SC7180_MASTER_GFX3D, 2, 32, SC7180_SLAVE_GEM_NOC_SNOC, SC7180_SLAVE_LLCC); -DEFINE_QNODE(ipa_core_master, SC7180_MASTER_IPA_CORE, 1, 8, SC7180_SLAVE_IPA_CORE); DEFINE_QNODE(llcc_mc, SC7180_MASTER_LLCC, 2, 4, SC7180_SLAVE_EBI1); DEFINE_QNODE(qhm_mnoc_cfg, SC7180_MASTER_CNOC_MNOC_CFG, 1, 4, SC7180_SLAVE_SERVICE_MNOC); DEFINE_QNODE(qxm_camnoc_hf0, SC7180_MASTER_CAMNOC_HF0, 2, 32, SC7180_SLAVE_MNOC_HF_MEM_NOC); @@ -129,7 +128,6 @@ DEFINE_QNODE(qhs_mdsp_ms_mpu_cfg, SC7180_SLAVE_MSS_PROC_MS_MPU_CFG, 1, 4); DEFINE_QNODE(qns_gem_noc_snoc, SC7180_SLAVE_GEM_NOC_SNOC, 1, 8, SC7180_MASTER_GEM_NOC_SNOC); DEFINE_QNODE(qns_llcc, SC7180_SLAVE_LLCC, 1, 16, SC7180_MASTER_LLCC); DEFINE_QNODE(srvc_gemnoc, SC7180_SLAVE_SERVICE_GEM_NOC, 1, 4); -DEFINE_QNODE(ipa_core_slave, SC7180_SLAVE_IPA_CORE, 1, 8); DEFINE_QNODE(ebi, SC7180_SLAVE_EBI1, 2, 4); DEFINE_QNODE(qns_mem_noc_hf, SC7180_SLAVE_MNOC_HF_MEM_NOC, 1, 32, SC7180_MASTER_MNOC_HF_MEM_NOC); DEFINE_QNODE(qns_mem_noc_sf, SC7180_SLAVE_MNOC_SF_MEM_NOC, 1, 32, SC7180_MASTER_MNOC_SF_MEM_NOC); @@ -160,7 +158,6 @@ DEFINE_QBCM(bcm_mc0, "MC0", true, &ebi); DEFINE_QBCM(bcm_sh0, "SH0", true, &qns_llcc); DEFINE_QBCM(bcm_mm0, "MM0", false, &qns_mem_noc_hf); DEFINE_QBCM(bcm_ce0, "CE0", false, &qxm_crypto); -DEFINE_QBCM(bcm_ip0, "IP0", false, &ipa_core_slave); DEFINE_QBCM(bcm_cn0, "CN0", true, &qnm_snoc, &xm_qdss_dap, &qhs_a1_noc_cfg, &qhs_a2_noc_cfg, &qhs_ahb2phy0, &qhs_aop, &qhs_aoss, &qhs_boot_rom, &qhs_camera_cfg, &qhs_camera_nrt_throttle_cfg, &qhs_camera_rt_throttle_cfg, &qhs_clk_ctl, &qhs_cpr_cx, &qhs_cpr_mx, &qhs_crypto0_cfg, &qhs_dcc_cfg, &qhs_ddrss_cfg, &qhs_display_cfg, &qhs_display_rt_throttle_cfg, &qhs_display_throttle_cfg, &qhs_glm, &qhs_gpuss_cfg, &qhs_imem_cfg, &qhs_ipa, &qhs_mnoc_cfg, &qhs_mss_cfg, &qhs_npu_cfg, &qhs_npu_dma_throttle_cfg, &qhs_npu_dsp_throttle_cfg, &qhs_pimem_cfg, &qhs_prng, &qhs_qdss_cfg, &qhs_qm_cfg, &qhs_qm_mpu_cfg, &qhs_qup0, &qhs_qup1, &qhs_security, &qhs_snoc_cfg, &qhs_tcsr, &qhs_tlmm_1, &qhs_tlmm_2, &qhs_tlmm_3, &qhs_ufs_mem_cfg, &qhs_usb3, &qhs_venus_cfg, &qhs_venus_throttle_cfg, &qhs_vsense_ctrl_cfg, &srvc_cnoc); DEFINE_QBCM(bcm_mm1, "MM1", false, &qxm_camnoc_hf0_uncomp, &qxm_camnoc_hf1_uncomp, &qxm_camnoc_sf_uncomp, &qhm_mnoc_cfg, &qxm_mdp0, &qxm_rot, &qxm_venus0, &qxm_venus_arm9); DEFINE_QBCM(bcm_sh2, "SH2", false, &acm_sys_tcu); @@ -372,22 +369,6 @@ static struct qcom_icc_desc sc7180_gem_noc = { .num_bcms = ARRAY_SIZE(gem_noc_bcms), }; -static struct qcom_icc_bcm *ipa_virt_bcms[] = { - &bcm_ip0, -}; - -static struct qcom_icc_node *ipa_virt_nodes[] = { - [MASTER_IPA_CORE] = &ipa_core_master, - [SLAVE_IPA_CORE] = &ipa_core_slave, -}; - -static struct qcom_icc_desc sc7180_ipa_virt = { - .nodes = ipa_virt_nodes, - .num_nodes = ARRAY_SIZE(ipa_virt_nodes), - .bcms = ipa_virt_bcms, - .num_bcms = ARRAY_SIZE(ipa_virt_bcms), -}; - static struct qcom_icc_bcm *mc_virt_bcms[] = { &bcm_acv, &bcm_mc0, @@ -519,8 +500,6 @@ static const struct of_device_id qnoc_of_match[] = { .data = &sc7180_dc_noc}, { .compatible = "qcom,sc7180-gem-noc", .data = &sc7180_gem_noc}, - { .compatible = "qcom,sc7180-ipa-virt", - .data = &sc7180_ipa_virt}, { .compatible = "qcom,sc7180-mc-virt", .data = &sc7180_mc_virt}, { .compatible = "qcom,sc7180-mmss-noc", diff --git a/drivers/interconnect/qcom/sdx55.c b/drivers/interconnect/qcom/sdx55.c index 03d604f84cc5..e3ac25a997b7 100644 --- a/drivers/interconnect/qcom/sdx55.c +++ b/drivers/interconnect/qcom/sdx55.c @@ -18,7 +18,6 @@ #include "icc-rpmh.h" #include "sdx55.h" -DEFINE_QNODE(ipa_core_master, SDX55_MASTER_IPA_CORE, 1, 8, SDX55_SLAVE_IPA_CORE); DEFINE_QNODE(llcc_mc, SDX55_MASTER_LLCC, 4, 4, SDX55_SLAVE_EBI_CH0); DEFINE_QNODE(acm_tcu, SDX55_MASTER_TCU_0, 1, 8, SDX55_SLAVE_LLCC, SDX55_SLAVE_MEM_NOC_SNOC, SDX55_SLAVE_MEM_NOC_PCIE_SNOC); DEFINE_QNODE(qnm_snoc_gc, SDX55_MASTER_SNOC_GC_MEM_NOC, 1, 8, SDX55_SLAVE_LLCC); @@ -40,7 +39,6 @@ DEFINE_QNODE(xm_pcie, SDX55_MASTER_PCIE, 1, 8, SDX55_SLAVE_ANOC_SNOC); DEFINE_QNODE(xm_qdss_etr, SDX55_MASTER_QDSS_ETR, 1, 8, SDX55_SLAVE_SNOC_CFG, SDX55_SLAVE_EMAC_CFG, SDX55_SLAVE_USB3, SDX55_SLAVE_AOSS, SDX55_SLAVE_SPMI_FETCHER, SDX55_SLAVE_QDSS_CFG, SDX55_SLAVE_PDM, SDX55_SLAVE_SNOC_MEM_NOC_GC, SDX55_SLAVE_TCSR, SDX55_SLAVE_CNOC_DDRSS, SDX55_SLAVE_SPMI_VGI_COEX, SDX55_SLAVE_QPIC, SDX55_SLAVE_OCIMEM, SDX55_SLAVE_IPA_CFG, SDX55_SLAVE_USB3_PHY_CFG, SDX55_SLAVE_AOP, SDX55_SLAVE_BLSP_1, SDX55_SLAVE_SDCC_1, SDX55_SLAVE_CNOC_MSS, SDX55_SLAVE_PCIE_PARF, SDX55_SLAVE_ECC_CFG, SDX55_SLAVE_AUDIO, SDX55_SLAVE_AOSS, SDX55_SLAVE_PRNG, SDX55_SLAVE_CRYPTO_0_CFG, SDX55_SLAVE_TCU, SDX55_SLAVE_CLK_CTL, SDX55_SLAVE_IMEM_CFG); DEFINE_QNODE(xm_sdc1, SDX55_MASTER_SDCC_1, 1, 8, SDX55_SLAVE_AOSS, SDX55_SLAVE_IPA_CFG, SDX55_SLAVE_ANOC_SNOC, SDX55_SLAVE_AOP, SDX55_SLAVE_AUDIO); DEFINE_QNODE(xm_usb3, SDX55_MASTER_USB3, 1, 8, SDX55_SLAVE_ANOC_SNOC); -DEFINE_QNODE(ipa_core_slave, SDX55_SLAVE_IPA_CORE, 1, 8); DEFINE_QNODE(ebi, SDX55_SLAVE_EBI_CH0, 1, 4); DEFINE_QNODE(qns_llcc, SDX55_SLAVE_LLCC, 1, 16, SDX55_SLAVE_EBI_CH0); DEFINE_QNODE(qns_memnoc_snoc, SDX55_SLAVE_MEM_NOC_SNOC, 1, 8, SDX55_MASTER_MEM_NOC_SNOC); @@ -82,7 +80,6 @@ DEFINE_QNODE(xs_sys_tcu_cfg, SDX55_SLAVE_TCU, 1, 8); DEFINE_QBCM(bcm_mc0, "MC0", true, &ebi); DEFINE_QBCM(bcm_sh0, "SH0", true, &qns_llcc); DEFINE_QBCM(bcm_ce0, "CE0", false, &qxm_crypto); -DEFINE_QBCM(bcm_ip0, "IP0", false, &ipa_core_slave); DEFINE_QBCM(bcm_pn0, "PN0", false, &qhm_snoc_cfg); DEFINE_QBCM(bcm_sh3, "SH3", false, &xm_apps_rdwr); DEFINE_QBCM(bcm_sh4, "SH4", false, &qns_memnoc_snoc, &qns_sys_pcie); @@ -219,22 +216,6 @@ static const struct qcom_icc_desc sdx55_system_noc = { .num_bcms = ARRAY_SIZE(system_noc_bcms), }; -static struct qcom_icc_bcm *ipa_virt_bcms[] = { - &bcm_ip0, -}; - -static struct qcom_icc_node *ipa_virt_nodes[] = { - [MASTER_IPA_CORE] = &ipa_core_master, - [SLAVE_IPA_CORE] = &ipa_core_slave, -}; - -static const struct qcom_icc_desc sdx55_ipa_virt = { - .nodes = ipa_virt_nodes, - .num_nodes = ARRAY_SIZE(ipa_virt_nodes), - .bcms = ipa_virt_bcms, - .num_bcms = ARRAY_SIZE(ipa_virt_bcms), -}; - static const struct of_device_id qnoc_of_match[] = { { .compatible = "qcom,sdx55-mc-virt", .data = &sdx55_mc_virt}, @@ -242,8 +223,6 @@ static const struct of_device_id qnoc_of_match[] = { .data = &sdx55_mem_noc}, { .compatible = "qcom,sdx55-system-noc", .data = &sdx55_system_noc}, - { .compatible = "qcom,sdx55-ipa-virt", - .data = &sdx55_ipa_virt}, { } }; MODULE_DEVICE_TABLE(of, qnoc_of_match); diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index 7c2ca52ca3e4..df5347ea450b 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -771,12 +771,12 @@ static void journal_write_unlocked(struct closure *cl) bio_reset(bio, ca->bdev, REQ_OP_WRITE | REQ_SYNC | REQ_META | REQ_PREFLUSH | REQ_FUA); - bch_bio_map(bio, w->data); bio->bi_iter.bi_sector = PTR_OFFSET(k, i); bio->bi_iter.bi_size = sectors << 9; bio->bi_end_io = journal_write_endio; bio->bi_private = w; + bch_bio_map(bio, w->data); trace_bcache_journal_write(bio, w->data->keys); bio_list_add(&list, bio); diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index fdd0194f84dd..320fcdfef48e 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -685,7 +685,7 @@ static void do_bio_hook(struct search *s, { struct bio *bio = &s->bio.bio; - bio_init_clone(bio->bi_bdev, bio, orig_bio, GFP_NOIO); + bio_init_clone(orig_bio->bi_bdev, bio, orig_bio, GFP_NOIO); /* * bi_end_io can be set separately somewhere else, e.g. the * variants in, diff --git a/drivers/memory/renesas-rpc-if.c b/drivers/memory/renesas-rpc-if.c index 2e545f473cc6..019a0822bde0 100644 --- a/drivers/memory/renesas-rpc-if.c +++ b/drivers/memory/renesas-rpc-if.c @@ -164,25 +164,39 @@ static const struct regmap_access_table rpcif_volatile_table = { /* - * Custom accessor functions to ensure SMRDR0 and SMWDR0 are always accessed - * with proper width. Requires SMENR_SPIDE to be correctly set before! + * Custom accessor functions to ensure SM[RW]DR[01] are always accessed with + * proper width. Requires rpcif.xfer_size to be correctly set before! */ static int rpcif_reg_read(void *context, unsigned int reg, unsigned int *val) { struct rpcif *rpc = context; - if (reg == RPCIF_SMRDR0 || reg == RPCIF_SMWDR0) { - u32 spide = readl(rpc->base + RPCIF_SMENR) & RPCIF_SMENR_SPIDE(0xF); - - if (spide == 0x8) { + switch (reg) { + case RPCIF_SMRDR0: + case RPCIF_SMWDR0: + switch (rpc->xfer_size) { + case 1: *val = readb(rpc->base + reg); return 0; - } else if (spide == 0xC) { + + case 2: *val = readw(rpc->base + reg); return 0; - } else if (spide != 0xF) { + + case 4: + case 8: + *val = readl(rpc->base + reg); + return 0; + + default: return -EILSEQ; } + + case RPCIF_SMRDR1: + case RPCIF_SMWDR1: + if (rpc->xfer_size != 8) + return -EILSEQ; + break; } *val = readl(rpc->base + reg); @@ -193,18 +207,34 @@ static int rpcif_reg_write(void *context, unsigned int reg, unsigned int val) { struct rpcif *rpc = context; - if (reg == RPCIF_SMRDR0 || reg == RPCIF_SMWDR0) { - u32 spide = readl(rpc->base + RPCIF_SMENR) & RPCIF_SMENR_SPIDE(0xF); - - if (spide == 0x8) { + switch (reg) { + case RPCIF_SMWDR0: + switch (rpc->xfer_size) { + case 1: writeb(val, rpc->base + reg); return 0; - } else if (spide == 0xC) { + + case 2: writew(val, rpc->base + reg); return 0; - } else if (spide != 0xF) { + + case 4: + case 8: + writel(val, rpc->base + reg); + return 0; + + default: return -EILSEQ; } + + case RPCIF_SMWDR1: + if (rpc->xfer_size != 8) + return -EILSEQ; + break; + + case RPCIF_SMRDR0: + case RPCIF_SMRDR1: + return -EPERM; } writel(val, rpc->base + reg); @@ -469,6 +499,7 @@ int rpcif_manual_xfer(struct rpcif *rpc) smenr |= RPCIF_SMENR_SPIDE(rpcif_bits_set(rpc, nbytes)); regmap_write(rpc->regmap, RPCIF_SMENR, smenr); + rpc->xfer_size = nbytes; memcpy(data, rpc->buffer + pos, nbytes); if (nbytes == 8) { @@ -533,6 +564,7 @@ int rpcif_manual_xfer(struct rpcif *rpc) regmap_write(rpc->regmap, RPCIF_SMENR, smenr); regmap_write(rpc->regmap, RPCIF_SMCR, rpc->smcr | RPCIF_SMCR_SPIE); + rpc->xfer_size = nbytes; ret = wait_msg_xfer_end(rpc); if (ret) goto err_out; diff --git a/drivers/misc/eeprom/at25.c b/drivers/misc/eeprom/at25.c index 91f96abbb3f9..8d169a35cf13 100644 --- a/drivers/misc/eeprom/at25.c +++ b/drivers/misc/eeprom/at25.c @@ -31,6 +31,8 @@ */ #define FM25_SN_LEN 8 /* serial number length */ +#define EE_MAXADDRLEN 3 /* 24 bit addresses, up to 2 MBytes */ + struct at25_data { struct spi_eeprom chip; struct spi_device *spi; @@ -39,6 +41,7 @@ struct at25_data { struct nvmem_config nvmem_config; struct nvmem_device *nvmem; u8 sernum[FM25_SN_LEN]; + u8 command[EE_MAXADDRLEN + 1]; }; #define AT25_WREN 0x06 /* latch the write enable */ @@ -61,8 +64,6 @@ struct at25_data { #define FM25_ID_LEN 9 /* ID length */ -#define EE_MAXADDRLEN 3 /* 24 bit addresses, up to 2 MBytes */ - /* * Specs often allow 5ms for a page write, sometimes 20ms; * it's important to recover from write timeouts. @@ -78,7 +79,6 @@ static int at25_ee_read(void *priv, unsigned int offset, { struct at25_data *at25 = priv; char *buf = val; - u8 command[EE_MAXADDRLEN + 1]; u8 *cp; ssize_t status; struct spi_transfer t[2]; @@ -92,12 +92,15 @@ static int at25_ee_read(void *priv, unsigned int offset, if (unlikely(!count)) return -EINVAL; - cp = command; + cp = at25->command; instr = AT25_READ; if (at25->chip.flags & EE_INSTR_BIT3_IS_ADDR) if (offset >= BIT(at25->addrlen * 8)) instr |= AT25_INSTR_BIT3; + + mutex_lock(&at25->lock); + *cp++ = instr; /* 8/16/24-bit address is written MSB first */ @@ -116,7 +119,7 @@ static int at25_ee_read(void *priv, unsigned int offset, spi_message_init(&m); memset(t, 0, sizeof(t)); - t[0].tx_buf = command; + t[0].tx_buf = at25->command; t[0].len = at25->addrlen + 1; spi_message_add_tail(&t[0], &m); @@ -124,8 +127,6 @@ static int at25_ee_read(void *priv, unsigned int offset, t[1].len = count; spi_message_add_tail(&t[1], &m); - mutex_lock(&at25->lock); - /* * Read it all at once. * @@ -152,7 +153,7 @@ static int fm25_aux_read(struct at25_data *at25, u8 *buf, uint8_t command, spi_message_init(&m); memset(t, 0, sizeof(t)); - t[0].tx_buf = &command; + t[0].tx_buf = at25->command; t[0].len = 1; spi_message_add_tail(&t[0], &m); @@ -162,6 +163,8 @@ static int fm25_aux_read(struct at25_data *at25, u8 *buf, uint8_t command, mutex_lock(&at25->lock); + at25->command[0] = command; + status = spi_sync(at25->spi, &m); dev_dbg(&at25->spi->dev, "read %d aux bytes --> %d\n", len, status); diff --git a/drivers/mtd/nand/raw/mtk_ecc.c b/drivers/mtd/nand/raw/mtk_ecc.c index e7df3dac705e..49ab3448b9b1 100644 --- a/drivers/mtd/nand/raw/mtk_ecc.c +++ b/drivers/mtd/nand/raw/mtk_ecc.c @@ -43,6 +43,7 @@ struct mtk_ecc_caps { u32 err_mask; + u32 err_shift; const u8 *ecc_strength; const u32 *ecc_regs; u8 num_ecc_strength; @@ -76,7 +77,7 @@ static const u8 ecc_strength_mt2712[] = { }; static const u8 ecc_strength_mt7622[] = { - 4, 6, 8, 10, 12, 14, 16 + 4, 6, 8, 10, 12 }; enum mtk_ecc_regs { @@ -221,7 +222,7 @@ void mtk_ecc_get_stats(struct mtk_ecc *ecc, struct mtk_ecc_stats *stats, for (i = 0; i < sectors; i++) { offset = (i >> 2) << 2; err = readl(ecc->regs + ECC_DECENUM0 + offset); - err = err >> ((i % 4) * 8); + err = err >> ((i % 4) * ecc->caps->err_shift); err &= ecc->caps->err_mask; if (err == ecc->caps->err_mask) { /* uncorrectable errors */ @@ -449,6 +450,7 @@ EXPORT_SYMBOL(mtk_ecc_get_parity_bits); static const struct mtk_ecc_caps mtk_ecc_caps_mt2701 = { .err_mask = 0x3f, + .err_shift = 8, .ecc_strength = ecc_strength_mt2701, .ecc_regs = mt2701_ecc_regs, .num_ecc_strength = 20, @@ -459,6 +461,7 @@ static const struct mtk_ecc_caps mtk_ecc_caps_mt2701 = { static const struct mtk_ecc_caps mtk_ecc_caps_mt2712 = { .err_mask = 0x7f, + .err_shift = 8, .ecc_strength = ecc_strength_mt2712, .ecc_regs = mt2712_ecc_regs, .num_ecc_strength = 23, @@ -468,10 +471,11 @@ static const struct mtk_ecc_caps mtk_ecc_caps_mt2712 = { }; static const struct mtk_ecc_caps mtk_ecc_caps_mt7622 = { - .err_mask = 0x3f, + .err_mask = 0x1f, + .err_shift = 5, .ecc_strength = ecc_strength_mt7622, .ecc_regs = mt7622_ecc_regs, - .num_ecc_strength = 7, + .num_ecc_strength = 5, .ecc_mode_shift = 4, .parity_bits = 13, .pg_irq_sel = 0, diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c index 1a77542c6d67..048b255faa76 100644 --- a/drivers/mtd/nand/raw/qcom_nandc.c +++ b/drivers/mtd/nand/raw/qcom_nandc.c @@ -2651,10 +2651,23 @@ static int qcom_nand_attach_chip(struct nand_chip *chip) ecc->engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; mtd_set_ooblayout(mtd, &qcom_nand_ooblayout_ops); + /* Free the initially allocated BAM transaction for reading the ONFI params */ + if (nandc->props->is_bam) + free_bam_transaction(nandc); nandc->max_cwperpage = max_t(unsigned int, nandc->max_cwperpage, cwperpage); + /* Now allocate the BAM transaction based on updated max_cwperpage */ + if (nandc->props->is_bam) { + nandc->bam_txn = alloc_bam_transaction(nandc); + if (!nandc->bam_txn) { + dev_err(nandc->dev, + "failed to allocate bam transaction\n"); + return -ENOMEM; + } + } + /* * DATA_UD_BYTES varies based on whether the read/write command protects * spare data with ECC too. We protect spare data by default, so we set @@ -2955,17 +2968,6 @@ static int qcom_nand_host_init_and_register(struct qcom_nand_controller *nandc, if (ret) return ret; - if (nandc->props->is_bam) { - free_bam_transaction(nandc); - nandc->bam_txn = alloc_bam_transaction(nandc); - if (!nandc->bam_txn) { - dev_err(nandc->dev, - "failed to allocate bam transaction\n"); - nand_cleanup(chip); - return -ENOMEM; - } - } - ret = mtd_device_parse_register(mtd, probes, NULL, NULL, 0); if (ret) nand_cleanup(chip); diff --git a/drivers/mtd/nand/raw/sh_flctl.c b/drivers/mtd/nand/raw/sh_flctl.c index b85b9c6fcc42..a278829469d6 100644 --- a/drivers/mtd/nand/raw/sh_flctl.c +++ b/drivers/mtd/nand/raw/sh_flctl.c @@ -384,7 +384,8 @@ static int flctl_dma_fifo0_transfer(struct sh_flctl *flctl, unsigned long *buf, dma_addr_t dma_addr; dma_cookie_t cookie; uint32_t reg; - int ret; + int ret = 0; + unsigned long time_left; if (dir == DMA_FROM_DEVICE) { chan = flctl->chan_fifo0_rx; @@ -425,13 +426,14 @@ static int flctl_dma_fifo0_transfer(struct sh_flctl *flctl, unsigned long *buf, goto out; } - ret = + time_left = wait_for_completion_timeout(&flctl->dma_complete, msecs_to_jiffies(3000)); - if (ret <= 0) { + if (time_left == 0) { dmaengine_terminate_all(chan); dev_err(&flctl->pdev->dev, "wait_for_completion_timeout\n"); + ret = -ETIMEDOUT; } out: @@ -441,7 +443,7 @@ out: dma_unmap_single(chan->device->dev, dma_addr, len, dir); - /* ret > 0 is success */ + /* ret == 0 is success */ return ret; } @@ -465,7 +467,7 @@ static void read_fiforeg(struct sh_flctl *flctl, int rlen, int offset) /* initiate DMA transfer */ if (flctl->chan_fifo0_rx && rlen >= 32 && - flctl_dma_fifo0_transfer(flctl, buf, rlen, DMA_FROM_DEVICE) > 0) + !flctl_dma_fifo0_transfer(flctl, buf, rlen, DMA_FROM_DEVICE)) goto convert; /* DMA success */ /* do polling transfer */ @@ -524,7 +526,7 @@ static void write_ec_fiforeg(struct sh_flctl *flctl, int rlen, /* initiate DMA transfer */ if (flctl->chan_fifo0_tx && rlen >= 32 && - flctl_dma_fifo0_transfer(flctl, buf, rlen, DMA_TO_DEVICE) > 0) + !flctl_dma_fifo0_transfer(flctl, buf, rlen, DMA_TO_DEVICE)) return; /* DMA success */ /* do polling transfer */ diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 15eddca7b4b6..38e152548126 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4027,14 +4027,19 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, const v return true; } -static u32 bond_ip_hash(u32 hash, struct flow_keys *flow) +static u32 bond_ip_hash(u32 hash, struct flow_keys *flow, int xmit_policy) { hash ^= (__force u32)flow_get_u32_dst(flow) ^ (__force u32)flow_get_u32_src(flow); hash ^= (hash >> 16); hash ^= (hash >> 8); + /* discard lowest hash bit to deal with the common even ports pattern */ - return hash >> 1; + if (xmit_policy == BOND_XMIT_POLICY_LAYER34 || + xmit_policy == BOND_XMIT_POLICY_ENCAP34) + return hash >> 1; + + return hash; } /* Generate hash based on xmit policy. If @skb is given it is used to linearize @@ -4064,7 +4069,7 @@ static u32 __bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, const voi memcpy(&hash, &flow.ports.ports, sizeof(hash)); } - return bond_ip_hash(hash, &flow); + return bond_ip_hash(hash, &flow, bond->params.xmit_policy); } /** @@ -5259,7 +5264,7 @@ static u32 bond_sk_hash_l34(struct sock *sk) /* L4 */ memcpy(&hash, &flow.ports.ports, sizeof(hash)); /* L3 */ - return bond_ip_hash(hash, &flow); + return bond_ip_hash(hash, &flow, BOND_XMIT_POLICY_LAYER34); } static struct net_device *__bond_sk_get_lower_dev(struct bonding *bond, diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index a416240d001b..12c15da55664 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -1681,9 +1681,6 @@ static void gswip_phylink_mac_config(struct dsa_switch *ds, int port, break; case PHY_INTERFACE_MODE_RMII: miicfg |= GSWIP_MII_CFG_MODE_RMIIM; - - /* Configure the RMII clock as output: */ - miicfg |= GSWIP_MII_CFG_RMII_CLK; break; case PHY_INTERFACE_MODE_RGMII: case PHY_INTERFACE_MODE_RGMII_ID: diff --git a/drivers/net/dsa/mv88e6xxx/port_hidden.c b/drivers/net/dsa/mv88e6xxx/port_hidden.c index b49d05f0e117..7a9f9ff6dedf 100644 --- a/drivers/net/dsa/mv88e6xxx/port_hidden.c +++ b/drivers/net/dsa/mv88e6xxx/port_hidden.c @@ -40,8 +40,9 @@ int mv88e6xxx_port_hidden_wait(struct mv88e6xxx_chip *chip) { int bit = __bf_shf(MV88E6XXX_PORT_RESERVED_1A_BUSY); - return mv88e6xxx_wait_bit(chip, MV88E6XXX_PORT_RESERVED_1A_CTRL_PORT, - MV88E6XXX_PORT_RESERVED_1A, bit, 0); + return mv88e6xxx_port_wait_bit(chip, + MV88E6XXX_PORT_RESERVED_1A_CTRL_PORT, + MV88E6XXX_PORT_RESERVED_1A, bit, 0); } int mv88e6xxx_port_hidden_read(struct mv88e6xxx_chip *chip, int block, int port, diff --git a/drivers/net/dsa/realtek/realtek-mdio.c b/drivers/net/dsa/realtek/realtek-mdio.c index 31e1f100e48e..c58f49d558d2 100644 --- a/drivers/net/dsa/realtek/realtek-mdio.c +++ b/drivers/net/dsa/realtek/realtek-mdio.c @@ -267,7 +267,6 @@ static const struct of_device_id realtek_mdio_of_match[] = { #endif #if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8365MB) { .compatible = "realtek,rtl8365mb", .data = &rtl8365mb_variant, }, - { .compatible = "realtek,rtl8367s", .data = &rtl8365mb_variant, }, #endif { /* sentinel */ }, }; diff --git a/drivers/net/dsa/realtek/realtek-smi.c b/drivers/net/dsa/realtek/realtek-smi.c index 6cec559c90ce..45992f79ec8d 100644 --- a/drivers/net/dsa/realtek/realtek-smi.c +++ b/drivers/net/dsa/realtek/realtek-smi.c @@ -551,10 +551,6 @@ static const struct of_device_id realtek_smi_of_match[] = { .compatible = "realtek,rtl8365mb", .data = &rtl8365mb_variant, }, - { - .compatible = "realtek,rtl8367s", - .data = &rtl8365mb_variant, - }, #endif { /* sentinel */ }, }; diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index bd4cb9d7c35d..827993022386 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -35,15 +35,6 @@ source "drivers/net/ethernet/aquantia/Kconfig" source "drivers/net/ethernet/arc/Kconfig" source "drivers/net/ethernet/asix/Kconfig" source "drivers/net/ethernet/atheros/Kconfig" -source "drivers/net/ethernet/broadcom/Kconfig" -source "drivers/net/ethernet/brocade/Kconfig" -source "drivers/net/ethernet/cadence/Kconfig" -source "drivers/net/ethernet/calxeda/Kconfig" -source "drivers/net/ethernet/cavium/Kconfig" -source "drivers/net/ethernet/chelsio/Kconfig" -source "drivers/net/ethernet/cirrus/Kconfig" -source "drivers/net/ethernet/cisco/Kconfig" -source "drivers/net/ethernet/cortina/Kconfig" config CX_ECAT tristate "Beckhoff CX5020 EtherCAT master support" @@ -57,6 +48,14 @@ config CX_ECAT To compile this driver as a module, choose M here. The module will be called ec_bhf. +source "drivers/net/ethernet/broadcom/Kconfig" +source "drivers/net/ethernet/cadence/Kconfig" +source "drivers/net/ethernet/calxeda/Kconfig" +source "drivers/net/ethernet/cavium/Kconfig" +source "drivers/net/ethernet/chelsio/Kconfig" +source "drivers/net/ethernet/cirrus/Kconfig" +source "drivers/net/ethernet/cisco/Kconfig" +source "drivers/net/ethernet/cortina/Kconfig" source "drivers/net/ethernet/davicom/Kconfig" config DNET @@ -85,7 +84,6 @@ source "drivers/net/ethernet/huawei/Kconfig" source "drivers/net/ethernet/i825xx/Kconfig" source "drivers/net/ethernet/ibm/Kconfig" source "drivers/net/ethernet/intel/Kconfig" -source "drivers/net/ethernet/microsoft/Kconfig" source "drivers/net/ethernet/xscale/Kconfig" config JME @@ -128,8 +126,9 @@ source "drivers/net/ethernet/mediatek/Kconfig" source "drivers/net/ethernet/mellanox/Kconfig" source "drivers/net/ethernet/micrel/Kconfig" source "drivers/net/ethernet/microchip/Kconfig" -source "drivers/net/ethernet/moxa/Kconfig" source "drivers/net/ethernet/mscc/Kconfig" +source "drivers/net/ethernet/microsoft/Kconfig" +source "drivers/net/ethernet/moxa/Kconfig" source "drivers/net/ethernet/myricom/Kconfig" config FEALNX @@ -141,10 +140,10 @@ config FEALNX Say Y here to support the Myson MTD-800 family of PCI-based Ethernet cards. <http://www.myson.com.tw/> +source "drivers/net/ethernet/ni/Kconfig" source "drivers/net/ethernet/natsemi/Kconfig" source "drivers/net/ethernet/neterion/Kconfig" source "drivers/net/ethernet/netronome/Kconfig" -source "drivers/net/ethernet/ni/Kconfig" source "drivers/net/ethernet/8390/Kconfig" source "drivers/net/ethernet/nvidia/Kconfig" source "drivers/net/ethernet/nxp/Kconfig" @@ -164,6 +163,7 @@ source "drivers/net/ethernet/packetengines/Kconfig" source "drivers/net/ethernet/pasemi/Kconfig" source "drivers/net/ethernet/pensando/Kconfig" source "drivers/net/ethernet/qlogic/Kconfig" +source "drivers/net/ethernet/brocade/Kconfig" source "drivers/net/ethernet/qualcomm/Kconfig" source "drivers/net/ethernet/rdc/Kconfig" source "drivers/net/ethernet/realtek/Kconfig" @@ -171,10 +171,10 @@ source "drivers/net/ethernet/renesas/Kconfig" source "drivers/net/ethernet/rocker/Kconfig" source "drivers/net/ethernet/samsung/Kconfig" source "drivers/net/ethernet/seeq/Kconfig" -source "drivers/net/ethernet/sfc/Kconfig" source "drivers/net/ethernet/sgi/Kconfig" source "drivers/net/ethernet/silan/Kconfig" source "drivers/net/ethernet/sis/Kconfig" +source "drivers/net/ethernet/sfc/Kconfig" source "drivers/net/ethernet/smsc/Kconfig" source "drivers/net/ethernet/socionext/Kconfig" source "drivers/net/ethernet/stmicro/Kconfig" diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index 797a95142d1f..3a529ee8c834 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -444,22 +444,22 @@ err_exit: static int aq_pm_freeze(struct device *dev) { - return aq_suspend_common(dev, false); + return aq_suspend_common(dev, true); } static int aq_pm_suspend_poweroff(struct device *dev) { - return aq_suspend_common(dev, true); + return aq_suspend_common(dev, false); } static int aq_pm_thaw(struct device *dev) { - return atl_resume_common(dev, false); + return atl_resume_common(dev, true); } static int aq_pm_resume_restore(struct device *dev) { - return atl_resume_common(dev, true); + return atl_resume_common(dev, false); } static const struct dev_pm_ops aq_pm_ops = { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index c19b072f3a23..962253db25b8 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -14153,10 +14153,6 @@ static int bnx2x_eeh_nic_unload(struct bnx2x *bp) /* Stop Tx */ bnx2x_tx_disable(bp); - /* Delete all NAPI objects */ - bnx2x_del_all_napi(bp); - if (CNIC_LOADED(bp)) - bnx2x_del_all_napi_cnic(bp); netdev_reset_tc(bp->dev); del_timer_sync(&bp->timer); @@ -14261,6 +14257,11 @@ static pci_ers_result_t bnx2x_io_slot_reset(struct pci_dev *pdev) bnx2x_drain_tx_queues(bp); bnx2x_send_unload_req(bp, UNLOAD_RECOVERY); bnx2x_netif_stop(bp, 1); + bnx2x_del_all_napi(bp); + + if (CNIC_LOADED(bp)) + bnx2x_del_all_napi_cnic(bp); + bnx2x_free_irq(bp); /* Report UNLOAD_DONE to MCP */ diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 9a41145dadfc..bf1ec8fdc2ad 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -2035,6 +2035,11 @@ static struct sk_buff *bcmgenet_add_tsb(struct net_device *dev, return skb; } +static void bcmgenet_hide_tsb(struct sk_buff *skb) +{ + __skb_pull(skb, sizeof(struct status_64)); +} + static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); @@ -2141,6 +2146,8 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) } GENET_CB(skb)->last_cb = tx_cb_ptr; + + bcmgenet_hide_tsb(skb); skb_tx_timestamp(skb); /* Decrement total BD count and advance our write pointer */ diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index 79afb1d7289b..9182631856d5 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -297,10 +297,6 @@ int enetc_setup_tc_txtime(struct net_device *ndev, void *type_data) if (tc < 0 || tc >= priv->num_tx_rings) return -EINVAL; - /* Do not support TXSTART and TX CSUM offload simutaniously */ - if (ndev->features & NETIF_F_CSUM_MASK) - return -EBUSY; - /* TSD and Qbv are mutually exclusive in hardware */ if (enetc_rd(&priv->si->hw, ENETC_QBV_PTGCR_OFFSET) & ENETC_QBV_TGE) return -EBUSY; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 11227f51404c..9f33ec838b52 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3731,7 +3731,7 @@ static int fec_enet_init_stop_mode(struct fec_enet_private *fep, ARRAY_SIZE(out_val)); if (ret) { dev_dbg(&fep->pdev->dev, "no stop mode property\n"); - return ret; + goto out; } fep->stop_gpr.gpr = syscon_node_to_regmap(gpr_np); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index 7edf8569514c..928d934cb21a 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -1065,19 +1065,23 @@ int hns_mac_init(struct dsaf_device *dsaf_dev) device_for_each_child_node(dsaf_dev->dev, child) { ret = fwnode_property_read_u32(child, "reg", &port_id); if (ret) { + fwnode_handle_put(child); dev_err(dsaf_dev->dev, "get reg fail, ret=%d!\n", ret); return ret; } if (port_id >= max_port_num) { + fwnode_handle_put(child); dev_err(dsaf_dev->dev, "reg(%u) out of range!\n", port_id); return -EINVAL; } mac_cb = devm_kzalloc(dsaf_dev->dev, sizeof(*mac_cb), GFP_KERNEL); - if (!mac_cb) + if (!mac_cb) { + fwnode_handle_put(child); return -ENOMEM; + } mac_cb->fw_port = child; mac_cb->mac_id = (u8)port_id; dsaf_dev->mac_cb[port_id] = mac_cb; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c index 0c60f41fca8a..f3c9395d8351 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c @@ -75,7 +75,7 @@ int hclge_comm_tqps_update_stats(struct hnae3_handle *handle, ret = hclge_comm_cmd_send(hw, &desc, 1); if (ret) { dev_err(&hw->cmq.csq.pdev->dev, - "failed to get tqp stat, ret = %d, tx = %u.\n", + "failed to get tqp stat, ret = %d, rx = %u.\n", ret, i); return ret; } @@ -89,7 +89,7 @@ int hclge_comm_tqps_update_stats(struct hnae3_handle *handle, ret = hclge_comm_cmd_send(hw, &desc, 1); if (ret) { dev_err(&hw->cmq.csq.pdev->dev, - "failed to get tqp stat, ret = %d, rx = %u.\n", + "failed to get tqp stat, ret = %d, tx = %u.\n", ret, i); return ret; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 44d9b560b337..93aeb615191d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -562,12 +562,12 @@ static void hns3_dbg_tx_spare_info(struct hns3_enet_ring *ring, char *buf, for (i = 0; i < ring_num; i++) { j = 0; - sprintf(result[j++], "%8u", i); - sprintf(result[j++], "%9u", ring->tx_copybreak); - sprintf(result[j++], "%3u", tx_spare->len); - sprintf(result[j++], "%3u", tx_spare->next_to_use); - sprintf(result[j++], "%3u", tx_spare->next_to_clean); - sprintf(result[j++], "%3u", tx_spare->last_to_clean); + sprintf(result[j++], "%u", i); + sprintf(result[j++], "%u", ring->tx_copybreak); + sprintf(result[j++], "%u", tx_spare->len); + sprintf(result[j++], "%u", tx_spare->next_to_use); + sprintf(result[j++], "%u", tx_spare->next_to_clean); + sprintf(result[j++], "%u", tx_spare->last_to_clean); sprintf(result[j++], "%pad", &tx_spare->dma); hns3_dbg_fill_content(content, sizeof(content), tx_spare_info_items, @@ -598,35 +598,35 @@ static void hns3_dump_rx_queue_info(struct hns3_enet_ring *ring, u32 base_add_l, base_add_h; u32 j = 0; - sprintf(result[j++], "%8u", index); + sprintf(result[j++], "%u", index); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_BD_NUM_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_BD_LEN_REG)); - sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_TAIL_REG)); - sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_HEAD_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_FBDNUM_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_PKTNUM_RECORD_REG)); - sprintf(result[j++], "%9u", ring->rx_copybreak); + sprintf(result[j++], "%u", ring->rx_copybreak); - sprintf(result[j++], "%7s", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base + HNS3_RING_EN_REG) ? "on" : "off"); if (hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev)) - sprintf(result[j++], "%10s", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_EN_REG) ? "on" : "off"); else - sprintf(result[j++], "%10s", "NA"); + sprintf(result[j++], "%s", "NA"); base_add_h = readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_BASEADDR_H_REG); @@ -700,36 +700,36 @@ static void hns3_dump_tx_queue_info(struct hns3_enet_ring *ring, u32 base_add_l, base_add_h; u32 j = 0; - sprintf(result[j++], "%8u", index); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", index); + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_BD_NUM_REG)); - sprintf(result[j++], "%2u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_TC_REG)); - sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_TAIL_REG)); - sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_HEAD_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_FBDNUM_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_OFFSET_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_PKTNUM_RECORD_REG)); - sprintf(result[j++], "%7s", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base + HNS3_RING_EN_REG) ? "on" : "off"); if (hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev)) - sprintf(result[j++], "%10s", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_EN_REG) ? "on" : "off"); else - sprintf(result[j++], "%10s", "NA"); + sprintf(result[j++], "%s", "NA"); base_add_h = readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_BASEADDR_H_REG); @@ -848,15 +848,15 @@ static void hns3_dump_rx_bd_info(struct hns3_nic_priv *priv, { unsigned int j = 0; - sprintf(result[j++], "%5d", idx); + sprintf(result[j++], "%d", idx); sprintf(result[j++], "%#x", le32_to_cpu(desc->rx.l234_info)); - sprintf(result[j++], "%7u", le16_to_cpu(desc->rx.pkt_len)); - sprintf(result[j++], "%4u", le16_to_cpu(desc->rx.size)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.pkt_len)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.size)); sprintf(result[j++], "%#x", le32_to_cpu(desc->rx.rss_hash)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->rx.fd_id)); - sprintf(result[j++], "%8u", le16_to_cpu(desc->rx.vlan_tag)); - sprintf(result[j++], "%15u", le16_to_cpu(desc->rx.o_dm_vlan_id_fb)); - sprintf(result[j++], "%11u", le16_to_cpu(desc->rx.ot_vlan_tag)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.fd_id)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.vlan_tag)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.o_dm_vlan_id_fb)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.ot_vlan_tag)); sprintf(result[j++], "%#x", le32_to_cpu(desc->rx.bd_base_info)); if (test_bit(HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, &priv->state)) { u32 ol_info = le32_to_cpu(desc->rx.ol_info); @@ -930,19 +930,19 @@ static void hns3_dump_tx_bd_info(struct hns3_nic_priv *priv, { unsigned int j = 0; - sprintf(result[j++], "%6d", idx); + sprintf(result[j++], "%d", idx); sprintf(result[j++], "%#llx", le64_to_cpu(desc->addr)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.vlan_tag)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.send_size)); + sprintf(result[j++], "%u", le16_to_cpu(desc->tx.vlan_tag)); + sprintf(result[j++], "%u", le16_to_cpu(desc->tx.send_size)); sprintf(result[j++], "%#x", le32_to_cpu(desc->tx.type_cs_vlan_tso_len)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.outer_vlan_tag)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.tv)); - sprintf(result[j++], "%10u", + sprintf(result[j++], "%u", le16_to_cpu(desc->tx.outer_vlan_tag)); + sprintf(result[j++], "%u", le16_to_cpu(desc->tx.tv)); + sprintf(result[j++], "%u", le32_to_cpu(desc->tx.ol_type_vlan_len_msec)); sprintf(result[j++], "%#x", le32_to_cpu(desc->tx.paylen_ol4cs)); sprintf(result[j++], "%#x", le16_to_cpu(desc->tx.bdtp_fe_sc_vld_ra_ri)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.mss_hw_csum)); + sprintf(result[j++], "%u", le16_to_cpu(desc->tx.mss_hw_csum)); } static int hns3_dbg_tx_bd_info(struct hns3_dbg_data *d, char *buf, int len) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 14dc12c2155d..a3ee7875d6a7 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -5203,6 +5203,13 @@ static void hns3_state_init(struct hnae3_handle *handle) set_bit(HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, &priv->state); } +static void hns3_state_uninit(struct hnae3_handle *handle) +{ + struct hns3_nic_priv *priv = handle->priv; + + clear_bit(HNS3_NIC_STATE_INITED, &priv->state); +} + static int hns3_client_init(struct hnae3_handle *handle) { struct pci_dev *pdev = handle->pdev; @@ -5320,7 +5327,9 @@ static int hns3_client_init(struct hnae3_handle *handle) return ret; out_reg_netdev_fail: + hns3_state_uninit(handle); hns3_dbg_uninit(handle); + hns3_client_stop(handle); out_client_start: hns3_free_rx_cpu_rmap(netdev); hns3_nic_uninit_irq(priv); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 6799d16de34b..7998ca617a92 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -94,6 +94,13 @@ static int hclge_send_mbx_msg(struct hclge_vport *vport, u8 *msg, u16 msg_len, enum hclge_comm_cmd_status status; struct hclge_desc desc; + if (msg_len > HCLGE_MBX_MAX_MSG_SIZE) { + dev_err(&hdev->pdev->dev, + "msg data length(=%u) exceeds maximum(=%u)\n", + msg_len, HCLGE_MBX_MAX_MSG_SIZE); + return -EMSGSIZE; + } + resp_pf_to_vf = (struct hclge_mbx_pf_to_vf_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_MBX_PF_TO_VF, false); @@ -176,7 +183,7 @@ static int hclge_get_ring_chain_from_mbx( ring_num = req->msg.ring_num; if (ring_num > HCLGE_MBX_MAX_RING_CHAIN_PARAM_NUM) - return -ENOMEM; + return -EINVAL; for (i = 0; i < ring_num; i++) { if (req->msg.param[i].tqp_index >= vport->nic.kinfo.rss_size) { @@ -587,9 +594,9 @@ static int hclge_set_vf_mtu(struct hclge_vport *vport, return hclge_set_vport_mtu(vport, mtu); } -static void hclge_get_queue_id_in_pf(struct hclge_vport *vport, - struct hclge_mbx_vf_to_pf_cmd *mbx_req, - struct hclge_respond_to_vf_msg *resp_msg) +static int hclge_get_queue_id_in_pf(struct hclge_vport *vport, + struct hclge_mbx_vf_to_pf_cmd *mbx_req, + struct hclge_respond_to_vf_msg *resp_msg) { struct hnae3_handle *handle = &vport->nic; struct hclge_dev *hdev = vport->back; @@ -599,17 +606,18 @@ static void hclge_get_queue_id_in_pf(struct hclge_vport *vport, if (queue_id >= handle->kinfo.num_tqps) { dev_err(&hdev->pdev->dev, "Invalid queue id(%u) from VF %u\n", queue_id, mbx_req->mbx_src_vfid); - return; + return -EINVAL; } qid_in_pf = hclge_covert_handle_qid_global(&vport->nic, queue_id); memcpy(resp_msg->data, &qid_in_pf, sizeof(qid_in_pf)); resp_msg->len = sizeof(qid_in_pf); + return 0; } -static void hclge_get_rss_key(struct hclge_vport *vport, - struct hclge_mbx_vf_to_pf_cmd *mbx_req, - struct hclge_respond_to_vf_msg *resp_msg) +static int hclge_get_rss_key(struct hclge_vport *vport, + struct hclge_mbx_vf_to_pf_cmd *mbx_req, + struct hclge_respond_to_vf_msg *resp_msg) { #define HCLGE_RSS_MBX_RESP_LEN 8 struct hclge_dev *hdev = vport->back; @@ -627,13 +635,14 @@ static void hclge_get_rss_key(struct hclge_vport *vport, dev_warn(&hdev->pdev->dev, "failed to get the rss hash key, the index(%u) invalid !\n", index); - return; + return -EINVAL; } memcpy(resp_msg->data, &rss_cfg->rss_hash_key[index * HCLGE_RSS_MBX_RESP_LEN], HCLGE_RSS_MBX_RESP_LEN); resp_msg->len = HCLGE_RSS_MBX_RESP_LEN; + return 0; } static void hclge_link_fail_parse(struct hclge_dev *hdev, u8 link_fail_code) @@ -809,10 +818,10 @@ void hclge_mbx_handler(struct hclge_dev *hdev) "VF fail(%d) to set mtu\n", ret); break; case HCLGE_MBX_GET_QID_IN_PF: - hclge_get_queue_id_in_pf(vport, req, &resp_msg); + ret = hclge_get_queue_id_in_pf(vport, req, &resp_msg); break; case HCLGE_MBX_GET_RSS_KEY: - hclge_get_rss_key(vport, req, &resp_msg); + ret = hclge_get_rss_key(vport, req, &resp_msg); break; case HCLGE_MBX_GET_LINK_MODE: hclge_get_link_mode(vport, req); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 77683909ca3d..5c5931dba51d 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -3210,13 +3210,8 @@ static void ibmvnic_get_ringparam(struct net_device *netdev, { struct ibmvnic_adapter *adapter = netdev_priv(netdev); - if (adapter->priv_flags & IBMVNIC_USE_SERVER_MAXES) { - ring->rx_max_pending = adapter->max_rx_add_entries_per_subcrq; - ring->tx_max_pending = adapter->max_tx_entries_per_subcrq; - } else { - ring->rx_max_pending = IBMVNIC_MAX_QUEUE_SZ; - ring->tx_max_pending = IBMVNIC_MAX_QUEUE_SZ; - } + ring->rx_max_pending = adapter->max_rx_add_entries_per_subcrq; + ring->tx_max_pending = adapter->max_tx_entries_per_subcrq; ring->rx_mini_max_pending = 0; ring->rx_jumbo_max_pending = 0; ring->rx_pending = adapter->req_rx_add_entries_per_subcrq; @@ -3231,23 +3226,21 @@ static int ibmvnic_set_ringparam(struct net_device *netdev, struct netlink_ext_ack *extack) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); - int ret; - ret = 0; + if (ring->rx_pending > adapter->max_rx_add_entries_per_subcrq || + ring->tx_pending > adapter->max_tx_entries_per_subcrq) { + netdev_err(netdev, "Invalid request.\n"); + netdev_err(netdev, "Max tx buffers = %llu\n", + adapter->max_rx_add_entries_per_subcrq); + netdev_err(netdev, "Max rx buffers = %llu\n", + adapter->max_tx_entries_per_subcrq); + return -EINVAL; + } + adapter->desired.rx_entries = ring->rx_pending; adapter->desired.tx_entries = ring->tx_pending; - ret = wait_for_reset(adapter); - - if (!ret && - (adapter->req_rx_add_entries_per_subcrq != ring->rx_pending || - adapter->req_tx_entries_per_subcrq != ring->tx_pending)) - netdev_info(netdev, - "Could not match full ringsize request. Requested: RX %d, TX %d; Allowed: RX %llu, TX %llu\n", - ring->rx_pending, ring->tx_pending, - adapter->req_rx_add_entries_per_subcrq, - adapter->req_tx_entries_per_subcrq); - return ret; + return wait_for_reset(adapter); } static void ibmvnic_get_channels(struct net_device *netdev, @@ -3255,14 +3248,8 @@ static void ibmvnic_get_channels(struct net_device *netdev, { struct ibmvnic_adapter *adapter = netdev_priv(netdev); - if (adapter->priv_flags & IBMVNIC_USE_SERVER_MAXES) { - channels->max_rx = adapter->max_rx_queues; - channels->max_tx = adapter->max_tx_queues; - } else { - channels->max_rx = IBMVNIC_MAX_QUEUES; - channels->max_tx = IBMVNIC_MAX_QUEUES; - } - + channels->max_rx = adapter->max_rx_queues; + channels->max_tx = adapter->max_tx_queues; channels->max_other = 0; channels->max_combined = 0; channels->rx_count = adapter->req_rx_queues; @@ -3275,22 +3262,11 @@ static int ibmvnic_set_channels(struct net_device *netdev, struct ethtool_channels *channels) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); - int ret; - ret = 0; adapter->desired.rx_queues = channels->rx_count; adapter->desired.tx_queues = channels->tx_count; - ret = wait_for_reset(adapter); - - if (!ret && - (adapter->req_rx_queues != channels->rx_count || - adapter->req_tx_queues != channels->tx_count)) - netdev_info(netdev, - "Could not match full channels request. Requested: RX %d, TX %d; Allowed: RX %llu, TX %llu\n", - channels->rx_count, channels->tx_count, - adapter->req_rx_queues, adapter->req_tx_queues); - return ret; + return wait_for_reset(adapter); } static void ibmvnic_get_strings(struct net_device *dev, u32 stringset, u8 *data) @@ -3298,43 +3274,32 @@ static void ibmvnic_get_strings(struct net_device *dev, u32 stringset, u8 *data) struct ibmvnic_adapter *adapter = netdev_priv(dev); int i; - switch (stringset) { - case ETH_SS_STATS: - for (i = 0; i < ARRAY_SIZE(ibmvnic_stats); - i++, data += ETH_GSTRING_LEN) - memcpy(data, ibmvnic_stats[i].name, ETH_GSTRING_LEN); + if (stringset != ETH_SS_STATS) + return; - for (i = 0; i < adapter->req_tx_queues; i++) { - snprintf(data, ETH_GSTRING_LEN, "tx%d_packets", i); - data += ETH_GSTRING_LEN; + for (i = 0; i < ARRAY_SIZE(ibmvnic_stats); i++, data += ETH_GSTRING_LEN) + memcpy(data, ibmvnic_stats[i].name, ETH_GSTRING_LEN); - snprintf(data, ETH_GSTRING_LEN, "tx%d_bytes", i); - data += ETH_GSTRING_LEN; + for (i = 0; i < adapter->req_tx_queues; i++) { + snprintf(data, ETH_GSTRING_LEN, "tx%d_packets", i); + data += ETH_GSTRING_LEN; - snprintf(data, ETH_GSTRING_LEN, - "tx%d_dropped_packets", i); - data += ETH_GSTRING_LEN; - } + snprintf(data, ETH_GSTRING_LEN, "tx%d_bytes", i); + data += ETH_GSTRING_LEN; - for (i = 0; i < adapter->req_rx_queues; i++) { - snprintf(data, ETH_GSTRING_LEN, "rx%d_packets", i); - data += ETH_GSTRING_LEN; + snprintf(data, ETH_GSTRING_LEN, "tx%d_dropped_packets", i); + data += ETH_GSTRING_LEN; + } - snprintf(data, ETH_GSTRING_LEN, "rx%d_bytes", i); - data += ETH_GSTRING_LEN; + for (i = 0; i < adapter->req_rx_queues; i++) { + snprintf(data, ETH_GSTRING_LEN, "rx%d_packets", i); + data += ETH_GSTRING_LEN; - snprintf(data, ETH_GSTRING_LEN, "rx%d_interrupts", i); - data += ETH_GSTRING_LEN; - } - break; + snprintf(data, ETH_GSTRING_LEN, "rx%d_bytes", i); + data += ETH_GSTRING_LEN; - case ETH_SS_PRIV_FLAGS: - for (i = 0; i < ARRAY_SIZE(ibmvnic_priv_flags); i++) - strcpy(data + i * ETH_GSTRING_LEN, - ibmvnic_priv_flags[i]); - break; - default: - return; + snprintf(data, ETH_GSTRING_LEN, "rx%d_interrupts", i); + data += ETH_GSTRING_LEN; } } @@ -3347,8 +3312,6 @@ static int ibmvnic_get_sset_count(struct net_device *dev, int sset) return ARRAY_SIZE(ibmvnic_stats) + adapter->req_tx_queues * NUM_TX_STATS + adapter->req_rx_queues * NUM_RX_STATS; - case ETH_SS_PRIV_FLAGS: - return ARRAY_SIZE(ibmvnic_priv_flags); default: return -EOPNOTSUPP; } @@ -3401,26 +3364,6 @@ static void ibmvnic_get_ethtool_stats(struct net_device *dev, } } -static u32 ibmvnic_get_priv_flags(struct net_device *netdev) -{ - struct ibmvnic_adapter *adapter = netdev_priv(netdev); - - return adapter->priv_flags; -} - -static int ibmvnic_set_priv_flags(struct net_device *netdev, u32 flags) -{ - struct ibmvnic_adapter *adapter = netdev_priv(netdev); - bool which_maxes = !!(flags & IBMVNIC_USE_SERVER_MAXES); - - if (which_maxes) - adapter->priv_flags |= IBMVNIC_USE_SERVER_MAXES; - else - adapter->priv_flags &= ~IBMVNIC_USE_SERVER_MAXES; - - return 0; -} - static const struct ethtool_ops ibmvnic_ethtool_ops = { .get_drvinfo = ibmvnic_get_drvinfo, .get_msglevel = ibmvnic_get_msglevel, @@ -3434,8 +3377,6 @@ static const struct ethtool_ops ibmvnic_ethtool_ops = { .get_sset_count = ibmvnic_get_sset_count, .get_ethtool_stats = ibmvnic_get_ethtool_stats, .get_link_ksettings = ibmvnic_get_link_ksettings, - .get_priv_flags = ibmvnic_get_priv_flags, - .set_priv_flags = ibmvnic_set_priv_flags, }; /* Routines for managing CRQs/sCRQs */ diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 8f5cefb932dd..1310c861bf83 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -41,11 +41,6 @@ #define IBMVNIC_RESET_DELAY 100 -static const char ibmvnic_priv_flags[][ETH_GSTRING_LEN] = { -#define IBMVNIC_USE_SERVER_MAXES 0x1 - "use-server-maxes" -}; - struct ibmvnic_login_buffer { __be32 len; __be32 version; @@ -883,7 +878,6 @@ struct ibmvnic_adapter { struct ibmvnic_control_ip_offload_buffer ip_offload_ctrl; dma_addr_t ip_offload_ctrl_tok; u32 msg_enable; - u32 priv_flags; /* Vital Product Data (VPD) */ struct ibmvnic_vpd *vpd; diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index d60e2016d03c..e6c8e6d5234f 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -1009,8 +1009,8 @@ static s32 e1000_platform_pm_pch_lpt(struct e1000_hw *hw, bool link) { u32 reg = link << (E1000_LTRV_REQ_SHIFT + E1000_LTRV_NOSNOOP_SHIFT) | link << E1000_LTRV_REQ_SHIFT | E1000_LTRV_SEND; - u16 max_ltr_enc_d = 0; /* maximum LTR decoded by platform */ - u16 lat_enc_d = 0; /* latency decoded */ + u32 max_ltr_enc_d = 0; /* maximum LTR decoded by platform */ + u32 lat_enc_d = 0; /* latency decoded */ u16 lat_enc = 0; /* latency encoded */ if (link) { diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index 9a84d746a6c4..6a463b242c7d 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -361,7 +361,8 @@ ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev) np = netdev_priv(netdev); vsi = np->vsi; - if (ice_is_reset_in_progress(vsi->back->state)) + if (ice_is_reset_in_progress(vsi->back->state) || + test_bit(ICE_VF_DIS, vsi->back->state)) return NETDEV_TX_BUSY; repr = ice_netdev_to_repr(netdev); diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.h b/drivers/net/ethernet/intel/ice/ice_eswitch.h index bd58d9d2e565..6a413331572b 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.h +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.h @@ -52,7 +52,7 @@ static inline void ice_eswitch_update_repr(struct ice_vsi *vsi) { } static inline int ice_eswitch_configure(struct ice_pf *pf) { - return -EOPNOTSUPP; + return 0; } static inline int ice_eswitch_rebuild(struct ice_pf *pf) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 5b1198859da7..9a0a358a15c2 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -6929,12 +6929,15 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) dev_dbg(dev, "rebuilding PF after reset_type=%d\n", reset_type); +#define ICE_EMP_RESET_SLEEP_MS 5000 if (reset_type == ICE_RESET_EMPR) { /* If an EMP reset has occurred, any previously pending flash * update will have completed. We no longer know whether or * not the NVM update EMP reset is restricted. */ pf->fw_emp_reset_disabled = false; + + msleep(ICE_EMP_RESET_SLEEP_MS); } err = ice_init_all_ctrlq(hw); diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c index 4eb0599714f4..13cdb5ea594d 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.c +++ b/drivers/net/ethernet/intel/ice/ice_nvm.c @@ -641,6 +641,7 @@ ice_get_orom_civd_data(struct ice_hw *hw, enum ice_bank_select bank, status = ice_read_flash_module(hw, bank, ICE_SR_1ST_OROM_BANK_PTR, 0, orom_data, hw->flash.banks.orom_size); if (status) { + vfree(orom_data); ice_debug(hw, ICE_DBG_NVM, "Unable to read Option ROM data\n"); return status; } diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index 8915a9d39e36..0c438219f7a3 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -1046,8 +1046,8 @@ int ice_sriov_configure(struct pci_dev *pdev, int num_vfs) if (!num_vfs) { if (!pci_vfs_assigned(pdev)) { - ice_mbx_deinit_snapshot(&pf->hw); ice_free_vfs(pf); + ice_mbx_deinit_snapshot(&pf->hw); if (pf->lag) ice_enable_lag(pf->lag); return 0; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 69ff4b929772..b72606c9e6d0 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -3625,6 +3625,8 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) return; } + mutex_lock(&vf->cfg_lock); + /* Check if VF is disabled. */ if (test_bit(ICE_VF_STATE_DIS, vf->vf_states)) { err = -EPERM; @@ -3642,32 +3644,20 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) err = -EINVAL; } - if (!ice_vc_is_opcode_allowed(vf, v_opcode)) { - ice_vc_send_msg_to_vf(vf, v_opcode, - VIRTCHNL_STATUS_ERR_NOT_SUPPORTED, NULL, - 0); - ice_put_vf(vf); - return; - } - error_handler: if (err) { ice_vc_send_msg_to_vf(vf, v_opcode, VIRTCHNL_STATUS_ERR_PARAM, NULL, 0); dev_err(dev, "Invalid message from VF %d, opcode %d, len %d, error %d\n", vf_id, v_opcode, msglen, err); - ice_put_vf(vf); - return; + goto finish; } - /* VF is being configured in another context that triggers a VFR, so no - * need to process this message - */ - if (!mutex_trylock(&vf->cfg_lock)) { - dev_info(dev, "VF %u is being configured in another context that will trigger a VFR, so there is no need to handle this message\n", - vf->vf_id); - ice_put_vf(vf); - return; + if (!ice_vc_is_opcode_allowed(vf, v_opcode)) { + ice_vc_send_msg_to_vf(vf, v_opcode, + VIRTCHNL_STATUS_ERR_NOT_SUPPORTED, NULL, + 0); + goto finish; } switch (v_opcode) { @@ -3780,6 +3770,7 @@ error_handler: vf_id, v_opcode, err); } +finish: mutex_unlock(&vf->cfg_lock); ice_put_vf(vf); } diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 866ee4df9671..9dd38f667059 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -415,8 +415,8 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp, */ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) { + u32 nb_buffs_extra = 0, nb_buffs = 0; union ice_32b_rx_flex_desc *rx_desc; - u32 nb_buffs_extra = 0, nb_buffs; u16 ntu = rx_ring->next_to_use; u16 total_count = count; struct xdp_buff **xdp; @@ -428,6 +428,10 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) nb_buffs_extra = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, rx_desc, rx_ring->count - ntu); + if (nb_buffs_extra != rx_ring->count - ntu) { + ntu += nb_buffs_extra; + goto exit; + } rx_desc = ICE_RX_DESC(rx_ring, 0); xdp = ice_xdp_buf(rx_ring, 0); ntu = 0; @@ -441,6 +445,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) if (ntu == rx_ring->count) ntu = 0; +exit: if (rx_ring->next_to_use != ntu) ice_release_rx_desc(rx_ring, ntu); diff --git a/drivers/net/ethernet/intel/igc/igc_i225.c b/drivers/net/ethernet/intel/igc/igc_i225.c index 66ea566488d1..59d5c467ea6e 100644 --- a/drivers/net/ethernet/intel/igc/igc_i225.c +++ b/drivers/net/ethernet/intel/igc/igc_i225.c @@ -156,8 +156,15 @@ void igc_release_swfw_sync_i225(struct igc_hw *hw, u16 mask) { u32 swfw_sync; - while (igc_get_hw_semaphore_i225(hw)) - ; /* Empty */ + /* Releasing the resource requires first getting the HW semaphore. + * If we fail to get the semaphore, there is nothing we can do, + * except log an error and quit. We are not allowed to hang here + * indefinitely, as it may cause denial of service or system crash. + */ + if (igc_get_hw_semaphore_i225(hw)) { + hw_dbg("Failed to release SW_FW_SYNC.\n"); + return; + } swfw_sync = rd32(IGC_SW_FW_SYNC); swfw_sync &= ~mask; diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c index 40dbf4b43234..6961f65d36b9 100644 --- a/drivers/net/ethernet/intel/igc/igc_phy.c +++ b/drivers/net/ethernet/intel/igc/igc_phy.c @@ -581,7 +581,7 @@ static s32 igc_read_phy_reg_mdic(struct igc_hw *hw, u32 offset, u16 *data) * the lower time out */ for (i = 0; i < IGC_GEN_POLL_TIMEOUT; i++) { - usleep_range(500, 1000); + udelay(50); mdic = rd32(IGC_MDIC); if (mdic & IGC_MDIC_READY) break; @@ -638,7 +638,7 @@ static s32 igc_write_phy_reg_mdic(struct igc_hw *hw, u32 offset, u16 data) * the lower time out */ for (i = 0; i < IGC_GEN_POLL_TIMEOUT; i++) { - usleep_range(500, 1000); + udelay(50); mdic = rd32(IGC_MDIC); if (mdic & IGC_MDIC_READY) break; diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 0d6e3215e98f..653e9f1e35b5 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -992,6 +992,17 @@ static void igc_ptp_time_restore(struct igc_adapter *adapter) igc_ptp_write_i225(adapter, &ts); } +static void igc_ptm_stop(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 ctrl; + + ctrl = rd32(IGC_PTM_CTRL); + ctrl &= ~IGC_PTM_CTRL_EN; + + wr32(IGC_PTM_CTRL, ctrl); +} + /** * igc_ptp_suspend - Disable PTP work items and prepare for suspend * @adapter: Board private structure @@ -1009,8 +1020,10 @@ void igc_ptp_suspend(struct igc_adapter *adapter) adapter->ptp_tx_skb = NULL; clear_bit_unlock(__IGC_PTP_TX_IN_PROGRESS, &adapter->state); - if (pci_device_is_present(adapter->pdev)) + if (pci_device_is_present(adapter->pdev)) { igc_ptp_time_save(adapter); + igc_ptm_stop(adapter); + } } /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c index e596e1a9fc75..69d11ff7677d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c @@ -903,7 +903,8 @@ int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) /* Tx IPsec offload doesn't seem to work on this * device, so block these requests for now. */ - if (!(sam->flags & XFRM_OFFLOAD_INBOUND)) { + sam->flags = sam->flags & ~XFRM_OFFLOAD_IPV6; + if (sam->flags != XFRM_OFFLOAD_INBOUND) { err = -EOPNOTSUPP; goto err_out; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index b73466470f75..fe663b0ab708 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -423,7 +423,7 @@ mlxsw_sp_span_gretap4_route(const struct net_device *to_dev, parms = mlxsw_sp_ipip_netdev_parms4(to_dev); ip_tunnel_init_flow(&fl4, parms.iph.protocol, *daddrp, *saddrp, - 0, 0, parms.link, tun->fwmark, 0); + 0, 0, dev_net(to_dev), parms.link, tun->fwmark, 0); rt = ip_route_output_key(tun->net, &fl4); if (IS_ERR(rt)) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c b/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c index 2679111ef669..005e56ea5da1 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c @@ -346,7 +346,7 @@ static void lan966x_mac_irq_process(struct lan966x *lan966x, u32 row, lan966x_mac_process_raw_entry(&raw_entries[column], mac, &vid, &dest_idx); - if (WARN_ON(dest_idx > lan966x->num_phys_ports)) + if (WARN_ON(dest_idx >= lan966x->num_phys_ports)) continue; /* If the entry in SW is found, then there is nothing @@ -393,7 +393,7 @@ static void lan966x_mac_irq_process(struct lan966x *lan966x, u32 row, lan966x_mac_process_raw_entry(&raw_entries[column], mac, &vid, &dest_idx); - if (WARN_ON(dest_idx > lan966x->num_phys_ports)) + if (WARN_ON(dest_idx >= lan966x->num_phys_ports)) continue; mac_entry = lan966x_mac_alloc_entry(mac, vid, dest_idx); diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index 958e55596b82..95830e3e2b1f 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -671,6 +671,9 @@ static void lan966x_cleanup_ports(struct lan966x *lan966x) disable_irq(lan966x->ana_irq); lan966x->ana_irq = -ENXIO; } + + if (lan966x->ptp_irq) + devm_free_irq(lan966x->dev, lan966x->ptp_irq, lan966x); } static int lan966x_probe_port(struct lan966x *lan966x, u32 p, diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index e443bd8b2d09..ca71b62a44dc 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -551,7 +551,7 @@ int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, struct ocelot_vcap_block *block = &ocelot->block[VCAP_IS1]; struct ocelot_port *ocelot_port = ocelot->ports[port]; struct ocelot_vcap_filter *filter; - int err; + int err = 0; u32 val; list_for_each_entry(filter, &block->rules, list) { @@ -570,7 +570,7 @@ int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, if (vlan_aware) err = ocelot_del_vlan_unaware_pvid(ocelot, port, ocelot_port->bridge); - else + else if (ocelot_port->bridge) err = ocelot_add_vlan_unaware_pvid(ocelot, port, ocelot_port->bridge); if (err) @@ -629,6 +629,13 @@ int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid, { int err; + /* Ignore VID 0 added to our RX filter by the 8021q module, since + * that collides with OCELOT_STANDALONE_PVID and changes it from + * egress-untagged to egress-tagged. + */ + if (!vid) + return 0; + err = ocelot_vlan_member_add(ocelot, port, vid, untagged); if (err) return err; @@ -651,6 +658,9 @@ int ocelot_vlan_del(struct ocelot *ocelot, int port, u16 vid) bool del_pvid = false; int err; + if (!vid) + return 0; + if (ocelot_port->pvid_vlan && ocelot_port->pvid_vlan->vid == vid) del_pvid = true; @@ -2859,6 +2869,8 @@ static void ocelot_port_set_mcast_flood(struct ocelot *ocelot, int port, val = BIT(port); ocelot_rmw_rix(ocelot, val, BIT(port), ANA_PGID_PGID, PGID_MC); + ocelot_rmw_rix(ocelot, val, BIT(port), ANA_PGID_PGID, PGID_MCIPV4); + ocelot_rmw_rix(ocelot, val, BIT(port), ANA_PGID_PGID, PGID_MCIPV6); } static void ocelot_port_set_bcast_flood(struct ocelot *ocelot, int port, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index ac9e6c7a33b5..6b447d8f0bd8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -65,8 +65,9 @@ static void socfpga_dwmac_fix_mac_speed(void *priv, unsigned int speed) struct phy_device *phy_dev = ndev->phydev; u32 val; - writew(SGMII_ADAPTER_DISABLE, - sgmii_adapter_base + SGMII_ADAPTER_CTRL_REG); + if (sgmii_adapter_base) + writew(SGMII_ADAPTER_DISABLE, + sgmii_adapter_base + SGMII_ADAPTER_CTRL_REG); if (splitter_base) { val = readl(splitter_base + EMAC_SPLITTER_CTRL_REG); @@ -88,10 +89,11 @@ static void socfpga_dwmac_fix_mac_speed(void *priv, unsigned int speed) writel(val, splitter_base + EMAC_SPLITTER_CTRL_REG); } - writew(SGMII_ADAPTER_ENABLE, - sgmii_adapter_base + SGMII_ADAPTER_CTRL_REG); - if (phy_dev) + if (phy_dev && sgmii_adapter_base) { + writew(SGMII_ADAPTER_ENABLE, + sgmii_adapter_base + SGMII_ADAPTER_CTRL_REG); tse_pcs_fix_mac_speed(&dwmac->pcs, phy_dev, speed); + } } static int socfpga_dwmac_parse_data(struct socfpga_dwmac *dwmac, struct device *dev) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index 22fea0f67245..92d32940aff0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -71,9 +71,9 @@ static int init_systime(void __iomem *ioaddr, u32 sec, u32 nsec) writel(value, ioaddr + PTP_TCR); /* wait for present system time initialize to complete */ - return readl_poll_timeout(ioaddr + PTP_TCR, value, + return readl_poll_timeout_atomic(ioaddr + PTP_TCR, value, !(value & PTP_TCR_TSINIT), - 10000, 100000); + 10, 100000); } static int config_addend(void __iomem *ioaddr, u32 addend) diff --git a/drivers/net/hippi/rrunner.c b/drivers/net/hippi/rrunner.c index 16105292b140..74e845fa2e07 100644 --- a/drivers/net/hippi/rrunner.c +++ b/drivers/net/hippi/rrunner.c @@ -1355,7 +1355,9 @@ static int rr_close(struct net_device *dev) rrpriv->fw_running = 0; + spin_unlock_irqrestore(&rrpriv->lock, flags); del_timer_sync(&rrpriv->timer); + spin_lock_irqsave(&rrpriv->lock, flags); writel(0, ®s->TxPi); writel(0, ®s->IpRxPi); diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index b6fea119fe13..2b7d0720720b 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -880,7 +880,7 @@ static int mv3310_read_status_copper(struct phy_device *phydev) cssr1 = phy_read_mmd(phydev, MDIO_MMD_PCS, MV_PCS_CSSR1); if (cssr1 < 0) - return val; + return cssr1; /* If the link settings are not resolved, mark the link down */ if (!(cssr1 & MV_PCS_CSSR1_RESOLVED)) { diff --git a/drivers/net/phy/microchip_t1.c b/drivers/net/phy/microchip_t1.c index 3f79bbbe62d3..c2c0e361fd3d 100644 --- a/drivers/net/phy/microchip_t1.c +++ b/drivers/net/phy/microchip_t1.c @@ -743,6 +743,7 @@ static struct phy_driver microchip_t1_phy_driver[] = { { PHY_ID_MATCH_MODEL(PHY_ID_LAN937X), .name = "Microchip LAN937x T1", + .flags = PHY_POLL_CABLE_TEST, .features = PHY_BASIC_T1_FEATURES, .config_init = lan87xx_config_init, .suspend = genphy_suspend, diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 87838cbe38cf..cbba9d2e8f32 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1005,6 +1005,24 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, * xdp.data_meta were adjusted */ len = xdp.data_end - xdp.data + vi->hdr_len + metasize; + + /* recalculate headroom if xdp.data or xdp_data_meta + * were adjusted, note that offset should always point + * to the start of the reserved bytes for virtio_net + * header which are followed by xdp.data, that means + * that offset is equal to the headroom (when buf is + * starting at the beginning of the page, otherwise + * there is a base offset inside the page) but it's used + * with a different starting point (buf start) than + * xdp.data (buf start + vnet hdr size). If xdp.data or + * data_meta were adjusted by the xdp prog then the + * headroom size has changed and so has the offset, we + * can use data_hard_start, which points at buf start + + * vnet hdr size, to calculate the new headroom and use + * it later to compute buf start in page_to_skb() + */ + headroom = xdp.data - xdp.data_hard_start - metasize; + /* We can only create skb based on xdp_page. */ if (unlikely(xdp_page != page)) { rcu_read_unlock(); @@ -1012,7 +1030,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, head_skb = page_to_skb(vi, rq, xdp_page, offset, len, PAGE_SIZE, false, metasize, - VIRTIO_XDP_HEADROOM); + headroom); return head_skb; } break; diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c index 23d2954d9747..1e5672019922 100644 --- a/drivers/net/wan/cosa.c +++ b/drivers/net/wan/cosa.c @@ -349,7 +349,7 @@ static int __init cosa_init(void) } } else { cosa_major = register_chrdev(0, "cosa", &cosa_fops); - if (!cosa_major) { + if (cosa_major < 0) { pr_warn("unable to register chardev\n"); err = -EIO; goto out; diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c index 0fad1331303c..aa9a7a5970fd 100644 --- a/drivers/net/wireguard/device.c +++ b/drivers/net/wireguard/device.c @@ -19,6 +19,7 @@ #include <linux/if_arp.h> #include <linux/icmp.h> #include <linux/suspend.h> +#include <net/dst_metadata.h> #include <net/icmp.h> #include <net/rtnetlink.h> #include <net/ip_tunnels.h> @@ -167,7 +168,7 @@ static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev) goto err_peer; } - mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; + mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; __skb_queue_head_init(&packets); if (!skb_is_gso(skb)) { diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 9694370651fa..59d3980b8ca2 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -400,6 +400,9 @@ validate_group(struct perf_event *event) if (!validate_event(event->pmu, &fake_pmu, leader)) return -EINVAL; + if (event == leader) + return 0; + for_each_sibling_event(sibling, leader) { if (!validate_event(event->pmu, &fake_pmu, sibling)) return -EINVAL; @@ -489,12 +492,7 @@ __hw_perf_event_init(struct perf_event *event) local64_set(&hwc->period_left, hwc->sample_period); } - if (event->group_leader != event) { - if (validate_group(event) != 0) - return -EINVAL; - } - - return 0; + return validate_group(event); } static int armpmu_event_init(struct perf_event *event) diff --git a/drivers/phy/amlogic/phy-meson-g12a-usb3-pcie.c b/drivers/phy/amlogic/phy-meson-g12a-usb3-pcie.c index 5b471ab80fe2..54d65a6f0fcc 100644 --- a/drivers/phy/amlogic/phy-meson-g12a-usb3-pcie.c +++ b/drivers/phy/amlogic/phy-meson-g12a-usb3-pcie.c @@ -414,19 +414,19 @@ static int phy_g12a_usb3_pcie_probe(struct platform_device *pdev) ret = clk_prepare_enable(priv->clk_ref); if (ret) - goto err_disable_clk_ref; + return ret; priv->reset = devm_reset_control_array_get_exclusive(dev); - if (IS_ERR(priv->reset)) - return PTR_ERR(priv->reset); + if (IS_ERR(priv->reset)) { + ret = PTR_ERR(priv->reset); + goto err_disable_clk_ref; + } priv->phy = devm_phy_create(dev, np, &phy_g12a_usb3_pcie_ops); if (IS_ERR(priv->phy)) { ret = PTR_ERR(priv->phy); - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to create PHY\n"); - - return ret; + dev_err_probe(dev, ret, "failed to create PHY\n"); + goto err_disable_clk_ref; } phy_set_drvdata(priv->phy, priv); @@ -434,8 +434,12 @@ static int phy_g12a_usb3_pcie_probe(struct platform_device *pdev) phy_provider = devm_of_phy_provider_register(dev, phy_g12a_usb3_pcie_xlate); + if (IS_ERR(phy_provider)) { + ret = PTR_ERR(phy_provider); + goto err_disable_clk_ref; + } - return PTR_ERR_OR_ZERO(phy_provider); + return 0; err_disable_clk_ref: clk_disable_unprepare(priv->clk_ref); diff --git a/drivers/phy/motorola/phy-mapphone-mdm6600.c b/drivers/phy/motorola/phy-mapphone-mdm6600.c index 5172971f4c36..3cd4d51c247c 100644 --- a/drivers/phy/motorola/phy-mapphone-mdm6600.c +++ b/drivers/phy/motorola/phy-mapphone-mdm6600.c @@ -629,7 +629,8 @@ idle: cleanup: if (error < 0) phy_mdm6600_device_power_off(ddata); - + pm_runtime_disable(ddata->dev); + pm_runtime_dont_use_autosuspend(ddata->dev); return error; } diff --git a/drivers/phy/samsung/phy-exynos5250-sata.c b/drivers/phy/samsung/phy-exynos5250-sata.c index 9ec234243f7c..595adba5fb8f 100644 --- a/drivers/phy/samsung/phy-exynos5250-sata.c +++ b/drivers/phy/samsung/phy-exynos5250-sata.c @@ -187,6 +187,7 @@ static int exynos_sata_phy_probe(struct platform_device *pdev) return -EINVAL; sata_phy->client = of_find_i2c_device_by_node(node); + of_node_put(node); if (!sata_phy->client) return -EPROBE_DEFER; @@ -195,20 +196,21 @@ static int exynos_sata_phy_probe(struct platform_device *pdev) sata_phy->phyclk = devm_clk_get(dev, "sata_phyctrl"); if (IS_ERR(sata_phy->phyclk)) { dev_err(dev, "failed to get clk for PHY\n"); - return PTR_ERR(sata_phy->phyclk); + ret = PTR_ERR(sata_phy->phyclk); + goto put_dev; } ret = clk_prepare_enable(sata_phy->phyclk); if (ret < 0) { dev_err(dev, "failed to enable source clk\n"); - return ret; + goto put_dev; } sata_phy->phy = devm_phy_create(dev, NULL, &exynos_sata_phy_ops); if (IS_ERR(sata_phy->phy)) { - clk_disable_unprepare(sata_phy->phyclk); dev_err(dev, "failed to create PHY\n"); - return PTR_ERR(sata_phy->phy); + ret = PTR_ERR(sata_phy->phy); + goto clk_disable; } phy_set_drvdata(sata_phy->phy, sata_phy); @@ -216,11 +218,18 @@ static int exynos_sata_phy_probe(struct platform_device *pdev) phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate); if (IS_ERR(phy_provider)) { - clk_disable_unprepare(sata_phy->phyclk); - return PTR_ERR(phy_provider); + ret = PTR_ERR(phy_provider); + goto clk_disable; } return 0; + +clk_disable: + clk_disable_unprepare(sata_phy->phyclk); +put_dev: + put_device(&sata_phy->client->dev); + + return ret; } static const struct of_device_id exynos_sata_phy_of_match[] = { diff --git a/drivers/phy/ti/phy-am654-serdes.c b/drivers/phy/ti/phy-am654-serdes.c index c1211c4f863c..0be727bb9f79 100644 --- a/drivers/phy/ti/phy-am654-serdes.c +++ b/drivers/phy/ti/phy-am654-serdes.c @@ -838,7 +838,7 @@ static int serdes_am654_probe(struct platform_device *pdev) clk_err: of_clk_del_provider(node); - + pm_runtime_disable(dev); return ret; } diff --git a/drivers/phy/ti/phy-omap-usb2.c b/drivers/phy/ti/phy-omap-usb2.c index 3a505fe5715a..31a775877f6e 100644 --- a/drivers/phy/ti/phy-omap-usb2.c +++ b/drivers/phy/ti/phy-omap-usb2.c @@ -215,7 +215,7 @@ static int omap_usb2_enable_clocks(struct omap_usb *phy) return 0; err1: - clk_disable(phy->wkupclk); + clk_disable_unprepare(phy->wkupclk); err0: return ret; diff --git a/drivers/phy/ti/phy-ti-pipe3.c b/drivers/phy/ti/phy-ti-pipe3.c index 2cbc91e535d4..f502c36f3be5 100644 --- a/drivers/phy/ti/phy-ti-pipe3.c +++ b/drivers/phy/ti/phy-ti-pipe3.c @@ -696,6 +696,7 @@ static int ti_pipe3_get_sysctrl(struct ti_pipe3 *phy) } control_pdev = of_find_device_by_node(control_node); + of_node_put(control_node); if (!control_pdev) { dev_err(dev, "Failed to get control device\n"); return -EINVAL; diff --git a/drivers/phy/ti/phy-tusb1210.c b/drivers/phy/ti/phy-tusb1210.c index a0cdbcadf09e..c3ab4b69ea68 100644 --- a/drivers/phy/ti/phy-tusb1210.c +++ b/drivers/phy/ti/phy-tusb1210.c @@ -155,7 +155,7 @@ static int tusb1210_set_mode(struct phy *phy, enum phy_mode mode, int submode) } #ifdef CONFIG_POWER_SUPPLY -const char * const tusb1210_chg_det_states[] = { +static const char * const tusb1210_chg_det_states[] = { "CHG_DET_CONNECTING", "CHG_DET_START_DET", "CHG_DET_READ_DET", @@ -537,12 +537,18 @@ static int tusb1210_probe(struct ulpi *ulpi) tusb1210_probe_charger_detect(tusb); tusb->phy = ulpi_phy_create(ulpi, &phy_ops); - if (IS_ERR(tusb->phy)) - return PTR_ERR(tusb->phy); + if (IS_ERR(tusb->phy)) { + ret = PTR_ERR(tusb->phy); + goto err_remove_charger; + } phy_set_drvdata(tusb->phy, tusb); ulpi_set_drvdata(ulpi, tusb); return 0; + +err_remove_charger: + tusb1210_remove_charger_detect(tusb); + return ret; } static void tusb1210_remove(struct ulpi *ulpi) diff --git a/drivers/pinctrl/intel/pinctrl-alderlake.c b/drivers/pinctrl/intel/pinctrl-alderlake.c index 32ba50efbceb..62dbd1e67513 100644 --- a/drivers/pinctrl/intel/pinctrl-alderlake.c +++ b/drivers/pinctrl/intel/pinctrl-alderlake.c @@ -14,11 +14,17 @@ #include "pinctrl-intel.h" -#define ADL_PAD_OWN 0x0a0 -#define ADL_PADCFGLOCK 0x110 -#define ADL_HOSTSW_OWN 0x150 -#define ADL_GPI_IS 0x200 -#define ADL_GPI_IE 0x220 +#define ADL_N_PAD_OWN 0x020 +#define ADL_N_PADCFGLOCK 0x080 +#define ADL_N_HOSTSW_OWN 0x0b0 +#define ADL_N_GPI_IS 0x100 +#define ADL_N_GPI_IE 0x120 + +#define ADL_S_PAD_OWN 0x0a0 +#define ADL_S_PADCFGLOCK 0x110 +#define ADL_S_HOSTSW_OWN 0x150 +#define ADL_S_GPI_IS 0x200 +#define ADL_S_GPI_IE 0x220 #define ADL_GPP(r, s, e, g) \ { \ @@ -28,14 +34,28 @@ .gpio_base = (g), \ } -#define ADL_COMMUNITY(b, s, e, g) \ +#define ADL_N_COMMUNITY(b, s, e, g) \ + { \ + .barno = (b), \ + .padown_offset = ADL_N_PAD_OWN, \ + .padcfglock_offset = ADL_N_PADCFGLOCK, \ + .hostown_offset = ADL_N_HOSTSW_OWN, \ + .is_offset = ADL_N_GPI_IS, \ + .ie_offset = ADL_N_GPI_IE, \ + .pin_base = (s), \ + .npins = ((e) - (s) + 1), \ + .gpps = (g), \ + .ngpps = ARRAY_SIZE(g), \ + } + +#define ADL_S_COMMUNITY(b, s, e, g) \ { \ .barno = (b), \ - .padown_offset = ADL_PAD_OWN, \ - .padcfglock_offset = ADL_PADCFGLOCK, \ - .hostown_offset = ADL_HOSTSW_OWN, \ - .is_offset = ADL_GPI_IS, \ - .ie_offset = ADL_GPI_IE, \ + .padown_offset = ADL_S_PAD_OWN, \ + .padcfglock_offset = ADL_S_PADCFGLOCK, \ + .hostown_offset = ADL_S_HOSTSW_OWN, \ + .is_offset = ADL_S_GPI_IS, \ + .ie_offset = ADL_S_GPI_IE, \ .pin_base = (s), \ .npins = ((e) - (s) + 1), \ .gpps = (g), \ @@ -342,10 +362,10 @@ static const struct intel_padgroup adln_community5_gpps[] = { }; static const struct intel_community adln_communities[] = { - ADL_COMMUNITY(0, 0, 66, adln_community0_gpps), - ADL_COMMUNITY(1, 67, 168, adln_community1_gpps), - ADL_COMMUNITY(2, 169, 248, adln_community4_gpps), - ADL_COMMUNITY(3, 249, 256, adln_community5_gpps), + ADL_N_COMMUNITY(0, 0, 66, adln_community0_gpps), + ADL_N_COMMUNITY(1, 67, 168, adln_community1_gpps), + ADL_N_COMMUNITY(2, 169, 248, adln_community4_gpps), + ADL_N_COMMUNITY(3, 249, 256, adln_community5_gpps), }; static const struct intel_pinctrl_soc_data adln_soc_data = { @@ -713,11 +733,11 @@ static const struct intel_padgroup adls_community5_gpps[] = { }; static const struct intel_community adls_communities[] = { - ADL_COMMUNITY(0, 0, 94, adls_community0_gpps), - ADL_COMMUNITY(1, 95, 150, adls_community1_gpps), - ADL_COMMUNITY(2, 151, 199, adls_community3_gpps), - ADL_COMMUNITY(3, 200, 269, adls_community4_gpps), - ADL_COMMUNITY(4, 270, 303, adls_community5_gpps), + ADL_S_COMMUNITY(0, 0, 94, adls_community0_gpps), + ADL_S_COMMUNITY(1, 95, 150, adls_community1_gpps), + ADL_S_COMMUNITY(2, 151, 199, adls_community3_gpps), + ADL_S_COMMUNITY(3, 200, 269, adls_community4_gpps), + ADL_S_COMMUNITY(4, 270, 303, adls_community5_gpps), }; static const struct intel_pinctrl_soc_data adls_soc_data = { diff --git a/drivers/pinctrl/mediatek/Kconfig b/drivers/pinctrl/mediatek/Kconfig index 8dca1ef04965..40accd110c3d 100644 --- a/drivers/pinctrl/mediatek/Kconfig +++ b/drivers/pinctrl/mediatek/Kconfig @@ -30,6 +30,7 @@ config PINCTRL_MTK_MOORE select GENERIC_PINMUX_FUNCTIONS select GPIOLIB select OF_GPIO + select EINT_MTK select PINCTRL_MTK_V2 config PINCTRL_MTK_PARIS diff --git a/drivers/pinctrl/pinctrl-pistachio.c b/drivers/pinctrl/pinctrl-pistachio.c index 8d271c6b0ca4..5de691c630b4 100644 --- a/drivers/pinctrl/pinctrl-pistachio.c +++ b/drivers/pinctrl/pinctrl-pistachio.c @@ -1374,10 +1374,10 @@ static int pistachio_gpio_register(struct pistachio_pinctrl *pctl) } irq = irq_of_parse_and_map(child, 0); - if (irq < 0) { - dev_err(pctl->dev, "No IRQ for bank %u: %d\n", i, irq); + if (!irq) { + dev_err(pctl->dev, "No IRQ for bank %u\n", i); of_node_put(child); - ret = irq; + ret = -EINVAL; goto err; } diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index a1b598b86aa9..2cb79e649fcf 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -457,95 +457,110 @@ static struct rockchip_mux_recalced_data rk3128_mux_recalced_data[] = { static struct rockchip_mux_recalced_data rk3308_mux_recalced_data[] = { { + /* gpio1b6_sel */ .num = 1, .pin = 14, .reg = 0x28, .bit = 12, .mask = 0xf }, { + /* gpio1b7_sel */ .num = 1, .pin = 15, .reg = 0x2c, .bit = 0, .mask = 0x3 }, { + /* gpio1c2_sel */ .num = 1, .pin = 18, .reg = 0x30, .bit = 4, .mask = 0xf }, { + /* gpio1c3_sel */ .num = 1, .pin = 19, .reg = 0x30, .bit = 8, .mask = 0xf }, { + /* gpio1c4_sel */ .num = 1, .pin = 20, .reg = 0x30, .bit = 12, .mask = 0xf }, { + /* gpio1c5_sel */ .num = 1, .pin = 21, .reg = 0x34, .bit = 0, .mask = 0xf }, { + /* gpio1c6_sel */ .num = 1, .pin = 22, .reg = 0x34, .bit = 4, .mask = 0xf }, { + /* gpio1c7_sel */ .num = 1, .pin = 23, .reg = 0x34, .bit = 8, .mask = 0xf }, { - .num = 3, - .pin = 12, - .reg = 0x68, - .bit = 8, - .mask = 0xf - }, { - .num = 3, - .pin = 13, - .reg = 0x68, - .bit = 12, - .mask = 0xf - }, { + /* gpio2a2_sel */ .num = 2, .pin = 2, - .reg = 0x608, - .bit = 0, - .mask = 0x7 + .reg = 0x40, + .bit = 4, + .mask = 0x3 }, { + /* gpio2a3_sel */ .num = 2, .pin = 3, - .reg = 0x608, - .bit = 4, - .mask = 0x7 + .reg = 0x40, + .bit = 6, + .mask = 0x3 }, { + /* gpio2c0_sel */ .num = 2, .pin = 16, - .reg = 0x610, - .bit = 8, - .mask = 0x7 + .reg = 0x50, + .bit = 0, + .mask = 0x3 }, { + /* gpio3b2_sel */ .num = 3, .pin = 10, - .reg = 0x610, - .bit = 0, - .mask = 0x7 + .reg = 0x68, + .bit = 4, + .mask = 0x3 }, { + /* gpio3b3_sel */ .num = 3, .pin = 11, - .reg = 0x610, - .bit = 4, - .mask = 0x7 + .reg = 0x68, + .bit = 6, + .mask = 0x3 + }, { + /* gpio3b4_sel */ + .num = 3, + .pin = 12, + .reg = 0x68, + .bit = 8, + .mask = 0xf + }, { + /* gpio3b5_sel */ + .num = 3, + .pin = 13, + .reg = 0x68, + .bit = 12, + .mask = 0xf }, }; diff --git a/drivers/pinctrl/qcom/pinctrl-sm6350.c b/drivers/pinctrl/qcom/pinctrl-sm6350.c index 4d37b817b232..a91a86628f2f 100644 --- a/drivers/pinctrl/qcom/pinctrl-sm6350.c +++ b/drivers/pinctrl/qcom/pinctrl-sm6350.c @@ -264,14 +264,14 @@ static const struct pinctrl_pin_desc sm6350_pins[] = { PINCTRL_PIN(153, "GPIO_153"), PINCTRL_PIN(154, "GPIO_154"), PINCTRL_PIN(155, "GPIO_155"), - PINCTRL_PIN(156, "SDC1_RCLK"), - PINCTRL_PIN(157, "SDC1_CLK"), - PINCTRL_PIN(158, "SDC1_CMD"), - PINCTRL_PIN(159, "SDC1_DATA"), - PINCTRL_PIN(160, "SDC2_CLK"), - PINCTRL_PIN(161, "SDC2_CMD"), - PINCTRL_PIN(162, "SDC2_DATA"), - PINCTRL_PIN(163, "UFS_RESET"), + PINCTRL_PIN(156, "UFS_RESET"), + PINCTRL_PIN(157, "SDC1_RCLK"), + PINCTRL_PIN(158, "SDC1_CLK"), + PINCTRL_PIN(159, "SDC1_CMD"), + PINCTRL_PIN(160, "SDC1_DATA"), + PINCTRL_PIN(161, "SDC2_CLK"), + PINCTRL_PIN(162, "SDC2_CMD"), + PINCTRL_PIN(163, "SDC2_DATA"), }; #define DECLARE_MSM_GPIO_PINS(pin) \ diff --git a/drivers/pinctrl/samsung/Kconfig b/drivers/pinctrl/samsung/Kconfig index dfd805e76862..7b0576f71376 100644 --- a/drivers/pinctrl/samsung/Kconfig +++ b/drivers/pinctrl/samsung/Kconfig @@ -4,14 +4,13 @@ # config PINCTRL_SAMSUNG bool - depends on OF_GPIO + select GPIOLIB select PINMUX select PINCONF config PINCTRL_EXYNOS bool "Pinctrl common driver part for Samsung Exynos SoCs" - depends on OF_GPIO - depends on ARCH_EXYNOS || ARCH_S5PV210 || COMPILE_TEST + depends on ARCH_EXYNOS || ARCH_S5PV210 || (COMPILE_TEST && OF) select PINCTRL_SAMSUNG select PINCTRL_EXYNOS_ARM if ARM && (ARCH_EXYNOS || ARCH_S5PV210) select PINCTRL_EXYNOS_ARM64 if ARM64 && ARCH_EXYNOS @@ -26,12 +25,10 @@ config PINCTRL_EXYNOS_ARM64 config PINCTRL_S3C24XX bool "Samsung S3C24XX SoC pinctrl driver" - depends on OF_GPIO - depends on ARCH_S3C24XX || COMPILE_TEST + depends on ARCH_S3C24XX || (COMPILE_TEST && OF) select PINCTRL_SAMSUNG config PINCTRL_S3C64XX bool "Samsung S3C64XX SoC pinctrl driver" - depends on OF_GPIO - depends on ARCH_S3C64XX || COMPILE_TEST + depends on ARCH_S3C64XX || (COMPILE_TEST && OF) select PINCTRL_SAMSUNG diff --git a/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c b/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c index d291819c2f77..cb965cf93705 100644 --- a/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c +++ b/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c @@ -770,7 +770,7 @@ static const struct samsung_pin_bank_data fsd_pin_banks2[] __initconst = { EXYNOS850_PIN_BANK_EINTN(3, 0x00, "gpq0"), }; -const struct samsung_pin_ctrl fsd_pin_ctrl[] __initconst = { +static const struct samsung_pin_ctrl fsd_pin_ctrl[] __initconst = { { /* pin-controller instance 0 FSYS0 data */ .pin_banks = fsd_pin_banks0, diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c index 9ed764731570..f7c9459f6628 100644 --- a/drivers/pinctrl/stm32/pinctrl-stm32.c +++ b/drivers/pinctrl/stm32/pinctrl-stm32.c @@ -225,6 +225,13 @@ static void stm32_gpio_free(struct gpio_chip *chip, unsigned offset) pinctrl_gpio_free(chip->base + offset); } +static int stm32_gpio_get_noclk(struct gpio_chip *chip, unsigned int offset) +{ + struct stm32_gpio_bank *bank = gpiochip_get_data(chip); + + return !!(readl_relaxed(bank->base + STM32_GPIO_IDR) & BIT(offset)); +} + static int stm32_gpio_get(struct gpio_chip *chip, unsigned offset) { struct stm32_gpio_bank *bank = gpiochip_get_data(chip); @@ -232,7 +239,7 @@ static int stm32_gpio_get(struct gpio_chip *chip, unsigned offset) clk_enable(bank->clk); - ret = !!(readl_relaxed(bank->base + STM32_GPIO_IDR) & BIT(offset)); + ret = stm32_gpio_get_noclk(chip, offset); clk_disable(bank->clk); @@ -311,8 +318,12 @@ static void stm32_gpio_irq_trigger(struct irq_data *d) struct stm32_gpio_bank *bank = d->domain->host_data; int level; + /* Do not access the GPIO if this is not LEVEL triggered IRQ. */ + if (!(bank->irq_type[d->hwirq] & IRQ_TYPE_LEVEL_MASK)) + return; + /* If level interrupt type then retrig */ - level = stm32_gpio_get(&bank->gpio_chip, d->hwirq); + level = stm32_gpio_get_noclk(&bank->gpio_chip, d->hwirq); if ((level == 0 && bank->irq_type[d->hwirq] == IRQ_TYPE_LEVEL_LOW) || (level == 1 && bank->irq_type[d->hwirq] == IRQ_TYPE_LEVEL_HIGH)) irq_chip_retrigger_hierarchy(d); @@ -354,6 +365,7 @@ static int stm32_gpio_irq_request_resources(struct irq_data *irq_data) { struct stm32_gpio_bank *bank = irq_data->domain->host_data; struct stm32_pinctrl *pctl = dev_get_drvdata(bank->gpio_chip.parent); + unsigned long flags; int ret; ret = stm32_gpio_direction_input(&bank->gpio_chip, irq_data->hwirq); @@ -367,6 +379,10 @@ static int stm32_gpio_irq_request_resources(struct irq_data *irq_data) return ret; } + flags = irqd_get_trigger_type(irq_data); + if (flags & IRQ_TYPE_LEVEL_MASK) + clk_enable(bank->clk); + return 0; } @@ -374,6 +390,9 @@ static void stm32_gpio_irq_release_resources(struct irq_data *irq_data) { struct stm32_gpio_bank *bank = irq_data->domain->host_data; + if (bank->irq_type[irq_data->hwirq] & IRQ_TYPE_LEVEL_MASK) + clk_disable(bank->clk); + gpiochip_unlock_as_irq(&bank->gpio_chip, irq_data->hwirq); } diff --git a/drivers/pinctrl/sunplus/sppctl_sp7021.c b/drivers/pinctrl/sunplus/sppctl_sp7021.c index 9748345b9298..cd657760a644 100644 --- a/drivers/pinctrl/sunplus/sppctl_sp7021.c +++ b/drivers/pinctrl/sunplus/sppctl_sp7021.c @@ -419,7 +419,15 @@ static const struct sppctl_grp sp7021grps_prbp[] = { EGRP("PROBE_PORT2", 2, pins_prp2), }; +/* + * Due to compatible reason, the first valid item should start at the third + * position of the array. Please keep the first two items of the table + * no use (dummy). + */ const struct sppctl_func sppctl_list_funcs[] = { + FNCN("", pinmux_type_fpmx, 0x00, 0, 0), + FNCN("", pinmux_type_fpmx, 0x00, 0, 0), + FNCN("L2SW_CLK_OUT", pinmux_type_fpmx, 0x00, 0, 7), FNCN("L2SW_MAC_SMI_MDC", pinmux_type_fpmx, 0x00, 8, 7), FNCN("L2SW_LED_FLASH0", pinmux_type_fpmx, 0x01, 0, 7), diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 2104a2621e50..0e7fbed8a50d 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -371,10 +371,14 @@ static int asus_wmi_evaluate_method_buf(u32 method_id, switch (obj->type) { case ACPI_TYPE_BUFFER: - if (obj->buffer.length > size) + if (obj->buffer.length > size) { err = -ENOSPC; - if (obj->buffer.length == 0) + break; + } + if (obj->buffer.length == 0) { err = -ENODATA; + break; + } memcpy(ret_buffer, obj->buffer.pointer, obj->buffer.length); break; @@ -2223,9 +2227,10 @@ static int fan_curve_check_present(struct asus_wmi *asus, bool *available, err = fan_curve_get_factory_default(asus, fan_dev); if (err) { - if (err == -ENODEV || err == -ENODATA) - return 0; - return err; + pr_debug("fan_curve_get_factory_default(0x%08x) failed: %d\n", + fan_dev, err); + /* Don't cause probe to fail on devices without fan-curves */ + return 0; } *available = true; diff --git a/drivers/platform/x86/dell/dell-laptop.c b/drivers/platform/x86/dell/dell-laptop.c index 8230e7a68a5e..1321687d923e 100644 --- a/drivers/platform/x86/dell/dell-laptop.c +++ b/drivers/platform/x86/dell/dell-laptop.c @@ -80,6 +80,10 @@ static struct quirk_entry quirk_dell_inspiron_1012 = { .kbd_led_not_present = true, }; +static struct quirk_entry quirk_dell_latitude_7520 = { + .kbd_missing_ac_tag = true, +}; + static struct platform_driver platform_driver = { .driver = { .name = "dell-laptop", @@ -336,6 +340,15 @@ static const struct dmi_system_id dell_quirks[] __initconst = { }, .driver_data = &quirk_dell_inspiron_1012, }, + { + .callback = dmi_matched, + .ident = "Dell Latitude 7520", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude 7520"), + }, + .driver_data = &quirk_dell_latitude_7520, + }, { } }; diff --git a/drivers/platform/x86/gigabyte-wmi.c b/drivers/platform/x86/gigabyte-wmi.c index 658bab4b7964..e87a931eab1e 100644 --- a/drivers/platform/x86/gigabyte-wmi.c +++ b/drivers/platform/x86/gigabyte-wmi.c @@ -148,6 +148,7 @@ static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = { DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550I AORUS PRO AX"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550M AORUS PRO-P"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550M DS3H"), + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B660 GAMING X DDR4"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("Z390 I AORUS PRO WIFI-CF"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 AORUS ELITE"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 GAMING X"), diff --git a/drivers/platform/x86/intel/pmc/core.h b/drivers/platform/x86/intel/pmc/core.h index a46d3b53bf61..7a059e02c265 100644 --- a/drivers/platform/x86/intel/pmc/core.h +++ b/drivers/platform/x86/intel/pmc/core.h @@ -236,7 +236,7 @@ enum ppfear_regs { #define ADL_LPM_STATUS_LATCH_EN_OFFSET 0x1704 #define ADL_LPM_LIVE_STATUS_OFFSET 0x1764 -const char *pmc_lpm_modes[] = { +static const char *pmc_lpm_modes[] = { "S0i2.0", "S0i2.1", "S0i2.2", diff --git a/drivers/platform/x86/intel/sdsi.c b/drivers/platform/x86/intel/sdsi.c index 11d14cc0ff0a..c830e98dfa38 100644 --- a/drivers/platform/x86/intel/sdsi.c +++ b/drivers/platform/x86/intel/sdsi.c @@ -51,6 +51,8 @@ #define MBOX_TIMEOUT_US 2000 #define MBOX_TIMEOUT_ACQUIRE_US 1000 #define MBOX_POLLING_PERIOD_US 100 +#define MBOX_ACQUIRE_NUM_RETRIES 5 +#define MBOX_ACQUIRE_RETRY_DELAY_MS 500 #define MBOX_MAX_PACKETS 4 #define MBOX_OWNER_NONE 0x00 @@ -81,7 +83,7 @@ enum sdsi_command { struct sdsi_mbox_info { u64 *payload; - u64 *buffer; + void *buffer; int size; }; @@ -163,9 +165,7 @@ static int sdsi_mbox_cmd_read(struct sdsi_priv *priv, struct sdsi_mbox_info *inf total = 0; loop = 0; do { - int offset = SDSI_SIZE_MAILBOX * loop; - void __iomem *addr = priv->mbox_addr + offset; - u64 *buf = info->buffer + offset / SDSI_SIZE_CMD; + void *buf = info->buffer + (SDSI_SIZE_MAILBOX * loop); u32 packet_size; /* Poll on ready bit */ @@ -196,7 +196,7 @@ static int sdsi_mbox_cmd_read(struct sdsi_priv *priv, struct sdsi_mbox_info *inf break; } - sdsi_memcpy64_fromio(buf, addr, round_up(packet_size, SDSI_SIZE_CMD)); + sdsi_memcpy64_fromio(buf, priv->mbox_addr, round_up(packet_size, SDSI_SIZE_CMD)); total += packet_size; @@ -243,8 +243,8 @@ static int sdsi_mbox_cmd_write(struct sdsi_priv *priv, struct sdsi_mbox_info *in FIELD_PREP(CTRL_PACKET_SIZE, info->size); writeq(control, priv->control_addr); - /* Poll on run_busy bit */ - ret = readq_poll_timeout(priv->control_addr, control, !(control & CTRL_RUN_BUSY), + /* Poll on ready bit */ + ret = readq_poll_timeout(priv->control_addr, control, control & CTRL_READY, MBOX_POLLING_PERIOD_US, MBOX_TIMEOUT_US); if (ret) @@ -263,7 +263,7 @@ static int sdsi_mbox_acquire(struct sdsi_priv *priv, struct sdsi_mbox_info *info { u64 control; u32 owner; - int ret; + int ret, retries = 0; lockdep_assert_held(&priv->mb_lock); @@ -273,13 +273,29 @@ static int sdsi_mbox_acquire(struct sdsi_priv *priv, struct sdsi_mbox_info *info if (owner != MBOX_OWNER_NONE) return -EBUSY; - /* Write first qword of payload */ - writeq(info->payload[0], priv->mbox_addr); + /* + * If there has been no recent transaction and no one owns the mailbox, + * we should acquire it in under 1ms. However, if we've accessed it + * recently it may take up to 2.1 seconds to acquire it again. + */ + do { + /* Write first qword of payload */ + writeq(info->payload[0], priv->mbox_addr); + + /* Check for ownership */ + ret = readq_poll_timeout(priv->control_addr, control, + FIELD_GET(CTRL_OWNER, control) == MBOX_OWNER_INBAND, + MBOX_POLLING_PERIOD_US, MBOX_TIMEOUT_ACQUIRE_US); + + if (FIELD_GET(CTRL_OWNER, control) == MBOX_OWNER_NONE && + retries++ < MBOX_ACQUIRE_NUM_RETRIES) { + msleep(MBOX_ACQUIRE_RETRY_DELAY_MS); + continue; + } - /* Check for ownership */ - ret = readq_poll_timeout(priv->control_addr, control, - FIELD_GET(CTRL_OWNER, control) & MBOX_OWNER_INBAND, - MBOX_POLLING_PERIOD_US, MBOX_TIMEOUT_ACQUIRE_US); + /* Either we got it or someone else did. */ + break; + } while (true); return ret; } diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c index c61f804dd44e..8f9c571d7257 100644 --- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c +++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c @@ -212,6 +212,9 @@ static int __init intel_uncore_init(void) const struct x86_cpu_id *id; int ret; + if (cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) + return -ENODEV; + id = x86_match_cpu(intel_uncore_cpu_ids); if (!id) return -ENODEV; diff --git a/drivers/scsi/sr_ioctl.c b/drivers/scsi/sr_ioctl.c index ddd00efc4882..fbdb5124d7f7 100644 --- a/drivers/scsi/sr_ioctl.c +++ b/drivers/scsi/sr_ioctl.c @@ -41,7 +41,7 @@ static int sr_read_tochdr(struct cdrom_device_info *cdi, int result; unsigned char *buffer; - buffer = kmalloc(32, GFP_KERNEL); + buffer = kzalloc(32, GFP_KERNEL); if (!buffer) return -ENOMEM; @@ -55,10 +55,13 @@ static int sr_read_tochdr(struct cdrom_device_info *cdi, cgc.data_direction = DMA_FROM_DEVICE; result = sr_do_ioctl(cd, &cgc); + if (result) + goto err; tochdr->cdth_trk0 = buffer[2]; tochdr->cdth_trk1 = buffer[3]; +err: kfree(buffer); return result; } @@ -71,7 +74,7 @@ static int sr_read_tocentry(struct cdrom_device_info *cdi, int result; unsigned char *buffer; - buffer = kmalloc(32, GFP_KERNEL); + buffer = kzalloc(32, GFP_KERNEL); if (!buffer) return -ENOMEM; @@ -86,6 +89,8 @@ static int sr_read_tocentry(struct cdrom_device_info *cdi, cgc.data_direction = DMA_FROM_DEVICE; result = sr_do_ioctl(cd, &cgc); + if (result) + goto err; tocentry->cdte_ctrl = buffer[5] & 0xf; tocentry->cdte_adr = buffer[5] >> 4; @@ -98,6 +103,7 @@ static int sr_read_tocentry(struct cdrom_device_info *cdi, tocentry->cdte_addr.lba = (((((buffer[8] << 8) + buffer[9]) << 8) + buffer[10]) << 8) + buffer[11]; +err: kfree(buffer); return result; } @@ -384,7 +390,7 @@ int sr_get_mcn(struct cdrom_device_info *cdi, struct cdrom_mcn *mcn) { Scsi_CD *cd = cdi->handle; struct packet_command cgc; - char *buffer = kmalloc(32, GFP_KERNEL); + char *buffer = kzalloc(32, GFP_KERNEL); int result; if (!buffer) @@ -400,10 +406,13 @@ int sr_get_mcn(struct cdrom_device_info *cdi, struct cdrom_mcn *mcn) cgc.data_direction = DMA_FROM_DEVICE; cgc.timeout = IOCTL_TIMEOUT; result = sr_do_ioctl(cd, &cgc); + if (result) + goto err; memcpy(mcn->medium_catalog_number, buffer + 9, 13); mcn->medium_catalog_number[13] = 0; +err: kfree(buffer); return result; } diff --git a/drivers/soc/imx/imx8m-blk-ctrl.c b/drivers/soc/imx/imx8m-blk-ctrl.c index 122f9c884b38..ccd0577a771e 100644 --- a/drivers/soc/imx/imx8m-blk-ctrl.c +++ b/drivers/soc/imx/imx8m-blk-ctrl.c @@ -50,7 +50,7 @@ struct imx8m_blk_ctrl_domain_data { u32 mipi_phy_rst_mask; }; -#define DOMAIN_MAX_CLKS 3 +#define DOMAIN_MAX_CLKS 4 struct imx8m_blk_ctrl_domain { struct generic_pm_domain genpd; diff --git a/drivers/spi/atmel-quadspi.c b/drivers/spi/atmel-quadspi.c index 92d9610df1fd..938017a60c8e 100644 --- a/drivers/spi/atmel-quadspi.c +++ b/drivers/spi/atmel-quadspi.c @@ -277,6 +277,9 @@ static int atmel_qspi_find_mode(const struct spi_mem_op *op) static bool atmel_qspi_supports_op(struct spi_mem *mem, const struct spi_mem_op *op) { + if (!spi_mem_default_supports_op(mem, op)) + return false; + if (atmel_qspi_find_mode(op) < 0) return false; diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 616ada891974..19686fb47bb3 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -1415,9 +1415,24 @@ static bool cqspi_supports_mem_op(struct spi_mem *mem, all_false = !op->cmd.dtr && !op->addr.dtr && !op->dummy.dtr && !op->data.dtr; - /* Mixed DTR modes not supported. */ - if (!(all_true || all_false)) + if (all_true) { + /* Right now we only support 8-8-8 DTR mode. */ + if (op->cmd.nbytes && op->cmd.buswidth != 8) + return false; + if (op->addr.nbytes && op->addr.buswidth != 8) + return false; + if (op->data.nbytes && op->data.buswidth != 8) + return false; + } else if (all_false) { + /* Only 1-1-X ops are supported without DTR */ + if (op->cmd.nbytes && op->cmd.buswidth > 1) + return false; + if (op->addr.nbytes && op->addr.buswidth > 1) + return false; + } else { + /* Mixed DTR modes are not supported. */ return false; + } return spi_mem_default_supports_op(mem, op); } diff --git a/drivers/spi/spi-intel-pci.c b/drivers/spi/spi-intel-pci.c index a5ef7a526a7f..f6eec7a869b6 100644 --- a/drivers/spi/spi-intel-pci.c +++ b/drivers/spi/spi-intel-pci.c @@ -72,6 +72,7 @@ static const struct pci_device_id intel_spi_pci_ids[] = { { PCI_VDEVICE(INTEL, 0x4da4), (unsigned long)&bxt_info }, { PCI_VDEVICE(INTEL, 0x51a4), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x54a4), (unsigned long)&cnl_info }, + { PCI_VDEVICE(INTEL, 0x7a24), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x7aa4), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0xa0a4), (unsigned long)&bxt_info }, { PCI_VDEVICE(INTEL, 0xa1a4), (unsigned long)&bxt_info }, diff --git a/drivers/spi/spi-mtk-nor.c b/drivers/spi/spi-mtk-nor.c index 94fb09696677..d167699a1a96 100644 --- a/drivers/spi/spi-mtk-nor.c +++ b/drivers/spi/spi-mtk-nor.c @@ -960,7 +960,17 @@ static int __maybe_unused mtk_nor_suspend(struct device *dev) static int __maybe_unused mtk_nor_resume(struct device *dev) { - return pm_runtime_force_resume(dev); + struct spi_controller *ctlr = dev_get_drvdata(dev); + struct mtk_nor *sp = spi_controller_get_devdata(ctlr); + int ret; + + ret = pm_runtime_force_resume(dev); + if (ret) + return ret; + + mtk_nor_init(sp); + + return 0; } static const struct dev_pm_ops mtk_nor_pm_ops = { diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index ff292b75e23f..60dafe4c581b 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -588,7 +588,7 @@ static void pscsi_destroy_device(struct se_device *dev) } static void pscsi_complete_cmd(struct se_cmd *cmd, u8 scsi_status, - unsigned char *req_sense) + unsigned char *req_sense, int valid_data) { struct pscsi_dev_virt *pdv = PSCSI_DEV(cmd->se_dev); struct scsi_device *sd = pdv->pdv_sd; @@ -681,7 +681,7 @@ after_mode_select: * back despite framework assumption that a * check condition means there is no data */ - if (sd->type == TYPE_TAPE && + if (sd->type == TYPE_TAPE && valid_data && cmd->data_direction == DMA_FROM_DEVICE) { /* * is sense data valid, fixed format, @@ -1032,6 +1032,7 @@ static void pscsi_req_done(struct request *req, blk_status_t status) struct se_cmd *cmd = req->end_io_data; struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(req); enum sam_status scsi_status = scmd->result & 0xff; + int valid_data = cmd->data_length - scmd->resid_len; u8 *cdb = cmd->priv; if (scsi_status != SAM_STAT_GOOD) { @@ -1039,12 +1040,11 @@ static void pscsi_req_done(struct request *req, blk_status_t status) " 0x%02x Result: 0x%08x\n", cmd, cdb[0], scmd->result); } - pscsi_complete_cmd(cmd, scsi_status, scmd->sense_buffer); + pscsi_complete_cmd(cmd, scsi_status, scmd->sense_buffer, valid_data); switch (host_byte(scmd->result)) { case DID_OK: - target_complete_cmd_with_length(cmd, scsi_status, - cmd->data_length - scmd->resid_len); + target_complete_cmd_with_length(cmd, scsi_status, valid_data); break; default: pr_debug("PSCSI Host Byte exception at cmd: %p CDB:" diff --git a/drivers/tee/optee/ffa_abi.c b/drivers/tee/optee/ffa_abi.c index a5eb4ef46971..c9b3b2cfb2b2 100644 --- a/drivers/tee/optee/ffa_abi.c +++ b/drivers/tee/optee/ffa_abi.c @@ -865,6 +865,7 @@ err_rhashtable_free: rhashtable_free_and_destroy(&optee->ffa.global_ids, rh_free_fn, NULL); optee_supp_uninit(&optee->supp); mutex_destroy(&optee->call_queue.mutex); + mutex_destroy(&optee->ffa.mutex); err_unreg_supp_teedev: tee_device_unregister(optee->supp_teedev); err_unreg_teedev: diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig index e37691e0bf20..0e5cc948373c 100644 --- a/drivers/thermal/Kconfig +++ b/drivers/thermal/Kconfig @@ -113,8 +113,10 @@ config THERMAL_DEFAULT_GOV_USER_SPACE bool "user_space" select THERMAL_GOV_USER_SPACE help - Select this if you want to let the user space manage the - platform thermals. + The Userspace governor allows to get trip point crossed + notification from the kernel via uevents. It is recommended + to use the netlink interface instead which gives richer + information about the thermal framework events. config THERMAL_DEFAULT_GOV_POWER_ALLOCATOR bool "power_allocator" diff --git a/drivers/thermal/gov_user_space.c b/drivers/thermal/gov_user_space.c index 64a18e354a20..a62a4e90bd3f 100644 --- a/drivers/thermal/gov_user_space.c +++ b/drivers/thermal/gov_user_space.c @@ -17,8 +17,7 @@ static int user_space_bind(struct thermal_zone_device *tz) { - pr_warn_once("Userspace governor deprecated: use thermal netlink " \ - "notification instead\n"); + pr_info_once("Consider using thermal netlink events interface\n"); return 0; } diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c index 4954800b9850..d97f496bab9b 100644 --- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c +++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c @@ -68,7 +68,7 @@ static int evaluate_odvp(struct int3400_thermal_priv *priv); struct odvp_attr { int odvp; struct int3400_thermal_priv *priv; - struct kobj_attribute attr; + struct device_attribute attr; }; static ssize_t data_vault_read(struct file *file, struct kobject *kobj, @@ -311,7 +311,7 @@ end: return result; } -static ssize_t odvp_show(struct kobject *kobj, struct kobj_attribute *attr, +static ssize_t odvp_show(struct device *dev, struct device_attribute *attr, char *buf) { struct odvp_attr *odvp_attr; diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c index f154bada2906..1c4aac8464a7 100644 --- a/drivers/thermal/thermal_sysfs.c +++ b/drivers/thermal/thermal_sysfs.c @@ -610,9 +610,6 @@ cur_state_store(struct device *dev, struct device_attribute *attr, unsigned long state; int result; - dev_warn_once(&cdev->device, - "Setting cooling device state is deprecated\n"); - if (sscanf(buf, "%ld\n", &state) != 1) return -EINVAL; diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index fa92f727fdf8..a38b922bcbc1 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -73,6 +73,8 @@ module_param(debug, int, 0600); */ #define MAX_MRU 1500 #define MAX_MTU 1500 +/* SOF, ADDR, CTRL, LEN1, LEN2, ..., FCS, EOF */ +#define PROT_OVERHEAD 7 #define GSM_NET_TX_TIMEOUT (HZ*10) /* @@ -219,7 +221,6 @@ struct gsm_mux { int encoding; u8 control; u8 fcs; - u8 received_fcs; u8 *txframe; /* TX framing buffer */ /* Method for the receiver side */ @@ -231,6 +232,7 @@ struct gsm_mux { int initiator; /* Did we initiate connection */ bool dead; /* Has the mux been shut down */ struct gsm_dlci *dlci[NUM_DLCI]; + int old_c_iflag; /* termios c_iflag value before attach */ bool constipated; /* Asked by remote to shut up */ spinlock_t tx_lock; @@ -271,10 +273,6 @@ static DEFINE_SPINLOCK(gsm_mux_lock); static struct tty_driver *gsm_tty_driver; -/* Save dlci open address */ -static int addr_open[256] = { 0 }; -/* Save dlci open count */ -static int addr_cnt; /* * This section of the driver logic implements the GSM encodings * both the basic and the 'advanced'. Reliable transport is not @@ -369,6 +367,7 @@ static const u8 gsm_fcs8[256] = { #define GOOD_FCS 0xCF static int gsmld_output(struct gsm_mux *gsm, u8 *data, int len); +static int gsm_modem_update(struct gsm_dlci *dlci, u8 brk); /** * gsm_fcs_add - update FCS @@ -832,7 +831,7 @@ static int gsm_dlci_data_output(struct gsm_mux *gsm, struct gsm_dlci *dlci) break; case 2: /* Unstructed with modem bits. Always one byte as we never send inline break data */ - *dp++ = gsm_encode_modem(dlci); + *dp++ = (gsm_encode_modem(dlci) << 1) | EA; break; } WARN_ON(kfifo_out_locked(&dlci->fifo, dp , len, &dlci->lock) != len); @@ -917,6 +916,66 @@ static int gsm_dlci_data_output_framed(struct gsm_mux *gsm, } /** + * gsm_dlci_modem_output - try and push modem status out of a DLCI + * @gsm: mux + * @dlci: the DLCI to pull modem status from + * @brk: break signal + * + * Push an empty frame in to the transmit queue to update the modem status + * bits and to transmit an optional break. + * + * Caller must hold the tx_lock of the mux. + */ + +static int gsm_dlci_modem_output(struct gsm_mux *gsm, struct gsm_dlci *dlci, + u8 brk) +{ + u8 *dp = NULL; + struct gsm_msg *msg; + int size = 0; + + /* for modem bits without break data */ + switch (dlci->adaption) { + case 1: /* Unstructured */ + break; + case 2: /* Unstructured with modem bits. */ + size++; + if (brk > 0) + size++; + break; + default: + pr_err("%s: unsupported adaption %d\n", __func__, + dlci->adaption); + return -EINVAL; + } + + msg = gsm_data_alloc(gsm, dlci->addr, size, gsm->ftype); + if (!msg) { + pr_err("%s: gsm_data_alloc error", __func__); + return -ENOMEM; + } + dp = msg->data; + switch (dlci->adaption) { + case 1: /* Unstructured */ + break; + case 2: /* Unstructured with modem bits. */ + if (brk == 0) { + *dp++ = (gsm_encode_modem(dlci) << 1) | EA; + } else { + *dp++ = gsm_encode_modem(dlci) << 1; + *dp++ = (brk << 4) | 2 | EA; /* Length, Break, EA */ + } + break; + default: + /* Handled above */ + break; + } + + __gsm_data_queue(dlci, msg); + return size; +} + +/** * gsm_dlci_data_sweep - look for data to send * @gsm: the GSM mux * @@ -1093,7 +1152,6 @@ static void gsm_control_modem(struct gsm_mux *gsm, const u8 *data, int clen) { unsigned int addr = 0; unsigned int modem = 0; - unsigned int brk = 0; struct gsm_dlci *dlci; int len = clen; int slen; @@ -1123,17 +1181,8 @@ static void gsm_control_modem(struct gsm_mux *gsm, const u8 *data, int clen) return; } len--; - if (len > 0) { - while (gsm_read_ea(&brk, *dp++) == 0) { - len--; - if (len == 0) - return; - } - modem <<= 7; - modem |= (brk & 0x7f); - } tty = tty_port_tty_get(&dlci->port); - gsm_process_modem(tty, dlci, modem, slen); + gsm_process_modem(tty, dlci, modem, slen - len); if (tty) { tty_wakeup(tty); tty_kref_put(tty); @@ -1193,7 +1242,6 @@ static void gsm_control_rls(struct gsm_mux *gsm, const u8 *data, int clen) } static void gsm_dlci_begin_close(struct gsm_dlci *dlci); -static void gsm_dlci_close(struct gsm_dlci *dlci); /** * gsm_control_message - DLCI 0 control processing @@ -1212,28 +1260,15 @@ static void gsm_control_message(struct gsm_mux *gsm, unsigned int command, { u8 buf[1]; unsigned long flags; - struct gsm_dlci *dlci; - int i; - int address; switch (command) { case CMD_CLD: { - if (addr_cnt > 0) { - for (i = 0; i < addr_cnt; i++) { - address = addr_open[i]; - dlci = gsm->dlci[address]; - gsm_dlci_close(dlci); - addr_open[i] = 0; - } - } + struct gsm_dlci *dlci = gsm->dlci[0]; /* Modem wishes to close down */ - dlci = gsm->dlci[0]; if (dlci) { dlci->dead = true; gsm->dead = true; - gsm_dlci_close(dlci); - addr_cnt = 0; - gsm_response(gsm, 0, UA|PF); + gsm_dlci_begin_close(dlci); } } break; @@ -1326,11 +1361,12 @@ static void gsm_control_response(struct gsm_mux *gsm, unsigned int command, static void gsm_control_transmit(struct gsm_mux *gsm, struct gsm_control *ctrl) { - struct gsm_msg *msg = gsm_data_alloc(gsm, 0, ctrl->len + 1, gsm->ftype); + struct gsm_msg *msg = gsm_data_alloc(gsm, 0, ctrl->len + 2, gsm->ftype); if (msg == NULL) return; - msg->data[0] = (ctrl->cmd << 1) | 2 | EA; /* command */ - memcpy(msg->data + 1, ctrl->data, ctrl->len); + msg->data[0] = (ctrl->cmd << 1) | CR | EA; /* command */ + msg->data[1] = (ctrl->len << 1) | EA; + memcpy(msg->data + 2, ctrl->data, ctrl->len); gsm_data_queue(gsm->dlci[0], msg); } @@ -1353,7 +1389,6 @@ static void gsm_control_retransmit(struct timer_list *t) spin_lock_irqsave(&gsm->control_lock, flags); ctrl = gsm->pending_cmd; if (ctrl) { - gsm->cretries--; if (gsm->cretries == 0) { gsm->pending_cmd = NULL; ctrl->error = -ETIMEDOUT; @@ -1362,6 +1397,7 @@ static void gsm_control_retransmit(struct timer_list *t) wake_up(&gsm->event); return; } + gsm->cretries--; gsm_control_transmit(gsm, ctrl); mod_timer(&gsm->t2_timer, jiffies + gsm->t2 * HZ / 100); } @@ -1402,7 +1438,7 @@ retry: /* If DLCI0 is in ADM mode skip retries, it won't respond */ if (gsm->dlci[0]->mode == DLCI_MODE_ADM) - gsm->cretries = 1; + gsm->cretries = 0; else gsm->cretries = gsm->n2; @@ -1450,20 +1486,22 @@ static int gsm_control_wait(struct gsm_mux *gsm, struct gsm_control *control) static void gsm_dlci_close(struct gsm_dlci *dlci) { + unsigned long flags; + del_timer(&dlci->t1); if (debug & 8) pr_debug("DLCI %d goes closed.\n", dlci->addr); dlci->state = DLCI_CLOSED; if (dlci->addr != 0) { tty_port_tty_hangup(&dlci->port, false); + spin_lock_irqsave(&dlci->lock, flags); kfifo_reset(&dlci->fifo); + spin_unlock_irqrestore(&dlci->lock, flags); /* Ensure that gsmtty_open() can return. */ tty_port_set_initialized(&dlci->port, 0); wake_up_interruptible(&dlci->port.open_wait); } else dlci->gsm->dead = true; - /* Unregister gsmtty driver,report gsmtty dev remove uevent for user */ - tty_unregister_device(gsm_tty_driver, dlci->addr); wake_up(&dlci->gsm->event); /* A DLCI 0 close is a MUX termination so we need to kick that back to userspace somehow */ @@ -1485,8 +1523,9 @@ static void gsm_dlci_open(struct gsm_dlci *dlci) dlci->state = DLCI_OPEN; if (debug & 8) pr_debug("DLCI %d goes open.\n", dlci->addr); - /* Register gsmtty driver,report gsmtty dev add uevent for user */ - tty_register_device(gsm_tty_driver, dlci->addr, NULL); + /* Send current modem state */ + if (dlci->addr) + gsm_modem_update(dlci, 0); wake_up(&dlci->gsm->event); } @@ -1623,6 +1662,7 @@ static void gsm_dlci_data(struct gsm_dlci *dlci, const u8 *data, int clen) tty = tty_port_tty_get(port); if (tty) { gsm_process_modem(tty, dlci, modem, slen); + tty_wakeup(tty); tty_kref_put(tty); } fallthrough; @@ -1793,19 +1833,7 @@ static void gsm_queue(struct gsm_mux *gsm) struct gsm_dlci *dlci; u8 cr; int address; - int i, j, k, address_tmp; - /* We have to sneak a look at the packet body to do the FCS. - A somewhat layering violation in the spec */ - if ((gsm->control & ~PF) == UI) - gsm->fcs = gsm_fcs_add_block(gsm->fcs, gsm->buf, gsm->len); - if (gsm->encoding == 0) { - /* WARNING: gsm->received_fcs is used for - gsm->encoding = 0 only. - In this case it contain the last piece of data - required to generate final CRC */ - gsm->fcs = gsm_fcs_add(gsm->fcs, gsm->received_fcs); - } if (gsm->fcs != GOOD_FCS) { gsm->bad_fcs++; if (debug & 4) @@ -1836,11 +1864,6 @@ static void gsm_queue(struct gsm_mux *gsm) else { gsm_response(gsm, address, UA|PF); gsm_dlci_open(dlci); - /* Save dlci open address */ - if (address) { - addr_open[addr_cnt] = address; - addr_cnt++; - } } break; case DISC|PF: @@ -1851,35 +1874,9 @@ static void gsm_queue(struct gsm_mux *gsm) return; } /* Real close complete */ - if (!address) { - if (addr_cnt > 0) { - for (i = 0; i < addr_cnt; i++) { - address = addr_open[i]; - dlci = gsm->dlci[address]; - gsm_dlci_close(dlci); - addr_open[i] = 0; - } - } - dlci = gsm->dlci[0]; - gsm_dlci_close(dlci); - addr_cnt = 0; - gsm_response(gsm, 0, UA|PF); - } else { - gsm_response(gsm, address, UA|PF); - gsm_dlci_close(dlci); - /* clear dlci address */ - for (j = 0; j < addr_cnt; j++) { - address_tmp = addr_open[j]; - if (address_tmp == address) { - for (k = j; k < addr_cnt; k++) - addr_open[k] = addr_open[k+1]; - addr_cnt--; - break; - } - } - } + gsm_response(gsm, address, UA|PF); + gsm_dlci_close(dlci); break; - case UA: case UA|PF: if (cr == 0 || dlci == NULL) break; @@ -1993,19 +1990,25 @@ static void gsm0_receive(struct gsm_mux *gsm, unsigned char c) break; case GSM_DATA: /* Data */ gsm->buf[gsm->count++] = c; - if (gsm->count == gsm->len) + if (gsm->count == gsm->len) { + /* Calculate final FCS for UI frames over all data */ + if ((gsm->control & ~PF) != UIH) { + gsm->fcs = gsm_fcs_add_block(gsm->fcs, gsm->buf, + gsm->count); + } gsm->state = GSM_FCS; + } break; case GSM_FCS: /* FCS follows the packet */ - gsm->received_fcs = c; - gsm_queue(gsm); + gsm->fcs = gsm_fcs_add(gsm->fcs, c); gsm->state = GSM_SSOF; break; case GSM_SSOF: - if (c == GSM0_SOF) { - gsm->state = GSM_SEARCH; - break; - } + gsm->state = GSM_SEARCH; + if (c == GSM0_SOF) + gsm_queue(gsm); + else + gsm->bad_size++; break; default: pr_debug("%s: unhandled state: %d\n", __func__, gsm->state); @@ -2023,12 +2026,35 @@ static void gsm0_receive(struct gsm_mux *gsm, unsigned char c) static void gsm1_receive(struct gsm_mux *gsm, unsigned char c) { + /* handle XON/XOFF */ + if ((c & ISO_IEC_646_MASK) == XON) { + gsm->constipated = true; + return; + } else if ((c & ISO_IEC_646_MASK) == XOFF) { + gsm->constipated = false; + /* Kick the link in case it is idling */ + gsm_data_kick(gsm, NULL); + return; + } if (c == GSM1_SOF) { - /* EOF is only valid in frame if we have got to the data state - and received at least one byte (the FCS) */ - if (gsm->state == GSM_DATA && gsm->count) { - /* Extract the FCS */ + /* EOF is only valid in frame if we have got to the data state */ + if (gsm->state == GSM_DATA) { + if (gsm->count < 1) { + /* Missing FSC */ + gsm->malformed++; + gsm->state = GSM_START; + return; + } + /* Remove the FCS from data */ gsm->count--; + if ((gsm->control & ~PF) != UIH) { + /* Calculate final FCS for UI frames over all + * data but FCS + */ + gsm->fcs = gsm_fcs_add_block(gsm->fcs, gsm->buf, + gsm->count); + } + /* Add the FCS itself to test against GOOD_FCS */ gsm->fcs = gsm_fcs_add(gsm->fcs, gsm->buf[gsm->count]); gsm->len = gsm->count; gsm_queue(gsm); @@ -2037,7 +2063,8 @@ static void gsm1_receive(struct gsm_mux *gsm, unsigned char c) } /* Any partial frame was a runt so go back to start */ if (gsm->state != GSM_START) { - gsm->malformed++; + if (gsm->state != GSM_SEARCH) + gsm->malformed++; gsm->state = GSM_START; } /* A SOF in GSM_START means we are still reading idling or @@ -2106,74 +2133,43 @@ static void gsm_error(struct gsm_mux *gsm) gsm->io_error++; } -static int gsm_disconnect(struct gsm_mux *gsm) -{ - struct gsm_dlci *dlci = gsm->dlci[0]; - struct gsm_control *gc; - - if (!dlci) - return 0; - - /* In theory disconnecting DLCI 0 is sufficient but for some - modems this is apparently not the case. */ - gc = gsm_control_send(gsm, CMD_CLD, NULL, 0); - if (gc) - gsm_control_wait(gsm, gc); - - del_timer_sync(&gsm->t2_timer); - /* Now we are sure T2 has stopped */ - - gsm_dlci_begin_close(dlci); - wait_event_interruptible(gsm->event, - dlci->state == DLCI_CLOSED); - - if (signal_pending(current)) - return -EINTR; - - return 0; -} - /** * gsm_cleanup_mux - generic GSM protocol cleanup * @gsm: our mux + * @disc: disconnect link? * * Clean up the bits of the mux which are the same for all framing * protocols. Remove the mux from the mux table, stop all the timers * and then shut down each device hanging up the channels as we go. */ -static void gsm_cleanup_mux(struct gsm_mux *gsm) +static void gsm_cleanup_mux(struct gsm_mux *gsm, bool disc) { int i; struct gsm_dlci *dlci = gsm->dlci[0]; struct gsm_msg *txq, *ntxq; gsm->dead = true; + mutex_lock(&gsm->mutex); - spin_lock(&gsm_mux_lock); - for (i = 0; i < MAX_MUX; i++) { - if (gsm_mux[i] == gsm) { - gsm_mux[i] = NULL; - break; + if (dlci) { + if (disc && dlci->state != DLCI_CLOSED) { + gsm_dlci_begin_close(dlci); + wait_event(gsm->event, dlci->state == DLCI_CLOSED); } + dlci->dead = true; } - spin_unlock(&gsm_mux_lock); - /* open failed before registering => nothing to do */ - if (i == MAX_MUX) - return; + /* Finish outstanding timers, making sure they are done */ del_timer_sync(&gsm->t2_timer); - /* Now we are sure T2 has stopped */ - if (dlci) - dlci->dead = true; - /* Free up any link layer users */ - mutex_lock(&gsm->mutex); - for (i = 0; i < NUM_DLCI; i++) + /* Free up any link layer users and finally the control channel */ + for (i = NUM_DLCI - 1; i >= 0; i--) if (gsm->dlci[i]) gsm_dlci_release(gsm->dlci[i]); mutex_unlock(&gsm->mutex); /* Now wipe the queues */ + tty_ldisc_flush(gsm->tty); list_for_each_entry_safe(txq, ntxq, &gsm->tx_list, list) kfree(txq); INIT_LIST_HEAD(&gsm->tx_list); @@ -2191,7 +2187,6 @@ static void gsm_cleanup_mux(struct gsm_mux *gsm) static int gsm_activate_mux(struct gsm_mux *gsm) { struct gsm_dlci *dlci; - int i = 0; timer_setup(&gsm->t2_timer, gsm_control_retransmit, 0); init_waitqueue_head(&gsm->event); @@ -2203,18 +2198,6 @@ static int gsm_activate_mux(struct gsm_mux *gsm) else gsm->receive = gsm1_receive; - spin_lock(&gsm_mux_lock); - for (i = 0; i < MAX_MUX; i++) { - if (gsm_mux[i] == NULL) { - gsm->num = i; - gsm_mux[i] = gsm; - break; - } - } - spin_unlock(&gsm_mux_lock); - if (i == MAX_MUX) - return -EBUSY; - dlci = gsm_dlci_alloc(gsm, 0); if (dlci == NULL) return -ENOMEM; @@ -2230,6 +2213,15 @@ static int gsm_activate_mux(struct gsm_mux *gsm) */ static void gsm_free_mux(struct gsm_mux *gsm) { + int i; + + for (i = 0; i < MAX_MUX; i++) { + if (gsm == gsm_mux[i]) { + gsm_mux[i] = NULL; + break; + } + } + mutex_destroy(&gsm->mutex); kfree(gsm->txframe); kfree(gsm->buf); kfree(gsm); @@ -2249,12 +2241,20 @@ static void gsm_free_muxr(struct kref *ref) static inline void mux_get(struct gsm_mux *gsm) { + unsigned long flags; + + spin_lock_irqsave(&gsm_mux_lock, flags); kref_get(&gsm->ref); + spin_unlock_irqrestore(&gsm_mux_lock, flags); } static inline void mux_put(struct gsm_mux *gsm) { + unsigned long flags; + + spin_lock_irqsave(&gsm_mux_lock, flags); kref_put(&gsm->ref, gsm_free_muxr); + spin_unlock_irqrestore(&gsm_mux_lock, flags); } static inline unsigned int mux_num_to_base(struct gsm_mux *gsm) @@ -2275,6 +2275,7 @@ static inline unsigned int mux_line_to_num(unsigned int line) static struct gsm_mux *gsm_alloc_mux(void) { + int i; struct gsm_mux *gsm = kzalloc(sizeof(struct gsm_mux), GFP_KERNEL); if (gsm == NULL) return NULL; @@ -2283,7 +2284,7 @@ static struct gsm_mux *gsm_alloc_mux(void) kfree(gsm); return NULL; } - gsm->txframe = kmalloc(2 * MAX_MRU + 2, GFP_KERNEL); + gsm->txframe = kmalloc(2 * (MAX_MTU + PROT_OVERHEAD - 1), GFP_KERNEL); if (gsm->txframe == NULL) { kfree(gsm->buf); kfree(gsm); @@ -2304,6 +2305,26 @@ static struct gsm_mux *gsm_alloc_mux(void) gsm->mtu = 64; gsm->dead = true; /* Avoid early tty opens */ + /* Store the instance to the mux array or abort if no space is + * available. + */ + spin_lock(&gsm_mux_lock); + for (i = 0; i < MAX_MUX; i++) { + if (!gsm_mux[i]) { + gsm_mux[i] = gsm; + gsm->num = i; + break; + } + } + spin_unlock(&gsm_mux_lock); + if (i == MAX_MUX) { + mutex_destroy(&gsm->mutex); + kfree(gsm->txframe); + kfree(gsm->buf); + kfree(gsm); + return NULL; + } + return gsm; } @@ -2339,7 +2360,7 @@ static int gsm_config(struct gsm_mux *gsm, struct gsm_config *c) /* Check the MRU/MTU range looks sane */ if (c->mru > MAX_MRU || c->mtu > MAX_MTU || c->mru < 8 || c->mtu < 8) return -EINVAL; - if (c->n2 < 3) + if (c->n2 > 255) return -EINVAL; if (c->encapsulation > 1) /* Basic, advanced, no I */ return -EINVAL; @@ -2370,19 +2391,11 @@ static int gsm_config(struct gsm_mux *gsm, struct gsm_config *c) /* * Close down what is needed, restart and initiate the new - * configuration + * configuration. On the first time there is no DLCI[0] + * and closing or cleaning up is not necessary. */ - - if (gsm->initiator && (need_close || need_restart)) { - int ret; - - ret = gsm_disconnect(gsm); - - if (ret) - return ret; - } - if (need_restart) - gsm_cleanup_mux(gsm); + if (need_close || need_restart) + gsm_cleanup_mux(gsm, true); gsm->initiator = c->initiator; gsm->mru = c->mru; @@ -2450,25 +2463,26 @@ static int gsmld_attach_gsm(struct tty_struct *tty, struct gsm_mux *gsm) int ret, i; gsm->tty = tty_kref_get(tty); + /* Turn off tty XON/XOFF handling to handle it explicitly. */ + gsm->old_c_iflag = tty->termios.c_iflag; + tty->termios.c_iflag &= (IXON | IXOFF); ret = gsm_activate_mux(gsm); if (ret != 0) tty_kref_put(gsm->tty); else { /* Don't register device 0 - this is the control channel and not a usable tty interface */ - if (gsm->initiator) { - base = mux_num_to_base(gsm); /* Base for this MUX */ - for (i = 1; i < NUM_DLCI; i++) { - struct device *dev; + base = mux_num_to_base(gsm); /* Base for this MUX */ + for (i = 1; i < NUM_DLCI; i++) { + struct device *dev; - dev = tty_register_device(gsm_tty_driver, + dev = tty_register_device(gsm_tty_driver, base + i, NULL); - if (IS_ERR(dev)) { - for (i--; i >= 1; i--) - tty_unregister_device(gsm_tty_driver, - base + i); - return PTR_ERR(dev); - } + if (IS_ERR(dev)) { + for (i--; i >= 1; i--) + tty_unregister_device(gsm_tty_driver, + base + i); + return PTR_ERR(dev); } } } @@ -2490,11 +2504,10 @@ static void gsmld_detach_gsm(struct tty_struct *tty, struct gsm_mux *gsm) int i; WARN_ON(tty != gsm->tty); - if (gsm->initiator) { - for (i = 1; i < NUM_DLCI; i++) - tty_unregister_device(gsm_tty_driver, base + i); - } - gsm_cleanup_mux(gsm); + for (i = 1; i < NUM_DLCI; i++) + tty_unregister_device(gsm_tty_driver, base + i); + /* Restore tty XON/XOFF handling. */ + gsm->tty->termios.c_iflag = gsm->old_c_iflag; tty_kref_put(gsm->tty); gsm->tty = NULL; } @@ -2559,6 +2572,12 @@ static void gsmld_close(struct tty_struct *tty) { struct gsm_mux *gsm = tty->disc_data; + /* The ldisc locks and closes the port before calling our close. This + * means we have no way to do a proper disconnect. We will not bother + * to do one. + */ + gsm_cleanup_mux(gsm, false); + gsmld_detach_gsm(tty, gsm); gsmld_flush_buffer(tty); @@ -2597,7 +2616,7 @@ static int gsmld_open(struct tty_struct *tty) ret = gsmld_attach_gsm(tty, gsm); if (ret != 0) { - gsm_cleanup_mux(gsm); + gsm_cleanup_mux(gsm, false); mux_put(gsm); } return ret; @@ -2954,26 +2973,78 @@ static struct tty_ldisc_ops tty_ldisc_packet = { #define TX_SIZE 512 -static int gsmtty_modem_update(struct gsm_dlci *dlci, u8 brk) +/** + * gsm_modem_upd_via_data - send modem bits via convergence layer + * @dlci: channel + * @brk: break signal + * + * Send an empty frame to signal mobile state changes and to transmit the + * break signal for adaption 2. + */ + +static void gsm_modem_upd_via_data(struct gsm_dlci *dlci, u8 brk) { - u8 modembits[5]; + struct gsm_mux *gsm = dlci->gsm; + unsigned long flags; + + if (dlci->state != DLCI_OPEN || dlci->adaption != 2) + return; + + spin_lock_irqsave(&gsm->tx_lock, flags); + gsm_dlci_modem_output(gsm, dlci, brk); + spin_unlock_irqrestore(&gsm->tx_lock, flags); +} + +/** + * gsm_modem_upd_via_msc - send modem bits via control frame + * @dlci: channel + * @brk: break signal + */ + +static int gsm_modem_upd_via_msc(struct gsm_dlci *dlci, u8 brk) +{ + u8 modembits[3]; struct gsm_control *ctrl; int len = 2; - if (brk) - len++; + if (dlci->gsm->encoding != 0) + return 0; - modembits[0] = len << 1 | EA; /* Data bytes */ - modembits[1] = dlci->addr << 2 | 3; /* DLCI, EA, 1 */ - modembits[2] = gsm_encode_modem(dlci) << 1 | EA; - if (brk) - modembits[3] = brk << 4 | 2 | EA; /* Valid, EA */ - ctrl = gsm_control_send(dlci->gsm, CMD_MSC, modembits, len + 1); + modembits[0] = (dlci->addr << 2) | 2 | EA; /* DLCI, Valid, EA */ + if (!brk) { + modembits[1] = (gsm_encode_modem(dlci) << 1) | EA; + } else { + modembits[1] = gsm_encode_modem(dlci) << 1; + modembits[2] = (brk << 4) | 2 | EA; /* Length, Break, EA */ + len++; + } + ctrl = gsm_control_send(dlci->gsm, CMD_MSC, modembits, len); if (ctrl == NULL) return -ENOMEM; return gsm_control_wait(dlci->gsm, ctrl); } +/** + * gsm_modem_update - send modem status line state + * @dlci: channel + * @brk: break signal + */ + +static int gsm_modem_update(struct gsm_dlci *dlci, u8 brk) +{ + if (dlci->adaption == 2) { + /* Send convergence layer type 2 empty data frame. */ + gsm_modem_upd_via_data(dlci, brk); + return 0; + } else if (dlci->gsm->encoding == 0) { + /* Send as MSC control message. */ + return gsm_modem_upd_via_msc(dlci, brk); + } + + /* Modem status lines are not supported. */ + return -EPROTONOSUPPORT; +} + static int gsm_carrier_raised(struct tty_port *port) { struct gsm_dlci *dlci = container_of(port, struct gsm_dlci, port); @@ -3006,7 +3077,7 @@ static void gsm_dtr_rts(struct tty_port *port, int onoff) modem_tx &= ~(TIOCM_DTR | TIOCM_RTS); if (modem_tx != dlci->modem_tx) { dlci->modem_tx = modem_tx; - gsmtty_modem_update(dlci, 0); + gsm_modem_update(dlci, 0); } } @@ -3155,13 +3226,17 @@ static unsigned int gsmtty_chars_in_buffer(struct tty_struct *tty) static void gsmtty_flush_buffer(struct tty_struct *tty) { struct gsm_dlci *dlci = tty->driver_data; + unsigned long flags; + if (dlci->state == DLCI_CLOSED) return; /* Caution needed: If we implement reliable transport classes then the data being transmitted can't simply be junked once it has first hit the stack. Until then we can just blow it away */ + spin_lock_irqsave(&dlci->lock, flags); kfifo_reset(&dlci->fifo); + spin_unlock_irqrestore(&dlci->lock, flags); /* Need to unhook this DLCI from the transmit queue logic */ } @@ -3193,7 +3268,7 @@ static int gsmtty_tiocmset(struct tty_struct *tty, if (modem_tx != dlci->modem_tx) { dlci->modem_tx = modem_tx; - return gsmtty_modem_update(dlci, 0); + return gsm_modem_update(dlci, 0); } return 0; } @@ -3254,7 +3329,7 @@ static void gsmtty_throttle(struct tty_struct *tty) dlci->modem_tx &= ~TIOCM_RTS; dlci->throttled = true; /* Send an MSC with RTS cleared */ - gsmtty_modem_update(dlci, 0); + gsm_modem_update(dlci, 0); } static void gsmtty_unthrottle(struct tty_struct *tty) @@ -3266,7 +3341,7 @@ static void gsmtty_unthrottle(struct tty_struct *tty) dlci->modem_tx |= TIOCM_RTS; dlci->throttled = false; /* Send an MSC with RTS set */ - gsmtty_modem_update(dlci, 0); + gsm_modem_update(dlci, 0); } static int gsmtty_break_ctl(struct tty_struct *tty, int state) @@ -3284,7 +3359,7 @@ static int gsmtty_break_ctl(struct tty_struct *tty, int state) if (encode > 0x0F) encode = 0x0F; /* Best effort */ } - return gsmtty_modem_update(dlci, encode); + return gsm_modem_update(dlci, encode); } static void gsmtty_cleanup(struct tty_struct *tty) diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index e17e97ea86fa..a293e9f107d0 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -2667,7 +2667,7 @@ enum pci_board_num_t { pbn_panacom2, pbn_panacom4, pbn_plx_romulus, - pbn_endrun_2_4000000, + pbn_endrun_2_3906250, pbn_oxsemi, pbn_oxsemi_1_3906250, pbn_oxsemi_2_3906250, @@ -3195,10 +3195,10 @@ static struct pciserial_board pci_boards[] = { * signal now many ports are available * 2 port 952 Uart support */ - [pbn_endrun_2_4000000] = { + [pbn_endrun_2_3906250] = { .flags = FL_BASE0, .num_ports = 2, - .base_baud = 4000000, + .base_baud = 3906250, .uart_offset = 0x200, .first_offset = 0x1000, }, @@ -4115,7 +4115,7 @@ static const struct pci_device_id serial_pci_tbl[] = { */ { PCI_VENDOR_ID_ENDRUN, PCI_DEVICE_ID_ENDRUN_1588, PCI_ANY_ID, PCI_ANY_ID, 0, 0, - pbn_endrun_2_4000000 }, + pbn_endrun_2_3906250 }, /* * Quatech cards. These actually have configurable clocks but for * now we just use the default. diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 318af6f13605..1fbd5bf264be 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1675,11 +1675,11 @@ static void serial8250_start_tx(struct uart_port *port) struct uart_8250_port *up = up_to_u8250p(port); struct uart_8250_em485 *em485 = up->em485; - serial8250_rpm_get_tx(up); - if (!port->x_char && uart_circ_empty(&port->state->xmit)) return; + serial8250_rpm_get_tx(up); + if (em485 && em485->active_timer == &em485->start_tx_timer) return; @@ -3329,7 +3329,7 @@ static void serial8250_console_restore(struct uart_8250_port *up) serial8250_set_divisor(port, baud, quot, frac); serial_port_out(port, UART_LCR, up->lcr); - serial8250_out_MCR(up, UART_MCR_DTR | UART_MCR_RTS); + serial8250_out_MCR(up, up->mcr | UART_MCR_DTR | UART_MCR_RTS); } /* diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index 51ecb050ae40..4d11a3e547f9 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -1255,13 +1255,18 @@ static inline bool pl011_dma_rx_running(struct uart_amba_port *uap) static void pl011_rs485_tx_stop(struct uart_amba_port *uap) { + /* + * To be on the safe side only time out after twice as many iterations + * as fifo size. + */ + const int MAX_TX_DRAIN_ITERS = uap->port.fifosize * 2; struct uart_port *port = &uap->port; int i = 0; u32 cr; /* Wait until hardware tx queue is empty */ while (!pl011_tx_empty(port)) { - if (i == port->fifosize) { + if (i > MAX_TX_DRAIN_ITERS) { dev_warn(port->dev, "timeout while draining hardware tx queue\n"); break; @@ -2052,7 +2057,7 @@ pl011_set_termios(struct uart_port *port, struct ktermios *termios, * with the given baud rate. We use this as the poll interval when we * wait for the tx queue to empty. */ - uap->rs485_tx_drain_interval = (bits * 1000 * 1000) / baud; + uap->rs485_tx_drain_interval = DIV_ROUND_UP(bits * 1000 * 1000, baud); pl011_setup_status_masks(port, termios); diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index fd38e6ed4fda..a2100be8d554 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -1448,7 +1448,7 @@ static int imx_uart_startup(struct uart_port *port) imx_uart_writel(sport, ucr1, UCR1); ucr4 = imx_uart_readl(sport, UCR4) & ~(UCR4_OREN | UCR4_INVR); - if (!sport->dma_is_enabled) + if (!dma_is_inited) ucr4 |= UCR4_OREN; if (sport->inverted_rx) ucr4 |= UCR4_INVR; diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index e857fb61efbf..5fb201c1b563 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -1238,12 +1238,10 @@ static void sc16is7xx_shutdown(struct uart_port *port) /* Disable all interrupts */ sc16is7xx_port_write(port, SC16IS7XX_IER_REG, 0); - /* Disable TX/RX, clear auto RS485 and RTS invert */ + /* Disable TX/RX */ sc16is7xx_port_update(port, SC16IS7XX_EFCR_REG, SC16IS7XX_EFCR_RXDISABLE_BIT | - SC16IS7XX_EFCR_TXDISABLE_BIT | - SC16IS7XX_EFCR_AUTO_RS485_BIT | - SC16IS7XX_EFCR_RTS_INVERT_BIT, + SC16IS7XX_EFCR_TXDISABLE_BIT, SC16IS7XX_EFCR_RXDISABLE_BIT | SC16IS7XX_EFCR_TXDISABLE_BIT); diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c index f9af7ebe003d..d6d515d598dc 100644 --- a/drivers/usb/cdns3/cdns3-gadget.c +++ b/drivers/usb/cdns3/cdns3-gadget.c @@ -2684,6 +2684,7 @@ int __cdns3_gadget_ep_clear_halt(struct cdns3_endpoint *priv_ep) struct usb_request *request; struct cdns3_request *priv_req; struct cdns3_trb *trb = NULL; + struct cdns3_trb trb_tmp; int ret; int val; @@ -2693,8 +2694,10 @@ int __cdns3_gadget_ep_clear_halt(struct cdns3_endpoint *priv_ep) if (request) { priv_req = to_cdns3_request(request); trb = priv_req->trb; - if (trb) + if (trb) { + trb_tmp = *trb; trb->control = trb->control ^ cpu_to_le32(TRB_CYCLE); + } } writel(EP_CMD_CSTALL | EP_CMD_EPRST, &priv_dev->regs->ep_cmd); @@ -2709,7 +2712,7 @@ int __cdns3_gadget_ep_clear_halt(struct cdns3_endpoint *priv_ep) if (request) { if (trb) - trb->control = trb->control ^ cpu_to_le32(TRB_CYCLE); + *trb = trb_tmp; cdns3_rearm_transfer(priv_ep, 1); } diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 6abb7294e919..b5b85bf80329 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -1209,12 +1209,16 @@ static int do_proc_control(struct usb_dev_state *ps, usb_unlock_device(dev); i = usbfs_start_wait_urb(urb, tmo, &actlen); + + /* Linger a bit, prior to the next control message. */ + if (dev->quirks & USB_QUIRK_DELAY_CTRL_MSG) + msleep(200); usb_lock_device(dev); snoop_urb(dev, NULL, pipe, actlen, i, COMPLETE, tbuf, actlen); if (!i && actlen) { if (copy_to_user(ctrl->data, tbuf, actlen)) { ret = -EFAULT; - goto recv_fault; + goto done; } } } else { @@ -1231,6 +1235,10 @@ static int do_proc_control(struct usb_dev_state *ps, usb_unlock_device(dev); i = usbfs_start_wait_urb(urb, tmo, &actlen); + + /* Linger a bit, prior to the next control message. */ + if (dev->quirks & USB_QUIRK_DELAY_CTRL_MSG) + msleep(200); usb_lock_device(dev); snoop_urb(dev, NULL, pipe, actlen, i, COMPLETE, NULL, 0); } @@ -1242,10 +1250,6 @@ static int do_proc_control(struct usb_dev_state *ps, } ret = (i < 0 ? i : actlen); - recv_fault: - /* Linger a bit, prior to the next control message. */ - if (dev->quirks & USB_QUIRK_DELAY_CTRL_MSG) - msleep(200); done: kfree(dr); usb_free_urb(urb); diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index d3c14b5ed4a1..97b44a68668a 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -404,6 +404,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x0b05, 0x17e0), .driver_info = USB_QUIRK_IGNORE_REMOTE_WAKEUP }, + /* Realtek Semiconductor Corp. Mass Storage Device (Multicard Reader)*/ + { USB_DEVICE(0x0bda, 0x0151), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, + /* Realtek hub in Dell WD19 (Type-C) */ { USB_DEVICE(0x0bda, 0x0487), .driver_info = USB_QUIRK_NO_LPM }, @@ -507,6 +510,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* DJI CineSSD */ { USB_DEVICE(0x2ca3, 0x0031), .driver_info = USB_QUIRK_NO_LPM }, + /* VCOM device */ + { USB_DEVICE(0x4296, 0x7570), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, + /* INTEL VALUE SSD */ { USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME }, diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 1170b800acdc..d28cd1a6709b 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -274,7 +274,8 @@ int dwc3_core_soft_reset(struct dwc3 *dwc) reg = dwc3_readl(dwc->regs, DWC3_DCTL); reg |= DWC3_DCTL_CSFTRST; - dwc3_writel(dwc->regs, DWC3_DCTL, reg); + reg &= ~DWC3_DCTL_RUN_STOP; + dwc3_gadget_dctl_write_safe(dwc, reg); /* * For DWC_usb31 controller 1.90a and later, the DCTL.CSFRST bit @@ -1377,10 +1378,10 @@ static void dwc3_get_properties(struct dwc3 *dwc) u8 lpm_nyet_threshold; u8 tx_de_emphasis; u8 hird_threshold; - u8 rx_thr_num_pkt_prd; - u8 rx_max_burst_prd; - u8 tx_thr_num_pkt_prd; - u8 tx_max_burst_prd; + u8 rx_thr_num_pkt_prd = 0; + u8 rx_max_burst_prd = 0; + u8 tx_thr_num_pkt_prd = 0; + u8 tx_max_burst_prd = 0; u8 tx_fifo_resize_max_num; const char *usb_psy_name; int ret; @@ -1690,21 +1691,44 @@ static int dwc3_probe(struct platform_device *pdev) /* * Clocks are optional, but new DT platforms should support all * clocks as required by the DT-binding. + * Some devices have different clock names in legacy device trees, + * check for them to retain backwards compatibility. */ dwc->bus_clk = devm_clk_get_optional(dev, "bus_early"); if (IS_ERR(dwc->bus_clk)) return dev_err_probe(dev, PTR_ERR(dwc->bus_clk), "could not get bus clock\n"); + if (dwc->bus_clk == NULL) { + dwc->bus_clk = devm_clk_get_optional(dev, "bus_clk"); + if (IS_ERR(dwc->bus_clk)) + return dev_err_probe(dev, PTR_ERR(dwc->bus_clk), + "could not get bus clock\n"); + } + dwc->ref_clk = devm_clk_get_optional(dev, "ref"); if (IS_ERR(dwc->ref_clk)) return dev_err_probe(dev, PTR_ERR(dwc->ref_clk), "could not get ref clock\n"); + if (dwc->ref_clk == NULL) { + dwc->ref_clk = devm_clk_get_optional(dev, "ref_clk"); + if (IS_ERR(dwc->ref_clk)) + return dev_err_probe(dev, PTR_ERR(dwc->ref_clk), + "could not get ref clock\n"); + } + dwc->susp_clk = devm_clk_get_optional(dev, "suspend"); if (IS_ERR(dwc->susp_clk)) return dev_err_probe(dev, PTR_ERR(dwc->susp_clk), "could not get suspend clock\n"); + + if (dwc->susp_clk == NULL) { + dwc->susp_clk = devm_clk_get_optional(dev, "suspend_clk"); + if (IS_ERR(dwc->susp_clk)) + return dev_err_probe(dev, PTR_ERR(dwc->susp_clk), + "could not get suspend clock\n"); + } } ret = reset_control_deassert(dwc->reset); diff --git a/drivers/usb/dwc3/drd.c b/drivers/usb/dwc3/drd.c index b60b5f7b6dff..8cad9e7d3368 100644 --- a/drivers/usb/dwc3/drd.c +++ b/drivers/usb/dwc3/drd.c @@ -584,16 +584,15 @@ int dwc3_drd_init(struct dwc3 *dwc) { int ret, irq; + if (ROLE_SWITCH && + device_property_read_bool(dwc->dev, "usb-role-switch")) + return dwc3_setup_role_switch(dwc); + dwc->edev = dwc3_get_extcon(dwc); if (IS_ERR(dwc->edev)) return PTR_ERR(dwc->edev); - if (ROLE_SWITCH && - device_property_read_bool(dwc->dev, "usb-role-switch")) { - ret = dwc3_setup_role_switch(dwc); - if (ret < 0) - return ret; - } else if (dwc->edev) { + if (dwc->edev) { dwc->edev_nb.notifier_call = dwc3_drd_notifier; ret = extcon_register_notifier(dwc->edev, EXTCON_USB_HOST, &dwc->edev_nb); diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 33f657d83246..2e19e0e4ea53 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -45,6 +45,8 @@ #define PCI_DEVICE_ID_INTEL_ADLM 0x54ee #define PCI_DEVICE_ID_INTEL_ADLS 0x7ae1 #define PCI_DEVICE_ID_INTEL_RPLS 0x7a61 +#define PCI_DEVICE_ID_INTEL_MTLP 0x7ec1 +#define PCI_DEVICE_ID_INTEL_MTL 0x7e7e #define PCI_DEVICE_ID_INTEL_TGL 0x9a15 #define PCI_DEVICE_ID_AMD_MR 0x163a @@ -456,6 +458,12 @@ static const struct pci_device_id dwc3_pci_id_table[] = { { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_RPLS), (kernel_ulong_t) &dwc3_pci_intel_swnode, }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTLP), + (kernel_ulong_t) &dwc3_pci_intel_swnode, }, + + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTL), + (kernel_ulong_t) &dwc3_pci_intel_swnode, }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL), (kernel_ulong_t) &dwc3_pci_intel_swnode, }, diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index ab725d2262d6..0b9c2493844a 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -3274,6 +3274,7 @@ static int dwc3_gadget_ep_cleanup_completed_request(struct dwc3_ep *dep, const struct dwc3_event_depevt *event, struct dwc3_request *req, int status) { + int request_status; int ret; if (req->request.num_mapped_sgs) @@ -3294,7 +3295,35 @@ static int dwc3_gadget_ep_cleanup_completed_request(struct dwc3_ep *dep, req->needs_extra_trb = false; } - dwc3_gadget_giveback(dep, req, status); + /* + * The event status only reflects the status of the TRB with IOC set. + * For the requests that don't set interrupt on completion, the driver + * needs to check and return the status of the completed TRBs associated + * with the request. Use the status of the last TRB of the request. + */ + if (req->request.no_interrupt) { + struct dwc3_trb *trb; + + trb = dwc3_ep_prev_trb(dep, dep->trb_dequeue); + switch (DWC3_TRB_SIZE_TRBSTS(trb->size)) { + case DWC3_TRBSTS_MISSED_ISOC: + /* Isoc endpoint only */ + request_status = -EXDEV; + break; + case DWC3_TRB_STS_XFER_IN_PROG: + /* Applicable when End Transfer with ForceRM=0 */ + case DWC3_TRBSTS_SETUP_PENDING: + /* Control endpoint only */ + case DWC3_TRBSTS_OK: + default: + request_status = 0; + break; + } + } else { + request_status = status; + } + + dwc3_gadget_giveback(dep, req, request_status); out: return ret; diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 1fb837d9271e..84b73cb03f87 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -1438,6 +1438,8 @@ static void configfs_composite_unbind(struct usb_gadget *gadget) usb_ep_autoconfig_reset(cdev->gadget); spin_lock_irqsave(&gi->spinlock, flags); cdev->gadget = NULL; + cdev->deactivations = 0; + gadget->deactivated = false; set_gadget_data(gadget, NULL); spin_unlock_irqrestore(&gi->spinlock, flags); } diff --git a/drivers/usb/gadget/function/uvc_queue.c b/drivers/usb/gadget/function/uvc_queue.c index d852ac9e47e7..2cda982f3765 100644 --- a/drivers/usb/gadget/function/uvc_queue.c +++ b/drivers/usb/gadget/function/uvc_queue.c @@ -264,6 +264,8 @@ void uvcg_queue_cancel(struct uvc_video_queue *queue, int disconnect) buf->state = UVC_BUF_STATE_ERROR; vb2_buffer_done(&buf->buf.vb2_buf, VB2_BUF_STATE_ERROR); } + queue->buf_used = 0; + /* This must be protected by the irqlock spinlock to avoid race * conditions between uvc_queue_buffer and the disconnection event that * could result in an interruptible wait in uvc_dequeue_buffer. Do not diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index 3d82e0b853be..684164fa9716 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -1103,6 +1103,26 @@ static void ehci_remove_device(struct usb_hcd *hcd, struct usb_device *udev) #ifdef CONFIG_PM +/* Clear wakeup signal locked in zhaoxin platform when device plug in. */ +static void ehci_zx_wakeup_clear(struct ehci_hcd *ehci) +{ + u32 __iomem *reg = &ehci->regs->port_status[4]; + u32 t1 = ehci_readl(ehci, reg); + + t1 &= (u32)~0xf0000; + t1 |= PORT_TEST_FORCE; + ehci_writel(ehci, t1, reg); + t1 = ehci_readl(ehci, reg); + msleep(1); + t1 &= (u32)~0xf0000; + ehci_writel(ehci, t1, reg); + ehci_readl(ehci, reg); + msleep(1); + t1 = ehci_readl(ehci, reg); + ehci_writel(ehci, t1 | PORT_CSC, reg); + ehci_readl(ehci, reg); +} + /* suspend/resume, section 4.3 */ /* These routines handle the generic parts of controller suspend/resume */ @@ -1154,6 +1174,9 @@ int ehci_resume(struct usb_hcd *hcd, bool force_reset) if (ehci->shutdown) return 0; /* Controller is dead */ + if (ehci->zx_wakeup_clear_needed) + ehci_zx_wakeup_clear(ehci); + /* * If CF is still set and reset isn't forced * then we maintained suspend power. diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c index 638f03b89739..9937c5a7efc2 100644 --- a/drivers/usb/host/ehci-pci.c +++ b/drivers/usb/host/ehci-pci.c @@ -231,6 +231,10 @@ static int ehci_pci_setup(struct usb_hcd *hcd) ehci->is_aspeed = 1; } break; + case PCI_VENDOR_ID_ZHAOXIN: + if (pdev->device == 0x3104 && (pdev->revision & 0xf0) == 0x90) + ehci->zx_wakeup_clear_needed = 1; + break; } /* optional debug port, normally in the first BAR */ diff --git a/drivers/usb/host/ehci.h b/drivers/usb/host/ehci.h index fdd073cc053b..ad3f13a3eaf1 100644 --- a/drivers/usb/host/ehci.h +++ b/drivers/usb/host/ehci.h @@ -220,6 +220,7 @@ struct ehci_hcd { /* one per controller */ unsigned imx28_write_fix:1; /* For Freescale i.MX28 */ unsigned spurious_oc:1; unsigned is_aspeed:1; + unsigned zx_wakeup_clear_needed:1; /* required for usb32 quirk */ #define OHCI_CTRL_HCFS (3 << 6) diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index 1e7dc130c39a..f65f1ba2b592 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -1434,7 +1434,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, } spin_unlock_irqrestore(&xhci->lock, flags); if (!wait_for_completion_timeout(&bus_state->u3exit_done[wIndex], - msecs_to_jiffies(100))) + msecs_to_jiffies(500))) xhci_dbg(xhci, "missing U0 port change event for port %d-%d\n", hcd->self.busnum, wIndex + 1); spin_lock_irqsave(&xhci->lock, flags); diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 5c351970cdf1..d7e0e6ebf080 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -59,6 +59,7 @@ #define PCI_DEVICE_ID_INTEL_TIGER_LAKE_XHCI 0x9a13 #define PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_XHCI 0x1138 #define PCI_DEVICE_ID_INTEL_ALDER_LAKE_XHCI 0x461e +#define PCI_DEVICE_ID_INTEL_ALDER_LAKE_PCH_XHCI 0x51ed #define PCI_DEVICE_ID_AMD_RENOIR_XHCI 0x1639 #define PCI_DEVICE_ID_AMD_PROMONTORYA_4 0x43b9 @@ -266,7 +267,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) pdev->device == PCI_DEVICE_ID_INTEL_ICE_LAKE_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_TIGER_LAKE_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_XHCI || - pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_XHCI)) + pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_PCH_XHCI)) xhci->quirks |= XHCI_DEFAULT_PM_RUNTIME_ALLOW; if (pdev->vendor == PCI_VENDOR_ID_ETRON && diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index d0b6806275e0..f9707997969d 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -3141,6 +3141,7 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd) if (event_loop++ < TRBS_PER_SEGMENT / 2) continue; xhci_update_erst_dequeue(xhci, event_ring_deq); + event_ring_deq = xhci->event_ring->dequeue; /* ring is half-full, force isoc trbs to interrupt more often */ if (xhci->isoc_bei_interval > AVOID_BEI_INTERVAL_MIN) diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index c8af2cd2216d..996958a6565c 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -1034,13 +1034,13 @@ static int tegra_xusb_unpowergate_partitions(struct tegra_xusb *tegra) int rc; if (tegra->use_genpd) { - rc = pm_runtime_get_sync(tegra->genpd_dev_ss); + rc = pm_runtime_resume_and_get(tegra->genpd_dev_ss); if (rc < 0) { dev_err(dev, "failed to enable XUSB SS partition\n"); return rc; } - rc = pm_runtime_get_sync(tegra->genpd_dev_host); + rc = pm_runtime_resume_and_get(tegra->genpd_dev_host); if (rc < 0) { dev_err(dev, "failed to enable XUSB Host partition\n"); pm_runtime_put_sync(tegra->genpd_dev_ss); diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 642610c78f58..25b87e99b4dd 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -781,6 +781,17 @@ void xhci_shutdown(struct usb_hcd *hcd) if (xhci->quirks & XHCI_SPURIOUS_REBOOT) usb_disable_xhci_ports(to_pci_dev(hcd->self.sysdev)); + /* Don't poll the roothubs after shutdown. */ + xhci_dbg(xhci, "%s: stopping usb%d port polling.\n", + __func__, hcd->self.busnum); + clear_bit(HCD_FLAG_POLL_RH, &hcd->flags); + del_timer_sync(&hcd->rh_timer); + + if (xhci->shared_hcd) { + clear_bit(HCD_FLAG_POLL_RH, &xhci->shared_hcd->flags); + del_timer_sync(&xhci->shared_hcd->rh_timer); + } + spin_lock_irq(&xhci->lock); xhci_halt(xhci); /* Workaround for spurious wakeups at shutdown with HSW */ diff --git a/drivers/usb/misc/qcom_eud.c b/drivers/usb/misc/qcom_eud.c index f929bffdc5d1..b7f13df00764 100644 --- a/drivers/usb/misc/qcom_eud.c +++ b/drivers/usb/misc/qcom_eud.c @@ -186,16 +186,16 @@ static int eud_probe(struct platform_device *pdev) chip->dev = &pdev->dev; - ret = devm_add_action_or_reset(chip->dev, eud_role_switch_release, chip); - if (ret) - return dev_err_probe(chip->dev, ret, - "failed to add role switch release action\n"); - chip->role_sw = usb_role_switch_get(&pdev->dev); if (IS_ERR(chip->role_sw)) return dev_err_probe(chip->dev, PTR_ERR(chip->role_sw), "failed to get role switch\n"); + ret = devm_add_action_or_reset(chip->dev, eud_role_switch_release, chip); + if (ret) + return dev_err_probe(chip->dev, ret, + "failed to add role switch release action\n"); + chip->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(chip->base)) return PTR_ERR(chip->base); diff --git a/drivers/usb/misc/uss720.c b/drivers/usb/misc/uss720.c index 748139d26263..0be8efcda15d 100644 --- a/drivers/usb/misc/uss720.c +++ b/drivers/usb/misc/uss720.c @@ -71,6 +71,7 @@ static void destroy_priv(struct kref *kref) dev_dbg(&priv->usbdev->dev, "destroying priv datastructure\n"); usb_put_dev(priv->usbdev); + priv->usbdev = NULL; kfree(priv); } @@ -736,7 +737,6 @@ static int uss720_probe(struct usb_interface *intf, parport_announce_port(pp); usb_set_intfdata(intf, pp); - usb_put_dev(usbdev); return 0; probe_abort: @@ -754,7 +754,6 @@ static void uss720_disconnect(struct usb_interface *intf) usb_set_intfdata(intf, NULL); if (pp) { priv = pp->private_data; - priv->usbdev = NULL; priv->pp = NULL; dev_dbg(&intf->dev, "parport_remove_port\n"); parport_remove_port(pp); diff --git a/drivers/usb/mtu3/mtu3_dr.c b/drivers/usb/mtu3/mtu3_dr.c index a6b04831b20b..9b8aded3d95e 100644 --- a/drivers/usb/mtu3/mtu3_dr.c +++ b/drivers/usb/mtu3/mtu3_dr.c @@ -21,10 +21,8 @@ static inline struct ssusb_mtk *otg_sx_to_ssusb(struct otg_switch_mtk *otg_sx) static void toggle_opstate(struct ssusb_mtk *ssusb) { - if (!ssusb->otg_switch.is_u3_drd) { - mtu3_setbits(ssusb->mac_base, U3D_DEVICE_CONTROL, DC_SESSION); - mtu3_setbits(ssusb->mac_base, U3D_POWER_MANAGEMENT, SOFT_CONN); - } + mtu3_setbits(ssusb->mac_base, U3D_DEVICE_CONTROL, DC_SESSION); + mtu3_setbits(ssusb->mac_base, U3D_POWER_MANAGEMENT, SOFT_CONN); } /* only port0 supports dual-role mode */ diff --git a/drivers/usb/phy/phy-generic.c b/drivers/usb/phy/phy-generic.c index 661a229c105d..34b9f8140187 100644 --- a/drivers/usb/phy/phy-generic.c +++ b/drivers/usb/phy/phy-generic.c @@ -268,6 +268,13 @@ int usb_phy_gen_create_phy(struct device *dev, struct usb_phy_generic *nop) return -EPROBE_DEFER; } + nop->vbus_draw = devm_regulator_get_exclusive(dev, "vbus"); + if (PTR_ERR(nop->vbus_draw) == -ENODEV) + nop->vbus_draw = NULL; + if (IS_ERR(nop->vbus_draw)) + return dev_err_probe(dev, PTR_ERR(nop->vbus_draw), + "could not get vbus regulator\n"); + nop->dev = dev; nop->phy.dev = nop->dev; nop->phy.label = "nop-xceiv"; diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index a27f7efcec6a..c374620a486f 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -194,6 +194,8 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x16DC, 0x0015) }, /* W-IE-NE-R Plein & Baus GmbH CML Control, Monitoring and Data Logger */ { USB_DEVICE(0x17A8, 0x0001) }, /* Kamstrup Optical Eye/3-wire */ { USB_DEVICE(0x17A8, 0x0005) }, /* Kamstrup M-Bus Master MultiPort 250D */ + { USB_DEVICE(0x17A8, 0x0101) }, /* Kamstrup 868 MHz wM-Bus C-Mode Meter Reader (Int Ant) */ + { USB_DEVICE(0x17A8, 0x0102) }, /* Kamstrup 868 MHz wM-Bus C-Mode Meter Reader (Ext Ant) */ { USB_DEVICE(0x17F4, 0xAAAA) }, /* Wavesense Jazz blood glucose meter */ { USB_DEVICE(0x1843, 0x0200) }, /* Vaisala USB Instrument Cable */ { USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index e7755d9cfc61..1364ce7f0abf 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -432,6 +432,8 @@ static void option_instat_callback(struct urb *urb); #define CINTERION_PRODUCT_CLS8 0x00b0 #define CINTERION_PRODUCT_MV31_MBIM 0x00b3 #define CINTERION_PRODUCT_MV31_RMNET 0x00b7 +#define CINTERION_PRODUCT_MV32_WA 0x00f1 +#define CINTERION_PRODUCT_MV32_WB 0x00f2 /* Olivetti products */ #define OLIVETTI_VENDOR_ID 0x0b3c @@ -1217,6 +1219,10 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1056, 0xff), /* Telit FD980 */ .driver_info = NCTRL(2) | RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1057, 0xff), /* Telit FN980 */ + .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1058, 0xff), /* Telit FN980 (PCIe) */ + .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1060, 0xff), /* Telit LN920 (rmnet) */ .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1061, 0xff), /* Telit LN920 (MBIM) */ @@ -1233,6 +1239,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1073, 0xff), /* Telit FN990 (ECM) */ .driver_info = NCTRL(0) | RSVD(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1075, 0xff), /* Telit FN990 (PCIe) */ + .driver_info = RSVD(0) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM), @@ -1969,6 +1977,10 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(3)}, { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_MV31_RMNET, 0xff), .driver_info = RSVD(0)}, + { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_MV32_WA, 0xff), + .driver_info = RSVD(3)}, + { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_MV32_WB, 0xff), + .driver_info = RSVD(3)}, { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD100), .driver_info = RSVD(4) }, { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD120), diff --git a/drivers/usb/serial/whiteheat.c b/drivers/usb/serial/whiteheat.c index da65d14c9ed5..06aad0d727dd 100644 --- a/drivers/usb/serial/whiteheat.c +++ b/drivers/usb/serial/whiteheat.c @@ -584,9 +584,8 @@ static int firm_send_command(struct usb_serial_port *port, __u8 command, switch (command) { case WHITEHEAT_GET_DTR_RTS: info = usb_get_serial_port_data(port); - memcpy(&info->mcr, command_info->result_buffer, - sizeof(struct whiteheat_dr_info)); - break; + info->mcr = command_info->result_buffer[0]; + break; } } exit: diff --git a/drivers/usb/typec/Kconfig b/drivers/usb/typec/Kconfig index 8f921213b17d..ba24847fb245 100644 --- a/drivers/usb/typec/Kconfig +++ b/drivers/usb/typec/Kconfig @@ -56,6 +56,7 @@ config TYPEC_RT1719 tristate "Richtek RT1719 Sink Only Type-C controller driver" depends on USB_ROLE_SWITCH || !USB_ROLE_SWITCH depends on I2C + depends on POWER_SUPPLY select REGMAP_I2C help Say Y or M here if your system has Richtek RT1719 sink only diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index f0c2fa19f3e0..a6045aef0d04 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -949,6 +949,8 @@ static int ucsi_dr_swap(struct typec_port *port, enum typec_data_role role) role == TYPEC_HOST)) goto out_unlock; + reinit_completion(&con->complete); + command = UCSI_SET_UOR | UCSI_CONNECTOR_NUMBER(con->num); command |= UCSI_SET_UOR_ROLE(role); command |= UCSI_SET_UOR_ACCEPT_ROLE_SWAPS; @@ -956,14 +958,18 @@ static int ucsi_dr_swap(struct typec_port *port, enum typec_data_role role) if (ret < 0) goto out_unlock; + mutex_unlock(&con->lock); + if (!wait_for_completion_timeout(&con->complete, - msecs_to_jiffies(UCSI_SWAP_TIMEOUT_MS))) - ret = -ETIMEDOUT; + msecs_to_jiffies(UCSI_SWAP_TIMEOUT_MS))) + return -ETIMEDOUT; + + return 0; out_unlock: mutex_unlock(&con->lock); - return ret < 0 ? ret : 0; + return ret; } static int ucsi_pr_swap(struct typec_port *port, enum typec_role role) @@ -985,6 +991,8 @@ static int ucsi_pr_swap(struct typec_port *port, enum typec_role role) if (cur_role == role) goto out_unlock; + reinit_completion(&con->complete); + command = UCSI_SET_PDR | UCSI_CONNECTOR_NUMBER(con->num); command |= UCSI_SET_PDR_ROLE(role); command |= UCSI_SET_PDR_ACCEPT_ROLE_SWAPS; @@ -992,11 +1000,13 @@ static int ucsi_pr_swap(struct typec_port *port, enum typec_role role) if (ret < 0) goto out_unlock; + mutex_unlock(&con->lock); + if (!wait_for_completion_timeout(&con->complete, - msecs_to_jiffies(UCSI_SWAP_TIMEOUT_MS))) { - ret = -ETIMEDOUT; - goto out_unlock; - } + msecs_to_jiffies(UCSI_SWAP_TIMEOUT_MS))) + return -ETIMEDOUT; + + mutex_lock(&con->lock); /* Something has gone wrong while swapping the role */ if (UCSI_CONSTAT_PWR_OPMODE(con->status.flags) != diff --git a/drivers/video/fbdev/arkfb.c b/drivers/video/fbdev/arkfb.c index edf169d0816e..eb3e47c58c5f 100644 --- a/drivers/video/fbdev/arkfb.c +++ b/drivers/video/fbdev/arkfb.c @@ -566,6 +566,9 @@ static int arkfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) { int rv, mem, step; + if (!var->pixclock) + return -EINVAL; + /* Find appropriate format */ rv = svga_match_format (arkfb_formats, var, NULL); if (rv < 0) diff --git a/drivers/video/fbdev/aty/aty128fb.c b/drivers/video/fbdev/aty/aty128fb.c index 6ff16d3132e5..b26c81233b6b 100644 --- a/drivers/video/fbdev/aty/aty128fb.c +++ b/drivers/video/fbdev/aty/aty128fb.c @@ -68,7 +68,6 @@ #ifdef CONFIG_PPC_PMAC #include <asm/machdep.h> #include <asm/pmac_feature.h> -#include <asm/prom.h> #include "../macmodes.h" #endif diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c index 1aef3d6ebd88..a3e6faed7745 100644 --- a/drivers/video/fbdev/aty/atyfb_base.c +++ b/drivers/video/fbdev/aty/atyfb_base.c @@ -79,7 +79,6 @@ #ifdef __powerpc__ #include <asm/machdep.h> -#include <asm/prom.h> #include "../macmodes.h" #endif #ifdef __sparc__ diff --git a/drivers/video/fbdev/aty/radeon_pm.c b/drivers/video/fbdev/aty/radeon_pm.c index b5fbd5329652..97a5972f5b1f 100644 --- a/drivers/video/fbdev/aty/radeon_pm.c +++ b/drivers/video/fbdev/aty/radeon_pm.c @@ -22,7 +22,6 @@ #ifdef CONFIG_PPC_PMAC #include <asm/machdep.h> -#include <asm/prom.h> #include <asm/pmac_feature.h> #endif diff --git a/drivers/video/fbdev/aty/radeonfb.h b/drivers/video/fbdev/aty/radeonfb.h index 93f403cbb415..91d81b576231 100644 --- a/drivers/video/fbdev/aty/radeonfb.h +++ b/drivers/video/fbdev/aty/radeonfb.h @@ -21,7 +21,7 @@ #include <asm/io.h> -#if defined(CONFIG_PPC) || defined(CONFIG_SPARC) +#ifdef CONFIG_SPARC #include <asm/prom.h> #endif diff --git a/drivers/video/fbdev/clps711x-fb.c b/drivers/video/fbdev/clps711x-fb.c index c5d15c6db287..771ce1f76951 100644 --- a/drivers/video/fbdev/clps711x-fb.c +++ b/drivers/video/fbdev/clps711x-fb.c @@ -268,8 +268,7 @@ static int clps711x_fb_probe(struct platform_device *pdev) goto out_fb_release; } - cfb->syscon = - syscon_regmap_lookup_by_compatible("cirrus,ep7209-syscon1"); + cfb->syscon = syscon_regmap_lookup_by_phandle(np, "syscon"); if (IS_ERR(cfb->syscon)) { ret = PTR_ERR(cfb->syscon); goto out_fb_release; diff --git a/drivers/video/fbdev/controlfb.c b/drivers/video/fbdev/controlfb.c index bd59e7b11ed5..aba46118b208 100644 --- a/drivers/video/fbdev/controlfb.c +++ b/drivers/video/fbdev/controlfb.c @@ -47,9 +47,6 @@ #include <linux/nvram.h> #include <linux/adb.h> #include <linux/cuda.h> -#ifdef CONFIG_PPC_PMAC -#include <asm/prom.h> -#endif #ifdef CONFIG_BOOTX_TEXT #include <asm/btext.h> #endif diff --git a/drivers/video/fbdev/i740fb.c b/drivers/video/fbdev/i740fb.c index 52cce0db8bd3..09dd85553d4f 100644 --- a/drivers/video/fbdev/i740fb.c +++ b/drivers/video/fbdev/i740fb.c @@ -657,6 +657,9 @@ static int i740fb_decode_var(const struct fb_var_screeninfo *var, static int i740fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) { + if (!var->pixclock) + return -EINVAL; + switch (var->bits_per_pixel) { case 8: var->red.offset = var->green.offset = var->blue.offset = 0; @@ -740,7 +743,7 @@ static int i740fb_set_par(struct fb_info *info) if (i) return i; - memset(info->screen_base, 0, info->screen_size); + memset_io(info->screen_base, 0, info->screen_size); vga_protect(par); diff --git a/drivers/video/fbdev/imxfb.c b/drivers/video/fbdev/imxfb.c index 68288756ffff..a2f644c97f28 100644 --- a/drivers/video/fbdev/imxfb.c +++ b/drivers/video/fbdev/imxfb.c @@ -925,10 +925,12 @@ static int imxfb_probe(struct platform_device *pdev) sizeof(struct imx_fb_videomode), GFP_KERNEL); if (!fbi->mode) { ret = -ENOMEM; + of_node_put(display_np); goto failed_of_parse; } ret = imxfb_of_read_mode(&pdev->dev, display_np, fbi->mode); + of_node_put(display_np); if (ret) goto failed_of_parse; } diff --git a/drivers/video/fbdev/kyro/fbdev.c b/drivers/video/fbdev/kyro/fbdev.c index 25801e8e3f74..d57772f96ad2 100644 --- a/drivers/video/fbdev/kyro/fbdev.c +++ b/drivers/video/fbdev/kyro/fbdev.c @@ -494,6 +494,8 @@ static int kyrofb_set_par(struct fb_info *info) info->var.hsync_len + info->var.left_margin)) / 1000; + if (!lineclock) + return -EINVAL; /* time for a frame in ns (precision in 32bpp) */ frameclock = lineclock * (info->var.yres + diff --git a/drivers/video/fbdev/matrox/matroxfb_base.h b/drivers/video/fbdev/matrox/matroxfb_base.h index 759dee996af1..958be6805f87 100644 --- a/drivers/video/fbdev/matrox/matroxfb_base.h +++ b/drivers/video/fbdev/matrox/matroxfb_base.h @@ -47,7 +47,6 @@ #include <asm/unaligned.h> #if defined(CONFIG_PPC_PMAC) -#include <asm/prom.h> #include "../macmodes.h" #endif diff --git a/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c b/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c index 63721337a377..a7508f5be343 100644 --- a/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c +++ b/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c @@ -18,6 +18,8 @@ #include <linux/interrupt.h> #include <linux/pci.h> #if defined(CONFIG_OF) +#include <linux/of_address.h> +#include <linux/of_irq.h> #include <linux/of_platform.h> #endif #include "mb862xxfb.h" diff --git a/drivers/video/fbdev/mmp/core.c b/drivers/video/fbdev/mmp/core.c index 154127256a2c..03707461eced 100644 --- a/drivers/video/fbdev/mmp/core.c +++ b/drivers/video/fbdev/mmp/core.c @@ -127,19 +127,18 @@ EXPORT_SYMBOL_GPL(mmp_unregister_panel); */ struct mmp_path *mmp_get_path(const char *name) { - struct mmp_path *path; - int found = 0; + struct mmp_path *path = NULL, *iter; mutex_lock(&disp_lock); - list_for_each_entry(path, &path_list, node) { - if (!strcmp(name, path->name)) { - found = 1; + list_for_each_entry(iter, &path_list, node) { + if (!strcmp(name, iter->name)) { + path = iter; break; } } mutex_unlock(&disp_lock); - return found ? path : NULL; + return path; } EXPORT_SYMBOL_GPL(mmp_get_path); diff --git a/drivers/video/fbdev/neofb.c b/drivers/video/fbdev/neofb.c index 966df2a07360..28d32cbf496b 100644 --- a/drivers/video/fbdev/neofb.c +++ b/drivers/video/fbdev/neofb.c @@ -585,7 +585,7 @@ neofb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) DBG("neofb_check_var"); - if (var->pixclock && PICOS2KHZ(var->pixclock) > par->maxClock) + if (!var->pixclock || PICOS2KHZ(var->pixclock) > par->maxClock) return -EINVAL; /* Is the mode larger than the LCD panel? */ diff --git a/drivers/video/fbdev/omap/hwa742.c b/drivers/video/fbdev/omap/hwa742.c index b191bef22d98..9d9fe5c3a7a1 100644 --- a/drivers/video/fbdev/omap/hwa742.c +++ b/drivers/video/fbdev/omap/hwa742.c @@ -964,7 +964,7 @@ static int hwa742_init(struct omapfb_device *fbdev, int ext_mode, if ((r = calc_extif_timings(ext_clk, &extif_mem_div)) < 0) goto err3; hwa742.extif->set_timings(&hwa742.reg_timings); - clk_enable(hwa742.sys_ck); + clk_prepare_enable(hwa742.sys_ck); calc_hwa742_clk_rates(ext_clk, &sys_clk, &pix_clk); if ((r = calc_extif_timings(sys_clk, &extif_mem_div)) < 0) @@ -1023,7 +1023,7 @@ static int hwa742_init(struct omapfb_device *fbdev, int ext_mode, return 0; err4: - clk_disable(hwa742.sys_ck); + clk_disable_unprepare(hwa742.sys_ck); err3: hwa742.extif->cleanup(); err2: @@ -1037,7 +1037,7 @@ static void hwa742_cleanup(void) hwa742_set_update_mode(OMAPFB_UPDATE_DISABLED); hwa742.extif->cleanup(); hwa742.int_ctrl->cleanup(); - clk_disable(hwa742.sys_ck); + clk_disable_unprepare(hwa742.sys_ck); } struct lcd_ctrl hwa742_ctrl = { diff --git a/drivers/video/fbdev/omap/lcdc.c b/drivers/video/fbdev/omap/lcdc.c index 7317c9aad677..97d20dc0d1d0 100644 --- a/drivers/video/fbdev/omap/lcdc.c +++ b/drivers/video/fbdev/omap/lcdc.c @@ -711,7 +711,7 @@ static int omap_lcdc_init(struct omapfb_device *fbdev, int ext_mode, dev_err(fbdev->dev, "failed to adjust LCD rate\n"); goto fail1; } - clk_enable(lcdc.lcd_ck); + clk_prepare_enable(lcdc.lcd_ck); r = request_irq(OMAP_LCDC_IRQ, lcdc_irq_handler, 0, MODULE_NAME, fbdev); if (r) { @@ -746,7 +746,7 @@ fail4: fail3: free_irq(OMAP_LCDC_IRQ, lcdc.fbdev); fail2: - clk_disable(lcdc.lcd_ck); + clk_disable_unprepare(lcdc.lcd_ck); fail1: clk_put(lcdc.lcd_ck); fail0: @@ -760,7 +760,7 @@ static void omap_lcdc_cleanup(void) free_fbmem(); omap_free_lcd_dma(); free_irq(OMAP_LCDC_IRQ, lcdc.fbdev); - clk_disable(lcdc.lcd_ck); + clk_disable_unprepare(lcdc.lcd_ck); clk_put(lcdc.lcd_ck); } diff --git a/drivers/video/fbdev/omap/sossi.c b/drivers/video/fbdev/omap/sossi.c index 80ac67f27f0d..b9cb8b386627 100644 --- a/drivers/video/fbdev/omap/sossi.c +++ b/drivers/video/fbdev/omap/sossi.c @@ -598,7 +598,7 @@ static int sossi_init(struct omapfb_device *fbdev) l &= ~CONF_SOSSI_RESET_R; omap_writel(l, MOD_CONF_CTRL_1); - clk_enable(sossi.fck); + clk_prepare_enable(sossi.fck); l = omap_readl(ARM_IDLECT2); l &= ~(1 << 8); /* DMACK_REQ */ omap_writel(l, ARM_IDLECT2); @@ -649,7 +649,7 @@ static int sossi_init(struct omapfb_device *fbdev) return 0; err: - clk_disable(sossi.fck); + clk_disable_unprepare(sossi.fck); clk_put(sossi.fck); return r; } @@ -657,6 +657,7 @@ err: static void sossi_cleanup(void) { omap_lcdc_free_dma_callback(); + clk_unprepare(sossi.fck); clk_put(sossi.fck); iounmap(sossi.base); } diff --git a/drivers/video/fbdev/platinumfb.c b/drivers/video/fbdev/platinumfb.c index ce413a9df06e..5b9e26ea6449 100644 --- a/drivers/video/fbdev/platinumfb.c +++ b/drivers/video/fbdev/platinumfb.c @@ -30,9 +30,9 @@ #include <linux/fb.h> #include <linux/init.h> #include <linux/nvram.h> +#include <linux/of_address.h> #include <linux/of_device.h> #include <linux/of_platform.h> -#include <asm/prom.h> #include "macmodes.h" #include "platinumfb.h" diff --git a/drivers/video/fbdev/pm2fb.c b/drivers/video/fbdev/pm2fb.c index c68725eebee3..d3be2c64f1c0 100644 --- a/drivers/video/fbdev/pm2fb.c +++ b/drivers/video/fbdev/pm2fb.c @@ -1504,9 +1504,7 @@ static const struct fb_ops pm2fb_ops = { /** - * Device initialisation - * - * Initialise and allocate resource for PCI device. + * pm2fb_probe - Initialise and allocate resource for PCI device. * * @pdev: PCI device. * @id: PCI device ID. @@ -1711,9 +1709,7 @@ static int pm2fb_probe(struct pci_dev *pdev, const struct pci_device_id *id) } /** - * Device removal. - * - * Release all device resources. + * pm2fb_remove - Release all device resources. * * @pdev: PCI device to clean up. */ diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c index f1551e00eb12..8ad91c251fe6 100644 --- a/drivers/video/fbdev/pxafb.c +++ b/drivers/video/fbdev/pxafb.c @@ -2256,10 +2256,10 @@ static int pxafb_probe(struct platform_device *dev) goto failed; for (i = 0; i < inf->num_modes; i++) inf->modes[i] = pdata->modes[i]; + } else { + inf = of_pxafb_of_mach_info(&dev->dev); } - if (!pdata) - inf = of_pxafb_of_mach_info(&dev->dev); if (IS_ERR_OR_NULL(inf)) goto failed; diff --git a/drivers/video/fbdev/s3fb.c b/drivers/video/fbdev/s3fb.c index 5c74253e7b2c..b93c8eb02336 100644 --- a/drivers/video/fbdev/s3fb.c +++ b/drivers/video/fbdev/s3fb.c @@ -549,6 +549,9 @@ static int s3fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) int rv, mem, step; u16 m, n, r; + if (!var->pixclock) + return -EINVAL; + /* Find appropriate format */ rv = svga_match_format (s3fb_formats, var, NULL); diff --git a/drivers/video/fbdev/sh_mobile_lcdcfb.c b/drivers/video/fbdev/sh_mobile_lcdcfb.c index aa4ebe3192ec..9a4417430b4e 100644 --- a/drivers/video/fbdev/sh_mobile_lcdcfb.c +++ b/drivers/video/fbdev/sh_mobile_lcdcfb.c @@ -531,9 +531,6 @@ static void sh_mobile_lcdc_display_off(struct sh_mobile_lcdc_chan *ch) ch->tx_dev->ops->display_off(ch->tx_dev); } -static int sh_mobile_lcdc_check_var(struct fb_var_screeninfo *var, - struct fb_info *info); - /* ----------------------------------------------------------------------------- * Format helpers */ diff --git a/drivers/video/fbdev/sis/sis_main.c b/drivers/video/fbdev/sis/sis_main.c index 742f62986b80..f28fd69d5eb7 100644 --- a/drivers/video/fbdev/sis/sis_main.c +++ b/drivers/video/fbdev/sis/sis_main.c @@ -4463,7 +4463,7 @@ static void sisfb_post_sis300(struct pci_dev *pdev) SiS_SetReg(SISCR, 0x37, 0x02); SiS_SetReg(SISPART2, 0x00, 0x1c); v4 = 0x00; v5 = 0x00; v6 = 0x10; - if(ivideo->SiS_Pr.UseROM) { + if (ivideo->SiS_Pr.UseROM && bios) { v4 = bios[0xf5]; v5 = bios[0xf6]; v6 = bios[0xf7]; diff --git a/drivers/video/fbdev/tridentfb.c b/drivers/video/fbdev/tridentfb.c index 4d20cb557ff0..319131bd72cf 100644 --- a/drivers/video/fbdev/tridentfb.c +++ b/drivers/video/fbdev/tridentfb.c @@ -996,6 +996,9 @@ static int tridentfb_check_var(struct fb_var_screeninfo *var, int ramdac = 230000; /* 230MHz for most 3D chips */ debug("enter\n"); + if (!var->pixclock) + return -EINVAL; + /* check color depth */ if (bpp == 24) bpp = var->bits_per_pixel = 32; diff --git a/drivers/video/fbdev/udlfb.c b/drivers/video/fbdev/udlfb.c index b6ec0b8e2b72..d280733f283b 100644 --- a/drivers/video/fbdev/udlfb.c +++ b/drivers/video/fbdev/udlfb.c @@ -1650,8 +1650,9 @@ static int dlfb_usb_probe(struct usb_interface *intf, const struct device_attribute *attr; struct dlfb_data *dlfb; struct fb_info *info; - int retval = -ENOMEM; + int retval; struct usb_device *usbdev = interface_to_usbdev(intf); + struct usb_endpoint_descriptor *out; /* usb initialization */ dlfb = kzalloc(sizeof(*dlfb), GFP_KERNEL); @@ -1665,6 +1666,12 @@ static int dlfb_usb_probe(struct usb_interface *intf, dlfb->udev = usb_get_dev(usbdev); usb_set_intfdata(intf, dlfb); + retval = usb_find_common_endpoints(intf->cur_altsetting, NULL, &out, NULL, NULL); + if (retval) { + dev_err(&intf->dev, "Device should have at lease 1 bulk endpoint!\n"); + goto error; + } + dev_dbg(&intf->dev, "console enable=%d\n", console); dev_dbg(&intf->dev, "fb_defio enable=%d\n", fb_defio); dev_dbg(&intf->dev, "shadow enable=%d\n", shadow); @@ -1674,6 +1681,7 @@ static int dlfb_usb_probe(struct usb_interface *intf, if (!dlfb_parse_vendor_descriptor(dlfb, intf)) { dev_err(&intf->dev, "firmware not recognized, incompatible device?\n"); + retval = -ENODEV; goto error; } @@ -1687,8 +1695,10 @@ static int dlfb_usb_probe(struct usb_interface *intf, /* allocates framebuffer driver structure, not framebuffer memory */ info = framebuffer_alloc(0, &dlfb->udev->dev); - if (!info) + if (!info) { + retval = -ENOMEM; goto error; + } dlfb->info = info; info->par = dlfb; diff --git a/drivers/video/fbdev/valkyriefb.c b/drivers/video/fbdev/valkyriefb.c index 8425afe37d7c..a6c9d4f26669 100644 --- a/drivers/video/fbdev/valkyriefb.c +++ b/drivers/video/fbdev/valkyriefb.c @@ -54,10 +54,9 @@ #include <linux/nvram.h> #include <linux/adb.h> #include <linux/cuda.h> +#include <linux/of_address.h> #ifdef CONFIG_MAC #include <asm/macintosh.h> -#else -#include <asm/prom.h> #endif #include "macmodes.h" diff --git a/drivers/video/fbdev/vt8623fb.c b/drivers/video/fbdev/vt8623fb.c index 7a959e5ba90b..a92a8c670cf0 100644 --- a/drivers/video/fbdev/vt8623fb.c +++ b/drivers/video/fbdev/vt8623fb.c @@ -321,6 +321,9 @@ static int vt8623fb_check_var(struct fb_var_screeninfo *var, struct fb_info *inf { int rv, mem, step; + if (!var->pixclock) + return -EINVAL; + /* Find appropriate format */ rv = svga_match_format (vt8623fb_formats, var, NULL); if (rv < 0) diff --git a/drivers/video/of_display_timing.c b/drivers/video/of_display_timing.c index f93b6abbe258..bebd371c6b93 100644 --- a/drivers/video/of_display_timing.c +++ b/drivers/video/of_display_timing.c @@ -199,7 +199,7 @@ struct display_timings *of_get_display_timings(const struct device_node *np) struct display_timing *dt; int r; - dt = kzalloc(sizeof(*dt), GFP_KERNEL); + dt = kmalloc(sizeof(*dt), GFP_KERNEL); if (!dt) { pr_err("%pOF: could not allocate display_timing struct\n", np); diff --git a/drivers/xen/gntalloc.c b/drivers/xen/gntalloc.c index 4849f94372a4..55acb32842a3 100644 --- a/drivers/xen/gntalloc.c +++ b/drivers/xen/gntalloc.c @@ -178,9 +178,9 @@ static void __del_gref(struct gntalloc_gref *gref) unsigned long addr; if (gref->notify.flags & UNMAP_NOTIFY_CLEAR_BYTE) { - uint8_t *tmp = kmap(gref->page); + uint8_t *tmp = kmap_local_page(gref->page); tmp[gref->notify.pgoff] = 0; - kunmap(gref->page); + kunmap_local(tmp); } if (gref->notify.flags & UNMAP_NOTIFY_SEND_EVENT) { notify_remote_via_evtchn(gref->notify.event); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index b7631b88426e..077c95e9baa5 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1060,6 +1060,7 @@ struct btrfs_fs_info { */ spinlock_t relocation_bg_lock; u64 data_reloc_bg; + struct mutex zoned_data_reloc_io_lock; u64 nr_global_roots; diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 71fd99b48283..f26202621989 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -734,7 +734,12 @@ static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); - /* Commit dev_replace state and reserve 1 item for it. */ + /* + * Commit dev_replace state and reserve 1 item for it. + * This is crucial to ensure we won't miss copying extents for new block + * groups that are allocated after we started the device replace, and + * must be done after setting up the device replace state. + */ trans = btrfs_start_transaction(root, 1); if (IS_ERR(trans)) { ret = PTR_ERR(trans); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 126f244cdf88..ed8e288cc369 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3157,6 +3157,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) mutex_init(&fs_info->reloc_mutex); mutex_init(&fs_info->delalloc_root_mutex); mutex_init(&fs_info->zoned_meta_io_lock); + mutex_init(&fs_info->zoned_data_reloc_io_lock); seqlock_init(&fs_info->profiles_lock); INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 724e8fe06aa0..33c19f51d79b 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2658,6 +2658,7 @@ int btrfs_repair_one_sector(struct inode *inode, repair_bio = btrfs_bio_alloc(1); repair_bbio = btrfs_bio(repair_bio); + repair_bbio->file_offset = start; repair_bio->bi_opf = REQ_OP_READ; repair_bio->bi_end_io = failed_bio->bi_end_io; repair_bio->bi_iter.bi_sector = failrec->logical >> 9; @@ -3333,24 +3334,37 @@ static int alloc_new_bio(struct btrfs_inode *inode, ret = calc_bio_boundaries(bio_ctrl, inode, file_offset); if (ret < 0) goto error; - if (wbc) { - struct block_device *bdev; - bdev = fs_info->fs_devices->latest_dev->bdev; - bio_set_dev(bio, bdev); - wbc_init_bio(wbc, bio); - } - if (bio_op(bio) == REQ_OP_ZONE_APPEND) { - struct btrfs_device *device; + if (wbc) { + /* + * For Zone append we need the correct block_device that we are + * going to write to set in the bio to be able to respect the + * hardware limitation. Look it up here: + */ + if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + struct btrfs_device *dev; + + dev = btrfs_zoned_get_device(fs_info, disk_bytenr, + fs_info->sectorsize); + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + goto error; + } - device = btrfs_zoned_get_device(fs_info, disk_bytenr, - fs_info->sectorsize); - if (IS_ERR(device)) { - ret = PTR_ERR(device); - goto error; + bio_set_dev(bio, dev->bdev); + } else { + /* + * Otherwise pick the last added device to support + * cgroup writeback. For multi-device file systems this + * means blk-cgroup policies have to always be set on the + * last added/replaced device. This is a bit odd but has + * been like that for a long time. + */ + bio_set_dev(bio, fs_info->fs_devices->latest_dev->bdev); } - - btrfs_bio(bio)->device = device; + wbc_init_bio(wbc, bio); + } else { + ASSERT(bio_op(bio) != REQ_OP_ZONE_APPEND); } return 0; error: diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 5082b9c70f8c..1c8a43ecfb9f 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7810,8 +7810,6 @@ static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip, const bool csum = !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM); struct bio_vec bvec; struct bvec_iter iter; - const u64 orig_file_offset = dip->file_offset; - u64 start = orig_file_offset; u32 bio_offset = 0; blk_status_t err = BLK_STS_OK; @@ -7821,6 +7819,8 @@ static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip, nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len); pgoff = bvec.bv_offset; for (i = 0; i < nr_sectors; i++) { + u64 start = bbio->file_offset + bio_offset; + ASSERT(pgoff < PAGE_SIZE); if (uptodate && (!csum || !check_data_csum(inode, bbio, @@ -7833,17 +7833,13 @@ static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip, } else { int ret; - ASSERT((start - orig_file_offset) < UINT_MAX); - ret = btrfs_repair_one_sector(inode, - &bbio->bio, - start - orig_file_offset, - bvec.bv_page, pgoff, + ret = btrfs_repair_one_sector(inode, &bbio->bio, + bio_offset, bvec.bv_page, pgoff, start, bbio->mirror_num, submit_dio_repair_bio); if (ret) err = errno_to_blk_status(ret); } - start += sectorsize; ASSERT(bio_offset + sectorsize > bio_offset); bio_offset += sectorsize; pgoff += sectorsize; @@ -7870,6 +7866,7 @@ static blk_status_t btrfs_submit_bio_start_direct_io(struct inode *inode, static void btrfs_end_dio_bio(struct bio *bio) { struct btrfs_dio_private *dip = bio->bi_private; + struct btrfs_bio *bbio = btrfs_bio(bio); blk_status_t err = bio->bi_status; if (err) @@ -7880,12 +7877,12 @@ static void btrfs_end_dio_bio(struct bio *bio) bio->bi_iter.bi_size, err); if (bio_op(bio) == REQ_OP_READ) - err = btrfs_check_read_dio_bio(dip, btrfs_bio(bio), !err); + err = btrfs_check_read_dio_bio(dip, bbio, !err); if (err) dip->dio_bio->bi_status = err; - btrfs_record_physical_zoned(dip->inode, dip->file_offset, bio); + btrfs_record_physical_zoned(dip->inode, bbio->file_offset, bio); bio_put(bio); btrfs_dio_private_put(dip); @@ -8046,6 +8043,7 @@ static void btrfs_submit_direct(const struct iomap_iter *iter, bio = btrfs_bio_clone_partial(dio_bio, clone_offset, clone_len); bio->bi_private = dip; bio->bi_end_io = btrfs_end_dio_bio; + btrfs_bio(bio)->file_offset = file_offset; if (bio_op(bio) == REQ_OP_ZONE_APPEND) { status = extract_ordered_extent(BTRFS_I(inode), bio, diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 11089568b287..8cd713d37ad2 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -3699,6 +3699,31 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, if (!cache) goto skip; + ASSERT(cache->start <= chunk_offset); + /* + * We are using the commit root to search for device extents, so + * that means we could have found a device extent item from a + * block group that was deleted in the current transaction. The + * logical start offset of the deleted block group, stored at + * @chunk_offset, might be part of the logical address range of + * a new block group (which uses different physical extents). + * In this case btrfs_lookup_block_group() has returned the new + * block group, and its start address is less than @chunk_offset. + * + * We skip such new block groups, because it's pointless to + * process them, as we won't find their extents because we search + * for them using the commit root of the extent tree. For a device + * replace it's also fine to skip it, we won't miss copying them + * to the target device because we have the write duplication + * setup through the regular write path (by btrfs_map_block()), + * and we have committed a transaction when we started the device + * replace, right after setting up the device replace state. + */ + if (cache->start < chunk_offset) { + btrfs_put_block_group(cache); + goto skip; + } + if (sctx->is_dev_replace && btrfs_is_zoned(fs_info)) { spin_lock(&cache->lock); if (!cache->to_copy) { @@ -3822,7 +3847,6 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, dev_replace->item_needs_writeback = 1; up_write(&dev_replace->rwsem); - ASSERT(cache->start == chunk_offset); ret = scrub_chunk(sctx, cache, scrub_dev, found_key.offset, dev_extent_len); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 571dae8ad65e..09e4f1a04e6f 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3188,6 +3188,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, ret = btrfs_alloc_log_tree_node(trans, log_root_tree); if (ret) { mutex_unlock(&fs_info->tree_root->log_mutex); + blk_finish_plug(&plug); goto out; } } diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index bd297f23d19e..f3e28f11cfb6 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -328,6 +328,9 @@ struct btrfs_fs_devices { struct btrfs_bio { unsigned int mirror_num; + /* for direct I/O */ + u64 file_offset; + /* @device is for stripe IO submission. */ struct btrfs_device *device; u8 *csum; diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h index cbf016a7bb5d..6dee76248cb4 100644 --- a/fs/btrfs/zoned.h +++ b/fs/btrfs/zoned.h @@ -359,7 +359,7 @@ static inline void btrfs_zoned_data_reloc_lock(struct btrfs_inode *inode) struct btrfs_root *root = inode->root; if (btrfs_is_data_reloc_root(root) && btrfs_is_zoned(root->fs_info)) - btrfs_inode_lock(&inode->vfs_inode, 0); + mutex_lock(&root->fs_info->zoned_data_reloc_io_lock); } static inline void btrfs_zoned_data_reloc_unlock(struct btrfs_inode *inode) @@ -367,7 +367,7 @@ static inline void btrfs_zoned_data_reloc_unlock(struct btrfs_inode *inode) struct btrfs_root *root = inode->root; if (btrfs_is_data_reloc_root(root) && btrfs_is_zoned(root->fs_info)) - btrfs_inode_unlock(&inode->vfs_inode, 0); + mutex_unlock(&root->fs_info->zoned_data_reloc_io_lock); } #endif diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index f1ad6884d4da..5c14ef04e474 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2274,6 +2274,8 @@ retry: list_for_each_entry(req, &ci->i_unsafe_dirops, r_unsafe_dir_item) { s = req->r_session; + if (!s) + continue; if (unlikely(s->s_mds >= max_sessions)) { spin_unlock(&ci->i_unsafe_lock); for (i = 0; i < max_sessions; i++) { @@ -2294,6 +2296,8 @@ retry: list_for_each_entry(req, &ci->i_unsafe_iops, r_unsafe_target_item) { s = req->r_session; + if (!s) + continue; if (unlikely(s->s_mds >= max_sessions)) { spin_unlock(&ci->i_unsafe_lock); for (i = 0; i < max_sessions; i++) { @@ -3870,6 +3874,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex, dout("handle_cap_export inode %p ci %p mds%d mseq %d target %d\n", inode, ci, mds, mseq, target); retry: + down_read(&mdsc->snap_rwsem); spin_lock(&ci->i_ceph_lock); cap = __get_cap_for_mds(ci, mds); if (!cap || cap->cap_id != le64_to_cpu(ex->cap_id)) @@ -3933,6 +3938,7 @@ retry: } spin_unlock(&ci->i_ceph_lock); + up_read(&mdsc->snap_rwsem); mutex_unlock(&session->s_mutex); /* open target session */ @@ -3958,6 +3964,7 @@ retry: out_unlock: spin_unlock(&ci->i_ceph_lock); + up_read(&mdsc->snap_rwsem); mutex_unlock(&session->s_mutex); if (tsession) { mutex_unlock(&tsession->s_mutex); diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index fa38c013126d..00c3de177dd6 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -4434,8 +4434,6 @@ static void maybe_recover_session(struct ceph_mds_client *mdsc) bool check_session_state(struct ceph_mds_session *s) { - struct ceph_fs_client *fsc = s->s_mdsc->fsc; - switch (s->s_state) { case CEPH_MDS_SESSION_OPEN: if (s->s_ttl && time_after(jiffies, s->s_ttl)) { @@ -4444,10 +4442,6 @@ bool check_session_state(struct ceph_mds_session *s) } break; case CEPH_MDS_SESSION_CLOSING: - /* Should never reach this when not force unmounting */ - WARN_ON_ONCE(s->s_ttl && - READ_ONCE(fsc->mount_state) != CEPH_MOUNT_SHUTDOWN); - fallthrough; case CEPH_MDS_SESSION_NEW: case CEPH_MDS_SESSION_RESTARTING: case CEPH_MDS_SESSION_CLOSED: diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 902e8c6c0f9c..42e14f408856 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -534,12 +534,19 @@ int cifs_reconnect(struct TCP_Server_Info *server, bool mark_smb_session) { /* If tcp session is not an dfs connection, then reconnect to last target server */ spin_lock(&cifs_tcp_ses_lock); - if (!server->is_dfs_conn || !server->origin_fullpath || !server->leaf_fullpath) { + if (!server->is_dfs_conn) { spin_unlock(&cifs_tcp_ses_lock); return __cifs_reconnect(server, mark_smb_session); } spin_unlock(&cifs_tcp_ses_lock); + mutex_lock(&server->refpath_lock); + if (!server->origin_fullpath || !server->leaf_fullpath) { + mutex_unlock(&server->refpath_lock); + return __cifs_reconnect(server, mark_smb_session); + } + mutex_unlock(&server->refpath_lock); + return reconnect_dfs_server(server); } #else @@ -3675,9 +3682,11 @@ static void setup_server_referral_paths(struct mount_ctx *mnt_ctx) { struct TCP_Server_Info *server = mnt_ctx->server; + mutex_lock(&server->refpath_lock); server->origin_fullpath = mnt_ctx->origin_fullpath; server->leaf_fullpath = mnt_ctx->leaf_fullpath; server->current_fullpath = mnt_ctx->leaf_fullpath; + mutex_unlock(&server->refpath_lock); mnt_ctx->origin_fullpath = mnt_ctx->leaf_fullpath = NULL; } diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index 30e040da4f09..956f8e5cf3e7 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -1422,12 +1422,14 @@ static int refresh_tcon(struct cifs_ses **sessions, struct cifs_tcon *tcon, bool struct TCP_Server_Info *server = tcon->ses->server; mutex_lock(&server->refpath_lock); - if (strcasecmp(server->leaf_fullpath, server->origin_fullpath)) - __refresh_tcon(server->leaf_fullpath + 1, sessions, tcon, force_refresh); + if (server->origin_fullpath) { + if (server->leaf_fullpath && strcasecmp(server->leaf_fullpath, + server->origin_fullpath)) + __refresh_tcon(server->leaf_fullpath + 1, sessions, tcon, force_refresh); + __refresh_tcon(server->origin_fullpath + 1, sessions, tcon, force_refresh); + } mutex_unlock(&server->refpath_lock); - __refresh_tcon(server->origin_fullpath + 1, sessions, tcon, force_refresh); - return 0; } @@ -1530,11 +1532,14 @@ static void refresh_mounts(struct cifs_ses **sessions) list_del_init(&tcon->ulist); mutex_lock(&server->refpath_lock); - if (strcasecmp(server->leaf_fullpath, server->origin_fullpath)) - __refresh_tcon(server->leaf_fullpath + 1, sessions, tcon, false); + if (server->origin_fullpath) { + if (server->leaf_fullpath && strcasecmp(server->leaf_fullpath, + server->origin_fullpath)) + __refresh_tcon(server->leaf_fullpath + 1, sessions, tcon, false); + __refresh_tcon(server->origin_fullpath + 1, sessions, tcon, false); + } mutex_unlock(&server->refpath_lock); - __refresh_tcon(server->origin_fullpath + 1, sessions, tcon, false); cifs_put_tcon(tcon); } } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index a67df8eaf702..d6aaeff4a30a 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1858,9 +1858,17 @@ smb2_copychunk_range(const unsigned int xid, int chunks_copied = 0; bool chunk_sizes_updated = false; ssize_t bytes_written, total_bytes_written = 0; + struct inode *inode; pcchunk = kmalloc(sizeof(struct copychunk_ioctl), GFP_KERNEL); + /* + * We need to flush all unwritten data before we can send the + * copychunk ioctl to the server. + */ + inode = d_inode(trgtfile->dentry); + filemap_write_and_wait(inode->i_mapping); + if (pcchunk == NULL) return -ENOMEM; diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index d9d1c353bafc..c667e6ddfe2f 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -464,13 +464,12 @@ smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, return -EIO; } - tr_hdr = kmalloc(sizeof(*tr_hdr), GFP_NOFS); + tr_hdr = kzalloc(sizeof(*tr_hdr), GFP_NOFS); if (!tr_hdr) return -ENOMEM; memset(&cur_rqst[0], 0, sizeof(cur_rqst)); memset(&iov, 0, sizeof(iov)); - memset(tr_hdr, 0, sizeof(*tr_hdr)); iov.iov_base = tr_hdr; iov.iov_len = sizeof(*tr_hdr); diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 0ed880f42525..e6dea6dfca16 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1066,12 +1066,9 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, /* wake up the caller thread for sync decompression */ if (sync) { - unsigned long flags; - - spin_lock_irqsave(&io->u.wait.lock, flags); if (!atomic_add_return(bios, &io->pending_bios)) - wake_up_locked(&io->u.wait); - spin_unlock_irqrestore(&io->u.wait.lock, flags); + complete(&io->u.done); + return; } @@ -1217,7 +1214,7 @@ jobqueue_init(struct super_block *sb, } else { fg_out: q = fgq; - init_waitqueue_head(&fgq->u.wait); + init_completion(&fgq->u.done); atomic_set(&fgq->pending_bios, 0); } q->sb = sb; @@ -1419,8 +1416,7 @@ static void z_erofs_runqueue(struct super_block *sb, return; /* wait until all bios are completed */ - io_wait_event(io[JQ_SUBMIT].u.wait, - !atomic_read(&io[JQ_SUBMIT].pending_bios)); + wait_for_completion_io(&io[JQ_SUBMIT].u.done); /* handle synchronous decompress queue in the caller context */ z_erofs_decompress_queue(&io[JQ_SUBMIT], pagepool); diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h index e043216b545f..800b11c53f57 100644 --- a/fs/erofs/zdata.h +++ b/fs/erofs/zdata.h @@ -97,7 +97,7 @@ struct z_erofs_decompressqueue { z_erofs_next_pcluster_t head; union { - wait_queue_head_t wait; + struct completion done; struct work_struct work; } u; }; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 3f87cca49f0c..a743b1e3b89e 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2273,6 +2273,10 @@ static inline int ext4_forced_shutdown(struct ext4_sb_info *sbi) * Structure of a directory entry */ #define EXT4_NAME_LEN 255 +/* + * Base length of the ext4 directory entry excluding the name length + */ +#define EXT4_BASE_DIR_LEN (sizeof(struct ext4_dir_entry_2) - EXT4_NAME_LEN) struct ext4_dir_entry { __le32 inode; /* Inode number */ @@ -3032,7 +3036,7 @@ extern int ext4_inode_attach_jinode(struct inode *inode); extern int ext4_can_truncate(struct inode *inode); extern int ext4_truncate(struct inode *); extern int ext4_break_layouts(struct inode *); -extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length); +extern int ext4_punch_hole(struct file *file, loff_t offset, loff_t length); extern void ext4_set_inode_flags(struct inode *, bool init); extern int ext4_alloc_da_blocks(struct inode *inode); extern void ext4_set_aops(struct inode *inode); @@ -3064,6 +3068,7 @@ int ext4_fileattr_set(struct user_namespace *mnt_userns, struct dentry *dentry, struct fileattr *fa); int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa); extern void ext4_reset_inode_seed(struct inode *inode); +int ext4_update_overhead(struct super_block *sb); /* migrate.c */ extern int ext4_ext_migrate(struct inode *); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 0d98cf402282..e473fde6b64b 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4500,9 +4500,9 @@ retry: return ret > 0 ? ret2 : ret; } -static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len); +static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len); -static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len); +static int ext4_insert_range(struct file *file, loff_t offset, loff_t len); static long ext4_zero_range(struct file *file, loff_t offset, loff_t len, int mode) @@ -4574,6 +4574,10 @@ static long ext4_zero_range(struct file *file, loff_t offset, /* Wait all existing dio workers, newcomers will block on i_rwsem */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out_mutex; + /* Preallocate the range including the unaligned edges */ if (partial_begin || partial_end) { ret = ext4_alloc_file_blocks(file, @@ -4690,7 +4694,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) return -EOPNOTSUPP; if (mode & FALLOC_FL_PUNCH_HOLE) { - ret = ext4_punch_hole(inode, offset, len); + ret = ext4_punch_hole(file, offset, len); goto exit; } @@ -4699,12 +4703,12 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) goto exit; if (mode & FALLOC_FL_COLLAPSE_RANGE) { - ret = ext4_collapse_range(inode, offset, len); + ret = ext4_collapse_range(file, offset, len); goto exit; } if (mode & FALLOC_FL_INSERT_RANGE) { - ret = ext4_insert_range(inode, offset, len); + ret = ext4_insert_range(file, offset, len); goto exit; } @@ -4740,6 +4744,10 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) /* Wait all existing dio workers, newcomers will block on i_rwsem */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out; + ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags); if (ret) goto out; @@ -5241,8 +5249,9 @@ out: * This implements the fallocate's collapse range functionality for ext4 * Returns: 0 and non-zero on error. */ -static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) +static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len) { + struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; ext4_lblk_t punch_start, punch_stop; @@ -5294,6 +5303,10 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) /* Wait for existing dio to complete */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out_mutex; + /* * Prevent page faults from reinstantiating pages we have released from * page cache. @@ -5387,8 +5400,9 @@ out_mutex: * by len bytes. * Returns 0 on success, error otherwise. */ -static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) +static int ext4_insert_range(struct file *file, loff_t offset, loff_t len) { + struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; handle_t *handle; @@ -5445,6 +5459,10 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) /* Wait for existing dio to complete */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out_mutex; + /* * Prevent page faults from reinstantiating pages we have released from * page cache. diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 13740f2d0e61..646ece9b3455 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3953,12 +3953,14 @@ int ext4_break_layouts(struct inode *inode) * Returns: 0 on success or negative on failure */ -int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) +int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) { + struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; ext4_lblk_t first_block, stop_block; struct address_space *mapping = inode->i_mapping; - loff_t first_block_offset, last_block_offset; + loff_t first_block_offset, last_block_offset, max_length; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); handle_t *handle; unsigned int credits; int ret = 0, ret2 = 0; @@ -4001,6 +4003,14 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) offset; } + /* + * For punch hole the length + offset needs to be within one block + * before last range. Adjust the length if it goes beyond that limit. + */ + max_length = sbi->s_bitmap_maxbytes - inode->i_sb->s_blocksize; + if (offset + length > max_length) + length = max_length - offset; + if (offset & (sb->s_blocksize - 1) || (offset + length) & (sb->s_blocksize - 1)) { /* @@ -4016,6 +4026,10 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) /* Wait all existing dio workers, newcomers will block on i_rwsem */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out_mutex; + /* * Prevent page faults from reinstantiating pages we have released from * page cache. diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 992229ca2d83..ba44fa1be70a 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -1652,3 +1652,19 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return ext4_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); } #endif + +static void set_overhead(struct ext4_super_block *es, const void *arg) +{ + es->s_overhead_clusters = cpu_to_le32(*((unsigned long *) arg)); +} + +int ext4_update_overhead(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (sb_rdonly(sb) || sbi->s_overhead == 0 || + sbi->s_overhead == le32_to_cpu(sbi->s_es->s_overhead_clusters)) + return 0; + + return ext4_update_superblocks_fn(sb, set_overhead, &sbi->s_overhead); +} diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index e37da8d5cd0c..767b4bfe39c3 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1466,10 +1466,10 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size, de = (struct ext4_dir_entry_2 *)search_buf; dlimit = search_buf + buf_size; - while ((char *) de < dlimit) { + while ((char *) de < dlimit - EXT4_BASE_DIR_LEN) { /* this code is executed quadratically often */ /* do minimal checking `by hand' */ - if ((char *) de + de->name_len <= dlimit && + if (de->name + de->name_len <= dlimit && ext4_match(dir, fname, de)) { /* found a match - just to be sure, do * a full check */ diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 495ce59fb4ad..14695e2b5042 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -134,8 +134,10 @@ static void ext4_finish_bio(struct bio *bio) continue; } clear_buffer_async_write(bh); - if (bio->bi_status) + if (bio->bi_status) { + set_buffer_write_io_error(bh); buffer_io_error(bh); + } } while ((bh = bh->b_this_page) != head); spin_unlock_irqrestore(&head->b_uptodate_lock, flags); if (!under_io) { diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 81749eaddf4c..1466fbdbc8e3 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1199,20 +1199,25 @@ static void ext4_put_super(struct super_block *sb) int aborted = 0; int i, err; - ext4_unregister_li_request(sb); - ext4_quota_off_umount(sb); - - flush_work(&sbi->s_error_work); - destroy_workqueue(sbi->rsv_conversion_wq); - ext4_release_orphan_info(sb); - /* * Unregister sysfs before destroying jbd2 journal. * Since we could still access attr_journal_task attribute via sysfs * path which could have sbi->s_journal->j_task as NULL + * Unregister sysfs before flush sbi->s_error_work. + * Since user may read /proc/fs/ext4/xx/mb_groups during umount, If + * read metadata verify failed then will queue error work. + * flush_stashed_error_work will call start_this_handle may trigger + * BUG_ON. */ ext4_unregister_sysfs(sb); + ext4_unregister_li_request(sb); + ext4_quota_off_umount(sb); + + flush_work(&sbi->s_error_work); + destroy_workqueue(sbi->rsv_conversion_wq); + ext4_release_orphan_info(sb); + if (sbi->s_journal) { aborted = is_journal_aborted(sbi->s_journal); err = jbd2_journal_destroy(sbi->s_journal); @@ -4172,9 +4177,11 @@ static int count_overhead(struct super_block *sb, ext4_group_t grp, ext4_fsblk_t first_block, last_block, b; ext4_group_t i, ngroups = ext4_get_groups_count(sb); int s, j, count = 0; + int has_super = ext4_bg_has_super(sb, grp); if (!ext4_has_feature_bigalloc(sb)) - return (ext4_bg_has_super(sb, grp) + ext4_bg_num_gdb(sb, grp) + + return (has_super + ext4_bg_num_gdb(sb, grp) + + (has_super ? le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) : 0) + sbi->s_itb_per_group + 2); first_block = le32_to_cpu(sbi->s_es->s_first_data_block) + @@ -5282,9 +5289,18 @@ no_journal: * Get the # of file system overhead blocks from the * superblock if present. */ - if (es->s_overhead_clusters) - sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters); - else { + sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters); + /* ignore the precalculated value if it is ridiculous */ + if (sbi->s_overhead > ext4_blocks_count(es)) + sbi->s_overhead = 0; + /* + * If the bigalloc feature is not enabled recalculating the + * overhead doesn't take long, so we might as well just redo + * it to make sure we are using the correct value. + */ + if (!ext4_has_feature_bigalloc(sb)) + sbi->s_overhead = 0; + if (sbi->s_overhead == 0) { err = ext4_calculate_overhead(sb); if (err) goto failed_mount_wq; @@ -5602,6 +5618,8 @@ static int ext4_fill_super(struct super_block *sb, struct fs_context *fc) ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. " "Quota mode: %s.", descr, ext4_quota_mode(sb)); + /* Update the s_overhead_clusters if necessary */ + ext4_update_overhead(sb); return 0; free_sbi: diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index f5366feea82d..909085a78f9c 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -98,9 +98,9 @@ repeat: } if (unlikely(!PageUptodate(page))) { - if (page->index == sbi->metapage_eio_ofs && - sbi->metapage_eio_cnt++ == MAX_RETRY_META_PAGE_EIO) { - set_ckpt_flags(sbi, CP_ERROR_FLAG); + if (page->index == sbi->metapage_eio_ofs) { + if (sbi->metapage_eio_cnt++ == MAX_RETRY_META_PAGE_EIO) + set_ckpt_flags(sbi, CP_ERROR_FLAG); } else { sbi->metapage_eio_ofs = page->index; sbi->metapage_eio_cnt = 0; diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 8e0c2e773c8d..9a1a526f2092 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -388,11 +388,23 @@ int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr) return 0; } -static void __attach_io_flag(struct f2fs_io_info *fio, unsigned int io_flag) +static unsigned int f2fs_io_flags(struct f2fs_io_info *fio) { unsigned int temp_mask = (1 << NR_TEMP_TYPE) - 1; - unsigned int fua_flag = io_flag & temp_mask; - unsigned int meta_flag = (io_flag >> NR_TEMP_TYPE) & temp_mask; + unsigned int fua_flag, meta_flag, io_flag; + unsigned int op_flags = 0; + + if (fio->op != REQ_OP_WRITE) + return 0; + if (fio->type == DATA) + io_flag = fio->sbi->data_io_flag; + else if (fio->type == NODE) + io_flag = fio->sbi->node_io_flag; + else + return 0; + + fua_flag = io_flag & temp_mask; + meta_flag = (io_flag >> NR_TEMP_TYPE) & temp_mask; /* * data/node io flag bits per temp: @@ -401,9 +413,10 @@ static void __attach_io_flag(struct f2fs_io_info *fio, unsigned int io_flag) * Cold | Warm | Hot | Cold | Warm | Hot | */ if ((1 << fio->temp) & meta_flag) - fio->op_flags |= REQ_META; + op_flags |= REQ_META; if ((1 << fio->temp) & fua_flag) - fio->op_flags |= REQ_FUA; + op_flags |= REQ_FUA; + return op_flags; } static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages) @@ -413,14 +426,10 @@ static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages) sector_t sector; struct bio *bio; - if (fio->type == DATA) - __attach_io_flag(fio, sbi->data_io_flag); - else if (fio->type == NODE) - __attach_io_flag(fio, sbi->node_io_flag); - bdev = f2fs_target_device(sbi, fio->new_blkaddr, §or); - bio = bio_alloc_bioset(bdev, npages, fio->op | fio->op_flags, GFP_NOIO, - &f2fs_bioset); + bio = bio_alloc_bioset(bdev, npages, + fio->op | fio->op_flags | f2fs_io_flags(fio), + GFP_NOIO, &f2fs_bioset); bio->bi_iter.bi_sector = sector; if (is_read_io(fio->op)) { bio->bi_end_io = f2fs_read_end_io; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index cd1e65bcf0b0..8c570de21ed5 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -154,7 +154,6 @@ struct f2fs_mount_info { int s_jquota_fmt; /* Format of quota to use */ #endif /* For which write hints are passed down to block layer */ - int whint_mode; int alloc_mode; /* segment allocation policy */ int fsync_mode; /* fsync policy */ int fs_mode; /* fs mode: LFS or ADAPTIVE */ @@ -1334,12 +1333,6 @@ enum { }; enum { - WHINT_MODE_OFF, /* not pass down write hints */ - WHINT_MODE_USER, /* try to pass down hints given by users */ - WHINT_MODE_FS, /* pass down hints with F2FS policy */ -}; - -enum { ALLOC_MODE_DEFAULT, /* stay default */ ALLOC_MODE_REUSE, /* reuse segments as much as possible */ }; @@ -3657,8 +3650,6 @@ void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi); int __init f2fs_create_segment_manager_caches(void); void f2fs_destroy_segment_manager_caches(void); int f2fs_rw_hint_to_seg_type(enum rw_hint hint); -enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi, - enum page_type type, enum temp_type temp); unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi, unsigned int segno); unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi, diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 71f232dcf3c2..83639238a1fe 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -550,7 +550,8 @@ make_now: } f2fs_set_inode_flags(inode); - if (file_should_truncate(inode)) { + if (file_should_truncate(inode) && + !is_sbi_flag_set(sbi, SBI_POR_DOING)) { ret = f2fs_truncate(inode); if (ret) goto bad_inode; diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 22dfeb991529..bd9731cdec56 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -3243,101 +3243,6 @@ int f2fs_rw_hint_to_seg_type(enum rw_hint hint) } } -/* This returns write hints for each segment type. This hints will be - * passed down to block layer. There are mapping tables which depend on - * the mount option 'whint_mode'. - * - * 1) whint_mode=off. F2FS only passes down WRITE_LIFE_NOT_SET. - * - * 2) whint_mode=user-based. F2FS tries to pass down hints given by users. - * - * User F2FS Block - * ---- ---- ----- - * META WRITE_LIFE_NOT_SET - * HOT_NODE " - * WARM_NODE " - * COLD_NODE " - * ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME - * extension list " " - * - * -- buffered io - * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME - * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT - * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET - * WRITE_LIFE_NONE " " - * WRITE_LIFE_MEDIUM " " - * WRITE_LIFE_LONG " " - * - * -- direct io - * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME - * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT - * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET - * WRITE_LIFE_NONE " WRITE_LIFE_NONE - * WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM - * WRITE_LIFE_LONG " WRITE_LIFE_LONG - * - * 3) whint_mode=fs-based. F2FS passes down hints with its policy. - * - * User F2FS Block - * ---- ---- ----- - * META WRITE_LIFE_MEDIUM; - * HOT_NODE WRITE_LIFE_NOT_SET - * WARM_NODE " - * COLD_NODE WRITE_LIFE_NONE - * ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME - * extension list " " - * - * -- buffered io - * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME - * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT - * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_LONG - * WRITE_LIFE_NONE " " - * WRITE_LIFE_MEDIUM " " - * WRITE_LIFE_LONG " " - * - * -- direct io - * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME - * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT - * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET - * WRITE_LIFE_NONE " WRITE_LIFE_NONE - * WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM - * WRITE_LIFE_LONG " WRITE_LIFE_LONG - */ - -enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi, - enum page_type type, enum temp_type temp) -{ - if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_USER) { - if (type == DATA) { - if (temp == WARM) - return WRITE_LIFE_NOT_SET; - else if (temp == HOT) - return WRITE_LIFE_SHORT; - else if (temp == COLD) - return WRITE_LIFE_EXTREME; - } else { - return WRITE_LIFE_NOT_SET; - } - } else if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_FS) { - if (type == DATA) { - if (temp == WARM) - return WRITE_LIFE_LONG; - else if (temp == HOT) - return WRITE_LIFE_SHORT; - else if (temp == COLD) - return WRITE_LIFE_EXTREME; - } else if (type == NODE) { - if (temp == WARM || temp == HOT) - return WRITE_LIFE_NOT_SET; - else if (temp == COLD) - return WRITE_LIFE_NONE; - } else if (type == META) { - return WRITE_LIFE_MEDIUM; - } - } - return WRITE_LIFE_NOT_SET; -} - static int __get_segment_type_2(struct f2fs_io_info *fio) { if (fio->type == DATA) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index ea939db18f88..4368f90571bd 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -138,7 +138,6 @@ enum { Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, - Opt_whint, Opt_alloc, Opt_fsync, Opt_test_dummy_encryption, @@ -214,7 +213,6 @@ static match_table_t f2fs_tokens = { {Opt_jqfmt_vfsold, "jqfmt=vfsold"}, {Opt_jqfmt_vfsv0, "jqfmt=vfsv0"}, {Opt_jqfmt_vfsv1, "jqfmt=vfsv1"}, - {Opt_whint, "whint_mode=%s"}, {Opt_alloc, "alloc_mode=%s"}, {Opt_fsync, "fsync_mode=%s"}, {Opt_test_dummy_encryption, "test_dummy_encryption=%s"}, @@ -975,22 +973,6 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) f2fs_info(sbi, "quota operations not supported"); break; #endif - case Opt_whint: - name = match_strdup(&args[0]); - if (!name) - return -ENOMEM; - if (!strcmp(name, "user-based")) { - F2FS_OPTION(sbi).whint_mode = WHINT_MODE_USER; - } else if (!strcmp(name, "off")) { - F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF; - } else if (!strcmp(name, "fs-based")) { - F2FS_OPTION(sbi).whint_mode = WHINT_MODE_FS; - } else { - kfree(name); - return -EINVAL; - } - kfree(name); - break; case Opt_alloc: name = match_strdup(&args[0]); if (!name) @@ -1328,12 +1310,6 @@ default_check: return -EINVAL; } - /* Not pass down write hints if the number of active logs is lesser - * than NR_CURSEG_PERSIST_TYPE. - */ - if (F2FS_OPTION(sbi).active_logs != NR_CURSEG_PERSIST_TYPE) - F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF; - if (f2fs_sb_has_readonly(sbi) && !f2fs_readonly(sbi->sb)) { f2fs_err(sbi, "Allow to mount readonly mode only"); return -EROFS; @@ -1978,10 +1954,6 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",prjquota"); #endif f2fs_show_quota_options(seq, sbi->sb); - if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_USER) - seq_printf(seq, ",whint_mode=%s", "user-based"); - else if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_FS) - seq_printf(seq, ",whint_mode=%s", "fs-based"); fscrypt_show_test_dummy_encryption(seq, ',', sbi->sb); @@ -2033,7 +2005,6 @@ static void default_options(struct f2fs_sb_info *sbi) F2FS_OPTION(sbi).active_logs = NR_CURSEG_PERSIST_TYPE; F2FS_OPTION(sbi).inline_xattr_size = DEFAULT_INLINE_XATTR_ADDRS; - F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF; F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_DEFAULT; F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_POSIX; F2FS_OPTION(sbi).s_resuid = make_kuid(&init_user_ns, F2FS_DEF_RESUID); @@ -2314,8 +2285,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) need_stop_gc = true; } - if (*flags & SB_RDONLY || - F2FS_OPTION(sbi).whint_mode != org_mount_opt.whint_mode) { + if (*flags & SB_RDONLY) { sync_inodes_sb(sb); set_sbi_flag(sbi, SBI_IS_DIRTY); diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 22b41acfbbc3..48f01323c37c 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -899,10 +899,10 @@ retry: ret = gfs2_glock_nq(gh); if (ret) goto out_uninit; -retry_under_glock: /* Silently fall back to buffered I/O when writing beyond EOF */ if (iocb->ki_pos + iov_iter_count(from) > i_size_read(&ip->i_inode)) goto out; +retry_under_glock: from->nofault = true; ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL, @@ -991,8 +991,6 @@ retry_under_glock: if (leftover != window_size) { if (gfs2_holder_queued(&gh)) goto retry_under_glock; - if (written) - goto out_uninit; goto retry; } } @@ -1069,8 +1067,6 @@ retry_under_glock: from->count = min(from->count, window_size - leftover); if (gfs2_holder_queued(gh)) goto retry_under_glock; - if (read && !(iocb->ki_flags & IOCB_DIRECT)) - goto out_uninit; goto retry; } } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 99c7477cee5c..dd3a088db11d 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -206,7 +206,7 @@ hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr, info.flags = 0; info.length = len; info.low_limit = current->mm->mmap_base; - info.high_limit = TASK_SIZE; + info.high_limit = arch_get_mmap_end(addr); info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; return vm_unmapped_area(&info); @@ -222,7 +222,7 @@ hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr, info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = max(PAGE_SIZE, mmap_min_addr); - info.high_limit = current->mm->mmap_base; + info.high_limit = arch_get_mmap_base(addr, current->mm->mmap_base); info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; addr = vm_unmapped_area(&info); @@ -237,7 +237,7 @@ hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr, VM_BUG_ON(addr != -ENOMEM); info.flags = 0; info.low_limit = current->mm->mmap_base; - info.high_limit = TASK_SIZE; + info.high_limit = arch_get_mmap_end(addr); addr = vm_unmapped_area(&info); } @@ -251,6 +251,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; struct hstate *h = hstate_file(file); + const unsigned long mmap_end = arch_get_mmap_end(addr); if (len & ~huge_page_mask(h)) return -EINVAL; @@ -266,7 +267,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, if (addr) { addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); - if (TASK_SIZE - len >= addr && + if (mmap_end - len >= addr && (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/fs/io_uring.c b/fs/io_uring.c index 4479013854d2..e01f595f5b7d 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2797,11 +2797,10 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin) /* order with io_complete_rw_iopoll(), e.g. ->result updates */ if (!smp_load_acquire(&req->iopoll_completed)) break; + nr_events++; if (unlikely(req->flags & REQ_F_CQE_SKIP)) continue; - __io_fill_cqe_req(req, req->result, io_put_kbuf(req, 0)); - nr_events++; } if (unlikely(!nr_events)) @@ -3784,6 +3783,7 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode) if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll) return -EOPNOTSUPP; + kiocb->private = NULL; kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE; kiocb->ki_complete = io_complete_rw_iopoll; req->iopoll_completed = 0; @@ -3832,8 +3832,10 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) iovec = NULL; } ret = io_rw_init_file(req, FMODE_READ); - if (unlikely(ret)) + if (unlikely(ret)) { + kfree(iovec); return ret; + } req->result = iov_iter_count(&s->iter); if (force_nonblock) { @@ -3958,8 +3960,10 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) iovec = NULL; } ret = io_rw_init_file(req, FMODE_WRITE); - if (unlikely(ret)) + if (unlikely(ret)) { + kfree(iovec); return ret; + } req->result = iov_iter_count(&s->iter); if (force_nonblock) { @@ -5204,6 +5208,8 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; + if (unlikely(sqe->addr2 || sqe->file_index)) + return -EINVAL; sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); @@ -5415,6 +5421,8 @@ static int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; + if (unlikely(sqe->addr2 || sqe->file_index)) + return -EINVAL; sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); @@ -10585,7 +10593,7 @@ static int io_ringfd_unregister(struct io_ring_ctx *ctx, void __user *__arg, ret = -EFAULT; break; } - if (reg.resv || reg.offset >= IO_RINGFD_REG_MAX) { + if (reg.resv || reg.data || reg.offset >= IO_RINGFD_REG_MAX) { ret = -EINVAL; break; } diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 5b9408e3b370..ac7f067b7bdd 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -488,7 +488,6 @@ void jbd2_journal_commit_transaction(journal_t *journal) jbd2_journal_wait_updates(journal); commit_transaction->t_state = T_SWITCH; - write_unlock(&journal->j_state_lock); J_ASSERT (atomic_read(&commit_transaction->t_outstanding_credits) <= journal->j_max_transaction_buffers); @@ -508,6 +507,8 @@ void jbd2_journal_commit_transaction(journal_t *journal) * has reserved. This is consistent with the existing behaviour * that multiple jbd2_journal_get_write_access() calls to the same * buffer are perfectly permissible. + * We use journal->j_state_lock here to serialize processing of + * t_reserved_list with eviction of buffers from journal_unmap_buffer(). */ while (commit_transaction->t_reserved_list) { jh = commit_transaction->t_reserved_list; @@ -527,6 +528,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) jbd2_journal_refile_buffer(journal, jh); } + write_unlock(&journal->j_state_lock); /* * Now try to drop any written-back buffers from the journal's * checkpoint lists. We do this *before* commit because it potentially diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 61a8edc4ba8b..e205fde7163a 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -1406,7 +1406,12 @@ static void __kernfs_remove(struct kernfs_node *kn) */ void kernfs_remove(struct kernfs_node *kn) { - struct kernfs_root *root = kernfs_root(kn); + struct kernfs_root *root; + + if (!kn) + return; + + root = kernfs_root(kn); down_write(&root->kernfs_rwsem); __kernfs_remove(kn); diff --git a/fs/ksmbd/misc.c b/fs/ksmbd/misc.c index 60e7ac62c917..1e2076a53bed 100644 --- a/fs/ksmbd/misc.c +++ b/fs/ksmbd/misc.c @@ -158,19 +158,41 @@ out: * Return : windows path string or error */ -char *convert_to_nt_pathname(char *filename) +char *convert_to_nt_pathname(struct ksmbd_share_config *share, + struct path *path) { - char *ab_pathname; + char *pathname, *ab_pathname, *nt_pathname; + int share_path_len = share->path_sz; - if (strlen(filename) == 0) - filename = "\\"; + pathname = kmalloc(PATH_MAX, GFP_KERNEL); + if (!pathname) + return ERR_PTR(-EACCES); - ab_pathname = kstrdup(filename, GFP_KERNEL); - if (!ab_pathname) - return NULL; + ab_pathname = d_path(path, pathname, PATH_MAX); + if (IS_ERR(ab_pathname)) { + nt_pathname = ERR_PTR(-EACCES); + goto free_pathname; + } + + if (strncmp(ab_pathname, share->path, share_path_len)) { + nt_pathname = ERR_PTR(-EACCES); + goto free_pathname; + } + + nt_pathname = kzalloc(strlen(&ab_pathname[share_path_len]) + 2, GFP_KERNEL); + if (!nt_pathname) { + nt_pathname = ERR_PTR(-ENOMEM); + goto free_pathname; + } + if (ab_pathname[share_path_len] == '\0') + strcpy(nt_pathname, "/"); + strcat(nt_pathname, &ab_pathname[share_path_len]); + + ksmbd_conv_path_to_windows(nt_pathname); - ksmbd_conv_path_to_windows(ab_pathname); - return ab_pathname; +free_pathname: + kfree(pathname); + return nt_pathname; } int get_nlink(struct kstat *st) diff --git a/fs/ksmbd/misc.h b/fs/ksmbd/misc.h index 253366bd0951..aae2a252945f 100644 --- a/fs/ksmbd/misc.h +++ b/fs/ksmbd/misc.h @@ -14,7 +14,8 @@ struct ksmbd_file; int match_pattern(const char *str, size_t len, const char *pattern); int ksmbd_validate_filename(char *filename); int parse_stream_name(char *filename, char **stream_name, int *s_type); -char *convert_to_nt_pathname(char *filename); +char *convert_to_nt_pathname(struct ksmbd_share_config *share, + struct path *path); int get_nlink(struct kstat *st); void ksmbd_conv_path_to_unix(char *path); void ksmbd_strip_last_slash(char *path); diff --git a/fs/ksmbd/oplock.c b/fs/ksmbd/oplock.c index 23871b18a429..8b5560574d4c 100644 --- a/fs/ksmbd/oplock.c +++ b/fs/ksmbd/oplock.c @@ -1694,33 +1694,3 @@ out: read_unlock(&lease_list_lock); return ret_op; } - -int smb2_check_durable_oplock(struct ksmbd_file *fp, - struct lease_ctx_info *lctx, char *name) -{ - struct oplock_info *opinfo = opinfo_get(fp); - int ret = 0; - - if (opinfo && opinfo->is_lease) { - if (!lctx) { - pr_err("open does not include lease\n"); - ret = -EBADF; - goto out; - } - if (memcmp(opinfo->o_lease->lease_key, lctx->lease_key, - SMB2_LEASE_KEY_SIZE)) { - pr_err("invalid lease key\n"); - ret = -EBADF; - goto out; - } - if (name && strcmp(fp->filename, name)) { - pr_err("invalid name reconnect %s\n", name); - ret = -EINVAL; - goto out; - } - } -out: - if (opinfo) - opinfo_put(opinfo); - return ret; -} diff --git a/fs/ksmbd/oplock.h b/fs/ksmbd/oplock.h index 0cf7a2b5bbc0..09753448f779 100644 --- a/fs/ksmbd/oplock.h +++ b/fs/ksmbd/oplock.h @@ -124,6 +124,4 @@ struct oplock_info *lookup_lease_in_table(struct ksmbd_conn *conn, int find_same_lease_key(struct ksmbd_session *sess, struct ksmbd_inode *ci, struct lease_ctx_info *lctx); void destroy_lease_table(struct ksmbd_conn *conn); -int smb2_check_durable_oplock(struct ksmbd_file *fp, - struct lease_ctx_info *lctx, char *name); #endif /* __KSMBD_OPLOCK_H */ diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 3bf6c56c654c..16c803a9d996 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -11,6 +11,7 @@ #include <linux/statfs.h> #include <linux/ethtool.h> #include <linux/falloc.h> +#include <linux/mount.h> #include "glob.h" #include "smbfsctl.h" @@ -2918,7 +2919,6 @@ int smb2_open(struct ksmbd_work *work) goto err_out; } - fp->filename = name; fp->cdoption = req->CreateDisposition; fp->daccess = daccess; fp->saccess = req->ShareAccess; @@ -3270,14 +3270,13 @@ err_out1: if (!rsp->hdr.Status) rsp->hdr.Status = STATUS_UNEXPECTED_IO_ERROR; - if (!fp || !fp->filename) - kfree(name); if (fp) ksmbd_fd_put(work, fp); smb2_set_err_rsp(work); ksmbd_debug(SMB, "Error response: %x\n", rsp->hdr.Status); } + kfree(name); kfree(lc); return 0; @@ -3895,8 +3894,6 @@ int smb2_query_dir(struct ksmbd_work *work) ksmbd_debug(SMB, "Search pattern is %s\n", srch_ptr); } - ksmbd_debug(SMB, "Directory name is %s\n", dir_fp->filename); - if (srch_flag & SMB2_REOPEN || srch_flag & SMB2_RESTART_SCANS) { ksmbd_debug(SMB, "Restart directory scan\n"); generic_file_llseek(dir_fp->filp, 0, SEEK_SET); @@ -4390,9 +4387,9 @@ static int get_file_all_info(struct ksmbd_work *work, return -EACCES; } - filename = convert_to_nt_pathname(fp->filename); - if (!filename) - return -ENOMEM; + filename = convert_to_nt_pathname(work->tcon->share_conf, &fp->filp->f_path); + if (IS_ERR(filename)) + return PTR_ERR(filename); inode = file_inode(fp->filp); generic_fillattr(file_mnt_user_ns(fp->filp), inode, &stat); @@ -4999,15 +4996,17 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, case FS_SECTOR_SIZE_INFORMATION: { struct smb3_fs_ss_info *info; + unsigned int sector_size = + min_t(unsigned int, path.mnt->mnt_sb->s_blocksize, 4096); info = (struct smb3_fs_ss_info *)(rsp->Buffer); - info->LogicalBytesPerSector = cpu_to_le32(stfs.f_bsize); + info->LogicalBytesPerSector = cpu_to_le32(sector_size); info->PhysicalBytesPerSectorForAtomicity = - cpu_to_le32(stfs.f_bsize); - info->PhysicalBytesPerSectorForPerf = cpu_to_le32(stfs.f_bsize); + cpu_to_le32(sector_size); + info->PhysicalBytesPerSectorForPerf = cpu_to_le32(sector_size); info->FSEffPhysicalBytesPerSectorForAtomicity = - cpu_to_le32(stfs.f_bsize); + cpu_to_le32(sector_size); info->Flags = cpu_to_le32(SSINFO_FLAGS_ALIGNED_DEVICE | SSINFO_FLAGS_PARTITION_ALIGNED_ON_DEVICE); info->ByteOffsetForSectorAlignment = 0; @@ -5683,8 +5682,7 @@ static int set_file_allocation_info(struct ksmbd_work *work, size = i_size_read(inode); rc = ksmbd_vfs_truncate(work, fp, alloc_blks * 512); if (rc) { - pr_err("truncate failed! filename : %s, err %d\n", - fp->filename, rc); + pr_err("truncate failed!, err %d\n", rc); return rc; } if (size < alloc_blks * 512) @@ -5714,12 +5712,10 @@ static int set_end_of_file_info(struct ksmbd_work *work, struct ksmbd_file *fp, * truncated range. */ if (inode->i_sb->s_magic != MSDOS_SUPER_MAGIC) { - ksmbd_debug(SMB, "filename : %s truncated to newsize %lld\n", - fp->filename, newsize); + ksmbd_debug(SMB, "truncated to newsize %lld\n", newsize); rc = ksmbd_vfs_truncate(work, fp, newsize); if (rc) { - ksmbd_debug(SMB, "truncate failed! filename : %s err %d\n", - fp->filename, rc); + ksmbd_debug(SMB, "truncate failed!, err %d\n", rc); if (rc != -EAGAIN) rc = -EBADF; return rc; @@ -5765,8 +5761,10 @@ static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp, if (parent_fp) { if (parent_fp->daccess & FILE_DELETE_LE) { pr_err("parent dir is opened with delete access\n"); + ksmbd_fd_put(work, parent_fp); return -ESHARE; } + ksmbd_fd_put(work, parent_fp); } next: return smb2_rename(work, fp, user_ns, rename_info, diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c index 9cebb6ba555b..dcdd07c6efff 100644 --- a/fs/ksmbd/vfs.c +++ b/fs/ksmbd/vfs.c @@ -398,8 +398,7 @@ int ksmbd_vfs_read(struct ksmbd_work *work, struct ksmbd_file *fp, size_t count, nbytes = kernel_read(filp, rbuf, count, pos); if (nbytes < 0) { - pr_err("smb read failed for (%s), err = %zd\n", - fp->filename, nbytes); + pr_err("smb read failed, err = %zd\n", nbytes); return nbytes; } @@ -875,8 +874,7 @@ int ksmbd_vfs_truncate(struct ksmbd_work *work, err = vfs_truncate(&filp->f_path, size); if (err) - pr_err("truncate failed for filename : %s err %d\n", - fp->filename, err); + pr_err("truncate failed, err %d\n", err); return err; } diff --git a/fs/ksmbd/vfs_cache.c b/fs/ksmbd/vfs_cache.c index 29c1db66bd0f..c4d59d2735f0 100644 --- a/fs/ksmbd/vfs_cache.c +++ b/fs/ksmbd/vfs_cache.c @@ -328,7 +328,6 @@ static void __ksmbd_close_fd(struct ksmbd_file_table *ft, struct ksmbd_file *fp) kfree(smb_lock); } - kfree(fp->filename); if (ksmbd_stream_fd(fp)) kfree(fp->stream.name); kmem_cache_free(filp_cache, fp); @@ -497,6 +496,7 @@ struct ksmbd_file *ksmbd_lookup_fd_inode(struct inode *inode) list_for_each_entry(lfp, &ci->m_fp_list, node) { if (inode == file_inode(lfp->filp)) { atomic_dec(&ci->m_count); + lfp = ksmbd_fp_get(lfp); read_unlock(&ci->m_lock); return lfp; } diff --git a/fs/ksmbd/vfs_cache.h b/fs/ksmbd/vfs_cache.h index 36239ce31afd..fcb13413fa8d 100644 --- a/fs/ksmbd/vfs_cache.h +++ b/fs/ksmbd/vfs_cache.h @@ -62,7 +62,6 @@ struct ksmbd_inode { struct ksmbd_file { struct file *filp; - char *filename; u64 persistent_id; u64 volatile_id; diff --git a/fs/namespace.c b/fs/namespace.c index a0a36bfa3aa0..afe2b64b14f1 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4058,10 +4058,22 @@ static int mount_setattr_prepare(struct mount_kattr *kattr, struct mount *mnt) if (err) { struct mount *p; - for (p = mnt; p != m; p = next_mnt(p, mnt)) { + /* + * If we had to call mnt_hold_writers() MNT_WRITE_HOLD will + * be set in @mnt_flags. The loop unsets MNT_WRITE_HOLD for all + * mounts and needs to take care to include the first mount. + */ + for (p = mnt; p; p = next_mnt(p, mnt)) { /* If we had to hold writers unblock them. */ if (p->mnt.mnt_flags & MNT_WRITE_HOLD) mnt_unhold_writers(p); + + /* + * We're done once the first mount we changed got + * MNT_WRITE_HOLD unset. + */ + if (p == m) + break; } } return err; diff --git a/fs/pipe.c b/fs/pipe.c index 9648ac15164a..e140ea150bbb 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -804,7 +804,7 @@ struct pipe_inode_info *alloc_pipe_info(void) if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user()) goto out_revert_acct; - pipe->bufs = kvcalloc(pipe_bufs, sizeof(struct pipe_buffer), + pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer), GFP_KERNEL_ACCOUNT); if (pipe->bufs) { @@ -849,7 +849,7 @@ void free_pipe_info(struct pipe_inode_info *pipe) #endif if (pipe->tmp_page) __free_page(pipe->tmp_page); - kvfree(pipe->bufs); + kfree(pipe->bufs); kfree(pipe); } @@ -1264,7 +1264,8 @@ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) if (nr_slots < n) return -EBUSY; - bufs = kvcalloc(nr_slots, sizeof(*bufs), GFP_KERNEL_ACCOUNT); + bufs = kcalloc(nr_slots, sizeof(*bufs), + GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (unlikely(!bufs)) return -ENOMEM; @@ -1291,7 +1292,7 @@ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) head = n; tail = 0; - kvfree(pipe->bufs); + kfree(pipe->bufs); pipe->bufs = bufs; pipe->ring_size = nr_slots; if (pipe->max_usage > nr_slots) diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 80acb6885cf9..962d32468eb4 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -759,9 +759,14 @@ static void posix_acl_fix_xattr_userns( } void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size) { struct user_namespace *user_ns = current_user_ns(); + + /* Leave ids untouched on non-idmapped mounts. */ + if (no_idmapping(mnt_userns, i_user_ns(inode))) + mnt_userns = &init_user_ns; if ((user_ns == &init_user_ns) && (mnt_userns == &init_user_ns)) return; posix_acl_fix_xattr_userns(&init_user_ns, user_ns, mnt_userns, value, @@ -769,9 +774,14 @@ void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, } void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size) { struct user_namespace *user_ns = current_user_ns(); + + /* Leave ids untouched on non-idmapped mounts. */ + if (no_idmapping(mnt_userns, i_user_ns(inode))) + mnt_userns = &init_user_ns; if ((user_ns == &init_user_ns) && (mnt_userns == &init_user_ns)) return; posix_acl_fix_xattr_userns(user_ns, &init_user_ns, mnt_userns, value, diff --git a/fs/xattr.c b/fs/xattr.c index 5c8c5175b385..998045165916 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -569,7 +569,8 @@ setxattr(struct user_namespace *mnt_userns, struct dentry *d, } if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) - posix_acl_fix_xattr_from_user(mnt_userns, kvalue, size); + posix_acl_fix_xattr_from_user(mnt_userns, d_inode(d), + kvalue, size); } error = vfs_setxattr(mnt_userns, d, kname, kvalue, size, flags); @@ -667,7 +668,8 @@ getxattr(struct user_namespace *mnt_userns, struct dentry *d, if (error > 0) { if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) - posix_acl_fix_xattr_to_user(mnt_userns, kvalue, error); + posix_acl_fix_xattr_to_user(mnt_userns, d_inode(d), + kvalue, error); if (size && copy_to_user(value, kvalue, error)) error = -EFAULT; } else if (error == -ERANGE && size >= XATTR_SIZE_MAX) { diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index e1afb9e503e1..bf4e60871068 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -406,7 +406,7 @@ xfs_buf_alloc_pages( STATIC int _xfs_buf_map_pages( struct xfs_buf *bp, - uint flags) + xfs_buf_flags_t flags) { ASSERT(bp->b_flags & _XBF_PAGES); if (bp->b_page_count == 1) { @@ -868,7 +868,7 @@ xfs_buf_read_uncached( struct xfs_buftarg *target, xfs_daddr_t daddr, size_t numblks, - int flags, + xfs_buf_flags_t flags, struct xfs_buf **bpp, const struct xfs_buf_ops *ops) { @@ -903,7 +903,7 @@ int xfs_buf_get_uncached( struct xfs_buftarg *target, size_t numblks, - int flags, + xfs_buf_flags_t flags, struct xfs_buf **bpp) { int error; diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index edcb6254fa6a..1ee3056ff9cf 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -22,28 +22,28 @@ struct xfs_buf; #define XFS_BUF_DADDR_NULL ((xfs_daddr_t) (-1LL)) -#define XBF_READ (1 << 0) /* buffer intended for reading from device */ -#define XBF_WRITE (1 << 1) /* buffer intended for writing to device */ -#define XBF_READ_AHEAD (1 << 2) /* asynchronous read-ahead */ -#define XBF_NO_IOACCT (1 << 3) /* bypass I/O accounting (non-LRU bufs) */ -#define XBF_ASYNC (1 << 4) /* initiator will not wait for completion */ -#define XBF_DONE (1 << 5) /* all pages in the buffer uptodate */ -#define XBF_STALE (1 << 6) /* buffer has been staled, do not find it */ -#define XBF_WRITE_FAIL (1 << 7) /* async writes have failed on this buffer */ +#define XBF_READ (1u << 0) /* buffer intended for reading from device */ +#define XBF_WRITE (1u << 1) /* buffer intended for writing to device */ +#define XBF_READ_AHEAD (1u << 2) /* asynchronous read-ahead */ +#define XBF_NO_IOACCT (1u << 3) /* bypass I/O accounting (non-LRU bufs) */ +#define XBF_ASYNC (1u << 4) /* initiator will not wait for completion */ +#define XBF_DONE (1u << 5) /* all pages in the buffer uptodate */ +#define XBF_STALE (1u << 6) /* buffer has been staled, do not find it */ +#define XBF_WRITE_FAIL (1u << 7) /* async writes have failed on this buffer */ /* buffer type flags for write callbacks */ -#define _XBF_INODES (1 << 16)/* inode buffer */ -#define _XBF_DQUOTS (1 << 17)/* dquot buffer */ -#define _XBF_LOGRECOVERY (1 << 18)/* log recovery buffer */ +#define _XBF_INODES (1u << 16)/* inode buffer */ +#define _XBF_DQUOTS (1u << 17)/* dquot buffer */ +#define _XBF_LOGRECOVERY (1u << 18)/* log recovery buffer */ /* flags used only internally */ -#define _XBF_PAGES (1 << 20)/* backed by refcounted pages */ -#define _XBF_KMEM (1 << 21)/* backed by heap memory */ -#define _XBF_DELWRI_Q (1 << 22)/* buffer on a delwri queue */ +#define _XBF_PAGES (1u << 20)/* backed by refcounted pages */ +#define _XBF_KMEM (1u << 21)/* backed by heap memory */ +#define _XBF_DELWRI_Q (1u << 22)/* buffer on a delwri queue */ /* flags used only as arguments to access routines */ -#define XBF_TRYLOCK (1 << 30)/* lock requested, but do not wait */ -#define XBF_UNMAPPED (1 << 31)/* do not map the buffer */ +#define XBF_TRYLOCK (1u << 30)/* lock requested, but do not wait */ +#define XBF_UNMAPPED (1u << 31)/* do not map the buffer */ typedef unsigned int xfs_buf_flags_t; @@ -58,7 +58,7 @@ typedef unsigned int xfs_buf_flags_t; { XBF_WRITE_FAIL, "WRITE_FAIL" }, \ { _XBF_INODES, "INODES" }, \ { _XBF_DQUOTS, "DQUOTS" }, \ - { _XBF_LOGRECOVERY, "LOG_RECOVERY" }, \ + { _XBF_LOGRECOVERY, "LOG_RECOVERY" }, \ { _XBF_PAGES, "PAGES" }, \ { _XBF_KMEM, "KMEM" }, \ { _XBF_DELWRI_Q, "DELWRI_Q" }, \ @@ -247,11 +247,11 @@ xfs_buf_readahead( return xfs_buf_readahead_map(target, &map, 1, ops); } -int xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks, int flags, - struct xfs_buf **bpp); +int xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks, + xfs_buf_flags_t flags, struct xfs_buf **bpp); int xfs_buf_read_uncached(struct xfs_buftarg *target, xfs_daddr_t daddr, - size_t numblks, int flags, struct xfs_buf **bpp, - const struct xfs_buf_ops *ops); + size_t numblks, xfs_buf_flags_t flags, struct xfs_buf **bpp, + const struct xfs_buf_ops *ops); int _xfs_buf_read(struct xfs_buf *bp, xfs_buf_flags_t flags); void xfs_buf_hold(struct xfs_buf *bp); diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 9de6205fe134..39ae53efb3ab 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2594,14 +2594,13 @@ xfs_ifree_cluster( } /* - * This is called to return an inode to the inode free list. - * The inode should already be truncated to 0 length and have - * no pages associated with it. This routine also assumes that - * the inode is already a part of the transaction. + * This is called to return an inode to the inode free list. The inode should + * already be truncated to 0 length and have no pages associated with it. This + * routine also assumes that the inode is already a part of the transaction. * - * The on-disk copy of the inode will have been added to the list - * of unlinked inodes in the AGI. We need to remove the inode from - * that list atomically with respect to freeing it here. + * The on-disk copy of the inode will have been added to the list of unlinked + * inodes in the AGI. We need to remove the inode from that list atomically with + * respect to freeing it here. */ int xfs_ifree( @@ -2623,13 +2622,16 @@ xfs_ifree( pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); /* - * Pull the on-disk inode from the AGI unlinked list. + * Free the inode first so that we guarantee that the AGI lock is going + * to be taken before we remove the inode from the unlinked list. This + * makes the AGI lock -> unlinked list modification order the same as + * used in O_TMPFILE creation. */ - error = xfs_iunlink_remove(tp, pag, ip); + error = xfs_difree(tp, pag, ip->i_ino, &xic); if (error) - goto out; + return error; - error = xfs_difree(tp, pag, ip->i_ino, &xic); + error = xfs_iunlink_remove(tp, pag, ip); if (error) goto out; diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index de177842b951..0c82673238f4 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -175,7 +175,7 @@ xfs_trans_get_buf( struct xfs_buftarg *target, xfs_daddr_t blkno, int numblks, - uint flags, + xfs_buf_flags_t flags, struct xfs_buf **bpp) { DEFINE_SINGLE_BUF_MAP(map, blkno, numblks); diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 3614c7834007..e20e7c841489 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -35,6 +35,17 @@ static inline int zonefs_zone_mgmt(struct inode *inode, lockdep_assert_held(&zi->i_truncate_mutex); + /* + * With ZNS drives, closing an explicitly open zone that has not been + * written will change the zone state to "closed", that is, the zone + * will remain active. Since this can then cause failure of explicit + * open operation on other zones if the drive active zone resources + * are exceeded, make sure that the zone does not remain active by + * resetting it. + */ + if (op == REQ_OP_ZONE_CLOSE && !zi->i_wpoffset) + op = REQ_OP_ZONE_RESET; + trace_zonefs_zone_mgmt(inode, op); ret = blkdev_zone_mgmt(inode->i_sb->s_bdev, op, zi->i_zsector, zi->i_zone_size >> SECTOR_SHIFT, GFP_NOFS); @@ -1142,6 +1153,7 @@ static struct inode *zonefs_alloc_inode(struct super_block *sb) inode_init_once(&zi->i_vnode); mutex_init(&zi->i_truncate_mutex); zi->i_wr_refcnt = 0; + zi->i_flags = 0; return &zi->i_vnode; } @@ -1293,12 +1305,13 @@ static void zonefs_init_dir_inode(struct inode *parent, struct inode *inode, inc_nlink(parent); } -static void zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone, - enum zonefs_ztype type) +static int zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone, + enum zonefs_ztype type) { struct super_block *sb = inode->i_sb; struct zonefs_sb_info *sbi = ZONEFS_SB(sb); struct zonefs_inode_info *zi = ZONEFS_I(inode); + int ret = 0; inode->i_ino = zone->start >> sbi->s_zone_sectors_shift; inode->i_mode = S_IFREG | sbi->s_perm; @@ -1323,6 +1336,22 @@ static void zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone, sb->s_maxbytes = max(zi->i_max_size, sb->s_maxbytes); sbi->s_blocks += zi->i_max_size >> sb->s_blocksize_bits; sbi->s_used_blocks += zi->i_wpoffset >> sb->s_blocksize_bits; + + /* + * For sequential zones, make sure that any open zone is closed first + * to ensure that the initial number of open zones is 0, in sync with + * the open zone accounting done when the mount option + * ZONEFS_MNTOPT_EXPLICIT_OPEN is used. + */ + if (type == ZONEFS_ZTYPE_SEQ && + (zone->cond == BLK_ZONE_COND_IMP_OPEN || + zone->cond == BLK_ZONE_COND_EXP_OPEN)) { + mutex_lock(&zi->i_truncate_mutex); + ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_CLOSE); + mutex_unlock(&zi->i_truncate_mutex); + } + + return ret; } static struct dentry *zonefs_create_inode(struct dentry *parent, @@ -1332,6 +1361,7 @@ static struct dentry *zonefs_create_inode(struct dentry *parent, struct inode *dir = d_inode(parent); struct dentry *dentry; struct inode *inode; + int ret; dentry = d_alloc_name(parent, name); if (!dentry) @@ -1342,10 +1372,16 @@ static struct dentry *zonefs_create_inode(struct dentry *parent, goto dput; inode->i_ctime = inode->i_mtime = inode->i_atime = dir->i_ctime; - if (zone) - zonefs_init_file_inode(inode, zone, type); - else + if (zone) { + ret = zonefs_init_file_inode(inode, zone, type); + if (ret) { + iput(inode); + goto dput; + } + } else { zonefs_init_dir_inode(dir, inode, type); + } + d_add(dentry, inode); dir->i_size++; diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index edb0e2a602a8..ba1f860af38b 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -21,6 +21,12 @@ #include <linux/panic.h> #include <linux/printk.h> +struct warn_args; +struct pt_regs; + +void __warn(const char *file, int line, void *caller, unsigned taint, + struct pt_regs *regs, struct warn_args *args); + #ifdef CONFIG_BUG #ifdef CONFIG_GENERIC_BUG @@ -110,11 +116,6 @@ extern __printf(1, 2) void __warn_printk(const char *fmt, ...); #endif /* used internally by panic.c */ -struct warn_args; -struct pt_regs; - -void __warn(const char *file, int line, void *caller, unsigned taint, - struct pt_regs *regs, struct warn_args *args); #ifndef WARN_ON #define WARN_ON(condition) ({ \ diff --git a/include/dt-bindings/clock/microchip,mpfs-clock.h b/include/dt-bindings/clock/microchip,mpfs-clock.h index 73f2a9324857..4048669bf756 100644 --- a/include/dt-bindings/clock/microchip,mpfs-clock.h +++ b/include/dt-bindings/clock/microchip,mpfs-clock.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ /* * Daire McNamara,<daire.mcnamara@microchip.com> - * Copyright (C) 2020 Microchip Technology Inc. All rights reserved. + * Copyright (C) 2020-2022 Microchip Technology Inc. All rights reserved. */ #ifndef _DT_BINDINGS_CLK_MICROCHIP_MPFS_H_ @@ -42,4 +42,7 @@ #define CLK_ATHENA 31 #define CLK_CFM 32 +#define CLK_RTCREF 33 +#define CLK_MSSPLL 34 + #endif /* _DT_BINDINGS_CLK_MICROCHIP_MPFS_H_ */ diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index 51c19381108c..cd6d8f260eab 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -76,8 +76,6 @@ int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_timer_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); -bool kvm_timer_is_pending(struct kvm_vcpu *vcpu); - u64 kvm_phys_timer_read(void); void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu); diff --git a/include/kvm/arm_hypercalls.h b/include/kvm/arm_hypercalls.h index 0e2509d27910..1188f116cf4e 100644 --- a/include/kvm/arm_hypercalls.h +++ b/include/kvm/arm_hypercalls.h @@ -40,4 +40,12 @@ static inline void smccc_set_retval(struct kvm_vcpu *vcpu, vcpu_set_reg(vcpu, 3, a3); } +struct kvm_one_reg; + +void kvm_arm_init_hypercalls(struct kvm *kvm); +int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu); +int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); +int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); +int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); + #endif diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h index 68b96c3826c3..6e55b9283789 100644 --- a/include/kvm/arm_psci.h +++ b/include/kvm/arm_psci.h @@ -39,11 +39,4 @@ static inline int kvm_psci_version(struct kvm_vcpu *vcpu) int kvm_psci_call(struct kvm_vcpu *vcpu); -struct kvm_one_reg; - -int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu); -int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); -int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); -int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); - #endif /* __KVM_ARM_PSCI_H__ */ diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 9cf51e41e697..54dc2f9a2d56 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -167,7 +167,7 @@ static inline int suspend_disable_secondary_cpus(void) { return 0; } static inline void suspend_enable_secondary_cpus(void) { } #endif /* !CONFIG_PM_SLEEP_SMP */ -void cpu_startup_entry(enum cpuhp_state state); +void __noreturn cpu_startup_entry(enum cpuhp_state state); void cpu_idle_poll_ctrl(bool enable); diff --git a/include/linux/dma-buf-map.h b/include/linux/dma-buf-map.h deleted file mode 100644 index 19fa0b5ae5ec..000000000000 --- a/include/linux/dma-buf-map.h +++ /dev/null @@ -1,266 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Pointer to dma-buf-mapped memory, plus helpers. - */ - -#ifndef __DMA_BUF_MAP_H__ -#define __DMA_BUF_MAP_H__ - -#include <linux/io.h> -#include <linux/string.h> - -/** - * DOC: overview - * - * Calling dma-buf's vmap operation returns a pointer to the buffer's memory. - * Depending on the location of the buffer, users may have to access it with - * I/O operations or memory load/store operations. For example, copying to - * system memory could be done with memcpy(), copying to I/O memory would be - * done with memcpy_toio(). - * - * .. code-block:: c - * - * void *vaddr = ...; // pointer to system memory - * memcpy(vaddr, src, len); - * - * void *vaddr_iomem = ...; // pointer to I/O memory - * memcpy_toio(vaddr, _iomem, src, len); - * - * When using dma-buf's vmap operation, the returned pointer is encoded as - * :c:type:`struct dma_buf_map <dma_buf_map>`. - * :c:type:`struct dma_buf_map <dma_buf_map>` stores the buffer's address in - * system or I/O memory and a flag that signals the required method of - * accessing the buffer. Use the returned instance and the helper functions - * to access the buffer's memory in the correct way. - * - * The type :c:type:`struct dma_buf_map <dma_buf_map>` and its helpers are - * actually independent from the dma-buf infrastructure. When sharing buffers - * among devices, drivers have to know the location of the memory to access - * the buffers in a safe way. :c:type:`struct dma_buf_map <dma_buf_map>` - * solves this problem for dma-buf and its users. If other drivers or - * sub-systems require similar functionality, the type could be generalized - * and moved to a more prominent header file. - * - * Open-coding access to :c:type:`struct dma_buf_map <dma_buf_map>` is - * considered bad style. Rather then accessing its fields directly, use one - * of the provided helper functions, or implement your own. For example, - * instances of :c:type:`struct dma_buf_map <dma_buf_map>` can be initialized - * statically with DMA_BUF_MAP_INIT_VADDR(), or at runtime with - * dma_buf_map_set_vaddr(). These helpers will set an address in system memory. - * - * .. code-block:: c - * - * struct dma_buf_map map = DMA_BUF_MAP_INIT_VADDR(0xdeadbeaf); - * - * dma_buf_map_set_vaddr(&map, 0xdeadbeaf); - * - * To set an address in I/O memory, use dma_buf_map_set_vaddr_iomem(). - * - * .. code-block:: c - * - * dma_buf_map_set_vaddr_iomem(&map, 0xdeadbeaf); - * - * Instances of struct dma_buf_map do not have to be cleaned up, but - * can be cleared to NULL with dma_buf_map_clear(). Cleared mappings - * always refer to system memory. - * - * .. code-block:: c - * - * dma_buf_map_clear(&map); - * - * Test if a mapping is valid with either dma_buf_map_is_set() or - * dma_buf_map_is_null(). - * - * .. code-block:: c - * - * if (dma_buf_map_is_set(&map) != dma_buf_map_is_null(&map)) - * // always true - * - * Instances of :c:type:`struct dma_buf_map <dma_buf_map>` can be compared - * for equality with dma_buf_map_is_equal(). Mappings the point to different - * memory spaces, system or I/O, are never equal. That's even true if both - * spaces are located in the same address space, both mappings contain the - * same address value, or both mappings refer to NULL. - * - * .. code-block:: c - * - * struct dma_buf_map sys_map; // refers to system memory - * struct dma_buf_map io_map; // refers to I/O memory - * - * if (dma_buf_map_is_equal(&sys_map, &io_map)) - * // always false - * - * A set up instance of struct dma_buf_map can be used to access or manipulate - * the buffer memory. Depending on the location of the memory, the provided - * helpers will pick the correct operations. Data can be copied into the memory - * with dma_buf_map_memcpy_to(). The address can be manipulated with - * dma_buf_map_incr(). - * - * .. code-block:: c - * - * const void *src = ...; // source buffer - * size_t len = ...; // length of src - * - * dma_buf_map_memcpy_to(&map, src, len); - * dma_buf_map_incr(&map, len); // go to first byte after the memcpy - */ - -/** - * struct dma_buf_map - Pointer to vmap'ed dma-buf memory. - * @vaddr_iomem: The buffer's address if in I/O memory - * @vaddr: The buffer's address if in system memory - * @is_iomem: True if the dma-buf memory is located in I/O - * memory, or false otherwise. - */ -struct dma_buf_map { - union { - void __iomem *vaddr_iomem; - void *vaddr; - }; - bool is_iomem; -}; - -/** - * DMA_BUF_MAP_INIT_VADDR - Initializes struct dma_buf_map to an address in system memory - * @vaddr_: A system-memory address - */ -#define DMA_BUF_MAP_INIT_VADDR(vaddr_) \ - { \ - .vaddr = (vaddr_), \ - .is_iomem = false, \ - } - -/** - * dma_buf_map_set_vaddr - Sets a dma-buf mapping structure to an address in system memory - * @map: The dma-buf mapping structure - * @vaddr: A system-memory address - * - * Sets the address and clears the I/O-memory flag. - */ -static inline void dma_buf_map_set_vaddr(struct dma_buf_map *map, void *vaddr) -{ - map->vaddr = vaddr; - map->is_iomem = false; -} - -/** - * dma_buf_map_set_vaddr_iomem - Sets a dma-buf mapping structure to an address in I/O memory - * @map: The dma-buf mapping structure - * @vaddr_iomem: An I/O-memory address - * - * Sets the address and the I/O-memory flag. - */ -static inline void dma_buf_map_set_vaddr_iomem(struct dma_buf_map *map, - void __iomem *vaddr_iomem) -{ - map->vaddr_iomem = vaddr_iomem; - map->is_iomem = true; -} - -/** - * dma_buf_map_is_equal - Compares two dma-buf mapping structures for equality - * @lhs: The dma-buf mapping structure - * @rhs: A dma-buf mapping structure to compare with - * - * Two dma-buf mapping structures are equal if they both refer to the same type of memory - * and to the same address within that memory. - * - * Returns: - * True is both structures are equal, or false otherwise. - */ -static inline bool dma_buf_map_is_equal(const struct dma_buf_map *lhs, - const struct dma_buf_map *rhs) -{ - if (lhs->is_iomem != rhs->is_iomem) - return false; - else if (lhs->is_iomem) - return lhs->vaddr_iomem == rhs->vaddr_iomem; - else - return lhs->vaddr == rhs->vaddr; -} - -/** - * dma_buf_map_is_null - Tests for a dma-buf mapping to be NULL - * @map: The dma-buf mapping structure - * - * Depending on the state of struct dma_buf_map.is_iomem, tests if the - * mapping is NULL. - * - * Returns: - * True if the mapping is NULL, or false otherwise. - */ -static inline bool dma_buf_map_is_null(const struct dma_buf_map *map) -{ - if (map->is_iomem) - return !map->vaddr_iomem; - return !map->vaddr; -} - -/** - * dma_buf_map_is_set - Tests is the dma-buf mapping has been set - * @map: The dma-buf mapping structure - * - * Depending on the state of struct dma_buf_map.is_iomem, tests if the - * mapping has been set. - * - * Returns: - * True if the mapping is been set, or false otherwise. - */ -static inline bool dma_buf_map_is_set(const struct dma_buf_map *map) -{ - return !dma_buf_map_is_null(map); -} - -/** - * dma_buf_map_clear - Clears a dma-buf mapping structure - * @map: The dma-buf mapping structure - * - * Clears all fields to zero; including struct dma_buf_map.is_iomem. So - * mapping structures that were set to point to I/O memory are reset for - * system memory. Pointers are cleared to NULL. This is the default. - */ -static inline void dma_buf_map_clear(struct dma_buf_map *map) -{ - if (map->is_iomem) { - map->vaddr_iomem = NULL; - map->is_iomem = false; - } else { - map->vaddr = NULL; - } -} - -/** - * dma_buf_map_memcpy_to - Memcpy into dma-buf mapping - * @dst: The dma-buf mapping structure - * @src: The source buffer - * @len: The number of byte in src - * - * Copies data into a dma-buf mapping. The source buffer is in system - * memory. Depending on the buffer's location, the helper picks the correct - * method of accessing the memory. - */ -static inline void dma_buf_map_memcpy_to(struct dma_buf_map *dst, const void *src, size_t len) -{ - if (dst->is_iomem) - memcpy_toio(dst->vaddr_iomem, src, len); - else - memcpy(dst->vaddr, src, len); -} - -/** - * dma_buf_map_incr - Increments the address stored in a dma-buf mapping - * @map: The dma-buf mapping structure - * @incr: The number of bytes to increment - * - * Increments the address stored in a dma-buf mapping. Depending on the - * buffer's location, the correct value will be updated. - */ -static inline void dma_buf_map_incr(struct dma_buf_map *map, size_t incr) -{ - if (map->is_iomem) - map->vaddr_iomem += incr; - else - map->vaddr += incr; -} - -#endif /* __DMA_BUF_MAP_H__ */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 53c1b6082a4c..ac2a1d758a80 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -169,6 +169,7 @@ long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); bool isolate_huge_page(struct page *page, struct list_head *list); int get_hwpoison_huge_page(struct page *page, bool *hugetlb); +int get_huge_page_for_hwpoison(unsigned long pfn, int flags); void putback_active_hugepage(struct page *page); void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason); void free_huge_page(struct page *page); @@ -378,6 +379,11 @@ static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb) return 0; } +static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags) +{ + return 0; +} + static inline void putback_active_hugepage(struct page *page) { } diff --git a/include/linux/kernel.h b/include/linux/kernel.h index a890428bcc1a..fe6efb24d151 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -285,7 +285,7 @@ static inline char *hex_byte_pack_upper(char *buf, u8 byte) return buf; } -extern int hex_to_bin(char ch); +extern int hex_to_bin(unsigned char ch); extern int __must_check hex2bin(u8 *dst, const char *src, size_t count); extern char *bin2hex(char *dst, const void *src, size_t count); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3f9b22c4983a..34eed5f85ed6 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -315,7 +315,10 @@ struct kvm_vcpu { int cpu; int vcpu_id; /* id given by userspace at creation */ int vcpu_idx; /* index in kvm->vcpus array */ - int srcu_idx; + int ____srcu_idx; /* Don't use this directly. You've been warned. */ +#ifdef CONFIG_PROVE_RCU + int srcu_depth; +#endif int mode; u64 requests; unsigned long guest_debug; @@ -840,6 +843,25 @@ static inline void kvm_vm_bugged(struct kvm *kvm) unlikely(__ret); \ }) +static inline void kvm_vcpu_srcu_read_lock(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_PROVE_RCU + WARN_ONCE(vcpu->srcu_depth++, + "KVM: Illegal vCPU srcu_idx LOCK, depth=%d", vcpu->srcu_depth - 1); +#endif + vcpu->____srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); +} + +static inline void kvm_vcpu_srcu_read_unlock(struct kvm_vcpu *vcpu) +{ + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->____srcu_idx); + +#ifdef CONFIG_PROVE_RCU + WARN_ONCE(--vcpu->srcu_depth, + "KVM: Illegal vCPU srcu_idx UNLOCK, depth=%d", vcpu->srcu_depth); +#endif +} + static inline bool kvm_dirty_log_manual_protect_and_init_set(struct kvm *kvm) { return !!(kvm->manual_dirty_log_protect & KVM_DIRTY_LOG_INITIALLY_SET); @@ -2197,6 +2219,8 @@ static inline long kvm_arch_vcpu_async_ioctl(struct file *filp, void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, unsigned long start, unsigned long end); +void kvm_arch_guest_memory_reclaimed(struct kvm *kvm); + #ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu); #else diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index a68dce3873fc..89b14729d59f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1012,6 +1012,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, } void mem_cgroup_flush_stats(void); +void mem_cgroup_flush_stats_delayed(void); void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); @@ -1455,6 +1456,10 @@ static inline void mem_cgroup_flush_stats(void) { } +static inline void mem_cgroup_flush_stats_delayed(void) +{ +} + static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { diff --git a/include/linux/mm.h b/include/linux/mm.h index e34edb775334..9f44254af8ce 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3197,6 +3197,14 @@ extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); +#ifdef CONFIG_MEMORY_FAILURE +extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags); +#else +static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags) +{ + return 0; +} +#endif #ifndef arch_memory_failure static inline int arch_memory_failure(unsigned long pfn, int flags) diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 151607e9d64a..955aee14b0f7 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -389,10 +389,8 @@ struct mtd_info { /* List of partitions attached to this MTD device */ struct list_head partitions; - union { - struct mtd_part part; - struct mtd_master master; - }; + struct mtd_part part; + struct mtd_master master; }; static inline struct mtd_info *mtd_get_master(struct mtd_info *mtd) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 59e27a2b7bf0..b1fbe21650bb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -199,10 +199,10 @@ struct net_device_stats { * Try to fit them in a single cache line, for dev_get_stats() sake. */ struct net_device_core_stats { - local_t rx_dropped; - local_t tx_dropped; - local_t rx_nohandler; -} __aligned(4 * sizeof(local_t)); + unsigned long rx_dropped; + unsigned long tx_dropped; + unsigned long rx_nohandler; +} __aligned(4 * sizeof(unsigned long)); #include <linux/cache.h> #include <linux/skbuff.h> @@ -3843,15 +3843,15 @@ static __always_inline bool __is_skb_forwardable(const struct net_device *dev, return false; } -struct net_device_core_stats *netdev_core_stats_alloc(struct net_device *dev); +struct net_device_core_stats __percpu *netdev_core_stats_alloc(struct net_device *dev); -static inline struct net_device_core_stats *dev_core_stats(struct net_device *dev) +static inline struct net_device_core_stats __percpu *dev_core_stats(struct net_device *dev) { /* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */ struct net_device_core_stats __percpu *p = READ_ONCE(dev->core_stats); if (likely(p)) - return this_cpu_ptr(p); + return p; return netdev_core_stats_alloc(dev); } @@ -3859,14 +3859,11 @@ static inline struct net_device_core_stats *dev_core_stats(struct net_device *de #define DEV_CORE_STATS_INC(FIELD) \ static inline void dev_core_stats_##FIELD##_inc(struct net_device *dev) \ { \ - struct net_device_core_stats *p; \ + struct net_device_core_stats __percpu *p; \ \ - preempt_disable(); \ p = dev_core_stats(dev); \ - \ if (p) \ - local_inc(&p->FIELD); \ - preempt_enable(); \ + this_cpu_inc(p->FIELD); \ } DEV_CORE_STATS_INC(rx_dropped) DEV_CORE_STATS_INC(tx_dropped) diff --git a/include/linux/posix_acl_xattr.h b/include/linux/posix_acl_xattr.h index 060e8d203181..1766e1de6956 100644 --- a/include/linux/posix_acl_xattr.h +++ b/include/linux/posix_acl_xattr.h @@ -34,15 +34,19 @@ posix_acl_xattr_count(size_t size) #ifdef CONFIG_FS_POSIX_ACL void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size); void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size); #else static inline void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size) { } static inline void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size) { } diff --git a/include/linux/sched.h b/include/linux/sched.h index d5e3c00b74e1..a8911b1f35aa 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1443,6 +1443,7 @@ struct task_struct { int pagefault_disabled; #ifdef CONFIG_MMU struct task_struct *oom_reaper_list; + struct timer_list oom_reaper_timer; #endif #ifdef CONFIG_VMAP_STACK struct vm_struct *stack_vm_area; diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index a80356e9dc69..1ad1f4bfa025 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -136,6 +136,14 @@ static inline void mm_update_next_owner(struct mm_struct *mm) #endif /* CONFIG_MEMCG */ #ifdef CONFIG_MMU +#ifndef arch_get_mmap_end +#define arch_get_mmap_end(addr) (TASK_SIZE) +#endif + +#ifndef arch_get_mmap_base +#define arch_get_mmap_base(addr, base) (base) +#endif + extern void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack); extern unsigned long diff --git a/include/linux/usb/pd_bdo.h b/include/linux/usb/pd_bdo.h index 033fe3e17141..7c25b88d79f9 100644 --- a/include/linux/usb/pd_bdo.h +++ b/include/linux/usb/pd_bdo.h @@ -15,7 +15,7 @@ #define BDO_MODE_CARRIER2 (5 << 28) #define BDO_MODE_CARRIER3 (6 << 28) #define BDO_MODE_EYE (7 << 28) -#define BDO_MODE_TESTDATA (8 << 28) +#define BDO_MODE_TESTDATA (8U << 28) #define BDO_MODE_MASK(mode) ((mode) & 0xf0000000) diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 3b1df7da402d..b159c2789961 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -26,7 +26,7 @@ struct notifier_block; /* in notifier.h */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ #define VM_FLUSH_RESET_PERMS 0x00000100 /* reset direct map and flush TLB on unmap, can't be freed in atomic context */ #define VM_MAP_PUT_PAGES 0x00000200 /* put pages and free array in vfree */ -#define VM_NO_HUGE_VMAP 0x00000400 /* force PAGE_SIZE pte mapping */ +#define VM_ALLOW_HUGE_VMAP 0x00000400 /* Allow for huge pages on archs with HAVE_ARCH_HUGE_VMALLOC */ #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ !defined(CONFIG_KASAN_VMALLOC) @@ -153,7 +153,7 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align, const void *caller) __alloc_size(1); void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) __alloc_size(1); -void *vmalloc_no_huge(unsigned long size) __alloc_size(1); +void *vmalloc_huge(unsigned long size, gfp_t gfp_mask) __alloc_size(1); extern void *__vmalloc_array(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); extern void *vmalloc_array(size_t n, size_t size) __alloc_size(1, 2); diff --git a/include/memory/renesas-rpc-if.h b/include/memory/renesas-rpc-if.h index 7c93f5177532..9c0ad64b8d29 100644 --- a/include/memory/renesas-rpc-if.h +++ b/include/memory/renesas-rpc-if.h @@ -72,6 +72,7 @@ struct rpcif { enum rpcif_type type; enum rpcif_data_dir dir; u8 bus_size; + u8 xfer_size; void *buffer; u32 xferlen; u32 smcr; diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 5cb095b09a94..69ef31cea582 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -578,6 +578,7 @@ enum { #define HCI_ERROR_CONNECTION_TIMEOUT 0x08 #define HCI_ERROR_REJ_LIMITED_RESOURCES 0x0d #define HCI_ERROR_REJ_BAD_ADDR 0x0f +#define HCI_ERROR_INVALID_PARAMETERS 0x12 #define HCI_ERROR_REMOTE_USER_TERM 0x13 #define HCI_ERROR_REMOTE_LOW_RESOURCES 0x14 #define HCI_ERROR_REMOTE_POWER_OFF 0x15 diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index d5377740e99c..8abd08245326 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1156,7 +1156,7 @@ int hci_conn_switch_role(struct hci_conn *conn, __u8 role); void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active); -void hci_le_conn_failed(struct hci_conn *conn, u8 status); +void hci_conn_failed(struct hci_conn *conn, u8 status); /* * hci_conn_get() and hci_conn_put() are used to control the life-time of an diff --git a/include/net/esp.h b/include/net/esp.h index 90cd02ff77ef..9c5637d41d95 100644 --- a/include/net/esp.h +++ b/include/net/esp.h @@ -4,8 +4,6 @@ #include <linux/skbuff.h> -#define ESP_SKB_FRAG_MAXSIZE (PAGE_SIZE << SKB_FRAG_PAGE_ORDER) - struct ip_esp_hdr; static inline struct ip_esp_hdr *ip_esp_hdr(const struct sk_buff *skb) diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index a38c4f1e4e5c..74b369bddf49 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -58,7 +58,7 @@ struct ip6_tnl { /* These fields used only by GRE */ __u32 i_seqno; /* The last seen seqno */ - __u32 o_seqno; /* The last output seqno */ + atomic_t o_seqno; /* The last output seqno */ int hlen; /* tun_hlen + encap_hlen */ int tun_hlen; /* Precalculated header length */ int encap_hlen; /* Encap header length (FOU,GUE) */ diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 0219fe907b26..c24fa934221d 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -116,7 +116,7 @@ struct ip_tunnel { /* These four fields used only by GRE */ u32 i_seqno; /* The last seen seqno */ - u32 o_seqno; /* The last output seqno */ + atomic_t o_seqno; /* The last output seqno */ int tun_hlen; /* Precalculated header length */ /* These four fields used only by ERSPAN */ @@ -243,11 +243,18 @@ static inline __be32 tunnel_id_to_key32(__be64 tun_id) static inline void ip_tunnel_init_flow(struct flowi4 *fl4, int proto, __be32 daddr, __be32 saddr, - __be32 key, __u8 tos, int oif, + __be32 key, __u8 tos, + struct net *net, int oif, __u32 mark, __u32 tun_inner_hash) { memset(fl4, 0, sizeof(*fl4)); - fl4->flowi4_oif = oif; + + if (oif) { + fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index_rcu(net, oif); + /* Legacy VRF/l3mdev use case */ + fl4->flowi4_oif = fl4->flowi4_l3mdev ? 0 : oif; + } + fl4->daddr = daddr; fl4->saddr = saddr; fl4->flowi4_tos = tos; diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 3d83b64471d3..b4af4837d80b 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -75,8 +75,8 @@ struct netns_ipv6 { struct list_head fib6_walkers; rwlock_t fib6_walker_lock; spinlock_t fib6_gc_lock; - unsigned int ip6_rt_gc_expire; - unsigned long ip6_rt_last_gc; + atomic_t ip6_rt_gc_expire; + unsigned long ip6_rt_last_gc; unsigned char flowlabel_has_excl; #ifdef CONFIG_IPV6_MULTIPLE_TABLES bool fib6_has_custom_rules; diff --git a/include/net/tcp.h b/include/net/tcp.h index 70ca4a5e330a..cc1295037533 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -480,6 +480,7 @@ int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, u32 cookie); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, + const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb); #ifdef CONFIG_SYN_COOKIES @@ -620,6 +621,7 @@ void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); void tcp_reset(struct sock *sk, struct sk_buff *skb); void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb); void tcp_fin(struct sock *sk); +void tcp_check_space(struct sock *sk); /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); @@ -1042,6 +1044,7 @@ struct rate_sample { int losses; /* number of packets marked lost upon ACK */ u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */ u32 prior_in_flight; /* in flight before this ACK */ + u32 last_end_seq; /* end_seq of most recently ACKed packet */ bool is_app_limited; /* is sample from packet with bubble in pipe? */ bool is_retrans; /* is sample from retransmission? */ bool is_ack_delayed; /* is this (likely) a delayed ACK? */ @@ -1164,6 +1167,11 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, bool is_sack_reneg, struct rate_sample *rs); void tcp_rate_check_app_limited(struct sock *sk); +static inline bool tcp_skb_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) +{ + return t1 > t2 || (t1 == t2 && after(seq1, seq2)); +} + /* These functions determine how the current flow behaves in respect of SACK * handling. SACK is negotiated with the peer, and therefore it can vary * between different flows. diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 5554ee75e7da..647722e847b4 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -97,6 +97,7 @@ int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, u16 queue_id, u16 flags); int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem, struct net_device *dev, u16 queue_id); +int xp_alloc_tx_descs(struct xsk_buff_pool *pool, struct xdp_sock *xs); void xp_destroy(struct xsk_buff_pool *pool); void xp_get_pool(struct xsk_buff_pool *pool); bool xp_put_pool(struct xsk_buff_pool *pool); diff --git a/include/sound/soc-component.h b/include/sound/soc-component.h index a52080407b98..766dc6f009c0 100644 --- a/include/sound/soc-component.h +++ b/include/sound/soc-component.h @@ -179,6 +179,10 @@ struct snd_soc_component_driver { struct snd_pcm_hw_params *params); bool use_dai_pcm_id; /* use DAI link PCM ID as PCM device number */ int be_pcm_base; /* base device ID for all BE PCMs */ + +#ifdef CONFIG_DEBUG_FS + const char *debugfs_prefix; +#endif }; struct snd_soc_component { diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 787c657bfae8..429bec8dd70a 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -42,7 +42,7 @@ typedef __s64 Elf64_Sxword; /* ARM MTE memory tag segment type */ -#define PT_ARM_MEMTAG_MTE (PT_LOPROC + 0x1) +#define PT_AARCH64_MEMTAG_MTE (PT_LOPROC + 0x2) /* * Extended Numbering @@ -431,6 +431,8 @@ typedef struct elf64_shdr { #define NT_ARM_PACG_KEYS 0x408 /* ARM pointer authentication generic key */ #define NT_ARM_TAGGED_ADDR_CTRL 0x409 /* arm64 tagged address control (prctl()) */ #define NT_ARM_PAC_ENABLED_KEYS 0x40a /* arm64 ptr auth enabled keys (prctl()) */ +#define NT_ARM_SSVE 0x40b /* ARM Streaming SVE registers */ +#define NT_ARM_ZA 0x40c /* ARM SME ZA registers */ #define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ #define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ diff --git a/include/uapi/linux/fb.h b/include/uapi/linux/fb.h index 4c14e8be7267..3a49913d006c 100644 --- a/include/uapi/linux/fb.h +++ b/include/uapi/linux/fb.h @@ -182,7 +182,7 @@ struct fb_fix_screeninfo { * * For pseudocolor: offset and length should be the same for all color * components. Offset specifies the position of the least significant bit - * of the pallette index in a pixel value. Length indicates the number + * of the palette index in a pixel value. Length indicates the number * of available palette entries (i.e. # of entries = 1 << length). */ struct fb_bitfield { diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 7989d9483ea7..dff8e7f17074 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -662,6 +662,27 @@ /* Select an area of screen to be copied */ #define KEY_SELECTIVE_SCREENSHOT 0x27a +/* Move the focus to the next or previous user controllable element within a UI container */ +#define KEY_NEXT_ELEMENT 0x27b +#define KEY_PREVIOUS_ELEMENT 0x27c + +/* Toggle Autopilot engagement */ +#define KEY_AUTOPILOT_ENGAGE_TOGGLE 0x27d + +/* Shortcut Keys */ +#define KEY_MARK_WAYPOINT 0x27e +#define KEY_SOS 0x27f +#define KEY_NAV_CHART 0x280 +#define KEY_FISHING_CHART 0x281 +#define KEY_SINGLE_RANGE_RADAR 0x282 +#define KEY_DUAL_RANGE_RADAR 0x283 +#define KEY_RADAR_OVERLAY 0x284 +#define KEY_TRADITIONAL_SONAR 0x285 +#define KEY_CLEARVU_SONAR 0x286 +#define KEY_SIDEVU_SONAR 0x287 +#define KEY_NAV_INFO 0x288 +#define KEY_BRIGHTNESS_MENU 0x289 + /* * Some keyboards have keys which do not have a defined meaning, these keys * are intended to be programmed / bound to macros by the user. For most diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 91a6fe4e02c0..32c56384fd08 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -444,8 +444,16 @@ struct kvm_run { #define KVM_SYSTEM_EVENT_SHUTDOWN 1 #define KVM_SYSTEM_EVENT_RESET 2 #define KVM_SYSTEM_EVENT_CRASH 3 +#define KVM_SYSTEM_EVENT_WAKEUP 4 +#define KVM_SYSTEM_EVENT_SUSPEND 5 __u32 type; - __u64 flags; + __u32 ndata; + union { +#ifndef __KERNEL__ + __u64 flags; +#endif + __u64 data[16]; + }; } system_event; /* KVM_EXIT_S390_STSI */ struct { @@ -640,6 +648,7 @@ struct kvm_vapic_addr { #define KVM_MP_STATE_OPERATING 7 #define KVM_MP_STATE_LOAD 8 #define KVM_MP_STATE_AP_RESET_HOLD 9 +#define KVM_MP_STATE_SUSPENDED 10 struct kvm_mp_state { __u32 mp_state; @@ -1144,6 +1153,9 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_MEM_OP_EXTENSION 211 #define KVM_CAP_PMU_CAPABILITY 212 #define KVM_CAP_DISABLE_QUIRKS2 213 +/* #define KVM_CAP_VM_TSC_CONTROL 214 */ +#define KVM_CAP_SYSTEM_EVENT_DATA 215 +#define KVM_CAP_ARM_SYSTEM_SUSPEND 216 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index e998764f0262..a5e06dcbba13 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -272,6 +272,15 @@ struct prctl_mm_map { # define PR_SCHED_CORE_SCOPE_THREAD_GROUP 1 # define PR_SCHED_CORE_SCOPE_PROCESS_GROUP 2 +/* arm64 Scalable Matrix Extension controls */ +/* Flag values must be in sync with SVE versions */ +#define PR_SME_SET_VL 63 /* set task vector length */ +# define PR_SME_SET_VL_ONEXEC (1 << 18) /* defer effect until exec */ +#define PR_SME_GET_VL 64 /* get task vector length */ +/* Bits common to PR_SME_SET_VL and PR_SME_GET_VL */ +# define PR_SME_VL_LEN_MASK 0xffff +# define PR_SME_VL_INHERIT (1 << 17) /* inherit across exec */ + #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0 diff --git a/kernel/events/core.c b/kernel/events/core.c index 23bb19716ad3..7858bafffa9d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6247,7 +6247,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) again: mutex_lock(&event->mmap_mutex); if (event->rb) { - if (event->rb->nr_pages != nr_pages) { + if (data_page_nr(event->rb) != nr_pages) { ret = -EINVAL; goto unlock; } diff --git a/kernel/events/internal.h b/kernel/events/internal.h index 082832738c8f..5150d5f84c03 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -116,6 +116,11 @@ static inline int page_order(struct perf_buffer *rb) } #endif +static inline int data_page_nr(struct perf_buffer *rb) +{ + return rb->nr_pages << page_order(rb); +} + static inline unsigned long perf_data_size(struct perf_buffer *rb) { return rb->nr_pages << (PAGE_SHIFT + page_order(rb)); diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 52868716ec35..fb35b926024c 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -859,11 +859,6 @@ void rb_free(struct perf_buffer *rb) } #else -static int data_page_nr(struct perf_buffer *rb) -{ - return rb->nr_pages << page_order(rb); -} - static struct page * __perf_mmap_to_page(struct perf_buffer *rb, unsigned long pgoff) { diff --git a/kernel/kcov.c b/kernel/kcov.c index 475524bd900a..b3732b210593 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -475,8 +475,11 @@ static int kcov_mmap(struct file *filep, struct vm_area_struct *vma) vma->vm_flags |= VM_DONTEXPAND; for (off = 0; off < size; off += PAGE_SIZE) { page = vmalloc_to_page(kcov->area + off); - if (vm_insert_page(vma, vma->vm_start + off, page)) - WARN_ONCE(1, "vm_insert_page() failed"); + res = vm_insert_page(vma, vma->vm_start + off, page); + if (res) { + pr_warn_once("kcov: vm_insert_page() failed\n"); + return res; + } } return 0; exit: diff --git a/kernel/kprobes.c b/kernel/kprobes.c index dbe57df2e199..dd58c0be9ce2 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2126,7 +2126,7 @@ static void kretprobe_rethook_handler(struct rethook_node *rh, void *data, struct kprobe_ctlblk *kcb; /* The data must NOT be null. This means rethook data structure is broken. */ - if (WARN_ON_ONCE(!data)) + if (WARN_ON_ONCE(!data) || !rp->handler) return; __this_cpu_write(current_kprobe, &rp->kp); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index d4bd299d67ab..a68482d66535 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3829,11 +3829,11 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s se->avg.runnable_sum = se->avg.runnable_avg * divider; - se->avg.load_sum = divider; - if (se_weight(se)) { - se->avg.load_sum = - div_u64(se->avg.load_avg * se->avg.load_sum, se_weight(se)); - } + se->avg.load_sum = se->avg.load_avg * divider; + if (se_weight(se) < se->avg.load_sum) + se->avg.load_sum = div_u64(se->avg.load_sum, se_weight(se)); + else + se->avg.load_sum = 1; enqueue_load_avg(cfs_rq, se); cfs_rq->avg.util_avg += se->avg.util_avg; diff --git a/kernel/sys.c b/kernel/sys.c index 374f83e95239..b911fa6d81ab 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -117,6 +117,12 @@ #ifndef SVE_GET_VL # define SVE_GET_VL() (-EINVAL) #endif +#ifndef SME_SET_VL +# define SME_SET_VL(a) (-EINVAL) +#endif +#ifndef SME_GET_VL +# define SME_GET_VL() (-EINVAL) +#endif #ifndef PAC_RESET_KEYS # define PAC_RESET_KEYS(a, b) (-EINVAL) #endif @@ -2541,6 +2547,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_SVE_GET_VL: error = SVE_GET_VL(); break; + case PR_SME_SET_VL: + error = SME_SET_VL(arg2); + break; + case PR_SME_GET_VL: + error = SME_GET_VL(); + break; case PR_GET_SPECULATION_CTRL: if (arg3 || arg4 || arg5) return -EINVAL; diff --git a/lib/hexdump.c b/lib/hexdump.c index 9301578f98e8..06833d404398 100644 --- a/lib/hexdump.c +++ b/lib/hexdump.c @@ -22,15 +22,33 @@ EXPORT_SYMBOL(hex_asc_upper); * * hex_to_bin() converts one hex digit to its actual value or -1 in case of bad * input. + * + * This function is used to load cryptographic keys, so it is coded in such a + * way that there are no conditions or memory accesses that depend on data. + * + * Explanation of the logic: + * (ch - '9' - 1) is negative if ch <= '9' + * ('0' - 1 - ch) is negative if ch >= '0' + * we "and" these two values, so the result is negative if ch is in the range + * '0' ... '9' + * we are only interested in the sign, so we do a shift ">> 8"; note that right + * shift of a negative value is implementation-defined, so we cast the + * value to (unsigned) before the shift --- we have 0xffffff if ch is in + * the range '0' ... '9', 0 otherwise + * we "and" this value with (ch - '0' + 1) --- we have a value 1 ... 10 if ch is + * in the range '0' ... '9', 0 otherwise + * we add this value to -1 --- we have a value 0 ... 9 if ch is in the range '0' + * ... '9', -1 otherwise + * the next line is similar to the previous one, but we need to decode both + * uppercase and lowercase letters, so we use (ch & 0xdf), which converts + * lowercase to uppercase */ -int hex_to_bin(char ch) +int hex_to_bin(unsigned char ch) { - if ((ch >= '0') && (ch <= '9')) - return ch - '0'; - ch = tolower(ch); - if ((ch >= 'a') && (ch <= 'f')) - return ch - 'a' + 10; - return -1; + unsigned char cu = ch & 0xdf; + return -1 + + ((ch - '0' + 1) & (unsigned)((ch - '9' - 1) & ('0' - 1 - ch)) >> 8) + + ((cu - 'A' + 11) & (unsigned)((cu - 'F' - 1) & ('A' - 1 - cu)) >> 8); } EXPORT_SYMBOL(hex_to_bin); @@ -45,10 +63,13 @@ EXPORT_SYMBOL(hex_to_bin); int hex2bin(u8 *dst, const char *src, size_t count) { while (count--) { - int hi = hex_to_bin(*src++); - int lo = hex_to_bin(*src++); + int hi, lo; - if ((hi < 0) || (lo < 0)) + hi = hex_to_bin(*src++); + if (unlikely(hi < 0)) + return -EINVAL; + lo = hex_to_bin(*src++); + if (unlikely(lo < 0)) return -EINVAL; *dst++ = (hi << 4) | lo; diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c index 08fc72d3ed16..6432b8c3e431 100644 --- a/lib/strncpy_from_user.c +++ b/lib/strncpy_from_user.c @@ -25,7 +25,7 @@ * hit it), 'max' is the address space maximum (and we return * -EFAULT if we hit it). */ -static inline long do_strncpy_from_user(char *dst, const char __user *src, +static __always_inline long do_strncpy_from_user(char *dst, const char __user *src, unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c index bffa0ebf9f8b..feeb935a2299 100644 --- a/lib/strnlen_user.c +++ b/lib/strnlen_user.c @@ -20,7 +20,7 @@ * if it fits in a aligned 'long'. The caller needs to check * the return value against "> max". */ -static inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long max) +static __always_inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; unsigned long align, res = 0; diff --git a/lib/xarray.c b/lib/xarray.c index 4acc88ea7c21..54e646e8e6ee 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -207,6 +207,8 @@ static void *xas_descend(struct xa_state *xas, struct xa_node *node) if (xa_is_sibling(entry)) { offset = xa_to_sibling(entry); entry = xa_entry(xas->xa, node, offset); + if (node->shift && xa_is_node(entry)) + entry = XA_RETRY_ENTRY; } xas->xa_offset = offset; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f8ca7cca3c1a..3fc721789743 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -6785,6 +6785,16 @@ int get_hwpoison_huge_page(struct page *page, bool *hugetlb) return ret; } +int get_huge_page_for_hwpoison(unsigned long pfn, int flags) +{ + int ret; + + spin_lock_irq(&hugetlb_lock); + ret = __get_huge_page_for_hwpoison(pfn, flags); + spin_unlock_irq(&hugetlb_lock); + return ret; +} + void putback_active_hugepage(struct page *page) { spin_lock_irq(&hugetlb_lock); diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index 08291ed33e93..0a9def8ce5e8 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -315,6 +315,13 @@ static void per_cpu_remove_cache(void *arg) struct qlist_head *q; q = this_cpu_ptr(&cpu_quarantine); + /* + * Ensure the ordering between the writing to q->offline and + * per_cpu_remove_cache. Prevent cpu_quarantine from being corrupted + * by interrupt. + */ + if (READ_ONCE(q->offline)) + return; qlist_move_cache(q, &to_free, cache); qlist_free_all(&to_free, cache); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 725f76723220..598fece89e2b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -587,6 +587,9 @@ static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork); static DEFINE_SPINLOCK(stats_flush_lock); static DEFINE_PER_CPU(unsigned int, stats_updates); static atomic_t stats_flush_threshold = ATOMIC_INIT(0); +static u64 flush_next_time; + +#define FLUSH_TIME (2UL*HZ) /* * Accessors to ensure that preemption is disabled on PREEMPT_RT because it can @@ -637,6 +640,7 @@ static void __mem_cgroup_flush_stats(void) if (!spin_trylock_irqsave(&stats_flush_lock, flag)) return; + flush_next_time = jiffies_64 + 2*FLUSH_TIME; cgroup_rstat_flush_irqsafe(root_mem_cgroup->css.cgroup); atomic_set(&stats_flush_threshold, 0); spin_unlock_irqrestore(&stats_flush_lock, flag); @@ -648,10 +652,16 @@ void mem_cgroup_flush_stats(void) __mem_cgroup_flush_stats(); } +void mem_cgroup_flush_stats_delayed(void) +{ + if (time_after64(jiffies_64, flush_next_time)) + mem_cgroup_flush_stats(); +} + static void flush_memcg_stats_dwork(struct work_struct *w) { __mem_cgroup_flush_stats(); - queue_delayed_work(system_unbound_wq, &stats_flush_dwork, 2UL*HZ); + queue_delayed_work(system_unbound_wq, &stats_flush_dwork, FLUSH_TIME); } /** diff --git a/mm/memory-failure.c b/mm/memory-failure.c index dcb6bb9cf731..27760c19bad7 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1498,50 +1498,113 @@ static int try_to_split_thp_page(struct page *page, const char *msg) return 0; } -static int memory_failure_hugetlb(unsigned long pfn, int flags) +/* + * Called from hugetlb code with hugetlb_lock held. + * + * Return values: + * 0 - free hugepage + * 1 - in-use hugepage + * 2 - not a hugepage + * -EBUSY - the hugepage is busy (try to retry) + * -EHWPOISON - the hugepage is already hwpoisoned + */ +int __get_huge_page_for_hwpoison(unsigned long pfn, int flags) +{ + struct page *page = pfn_to_page(pfn); + struct page *head = compound_head(page); + int ret = 2; /* fallback to normal page handling */ + bool count_increased = false; + + if (!PageHeadHuge(head)) + goto out; + + if (flags & MF_COUNT_INCREASED) { + ret = 1; + count_increased = true; + } else if (HPageFreed(head) || HPageMigratable(head)) { + ret = get_page_unless_zero(head); + if (ret) + count_increased = true; + } else { + ret = -EBUSY; + goto out; + } + + if (TestSetPageHWPoison(head)) { + ret = -EHWPOISON; + goto out; + } + + return ret; +out: + if (count_increased) + put_page(head); + return ret; +} + +#ifdef CONFIG_HUGETLB_PAGE +/* + * Taking refcount of hugetlb pages needs extra care about race conditions + * with basic operations like hugepage allocation/free/demotion. + * So some of prechecks for hwpoison (pinning, and testing/setting + * PageHWPoison) should be done in single hugetlb_lock range. + */ +static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb) { - struct page *p = pfn_to_page(pfn); - struct page *head = compound_head(p); int res; + struct page *p = pfn_to_page(pfn); + struct page *head; unsigned long page_flags; + bool retry = true; - if (TestSetPageHWPoison(head)) { - pr_err("Memory failure: %#lx: already hardware poisoned\n", - pfn); - res = -EHWPOISON; - if (flags & MF_ACTION_REQUIRED) + *hugetlb = 1; +retry: + res = get_huge_page_for_hwpoison(pfn, flags); + if (res == 2) { /* fallback to normal page handling */ + *hugetlb = 0; + return 0; + } else if (res == -EHWPOISON) { + pr_err("Memory failure: %#lx: already hardware poisoned\n", pfn); + if (flags & MF_ACTION_REQUIRED) { + head = compound_head(p); res = kill_accessing_process(current, page_to_pfn(head), flags); + } + return res; + } else if (res == -EBUSY) { + if (retry) { + retry = false; + goto retry; + } + action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED); return res; } + head = compound_head(p); + lock_page(head); + + if (hwpoison_filter(p)) { + ClearPageHWPoison(head); + res = -EOPNOTSUPP; + goto out; + } + num_poisoned_pages_inc(); - if (!(flags & MF_COUNT_INCREASED)) { - res = get_hwpoison_page(p, flags); - if (!res) { - lock_page(head); - if (hwpoison_filter(p)) { - if (TestClearPageHWPoison(head)) - num_poisoned_pages_dec(); - unlock_page(head); - return -EOPNOTSUPP; - } - unlock_page(head); - res = MF_FAILED; - if (__page_handle_poison(p)) { - page_ref_inc(p); - res = MF_RECOVERED; - } - action_result(pfn, MF_MSG_FREE_HUGE, res); - return res == MF_RECOVERED ? 0 : -EBUSY; - } else if (res < 0) { - action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED); - return -EBUSY; + /* + * Handling free hugepage. The possible race with hugepage allocation + * or demotion can be prevented by PageHWPoison flag. + */ + if (res == 0) { + unlock_page(head); + res = MF_FAILED; + if (__page_handle_poison(p)) { + page_ref_inc(p); + res = MF_RECOVERED; } + action_result(pfn, MF_MSG_FREE_HUGE, res); + return res == MF_RECOVERED ? 0 : -EBUSY; } - lock_page(head); - /* * The page could have changed compound pages due to race window. * If this happens just bail out. @@ -1554,14 +1617,6 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags) page_flags = head->flags; - if (hwpoison_filter(p)) { - if (TestClearPageHWPoison(head)) - num_poisoned_pages_dec(); - put_page(p); - res = -EOPNOTSUPP; - goto out; - } - /* * TODO: hwpoison for pud-sized hugetlb doesn't work right now, so * simply disable it. In order to make it work properly, we need @@ -1588,6 +1643,12 @@ out: unlock_page(head); return res; } +#else +static inline int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb) +{ + return 0; +} +#endif static int memory_failure_dev_pagemap(unsigned long pfn, int flags, struct dev_pagemap *pgmap) @@ -1712,6 +1773,7 @@ int memory_failure(unsigned long pfn, int flags) int res = 0; unsigned long page_flags; bool retry = true; + int hugetlb = 0; if (!sysctl_memory_failure_recovery) panic("Memory failure on page %lx", pfn); @@ -1739,10 +1801,9 @@ int memory_failure(unsigned long pfn, int flags) } try_again: - if (PageHuge(p)) { - res = memory_failure_hugetlb(pfn, flags); + res = try_memory_failure_hugetlb(pfn, flags, &hugetlb); + if (hugetlb) goto unlock_mutex; - } if (TestSetPageHWPoison(p)) { pr_err("Memory failure: %#lx: already hardware poisoned\n", @@ -1800,6 +1861,19 @@ try_again: if (PageTransHuge(hpage)) { /* + * Bail out before SetPageHasHWPoisoned() if hpage is + * huge_zero_page, although PG_has_hwpoisoned is not + * checked in set_huge_zero_page(). + * + * TODO: Handle memory failure of huge_zero_page thoroughly. + */ + if (is_huge_zero_page(hpage)) { + action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED); + res = -EBUSY; + goto unlock_mutex; + } + + /* * The flag must be set after the refcount is bumped * otherwise it may race with THP split. * And the flag can't be set in get_hwpoison_page() since diff --git a/mm/mmap.c b/mm/mmap.c index 3aa839f81e63..313b57d55a63 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2117,14 +2117,6 @@ unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info) return addr; } -#ifndef arch_get_mmap_end -#define arch_get_mmap_end(addr) (TASK_SIZE) -#endif - -#ifndef arch_get_mmap_base -#define arch_get_mmap_base(addr, base) (base) -#endif - /* Get an address range which is currently unmapped. * For shmat() with addr=0. * diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 459d195d2ff6..f45ff1b7626a 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -1036,6 +1036,18 @@ int mmu_interval_notifier_insert_locked( } EXPORT_SYMBOL_GPL(mmu_interval_notifier_insert_locked); +static bool +mmu_interval_seq_released(struct mmu_notifier_subscriptions *subscriptions, + unsigned long seq) +{ + bool ret; + + spin_lock(&subscriptions->lock); + ret = subscriptions->invalidate_seq != seq; + spin_unlock(&subscriptions->lock); + return ret; +} + /** * mmu_interval_notifier_remove - Remove a interval notifier * @interval_sub: Interval subscription to unregister @@ -1083,7 +1095,7 @@ void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub) lock_map_release(&__mmu_notifier_invalidate_range_start_map); if (seq) wait_event(subscriptions->wq, - READ_ONCE(subscriptions->invalidate_seq) != seq); + mmu_interval_seq_released(subscriptions, seq)); /* pairs with mmgrab in mmu_interval_notifier_insert() */ mmdrop(mm); diff --git a/mm/nommu.c b/mm/nommu.c index 55a9e48a7a02..9d7afc2d959e 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -226,6 +226,8 @@ void *vmalloc(unsigned long size) } EXPORT_SYMBOL(vmalloc); +void *vmalloc_huge(unsigned long size, gfp_t gfp_mask) __weak __alias(__vmalloc); + /* * vzalloc - allocate virtually contiguous memory with zero fill * diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 7ec38194f8e1..49d7df39b02d 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -632,7 +632,7 @@ done: */ set_bit(MMF_OOM_SKIP, &mm->flags); - /* Drop a reference taken by wake_oom_reaper */ + /* Drop a reference taken by queue_oom_reaper */ put_task_struct(tsk); } @@ -644,12 +644,12 @@ static int oom_reaper(void *unused) struct task_struct *tsk = NULL; wait_event_freezable(oom_reaper_wait, oom_reaper_list != NULL); - spin_lock(&oom_reaper_lock); + spin_lock_irq(&oom_reaper_lock); if (oom_reaper_list != NULL) { tsk = oom_reaper_list; oom_reaper_list = tsk->oom_reaper_list; } - spin_unlock(&oom_reaper_lock); + spin_unlock_irq(&oom_reaper_lock); if (tsk) oom_reap_task(tsk); @@ -658,22 +658,48 @@ static int oom_reaper(void *unused) return 0; } -static void wake_oom_reaper(struct task_struct *tsk) +static void wake_oom_reaper(struct timer_list *timer) { - /* mm is already queued? */ - if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags)) - return; + struct task_struct *tsk = container_of(timer, struct task_struct, + oom_reaper_timer); + struct mm_struct *mm = tsk->signal->oom_mm; + unsigned long flags; - get_task_struct(tsk); + /* The victim managed to terminate on its own - see exit_mmap */ + if (test_bit(MMF_OOM_SKIP, &mm->flags)) { + put_task_struct(tsk); + return; + } - spin_lock(&oom_reaper_lock); + spin_lock_irqsave(&oom_reaper_lock, flags); tsk->oom_reaper_list = oom_reaper_list; oom_reaper_list = tsk; - spin_unlock(&oom_reaper_lock); + spin_unlock_irqrestore(&oom_reaper_lock, flags); trace_wake_reaper(tsk->pid); wake_up(&oom_reaper_wait); } +/* + * Give the OOM victim time to exit naturally before invoking the oom_reaping. + * The timers timeout is arbitrary... the longer it is, the longer the worst + * case scenario for the OOM can take. If it is too small, the oom_reaper can + * get in the way and release resources needed by the process exit path. + * e.g. The futex robust list can sit in Anon|Private memory that gets reaped + * before the exit path is able to wake the futex waiters. + */ +#define OOM_REAPER_DELAY (2*HZ) +static void queue_oom_reaper(struct task_struct *tsk) +{ + /* mm is already queued? */ + if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags)) + return; + + get_task_struct(tsk); + timer_setup(&tsk->oom_reaper_timer, wake_oom_reaper, 0); + tsk->oom_reaper_timer.expires = jiffies + OOM_REAPER_DELAY; + add_timer(&tsk->oom_reaper_timer); +} + static int __init oom_init(void) { oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper"); @@ -681,7 +707,7 @@ static int __init oom_init(void) } subsys_initcall(oom_init) #else -static inline void wake_oom_reaper(struct task_struct *tsk) +static inline void queue_oom_reaper(struct task_struct *tsk) { } #endif /* CONFIG_MMU */ @@ -932,7 +958,7 @@ static void __oom_kill_process(struct task_struct *victim, const char *message) rcu_read_unlock(); if (can_oom_reap) - wake_oom_reaper(victim); + queue_oom_reaper(victim); mmdrop(mm); put_task_struct(victim); @@ -968,7 +994,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message) task_lock(victim); if (task_will_free_mem(victim)) { mark_oom_victim(victim); - wake_oom_reaper(victim); + queue_oom_reaper(victim); task_unlock(victim); put_task_struct(victim); return; @@ -1067,7 +1093,7 @@ bool out_of_memory(struct oom_control *oc) */ if (task_will_free_mem(current)) { mark_oom_victim(current); - wake_oom_reaper(current); + queue_oom_reaper(current); return true; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 33ca8cab21e6..0e42038382c1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8919,7 +8919,7 @@ void *__init alloc_large_system_hash(const char *tablename, table = memblock_alloc_raw(size, SMP_CACHE_BYTES); } else if (get_order(size) >= MAX_ORDER || hashdist) { - table = __vmalloc(size, gfp_flags); + table = vmalloc_huge(size, gfp_flags); virt = true; if (table) huge = is_vm_area_hugepages(table); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 0cb8e5ef1713..e9bb6db002aa 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -72,12 +72,15 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, _dst_pte = pte_mkdirty(_dst_pte); if (page_in_cache && !vm_shared) writable = false; - if (writable) { - if (wp_copy) - _dst_pte = pte_mkuffd_wp(_dst_pte); - else - _dst_pte = pte_mkwrite(_dst_pte); - } + + /* + * Always mark a PTE as write-protected when needed, regardless of + * VM_WRITE, which the user might change. + */ + if (wp_copy) + _dst_pte = pte_mkuffd_wp(_dst_pte); + else if (writable) + _dst_pte = pte_mkwrite(_dst_pte); dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); diff --git a/mm/util.c b/mm/util.c index 54e5e761a9a9..3492a9e81aa3 100644 --- a/mm/util.c +++ b/mm/util.c @@ -592,8 +592,15 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) return NULL; } - return __vmalloc_node(size, 1, flags, node, - __builtin_return_address(0)); + /* + * kvmalloc() can always use VM_ALLOW_HUGE_VMAP, + * since the callers already cannot assume anything + * about the resulting pointer, and cannot play + * protection games. + */ + return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, + flags, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP, + node, __builtin_return_address(0)); } EXPORT_SYMBOL(kvmalloc_node); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 0b17498a34f1..cadfbb5155ea 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2653,15 +2653,18 @@ static void __vunmap(const void *addr, int deallocate_pages) vm_remove_mappings(area, deallocate_pages); if (deallocate_pages) { - unsigned int page_order = vm_area_page_order(area); - int i, step = 1U << page_order; + int i; - for (i = 0; i < area->nr_pages; i += step) { + for (i = 0; i < area->nr_pages; i++) { struct page *page = area->pages[i]; BUG_ON(!page); - mod_memcg_page_state(page, MEMCG_VMALLOC, -step); - __free_pages(page, page_order); + mod_memcg_page_state(page, MEMCG_VMALLOC, -1); + /* + * High-order allocs for huge vmallocs are split, so + * can be freed as an array of order-0 allocations + */ + __free_pages(page, 0); cond_resched(); } atomic_long_sub(area->nr_pages, &nr_vmalloc_pages); @@ -2914,12 +2917,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid, if (nr != nr_pages_request) break; } - } else - /* - * Compound pages required for remap_vmalloc_page if - * high-order pages. - */ - gfp |= __GFP_COMP; + } /* High-order pages or fallback path if "bulk" fails. */ @@ -2933,6 +2931,15 @@ vm_area_alloc_pages(gfp_t gfp, int nid, page = alloc_pages_node(nid, gfp, order); if (unlikely(!page)) break; + /* + * Higher order allocations must be able to be treated as + * indepdenent small pages by callers (as they can with + * small-page vmallocs). Some drivers do their own refcounting + * on vmalloc_to_page() pages, some use page->mapping, + * page->lru, etc. + */ + if (order) + split_page(page, order); /* * Careful, we allocate and map page-order pages, but @@ -2992,11 +2999,10 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, atomic_long_add(area->nr_pages, &nr_vmalloc_pages); if (gfp_mask & __GFP_ACCOUNT) { - int i, step = 1U << page_order; + int i; - for (i = 0; i < area->nr_pages; i += step) - mod_memcg_page_state(area->pages[i], MEMCG_VMALLOC, - step); + for (i = 0; i < area->nr_pages; i++) + mod_memcg_page_state(area->pages[i], MEMCG_VMALLOC, 1); } /* @@ -3095,7 +3101,7 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, return NULL; } - if (vmap_allow_huge && !(vm_flags & VM_NO_HUGE_VMAP)) { + if (vmap_allow_huge && (vm_flags & VM_ALLOW_HUGE_VMAP)) { unsigned long size_per_node; /* @@ -3262,21 +3268,24 @@ void *vmalloc(unsigned long size) EXPORT_SYMBOL(vmalloc); /** - * vmalloc_no_huge - allocate virtually contiguous memory using small pages - * @size: allocation size + * vmalloc_huge - allocate virtually contiguous memory, allow huge pages + * @size: allocation size + * @gfp_mask: flags for the page level allocator * - * Allocate enough non-huge pages to cover @size from the page level + * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. + * If @size is greater than or equal to PMD_SIZE, allow using + * huge pages for the memory * * Return: pointer to the allocated memory or %NULL on error */ -void *vmalloc_no_huge(unsigned long size) +void *vmalloc_huge(unsigned long size, gfp_t gfp_mask) { return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, - GFP_KERNEL, PAGE_KERNEL, VM_NO_HUGE_VMAP, + gfp_mask, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP, NUMA_NO_NODE, __builtin_return_address(0)); } -EXPORT_SYMBOL(vmalloc_no_huge); +EXPORT_SYMBOL_GPL(vmalloc_huge); /** * vzalloc - allocate virtually contiguous memory with zero fill diff --git a/mm/workingset.c b/mm/workingset.c index 8a3828acc0bf..592569a8974c 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -355,7 +355,7 @@ void workingset_refault(struct folio *folio, void *shadow) mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr); - mem_cgroup_flush_stats(); + mem_cgroup_flush_stats_delayed(); /* * Compare the distance to the existing workingset size. We * don't activate pages that couldn't stay resident even if diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 84312c836549..fe803bee419a 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -670,7 +670,7 @@ static void le_conn_timeout(struct work_struct *work) /* Disable LE Advertising */ le_disable_advertising(hdev); hci_dev_lock(hdev); - hci_le_conn_failed(conn, HCI_ERROR_ADVERTISING_TIMEOUT); + hci_conn_failed(conn, HCI_ERROR_ADVERTISING_TIMEOUT); hci_dev_unlock(hdev); return; } @@ -873,7 +873,7 @@ struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, uint8_t src_type) EXPORT_SYMBOL(hci_get_route); /* This function requires the caller holds hdev->lock */ -void hci_le_conn_failed(struct hci_conn *conn, u8 status) +static void hci_le_conn_failed(struct hci_conn *conn, u8 status) { struct hci_dev *hdev = conn->hdev; struct hci_conn_params *params; @@ -886,8 +886,6 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status) params->conn = NULL; } - conn->state = BT_CLOSED; - /* If the status indicates successful cancellation of * the attempt (i.e. Unknown Connection Id) there's no point of * notifying failure since we'll go back to keep trying to @@ -899,10 +897,6 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status) mgmt_connect_failed(hdev, &conn->dst, conn->type, conn->dst_type, status); - hci_connect_cfm(conn, status); - - hci_conn_del(conn); - /* Since we may have temporarily stopped the background scanning in * favor of connection establishment, we should restart it. */ @@ -914,6 +908,28 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status) hci_enable_advertising(hdev); } +/* This function requires the caller holds hdev->lock */ +void hci_conn_failed(struct hci_conn *conn, u8 status) +{ + struct hci_dev *hdev = conn->hdev; + + bt_dev_dbg(hdev, "status 0x%2.2x", status); + + switch (conn->type) { + case LE_LINK: + hci_le_conn_failed(conn, status); + break; + case ACL_LINK: + mgmt_connect_failed(hdev, &conn->dst, conn->type, + conn->dst_type, status); + break; + } + + conn->state = BT_CLOSED; + hci_connect_cfm(conn, status); + hci_conn_del(conn); +} + static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) { struct hci_conn *conn = data; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index abaabfae19cc..66451661283c 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -2834,7 +2834,7 @@ static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status) bt_dev_dbg(hdev, "status 0x%2.2x", status); /* All connection failure handling is taken care of by the - * hci_le_conn_failed function which is triggered by the HCI + * hci_conn_failed function which is triggered by the HCI * request completion callbacks used for connecting. */ if (status) @@ -2859,7 +2859,7 @@ static void hci_cs_le_ext_create_conn(struct hci_dev *hdev, u8 status) bt_dev_dbg(hdev, "status 0x%2.2x", status); /* All connection failure handling is taken care of by the - * hci_le_conn_failed function which is triggered by the HCI + * hci_conn_failed function which is triggered by the HCI * request completion callbacks used for connecting. */ if (status) @@ -3067,18 +3067,20 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, { struct hci_ev_conn_complete *ev = data; struct hci_conn *conn; + u8 status = ev->status; - if (__le16_to_cpu(ev->handle) > HCI_CONN_HANDLE_MAX) { - bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for invalid handle"); - return; - } - - bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); + bt_dev_dbg(hdev, "status 0x%2.2x", status); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ev->link_type, &ev->bdaddr); if (!conn) { + /* In case of error status and there is no connection pending + * just unlock as there is nothing to cleanup. + */ + if (ev->status) + goto unlock; + /* Connection may not exist if auto-connected. Check the bredr * allowlist to see if this device is allowed to auto connect. * If link is an ACL type, create a connection class @@ -3122,8 +3124,14 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, goto unlock; } - if (!ev->status) { + if (!status) { conn->handle = __le16_to_cpu(ev->handle); + if (conn->handle > HCI_CONN_HANDLE_MAX) { + bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x", + conn->handle, HCI_CONN_HANDLE_MAX); + status = HCI_ERROR_INVALID_PARAMETERS; + goto done; + } if (conn->type == ACL_LINK) { conn->state = BT_CONFIG; @@ -3164,19 +3172,14 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, hci_send_cmd(hdev, HCI_OP_CHANGE_CONN_PTYPE, sizeof(cp), &cp); } - } else { - conn->state = BT_CLOSED; - if (conn->type == ACL_LINK) - mgmt_connect_failed(hdev, &conn->dst, conn->type, - conn->dst_type, ev->status); } if (conn->type == ACL_LINK) hci_sco_setup(conn, ev->status); - if (ev->status) { - hci_connect_cfm(conn, ev->status); - hci_conn_del(conn); +done: + if (status) { + hci_conn_failed(conn, status); } else if (ev->link_type == SCO_LINK) { switch (conn->setting & SCO_AIRMODE_MASK) { case SCO_AIRMODE_CVSD: @@ -3185,7 +3188,7 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, break; } - hci_connect_cfm(conn, ev->status); + hci_connect_cfm(conn, status); } unlock: @@ -4676,6 +4679,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, { struct hci_ev_sync_conn_complete *ev = data; struct hci_conn *conn; + u8 status = ev->status; switch (ev->link_type) { case SCO_LINK: @@ -4690,12 +4694,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, return; } - if (__le16_to_cpu(ev->handle) > HCI_CONN_HANDLE_MAX) { - bt_dev_err(hdev, "Ignoring HCI_Sync_Conn_Complete for invalid handle"); - return; - } - - bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); + bt_dev_dbg(hdev, "status 0x%2.2x", status); hci_dev_lock(hdev); @@ -4729,9 +4728,17 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, goto unlock; } - switch (ev->status) { + switch (status) { case 0x00: conn->handle = __le16_to_cpu(ev->handle); + if (conn->handle > HCI_CONN_HANDLE_MAX) { + bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x", + conn->handle, HCI_CONN_HANDLE_MAX); + status = HCI_ERROR_INVALID_PARAMETERS; + conn->state = BT_CLOSED; + break; + } + conn->state = BT_CONNECTED; conn->type = ev->link_type; @@ -4775,8 +4782,8 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, } } - hci_connect_cfm(conn, ev->status); - if (ev->status) + hci_connect_cfm(conn, status); + if (status) hci_conn_del(conn); unlock: @@ -5527,11 +5534,6 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, struct smp_irk *irk; u8 addr_type; - if (handle > HCI_CONN_HANDLE_MAX) { - bt_dev_err(hdev, "Ignoring HCI_LE_Connection_Complete for invalid handle"); - return; - } - hci_dev_lock(hdev); /* All controllers implicitly stop advertising in the event of a @@ -5541,6 +5543,12 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, conn = hci_lookup_le_connect(hdev); if (!conn) { + /* In case of error status and there is no connection pending + * just unlock as there is nothing to cleanup. + */ + if (status) + goto unlock; + conn = hci_conn_add(hdev, LE_LINK, bdaddr, role); if (!conn) { bt_dev_err(hdev, "no memory for new connection"); @@ -5603,8 +5611,14 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, conn->dst_type = ev_bdaddr_type(hdev, conn->dst_type, NULL); + if (handle > HCI_CONN_HANDLE_MAX) { + bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x", handle, + HCI_CONN_HANDLE_MAX); + status = HCI_ERROR_INVALID_PARAMETERS; + } + if (status) { - hci_le_conn_failed(conn, status); + hci_conn_failed(conn, status); goto unlock; } diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 8f4c5698913d..13600bf120b0 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -4408,12 +4408,21 @@ static int hci_reject_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, static int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason) { + int err; + switch (conn->state) { case BT_CONNECTED: case BT_CONFIG: return hci_disconnect_sync(hdev, conn, reason); case BT_CONNECT: - return hci_connect_cancel_sync(hdev, conn); + err = hci_connect_cancel_sync(hdev, conn); + /* Cleanup hci_conn object if it cannot be cancelled as it + * likelly means the controller and host stack are out of sync. + */ + if (err) + hci_conn_failed(conn, err); + + return err; case BT_CONNECT2: return hci_reject_conn_sync(hdev, conn, reason); default: diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index e7b9c2636d10..af709c182674 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -108,6 +108,7 @@ struct xdp_test_data { struct page_pool *pp; struct xdp_frame **frames; struct sk_buff **skbs; + struct xdp_mem_info mem; u32 batch_size; u32 frame_cnt; }; @@ -147,7 +148,6 @@ static void xdp_test_run_init_page(struct page *page, void *arg) static int xdp_test_run_setup(struct xdp_test_data *xdp, struct xdp_buff *orig_ctx) { - struct xdp_mem_info mem = {}; struct page_pool *pp; int err = -ENOMEM; struct page_pool_params pp_params = { @@ -174,7 +174,7 @@ static int xdp_test_run_setup(struct xdp_test_data *xdp, struct xdp_buff *orig_c } /* will copy 'mem.id' into pp->xdp_mem_id */ - err = xdp_reg_mem_model(&mem, MEM_TYPE_PAGE_POOL, pp); + err = xdp_reg_mem_model(&xdp->mem, MEM_TYPE_PAGE_POOL, pp); if (err) goto err_mmodel; @@ -202,6 +202,7 @@ err_skbs: static void xdp_test_run_teardown(struct xdp_test_data *xdp) { + xdp_unreg_mem_model(&xdp->mem); page_pool_destroy(xdp->pp); kfree(xdp->frames); kfree(xdp->skbs); diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 8cc44c367231..18affda2b522 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -353,6 +353,8 @@ static int br_switchdev_vlan_attr_replay(struct net_device *br_dev, attr.orig_dev = br_dev; vg = br_vlan_group(br); + if (!vg) + return 0; list_for_each_entry(v, &vg->vlan_list, vlist) { if (v->msti) { diff --git a/net/can/isotp.c b/net/can/isotp.c index bafb0fb5f0e0..ff5d7870294e 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -906,6 +906,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) struct canfd_frame *cf; int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0; int wait_tx_done = (so->opt.flags & CAN_ISOTP_WAIT_TX_DONE) ? 1 : 0; + s64 hrtimer_sec = 0; int off; int err; @@ -1004,7 +1005,9 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) isotp_create_fframe(cf, so, ae); /* start timeout for FC */ - hrtimer_start(&so->txtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); + hrtimer_sec = 1; + hrtimer_start(&so->txtimer, ktime_set(hrtimer_sec, 0), + HRTIMER_MODE_REL_SOFT); } /* send the first or only CAN frame */ @@ -1017,6 +1020,11 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (err) { pr_notice_once("can-isotp: %s: can_send_ret %pe\n", __func__, ERR_PTR(err)); + + /* no transmission -> no timeout monitoring */ + if (hrtimer_sec) + hrtimer_cancel(&so->txtimer); + goto err_out_drop; } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 1c5815530e0d..83eb97c94e83 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -2385,7 +2385,11 @@ again: if (ceph_test_opt(osdc->client, ABORT_ON_FULL)) { err = -ENOSPC; } else { - pr_warn_ratelimited("FULL or reached pool quota\n"); + if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL)) + pr_warn_ratelimited("cluster is full (osdmap FULL)\n"); + else + pr_warn_ratelimited("pool %lld is full or reached quota\n", + req->r_t.base_oloc.pool); req->r_t.paused = true; maybe_request_map(osdc); } diff --git a/net/core/dev.c b/net/core/dev.c index 8c6c08446556..1461c2d9dec8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10304,7 +10304,7 @@ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, } EXPORT_SYMBOL(netdev_stats_to_stats64); -struct net_device_core_stats *netdev_core_stats_alloc(struct net_device *dev) +struct net_device_core_stats __percpu *netdev_core_stats_alloc(struct net_device *dev) { struct net_device_core_stats __percpu *p; @@ -10315,11 +10315,7 @@ struct net_device_core_stats *netdev_core_stats_alloc(struct net_device *dev) free_percpu(p); /* This READ_ONCE() pairs with the cmpxchg() above */ - p = READ_ONCE(dev->core_stats); - if (!p) - return NULL; - - return this_cpu_ptr(p); + return READ_ONCE(dev->core_stats); } EXPORT_SYMBOL(netdev_core_stats_alloc); @@ -10356,9 +10352,9 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, for_each_possible_cpu(i) { core_stats = per_cpu_ptr(p, i); - storage->rx_dropped += local_read(&core_stats->rx_dropped); - storage->tx_dropped += local_read(&core_stats->tx_dropped); - storage->rx_nohandler += local_read(&core_stats->rx_nohandler); + storage->rx_dropped += READ_ONCE(core_stats->rx_dropped); + storage->tx_dropped += READ_ONCE(core_stats->tx_dropped); + storage->rx_nohandler += READ_ONCE(core_stats->rx_nohandler); } } return storage; diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 349480ef68a5..8b6b5e72b217 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -159,10 +159,8 @@ static int bpf_output(struct net *net, struct sock *sk, struct sk_buff *skb) return dst->lwtstate->orig_output(net, sk, skb); } -static int xmit_check_hhlen(struct sk_buff *skb) +static int xmit_check_hhlen(struct sk_buff *skb, int hh_len) { - int hh_len = skb_dst(skb)->dev->hard_header_len; - if (skb_headroom(skb) < hh_len) { int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb)); @@ -274,6 +272,7 @@ static int bpf_xmit(struct sk_buff *skb) bpf = bpf_lwt_lwtunnel(dst->lwtstate); if (bpf->xmit.prog) { + int hh_len = dst->dev->hard_header_len; __be16 proto = skb->protocol; int ret; @@ -291,7 +290,7 @@ static int bpf_xmit(struct sk_buff *skb) /* If the header was expanded, headroom might be too * small for L2 header to come, expand as needed. */ - ret = xmit_check_hhlen(skb); + ret = xmit_check_hhlen(skb, hh_len); if (unlikely(ret)) return ret; diff --git a/net/dsa/port.c b/net/dsa/port.c index 32d472a82241..cdc56ba11f52 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -1620,8 +1620,10 @@ int dsa_port_link_register_of(struct dsa_port *dp) if (ds->ops->phylink_mac_link_down) ds->ops->phylink_mac_link_down(ds, port, MLO_AN_FIXED, PHY_INTERFACE_MODE_NA); + of_node_put(phy_np); return dsa_port_phylink_register(dp); } + of_node_put(phy_np); return 0; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 41c69a6e7854..8022d50584db 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -285,7 +285,7 @@ static void dsa_port_manage_cpu_flood(struct dsa_port *dp) if (other_dp->slave->flags & IFF_ALLMULTI) flags.val |= BR_MCAST_FLOOD; if (other_dp->slave->flags & IFF_PROMISC) - flags.val |= BR_FLOOD; + flags.val |= BR_FLOOD | BR_MCAST_FLOOD; } err = dsa_port_pre_bridge_flags(dp, flags, NULL); diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c index f64b805303cd..eb204ad36eee 100644 --- a/net/dsa/tag_hellcreek.c +++ b/net/dsa/tag_hellcreek.c @@ -21,6 +21,14 @@ static struct sk_buff *hellcreek_xmit(struct sk_buff *skb, struct dsa_port *dp = dsa_slave_to_port(dev); u8 *tag; + /* Calculate checksums (if required) before adding the trailer tag to + * avoid including it in calculations. That would lead to wrong + * checksums after the switch strips the tag. + */ + if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_help(skb)) + return NULL; + /* Tag encoding */ tag = skb_put(skb, HELLCREEK_TAG_LEN); *tag = BIT(dp->index); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 70e6c87fbe3d..d747166bb291 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -446,7 +446,6 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * struct page *page; struct sk_buff *trailer; int tailen = esp->tailen; - unsigned int allocsz; /* this is non-NULL only with TCP/UDP Encapsulation */ if (x->encap) { @@ -456,8 +455,8 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * return err; } - allocsz = ALIGN(skb->data_len + tailen, L1_CACHE_BYTES); - if (allocsz > ESP_SKB_FRAG_MAXSIZE) + if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE || + ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE) goto cow; if (!skb_cloned(skb)) { diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 99db2e41ed10..aacee9dd771b 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -459,14 +459,12 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); - - if (tunnel->parms.o_flags & TUNNEL_SEQ) - tunnel->o_seqno++; + __be16 flags = tunnel->parms.o_flags; /* Push GRE header. */ gre_build_header(skb, tunnel->tun_hlen, - tunnel->parms.o_flags, proto, tunnel->parms.o_key, - htonl(tunnel->o_seqno)); + flags, proto, tunnel->parms.o_key, + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } @@ -504,7 +502,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); gre_build_header(skb, tunnel_hlen, flags, proto, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0); + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); @@ -581,7 +579,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) } gre_build_header(skb, 8, TUNNEL_SEQ, - proto, 0, htonl(tunnel->o_seqno++)); + proto, 0, htonl(atomic_fetch_inc(&tunnel->o_seqno))); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); @@ -605,8 +603,8 @@ static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) key = &info->key; ip_tunnel_init_flow(&fl4, IPPROTO_GRE, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), - key->tos & ~INET_ECN_MASK, 0, skb->mark, - skb_get_hash(skb)); + key->tos & ~INET_ECN_MASK, dev_net(dev), 0, + skb->mark, skb_get_hash(skb)); rt = ip_route_output_key(dev_net(dev), &fl4); if (IS_ERR(rt)) return PTR_ERR(rt); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 5a473319d3a5..94017a8c3994 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -294,8 +294,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev) ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr, iph->saddr, tunnel->parms.o_key, - RT_TOS(iph->tos), tunnel->parms.link, - tunnel->fwmark, 0); + RT_TOS(iph->tos), dev_net(dev), + tunnel->parms.link, tunnel->fwmark, 0); rt = ip_route_output_key(tunnel->net, &fl4); if (!IS_ERR(rt)) { @@ -570,7 +570,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), RT_TOS(tos), - 0, skb->mark, skb_get_hash(skb)); + dev_net(dev), 0, skb->mark, skb_get_hash(skb)); if (tunnel->encap.type != TUNNEL_ENCAP_NONE) goto tx_error; @@ -726,7 +726,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, - tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, + tunnel->parms.o_key, RT_TOS(tos), + dev_net(dev), tunnel->parms.link, tunnel->fwmark, skb_get_hash(skb)); if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/net/ipv4/netfilter/nf_flow_table_ipv4.c +++ /dev/null diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 2cb3b852d148..f33c31dd7366 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -281,6 +281,7 @@ bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt, EXPORT_SYMBOL(cookie_ecn_ok); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, + const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb) { @@ -297,6 +298,10 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, return NULL; treq = tcp_rsk(req); + + /* treq->af_specific might be used to perform TCP_MD5 lookup */ + treq->af_specific = af_ops; + treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield; #if IS_ENABLED(CONFIG_MPTCP) treq->is_mptcp = sk_is_mptcp(sk); @@ -364,7 +369,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, sk, skb); + req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, + &tcp_request_sock_ipv4_ops, sk, skb); if (!req) goto out; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2088f93fa37b..60f99e9fb6d1 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3867,7 +3867,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_process_tlp_ack(sk, ack, flag); if (tcp_ack_is_dubious(sk, flag)) { - if (!(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP))) { + if (!(flag & (FLAG_SND_UNA_ADVANCED | + FLAG_NOT_DUP | FLAG_DSACKING_ACK))) { num_dupack = 1; /* Consider if pure acks were aggregated in tcp_add_backlog() */ if (!(flag & FLAG_DATA)) @@ -5454,7 +5455,17 @@ static void tcp_new_space(struct sock *sk) INDIRECT_CALL_1(sk->sk_write_space, sk_stream_write_space, sk); } -static void tcp_check_space(struct sock *sk) +/* Caller made space either from: + * 1) Freeing skbs in rtx queues (after tp->snd_una has advanced) + * 2) Sent skbs from output queue (and thus advancing tp->snd_nxt) + * + * We might be able to generate EPOLLOUT to the application if: + * 1) Space consumed in output/rtx queues is below sk->sk_sndbuf/2 + * 2) notsent amount (tp->write_seq - tp->snd_nxt) became + * small enough that tcp_stream_memory_free() decides it + * is time to generate EPOLLOUT. + */ +void tcp_check_space(struct sock *sk) { /* pairs with tcp_poll() */ smp_mb(); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 6366df7aaf2a..6854bb1fb32b 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -531,7 +531,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->tsoffset = treq->ts_off; #ifdef CONFIG_TCP_MD5SIG newtp->md5sig_info = NULL; /*XXX*/ - if (newtp->af_specific->md5_lookup(sk, newsk)) + if (treq->af_specific->req_md5_lookup(sk, req_to_sk(req))) newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED; #endif if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 9ede847f4199..1ca2f28c9981 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -82,6 +82,7 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT, tcp_skb_pcount(skb)); + tcp_check_space(sk); } /* SND.NXT, if window was not shrunk or the amount of shrunk was less than one diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c index fbab921670cc..9a8e014d9b5b 100644 --- a/net/ipv4/tcp_rate.c +++ b/net/ipv4/tcp_rate.c @@ -74,27 +74,32 @@ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb) * * If an ACK (s)acks multiple skbs (e.g., stretched-acks), this function is * called multiple times. We favor the information from the most recently - * sent skb, i.e., the skb with the highest prior_delivered count. + * sent skb, i.e., the skb with the most recently sent time and the highest + * sequence. */ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, struct rate_sample *rs) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_skb_cb *scb = TCP_SKB_CB(skb); + u64 tx_tstamp; if (!scb->tx.delivered_mstamp) return; + tx_tstamp = tcp_skb_timestamp_us(skb); if (!rs->prior_delivered || - after(scb->tx.delivered, rs->prior_delivered)) { + tcp_skb_sent_after(tx_tstamp, tp->first_tx_mstamp, + scb->end_seq, rs->last_end_seq)) { rs->prior_delivered_ce = scb->tx.delivered_ce; rs->prior_delivered = scb->tx.delivered; rs->prior_mstamp = scb->tx.delivered_mstamp; rs->is_app_limited = scb->tx.is_app_limited; rs->is_retrans = scb->sacked & TCPCB_RETRANS; + rs->last_end_seq = scb->end_seq; /* Record send time of most recently ACKed packet: */ - tp->first_tx_mstamp = tcp_skb_timestamp_us(skb); + tp->first_tx_mstamp = tx_tstamp; /* Find the duration of the "send phase" of this window: */ rs->interval_us = tcp_stamp_us_delta(tp->first_tx_mstamp, scb->tx.first_tx_mstamp); diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 55d604c9b3b3..f2120e92caf1 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -482,7 +482,6 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info struct page *page; struct sk_buff *trailer; int tailen = esp->tailen; - unsigned int allocsz; if (x->encap) { int err = esp6_output_encap(x, skb, esp); @@ -491,8 +490,8 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info return err; } - allocsz = ALIGN(skb->data_len + tailen, L1_CACHE_BYTES); - if (allocsz > ESP_SKB_FRAG_MAXSIZE) + if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE || + ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE) goto cow; if (!skb_cloned(skb)) { diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 8753e9cec326..5136959b3dc5 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -724,6 +724,7 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, { struct ip6_tnl *tunnel = netdev_priv(dev); __be16 protocol; + __be16 flags; if (dev->type == ARPHRD_ETHER) IPCB(skb)->flags = 0; @@ -733,16 +734,13 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, else fl6->daddr = tunnel->parms.raddr; - if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen)) - return -ENOMEM; - /* Push GRE header. */ protocol = (dev->type == ARPHRD_ETHER) ? htons(ETH_P_TEB) : proto; if (tunnel->parms.collect_md) { struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; - __be16 flags; + int tun_hlen; tun_info = skb_tunnel_info_txcheck(skb); if (IS_ERR(tun_info) || @@ -760,21 +758,27 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, dsfield = key->tos; flags = key->tun_flags & (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); - tunnel->tun_hlen = gre_calc_hlen(flags); + tun_hlen = gre_calc_hlen(flags); - gre_build_header(skb, tunnel->tun_hlen, + if (skb_cow_head(skb, dev->needed_headroom ?: tun_hlen + tunnel->encap_hlen)) + return -ENOMEM; + + gre_build_header(skb, tun_hlen, flags, protocol, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); } else { - if (tunnel->parms.o_flags & TUNNEL_SEQ) - tunnel->o_seqno++; + if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen)) + return -ENOMEM; + + flags = tunnel->parms.o_flags; - gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags, + gre_build_header(skb, tunnel->tun_hlen, flags, protocol, tunnel->parms.o_key, - htonl(tunnel->o_seqno)); + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) + : 0); } return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu, @@ -1052,7 +1056,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, /* Push GRE header. */ proto = (t->parms.erspan_ver == 1) ? htons(ETH_P_ERSPAN) : htons(ETH_P_ERSPAN2); - gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(t->o_seqno++)); + gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(atomic_fetch_inc(&t->o_seqno))); /* TooBig packet may have updated dst->dev's mtu */ if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu) diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 1da332450d98..8ce60ab89015 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -24,14 +24,13 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff { const struct ipv6hdr *iph = ipv6_hdr(skb); struct sock *sk = sk_to_full_sk(sk_partial); + struct net_device *dev = skb_dst(skb)->dev; struct flow_keys flkeys; unsigned int hh_len; struct dst_entry *dst; int strict = (ipv6_addr_type(&iph->daddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)); struct flowi6 fl6 = { - .flowi6_oif = sk && sk->sk_bound_dev_if ? sk->sk_bound_dev_if : - strict ? skb_dst(skb)->dev->ifindex : 0, .flowi6_mark = skb->mark, .flowi6_uid = sock_net_uid(net, sk), .daddr = iph->daddr, @@ -39,6 +38,13 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff }; int err; + if (sk && sk->sk_bound_dev_if) + fl6.flowi6_oif = sk->sk_bound_dev_if; + else if (strict) + fl6.flowi6_oif = dev->ifindex; + else + fl6.flowi6_oif = l3mdev_master_ifindex(dev); + fib6_rules_early_flow_dissect(net, skb, &fl6, &flkeys); dst = ip6_route_output(net, sk, &fl6); err = dst->error; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 169e9df6d172..c4b6ce017d5e 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3292,6 +3292,7 @@ static int ip6_dst_gc(struct dst_ops *ops) int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity; int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout; unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc; + unsigned int val; int entries; entries = dst_entries_get_fast(ops); @@ -3302,13 +3303,13 @@ static int ip6_dst_gc(struct dst_ops *ops) entries <= rt_max_size) goto out; - net->ipv6.ip6_rt_gc_expire++; - fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, true); + fib6_run_gc(atomic_inc_return(&net->ipv6.ip6_rt_gc_expire), net, true); entries = dst_entries_get_slow(ops); if (entries < ops->gc_thresh) - net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1; + atomic_set(&net->ipv6.ip6_rt_gc_expire, rt_gc_timeout >> 1); out: - net->ipv6.ip6_rt_gc_expire -= net->ipv6.ip6_rt_gc_expire>>rt_elasticity; + val = atomic_read(&net->ipv6.ip6_rt_gc_expire); + atomic_set(&net->ipv6.ip6_rt_gc_expire, val - (val >> rt_elasticity)); return entries > rt_max_size; } @@ -6509,7 +6510,7 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40; net->ipv6.sysctl.skip_notify_on_dev_down = 0; - net->ipv6.ip6_rt_gc_expire = 30*HZ; + atomic_set(&net->ipv6.ip6_rt_gc_expire, 30*HZ); ret = 0; out: diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index d1b61d00368e..9cc123f000fb 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -170,7 +170,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, sk, skb); + req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, + &tcp_request_sock_ipv6_ops, sk, skb); if (!req) goto out; diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c index 4eb8892fb2ff..ca10916340b0 100644 --- a/net/l3mdev/l3mdev.c +++ b/net/l3mdev/l3mdev.c @@ -147,7 +147,7 @@ int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex) dev = dev_get_by_index_rcu(net, ifindex); while (dev && !netif_is_l3_master(dev)) - dev = netdev_master_upper_dev_get(dev); + dev = netdev_master_upper_dev_get_rcu(dev); return dev ? dev->ifindex : 0; } diff --git a/net/mctp/device.c b/net/mctp/device.c index f49be882e98e..99a3bda8852f 100644 --- a/net/mctp/device.c +++ b/net/mctp/device.c @@ -313,6 +313,7 @@ void mctp_dev_hold(struct mctp_dev *mdev) void mctp_dev_put(struct mctp_dev *mdev) { if (mdev && refcount_dec_and_test(&mdev->refs)) { + kfree(mdev->addrs); dev_put(mdev->dev); kfree_rcu(mdev, rcu); } @@ -441,7 +442,6 @@ static void mctp_unregister(struct net_device *dev) mctp_route_remove_dev(mdev); mctp_neigh_remove_dev(mdev); - kfree(mdev->addrs); mctp_dev_put(mdev); } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 2c467c422dc6..fb67f1ca2495 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1495,7 +1495,7 @@ int __init ip_vs_conn_init(void) pr_info("Connection hash table configured " "(size=%d, memory=%ldKbytes)\n", ip_vs_conn_tab_size, - (long)(ip_vs_conn_tab_size*sizeof(struct list_head))/1024); + (long)(ip_vs_conn_tab_size*sizeof(*ip_vs_conn_tab))/1024); IP_VS_DBG(0, "Each connection entry needs %zd bytes at least\n", sizeof(struct ip_vs_conn)); diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 8ec55cd72572..204a5cdff5b1 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -556,24 +556,14 @@ static bool tcp_in_window(struct nf_conn *ct, } } - } else if (((state->state == TCP_CONNTRACK_SYN_SENT - && dir == IP_CT_DIR_ORIGINAL) - || (state->state == TCP_CONNTRACK_SYN_RECV - && dir == IP_CT_DIR_REPLY)) - && after(end, sender->td_end)) { + } else if (tcph->syn && + after(end, sender->td_end) && + (state->state == TCP_CONNTRACK_SYN_SENT || + state->state == TCP_CONNTRACK_SYN_RECV)) { /* * RFC 793: "if a TCP is reinitialized ... then it need * not wait at all; it must only be sure to use sequence * numbers larger than those recently used." - */ - sender->td_end = - sender->td_maxend = end; - sender->td_maxwin = (win == 0 ? 1 : win); - - tcp_options(skb, dataoff, tcph, sender); - } else if (tcph->syn && dir == IP_CT_DIR_REPLY && - state->state == TCP_CONNTRACK_SYN_SENT) { - /* Retransmitted syn-ack, or syn (simultaneous open). * * Re-init state for this direction, just like for the first * syn(-ack) reply, it might differ in seq, ack or tcp options. @@ -581,7 +571,8 @@ static bool tcp_in_window(struct nf_conn *ct, tcp_init_sender(sender, receiver, skb, dataoff, tcph, end, win); - if (!tcph->ack) + + if (dir == IP_CT_DIR_REPLY && !tcph->ack) return true; } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 3e1afd10a9b6..55aa55b252b2 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -823,7 +823,7 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, -#if IS_ENABLED(CONFIG_NFT_FLOW_OFFLOAD) +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) [NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD] = { .procname = "nf_flowtable_udp_timeout", .maxlen = sizeof(unsigned int), diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index d600a566da32..7325bee7d144 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -349,7 +349,11 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, *ext = &rbe->ext; return -EEXIST; } else { - p = &parent->rb_left; + overlap = false; + if (nft_rbtree_interval_end(rbe)) + p = &parent->rb_left; + else + p = &parent->rb_right; } } diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 6d9e8e0a3a7d..05ae5a338b6f 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -54,6 +54,32 @@ nft_sock_get_eval_cgroupv2(u32 *dest, struct sock *sk, const struct nft_pktinfo } #endif +static struct sock *nft_socket_do_lookup(const struct nft_pktinfo *pkt) +{ + const struct net_device *indev = nft_in(pkt); + const struct sk_buff *skb = pkt->skb; + struct sock *sk = NULL; + + if (!indev) + return NULL; + + switch (nft_pf(pkt)) { + case NFPROTO_IPV4: + sk = nf_sk_lookup_slow_v4(nft_net(pkt), skb, indev); + break; +#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) + case NFPROTO_IPV6: + sk = nf_sk_lookup_slow_v6(nft_net(pkt), skb, indev); + break; +#endif + default: + WARN_ON_ONCE(1); + break; + } + + return sk; +} + static void nft_socket_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -67,20 +93,7 @@ static void nft_socket_eval(const struct nft_expr *expr, sk = NULL; if (!sk) - switch(nft_pf(pkt)) { - case NFPROTO_IPV4: - sk = nf_sk_lookup_slow_v4(nft_net(pkt), skb, nft_in(pkt)); - break; -#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) - case NFPROTO_IPV6: - sk = nf_sk_lookup_slow_v6(nft_net(pkt), skb, nft_in(pkt)); - break; -#endif - default: - WARN_ON_ONCE(1); - regs->verdict.code = NFT_BREAK; - return; - } + sk = nft_socket_do_lookup(pkt); if (!sk) { regs->verdict.code = NFT_BREAK; @@ -224,6 +237,16 @@ static bool nft_socket_reduce(struct nft_regs_track *track, return nft_expr_reduce_bitwise(track, expr); } +static int nft_socket_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) +{ + return nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_LOCAL_OUT)); +} + static struct nft_expr_type nft_socket_type; static const struct nft_expr_ops nft_socket_ops = { .type = &nft_socket_type, @@ -231,6 +254,7 @@ static const struct nft_expr_ops nft_socket_ops = { .eval = nft_socket_eval, .init = nft_socket_init, .dump = nft_socket_dump, + .validate = nft_socket_validate, .reduce = nft_socket_reduce, }; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 47a876ccd288..05a3795eac8e 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2263,6 +2263,13 @@ static int netlink_dump(struct sock *sk) * single netdev. The outcome is MSG_TRUNC error. */ skb_reserve(skb, skb_tailroom(skb) - alloc_size); + + /* Make sure malicious BPF programs can not read unitialized memory + * from skb->head -> skb->data + */ + skb_reset_network_header(skb); + skb_reset_mac_header(skb); + netlink_skb_set_owner_r(skb, sk); if (nlk->dump_done_errno > 0) { diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 7176156d3844..4c09cf8a0ab2 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2465,7 +2465,7 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa, new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2); if (new_acts_size > MAX_ACTIONS_BUFSIZE) { - if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) { + if ((next_offset + req_size) > MAX_ACTIONS_BUFSIZE) { OVS_NLERR(log, "Flow action size exceeds max %u", MAX_ACTIONS_BUFSIZE); return ERR_PTR(-EMSGSIZE); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c39c09899fd0..002d2b9c69dd 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2858,8 +2858,9 @@ tpacket_error: status = TP_STATUS_SEND_REQUEST; err = po->xmit(skb); - if (unlikely(err > 0)) { - err = net_xmit_errno(err); + if (unlikely(err != 0)) { + if (err > 0) + err = net_xmit_errno(err); if (err && __packet_get_status(po, ph) == TP_STATUS_AVAILABLE) { /* skb was destructed already */ @@ -3060,8 +3061,12 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->no_fcs = 1; err = po->xmit(skb); - if (err > 0 && (err = net_xmit_errno(err)) != 0) - goto out_unlock; + if (unlikely(err != 0)) { + if (err > 0) + err = net_xmit_errno(err); + if (err) + goto out_unlock; + } dev_put(dev); diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c index f15d6942da45..cc7e30733feb 100644 --- a/net/rxrpc/net_ns.c +++ b/net/rxrpc/net_ns.c @@ -113,7 +113,9 @@ static __net_exit void rxrpc_exit_net(struct net *net) struct rxrpc_net *rxnet = rxrpc_net(net); rxnet->live = false; + del_timer_sync(&rxnet->peer_keepalive_timer); cancel_work_sync(&rxnet->peer_keepalive_work); + /* Remove the timer again as the worker may have restarted it. */ del_timer_sync(&rxnet->peer_keepalive_timer); rxrpc_destroy_all_calls(rxnet); rxrpc_destroy_all_connections(rxnet); diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index cf5649292ee0..4d27300c287c 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -386,14 +386,19 @@ static int u32_init(struct tcf_proto *tp) return 0; } -static int u32_destroy_key(struct tc_u_knode *n, bool free_pf) +static void __u32_destroy_key(struct tc_u_knode *n) { struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); tcf_exts_destroy(&n->exts); - tcf_exts_put_net(&n->exts); if (ht && --ht->refcnt == 0) kfree(ht); + kfree(n); +} + +static void u32_destroy_key(struct tc_u_knode *n, bool free_pf) +{ + tcf_exts_put_net(&n->exts); #ifdef CONFIG_CLS_U32_PERF if (free_pf) free_percpu(n->pf); @@ -402,8 +407,7 @@ static int u32_destroy_key(struct tc_u_knode *n, bool free_pf) if (free_pf) free_percpu(n->pcpu_success); #endif - kfree(n); - return 0; + __u32_destroy_key(n); } /* u32_delete_key_rcu should be called when free'ing a copied @@ -811,10 +815,6 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, new->flags = n->flags; RCU_INIT_POINTER(new->ht_down, ht); - /* bump reference count as long as we hold pointer to structure */ - if (ht) - ht->refcnt++; - #ifdef CONFIG_CLS_U32_PERF /* Statistics may be incremented by readers during update * so we must keep them in tact. When the node is later destroyed @@ -836,6 +836,10 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, return NULL; } + /* bump reference count as long as we hold pointer to structure */ + if (ht) + ht->refcnt++; + return new; } @@ -900,13 +904,13 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, extack); if (err) { - u32_destroy_key(new, false); + __u32_destroy_key(new); return err; } err = u32_replace_hw_knode(tp, new, flags, extack); if (err) { - u32_destroy_key(new, false); + __u32_destroy_key(new); return err; } diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index b3815b568e8e..463c4a58d2c3 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -458,6 +458,10 @@ void sctp_generate_reconf_event(struct timer_list *t) goto out_unlock; } + /* This happens when the response arrives after the timer is triggered. */ + if (!asoc->strreset_chunk) + goto out_unlock; + error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT, SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_RECONF), asoc->state, asoc->ep, asoc, diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 14ddc40149e8..fce16b9d6e1a 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -243,11 +243,27 @@ struct proto smc_proto6 = { }; EXPORT_SYMBOL_GPL(smc_proto6); +static void smc_fback_restore_callbacks(struct smc_sock *smc) +{ + struct sock *clcsk = smc->clcsock->sk; + + write_lock_bh(&clcsk->sk_callback_lock); + clcsk->sk_user_data = NULL; + + smc_clcsock_restore_cb(&clcsk->sk_state_change, &smc->clcsk_state_change); + smc_clcsock_restore_cb(&clcsk->sk_data_ready, &smc->clcsk_data_ready); + smc_clcsock_restore_cb(&clcsk->sk_write_space, &smc->clcsk_write_space); + smc_clcsock_restore_cb(&clcsk->sk_error_report, &smc->clcsk_error_report); + + write_unlock_bh(&clcsk->sk_callback_lock); +} + static void smc_restore_fallback_changes(struct smc_sock *smc) { if (smc->clcsock->file) { /* non-accepted sockets have no file yet */ smc->clcsock->file->private_data = smc->sk.sk_socket; smc->clcsock->file = NULL; + smc_fback_restore_callbacks(smc); } } @@ -373,6 +389,7 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, sk->sk_prot->hash(sk); sk_refcnt_debug_inc(sk); mutex_init(&smc->clcsock_release_lock); + smc_init_saved_callbacks(smc); return sk; } @@ -744,47 +761,73 @@ out: static void smc_fback_state_change(struct sock *clcsk) { - struct smc_sock *smc = - smc_clcsock_user_data(clcsk); + struct smc_sock *smc; - if (!smc) - return; - smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_state_change); + read_lock_bh(&clcsk->sk_callback_lock); + smc = smc_clcsock_user_data(clcsk); + if (smc) + smc_fback_forward_wakeup(smc, clcsk, + smc->clcsk_state_change); + read_unlock_bh(&clcsk->sk_callback_lock); } static void smc_fback_data_ready(struct sock *clcsk) { - struct smc_sock *smc = - smc_clcsock_user_data(clcsk); + struct smc_sock *smc; - if (!smc) - return; - smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_data_ready); + read_lock_bh(&clcsk->sk_callback_lock); + smc = smc_clcsock_user_data(clcsk); + if (smc) + smc_fback_forward_wakeup(smc, clcsk, + smc->clcsk_data_ready); + read_unlock_bh(&clcsk->sk_callback_lock); } static void smc_fback_write_space(struct sock *clcsk) { - struct smc_sock *smc = - smc_clcsock_user_data(clcsk); + struct smc_sock *smc; - if (!smc) - return; - smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_write_space); + read_lock_bh(&clcsk->sk_callback_lock); + smc = smc_clcsock_user_data(clcsk); + if (smc) + smc_fback_forward_wakeup(smc, clcsk, + smc->clcsk_write_space); + read_unlock_bh(&clcsk->sk_callback_lock); } static void smc_fback_error_report(struct sock *clcsk) { - struct smc_sock *smc = - smc_clcsock_user_data(clcsk); + struct smc_sock *smc; - if (!smc) - return; - smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_error_report); + read_lock_bh(&clcsk->sk_callback_lock); + smc = smc_clcsock_user_data(clcsk); + if (smc) + smc_fback_forward_wakeup(smc, clcsk, + smc->clcsk_error_report); + read_unlock_bh(&clcsk->sk_callback_lock); +} + +static void smc_fback_replace_callbacks(struct smc_sock *smc) +{ + struct sock *clcsk = smc->clcsock->sk; + + write_lock_bh(&clcsk->sk_callback_lock); + clcsk->sk_user_data = (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); + + smc_clcsock_replace_cb(&clcsk->sk_state_change, smc_fback_state_change, + &smc->clcsk_state_change); + smc_clcsock_replace_cb(&clcsk->sk_data_ready, smc_fback_data_ready, + &smc->clcsk_data_ready); + smc_clcsock_replace_cb(&clcsk->sk_write_space, smc_fback_write_space, + &smc->clcsk_write_space); + smc_clcsock_replace_cb(&clcsk->sk_error_report, smc_fback_error_report, + &smc->clcsk_error_report); + + write_unlock_bh(&clcsk->sk_callback_lock); } static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code) { - struct sock *clcsk; int rc = 0; mutex_lock(&smc->clcsock_release_lock); @@ -792,10 +835,7 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code) rc = -EBADF; goto out; } - clcsk = smc->clcsock->sk; - if (smc->use_fallback) - goto out; smc->use_fallback = true; smc->fallback_rsn = reason_code; smc_stat_fallback(smc); @@ -810,18 +850,7 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code) * in smc sk->sk_wq and they should be woken up * as clcsock's wait queue is woken up. */ - smc->clcsk_state_change = clcsk->sk_state_change; - smc->clcsk_data_ready = clcsk->sk_data_ready; - smc->clcsk_write_space = clcsk->sk_write_space; - smc->clcsk_error_report = clcsk->sk_error_report; - - clcsk->sk_state_change = smc_fback_state_change; - clcsk->sk_data_ready = smc_fback_data_ready; - clcsk->sk_write_space = smc_fback_write_space; - clcsk->sk_error_report = smc_fback_error_report; - - smc->clcsock->sk->sk_user_data = - (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); + smc_fback_replace_callbacks(smc); } out: mutex_unlock(&smc->clcsock_release_lock); @@ -1475,6 +1504,8 @@ static void smc_connect_work(struct work_struct *work) smc->sk.sk_state = SMC_CLOSED; if (rc == -EPIPE || rc == -EAGAIN) smc->sk.sk_err = EPIPE; + else if (rc == -ECONNREFUSED) + smc->sk.sk_err = ECONNREFUSED; else if (signal_pending(current)) smc->sk.sk_err = -sock_intr_errno(timeo); sock_put(&smc->sk); /* passive closing */ @@ -1594,6 +1625,19 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) * function; switch it back to the original sk_data_ready function */ new_clcsock->sk->sk_data_ready = lsmc->clcsk_data_ready; + + /* if new clcsock has also inherited the fallback-specific callback + * functions, switch them back to the original ones. + */ + if (lsmc->use_fallback) { + if (lsmc->clcsk_state_change) + new_clcsock->sk->sk_state_change = lsmc->clcsk_state_change; + if (lsmc->clcsk_write_space) + new_clcsock->sk->sk_write_space = lsmc->clcsk_write_space; + if (lsmc->clcsk_error_report) + new_clcsock->sk->sk_error_report = lsmc->clcsk_error_report; + } + (*new_smc)->clcsock = new_clcsock; out: return rc; @@ -2353,17 +2397,20 @@ out: static void smc_clcsock_data_ready(struct sock *listen_clcsock) { - struct smc_sock *lsmc = - smc_clcsock_user_data(listen_clcsock); + struct smc_sock *lsmc; + read_lock_bh(&listen_clcsock->sk_callback_lock); + lsmc = smc_clcsock_user_data(listen_clcsock); if (!lsmc) - return; + goto out; lsmc->clcsk_data_ready(listen_clcsock); if (lsmc->sk.sk_state == SMC_LISTEN) { sock_hold(&lsmc->sk); /* sock_put in smc_tcp_listen_work() */ if (!queue_work(smc_tcp_ls_wq, &lsmc->tcp_listen_work)) sock_put(&lsmc->sk); } +out: + read_unlock_bh(&listen_clcsock->sk_callback_lock); } static int smc_listen(struct socket *sock, int backlog) @@ -2395,10 +2442,12 @@ static int smc_listen(struct socket *sock, int backlog) /* save original sk_data_ready function and establish * smc-specific sk_data_ready function */ - smc->clcsk_data_ready = smc->clcsock->sk->sk_data_ready; - smc->clcsock->sk->sk_data_ready = smc_clcsock_data_ready; + write_lock_bh(&smc->clcsock->sk->sk_callback_lock); smc->clcsock->sk->sk_user_data = (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); + smc_clcsock_replace_cb(&smc->clcsock->sk->sk_data_ready, + smc_clcsock_data_ready, &smc->clcsk_data_ready); + write_unlock_bh(&smc->clcsock->sk->sk_callback_lock); /* save original ops */ smc->ori_af_ops = inet_csk(smc->clcsock->sk)->icsk_af_ops; @@ -2413,7 +2462,11 @@ static int smc_listen(struct socket *sock, int backlog) rc = kernel_listen(smc->clcsock, backlog); if (rc) { - smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready; + write_lock_bh(&smc->clcsock->sk->sk_callback_lock); + smc_clcsock_restore_cb(&smc->clcsock->sk->sk_data_ready, + &smc->clcsk_data_ready); + smc->clcsock->sk->sk_user_data = NULL; + write_unlock_bh(&smc->clcsock->sk->sk_callback_lock); goto out; } sk->sk_max_ack_backlog = backlog; @@ -2674,8 +2727,10 @@ static int smc_shutdown(struct socket *sock, int how) if (smc->use_fallback) { rc = kernel_sock_shutdown(smc->clcsock, how); sk->sk_shutdown = smc->clcsock->sk->sk_shutdown; - if (sk->sk_shutdown == SHUTDOWN_MASK) + if (sk->sk_shutdown == SHUTDOWN_MASK) { sk->sk_state = SMC_CLOSED; + sock_put(sk); + } goto out; } switch (how) { diff --git a/net/smc/smc.h b/net/smc/smc.h index ea0620529ebe..5ed765ea0c73 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -288,12 +288,41 @@ static inline struct smc_sock *smc_sk(const struct sock *sk) return (struct smc_sock *)sk; } +static inline void smc_init_saved_callbacks(struct smc_sock *smc) +{ + smc->clcsk_state_change = NULL; + smc->clcsk_data_ready = NULL; + smc->clcsk_write_space = NULL; + smc->clcsk_error_report = NULL; +} + static inline struct smc_sock *smc_clcsock_user_data(const struct sock *clcsk) { return (struct smc_sock *) ((uintptr_t)clcsk->sk_user_data & ~SK_USER_DATA_NOCOPY); } +/* save target_cb in saved_cb, and replace target_cb with new_cb */ +static inline void smc_clcsock_replace_cb(void (**target_cb)(struct sock *), + void (*new_cb)(struct sock *), + void (**saved_cb)(struct sock *)) +{ + /* only save once */ + if (!*saved_cb) + *saved_cb = *target_cb; + *target_cb = new_cb; +} + +/* restore target_cb to saved_cb, and reset saved_cb to NULL */ +static inline void smc_clcsock_restore_cb(void (**target_cb)(struct sock *), + void (**saved_cb)(struct sock *)) +{ + if (!*saved_cb) + return; + *target_cb = *saved_cb; + *saved_cb = NULL; +} + extern struct workqueue_struct *smc_hs_wq; /* wq for handshake work */ extern struct workqueue_struct *smc_close_wq; /* wq for close work */ diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 676cb2333d3c..31db7438857c 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -214,8 +214,11 @@ again: sk->sk_state = SMC_CLOSED; sk->sk_state_change(sk); /* wake up accept */ if (smc->clcsock && smc->clcsock->sk) { - smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready; + write_lock_bh(&smc->clcsock->sk->sk_callback_lock); + smc_clcsock_restore_cb(&smc->clcsock->sk->sk_data_ready, + &smc->clcsk_data_ready); smc->clcsock->sk->sk_user_data = NULL; + write_unlock_bh(&smc->clcsock->sk->sk_callback_lock); rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); } smc_close_cleanup_listen(sk); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 12f7b56771d9..af875ad4a822 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -483,11 +483,13 @@ handle_error: copy = min_t(size_t, size, (pfrag->size - pfrag->offset)); copy = min_t(size_t, copy, (max_open_record_len - record->len)); - rc = tls_device_copy_data(page_address(pfrag->page) + - pfrag->offset, copy, msg_iter); - if (rc) - goto handle_error; - tls_append_frag(record, pfrag, copy); + if (copy) { + rc = tls_device_copy_data(page_address(pfrag->page) + + pfrag->offset, copy, msg_iter); + if (rc) + goto handle_error; + tls_append_frag(record, pfrag, copy); + } size -= copy; if (!size) { diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 2c34caee0fd1..3a9348030e20 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -639,7 +639,7 @@ static int __xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len if (sk_can_busy_loop(sk)) sk_busy_loop(sk, 1); /* only support non-blocking sockets */ - if (xsk_no_wakeup(sk)) + if (xs->zc && xsk_no_wakeup(sk)) return 0; pool = xs->pool; @@ -967,6 +967,19 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) xp_get_pool(umem_xs->pool); xs->pool = umem_xs->pool; + + /* If underlying shared umem was created without Tx + * ring, allocate Tx descs array that Tx batching API + * utilizes + */ + if (xs->tx && !xs->pool->tx_descs) { + err = xp_alloc_tx_descs(xs->pool, xs); + if (err) { + xp_put_pool(xs->pool); + sockfd_put(sock); + goto out_unlock; + } + } } xdp_get_umem(umem_xs->umem); diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index af040ffa14ff..87bdd71c7bb6 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -42,6 +42,16 @@ void xp_destroy(struct xsk_buff_pool *pool) kvfree(pool); } +int xp_alloc_tx_descs(struct xsk_buff_pool *pool, struct xdp_sock *xs) +{ + pool->tx_descs = kvcalloc(xs->tx->nentries, sizeof(*pool->tx_descs), + GFP_KERNEL); + if (!pool->tx_descs) + return -ENOMEM; + + return 0; +} + struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, struct xdp_umem *umem) { @@ -59,11 +69,9 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, if (!pool->heads) goto out; - if (xs->tx) { - pool->tx_descs = kcalloc(xs->tx->nentries, sizeof(*pool->tx_descs), GFP_KERNEL); - if (!pool->tx_descs) + if (xs->tx) + if (xp_alloc_tx_descs(pool, xs)) goto out; - } pool->chunk_mask = ~((u64)umem->chunk_size - 1); pool->addrs_cnt = umem->size; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 19aa994f5d2c..00bd0ecff5a1 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2593,12 +2593,14 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { __u32 mark = 0; + int oif; if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m) mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]); family = xfrm[i]->props.family; - dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif, + oif = fl->flowi_oif ? : fl->flowi_l3mdev; + dst = xfrm_dst_lookup(xfrm[i], tos, oif, &saddr, &daddr, family, mark); err = PTR_ERR(dst); if (IS_ERR(dst)) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 9717e6f6fb31..33c1ed581522 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -231,7 +231,7 @@ objtool_args = \ $(if $(part-of-module), --module) \ $(if $(CONFIG_X86_KERNEL_IBT), --lto --ibt) \ $(if $(CONFIG_FRAME_POINTER),, --no-fp) \ - $(if $(CONFIG_GCOV_KERNEL)$(CONFIG_LTO_CLANG), --no-unreachable)\ + $(if $(CONFIG_GCOV_KERNEL), --no-unreachable) \ $(if $(CONFIG_RETPOLINE), --retpoline) \ $(if $(CONFIG_X86_SMAP), --uaccess) \ $(if $(CONFIG_FTRACE_MCOUNT_USE_OBJTOOL), --mcount) \ diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 8caabddf817c..e6906f79833d 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -111,7 +111,8 @@ static bool is_ignored_symbol(const char *name, char type) ".L", /* local labels, .LBB,.Ltmpxxx,.L__unnamed_xx,.LASANPC, etc. */ "__crc_", /* modversions */ "__efistub_", /* arm64 EFI stub namespace */ - "__kvm_nvhe_", /* arm64 non-VHE KVM namespace */ + "__kvm_nvhe_$", /* arm64 local symbols in non-VHE KVM namespace */ + "__kvm_nvhe_.L", /* arm64 local symbols in non-VHE KVM namespace */ "__AArch64ADRPThunk_", /* arm64 lld */ "__ARMV5PILongThunk_", /* arm lld */ "__ARMV7PILongThunk_", diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 20f44504a644..9361a1ef02c9 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -140,7 +140,7 @@ objtool_link() if ! is_enabled CONFIG_FRAME_POINTER; then objtoolopt="${objtoolopt} --no-fp" fi - if is_enabled CONFIG_GCOV_KERNEL || is_enabled CONFIG_LTO_CLANG; then + if is_enabled CONFIG_GCOV_KERNEL; then objtoolopt="${objtoolopt} --no-unreachable" fi if is_enabled CONFIG_RETPOLINE; then diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c index 48b8ed752b69..3f35972e1cf7 100644 --- a/sound/hda/hdac_i915.c +++ b/sound/hda/hdac_i915.c @@ -127,11 +127,10 @@ static int i915_gfx_present(struct pci_dev *hdac_pci) display_dev = pci_get_class(class, display_dev); if (display_dev && display_dev->vendor == PCI_VENDOR_ID_INTEL && - connectivity_check(display_dev, hdac_pci)) + connectivity_check(display_dev, hdac_pci)) { + pci_dev_put(display_dev); match = true; - - pci_dev_put(display_dev); - + } } while (!match && display_dev); return match; diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index 8b0a16ba27d3..a8fe01764b25 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -424,6 +424,15 @@ static const struct config_entry config_table[] = { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, .device = 0x54c8, }, + /* RaptorLake-P */ + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = 0x51ca, + }, + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = 0x51cb, + }, #endif }; diff --git a/sound/oss/dmasound/dmasound_core.c b/sound/oss/dmasound/dmasound_core.c index 9c48f3a9e3d1..164335d3c200 100644 --- a/sound/oss/dmasound/dmasound_core.c +++ b/sound/oss/dmasound/dmasound_core.c @@ -1428,7 +1428,7 @@ void dmasound_deinit(void) unregister_sound_dsp(sq_unit); } -static int dmasound_setup(char *str) +static int __maybe_unused dmasound_setup(char *str) { int ints[6], size; diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 3e086eebf88d..31fe41795571 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1395,7 +1395,7 @@ static int hdmi_find_pcm_slot(struct hdmi_spec *spec, last_try: /* the last try; check the empty slots in pins */ - for (i = 0; i < spec->num_nids; i++) { + for (i = 0; i < spec->pcm_used; i++) { if (!test_bit(i, &spec->pcm_bitmap)) return i; } @@ -2325,7 +2325,9 @@ static int generic_hdmi_build_pcms(struct hda_codec *codec) * dev_num is the device entry number in a pin */ - if (codec->mst_no_extra_pcms) + if (spec->dyn_pcm_no_legacy && codec->mst_no_extra_pcms) + pcm_num = spec->num_cvts; + else if (codec->mst_no_extra_pcms) pcm_num = spec->num_nids; else pcm_num = spec->num_nids + spec->dev_num - 1; @@ -4551,6 +4553,7 @@ HDA_CODEC_ENTRY(0x80862819, "DG2 HDMI", patch_i915_adlp_hdmi), HDA_CODEC_ENTRY(0x8086281a, "Jasperlake HDMI", patch_i915_icl_hdmi), HDA_CODEC_ENTRY(0x8086281b, "Elkhartlake HDMI", patch_i915_icl_hdmi), HDA_CODEC_ENTRY(0x8086281c, "Alderlake-P HDMI", patch_i915_adlp_hdmi), +HDA_CODEC_ENTRY(0x8086281f, "Raptorlake-P HDMI", patch_i915_adlp_hdmi), HDA_CODEC_ENTRY(0x80862880, "CedarTrail HDMI", patch_generic_hdmi), HDA_CODEC_ENTRY(0x80862882, "Valleyview2 HDMI", patch_i915_byt_hdmi), HDA_CODEC_ENTRY(0x80862883, "Braswell HDMI", patch_i915_byt_hdmi), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 62fbf3772b41..4c0c593f3c0a 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7006,6 +7006,7 @@ enum { ALC285_FIXUP_LEGION_Y9000X_AUTOMUTE, ALC287_FIXUP_LEGION_16ACHG6, ALC287_FIXUP_CS35L41_I2C_2, + ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED, ALC245_FIXUP_CS35L41_SPI_2, ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED, ALC245_FIXUP_CS35L41_SPI_4, @@ -8769,6 +8770,12 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = cs35l41_fixup_i2c_two, }, + [ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED] = { + .type = HDA_FIXUP_FUNC, + .v.func = cs35l41_fixup_i2c_two, + .chained = true, + .chain_id = ALC285_FIXUP_HP_MUTE_LED, + }, [ALC245_FIXUP_CS35L41_SPI_2] = { .type = HDA_FIXUP_FUNC, .v.func = cs35l41_fixup_spi_two, @@ -9025,9 +9032,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8981, "HP Elite Dragonfly G3", ALC245_FIXUP_CS35L41_SPI_4), SND_PCI_QUIRK(0x103c, 0x898e, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x898f, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2), - SND_PCI_QUIRK(0x103c, 0x8991, "HP EliteBook 845 G9", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8991, "HP EliteBook 845 G9", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8992, "HP EliteBook 845 G9", ALC287_FIXUP_CS35L41_I2C_2), - SND_PCI_QUIRK(0x103c, 0x8994, "HP EliteBook 855 G9", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8994, "HP EliteBook 855 G9", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8995, "HP EliteBook 855 G9", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x89a4, "HP ProBook 440 G9", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x89a6, "HP ProBook 450 G9", ALC236_FIXUP_HP_GPIO_LED), @@ -9163,6 +9170,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x8562, "Clevo NH[57][0-9]RZ[Q]", ALC269_FIXUP_DMIC), SND_PCI_QUIRK(0x1558, 0x8668, "Clevo NP50B[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x866d, "Clevo NP5[05]PN[HJK]", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x867c, "Clevo NP7[01]PNP", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x867d, "Clevo NP7[01]PN[HJK]", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8680, "Clevo NJ50LU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8686, "Clevo NH50[CZ]U", ALC256_FIXUP_MIC_NO_PRESENCE_AND_RESUME), diff --git a/sound/soc/atmel/sam9g20_wm8731.c b/sound/soc/atmel/sam9g20_wm8731.c index 33e43013ff77..0d639a33ad96 100644 --- a/sound/soc/atmel/sam9g20_wm8731.c +++ b/sound/soc/atmel/sam9g20_wm8731.c @@ -46,35 +46,6 @@ */ #undef ENABLE_MIC_INPUT -static struct clk *mclk; - -static int at91sam9g20ek_set_bias_level(struct snd_soc_card *card, - struct snd_soc_dapm_context *dapm, - enum snd_soc_bias_level level) -{ - static int mclk_on; - int ret = 0; - - switch (level) { - case SND_SOC_BIAS_ON: - case SND_SOC_BIAS_PREPARE: - if (!mclk_on) - ret = clk_enable(mclk); - if (ret == 0) - mclk_on = 1; - break; - - case SND_SOC_BIAS_OFF: - case SND_SOC_BIAS_STANDBY: - if (mclk_on) - clk_disable(mclk); - mclk_on = 0; - break; - } - - return ret; -} - static const struct snd_soc_dapm_widget at91sam9g20ek_dapm_widgets[] = { SND_SOC_DAPM_MIC("Int Mic", NULL), SND_SOC_DAPM_SPK("Ext Spk", NULL), @@ -135,7 +106,6 @@ static struct snd_soc_card snd_soc_at91sam9g20ek = { .owner = THIS_MODULE, .dai_link = &at91sam9g20ek_dai, .num_links = 1, - .set_bias_level = at91sam9g20ek_set_bias_level, .dapm_widgets = at91sam9g20ek_dapm_widgets, .num_dapm_widgets = ARRAY_SIZE(at91sam9g20ek_dapm_widgets), @@ -148,7 +118,6 @@ static int at91sam9g20ek_audio_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; struct device_node *codec_np, *cpu_np; - struct clk *pllb; struct snd_soc_card *card = &snd_soc_at91sam9g20ek; int ret; @@ -162,31 +131,6 @@ static int at91sam9g20ek_audio_probe(struct platform_device *pdev) return -EINVAL; } - /* - * Codec MCLK is supplied by PCK0 - set it up. - */ - mclk = clk_get(NULL, "pck0"); - if (IS_ERR(mclk)) { - dev_err(&pdev->dev, "Failed to get MCLK\n"); - ret = PTR_ERR(mclk); - goto err; - } - - pllb = clk_get(NULL, "pllb"); - if (IS_ERR(pllb)) { - dev_err(&pdev->dev, "Failed to get PLLB\n"); - ret = PTR_ERR(pllb); - goto err_mclk; - } - ret = clk_set_parent(mclk, pllb); - clk_put(pllb); - if (ret != 0) { - dev_err(&pdev->dev, "Failed to set MCLK parent\n"); - goto err_mclk; - } - - clk_set_rate(mclk, MCLK_RATE); - card->dev = &pdev->dev; /* Parse device node info */ @@ -230,9 +174,6 @@ static int at91sam9g20ek_audio_probe(struct platform_device *pdev) return ret; -err_mclk: - clk_put(mclk); - mclk = NULL; err: atmel_ssc_put_audio(0); return ret; @@ -242,8 +183,6 @@ static int at91sam9g20ek_audio_remove(struct platform_device *pdev) { struct snd_soc_card *card = platform_get_drvdata(pdev); - clk_disable(mclk); - mclk = NULL; snd_soc_unregister_card(card); atmel_ssc_put_audio(0); diff --git a/sound/soc/codecs/cs35l41-lib.c b/sound/soc/codecs/cs35l41-lib.c index e5a56bcbb223..aa6823fbd1a4 100644 --- a/sound/soc/codecs/cs35l41-lib.c +++ b/sound/soc/codecs/cs35l41-lib.c @@ -822,8 +822,8 @@ int cs35l41_otp_unpack(struct device *dev, struct regmap *regmap) word_offset = otp_map_match->word_offset; for (i = 0; i < otp_map_match->num_elements; i++) { - dev_dbg(dev, "bitoffset= %d, word_offset=%d, bit_sum mod 32=%d\n", - bit_offset, word_offset, bit_sum % 32); + dev_dbg(dev, "bitoffset= %d, word_offset=%d, bit_sum mod 32=%d otp_map[i].size = %d\n", + bit_offset, word_offset, bit_sum % 32, otp_map[i].size); if (bit_offset + otp_map[i].size - 1 >= 32) { otp_val = (otp_mem[word_offset] & GENMASK(31, bit_offset)) >> bit_offset; @@ -831,12 +831,14 @@ int cs35l41_otp_unpack(struct device *dev, struct regmap *regmap) GENMASK(bit_offset + otp_map[i].size - 33, 0)) << (32 - bit_offset); bit_offset += otp_map[i].size - 32; - } else { + } else if (bit_offset + otp_map[i].size - 1 >= 0) { otp_val = (otp_mem[word_offset] & GENMASK(bit_offset + otp_map[i].size - 1, bit_offset) ) >> bit_offset; bit_offset += otp_map[i].size; - } + } else /* both bit_offset and otp_map[i].size are 0 */ + otp_val = 0; + bit_sum += otp_map[i].size; if (bit_offset == 32) { diff --git a/sound/soc/codecs/lpass-rx-macro.c b/sound/soc/codecs/lpass-rx-macro.c index 6884ae505e33..3143f9cd7277 100644 --- a/sound/soc/codecs/lpass-rx-macro.c +++ b/sound/soc/codecs/lpass-rx-macro.c @@ -3566,12 +3566,16 @@ static int rx_macro_probe(struct platform_device *pdev) return PTR_ERR(rx->pds); base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(base)) - return PTR_ERR(base); + if (IS_ERR(base)) { + ret = PTR_ERR(base); + goto err; + } rx->regmap = devm_regmap_init_mmio(dev, base, &rx_regmap_config); - if (IS_ERR(rx->regmap)) - return PTR_ERR(rx->regmap); + if (IS_ERR(rx->regmap)) { + ret = PTR_ERR(rx->regmap); + goto err; + } dev_set_drvdata(dev, rx); @@ -3632,6 +3636,8 @@ err_mclk: err_dcodec: clk_disable_unprepare(rx->macro); err: + lpass_macro_pds_exit(rx->pds); + return ret; } diff --git a/sound/soc/codecs/lpass-tx-macro.c b/sound/soc/codecs/lpass-tx-macro.c index 714a411d5337..55503ba480bb 100644 --- a/sound/soc/codecs/lpass-tx-macro.c +++ b/sound/soc/codecs/lpass-tx-macro.c @@ -1828,8 +1828,10 @@ static int tx_macro_probe(struct platform_device *pdev) return PTR_ERR(tx->pds); base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(base)) - return PTR_ERR(base); + if (IS_ERR(base)) { + ret = PTR_ERR(base); + goto err; + } /* Update defaults for lpass sc7280 */ if (of_device_is_compatible(np, "qcom,sc7280-lpass-tx-macro")) { @@ -1846,8 +1848,10 @@ static int tx_macro_probe(struct platform_device *pdev) } tx->regmap = devm_regmap_init_mmio(dev, base, &tx_regmap_config); - if (IS_ERR(tx->regmap)) - return PTR_ERR(tx->regmap); + if (IS_ERR(tx->regmap)) { + ret = PTR_ERR(tx->regmap); + goto err; + } dev_set_drvdata(dev, tx); @@ -1907,6 +1911,8 @@ err_mclk: err_dcodec: clk_disable_unprepare(tx->macro); err: + lpass_macro_pds_exit(tx->pds); + return ret; } diff --git a/sound/soc/codecs/lpass-va-macro.c b/sound/soc/codecs/lpass-va-macro.c index f3cb596058e0..d18b56e60433 100644 --- a/sound/soc/codecs/lpass-va-macro.c +++ b/sound/soc/codecs/lpass-va-macro.c @@ -1434,8 +1434,10 @@ static int va_macro_probe(struct platform_device *pdev) va->dmic_clk_div = VA_MACRO_CLK_DIV_2; } else { ret = va_macro_validate_dmic_sample_rate(sample_rate, va); - if (!ret) - return -EINVAL; + if (!ret) { + ret = -EINVAL; + goto err; + } } base = devm_platform_ioremap_resource(pdev, 0); @@ -1492,6 +1494,8 @@ err_mclk: err_dcodec: clk_disable_unprepare(va->macro); err: + lpass_macro_pds_exit(va->pds); + return ret; } diff --git a/sound/soc/codecs/msm8916-wcd-digital.c b/sound/soc/codecs/msm8916-wcd-digital.c index 9ad7fc0baf07..20a07c92b2fc 100644 --- a/sound/soc/codecs/msm8916-wcd-digital.c +++ b/sound/soc/codecs/msm8916-wcd-digital.c @@ -1206,9 +1206,16 @@ static int msm8916_wcd_digital_probe(struct platform_device *pdev) dev_set_drvdata(dev, priv); - return devm_snd_soc_register_component(dev, &msm8916_wcd_digital, + ret = devm_snd_soc_register_component(dev, &msm8916_wcd_digital, msm8916_wcd_digital_dai, ARRAY_SIZE(msm8916_wcd_digital_dai)); + if (ret) + goto err_mclk; + + return 0; + +err_mclk: + clk_disable_unprepare(priv->mclk); err_clk: clk_disable_unprepare(priv->ahbclk); return ret; diff --git a/sound/soc/codecs/rk817_codec.c b/sound/soc/codecs/rk817_codec.c index 8fffe378618d..cce6f4e7992f 100644 --- a/sound/soc/codecs/rk817_codec.c +++ b/sound/soc/codecs/rk817_codec.c @@ -489,7 +489,7 @@ static int rk817_platform_probe(struct platform_device *pdev) rk817_codec_parse_dt_property(&pdev->dev, rk817_codec_data); - rk817_codec_data->mclk = clk_get(pdev->dev.parent, "mclk"); + rk817_codec_data->mclk = devm_clk_get(pdev->dev.parent, "mclk"); if (IS_ERR(rk817_codec_data->mclk)) { dev_dbg(&pdev->dev, "Unable to get mclk\n"); ret = -ENXIO; diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index be68d573a490..2b6c6d6b9771 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -1100,6 +1100,15 @@ void rt5682_jack_detect_handler(struct work_struct *work) return; } + if (rt5682->is_sdw) { + if (pm_runtime_status_suspended(rt5682->slave->dev.parent)) { + dev_dbg(&rt5682->slave->dev, + "%s: parent device is pm_runtime_status_suspended, skipping jack detection\n", + __func__); + return; + } + } + dapm = snd_soc_component_get_dapm(rt5682->component); snd_soc_dapm_mutex_lock(dapm); @@ -2822,14 +2831,11 @@ static int rt5682_bclk_set_rate(struct clk_hw *hw, unsigned long rate, for_each_component_dais(component, dai) if (dai->id == RT5682_AIF1) - break; - if (!dai) { - dev_err(rt5682->i2c_dev, "dai %d not found in component\n", - RT5682_AIF1); - return -ENODEV; - } + return rt5682_set_bclk1_ratio(dai, factor); - return rt5682_set_bclk1_ratio(dai, factor); + dev_err(rt5682->i2c_dev, "dai %d not found in component\n", + RT5682_AIF1); + return -ENODEV; } static const struct clk_ops rt5682_dai_clk_ops[RT5682_DAI_NUM_CLKS] = { diff --git a/sound/soc/codecs/rt5682s.c b/sound/soc/codecs/rt5682s.c index 1cba8ec7cedb..b55f3ac3a267 100644 --- a/sound/soc/codecs/rt5682s.c +++ b/sound/soc/codecs/rt5682s.c @@ -2687,14 +2687,11 @@ static int rt5682s_bclk_set_rate(struct clk_hw *hw, unsigned long rate, for_each_component_dais(component, dai) if (dai->id == RT5682S_AIF1) - break; - if (!dai) { - dev_err(component->dev, "dai %d not found in component\n", - RT5682S_AIF1); - return -ENODEV; - } + return rt5682s_set_bclk1_ratio(dai, factor); - return rt5682s_set_bclk1_ratio(dai, factor); + dev_err(component->dev, "dai %d not found in component\n", + RT5682S_AIF1); + return -ENODEV; } static const struct clk_ops rt5682s_dai_clk_ops[RT5682S_DAI_NUM_CLKS] = { diff --git a/sound/soc/codecs/rt711.c b/sound/soc/codecs/rt711.c index 6770825d037a..ea25fd58d43a 100644 --- a/sound/soc/codecs/rt711.c +++ b/sound/soc/codecs/rt711.c @@ -245,6 +245,13 @@ static void rt711_jack_detect_handler(struct work_struct *work) if (!rt711->component->card->instantiated) return; + if (pm_runtime_status_suspended(rt711->slave->dev.parent)) { + dev_dbg(&rt711->slave->dev, + "%s: parent device is pm_runtime_status_suspended, skipping jack detection\n", + __func__); + return; + } + reg = RT711_VERB_GET_PIN_SENSE | RT711_HP_OUT; ret = regmap_read(rt711->regmap, reg, &jack_status); if (ret < 0) diff --git a/sound/soc/codecs/wcd934x.c b/sound/soc/codecs/wcd934x.c index 1e75e93cf28f..6298ebe96e94 100644 --- a/sound/soc/codecs/wcd934x.c +++ b/sound/soc/codecs/wcd934x.c @@ -1274,29 +1274,7 @@ static int wcd934x_set_sido_input_src(struct wcd934x_codec *wcd, int sido_src) if (sido_src == wcd->sido_input_src) return 0; - if (sido_src == SIDO_SOURCE_INTERNAL) { - regmap_update_bits(wcd->regmap, WCD934X_ANA_BUCK_CTL, - WCD934X_ANA_BUCK_HI_ACCU_EN_MASK, 0); - usleep_range(100, 110); - regmap_update_bits(wcd->regmap, WCD934X_ANA_BUCK_CTL, - WCD934X_ANA_BUCK_HI_ACCU_PRE_ENX_MASK, 0x0); - usleep_range(100, 110); - regmap_update_bits(wcd->regmap, WCD934X_ANA_RCO, - WCD934X_ANA_RCO_BG_EN_MASK, 0); - usleep_range(100, 110); - regmap_update_bits(wcd->regmap, WCD934X_ANA_BUCK_CTL, - WCD934X_ANA_BUCK_PRE_EN1_MASK, - WCD934X_ANA_BUCK_PRE_EN1_ENABLE); - usleep_range(100, 110); - regmap_update_bits(wcd->regmap, WCD934X_ANA_BUCK_CTL, - WCD934X_ANA_BUCK_PRE_EN2_MASK, - WCD934X_ANA_BUCK_PRE_EN2_ENABLE); - usleep_range(100, 110); - regmap_update_bits(wcd->regmap, WCD934X_ANA_BUCK_CTL, - WCD934X_ANA_BUCK_HI_ACCU_EN_MASK, - WCD934X_ANA_BUCK_HI_ACCU_ENABLE); - usleep_range(100, 110); - } else if (sido_src == SIDO_SOURCE_RCO_BG) { + if (sido_src == SIDO_SOURCE_RCO_BG) { regmap_update_bits(wcd->regmap, WCD934X_ANA_RCO, WCD934X_ANA_RCO_BG_EN_MASK, WCD934X_ANA_RCO_BG_ENABLE); @@ -1382,8 +1360,6 @@ static int wcd934x_disable_ana_bias_and_syclk(struct wcd934x_codec *wcd) regmap_update_bits(wcd->regmap, WCD934X_CLK_SYS_MCLK_PRG, WCD934X_EXT_CLK_BUF_EN_MASK | WCD934X_MCLK_EN_MASK, 0x0); - wcd934x_set_sido_input_src(wcd, SIDO_SOURCE_INTERNAL); - regmap_update_bits(wcd->regmap, WCD934X_ANA_BIAS, WCD934X_ANA_BIAS_EN_MASK, 0); regmap_update_bits(wcd->regmap, WCD934X_ANA_BIAS, diff --git a/sound/soc/codecs/wm8731.c b/sound/soc/codecs/wm8731.c index 5d4949c2ec9b..b14c6d104e6d 100644 --- a/sound/soc/codecs/wm8731.c +++ b/sound/soc/codecs/wm8731.c @@ -602,7 +602,7 @@ static int wm8731_hw_init(struct device *dev, struct wm8731_priv *wm8731) ret = wm8731_reset(wm8731->regmap); if (ret < 0) { dev_err(dev, "Failed to issue reset: %d\n", ret); - goto err_regulator_enable; + goto err; } /* Clear POWEROFF, keep everything else disabled */ @@ -619,10 +619,7 @@ static int wm8731_hw_init(struct device *dev, struct wm8731_priv *wm8731) regcache_mark_dirty(wm8731->regmap); -err_regulator_enable: - /* Regulators will be enabled by bias management */ - regulator_bulk_disable(ARRAY_SIZE(wm8731->supplies), wm8731->supplies); - +err: return ret; } @@ -760,21 +757,27 @@ static int wm8731_i2c_probe(struct i2c_client *i2c, ret = PTR_ERR(wm8731->regmap); dev_err(&i2c->dev, "Failed to allocate register map: %d\n", ret); - return ret; + goto err_regulator_enable; } ret = wm8731_hw_init(&i2c->dev, wm8731); if (ret != 0) - return ret; + goto err_regulator_enable; ret = devm_snd_soc_register_component(&i2c->dev, &soc_component_dev_wm8731, &wm8731_dai, 1); if (ret != 0) { dev_err(&i2c->dev, "Failed to register CODEC: %d\n", ret); - return ret; + goto err_regulator_enable; } return 0; + +err_regulator_enable: + /* Regulators will be enabled by bias management */ + regulator_bulk_disable(ARRAY_SIZE(wm8731->supplies), wm8731->supplies); + + return ret; } static const struct i2c_device_id wm8731_i2c_id[] = { diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index 4650a6931a94..ffc24afb5a7a 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -372,7 +372,7 @@ static int fsl_sai_set_bclk(struct snd_soc_dai *dai, bool tx, u32 freq) continue; if (ratio == 1 && !support_1_1_ratio) continue; - else if (ratio & 1) + if ((ratio & 1) && ratio > 1) continue; diff = abs((long)clk_rate - ratio * freq); diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index 8e037835bc58..f2157944247f 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -364,13 +364,15 @@ static int asoc_simple_set_tdm(struct snd_soc_dai *dai, struct snd_pcm_hw_params *params) { int sample_bits = params_width(params); - int slot_width = simple_dai->slot_width; - int slot_count = simple_dai->slots; + int slot_width, slot_count; int i, ret; if (!simple_dai || !simple_dai->tdm_width_map) return 0; + slot_width = simple_dai->slot_width; + slot_count = simple_dai->slots; + if (slot_width == 0) slot_width = sample_bits; diff --git a/sound/soc/intel/boards/sof_es8336.c b/sound/soc/intel/boards/sof_es8336.c index 5e0529aa4f1d..9d617831dd20 100644 --- a/sound/soc/intel/boards/sof_es8336.c +++ b/sound/soc/intel/boards/sof_es8336.c @@ -27,9 +27,11 @@ #define SOF_ES8336_SSP_CODEC(quirk) ((quirk) & GENMASK(3, 0)) #define SOF_ES8336_SSP_CODEC_MASK (GENMASK(3, 0)) -#define SOF_ES8336_TGL_GPIO_QUIRK BIT(4) +#define SOF_ES8336_SPEAKERS_EN_GPIO1_QUIRK BIT(4) #define SOF_ES8336_ENABLE_DMIC BIT(5) #define SOF_ES8336_JD_INVERTED BIT(6) +#define SOF_ES8336_HEADPHONE_GPIO BIT(7) +#define SOC_ES8336_HEADSET_MIC1 BIT(8) static unsigned long quirk; @@ -39,7 +41,7 @@ MODULE_PARM_DESC(quirk, "Board-specific quirk override"); struct sof_es8336_private { struct device *codec_dev; - struct gpio_desc *gpio_pa; + struct gpio_desc *gpio_speakers, *gpio_headphone; struct snd_soc_jack jack; struct list_head hdmi_pcm_list; bool speaker_en; @@ -51,19 +53,31 @@ struct sof_hdmi_pcm { int device; }; -static const struct acpi_gpio_params pa_enable_gpio = { 0, 0, true }; -static const struct acpi_gpio_mapping acpi_es8336_gpios[] = { - { "pa-enable-gpios", &pa_enable_gpio, 1 }, +static const struct acpi_gpio_params enable_gpio0 = { 0, 0, true }; +static const struct acpi_gpio_params enable_gpio1 = { 1, 0, true }; + +static const struct acpi_gpio_mapping acpi_speakers_enable_gpio0[] = { + { "speakers-enable-gpios", &enable_gpio0, 1 }, { } }; -static const struct acpi_gpio_params quirk_pa_enable_gpio = { 1, 0, true }; -static const struct acpi_gpio_mapping quirk_acpi_es8336_gpios[] = { - { "pa-enable-gpios", &quirk_pa_enable_gpio, 1 }, +static const struct acpi_gpio_mapping acpi_speakers_enable_gpio1[] = { + { "speakers-enable-gpios", &enable_gpio1, 1 }, +}; + +static const struct acpi_gpio_mapping acpi_enable_both_gpios[] = { + { "speakers-enable-gpios", &enable_gpio0, 1 }, + { "headphone-enable-gpios", &enable_gpio1, 1 }, { } }; -static const struct acpi_gpio_mapping *gpio_mapping = acpi_es8336_gpios; +static const struct acpi_gpio_mapping acpi_enable_both_gpios_rev_order[] = { + { "speakers-enable-gpios", &enable_gpio1, 1 }, + { "headphone-enable-gpios", &enable_gpio0, 1 }, + { } +}; + +static const struct acpi_gpio_mapping *gpio_mapping = acpi_speakers_enable_gpio0; static void log_quirks(struct device *dev) { @@ -71,10 +85,14 @@ static void log_quirks(struct device *dev) dev_info(dev, "quirk SSP%ld\n", SOF_ES8336_SSP_CODEC(quirk)); if (quirk & SOF_ES8336_ENABLE_DMIC) dev_info(dev, "quirk DMIC enabled\n"); - if (quirk & SOF_ES8336_TGL_GPIO_QUIRK) - dev_info(dev, "quirk TGL GPIO enabled\n"); + if (quirk & SOF_ES8336_SPEAKERS_EN_GPIO1_QUIRK) + dev_info(dev, "Speakers GPIO1 quirk enabled\n"); + if (quirk & SOF_ES8336_HEADPHONE_GPIO) + dev_info(dev, "quirk headphone GPIO enabled\n"); if (quirk & SOF_ES8336_JD_INVERTED) dev_info(dev, "quirk JD inverted enabled\n"); + if (quirk & SOC_ES8336_HEADSET_MIC1) + dev_info(dev, "quirk headset at mic1 port enabled\n"); } static int sof_es8316_speaker_power_event(struct snd_soc_dapm_widget *w, @@ -83,12 +101,23 @@ static int sof_es8316_speaker_power_event(struct snd_soc_dapm_widget *w, struct snd_soc_card *card = w->dapm->card; struct sof_es8336_private *priv = snd_soc_card_get_drvdata(card); + if (priv->speaker_en == !SND_SOC_DAPM_EVENT_ON(event)) + return 0; + + priv->speaker_en = !SND_SOC_DAPM_EVENT_ON(event); + + if (SND_SOC_DAPM_EVENT_ON(event)) + msleep(70); + + gpiod_set_value_cansleep(priv->gpio_speakers, priv->speaker_en); + + if (!(quirk & SOF_ES8336_HEADPHONE_GPIO)) + return 0; + if (SND_SOC_DAPM_EVENT_ON(event)) - priv->speaker_en = false; - else - priv->speaker_en = true; + msleep(70); - gpiod_set_value_cansleep(priv->gpio_pa, priv->speaker_en); + gpiod_set_value_cansleep(priv->gpio_headphone, priv->speaker_en); return 0; } @@ -114,18 +143,23 @@ static const struct snd_soc_dapm_route sof_es8316_audio_map[] = { /* * There is no separate speaker output instead the speakers are muxed to - * the HP outputs. The mux is controlled by the "Speaker Power" supply. + * the HP outputs. The mux is controlled Speaker and/or headphone switch. */ {"Speaker", NULL, "HPOL"}, {"Speaker", NULL, "HPOR"}, {"Speaker", NULL, "Speaker Power"}, }; -static const struct snd_soc_dapm_route sof_es8316_intmic_in1_map[] = { +static const struct snd_soc_dapm_route sof_es8316_headset_mic2_map[] = { {"MIC1", NULL, "Internal Mic"}, {"MIC2", NULL, "Headset Mic"}, }; +static const struct snd_soc_dapm_route sof_es8316_headset_mic1_map[] = { + {"MIC2", NULL, "Internal Mic"}, + {"MIC1", NULL, "Headset Mic"}, +}; + static const struct snd_soc_dapm_route dmic_map[] = { /* digital mics */ {"DMic", NULL, "SoC DMIC"}, @@ -199,8 +233,13 @@ static int sof_es8316_init(struct snd_soc_pcm_runtime *runtime) card->dapm.idle_bias_off = true; - custom_map = sof_es8316_intmic_in1_map; - num_routes = ARRAY_SIZE(sof_es8316_intmic_in1_map); + if (quirk & SOC_ES8336_HEADSET_MIC1) { + custom_map = sof_es8316_headset_mic1_map; + num_routes = ARRAY_SIZE(sof_es8316_headset_mic1_map); + } else { + custom_map = sof_es8316_headset_mic2_map; + num_routes = ARRAY_SIZE(sof_es8316_headset_mic2_map); + } ret = snd_soc_dapm_add_routes(&card->dapm, custom_map, num_routes); if (ret) @@ -233,8 +272,14 @@ static int sof_es8336_quirk_cb(const struct dmi_system_id *id) { quirk = (unsigned long)id->driver_data; - if (quirk & SOF_ES8336_TGL_GPIO_QUIRK) - gpio_mapping = quirk_acpi_es8336_gpios; + if (quirk & SOF_ES8336_HEADPHONE_GPIO) { + if (quirk & SOF_ES8336_SPEAKERS_EN_GPIO1_QUIRK) + gpio_mapping = acpi_enable_both_gpios; + else + gpio_mapping = acpi_enable_both_gpios_rev_order; + } else if (quirk & SOF_ES8336_SPEAKERS_EN_GPIO1_QUIRK) { + gpio_mapping = acpi_speakers_enable_gpio1; + } return 1; } @@ -257,7 +302,16 @@ static const struct dmi_system_id sof_es8336_quirk_table[] = { DMI_MATCH(DMI_SYS_VENDOR, "IP3 tech"), DMI_MATCH(DMI_BOARD_NAME, "WN1"), }, - .driver_data = (void *)(SOF_ES8336_TGL_GPIO_QUIRK) + .driver_data = (void *)(SOF_ES8336_SPEAKERS_EN_GPIO1_QUIRK) + }, + { + .callback = sof_es8336_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HUAWEI"), + DMI_MATCH(DMI_BOARD_NAME, "BOHB-WAX9-PCB-B2"), + }, + .driver_data = (void *)(SOF_ES8336_HEADPHONE_GPIO | + SOC_ES8336_HEADSET_MIC1) }, {} }; @@ -585,10 +639,17 @@ static int sof_es8336_probe(struct platform_device *pdev) if (ret) dev_warn(codec_dev, "unable to add GPIO mapping table\n"); - priv->gpio_pa = gpiod_get_optional(codec_dev, "pa-enable", GPIOD_OUT_LOW); - if (IS_ERR(priv->gpio_pa)) { - ret = dev_err_probe(dev, PTR_ERR(priv->gpio_pa), - "could not get pa-enable GPIO\n"); + priv->gpio_speakers = gpiod_get_optional(codec_dev, "speakers-enable", GPIOD_OUT_LOW); + if (IS_ERR(priv->gpio_speakers)) { + ret = dev_err_probe(dev, PTR_ERR(priv->gpio_speakers), + "could not get speakers-enable GPIO\n"); + goto err_put_codec; + } + + priv->gpio_headphone = gpiod_get_optional(codec_dev, "headphone-enable", GPIOD_OUT_LOW); + if (IS_ERR(priv->gpio_headphone)) { + ret = dev_err_probe(dev, PTR_ERR(priv->gpio_headphone), + "could not get headphone-enable GPIO\n"); goto err_put_codec; } @@ -604,7 +665,7 @@ static int sof_es8336_probe(struct platform_device *pdev) ret = devm_snd_soc_register_card(dev, card); if (ret) { - gpiod_put(priv->gpio_pa); + gpiod_put(priv->gpio_speakers); dev_err(dev, "snd_soc_register_card failed: %d\n", ret); goto err_put_codec; } @@ -622,7 +683,7 @@ static int sof_es8336_remove(struct platform_device *pdev) struct snd_soc_card *card = platform_get_drvdata(pdev); struct sof_es8336_private *priv = snd_soc_card_get_drvdata(card); - gpiod_put(priv->gpio_pa); + gpiod_put(priv->gpio_speakers); device_remove_software_node(priv->codec_dev); put_device(priv->codec_dev); diff --git a/sound/soc/intel/boards/sof_rt5682.c b/sound/soc/intel/boards/sof_rt5682.c index ebec4d15edaa..7126fcb63d90 100644 --- a/sound/soc/intel/boards/sof_rt5682.c +++ b/sound/soc/intel/boards/sof_rt5682.c @@ -212,6 +212,19 @@ static const struct dmi_system_id sof_rt5682_quirk_table[] = { SOF_SSP_BT_OFFLOAD_PRESENT), }, + { + .callback = sof_rt5682_quirk_cb, + .matches = { + DMI_MATCH(DMI_PRODUCT_FAMILY, "Google_Brya"), + DMI_MATCH(DMI_OEM_STRING, "AUDIO-MAX98360_ALC5682I_I2S_AMP_SSP2"), + }, + .driver_data = (void *)(SOF_RT5682_MCLK_EN | + SOF_RT5682_SSP_CODEC(0) | + SOF_SPEAKER_AMP_PRESENT | + SOF_MAX98360A_SPEAKER_AMP_PRESENT | + SOF_RT5682_SSP_AMP(2) | + SOF_RT5682_NUM_HDMIDEV(4)), + }, {} }; diff --git a/sound/soc/intel/common/soc-acpi-intel-tgl-match.c b/sound/soc/intel/common/soc-acpi-intel-tgl-match.c index 6edc9b7108cd..ef19150e7b2e 100644 --- a/sound/soc/intel/common/soc-acpi-intel-tgl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-tgl-match.c @@ -132,13 +132,13 @@ static const struct snd_soc_acpi_adr_device mx8373_1_adr[] = { { .adr = 0x000123019F837300ull, .num_endpoints = 1, - .endpoints = &spk_l_endpoint, + .endpoints = &spk_r_endpoint, .name_prefix = "Right" }, { .adr = 0x000127019F837300ull, .num_endpoints = 1, - .endpoints = &spk_r_endpoint, + .endpoints = &spk_l_endpoint, .name_prefix = "Left" } }; diff --git a/sound/soc/meson/aiu-acodec-ctrl.c b/sound/soc/meson/aiu-acodec-ctrl.c index 27a6d3259c50..22e181646bc3 100644 --- a/sound/soc/meson/aiu-acodec-ctrl.c +++ b/sound/soc/meson/aiu-acodec-ctrl.c @@ -193,6 +193,9 @@ static const struct snd_soc_component_driver aiu_acodec_ctrl_component = { .of_xlate_dai_name = aiu_acodec_of_xlate_dai_name, .endianness = 1, .non_legacy_dai_naming = 1, +#ifdef CONFIG_DEBUG_FS + .debugfs_prefix = "acodec", +#endif }; int aiu_acodec_ctrl_register_component(struct device *dev) diff --git a/sound/soc/meson/aiu-codec-ctrl.c b/sound/soc/meson/aiu-codec-ctrl.c index c3ea733fce91..59ee66fc2bcd 100644 --- a/sound/soc/meson/aiu-codec-ctrl.c +++ b/sound/soc/meson/aiu-codec-ctrl.c @@ -140,6 +140,9 @@ static const struct snd_soc_component_driver aiu_hdmi_ctrl_component = { .of_xlate_dai_name = aiu_hdmi_of_xlate_dai_name, .endianness = 1, .non_legacy_dai_naming = 1, +#ifdef CONFIG_DEBUG_FS + .debugfs_prefix = "hdmi", +#endif }; int aiu_hdmi_ctrl_register_component(struct device *dev) diff --git a/sound/soc/meson/aiu.c b/sound/soc/meson/aiu.c index d299a70db7e5..88e611e64d14 100644 --- a/sound/soc/meson/aiu.c +++ b/sound/soc/meson/aiu.c @@ -103,6 +103,9 @@ static const struct snd_soc_component_driver aiu_cpu_component = { .pointer = aiu_fifo_pointer, .probe = aiu_cpu_component_probe, .remove = aiu_cpu_component_remove, +#ifdef CONFIG_DEBUG_FS + .debugfs_prefix = "cpu", +#endif }; static struct snd_soc_dai_driver aiu_cpu_dai_drv[] = { diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index ce153ac2c3ab..8c7da82a62ca 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -2587,6 +2587,11 @@ int snd_soc_component_initialize(struct snd_soc_component *component, component->dev = dev; component->driver = driver; +#ifdef CONFIG_DEBUG_FS + if (!component->debugfs_prefix) + component->debugfs_prefix = driver->debugfs_prefix; +#endif + return 0; } EXPORT_SYMBOL_GPL(snd_soc_component_initialize); diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index b435b5c4cfb7..ca917a849c42 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -1687,8 +1687,7 @@ static void dapm_seq_run(struct snd_soc_card *card, switch (w->id) { case snd_soc_dapm_pre: if (!w->event) - list_for_each_entry_safe_continue(w, n, list, - power_list); + continue; if (event == SND_SOC_DAPM_STREAM_START) ret = w->event(w, @@ -1700,8 +1699,7 @@ static void dapm_seq_run(struct snd_soc_card *card, case snd_soc_dapm_post: if (!w->event) - list_for_each_entry_safe_continue(w, n, list, - power_list); + continue; if (event == SND_SOC_DAPM_STREAM_START) ret = w->event(w, diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 9a954680d492..11c9853e9e80 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -1214,7 +1214,7 @@ static int dpcm_be_connect(struct snd_soc_pcm_runtime *fe, be_substream->pcm->nonatomic = 1; } - dpcm = kzalloc(sizeof(struct snd_soc_dpcm), GFP_ATOMIC); + dpcm = kzalloc(sizeof(struct snd_soc_dpcm), GFP_KERNEL); if (!dpcm) return -ENOMEM; diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 72e50df7052c..3bb90a819650 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -1436,12 +1436,12 @@ static int soc_tplg_dapm_widget_create(struct soc_tplg *tplg, template.num_kcontrols = le32_to_cpu(w->num_kcontrols); kc = devm_kcalloc(tplg->dev, le32_to_cpu(w->num_kcontrols), sizeof(*kc), GFP_KERNEL); if (!kc) - goto err; + goto hdr_err; kcontrol_type = devm_kcalloc(tplg->dev, le32_to_cpu(w->num_kcontrols), sizeof(unsigned int), GFP_KERNEL); if (!kcontrol_type) - goto err; + goto hdr_err; for (i = 0; i < le32_to_cpu(w->num_kcontrols); i++) { control_hdr = (struct snd_soc_tplg_ctl_hdr *)tplg->pos; diff --git a/sound/soc/sof/sof-pci-dev.c b/sound/soc/sof/sof-pci-dev.c index 4c9596742844..12f5cff22448 100644 --- a/sound/soc/sof/sof-pci-dev.c +++ b/sound/soc/sof/sof-pci-dev.c @@ -83,7 +83,14 @@ static const struct dmi_system_id sof_tplg_table[] = { }, .driver_data = "sof-adl-max98357a-rt5682-2way.tplg", }, - + { + .callback = sof_tplg_cb, + .matches = { + DMI_MATCH(DMI_PRODUCT_FAMILY, "Google_Brya"), + DMI_MATCH(DMI_OEM_STRING, "AUDIO-MAX98360_ALC5682I_I2S_AMP_SSP2"), + }, + .driver_data = "sof-adl-max98357a-rt5682.tplg", + }, {} }; diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c index 9b11e9795a7a..3e5b319b44c7 100644 --- a/sound/soc/sof/topology.c +++ b/sound/soc/sof/topology.c @@ -904,8 +904,10 @@ static int sof_control_load(struct snd_soc_component *scomp, int index, return -ENOMEM; scontrol->name = kstrdup(hdr->name, GFP_KERNEL); - if (!scontrol->name) + if (!scontrol->name) { + kfree(scontrol); return -ENOMEM; + } scontrol->scomp = scomp; scontrol->access = kc->access; @@ -941,11 +943,13 @@ static int sof_control_load(struct snd_soc_component *scomp, int index, default: dev_warn(scomp->dev, "control type not supported %d:%d:%d\n", hdr->ops.get, hdr->ops.put, hdr->ops.info); + kfree(scontrol->name); kfree(scontrol); return 0; } if (ret < 0) { + kfree(scontrol->name); kfree(scontrol); return ret; } @@ -1068,6 +1072,46 @@ static int sof_connect_dai_widget(struct snd_soc_component *scomp, return 0; } +static void sof_disconnect_dai_widget(struct snd_soc_component *scomp, + struct snd_soc_dapm_widget *w) +{ + struct snd_soc_card *card = scomp->card; + struct snd_soc_pcm_runtime *rtd; + struct snd_soc_dai *cpu_dai; + int i; + + if (!w->sname) + return; + + list_for_each_entry(rtd, &card->rtd_list, list) { + /* does stream match DAI link ? */ + if (!rtd->dai_link->stream_name || + strcmp(w->sname, rtd->dai_link->stream_name)) + continue; + + switch (w->id) { + case snd_soc_dapm_dai_out: + for_each_rtd_cpu_dais(rtd, i, cpu_dai) { + if (cpu_dai->capture_widget == w) { + cpu_dai->capture_widget = NULL; + break; + } + } + break; + case snd_soc_dapm_dai_in: + for_each_rtd_cpu_dais(rtd, i, cpu_dai) { + if (cpu_dai->playback_widget == w) { + cpu_dai->playback_widget = NULL; + break; + } + } + break; + default: + break; + } + } +} + /* bind PCM ID to host component ID */ static int spcm_bind(struct snd_soc_component *scomp, struct snd_sof_pcm *spcm, int dir) @@ -1353,6 +1397,9 @@ static int sof_widget_unload(struct snd_soc_component *scomp, if (dai) list_del(&dai->list); + + sof_disconnect_dai_widget(scomp, widget); + break; default: break; @@ -1380,6 +1427,7 @@ static int sof_widget_unload(struct snd_soc_component *scomp, } kfree(scontrol->ipc_control_data); list_del(&scontrol->list); + kfree(scontrol->name); kfree(scontrol); } diff --git a/sound/usb/midi.c b/sound/usb/midi.c index 2c01649c70f6..7c6ca2b433a5 100644 --- a/sound/usb/midi.c +++ b/sound/usb/midi.c @@ -1194,6 +1194,7 @@ static void snd_usbmidi_output_drain(struct snd_rawmidi_substream *substream) } while (drain_urbs && timeout); finish_wait(&ep->drain_wait, &wait); } + port->active = 0; spin_unlock_irq(&ep->buffer_lock); } diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index 64f5544d0a0a..7ef7a8abcc2b 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -599,6 +599,10 @@ static const struct usbmix_ctl_map usbmix_ctl_maps[] = { .id = USB_ID(0x0db0, 0x419c), .map = msi_mpg_x570s_carbon_max_wifi_alc4080_map, }, + { /* MSI MAG X570S Torpedo Max */ + .id = USB_ID(0x0db0, 0xa073), + .map = msi_mpg_x570s_carbon_max_wifi_alc4080_map, + }, { /* MSI TRX40 */ .id = USB_ID(0x0db0, 0x543d), .map = trx40_mobo_map, diff --git a/tools/include/linux/arm-smccc.h b/tools/include/linux/arm-smccc.h new file mode 100644 index 000000000000..63ce9bebccd3 --- /dev/null +++ b/tools/include/linux/arm-smccc.h @@ -0,0 +1,193 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2015, Linaro Limited + */ +#ifndef __LINUX_ARM_SMCCC_H +#define __LINUX_ARM_SMCCC_H + +#include <linux/const.h> + +/* + * This file provides common defines for ARM SMC Calling Convention as + * specified in + * https://developer.arm.com/docs/den0028/latest + * + * This code is up-to-date with version DEN 0028 C + */ + +#define ARM_SMCCC_STD_CALL _AC(0,U) +#define ARM_SMCCC_FAST_CALL _AC(1,U) +#define ARM_SMCCC_TYPE_SHIFT 31 + +#define ARM_SMCCC_SMC_32 0 +#define ARM_SMCCC_SMC_64 1 +#define ARM_SMCCC_CALL_CONV_SHIFT 30 + +#define ARM_SMCCC_OWNER_MASK 0x3F +#define ARM_SMCCC_OWNER_SHIFT 24 + +#define ARM_SMCCC_FUNC_MASK 0xFFFF + +#define ARM_SMCCC_IS_FAST_CALL(smc_val) \ + ((smc_val) & (ARM_SMCCC_FAST_CALL << ARM_SMCCC_TYPE_SHIFT)) +#define ARM_SMCCC_IS_64(smc_val) \ + ((smc_val) & (ARM_SMCCC_SMC_64 << ARM_SMCCC_CALL_CONV_SHIFT)) +#define ARM_SMCCC_FUNC_NUM(smc_val) ((smc_val) & ARM_SMCCC_FUNC_MASK) +#define ARM_SMCCC_OWNER_NUM(smc_val) \ + (((smc_val) >> ARM_SMCCC_OWNER_SHIFT) & ARM_SMCCC_OWNER_MASK) + +#define ARM_SMCCC_CALL_VAL(type, calling_convention, owner, func_num) \ + (((type) << ARM_SMCCC_TYPE_SHIFT) | \ + ((calling_convention) << ARM_SMCCC_CALL_CONV_SHIFT) | \ + (((owner) & ARM_SMCCC_OWNER_MASK) << ARM_SMCCC_OWNER_SHIFT) | \ + ((func_num) & ARM_SMCCC_FUNC_MASK)) + +#define ARM_SMCCC_OWNER_ARCH 0 +#define ARM_SMCCC_OWNER_CPU 1 +#define ARM_SMCCC_OWNER_SIP 2 +#define ARM_SMCCC_OWNER_OEM 3 +#define ARM_SMCCC_OWNER_STANDARD 4 +#define ARM_SMCCC_OWNER_STANDARD_HYP 5 +#define ARM_SMCCC_OWNER_VENDOR_HYP 6 +#define ARM_SMCCC_OWNER_TRUSTED_APP 48 +#define ARM_SMCCC_OWNER_TRUSTED_APP_END 49 +#define ARM_SMCCC_OWNER_TRUSTED_OS 50 +#define ARM_SMCCC_OWNER_TRUSTED_OS_END 63 + +#define ARM_SMCCC_FUNC_QUERY_CALL_UID 0xff01 + +#define ARM_SMCCC_QUIRK_NONE 0 +#define ARM_SMCCC_QUIRK_QCOM_A6 1 /* Save/restore register a6 */ + +#define ARM_SMCCC_VERSION_1_0 0x10000 +#define ARM_SMCCC_VERSION_1_1 0x10001 +#define ARM_SMCCC_VERSION_1_2 0x10002 +#define ARM_SMCCC_VERSION_1_3 0x10003 + +#define ARM_SMCCC_1_3_SVE_HINT 0x10000 + +#define ARM_SMCCC_VERSION_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 0) + +#define ARM_SMCCC_ARCH_FEATURES_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 1) + +#define ARM_SMCCC_ARCH_SOC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 2) + +#define ARM_SMCCC_ARCH_WORKAROUND_1 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 0x8000) + +#define ARM_SMCCC_ARCH_WORKAROUND_2 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 0x7fff) + +#define ARM_SMCCC_ARCH_WORKAROUND_3 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 0x3fff) + +#define ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_FUNC_QUERY_CALL_UID) + +/* KVM UID value: 28b46fb6-2ec5-11e9-a9ca-4b564d003a74 */ +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0 0xb66fb428U +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1 0xe911c52eU +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2 0x564bcaa9U +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3 0x743a004dU + +/* KVM "vendor specific" services */ +#define ARM_SMCCC_KVM_FUNC_FEATURES 0 +#define ARM_SMCCC_KVM_FUNC_PTP 1 +#define ARM_SMCCC_KVM_FUNC_FEATURES_2 127 +#define ARM_SMCCC_KVM_NUM_FUNCS 128 + +#define ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_KVM_FUNC_FEATURES) + +#define SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED 1 + +/* + * ptp_kvm is a feature used for time sync between vm and host. + * ptp_kvm module in guest kernel will get service from host using + * this hypercall ID. + */ +#define ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_KVM_FUNC_PTP) + +/* ptp_kvm counter type ID */ +#define KVM_PTP_VIRT_COUNTER 0 +#define KVM_PTP_PHYS_COUNTER 1 + +/* Paravirtualised time calls (defined by ARM DEN0057A) */ +#define ARM_SMCCC_HV_PV_TIME_FEATURES \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_STANDARD_HYP, \ + 0x20) + +#define ARM_SMCCC_HV_PV_TIME_ST \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_STANDARD_HYP, \ + 0x21) + +/* TRNG entropy source calls (defined by ARM DEN0098) */ +#define ARM_SMCCC_TRNG_VERSION \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_STANDARD, \ + 0x50) + +#define ARM_SMCCC_TRNG_FEATURES \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_STANDARD, \ + 0x51) + +#define ARM_SMCCC_TRNG_GET_UUID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_STANDARD, \ + 0x52) + +#define ARM_SMCCC_TRNG_RND32 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_STANDARD, \ + 0x53) + +#define ARM_SMCCC_TRNG_RND64 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_STANDARD, \ + 0x53) + +/* + * Return codes defined in ARM DEN 0070A + * ARM DEN 0070A is now merged/consolidated into ARM DEN 0028 C + */ +#define SMCCC_RET_SUCCESS 0 +#define SMCCC_RET_NOT_SUPPORTED -1 +#define SMCCC_RET_NOT_REQUIRED -2 +#define SMCCC_RET_INVALID_PARAMETER -3 + +#endif /*__LINUX_ARM_SMCCC_H*/ diff --git a/tools/include/linux/slab.h b/tools/include/linux/slab.h index f41d8a0eb1a4..0616409513eb 100644 --- a/tools/include/linux/slab.h +++ b/tools/include/linux/slab.h @@ -28,7 +28,13 @@ static inline void *kzalloc(size_t size, gfp_t gfp) return kmalloc(size, gfp | __GFP_ZERO); } -void *kmem_cache_alloc(struct kmem_cache *cachep, int flags); +struct list_lru; + +void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *, int flags); +static inline void *kmem_cache_alloc(struct kmem_cache *cachep, int flags) +{ + return kmem_cache_alloc_lru(cachep, NULL, flags); +} void kmem_cache_free(struct kmem_cache *cachep, void *objp); struct kmem_cache *kmem_cache_create(const char *name, unsigned int size, diff --git a/tools/objtool/check.c b/tools/objtool/check.c index bd0c2c828940..ca5b74603008 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -184,6 +184,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "do_group_exit", "stop_this_cpu", "__invalid_creds", + "cpu_startup_entry", }; if (!func) @@ -559,12 +560,12 @@ static int add_dead_ends(struct objtool_file *file) else if (reloc->addend == reloc->sym->sec->sh.sh_size) { insn = find_last_insn(file, reloc->sym->sec); if (!insn) { - WARN("can't find unreachable insn at %s+0x%x", + WARN("can't find unreachable insn at %s+0x%lx", reloc->sym->sec->name, reloc->addend); return -1; } } else { - WARN("can't find unreachable insn at %s+0x%x", + WARN("can't find unreachable insn at %s+0x%lx", reloc->sym->sec->name, reloc->addend); return -1; } @@ -594,12 +595,12 @@ reachable: else if (reloc->addend == reloc->sym->sec->sh.sh_size) { insn = find_last_insn(file, reloc->sym->sec); if (!insn) { - WARN("can't find reachable insn at %s+0x%x", + WARN("can't find reachable insn at %s+0x%lx", reloc->sym->sec->name, reloc->addend); return -1; } } else { - WARN("can't find reachable insn at %s+0x%x", + WARN("can't find reachable insn at %s+0x%lx", reloc->sym->sec->name, reloc->addend); return -1; } @@ -1271,12 +1272,19 @@ static bool is_first_func_insn(struct objtool_file *file, struct instruction *in */ static int add_jump_destinations(struct objtool_file *file) { - struct instruction *insn; + struct instruction *insn, *jump_dest; struct reloc *reloc; struct section *dest_sec; unsigned long dest_off; for_each_insn(file, insn) { + if (insn->jump_dest) { + /* + * handle_group_alt() may have previously set + * 'jump_dest' for some alternatives. + */ + continue; + } if (!is_static_jump(insn)) continue; @@ -1291,7 +1299,10 @@ static int add_jump_destinations(struct objtool_file *file) add_retpoline_call(file, insn); continue; } else if (insn->func) { - /* internal or external sibling call (with reloc) */ + /* + * External sibling call or internal sibling call with + * STT_FUNC reloc. + */ add_call_dest(file, insn, reloc->sym, true); continue; } else if (reloc->sym->sec->idx) { @@ -1303,17 +1314,8 @@ static int add_jump_destinations(struct objtool_file *file) continue; } - insn->jump_dest = find_insn(file, dest_sec, dest_off); - if (!insn->jump_dest) { - - /* - * This is a special case where an alt instruction - * jumps past the end of the section. These are - * handled later in handle_group_alt(). - */ - if (!strcmp(insn->sec->name, ".altinstr_replacement")) - continue; - + jump_dest = find_insn(file, dest_sec, dest_off); + if (!jump_dest) { WARN_FUNC("can't find jump dest instruction at %s+0x%lx", insn->sec, insn->offset, dest_sec->name, dest_off); @@ -1323,8 +1325,8 @@ static int add_jump_destinations(struct objtool_file *file) /* * Cross-function jump. */ - if (insn->func && insn->jump_dest->func && - insn->func != insn->jump_dest->func) { + if (insn->func && jump_dest->func && + insn->func != jump_dest->func) { /* * For GCC 8+, create parent/child links for any cold @@ -1342,16 +1344,22 @@ static int add_jump_destinations(struct objtool_file *file) * subfunction is through a jump table. */ if (!strstr(insn->func->name, ".cold") && - strstr(insn->jump_dest->func->name, ".cold")) { - insn->func->cfunc = insn->jump_dest->func; - insn->jump_dest->func->pfunc = insn->func; + strstr(jump_dest->func->name, ".cold")) { + insn->func->cfunc = jump_dest->func; + jump_dest->func->pfunc = insn->func; - } else if (!same_function(insn, insn->jump_dest) && - is_first_func_insn(file, insn->jump_dest)) { - /* internal sibling call (without reloc) */ - add_call_dest(file, insn, insn->jump_dest->func, true); + } else if (!same_function(insn, jump_dest) && + is_first_func_insn(file, jump_dest)) { + /* + * Internal sibling call without reloc or with + * STT_SECTION reloc. + */ + add_call_dest(file, insn, jump_dest->func, true); + continue; } } + + insn->jump_dest = jump_dest; } return 0; @@ -1540,13 +1548,13 @@ static int handle_group_alt(struct objtool_file *file, continue; dest_off = arch_jump_destination(insn); - if (dest_off == special_alt->new_off + special_alt->new_len) + if (dest_off == special_alt->new_off + special_alt->new_len) { insn->jump_dest = next_insn_same_sec(file, last_orig_insn); - - if (!insn->jump_dest) { - WARN_FUNC("can't find alternative jump destination", - insn->sec, insn->offset); - return -1; + if (!insn->jump_dest) { + WARN_FUNC("can't find alternative jump destination", + insn->sec, insn->offset); + return -1; + } } } @@ -2245,14 +2253,14 @@ static int decode_sections(struct objtool_file *file) return ret; /* - * Must be before add_special_section_alts() as that depends on - * jump_dest being set. + * Must be before add_jump_destinations(), which depends on 'func' + * being set for alternatives, to enable proper sibling call detection. */ - ret = add_jump_destinations(file); + ret = add_special_section_alts(file); if (ret) return ret; - ret = add_special_section_alts(file); + ret = add_jump_destinations(file); if (ret) return ret; @@ -3210,9 +3218,8 @@ validate_ibt_reloc(struct objtool_file *file, struct reloc *reloc) static void warn_noendbr(const char *msg, struct section *sec, unsigned long offset, struct instruction *dest) { - WARN_FUNC("%srelocation to !ENDBR: %s+0x%lx", sec, offset, msg, - dest->func ? dest->func->name : dest->sec->name, - dest->func ? dest->offset - dest->func->offset : dest->offset); + WARN_FUNC("%srelocation to !ENDBR: %s", sec, offset, msg, + offstr(dest->sec, dest->offset)); } static void validate_ibt_dest(struct objtool_file *file, struct instruction *insn, @@ -3303,7 +3310,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, while (1) { next_insn = next_insn_to_validate(file, insn); - if (file->c_file && func && insn->func && func != insn->func->pfunc) { + if (func && insn->func && func != insn->func->pfunc) { WARN("%s() falls through to next function %s()", func->name, insn->func->name); return 1; @@ -3816,11 +3823,8 @@ static int validate_ibt(struct objtool_file *file) struct instruction *dest; dest = validate_ibt_reloc(file, reloc); - if (is_data && dest && !dest->noendbr) { - warn_noendbr("data ", reloc->sym->sec, - reloc->sym->offset + reloc->addend, - dest); - } + if (is_data && dest && !dest->noendbr) + warn_noendbr("data ", sec, reloc->offset, dest); } } diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index d7b99a737496..ebf2ba5755c1 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -546,7 +546,7 @@ static struct section *elf_create_reloc_section(struct elf *elf, int reltype); int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset, - unsigned int type, struct symbol *sym, int addend) + unsigned int type, struct symbol *sym, long addend) { struct reloc *reloc; @@ -575,37 +575,180 @@ int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset, return 0; } -int elf_add_reloc_to_insn(struct elf *elf, struct section *sec, - unsigned long offset, unsigned int type, - struct section *insn_sec, unsigned long insn_off) +/* + * Ensure that any reloc section containing references to @sym is marked + * changed such that it will get re-generated in elf_rebuild_reloc_sections() + * with the new symbol index. + */ +static void elf_dirty_reloc_sym(struct elf *elf, struct symbol *sym) +{ + struct section *sec; + + list_for_each_entry(sec, &elf->sections, list) { + struct reloc *reloc; + + if (sec->changed) + continue; + + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym == sym) { + sec->changed = true; + break; + } + } + } +} + +/* + * Move the first global symbol, as per sh_info, into a new, higher symbol + * index. This fees up the shndx for a new local symbol. + */ +static int elf_move_global_symbol(struct elf *elf, struct section *symtab, + struct section *symtab_shndx) { + Elf_Data *data, *shndx_data = NULL; + Elf32_Word first_non_local; struct symbol *sym; - int addend; + Elf_Scn *s; - if (insn_sec->sym) { - sym = insn_sec->sym; - addend = insn_off; + first_non_local = symtab->sh.sh_info; - } else { - /* - * The Clang assembler strips section symbols, so we have to - * reference the function symbol instead: - */ - sym = find_symbol_containing(insn_sec, insn_off); - if (!sym) { - /* - * Hack alert. This happens when we need to reference - * the NOP pad insn immediately after the function. - */ - sym = find_symbol_containing(insn_sec, insn_off - 1); + sym = find_symbol_by_index(elf, first_non_local); + if (!sym) { + WARN("no non-local symbols !?"); + return first_non_local; + } + + s = elf_getscn(elf->elf, symtab->idx); + if (!s) { + WARN_ELF("elf_getscn"); + return -1; + } + + data = elf_newdata(s); + if (!data) { + WARN_ELF("elf_newdata"); + return -1; + } + + data->d_buf = &sym->sym; + data->d_size = sizeof(sym->sym); + data->d_align = 1; + data->d_type = ELF_T_SYM; + + sym->idx = symtab->sh.sh_size / sizeof(sym->sym); + elf_dirty_reloc_sym(elf, sym); + + symtab->sh.sh_info += 1; + symtab->sh.sh_size += data->d_size; + symtab->changed = true; + + if (symtab_shndx) { + s = elf_getscn(elf->elf, symtab_shndx->idx); + if (!s) { + WARN_ELF("elf_getscn"); + return -1; } - if (!sym) { - WARN("can't find symbol containing %s+0x%lx", insn_sec->name, insn_off); + shndx_data = elf_newdata(s); + if (!shndx_data) { + WARN_ELF("elf_newshndx_data"); return -1; } - addend = insn_off - sym->offset; + shndx_data->d_buf = &sym->sec->idx; + shndx_data->d_size = sizeof(Elf32_Word); + shndx_data->d_align = 4; + shndx_data->d_type = ELF_T_WORD; + + symtab_shndx->sh.sh_size += 4; + symtab_shndx->changed = true; + } + + return first_non_local; +} + +static struct symbol * +elf_create_section_symbol(struct elf *elf, struct section *sec) +{ + struct section *symtab, *symtab_shndx; + Elf_Data *shndx_data = NULL; + struct symbol *sym; + Elf32_Word shndx; + + symtab = find_section_by_name(elf, ".symtab"); + if (symtab) { + symtab_shndx = find_section_by_name(elf, ".symtab_shndx"); + if (symtab_shndx) + shndx_data = symtab_shndx->data; + } else { + WARN("no .symtab"); + return NULL; + } + + sym = malloc(sizeof(*sym)); + if (!sym) { + perror("malloc"); + return NULL; + } + memset(sym, 0, sizeof(*sym)); + + sym->idx = elf_move_global_symbol(elf, symtab, symtab_shndx); + if (sym->idx < 0) { + WARN("elf_move_global_symbol"); + return NULL; + } + + sym->name = sec->name; + sym->sec = sec; + + // st_name 0 + sym->sym.st_info = GELF_ST_INFO(STB_LOCAL, STT_SECTION); + // st_other 0 + // st_value 0 + // st_size 0 + shndx = sec->idx; + if (shndx >= SHN_UNDEF && shndx < SHN_LORESERVE) { + sym->sym.st_shndx = shndx; + if (!shndx_data) + shndx = 0; + } else { + sym->sym.st_shndx = SHN_XINDEX; + if (!shndx_data) { + WARN("no .symtab_shndx"); + return NULL; + } + } + + if (!gelf_update_symshndx(symtab->data, shndx_data, sym->idx, &sym->sym, shndx)) { + WARN_ELF("gelf_update_symshndx"); + return NULL; + } + + elf_add_symbol(elf, sym); + + return sym; +} + +int elf_add_reloc_to_insn(struct elf *elf, struct section *sec, + unsigned long offset, unsigned int type, + struct section *insn_sec, unsigned long insn_off) +{ + struct symbol *sym = insn_sec->sym; + int addend = insn_off; + + if (!sym) { + /* + * Due to how weak functions work, we must use section based + * relocations. Symbol based relocations would result in the + * weak and non-weak function annotations being overlaid on the + * non-weak function after linking. + */ + sym = elf_create_section_symbol(elf, insn_sec); + if (!sym) + return -1; + + insn_sec->sym = sym; } return elf_add_reloc(elf, sec, offset, type, sym, addend); diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h index 22ba7e2b816e..9b36802ed86f 100644 --- a/tools/objtool/include/objtool/elf.h +++ b/tools/objtool/include/objtool/elf.h @@ -73,7 +73,7 @@ struct reloc { struct symbol *sym; unsigned long offset; unsigned int type; - int addend; + long addend; int idx; bool jump_table_start; }; @@ -135,7 +135,7 @@ struct elf *elf_open_read(const char *name, int flags); struct section *elf_create_section(struct elf *elf, const char *name, unsigned int sh_flags, size_t entsize, int nr); int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset, - unsigned int type, struct symbol *sym, int addend); + unsigned int type, struct symbol *sym, long addend); int elf_add_reloc_to_insn(struct elf *elf, struct section *sec, unsigned long offset, unsigned int type, struct section *insn_sec, unsigned long insn_off); diff --git a/tools/objtool/include/objtool/objtool.h b/tools/objtool/include/objtool/objtool.h index 7a5c13a78f87..a6e72d916807 100644 --- a/tools/objtool/include/objtool/objtool.h +++ b/tools/objtool/include/objtool/objtool.h @@ -27,7 +27,7 @@ struct objtool_file { struct list_head static_call_list; struct list_head mcount_loc_list; struct list_head endbr_list; - bool ignore_unreachables, c_file, hints, rodata; + bool ignore_unreachables, hints, rodata; unsigned int nr_endbr; unsigned int nr_endbr_int; diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c index b09946f4e1d6..843ff3c2f28e 100644 --- a/tools/objtool/objtool.c +++ b/tools/objtool/objtool.c @@ -129,7 +129,6 @@ struct objtool_file *objtool_open_read(const char *_objname) INIT_LIST_HEAD(&file.static_call_list); INIT_LIST_HEAD(&file.mcount_loc_list); INIT_LIST_HEAD(&file.endbr_list); - file.c_file = !vmlinux && find_section_by_name(file.elf, ".comment"); file.ignore_unreachables = no_unreachable; file.hints = false; diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index af4d63af8072..e8b577d33e53 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -148,6 +148,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, bool privileged = perf_event_paranoid_check(-1); struct evsel *tracking_evsel; int err; + u64 bit; sper->evlist = evlist; @@ -245,6 +246,15 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, */ evsel__set_sample_bit(arm_spe_evsel, DATA_SRC); + /* + * The PHYS_ADDR flag does not affect the driver behaviour, it is used to + * inform that the resulting output's SPE samples contain physical addresses + * where applicable. + */ + bit = perf_pmu__format_bits(&arm_spe_pmu->format, "pa_enable"); + if (arm_spe_evsel->core.attr.config & bit) + evsel__set_sample_bit(arm_spe_evsel, PHYS_ADDR); + /* Add dummy event to keep tracking */ err = parse_events(evlist, "dummy:u", NULL); if (err) diff --git a/tools/perf/arch/arm64/util/machine.c b/tools/perf/arch/arm64/util/machine.c index d2ce31e28cd7..41c1596e5207 100644 --- a/tools/perf/arch/arm64/util/machine.c +++ b/tools/perf/arch/arm64/util/machine.c @@ -8,27 +8,6 @@ #include "callchain.h" #include "record.h" -/* On arm64, kernel text segment starts at high memory address, - * for example 0xffff 0000 8xxx xxxx. Modules start at a low memory - * address, like 0xffff 0000 00ax xxxx. When only small amount of - * memory is used by modules, gap between end of module's text segment - * and start of kernel text segment may reach 2G. - * Therefore do not fill this gap and do not assign it to the kernel dso map. - */ - -#define SYMBOL_LIMIT (1 << 12) /* 4K */ - -void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) -{ - if ((strchr(p->name, '[') && strchr(c->name, '[') == NULL) || - (strchr(p->name, '[') == NULL && strchr(c->name, '['))) - /* Limit range of last symbol in module and kernel */ - p->end += SYMBOL_LIMIT; - else - p->end = c->start; - pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end); -} - void arch__add_leaf_frame_record_opts(struct record_opts *opts) { opts->sample_user_regs |= sample_reg_masks[PERF_REG_ARM64_LR].mask; diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build index 8a79c4126e5b..0115f3166568 100644 --- a/tools/perf/arch/powerpc/util/Build +++ b/tools/perf/arch/powerpc/util/Build @@ -1,5 +1,4 @@ perf-y += header.o -perf-y += machine.o perf-y += kvm-stat.o perf-y += perf_regs.o perf-y += mem-events.o diff --git a/tools/perf/arch/powerpc/util/machine.c b/tools/perf/arch/powerpc/util/machine.c deleted file mode 100644 index e652a1aa8132..000000000000 --- a/tools/perf/arch/powerpc/util/machine.c +++ /dev/null @@ -1,25 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -#include <inttypes.h> -#include <stdio.h> -#include <string.h> -#include <internal/lib.h> // page_size -#include "debug.h" -#include "symbol.h" - -/* On powerpc kernel text segment start at memory addresses, 0xc000000000000000 - * whereas the modules are located at very high memory addresses, - * for example 0xc00800000xxxxxxx. The gap between end of kernel text segment - * and beginning of first module's text segment is very high. - * Therefore do not fill this gap and do not assign it to the kernel dso map. - */ - -void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) -{ - if (strchr(p->name, '[') == NULL && strchr(c->name, '[')) - /* Limit the range of last kernel symbol */ - p->end += page_size; - else - p->end = c->start; - pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end); -} diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c index 7644a4f6d4a4..98bc3f39d5f3 100644 --- a/tools/perf/arch/s390/util/machine.c +++ b/tools/perf/arch/s390/util/machine.c @@ -35,19 +35,3 @@ int arch__fix_module_text_start(u64 *start, u64 *size, const char *name) return 0; } - -/* On s390 kernel text segment start is located at very low memory addresses, - * for example 0x10000. Modules are located at very high memory addresses, - * for example 0x3ff xxxx xxxx. The gap between end of kernel text segment - * and beginning of first module's text segment is very big. - * Therefore do not fill this gap and do not assign it to the kernel dso map. - */ -void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) -{ - if (strchr(p->name, '[') == NULL && strchr(c->name, '[')) - /* Last kernel symbol mapped to end of page */ - p->end = roundup(p->end, page_size); - else - p->end = c->start; - pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end); -} diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 1ad75c7ba074..afe4a5539ecc 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -353,6 +353,7 @@ static int report__setup_sample_type(struct report *rep) struct perf_session *session = rep->session; u64 sample_type = evlist__combined_sample_type(session->evlist); bool is_pipe = perf_data__is_pipe(session->data); + struct evsel *evsel; if (session->itrace_synth_opts->callchain || session->itrace_synth_opts->add_callchain || @@ -407,6 +408,19 @@ static int report__setup_sample_type(struct report *rep) } if (sort__mode == SORT_MODE__MEMORY) { + /* + * FIXUP: prior to kernel 5.18, Arm SPE missed to set + * PERF_SAMPLE_DATA_SRC bit in sample type. For backward + * compatibility, set the bit if it's an old perf data file. + */ + evlist__for_each_entry(session->evlist, evsel) { + if (strstr(evsel->name, "arm_spe") && + !(sample_type & PERF_SAMPLE_DATA_SRC)) { + evsel->core.attr.sample_type |= PERF_SAMPLE_DATA_SRC; + sample_type |= PERF_SAMPLE_DATA_SRC; + } + } + if (!is_pipe && !(sample_type & PERF_SAMPLE_DATA_SRC)) { ui__error("Selected --mem-mode but no mem data. " "Did you call perf record without -d?\n"); diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index a2f117936188..cf5eab5431b4 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -461,7 +461,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) return -EINVAL; if (PRINT_FIELD(DATA_SRC) && - evsel__check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC", PERF_OUTPUT_DATA_SRC)) + evsel__do_check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC", PERF_OUTPUT_DATA_SRC, allow_user_set)) return -EINVAL; if (PRINT_FIELD(WEIGHT) && diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README index 454505d343fa..eb3f7d4bb324 100644 --- a/tools/perf/tests/attr/README +++ b/tools/perf/tests/attr/README @@ -60,6 +60,7 @@ Following tests are defined (with perf commands): perf record -R kill (test-record-raw) perf record -c 2 -e arm_spe_0// -- kill (test-record-spe-period) perf record -e arm_spe_0/period=3/ -- kill (test-record-spe-period-term) + perf record -e arm_spe_0/pa_enable=1/ -- kill (test-record-spe-physical-address) perf stat -e cycles kill (test-stat-basic) perf stat kill (test-stat-default) perf stat -d kill (test-stat-detailed-1) diff --git a/tools/perf/tests/attr/test-record-spe-physical-address b/tools/perf/tests/attr/test-record-spe-physical-address new file mode 100644 index 000000000000..7ebcf5012ce3 --- /dev/null +++ b/tools/perf/tests/attr/test-record-spe-physical-address @@ -0,0 +1,12 @@ +[config] +command = record +args = --no-bpf-event -e arm_spe_0/pa_enable=1/ -- kill >/dev/null 2>&1 +ret = 1 +arch = aarch64 + +[event-10:base-record-spe] +# 622727 is the decimal of IP|TID|TIME|CPU|IDENTIFIER|DATA_SRC|PHYS_ADDR +sample_type=622727 + +# dummy event +[event-1:base-record-spe]
\ No newline at end of file diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index cc6df49a65a1..4ad0dfbc8b21 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -123,6 +123,10 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su evsel->core.attr.enable_on_exec = 0; } + if (evlist__open(evlist) == -ENOENT) { + err = TEST_SKIP; + goto out_err; + } CHECK__(evlist__open(evlist)); CHECK__(evlist__mmap(evlist, UINT_MAX)); diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index d2b64e3f588b..1a80151baed9 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -1033,10 +1033,11 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session) memset(&attr, 0, sizeof(struct perf_event_attr)); attr.size = sizeof(struct perf_event_attr); attr.type = PERF_TYPE_HARDWARE; - attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK; + attr.sample_type = evsel->core.attr.sample_type & + (PERF_SAMPLE_MASK | PERF_SAMPLE_PHYS_ADDR); attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC | - PERF_SAMPLE_WEIGHT; + PERF_SAMPLE_WEIGHT | PERF_SAMPLE_ADDR; if (spe->timeless_decoding) attr.sample_type &= ~(u64)PERF_SAMPLE_TIME; else diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp index df7b18fb6b6e..1aad7d6d34aa 100644 --- a/tools/perf/util/c++/clang.cpp +++ b/tools/perf/util/c++/clang.cpp @@ -20,7 +20,11 @@ #include "llvm/Option/Option.h" #include "llvm/Support/FileSystem.h" #include "llvm/Support/ManagedStatic.h" +#if CLANG_VERSION_MAJOR >= 14 +#include "llvm/MC/TargetRegistry.h" +#else #include "llvm/Support/TargetRegistry.h" +#endif #include "llvm/Support/TargetSelect.h" #include "llvm/Target/TargetMachine.h" #include "llvm/Target/TargetOptions.h" diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 45a30040ec8d..f9a320694b85 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -2576,7 +2576,7 @@ int perf_session__process_events(struct perf_session *session) if (perf_data__is_pipe(session->data)) return __perf_session__process_pipe_events(session); - if (perf_data__is_dir(session->data)) + if (perf_data__is_dir(session->data) && session->data->dir.nr) return __perf_session__process_dir_events(session); return __perf_session__process_events(session); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 31cd59a2b66e..ecd377938eea 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1290,7 +1290,7 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss, * For misannotated, zeroed, ASM function sizes. */ if (nr > 0) { - symbols__fixup_end(&dso->symbols); + symbols__fixup_end(&dso->symbols, false); symbols__fixup_duplicate(&dso->symbols); if (kmap) { /* diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index dea0fc495185..f72baf636724 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -101,11 +101,6 @@ static int prefix_underscores_count(const char *str) return tail - str; } -void __weak arch__symbols__fixup_end(struct symbol *p, struct symbol *c) -{ - p->end = c->start; -} - const char * __weak arch__normalize_symbol_name(const char *name) { return name; @@ -217,7 +212,8 @@ again: } } -void symbols__fixup_end(struct rb_root_cached *symbols) +/* Update zero-sized symbols using the address of the next symbol */ +void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms) { struct rb_node *nd, *prevnd = rb_first_cached(symbols); struct symbol *curr, *prev; @@ -231,8 +227,29 @@ void symbols__fixup_end(struct rb_root_cached *symbols) prev = curr; curr = rb_entry(nd, struct symbol, rb_node); - if (prev->end == prev->start || prev->end != curr->start) - arch__symbols__fixup_end(prev, curr); + /* + * On some architecture kernel text segment start is located at + * some low memory address, while modules are located at high + * memory addresses (or vice versa). The gap between end of + * kernel text segment and beginning of first module's text + * segment is very big. Therefore do not fill this gap and do + * not assign it to the kernel dso map (kallsyms). + * + * In kallsyms, it determines module symbols using '[' character + * like in: + * ffffffffc1937000 T hdmi_driver_init [snd_hda_codec_hdmi] + */ + if (prev->end == prev->start) { + /* Last kernel/module symbol mapped to end of page */ + if (is_kallsyms && (!strchr(prev->name, '[') != + !strchr(curr->name, '['))) + prev->end = roundup(prev->end + 4096, 4096); + else + prev->end = curr->start; + + pr_debug4("%s sym:%s end:%#" PRIx64 "\n", + __func__, prev->name, prev->end); + } } /* Last entry */ @@ -1467,7 +1484,7 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename, if (kallsyms__delta(kmap, filename, &delta)) return -1; - symbols__fixup_end(&dso->symbols); + symbols__fixup_end(&dso->symbols, true); symbols__fixup_duplicate(&dso->symbols); if (dso->kernel == DSO_SPACE__KERNEL_GUEST) @@ -1659,7 +1676,7 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile) #undef bfd_asymbol_section #endif - symbols__fixup_end(&dso->symbols); + symbols__fixup_end(&dso->symbols, false); symbols__fixup_duplicate(&dso->symbols); dso->adjust_symbols = 1; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index fbf866d82dcc..0b893dcc8ea6 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -203,7 +203,7 @@ void __symbols__insert(struct rb_root_cached *symbols, struct symbol *sym, bool kernel); void symbols__insert(struct rb_root_cached *symbols, struct symbol *sym); void symbols__fixup_duplicate(struct rb_root_cached *symbols); -void symbols__fixup_end(struct rb_root_cached *symbols); +void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms); void maps__fixup_end(struct maps *maps); typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data); @@ -241,7 +241,6 @@ const char *arch__normalize_symbol_name(const char *name); #define SYMBOL_A 0 #define SYMBOL_B 1 -void arch__symbols__fixup_end(struct symbol *p, struct symbol *c); int arch__compare_symbol_names(const char *namea, const char *nameb); int arch__compare_symbol_names_n(const char *namea, const char *nameb, unsigned int n); diff --git a/tools/power/x86/intel-speed-select/Makefile b/tools/power/x86/intel-speed-select/Makefile index 846f785e278d..7221f2f55e8b 100644 --- a/tools/power/x86/intel-speed-select/Makefile +++ b/tools/power/x86/intel-speed-select/Makefile @@ -42,7 +42,7 @@ ISST_IN := $(OUTPUT)intel-speed-select-in.o $(ISST_IN): prepare FORCE $(Q)$(MAKE) $(build)=intel-speed-select $(OUTPUT)intel-speed-select: $(ISST_IN) - $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ + $(QUIET_LINK)$(CC) $(CFLAGS) $< $(LDFLAGS) -o $@ clean: rm -f $(ALL_PROGRAMS) diff --git a/tools/testing/radix-tree/linux.c b/tools/testing/radix-tree/linux.c index 81539f543954..d5c1bcba86fe 100644 --- a/tools/testing/radix-tree/linux.c +++ b/tools/testing/radix-tree/linux.c @@ -25,7 +25,8 @@ struct kmem_cache { void (*ctor)(void *); }; -void *kmem_cache_alloc(struct kmem_cache *cachep, int gfp) +void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru, + int gfp) { void *p; diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh index 429f7ee735cf..fd23c80eba31 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh @@ -159,6 +159,17 @@ flooding_remotes_add() local lsb local i + # Prevent unwanted packets from entering the bridge and interfering + # with the test. + tc qdisc add dev br0 clsact + tc filter add dev br0 egress protocol all pref 1 handle 1 \ + matchall skip_hw action drop + tc qdisc add dev $h1 clsact + tc filter add dev $h1 egress protocol all pref 1 handle 1 \ + flower skip_hw dst_mac de:ad:be:ef:13:37 action pass + tc filter add dev $h1 egress protocol all pref 2 handle 2 \ + matchall skip_hw action drop + for i in $(eval echo {1..$num_remotes}); do lsb=$((i + 1)) @@ -195,6 +206,12 @@ flooding_filters_del() done tc qdisc del dev $rp2 clsact + + tc filter del dev $h1 egress protocol all pref 2 handle 2 matchall + tc filter del dev $h1 egress protocol all pref 1 handle 1 flower + tc qdisc del dev $h1 clsact + tc filter del dev br0 egress protocol all pref 1 handle 1 matchall + tc qdisc del dev br0 clsact } flooding_check_packets() diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh index fedcb7b35af9..af5ea50ed5c0 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh @@ -172,6 +172,17 @@ flooding_filters_add() local lsb local i + # Prevent unwanted packets from entering the bridge and interfering + # with the test. + tc qdisc add dev br0 clsact + tc filter add dev br0 egress protocol all pref 1 handle 1 \ + matchall skip_hw action drop + tc qdisc add dev $h1 clsact + tc filter add dev $h1 egress protocol all pref 1 handle 1 \ + flower skip_hw dst_mac de:ad:be:ef:13:37 action pass + tc filter add dev $h1 egress protocol all pref 2 handle 2 \ + matchall skip_hw action drop + tc qdisc add dev $rp2 clsact for i in $(eval echo {1..$num_remotes}); do @@ -194,6 +205,12 @@ flooding_filters_del() done tc qdisc del dev $rp2 clsact + + tc filter del dev $h1 egress protocol all pref 2 handle 2 matchall + tc filter del dev $h1 egress protocol all pref 1 handle 1 flower + tc qdisc del dev $h1 clsact + tc filter del dev br0 egress protocol all pref 1 handle 1 matchall + tc qdisc del dev br0 clsact } flooding_check_packets() diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 0b0e4402bba6..b17e464ec661 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -2,7 +2,8 @@ /aarch64/arch_timer /aarch64/debug-exceptions /aarch64/get-reg-list -/aarch64/psci_cpu_on_test +/aarch64/hypercalls +/aarch64/psci_test /aarch64/vcpu_width_config /aarch64/vgic_init /aarch64/vgic_irq diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 681b173aa87c..97eef0c03d3b 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -105,7 +105,8 @@ TEST_GEN_PROGS_x86_64 += system_counter_offset_test TEST_GEN_PROGS_aarch64 += aarch64/arch_timer TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list -TEST_GEN_PROGS_aarch64 += aarch64/psci_cpu_on_test +TEST_GEN_PROGS_aarch64 += aarch64/hypercalls +TEST_GEN_PROGS_aarch64 += aarch64/psci_test TEST_GEN_PROGS_aarch64 += aarch64/vcpu_width_config TEST_GEN_PROGS_aarch64 += aarch64/vgic_init TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index 0b571f3fe64c..d3a7dbfcbb3d 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -294,6 +294,11 @@ static void print_reg(struct vcpu_config *c, __u64 id) "%s: Unexpected bits set in FW reg id: 0x%llx", config_name(c), id); printf("\tKVM_REG_ARM_FW_REG(%lld),\n", id & 0xffff); break; + case KVM_REG_ARM_FW_FEAT_BMAP: + TEST_ASSERT(id == KVM_REG_ARM_FW_FEAT_BMAP_REG(id & 0xffff), + "%s: Unexpected bits set in the bitmap feature FW reg id: 0x%llx", config_name(c), id); + printf("\tKVM_REG_ARM_FW_FEAT_BMAP_REG(%lld),\n", id & 0xffff); + break; case KVM_REG_ARM64_SVE: if (has_cap(c, KVM_CAP_ARM_SVE)) printf("\t%s,\n", sve_id_to_str(c, id)); @@ -692,6 +697,9 @@ static __u64 base_regs[] = { KVM_REG_ARM_FW_REG(1), /* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 */ KVM_REG_ARM_FW_REG(2), /* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 */ KVM_REG_ARM_FW_REG(3), /* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3 */ + KVM_REG_ARM_FW_FEAT_BMAP_REG(0), /* KVM_REG_ARM_STD_BMAP */ + KVM_REG_ARM_FW_FEAT_BMAP_REG(1), /* KVM_REG_ARM_STD_HYP_BMAP */ + KVM_REG_ARM_FW_FEAT_BMAP_REG(2), /* KVM_REG_ARM_VENDOR_HYP_BMAP */ ARM64_SYS_REG(3, 3, 14, 3, 1), /* CNTV_CTL_EL0 */ ARM64_SYS_REG(3, 3, 14, 3, 2), /* CNTV_CVAL_EL0 */ ARM64_SYS_REG(3, 3, 14, 0, 2), diff --git a/tools/testing/selftests/kvm/aarch64/hypercalls.c b/tools/testing/selftests/kvm/aarch64/hypercalls.c new file mode 100644 index 000000000000..41e0210b7a5e --- /dev/null +++ b/tools/testing/selftests/kvm/aarch64/hypercalls.c @@ -0,0 +1,336 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* hypercalls: Check the ARM64's psuedo-firmware bitmap register interface. + * + * The test validates the basic hypercall functionalities that are exposed + * via the psuedo-firmware bitmap register. This includes the registers' + * read/write behavior before and after the VM has started, and if the + * hypercalls are properly masked or unmasked to the guest when disabled or + * enabled from the KVM userspace, respectively. + */ + +#include <errno.h> +#include <linux/arm-smccc.h> +#include <asm/kvm.h> +#include <kvm_util.h> + +#include "processor.h" + +#define FW_REG_ULIMIT_VAL(max_feat_bit) (GENMASK(max_feat_bit, 0)) + +/* Last valid bits of the bitmapped firmware registers */ +#define KVM_REG_ARM_STD_BMAP_BIT_MAX 0 +#define KVM_REG_ARM_STD_HYP_BMAP_BIT_MAX 0 +#define KVM_REG_ARM_VENDOR_HYP_BMAP_BIT_MAX 1 + +struct kvm_fw_reg_info { + uint64_t reg; /* Register definition */ + uint64_t max_feat_bit; /* Bit that represents the upper limit of the feature-map */ +}; + +#define FW_REG_INFO(r) \ + { \ + .reg = r, \ + .max_feat_bit = r##_BIT_MAX, \ + } + +static const struct kvm_fw_reg_info fw_reg_info[] = { + FW_REG_INFO(KVM_REG_ARM_STD_BMAP), + FW_REG_INFO(KVM_REG_ARM_STD_HYP_BMAP), + FW_REG_INFO(KVM_REG_ARM_VENDOR_HYP_BMAP), +}; + +enum test_stage { + TEST_STAGE_REG_IFACE, + TEST_STAGE_HVC_IFACE_FEAT_DISABLED, + TEST_STAGE_HVC_IFACE_FEAT_ENABLED, + TEST_STAGE_HVC_IFACE_FALSE_INFO, + TEST_STAGE_END, +}; + +static int stage = TEST_STAGE_REG_IFACE; + +struct test_hvc_info { + uint32_t func_id; + uint64_t arg1; +}; + +#define TEST_HVC_INFO(f, a1) \ + { \ + .func_id = f, \ + .arg1 = a1, \ + } + +static const struct test_hvc_info hvc_info[] = { + /* KVM_REG_ARM_STD_BMAP */ + TEST_HVC_INFO(ARM_SMCCC_TRNG_VERSION, 0), + TEST_HVC_INFO(ARM_SMCCC_TRNG_FEATURES, ARM_SMCCC_TRNG_RND64), + TEST_HVC_INFO(ARM_SMCCC_TRNG_GET_UUID, 0), + TEST_HVC_INFO(ARM_SMCCC_TRNG_RND32, 0), + TEST_HVC_INFO(ARM_SMCCC_TRNG_RND64, 0), + + /* KVM_REG_ARM_STD_HYP_BMAP */ + TEST_HVC_INFO(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_HV_PV_TIME_FEATURES), + TEST_HVC_INFO(ARM_SMCCC_HV_PV_TIME_FEATURES, ARM_SMCCC_HV_PV_TIME_ST), + TEST_HVC_INFO(ARM_SMCCC_HV_PV_TIME_ST, 0), + + /* KVM_REG_ARM_VENDOR_HYP_BMAP */ + TEST_HVC_INFO(ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID, + ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID), + TEST_HVC_INFO(ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID, 0), + TEST_HVC_INFO(ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID, KVM_PTP_VIRT_COUNTER), +}; + +/* Feed false hypercall info to test the KVM behavior */ +static const struct test_hvc_info false_hvc_info[] = { + /* Feature support check against a different family of hypercalls */ + TEST_HVC_INFO(ARM_SMCCC_TRNG_FEATURES, ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID), + TEST_HVC_INFO(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_TRNG_RND64), + TEST_HVC_INFO(ARM_SMCCC_HV_PV_TIME_FEATURES, ARM_SMCCC_TRNG_RND64), +}; + +static void guest_test_hvc(const struct test_hvc_info *hc_info) +{ + unsigned int i; + struct arm_smccc_res res; + unsigned int hvc_info_arr_sz; + + hvc_info_arr_sz = + hc_info == hvc_info ? ARRAY_SIZE(hvc_info) : ARRAY_SIZE(false_hvc_info); + + for (i = 0; i < hvc_info_arr_sz; i++, hc_info++) { + memset(&res, 0, sizeof(res)); + smccc_hvc(hc_info->func_id, hc_info->arg1, 0, 0, 0, 0, 0, 0, &res); + + switch (stage) { + case TEST_STAGE_HVC_IFACE_FEAT_DISABLED: + case TEST_STAGE_HVC_IFACE_FALSE_INFO: + GUEST_ASSERT_3(res.a0 == SMCCC_RET_NOT_SUPPORTED, + res.a0, hc_info->func_id, hc_info->arg1); + break; + case TEST_STAGE_HVC_IFACE_FEAT_ENABLED: + GUEST_ASSERT_3(res.a0 != SMCCC_RET_NOT_SUPPORTED, + res.a0, hc_info->func_id, hc_info->arg1); + break; + default: + GUEST_ASSERT_1(0, stage); + } + } +} + +static void guest_code(void) +{ + while (stage != TEST_STAGE_END) { + switch (stage) { + case TEST_STAGE_REG_IFACE: + break; + case TEST_STAGE_HVC_IFACE_FEAT_DISABLED: + case TEST_STAGE_HVC_IFACE_FEAT_ENABLED: + guest_test_hvc(hvc_info); + break; + case TEST_STAGE_HVC_IFACE_FALSE_INFO: + guest_test_hvc(false_hvc_info); + break; + default: + GUEST_ASSERT_1(0, stage); + } + + GUEST_SYNC(stage); + } + + GUEST_DONE(); +} + +static int set_fw_reg(struct kvm_vm *vm, uint64_t id, uint64_t val) +{ + struct kvm_one_reg reg = { + .id = id, + .addr = (uint64_t)&val, + }; + + return _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, ®); +} + +static void get_fw_reg(struct kvm_vm *vm, uint64_t id, uint64_t *addr) +{ + struct kvm_one_reg reg = { + .id = id, + .addr = (uint64_t)addr, + }; + + vcpu_ioctl(vm, 0, KVM_GET_ONE_REG, ®); +} + +struct st_time { + uint32_t rev; + uint32_t attr; + uint64_t st_time; +}; + +#define STEAL_TIME_SIZE ((sizeof(struct st_time) + 63) & ~63) +#define ST_GPA_BASE (1 << 30) + +static void steal_time_init(struct kvm_vm *vm) +{ + uint64_t st_ipa = (ulong)ST_GPA_BASE; + unsigned int gpages; + struct kvm_device_attr dev = { + .group = KVM_ARM_VCPU_PVTIME_CTRL, + .attr = KVM_ARM_VCPU_PVTIME_IPA, + .addr = (uint64_t)&st_ipa, + }; + + gpages = vm_calc_num_guest_pages(VM_MODE_DEFAULT, STEAL_TIME_SIZE); + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, ST_GPA_BASE, 1, gpages, 0); + + vcpu_ioctl(vm, 0, KVM_SET_DEVICE_ATTR, &dev); +} + +static void test_fw_regs_before_vm_start(struct kvm_vm *vm) +{ + uint64_t val; + unsigned int i; + int ret; + + for (i = 0; i < ARRAY_SIZE(fw_reg_info); i++) { + const struct kvm_fw_reg_info *reg_info = &fw_reg_info[i]; + + /* First 'read' should be an upper limit of the features supported */ + get_fw_reg(vm, reg_info->reg, &val); + TEST_ASSERT(val == FW_REG_ULIMIT_VAL(reg_info->max_feat_bit), + "Expected all the features to be set for reg: 0x%lx; expected: 0x%lx; read: 0x%lx\n", + reg_info->reg, FW_REG_ULIMIT_VAL(reg_info->max_feat_bit), val); + + /* Test a 'write' by disabling all the features of the register map */ + ret = set_fw_reg(vm, reg_info->reg, 0); + TEST_ASSERT(ret == 0, + "Failed to clear all the features of reg: 0x%lx; ret: %d\n", + reg_info->reg, errno); + + get_fw_reg(vm, reg_info->reg, &val); + TEST_ASSERT(val == 0, + "Expected all the features to be cleared for reg: 0x%lx\n", reg_info->reg); + + /* + * Test enabling a feature that's not supported. + * Avoid this check if all the bits are occupied. + */ + if (reg_info->max_feat_bit < 63) { + ret = set_fw_reg(vm, reg_info->reg, BIT(reg_info->max_feat_bit + 1)); + TEST_ASSERT(ret != 0 && errno == EINVAL, + "Unexpected behavior or return value (%d) while setting an unsupported feature for reg: 0x%lx\n", + errno, reg_info->reg); + } + } +} + +static void test_fw_regs_after_vm_start(struct kvm_vm *vm) +{ + uint64_t val; + unsigned int i; + int ret; + + for (i = 0; i < ARRAY_SIZE(fw_reg_info); i++) { + const struct kvm_fw_reg_info *reg_info = &fw_reg_info[i]; + + /* + * Before starting the VM, the test clears all the bits. + * Check if that's still the case. + */ + get_fw_reg(vm, reg_info->reg, &val); + TEST_ASSERT(val == 0, + "Expected all the features to be cleared for reg: 0x%lx\n", + reg_info->reg); + + /* + * Since the VM has run at least once, KVM shouldn't allow modification of + * the registers and should return EBUSY. Set the registers and check for + * the expected errno. + */ + ret = set_fw_reg(vm, reg_info->reg, FW_REG_ULIMIT_VAL(reg_info->max_feat_bit)); + TEST_ASSERT(ret != 0 && errno == EBUSY, + "Unexpected behavior or return value (%d) while setting a feature while VM is running for reg: 0x%lx\n", + errno, reg_info->reg); + } +} + +static struct kvm_vm *test_vm_create(void) +{ + struct kvm_vm *vm; + + vm = vm_create_default(0, 0, guest_code); + + ucall_init(vm, NULL); + steal_time_init(vm); + + return vm; +} + +static struct kvm_vm *test_guest_stage(struct kvm_vm *vm) +{ + struct kvm_vm *ret_vm = vm; + + pr_debug("Stage: %d\n", stage); + + switch (stage) { + case TEST_STAGE_REG_IFACE: + test_fw_regs_after_vm_start(vm); + break; + case TEST_STAGE_HVC_IFACE_FEAT_DISABLED: + /* Start a new VM so that all the features are now enabled by default */ + kvm_vm_free(vm); + ret_vm = test_vm_create(); + break; + case TEST_STAGE_HVC_IFACE_FEAT_ENABLED: + case TEST_STAGE_HVC_IFACE_FALSE_INFO: + break; + default: + TEST_FAIL("Unknown test stage: %d\n", stage); + } + + stage++; + sync_global_to_guest(vm, stage); + + return ret_vm; +} + +static void test_run(void) +{ + struct kvm_vm *vm; + struct ucall uc; + bool guest_done = false; + + vm = test_vm_create(); + + test_fw_regs_before_vm_start(vm); + + while (!guest_done) { + vcpu_run(vm, 0); + + switch (get_ucall(vm, 0, &uc)) { + case UCALL_SYNC: + vm = test_guest_stage(vm); + break; + case UCALL_DONE: + guest_done = true; + break; + case UCALL_ABORT: + TEST_FAIL("%s at %s:%ld\n\tvalues: 0x%lx, 0x%lx; 0x%lx, stage: %u", + (const char *)uc.args[0], __FILE__, uc.args[1], + uc.args[2], uc.args[3], uc.args[4], stage); + break; + default: + TEST_FAIL("Unexpected guest exit\n"); + } + } + + kvm_vm_free(vm); +} + +int main(void) +{ + setbuf(stdout, NULL); + + test_run(); + return 0; +} diff --git a/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c b/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c deleted file mode 100644 index 4c5f6814030f..000000000000 --- a/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c +++ /dev/null @@ -1,121 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * psci_cpu_on_test - Test that the observable state of a vCPU targeted by the - * CPU_ON PSCI call matches what the caller requested. - * - * Copyright (c) 2021 Google LLC. - * - * This is a regression test for a race between KVM servicing the PSCI call and - * userspace reading the vCPUs registers. - */ - -#define _GNU_SOURCE - -#include <linux/psci.h> - -#include "kvm_util.h" -#include "processor.h" -#include "test_util.h" - -#define VCPU_ID_SOURCE 0 -#define VCPU_ID_TARGET 1 - -#define CPU_ON_ENTRY_ADDR 0xfeedf00dul -#define CPU_ON_CONTEXT_ID 0xdeadc0deul - -static uint64_t psci_cpu_on(uint64_t target_cpu, uint64_t entry_addr, - uint64_t context_id) -{ - register uint64_t x0 asm("x0") = PSCI_0_2_FN64_CPU_ON; - register uint64_t x1 asm("x1") = target_cpu; - register uint64_t x2 asm("x2") = entry_addr; - register uint64_t x3 asm("x3") = context_id; - - asm("hvc #0" - : "=r"(x0) - : "r"(x0), "r"(x1), "r"(x2), "r"(x3) - : "memory"); - - return x0; -} - -static uint64_t psci_affinity_info(uint64_t target_affinity, - uint64_t lowest_affinity_level) -{ - register uint64_t x0 asm("x0") = PSCI_0_2_FN64_AFFINITY_INFO; - register uint64_t x1 asm("x1") = target_affinity; - register uint64_t x2 asm("x2") = lowest_affinity_level; - - asm("hvc #0" - : "=r"(x0) - : "r"(x0), "r"(x1), "r"(x2) - : "memory"); - - return x0; -} - -static void guest_main(uint64_t target_cpu) -{ - GUEST_ASSERT(!psci_cpu_on(target_cpu, CPU_ON_ENTRY_ADDR, CPU_ON_CONTEXT_ID)); - uint64_t target_state; - - do { - target_state = psci_affinity_info(target_cpu, 0); - - GUEST_ASSERT((target_state == PSCI_0_2_AFFINITY_LEVEL_ON) || - (target_state == PSCI_0_2_AFFINITY_LEVEL_OFF)); - } while (target_state != PSCI_0_2_AFFINITY_LEVEL_ON); - - GUEST_DONE(); -} - -int main(void) -{ - uint64_t target_mpidr, obs_pc, obs_x0; - struct kvm_vcpu_init init; - struct kvm_vm *vm; - struct ucall uc; - - vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); - kvm_vm_elf_load(vm, program_invocation_name); - ucall_init(vm, NULL); - - vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init); - init.features[0] |= (1 << KVM_ARM_VCPU_PSCI_0_2); - - aarch64_vcpu_add_default(vm, VCPU_ID_SOURCE, &init, guest_main); - - /* - * make sure the target is already off when executing the test. - */ - init.features[0] |= (1 << KVM_ARM_VCPU_POWER_OFF); - aarch64_vcpu_add_default(vm, VCPU_ID_TARGET, &init, guest_main); - - get_reg(vm, VCPU_ID_TARGET, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), &target_mpidr); - vcpu_args_set(vm, VCPU_ID_SOURCE, 1, target_mpidr & MPIDR_HWID_BITMASK); - vcpu_run(vm, VCPU_ID_SOURCE); - - switch (get_ucall(vm, VCPU_ID_SOURCE, &uc)) { - case UCALL_DONE: - break; - case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], __FILE__, - uc.args[1]); - break; - default: - TEST_FAIL("Unhandled ucall: %lu", uc.cmd); - } - - get_reg(vm, VCPU_ID_TARGET, ARM64_CORE_REG(regs.pc), &obs_pc); - get_reg(vm, VCPU_ID_TARGET, ARM64_CORE_REG(regs.regs[0]), &obs_x0); - - TEST_ASSERT(obs_pc == CPU_ON_ENTRY_ADDR, - "unexpected target cpu pc: %lx (expected: %lx)", - obs_pc, CPU_ON_ENTRY_ADDR); - TEST_ASSERT(obs_x0 == CPU_ON_CONTEXT_ID, - "unexpected target context id: %lx (expected: %lx)", - obs_x0, CPU_ON_CONTEXT_ID); - - kvm_vm_free(vm); - return 0; -} diff --git a/tools/testing/selftests/kvm/aarch64/psci_test.c b/tools/testing/selftests/kvm/aarch64/psci_test.c new file mode 100644 index 000000000000..88541de21c41 --- /dev/null +++ b/tools/testing/selftests/kvm/aarch64/psci_test.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * psci_cpu_on_test - Test that the observable state of a vCPU targeted by the + * CPU_ON PSCI call matches what the caller requested. + * + * Copyright (c) 2021 Google LLC. + * + * This is a regression test for a race between KVM servicing the PSCI call and + * userspace reading the vCPUs registers. + */ + +#define _GNU_SOURCE + +#include <linux/psci.h> + +#include "kvm_util.h" +#include "processor.h" +#include "test_util.h" + +#define VCPU_ID_SOURCE 0 +#define VCPU_ID_TARGET 1 + +#define CPU_ON_ENTRY_ADDR 0xfeedf00dul +#define CPU_ON_CONTEXT_ID 0xdeadc0deul + +static uint64_t psci_cpu_on(uint64_t target_cpu, uint64_t entry_addr, + uint64_t context_id) +{ + struct arm_smccc_res res; + + smccc_hvc(PSCI_0_2_FN64_CPU_ON, target_cpu, entry_addr, context_id, + 0, 0, 0, 0, &res); + + return res.a0; +} + +static uint64_t psci_affinity_info(uint64_t target_affinity, + uint64_t lowest_affinity_level) +{ + struct arm_smccc_res res; + + smccc_hvc(PSCI_0_2_FN64_AFFINITY_INFO, target_affinity, lowest_affinity_level, + 0, 0, 0, 0, 0, &res); + + return res.a0; +} + +static uint64_t psci_system_suspend(uint64_t entry_addr, uint64_t context_id) +{ + struct arm_smccc_res res; + + smccc_hvc(PSCI_1_0_FN64_SYSTEM_SUSPEND, entry_addr, context_id, + 0, 0, 0, 0, 0, &res); + + return res.a0; +} + +static uint64_t psci_features(uint32_t func_id) +{ + struct arm_smccc_res res; + + smccc_hvc(PSCI_1_0_FN_PSCI_FEATURES, func_id, 0, 0, 0, 0, 0, 0, &res); + + return res.a0; +} + +static void vcpu_power_off(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct kvm_mp_state mp_state = { + .mp_state = KVM_MP_STATE_STOPPED, + }; + + vcpu_set_mp_state(vm, vcpuid, &mp_state); +} + +static struct kvm_vm *setup_vm(void *guest_code) +{ + struct kvm_vcpu_init init; + struct kvm_vm *vm; + + vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + kvm_vm_elf_load(vm, program_invocation_name); + ucall_init(vm, NULL); + + vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init); + init.features[0] |= (1 << KVM_ARM_VCPU_PSCI_0_2); + + aarch64_vcpu_add_default(vm, VCPU_ID_SOURCE, &init, guest_code); + aarch64_vcpu_add_default(vm, VCPU_ID_TARGET, &init, guest_code); + + return vm; +} + +static void enter_guest(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct ucall uc; + + vcpu_run(vm, vcpuid); + if (get_ucall(vm, vcpuid, &uc) == UCALL_ABORT) + TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], __FILE__, + uc.args[1]); +} + +static void assert_vcpu_reset(struct kvm_vm *vm, uint32_t vcpuid) +{ + uint64_t obs_pc, obs_x0; + + get_reg(vm, vcpuid, ARM64_CORE_REG(regs.pc), &obs_pc); + get_reg(vm, vcpuid, ARM64_CORE_REG(regs.regs[0]), &obs_x0); + + TEST_ASSERT(obs_pc == CPU_ON_ENTRY_ADDR, + "unexpected target cpu pc: %lx (expected: %lx)", + obs_pc, CPU_ON_ENTRY_ADDR); + TEST_ASSERT(obs_x0 == CPU_ON_CONTEXT_ID, + "unexpected target context id: %lx (expected: %lx)", + obs_x0, CPU_ON_CONTEXT_ID); +} + +static void guest_test_cpu_on(uint64_t target_cpu) +{ + uint64_t target_state; + + GUEST_ASSERT(!psci_cpu_on(target_cpu, CPU_ON_ENTRY_ADDR, CPU_ON_CONTEXT_ID)); + + do { + target_state = psci_affinity_info(target_cpu, 0); + + GUEST_ASSERT((target_state == PSCI_0_2_AFFINITY_LEVEL_ON) || + (target_state == PSCI_0_2_AFFINITY_LEVEL_OFF)); + } while (target_state != PSCI_0_2_AFFINITY_LEVEL_ON); + + GUEST_DONE(); +} + +static void host_test_cpu_on(void) +{ + uint64_t target_mpidr; + struct kvm_vm *vm; + struct ucall uc; + + vm = setup_vm(guest_test_cpu_on); + + /* + * make sure the target is already off when executing the test. + */ + vcpu_power_off(vm, VCPU_ID_TARGET); + + get_reg(vm, VCPU_ID_TARGET, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), &target_mpidr); + vcpu_args_set(vm, VCPU_ID_SOURCE, 1, target_mpidr & MPIDR_HWID_BITMASK); + enter_guest(vm, VCPU_ID_SOURCE); + + if (get_ucall(vm, VCPU_ID_SOURCE, &uc) != UCALL_DONE) + TEST_FAIL("Unhandled ucall: %lu", uc.cmd); + + assert_vcpu_reset(vm, VCPU_ID_TARGET); + kvm_vm_free(vm); +} + +static void enable_system_suspend(struct kvm_vm *vm) +{ + struct kvm_enable_cap cap = { + .cap = KVM_CAP_ARM_SYSTEM_SUSPEND, + }; + + vm_enable_cap(vm, &cap); +} + +static void guest_test_system_suspend(void) +{ + uint64_t ret; + + /* assert that SYSTEM_SUSPEND is discoverable */ + GUEST_ASSERT(!psci_features(PSCI_1_0_FN_SYSTEM_SUSPEND)); + GUEST_ASSERT(!psci_features(PSCI_1_0_FN64_SYSTEM_SUSPEND)); + + ret = psci_system_suspend(CPU_ON_ENTRY_ADDR, CPU_ON_CONTEXT_ID); + GUEST_SYNC(ret); +} + +static void host_test_system_suspend(void) +{ + struct kvm_run *run; + struct kvm_vm *vm; + + vm = setup_vm(guest_test_system_suspend); + enable_system_suspend(vm); + + vcpu_power_off(vm, VCPU_ID_TARGET); + run = vcpu_state(vm, VCPU_ID_SOURCE); + + enter_guest(vm, VCPU_ID_SOURCE); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_SYSTEM_EVENT, + "Unhandled exit reason: %u (%s)", + run->exit_reason, exit_reason_str(run->exit_reason)); + TEST_ASSERT(run->system_event.type == KVM_SYSTEM_EVENT_SUSPEND, + "Unhandled system event: %u (expected: %u)", + run->system_event.type, KVM_SYSTEM_EVENT_SUSPEND); + + kvm_vm_free(vm); +} + +int main(void) +{ + if (!kvm_check_cap(KVM_CAP_ARM_SYSTEM_SUSPEND)) { + print_skip("KVM_CAP_ARM_SYSTEM_SUSPEND not supported"); + exit(KSFT_SKIP); + } + + host_test_cpu_on(); + host_test_system_suspend(); + return 0; +} diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h index 8f9f46979a00..59ece9d4e0d1 100644 --- a/tools/testing/selftests/kvm/include/aarch64/processor.h +++ b/tools/testing/selftests/kvm/include/aarch64/processor.h @@ -185,4 +185,26 @@ static inline void local_irq_disable(void) asm volatile("msr daifset, #3" : : : "memory"); } +/** + * struct arm_smccc_res - Result from SMC/HVC call + * @a0-a3 result values from registers 0 to 3 + */ +struct arm_smccc_res { + unsigned long a0; + unsigned long a1; + unsigned long a2; + unsigned long a3; +}; + +/** + * smccc_hvc - Invoke a SMCCC function using the hvc conduit + * @function_id: the SMCCC function to be called + * @arg0-arg6: SMCCC function arguments, corresponding to registers x1-x7 + * @res: pointer to write the return values from registers x0-x3 + * + */ +void smccc_hvc(uint32_t function_id, uint64_t arg0, uint64_t arg1, + uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5, + uint64_t arg6, struct arm_smccc_res *res); + #endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 37db341d4cc5..d0d51adec76e 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -60,6 +60,23 @@ /* CPUID.0x8000_0001.EDX */ #define CPUID_GBPAGES (1ul << 26) +/* Page table bitfield declarations */ +#define PTE_PRESENT_MASK BIT_ULL(0) +#define PTE_WRITABLE_MASK BIT_ULL(1) +#define PTE_USER_MASK BIT_ULL(2) +#define PTE_ACCESSED_MASK BIT_ULL(5) +#define PTE_DIRTY_MASK BIT_ULL(6) +#define PTE_LARGE_MASK BIT_ULL(7) +#define PTE_GLOBAL_MASK BIT_ULL(8) +#define PTE_NX_MASK BIT_ULL(63) + +#define PAGE_SHIFT 12 +#define PAGE_SIZE (1ULL << PAGE_SHIFT) +#define PAGE_MASK (~(PAGE_SIZE-1)) + +#define PHYSICAL_PAGE_MASK GENMASK_ULL(51, 12) +#define PTE_GET_PFN(pte) (((pte) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT) + /* General Registers in 64-Bit Mode */ struct gpr64_regs { u64 rax; diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index ba1fdc3dcf4a..2c4a7563a4f8 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -278,7 +278,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) else guest_test_phys_mem = p->phys_offset; #ifdef __s390x__ - alignment = max(0x100000, alignment); + alignment = max(0x100000UL, alignment); #endif guest_test_phys_mem = align_down(guest_test_phys_mem, alignment); diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index 9343d82519b4..6a041289fa80 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -500,3 +500,28 @@ void __attribute__((constructor)) init_guest_modes(void) { guest_modes_append_default(); } + +void smccc_hvc(uint32_t function_id, uint64_t arg0, uint64_t arg1, + uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5, + uint64_t arg6, struct arm_smccc_res *res) +{ + asm volatile("mov w0, %w[function_id]\n" + "mov x1, %[arg0]\n" + "mov x2, %[arg1]\n" + "mov x3, %[arg2]\n" + "mov x4, %[arg3]\n" + "mov x5, %[arg4]\n" + "mov x6, %[arg5]\n" + "mov x7, %[arg6]\n" + "hvc #0\n" + "mov %[res0], x0\n" + "mov %[res1], x1\n" + "mov %[res2], x2\n" + "mov %[res3], x3\n" + : [res0] "=r"(res->a0), [res1] "=r"(res->a1), + [res2] "=r"(res->a2), [res3] "=r"(res->a3) + : [function_id] "r"(function_id), [arg0] "r"(arg0), + [arg1] "r"(arg1), [arg2] "r"(arg2), [arg3] "r"(arg3), + [arg4] "r"(arg4), [arg5] "r"(arg5), [arg6] "r"(arg6) + : "x0", "x1", "x2", "x3", "x4", "x5", "x6", "x7"); +} diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 9f000dfb5594..33ea5e9955d9 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -19,38 +19,6 @@ vm_vaddr_t exception_handlers; -/* Virtual translation table structure declarations */ -struct pageUpperEntry { - uint64_t present:1; - uint64_t writable:1; - uint64_t user:1; - uint64_t write_through:1; - uint64_t cache_disable:1; - uint64_t accessed:1; - uint64_t ignored_06:1; - uint64_t page_size:1; - uint64_t ignored_11_08:4; - uint64_t pfn:40; - uint64_t ignored_62_52:11; - uint64_t execute_disable:1; -}; - -struct pageTableEntry { - uint64_t present:1; - uint64_t writable:1; - uint64_t user:1; - uint64_t write_through:1; - uint64_t cache_disable:1; - uint64_t accessed:1; - uint64_t dirty:1; - uint64_t reserved_07:1; - uint64_t global:1; - uint64_t ignored_11_09:3; - uint64_t pfn:40; - uint64_t ignored_62_52:11; - uint64_t execute_disable:1; -}; - void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent) { @@ -195,23 +163,21 @@ static void *virt_get_pte(struct kvm_vm *vm, uint64_t pt_pfn, uint64_t vaddr, return &page_table[index]; } -static struct pageUpperEntry *virt_create_upper_pte(struct kvm_vm *vm, - uint64_t pt_pfn, - uint64_t vaddr, - uint64_t paddr, - int level, - enum x86_page_size page_size) +static uint64_t *virt_create_upper_pte(struct kvm_vm *vm, + uint64_t pt_pfn, + uint64_t vaddr, + uint64_t paddr, + int level, + enum x86_page_size page_size) { - struct pageUpperEntry *pte = virt_get_pte(vm, pt_pfn, vaddr, level); - - if (!pte->present) { - pte->writable = true; - pte->present = true; - pte->page_size = (level == page_size); - if (pte->page_size) - pte->pfn = paddr >> vm->page_shift; + uint64_t *pte = virt_get_pte(vm, pt_pfn, vaddr, level); + + if (!(*pte & PTE_PRESENT_MASK)) { + *pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK; + if (level == page_size) + *pte |= PTE_LARGE_MASK | (paddr & PHYSICAL_PAGE_MASK); else - pte->pfn = vm_alloc_page_table(vm) >> vm->page_shift; + *pte |= vm_alloc_page_table(vm) & PHYSICAL_PAGE_MASK; } else { /* * Entry already present. Assert that the caller doesn't want @@ -221,7 +187,7 @@ static struct pageUpperEntry *virt_create_upper_pte(struct kvm_vm *vm, TEST_ASSERT(level != page_size, "Cannot create hugepage at level: %u, vaddr: 0x%lx\n", page_size, vaddr); - TEST_ASSERT(!pte->page_size, + TEST_ASSERT(!(*pte & PTE_LARGE_MASK), "Cannot create page table at level: %u, vaddr: 0x%lx\n", level, vaddr); } @@ -232,8 +198,8 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, enum x86_page_size page_size) { const uint64_t pg_size = 1ull << ((page_size * 9) + 12); - struct pageUpperEntry *pml4e, *pdpe, *pde; - struct pageTableEntry *pte; + uint64_t *pml4e, *pdpe, *pde; + uint64_t *pte; TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Unknown or unsupported guest mode, mode: 0x%x", vm->mode); @@ -257,24 +223,22 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, */ pml4e = virt_create_upper_pte(vm, vm->pgd >> vm->page_shift, vaddr, paddr, 3, page_size); - if (pml4e->page_size) + if (*pml4e & PTE_LARGE_MASK) return; - pdpe = virt_create_upper_pte(vm, pml4e->pfn, vaddr, paddr, 2, page_size); - if (pdpe->page_size) + pdpe = virt_create_upper_pte(vm, PTE_GET_PFN(*pml4e), vaddr, paddr, 2, page_size); + if (*pdpe & PTE_LARGE_MASK) return; - pde = virt_create_upper_pte(vm, pdpe->pfn, vaddr, paddr, 1, page_size); - if (pde->page_size) + pde = virt_create_upper_pte(vm, PTE_GET_PFN(*pdpe), vaddr, paddr, 1, page_size); + if (*pde & PTE_LARGE_MASK) return; /* Fill in page table entry. */ - pte = virt_get_pte(vm, pde->pfn, vaddr, 0); - TEST_ASSERT(!pte->present, + pte = virt_get_pte(vm, PTE_GET_PFN(*pde), vaddr, 0); + TEST_ASSERT(!(*pte & PTE_PRESENT_MASK), "PTE already present for 4k page at vaddr: 0x%lx\n", vaddr); - pte->pfn = paddr >> vm->page_shift; - pte->writable = true; - pte->present = 1; + *pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK | (paddr & PHYSICAL_PAGE_MASK); } void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) @@ -282,22 +246,22 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) __virt_pg_map(vm, vaddr, paddr, X86_PAGE_SIZE_4K); } -static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, +static uint64_t *_vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr) { uint16_t index[4]; - struct pageUpperEntry *pml4e, *pdpe, *pde; - struct pageTableEntry *pte; + uint64_t *pml4e, *pdpe, *pde; + uint64_t *pte; struct kvm_cpuid_entry2 *entry; struct kvm_sregs sregs; int max_phy_addr; - /* Set the bottom 52 bits. */ - uint64_t rsvd_mask = 0x000fffffffffffff; + uint64_t rsvd_mask = 0; entry = kvm_get_supported_cpuid_index(0x80000008, 0); max_phy_addr = entry->eax & 0x000000ff; - /* Clear the bottom bits of the reserved mask. */ - rsvd_mask = (rsvd_mask >> max_phy_addr) << max_phy_addr; + /* Set the high bits in the reserved mask. */ + if (max_phy_addr < 52) + rsvd_mask = GENMASK_ULL(51, max_phy_addr); /* * SDM vol 3, fig 4-11 "Formats of CR3 and Paging-Structure Entries @@ -307,7 +271,7 @@ static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vc */ vcpu_sregs_get(vm, vcpuid, &sregs); if ((sregs.efer & EFER_NX) == 0) { - rsvd_mask |= (1ull << 63); + rsvd_mask |= PTE_NX_MASK; } TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use " @@ -329,30 +293,29 @@ static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vc index[3] = (vaddr >> 39) & 0x1ffu; pml4e = addr_gpa2hva(vm, vm->pgd); - TEST_ASSERT(pml4e[index[3]].present, + TEST_ASSERT(pml4e[index[3]] & PTE_PRESENT_MASK, "Expected pml4e to be present for gva: 0x%08lx", vaddr); - TEST_ASSERT((*(uint64_t*)(&pml4e[index[3]]) & - (rsvd_mask | (1ull << 7))) == 0, + TEST_ASSERT((pml4e[index[3]] & (rsvd_mask | PTE_LARGE_MASK)) == 0, "Unexpected reserved bits set."); - pdpe = addr_gpa2hva(vm, pml4e[index[3]].pfn * vm->page_size); - TEST_ASSERT(pdpe[index[2]].present, + pdpe = addr_gpa2hva(vm, PTE_GET_PFN(pml4e[index[3]]) * vm->page_size); + TEST_ASSERT(pdpe[index[2]] & PTE_PRESENT_MASK, "Expected pdpe to be present for gva: 0x%08lx", vaddr); - TEST_ASSERT(pdpe[index[2]].page_size == 0, + TEST_ASSERT(!(pdpe[index[2]] & PTE_LARGE_MASK), "Expected pdpe to map a pde not a 1-GByte page."); - TEST_ASSERT((*(uint64_t*)(&pdpe[index[2]]) & rsvd_mask) == 0, + TEST_ASSERT((pdpe[index[2]] & rsvd_mask) == 0, "Unexpected reserved bits set."); - pde = addr_gpa2hva(vm, pdpe[index[2]].pfn * vm->page_size); - TEST_ASSERT(pde[index[1]].present, + pde = addr_gpa2hva(vm, PTE_GET_PFN(pdpe[index[2]]) * vm->page_size); + TEST_ASSERT(pde[index[1]] & PTE_PRESENT_MASK, "Expected pde to be present for gva: 0x%08lx", vaddr); - TEST_ASSERT(pde[index[1]].page_size == 0, + TEST_ASSERT(!(pde[index[1]] & PTE_LARGE_MASK), "Expected pde to map a pte not a 2-MByte page."); - TEST_ASSERT((*(uint64_t*)(&pde[index[1]]) & rsvd_mask) == 0, + TEST_ASSERT((pde[index[1]] & rsvd_mask) == 0, "Unexpected reserved bits set."); - pte = addr_gpa2hva(vm, pde[index[1]].pfn * vm->page_size); - TEST_ASSERT(pte[index[0]].present, + pte = addr_gpa2hva(vm, PTE_GET_PFN(pde[index[1]]) * vm->page_size); + TEST_ASSERT(pte[index[0]] & PTE_PRESENT_MASK, "Expected pte to be present for gva: 0x%08lx", vaddr); return &pte[index[0]]; @@ -360,7 +323,7 @@ static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vc uint64_t vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr) { - struct pageTableEntry *pte = _vm_get_page_table_entry(vm, vcpuid, vaddr); + uint64_t *pte = _vm_get_page_table_entry(vm, vcpuid, vaddr); return *(uint64_t *)pte; } @@ -368,18 +331,17 @@ uint64_t vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr) void vm_set_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr, uint64_t pte) { - struct pageTableEntry *new_pte = _vm_get_page_table_entry(vm, vcpuid, - vaddr); + uint64_t *new_pte = _vm_get_page_table_entry(vm, vcpuid, vaddr); *(uint64_t *)new_pte = pte; } void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) { - struct pageUpperEntry *pml4e, *pml4e_start; - struct pageUpperEntry *pdpe, *pdpe_start; - struct pageUpperEntry *pde, *pde_start; - struct pageTableEntry *pte, *pte_start; + uint64_t *pml4e, *pml4e_start; + uint64_t *pdpe, *pdpe_start; + uint64_t *pde, *pde_start; + uint64_t *pte, *pte_start; if (!vm->pgd_created) return; @@ -389,58 +351,58 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) fprintf(stream, "%*s index hvaddr gpaddr " "addr w exec dirty\n", indent, ""); - pml4e_start = (struct pageUpperEntry *) addr_gpa2hva(vm, vm->pgd); + pml4e_start = (uint64_t *) addr_gpa2hva(vm, vm->pgd); for (uint16_t n1 = 0; n1 <= 0x1ffu; n1++) { pml4e = &pml4e_start[n1]; - if (!pml4e->present) + if (!(*pml4e & PTE_PRESENT_MASK)) continue; - fprintf(stream, "%*spml4e 0x%-3zx %p 0x%-12lx 0x%-10lx %u " + fprintf(stream, "%*spml4e 0x%-3zx %p 0x%-12lx 0x%-10llx %u " " %u\n", indent, "", pml4e - pml4e_start, pml4e, - addr_hva2gpa(vm, pml4e), (uint64_t) pml4e->pfn, - pml4e->writable, pml4e->execute_disable); + addr_hva2gpa(vm, pml4e), PTE_GET_PFN(*pml4e), + !!(*pml4e & PTE_WRITABLE_MASK), !!(*pml4e & PTE_NX_MASK)); - pdpe_start = addr_gpa2hva(vm, pml4e->pfn * vm->page_size); + pdpe_start = addr_gpa2hva(vm, *pml4e & PHYSICAL_PAGE_MASK); for (uint16_t n2 = 0; n2 <= 0x1ffu; n2++) { pdpe = &pdpe_start[n2]; - if (!pdpe->present) + if (!(*pdpe & PTE_PRESENT_MASK)) continue; - fprintf(stream, "%*spdpe 0x%-3zx %p 0x%-12lx 0x%-10lx " + fprintf(stream, "%*spdpe 0x%-3zx %p 0x%-12lx 0x%-10llx " "%u %u\n", indent, "", pdpe - pdpe_start, pdpe, addr_hva2gpa(vm, pdpe), - (uint64_t) pdpe->pfn, pdpe->writable, - pdpe->execute_disable); + PTE_GET_PFN(*pdpe), !!(*pdpe & PTE_WRITABLE_MASK), + !!(*pdpe & PTE_NX_MASK)); - pde_start = addr_gpa2hva(vm, pdpe->pfn * vm->page_size); + pde_start = addr_gpa2hva(vm, *pdpe & PHYSICAL_PAGE_MASK); for (uint16_t n3 = 0; n3 <= 0x1ffu; n3++) { pde = &pde_start[n3]; - if (!pde->present) + if (!(*pde & PTE_PRESENT_MASK)) continue; fprintf(stream, "%*spde 0x%-3zx %p " - "0x%-12lx 0x%-10lx %u %u\n", + "0x%-12lx 0x%-10llx %u %u\n", indent, "", pde - pde_start, pde, addr_hva2gpa(vm, pde), - (uint64_t) pde->pfn, pde->writable, - pde->execute_disable); + PTE_GET_PFN(*pde), !!(*pde & PTE_WRITABLE_MASK), + !!(*pde & PTE_NX_MASK)); - pte_start = addr_gpa2hva(vm, pde->pfn * vm->page_size); + pte_start = addr_gpa2hva(vm, *pde & PHYSICAL_PAGE_MASK); for (uint16_t n4 = 0; n4 <= 0x1ffu; n4++) { pte = &pte_start[n4]; - if (!pte->present) + if (!(*pte & PTE_PRESENT_MASK)) continue; fprintf(stream, "%*spte 0x%-3zx %p " - "0x%-12lx 0x%-10lx %u %u " + "0x%-12lx 0x%-10llx %u %u " " %u 0x%-10lx\n", indent, "", pte - pte_start, pte, addr_hva2gpa(vm, pte), - (uint64_t) pte->pfn, - pte->writable, - pte->execute_disable, - pte->dirty, + PTE_GET_PFN(*pte), + !!(*pte & PTE_WRITABLE_MASK), + !!(*pte & PTE_NX_MASK), + !!(*pte & PTE_DIRTY_MASK), ((uint64_t) n1 << 27) | ((uint64_t) n2 << 18) | ((uint64_t) n3 << 9) @@ -558,8 +520,8 @@ static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector, vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) { uint16_t index[4]; - struct pageUpperEntry *pml4e, *pdpe, *pde; - struct pageTableEntry *pte; + uint64_t *pml4e, *pdpe, *pde; + uint64_t *pte; TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use " "unknown or unsupported guest mode, mode: 0x%x", vm->mode); @@ -572,22 +534,22 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) if (!vm->pgd_created) goto unmapped_gva; pml4e = addr_gpa2hva(vm, vm->pgd); - if (!pml4e[index[3]].present) + if (!(pml4e[index[3]] & PTE_PRESENT_MASK)) goto unmapped_gva; - pdpe = addr_gpa2hva(vm, pml4e[index[3]].pfn * vm->page_size); - if (!pdpe[index[2]].present) + pdpe = addr_gpa2hva(vm, PTE_GET_PFN(pml4e[index[3]]) * vm->page_size); + if (!(pdpe[index[2]] & PTE_PRESENT_MASK)) goto unmapped_gva; - pde = addr_gpa2hva(vm, pdpe[index[2]].pfn * vm->page_size); - if (!pde[index[1]].present) + pde = addr_gpa2hva(vm, PTE_GET_PFN(pdpe[index[2]]) * vm->page_size); + if (!(pde[index[1]] & PTE_PRESENT_MASK)) goto unmapped_gva; - pte = addr_gpa2hva(vm, pde[index[1]].pfn * vm->page_size); - if (!pte[index[0]].present) + pte = addr_gpa2hva(vm, PTE_GET_PFN(pde[index[1]]) * vm->page_size); + if (!(pte[index[0]] & PTE_PRESENT_MASK)) goto unmapped_gva; - return (pte[index[0]].pfn * vm->page_size) + (gva & 0xfffu); + return (PTE_GET_PFN(pte[index[0]]) * vm->page_size) + (gva & ~PAGE_MASK); unmapped_gva: TEST_FAIL("No mapping for vm virtual address, gva: 0x%lx", gva); diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index 62f2eb9ee3d5..8c4e811bd586 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -118,17 +118,10 @@ struct st_time { static int64_t smccc(uint32_t func, uint64_t arg) { - unsigned long ret; + struct arm_smccc_res res; - asm volatile( - "mov w0, %w1\n" - "mov x1, %2\n" - "hvc #0\n" - "mov %0, x0\n" - : "=r" (ret) : "r" (func), "r" (arg) : - "x0", "x1", "x2", "x3"); - - return ret; + smccc_hvc(func, arg, 0, 0, 0, 0, 0, 0, &res); + return res.a0; } static void check_status(struct st_time *st) diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index 52a3ef6629e8..76f65c22796f 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -29,7 +29,6 @@ #define X86_FEATURE_XSAVE (1 << 26) #define X86_FEATURE_OSXSAVE (1 << 27) -#define PAGE_SIZE (1 << 12) #define NUM_TILES 8 #define TILE_SIZE 1024 #define XSAVE_SIZE ((NUM_TILES * TILE_SIZE) + PAGE_SIZE) diff --git a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c index f070ff0224fa..aeb3850f81bd 100644 --- a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c +++ b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c @@ -12,7 +12,6 @@ #include "vmx.h" #define VCPU_ID 1 -#define PAGE_SIZE 4096 #define MAXPHYADDR 36 #define MEM_REGION_GVA 0x0000123456789000 diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c index a626d40fdb48..b4e0c860769e 100644 --- a/tools/testing/selftests/kvm/x86_64/smm_test.c +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -21,8 +21,6 @@ #define VCPU_ID 1 -#define PAGE_SIZE 4096 - #define SMRAM_SIZE 65536 #define SMRAM_MEMSLOT ((1 << 16) | 1) #define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c index e683d0ac3e45..19b35c607dc6 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c @@ -32,7 +32,6 @@ #define MSR_IA32_TSC_ADJUST 0x3b #endif -#define PAGE_SIZE 4096 #define VCPU_ID 5 #define TSC_ADJUST_VALUE (1ll << 32) diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index 865e17146815..bcd370827859 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -23,7 +23,6 @@ #define SHINFO_REGION_GVA 0xc0000000ULL #define SHINFO_REGION_GPA 0xc0000000ULL #define SHINFO_REGION_SLOT 10 -#define PAGE_SIZE 4096 #define DUMMY_REGION_GPA (SHINFO_REGION_GPA + (2 * PAGE_SIZE)) #define DUMMY_REGION_SLOT 11 diff --git a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c index adc94452b57c..b30fe9de1d4f 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c @@ -15,7 +15,6 @@ #define HCALL_REGION_GPA 0xc0000000ULL #define HCALL_REGION_SLOT 10 -#define PAGE_SIZE 4096 static struct kvm_vm *vm; diff --git a/tools/testing/selftests/vm/mremap_test.c b/tools/testing/selftests/vm/mremap_test.c index 7c0b0617b9f8..db0270127aeb 100644 --- a/tools/testing/selftests/vm/mremap_test.c +++ b/tools/testing/selftests/vm/mremap_test.c @@ -6,9 +6,11 @@ #include <errno.h> #include <stdlib.h> +#include <stdio.h> #include <string.h> #include <sys/mman.h> #include <time.h> +#include <stdbool.h> #include "../kselftest.h" @@ -64,6 +66,59 @@ enum { } /* + * Returns false if the requested remap region overlaps with an + * existing mapping (e.g text, stack) else returns true. + */ +static bool is_remap_region_valid(void *addr, unsigned long long size) +{ + void *remap_addr = NULL; + bool ret = true; + + /* Use MAP_FIXED_NOREPLACE flag to ensure region is not mapped */ + remap_addr = mmap(addr, size, PROT_READ | PROT_WRITE, + MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, + -1, 0); + + if (remap_addr == MAP_FAILED) { + if (errno == EEXIST) + ret = false; + } else { + munmap(remap_addr, size); + } + + return ret; +} + +/* Returns mmap_min_addr sysctl tunable from procfs */ +static unsigned long long get_mmap_min_addr(void) +{ + FILE *fp; + int n_matched; + static unsigned long long addr; + + if (addr) + return addr; + + fp = fopen("/proc/sys/vm/mmap_min_addr", "r"); + if (fp == NULL) { + ksft_print_msg("Failed to open /proc/sys/vm/mmap_min_addr: %s\n", + strerror(errno)); + exit(KSFT_SKIP); + } + + n_matched = fscanf(fp, "%llu", &addr); + if (n_matched != 1) { + ksft_print_msg("Failed to read /proc/sys/vm/mmap_min_addr: %s\n", + strerror(errno)); + fclose(fp); + exit(KSFT_SKIP); + } + + fclose(fp); + return addr; +} + +/* * Returns the start address of the mapping on success, else returns * NULL on failure. */ @@ -71,11 +126,18 @@ static void *get_source_mapping(struct config c) { unsigned long long addr = 0ULL; void *src_addr = NULL; + unsigned long long mmap_min_addr; + + mmap_min_addr = get_mmap_min_addr(); + retry: addr += c.src_alignment; + if (addr < mmap_min_addr) + goto retry; + src_addr = mmap((void *) addr, c.region_size, PROT_READ | PROT_WRITE, - MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, - -1, 0); + MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, + -1, 0); if (src_addr == MAP_FAILED) { if (errno == EPERM || errno == EEXIST) goto retry; @@ -90,8 +152,10 @@ retry: * alignment in the tests. */ if (((unsigned long long) src_addr & (c.src_alignment - 1)) || - !((unsigned long long) src_addr & c.src_alignment)) + !((unsigned long long) src_addr & c.src_alignment)) { + munmap(src_addr, c.region_size); goto retry; + } if (!src_addr) goto error; @@ -140,9 +204,20 @@ static long long remap_region(struct config c, unsigned int threshold_mb, if (!((unsigned long long) addr & c.dest_alignment)) addr = (void *) ((unsigned long long) addr | c.dest_alignment); + /* Don't destroy existing mappings unless expected to overlap */ + while (!is_remap_region_valid(addr, c.region_size) && !c.overlapping) { + /* Check for unsigned overflow */ + if (addr + c.dest_alignment < addr) { + ksft_print_msg("Couldn't find a valid region to remap to\n"); + ret = -1; + goto out; + } + addr += c.dest_alignment; + } + clock_gettime(CLOCK_MONOTONIC, &t_start); dest_addr = mremap(src_addr, c.region_size, c.region_size, - MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr); + MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr); clock_gettime(CLOCK_MONOTONIC, &t_end); if (dest_addr == MAP_FAILED) { @@ -193,7 +268,7 @@ static void run_mremap_test_case(struct test test_case, int *failures, if (remap_time < 0) { if (test_case.expect_failure) - ksft_test_result_pass("%s\n\tExpected mremap failure\n", + ksft_test_result_xfail("%s\n\tExpected mremap failure\n", test_case.name); else { ksft_test_result_fail("%s\n", test_case.name); diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh index 3b265f140c25..352ba00cf26b 100755 --- a/tools/testing/selftests/vm/run_vmtests.sh +++ b/tools/testing/selftests/vm/run_vmtests.sh @@ -291,11 +291,16 @@ echo "-------------------" echo "running mremap_test" echo "-------------------" ./mremap_test -if [ $? -ne 0 ]; then +ret_val=$? + +if [ $ret_val -eq 0 ]; then + echo "[PASS]" +elif [ $ret_val -eq $ksft_skip ]; then + echo "[SKIP]" + exitcode=$ksft_skip +else echo "[FAIL]" exitcode=1 -else - echo "[PASS]" fi echo "-----------------" diff --git a/tools/testing/selftests/wireguard/qemu/arch/i686.config b/tools/testing/selftests/wireguard/qemu/arch/i686.config index a85025d7206e..a9b4fe795048 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/i686.config +++ b/tools/testing/selftests/wireguard/qemu/arch/i686.config @@ -1,3 +1,4 @@ +CONFIG_ACPI=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_CMDLINE_BOOL=y diff --git a/tools/testing/selftests/wireguard/qemu/arch/x86_64.config b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config index 00a1ef4869d5..45dd53a0d760 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/x86_64.config +++ b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config @@ -1,3 +1,4 @@ +CONFIG_ACPI=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_CMDLINE_BOOL=y diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c index 222ecc81d7df..f4c2a6eb1666 100644 --- a/virt/kvm/dirty_ring.c +++ b/virt/kvm/dirty_ring.c @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +// SPDX-License-Identifier: GPL-2.0-only /* * KVM dirty ring implementation * diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index dfb7dabdbc63..6d971fb1b08d 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -164,6 +164,10 @@ __weak void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, { } +__weak void kvm_arch_guest_memory_reclaimed(struct kvm *kvm) +{ +} + bool kvm_is_zone_device_pfn(kvm_pfn_t pfn) { /* @@ -357,6 +361,12 @@ void kvm_flush_remote_tlbs(struct kvm *kvm) EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs); #endif +static void kvm_flush_shadow_all(struct kvm *kvm) +{ + kvm_arch_flush_shadow_all(kvm); + kvm_arch_guest_memory_reclaimed(kvm); +} + #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc, gfp_t gfp_flags) @@ -485,12 +495,15 @@ typedef bool (*hva_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range); typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start, unsigned long end); +typedef void (*on_unlock_fn_t)(struct kvm *kvm); + struct kvm_hva_range { unsigned long start; unsigned long end; pte_t pte; hva_handler_t handler; on_lock_fn_t on_lock; + on_unlock_fn_t on_unlock; bool flush_on_ret; bool may_block; }; @@ -578,8 +591,11 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, if (range->flush_on_ret && ret) kvm_flush_remote_tlbs(kvm); - if (locked) + if (locked) { KVM_MMU_UNLOCK(kvm); + if (!IS_KVM_NULL_FN(range->on_unlock)) + range->on_unlock(kvm); + } srcu_read_unlock(&kvm->srcu, idx); @@ -600,6 +616,7 @@ static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn, .pte = pte, .handler = handler, .on_lock = (void *)kvm_null_fn, + .on_unlock = (void *)kvm_null_fn, .flush_on_ret = true, .may_block = false, }; @@ -619,6 +636,7 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn .pte = __pte(0), .handler = handler, .on_lock = (void *)kvm_null_fn, + .on_unlock = (void *)kvm_null_fn, .flush_on_ret = false, .may_block = false, }; @@ -662,7 +680,7 @@ void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start, kvm->mmu_notifier_range_end = end; } else { /* - * Fully tracking multiple concurrent ranges has dimishing + * Fully tracking multiple concurrent ranges has diminishing * returns. Keep things simple and just find the minimal range * which includes the current and new ranges. As there won't be * enough information to subtract a range after its invalidate @@ -687,6 +705,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, .pte = __pte(0), .handler = kvm_unmap_gfn_range, .on_lock = kvm_inc_notifier_count, + .on_unlock = kvm_arch_guest_memory_reclaimed, .flush_on_ret = true, .may_block = mmu_notifier_range_blockable(range), }; @@ -741,6 +760,7 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn, .pte = __pte(0), .handler = (void *)kvm_null_fn, .on_lock = kvm_dec_notifier_count, + .on_unlock = (void *)kvm_null_fn, .flush_on_ret = false, .may_block = mmu_notifier_range_blockable(range), }; @@ -813,7 +833,7 @@ static void kvm_mmu_notifier_release(struct mmu_notifier *mn, int idx; idx = srcu_read_lock(&kvm->srcu); - kvm_arch_flush_shadow_all(kvm); + kvm_flush_shadow_all(kvm); srcu_read_unlock(&kvm->srcu, idx); } @@ -955,12 +975,6 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd) int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc + kvm_vcpu_stats_header.num_desc; - /* - * Force subsequent debugfs file creations to fail if the VM directory - * is not created. - */ - kvm->debugfs_dentry = ERR_PTR(-ENOENT); - if (!debugfs_initialized()) return 0; @@ -1081,6 +1095,12 @@ static struct kvm *kvm_create_vm(unsigned long type) BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); + /* + * Force subsequent debugfs file creations to fail if the VM directory + * is not created (by kvm_create_vm_debugfs()). + */ + kvm->debugfs_dentry = ERR_PTR(-ENOENT); + if (init_srcu_struct(&kvm->srcu)) goto out_err_no_srcu; if (init_srcu_struct(&kvm->irq_srcu)) @@ -1225,7 +1245,7 @@ static void kvm_destroy_vm(struct kvm *kvm) WARN_ON(rcuwait_active(&kvm->mn_memslots_update_rcuwait)); kvm->mn_active_invalidate_count = 0; #else - kvm_arch_flush_shadow_all(kvm); + kvm_flush_shadow_all(kvm); #endif kvm_arch_destroy_vm(kvm); kvm_destroy_devices(kvm); @@ -1652,6 +1672,7 @@ static void kvm_invalidate_memslot(struct kvm *kvm, * - kvm_is_visible_gfn (mmu_check_root) */ kvm_arch_flush_shadow_memslot(kvm, old); + kvm_arch_guest_memory_reclaimed(kvm); /* Was released by kvm_swap_active_memslots, reacquire. */ mutex_lock(&kvm->slots_arch_lock); @@ -1799,7 +1820,7 @@ static int kvm_set_memslot(struct kvm *kvm, /* * No need to refresh new->arch, changes after dropping slots_arch_lock - * will directly hit the final, active memsot. Architectures are + * will directly hit the final, active memslot. Architectures are * responsible for knowing that new->arch may be stale. */ kvm_commit_memory_region(kvm, old, new, change); @@ -4333,6 +4354,7 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) return 0; #endif case KVM_CAP_BINARY_STATS_FD: + case KVM_CAP_SYSTEM_EVENT_DATA: return 1; default: break; diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h index 34ca40823260..41da467d99c9 100644 --- a/virt/kvm/kvm_mm.h +++ b/virt/kvm/kvm_mm.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0-only +/* SPDX-License-Identifier: GPL-2.0-only */ #ifndef __KVM_MM_H__ #define __KVM_MM_H__ 1 |