diff options
286 files changed, 3845 insertions, 1610 deletions
@@ -857,6 +857,7 @@ Tobias Klauser <tklauser@distanz.ch> <klto@zhaw.ch> Tobias Klauser <tklauser@distanz.ch> <tklauser@nuerscht.ch> Tobias Klauser <tklauser@distanz.ch> <tklauser@xenon.tklauser.home> Todor Tomov <todor.too@gmail.com> <todor.tomov@linaro.org> +Tomasz Jeznach <tomasz.jeznach@linux.dev> <tjeznach@rivosinc.com> Tony Luck <tony.luck@intel.com> Trilok Soni <quic_tsoni@quicinc.com> <tsoni@codeaurora.org> TripleX Chung <xxx.phy@gmail.com> <triplex@zh-kernel.org> diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml index 57f59fe23e3f..4ea31e8fc4d1 100644 --- a/Documentation/netlink/genetlink-c.yaml +++ b/Documentation/netlink/genetlink-c.yaml @@ -69,6 +69,15 @@ properties: header: description: For C-compatible languages, header which already defines this value. type: string + scope: + description: | + Visibility of this definition. "uapi" (default) renders into + the uAPI header, "kernel" renders into the kernel-side + generated header, "user" renders into the user-side + generated header. When combined with `header:`, the + definition is not rendered, and the named header is + included only by code matching the scope. + enum: [ uapi, kernel, user ] type: enum: [ const, enum, flags ] doc: diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml index 66fb8653a344..f9c44747729a 100644 --- a/Documentation/netlink/genetlink-legacy.yaml +++ b/Documentation/netlink/genetlink-legacy.yaml @@ -83,6 +83,15 @@ properties: header: description: For C-compatible languages, header which already defines this value. type: string + scope: + description: | + Visibility of this definition. "uapi" (default) renders into + the uAPI header, "kernel" renders into the kernel-side + generated header, "user" renders into the user-side + generated header. When combined with `header:`, the + definition is not rendered, and the named header is + included only by code matching the scope. + enum: [ uapi, kernel, user ] type: enum: [ const, enum, flags, struct ] # Trim doc: diff --git a/Documentation/netlink/genetlink.yaml b/Documentation/netlink/genetlink.yaml index a1194d5d93fc..d3f3f3399ddf 100644 --- a/Documentation/netlink/genetlink.yaml +++ b/Documentation/netlink/genetlink.yaml @@ -55,6 +55,15 @@ properties: header: description: For C-compatible languages, header which already defines this value. type: string + scope: + description: | + Visibility of this definition. "uapi" (default) renders into + the uAPI header, "kernel" renders into the kernel-side + generated header, "user" renders into the user-side + generated header. When combined with `header:`, the + definition is not rendered, and the named header is + included only by code matching the scope. + enum: [ uapi, kernel, user ] type: enum: [ const, enum, flags ] doc: diff --git a/Documentation/netlink/netlink-raw.yaml b/Documentation/netlink/netlink-raw.yaml index dd98dda55bd0..4c436b59a34b 100644 --- a/Documentation/netlink/netlink-raw.yaml +++ b/Documentation/netlink/netlink-raw.yaml @@ -87,6 +87,15 @@ properties: header: description: For C-compatible languages, header which already defines this value. type: string + scope: + description: | + Visibility of this definition. "uapi" (default) renders into + the uAPI header, "kernel" renders into the kernel-side + generated header, "user" renders into the user-side + generated header. When combined with `header:`, the + definition is not rendered, and the named header is + included only by code matching the scope. + enum: [ uapi, kernel, user ] type: enum: [ const, enum, flags, struct ] # Trim doc: diff --git a/Documentation/netlink/specs/net_shaper.yaml b/Documentation/netlink/specs/net_shaper.yaml index 3f2ad772b64b..de01f922040a 100644 --- a/Documentation/netlink/specs/net_shaper.yaml +++ b/Documentation/netlink/specs/net_shaper.yaml @@ -34,6 +34,11 @@ doc: | definitions: - + type: const + name: max-handle-id + value: 0x3fffffe + scope: kernel + - type: enum name: scope doc: Defines the shaper @id interpretation. @@ -140,6 +145,8 @@ attribute-sets: - name: id type: u32 + checks: + max: max-handle-id doc: | Numeric identifier of a shaper. The id semantic depends on the scope. For @queue scope it's the queue id and for @node diff --git a/Documentation/process/index.rst b/Documentation/process/index.rst index dbd6ea16aca7..aa7c959a52b8 100644 --- a/Documentation/process/index.rst +++ b/Documentation/process/index.rst @@ -86,6 +86,7 @@ regressions and security problems. debugging/index handling-regressions security-bugs + threat-model cve embargoed-hardware-issues diff --git a/Documentation/process/security-bugs.rst b/Documentation/process/security-bugs.rst index 27b028e85861..3c51ddde31dd 100644 --- a/Documentation/process/security-bugs.rst +++ b/Documentation/process/security-bugs.rst @@ -66,6 +66,42 @@ In addition, the following information are highly desirable: the issue appear. It is useful to share them, as they can be helpful to keep end users protected during the time it takes them to apply the fix. +What qualifies as a security bug +-------------------------------- + +It is important that most bugs are handled publicly so as to involve the widest +possible audience and find the best solution. By nature, bugs that are handled +in closed discussions between a small set of participants are less likely to +produce the best possible fix (e.g., risk of missing valid use cases, limited +testing abilities). + +It turns out that the majority of the bugs reported via the security team are +just regular bugs that have been improperly qualified as security bugs due to +a lack of awareness of the Linux kernel's threat model, as described in +Documentation/process/threat-model.rst, and ought to have been sent through +the normal channels described in Documentation/admin-guide/reporting-issues.rst +instead. + +The security list exists for urgent bugs that grant an attacker a capability +they are not supposed to have on a correctly configured production system, and +can be easily exploited, representing an imminent threat to many users. Before +reporting, consider whether the issue actually crosses a trust boundary on such +a system. + +**If you resorted to AI assistance to identify a bug, you must treat it as +public**. While you may have valid reasons to believe it is not, the security +team's experience shows that bugs discovered this way systematically surface +simultaneously across multiple researchers, often on the same day. In this +case, do not publicly share a reproducer, as this could cause unintended harm; +just mention that one is available and maintainers might ask for it privately +if they need it. + +If you are unsure whether an issue qualifies, err on the side of reporting +privately: the security team would rather triage a borderline report than miss +a real vulnerability. Reporting ordinary bugs to the security list, however, +does not make them move faster and consumes triage capacity that other reports +need. + Identifying contacts -------------------- @@ -74,7 +110,7 @@ affected subsystem's maintainers and Cc: the Linux kernel security team. Do not send it to a public list at this stage, unless you have good reasons to consider the issue as being public or trivial to discover (e.g. result of a widely available automated vulnerability scanning tool that can be repeated by -anyone). +anyone, or use of AI-based tools). If you're sending a report for issues affecting multiple parts in the kernel, even if they're fairly similar issues, please send individual messages (think @@ -131,6 +167,64 @@ the Linux kernel security team only. Your message will be triaged, and you will receive instructions about whom to contact, if needed. Your message may equally be forwarded as-is to the relevant maintainers. +Responsible use of AI to find bugs +---------------------------------- + +A significant fraction of bug reports submitted to the security team are +actually the result of code reviews assisted by AI tools. While this can be an +efficient means to find bugs in rarely explored areas, it causes an overload on +maintainers, who are sometimes forced to ignore such reports due to their poor +quality or accuracy. As such, reporters must be particularly cautious about a +number of points which tend to make these reports needlessly difficult to +handle: + + * **Length**: AI-generated reports tend to be excessively long, containing + multiple sections and excessive detail. This makes it difficult to spot + important information such as affected files, versions, and impact. Please + ensure that a clear summary of the problem and all critical details are + presented first. Do not require triage engineers to scan multiple pages of + text. Configure your tools to produce concise, human-style reports. + + * **Formatting**: Most AI-generated reports are littered with Markdown tags. + These decorations complicate the search for important information and do + not survive the quoting processes involved in forwarding or replying. + Please **always convert your report to plain text** without any formatting + decorations before sending it. + + * **Impact Evaluation**: Many AI-generated reports lack an understanding + of the kernel's threat model (see Documentation/process/threat-model.rst) + and go to great lengths inventing theoretical consequences. This adds + noise and complicates triage. Please stick to verifiable facts (e.g., + "this bug permits any user to gain CAP_NET_ADMIN") without enumerating + speculative implications. Have your tool read this documentation as + part of the evaluation process. + + * **Reproducer**: AI-based tools are often capable of generating reproducers. + Please always ensure your tool provides one and **test it thoroughly**. If + the reproducer does not work, or if the tool cannot produce one, the + validity of the report should be seriously questioned. Note that since the + report will be posted to a public list, the reproducer should only be + shared upon maintainers' request. + + * **Propose a Fix**: Many AI tools are actually better at writing code than + evaluating it. Please ask your tool to propose a fix and **test it** before + reporting the problem. If the fix cannot be tested because it relies on + rare hardware or almost extinct network protocols, the issue is likely not + a security bug. In any case, if a fix is proposed, it must adhere to + Documentation/process/submitting-patches.rst and include a 'Fixes:' tag + designating the commit that introduced the bug. + +Failure to consider these points exposes your report to the risk of being +ignored. + +Use common sense when evaluating the report. If the affected file has not been +touched for more than one year and is maintained by a single individual, it is +likely that usage has declined and exposed users are virtually non-existent +(e.g., drivers for very old hardware, obsolete filesystems). In such cases, +there is no need to consume a maintainer's time with an unimportant report. If +the issue is clearly trivial and publicly discoverable, you should report it +directly to the public mailing lists. + Sending the report ------------------ @@ -148,7 +242,15 @@ run additional tests. Reports where the reporter does not respond promptly or cannot effectively discuss their findings may be abandoned if the communication does not quickly improve. -The report must be sent to maintainers, with the security team in ``Cc:``. +The report must be sent to maintainers. If there are two or fewer +recipients in your message, you must also always Cc: the Linux kernel +security team who will ensure the message is delivered to the proper +people, and will be able to assist small maintainer teams with processes +they may not be familiar with. For larger teams, Cc: the Linux kernel +security team for your first few reports or when seeking specific help, +such as when resending a message which got no response within a week. +Once you have become comfortable with the process for a few reports, it is +no longer necessary to Cc: the security list when sending to large teams. The Linux kernel security team can be contacted by email at <security@kernel.org>. This is a private list of security officers who will help verify the bug report and assist developers working on a fix. diff --git a/Documentation/process/threat-model.rst b/Documentation/process/threat-model.rst new file mode 100644 index 000000000000..f177b8d3c1ca --- /dev/null +++ b/Documentation/process/threat-model.rst @@ -0,0 +1,235 @@ +The Linux Kernel threat model +============================= + +There are a lot of assumptions regarding what the kernel does and does not +protect against. These assumptions tend to cause confusion for bug reports +(:doc:`security-related ones <security-bugs>` vs :doc:`non-security ones +<../admin-guide/reporting-issues>`), and can complicate security enforcement +when the responsibilities for some boundaries is not clear between the kernel, +distros, administrators and users. + +This document tries to clarify the responsibilities of the kernel in this +domain. + +The kernel's responsibilities +----------------------------- + +The kernel abstracts access to local hardware resources and to remote systems +in a way that allows multiple local users to get a fair share of the available +resources granted to them, and, when the underlying hardware permits, to assign +a level of confidentiality to their communications and to the data they are +processing or storing. + +The kernel assumes that the underlying hardware behaves according to its +specifications. This includes the integrity of the CPU's instruction set, the +transparency of the branch prediction unit and the cache units, the consistency +of the Memory Management Unit (MMU), the isolation of DMA-capable peripherals +(e.g., via IOMMU), state transitions in controllers, ranges of values read from +registers, the respect of documented hardware limitations, etc. + +When hardware fails to maintain its specified isolation (e.g., CPU bugs, +side-channels, hardware response to unexpected inputs), the kernel will usually +attempt to implement reasonable mitigations. These are best-effort measures +intended to reduce the attack surface or elevate the cost of an attack within +the limits of the hardware's facilities; they do not constitute a +kernel-provided safety guarantee. + +Users always perform their activities under the authority of an administrator +who is able to grant or deny various types of permissions that may affect how +users benefit from available resources, or the level of confidentiality of +their activities. Administrators may also delegate all or part of their own +permissions to some users, particularly via capabilities but not only. All this +is performed via configuration (sysctl, file-system permissions etc). + +The Linux Kernel applies a certain collection of default settings that match +its threat model. Distros have their own threat model and will come with their +own configuration presets, that the administrator may have to adjust to better +suit their expectations (relax or restrict). + +By default, the Linux Kernel guarantees the following protections when running +on common processors featuring privilege levels and memory management units: + +* **User-based isolation**: an unprivileged user may restrict access to their + own data from other unprivileged users running on the same system. This + includes: + + * stored data, via file system permissions + * in-memory data (pages are not accessible by default to other users) + * process activity (ptrace is not permitted to other users) + * inter-process communication (other users may not observe data exchanged via + UNIX domain sockets or other IPC mechanisms). + * network communications within the same or with other systems + +* **Capability-based protection**: + + * users not having elevated capabilities (including but not limited to + CAP_SYS_ADMIN) may not alter the + kernel's configuration, memory nor state, change other users' view of the + file system layout, grant any user capabilities they do not have, nor + affect the system's availability (shutdown, reboot, panic, hang, or making + the system unresponsive via unbounded resource exhaustion). + * users not having the ``CAP_NET_ADMIN`` capability may not alter the network + configuration, intercept nor spoof network communications from other users + nor systems. + * users not having ``CAP_SYS_PTRACE`` may not observe other users' processes + activities. + +When ``CONFIG_USER_NS`` is set, the kernel also permits unprivileged users to +create their own user namespace in which they have all capabilities, but with a +number of restrictions (they may not perform actions that have impacts on the +initial user namespace, such as changing time, loading modules or mounting +block devices). Please refer to ``user_namespaces(7)`` for more details, the +possibilities of user namespaces are not covered in this document. + +The kernel also offers a lot of troubleshooting and debugging facilities, which +can constitute attack vectors when placed in wrong hands. While some of them +are designed to be accessible to regular local users with a low risk (e.g. +kernel logs via ``/proc/kmsg``), some would expose enough information to +represent a risk in most places and the decision to expose them is under the +administrator's responsibility (perf events, traces), and others are not +designed to be accessed by non-privileged users (e.g. debugfs). Access to these +facilities by a user who has been explicitly granted permission by an +administrator does not constitute a security breach. + +Bugs that permit to violate the principles above constitute security breaches. +However, bugs that permit one violation only once another one was already +achieved are only weaknesses. The kernel applies a number of self-protection +measures whose purpose is to avoid crossing a security boundary when certain +classes of bugs are found, but a failure of these extra protections do not +constitute a vulnerability alone. + +What does not constitute a security bug +--------------------------------------- + +In the Linux kernel's threat model, the following classes of problems are +**NOT** considered as Linux Kernel security bugs. However, when it is believed +that the kernel could do better, they should be reported, so that they can be +reviewed and fixed where reasonably possible, but they will be handled as any +regular bug: + +* **Configuration**: + + * outdated kernels and particularly end-of-life branches are out of the scope + of the kernel's threat model: administrators are responsible for keeping + their system up to date. For a bug to qualify as a security bug, it must be + demonstrated that it affects actively maintained versions. + + * build-level: changes to the kernel configuration that are explicitly + documented as lowering the security level (e.g. ``CONFIG_NOMMU``), or + targeted at developers only. + + * OS-level: changes to command line parameters, sysctls, filesystem + permissions, user capabilities, exposure of privileged interfaces, that + explicitly increase exposure by either offering non-default access to + unprivileged users, or reduce the kernel's ability to enforce some + protections or mitigations. Example: write access to procfs or debugfs. + + * issues triggered only when using features intended for development or + debugging (e.g., LOCKDEP, KASAN, FAULT_INJECTION): these features are known + to introduce overhead and potential instability and are not intended for + production use. + + * issues affecting drivers exposed under CONFIG_STAGING, as well as features + marked EXPERIMENTAL in the configuration. + + * loading of explicitly insecure/broken/staging modules, and generally any + using any subsystem marked as experimental or not intended for production + use. + + * running out-of-tree modules or unofficial kernel forks; these should be + reported to the relevant vendor. + +* **Excess of initial privileges**: + + * actions performed by a user already possessing the privileges required to + perform that action or modify that state (e.g. ``CAP_SYS_ADMIN``, + ``CAP_NET_ADMIN``, ``CAP_SYS_RAWIO``, ``CAP_SYS_MODULE`` with no further + boundary being crossed). + + * actions performed in user namespace that do not bypass the restrictions + imposed to the initial user (e.g. ptrace usage, signal delivery, resource + usage, access to FS/device/sysctl/memory, network binding, system/network + configuration etc). + + * anything performed by the root user in the initial namespace (e.g. kernel + oops when writing to a privileged device). + +* **Out of production use**: + + This covers theoretical/probabilistic attacks that rely on laboratory + conditions with zero system noise, or those requiring an unrealistic number + of attempts (e.g., billions of trials) that would be detected by standard + system monitoring long before success, such as: + + * prediction of random numbers that only works in a totally silent + environment (such as IP ID, TCP ports or sequence numbers that can only be + guessed in a lab). + + * activity observation and information leaks based on probabilistic + approaches that are prone to measurement noise and not realistically + reproducible on a production system. + + * issues that can only be triggered by heavy attacks (e.g. brute force) whose + impact on the system makes it unlikely or impossible to remain undetected + before they succeed (e.g. consuming all memory before succeeding). + + * problems seen only under development simulators, emulators, or combinations + that do not exist on real systems at the time of reporting (issues + involving tens of millions of threads, tens of thousands of CPUs, + unrealistic CPU frequencies, RAM sizes or disk capacities, network speeds. + + * issues whose reproduction requires hardware modification or emulation, + including fake USB devices that pretend to be another one. + + * as well as issues that can be triggered at a cost that is orders of + magnitude higher than the expected benefits (e.g. fully functional keyboard + emulator only to retrieve 7 uninitialized bytes in a structure, or + brute-force method involving millions of connection attempts to guess a + port number). + +* **Hardening failures**: + + * ability to bypass some of the kernel's hardening measures with no + demonstrable exploit path (e.g. ASLR bypass, events timing or probing with + no demonstrable consequence). These are just weaknesses, not + vulnerabilities. + + * missing argument checks and failure to report certain errors with no + immediate consequence. + +* **Random information leaks**: + + This concerns information leaks of small data parts that happen to be there + and that cannot be chosen by the attacker, or face access restrictions: + + * structure padding reported by syscalls or other interfaces. + + * identifiers, partial data, non-terminated strings reported in error + messages. + + * Leaks of kernel memory addresses/pointers do not constitute an immediately + exploitable vector and are not security bugs, though they must be reported + and fixed. + +* **Crafted file system images**: + + * bugs triggered by mounting a corrupted or maliciously crafted file system + image are generally not security bugs, as the kernel assumes the underlying + storage media is under the administrator's control, unless the filesystem + driver is specifically documented as being hardened against untrusted media. + + * issues that are resolved, mitigated, or detected by running a filesystem + consistency check (fsck) on the image prior to mounting. + +* **Physical access**: + + Issues that require physical access to the machine, hardware modification, or + the use of specialized hardware (e.g., logic analyzers, DMA-attack tools over + PCI-E/Thunderbolt) are out of scope unless the system is explicitly + configured with technologies meant to defend against such attacks + (e.g. IOMMU). + +* **Functional and performance regressions**: + + Any issue that can be mitigated by setting proper permissions and limits + doesn't qualify as a security bug. diff --git a/Documentation/virt/kvm/x86/amd-memory-encryption.rst b/Documentation/virt/kvm/x86/amd-memory-encryption.rst index b2395dd4769d..bd04a908a8db 100644 --- a/Documentation/virt/kvm/x86/amd-memory-encryption.rst +++ b/Documentation/virt/kvm/x86/amd-memory-encryption.rst @@ -656,8 +656,8 @@ References See [white-paper]_, [api-spec]_, [amd-apm]_, [kvm-forum]_, and [snp-fw-abi]_ for more info. -.. [white-paper] https://developer.amd.com/wordpress/media/2013/12/AMD_Memory_Encryption_Whitepaper_v7-Public.pdf -.. [api-spec] https://support.amd.com/TechDocs/55766_SEV-KM_API_Specification.pdf -.. [amd-apm] https://support.amd.com/TechDocs/24593.pdf (section 15.34) +.. [white-paper] https://docs.amd.com/v/u/en-US/memory-encryption-white-paper +.. [api-spec] https://docs.amd.com/v/u/en-US/55766_PUB_3.24_SEV_API +.. [amd-apm] https://docs.amd.com/v/u/en-US/24593_3.44_APM_Vol2 (section 15.34) .. [kvm-forum] https://www.linux-kvm.org/images/7/74/02x08A-Thomas_Lendacky-AMDs_Virtualizatoin_Memory_Encryption_Technology.pdf -.. [snp-fw-abi] https://www.amd.com/system/files/TechDocs/56860.pdf +.. [snp-fw-abi] https://www.amd.com/content/dam/amd/en/documents/developer/56860.pdf diff --git a/MAINTAINERS b/MAINTAINERS index b2040011a386..c2c6d79275c6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -68,6 +68,12 @@ Maintainers List first. When adding to this list, please keep the entries in alphabetical order. +3C509 NETWORK DRIVER +M: "Maciej W. Rozycki" <macro@orcam.me.uk> +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/ethernet/3com/3c509.c + 3C59X NETWORK DRIVER M: Steffen Klassert <klassert@kernel.org> L: netdev@vger.kernel.org @@ -2015,7 +2021,7 @@ F: Documentation/hwmon/aquacomputer_d5next.rst F: drivers/hwmon/aquacomputer_d5next.c AQUANTIA ETHERNET DRIVER (atlantic) -M: Igor Russkikh <irusskikh@marvell.com> +M: Sukhdeep Singh <sukhdeeps@marvell.com> L: netdev@vger.kernel.org S: Maintained W: https://www.marvell.com/ @@ -2024,7 +2030,7 @@ F: Documentation/networking/device_drivers/ethernet/aquantia/atlantic.rst F: drivers/net/ethernet/aquantia/atlantic/ AQUANTIA ETHERNET DRIVER PTP SUBSYSTEM -M: Egor Pomozov <epomozov@marvell.com> +M: Sukhdeep Singh <sukhdeeps@marvell.com> L: netdev@vger.kernel.org S: Maintained W: http://www.aquantia.com @@ -4181,8 +4187,8 @@ F: include/uapi/linux/sonet.h F: net/atm/ ATMEL MACB ETHERNET DRIVER -M: Nicolas Ferre <nicolas.ferre@microchip.com> -M: Claudiu Beznea <claudiu.beznea@tuxon.dev> +M: Théo Lebrun <theo.lebrun@bootlin.com> +R: Conor Dooley <conor.dooley@microchip.com> S: Maintained F: drivers/net/ethernet/cadence/ @@ -14055,6 +14061,7 @@ KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64) M: Marc Zyngier <maz@kernel.org> M: Oliver Upton <oupton@kernel.org> R: Joey Gouly <joey.gouly@arm.com> +R: Steffen Eiden <seiden@linux.ibm.com> R: Suzuki K Poulose <suzuki.poulose@arm.com> R: Zenghui Yu <yuzenghui@huawei.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -22944,7 +22951,7 @@ N: riscv K: riscv RISC-V IOMMU -M: Tomasz Jeznach <tjeznach@rivosinc.com> +M: Tomasz Jeznach <tomasz.jeznach@linux.dev> L: iommu@lists.linux.dev L: linux-riscv@lists.infradead.org S: Maintained diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h index 091544e6af44..dc2957662ff2 100644 --- a/arch/arm64/include/asm/kvm_nested.h +++ b/arch/arm64/include/asm/kvm_nested.h @@ -23,6 +23,7 @@ static inline u64 tcr_el2_ps_to_tcr_el1_ips(u64 tcr_el2) static inline u64 translate_tcr_el2_to_tcr_el1(u64 tcr) { return TCR_EPD1_MASK | /* disable TTBR1_EL1 */ + ((tcr & TCR_EL2_DS) ? TCR_DS : 0) | ((tcr & TCR_EL2_TBI) ? TCR_TBI0 : 0) | tcr_el2_ps_to_tcr_el1_ips(tcr) | (tcr & TCR_EL2_TG0_MASK) | diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 736561480f36..7aa08d59d494 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -844,7 +844,7 @@ #define INIT_SCTLR_EL2_MMU_ON \ (SCTLR_ELx_M | SCTLR_ELx_C | SCTLR_ELx_SA | SCTLR_ELx_I | \ SCTLR_ELx_IESB | SCTLR_ELx_WXN | ENDIAN_SET_EL2 | \ - SCTLR_ELx_ITFSB | SCTLR_EL2_RES1) + SCTLR_ELx_ITFSB | SCTLR_ELx_EIS | SCTLR_ELx_EOS | SCTLR_EL2_RES1) #define INIT_SCTLR_EL2_MMU_OFF \ (SCTLR_EL2_RES1 | ENDIAN_SET_EL2) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 8bb2c7422cc8..34c9950884d5 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -4,6 +4,7 @@ * Author: Christoffer Dall <c.dall@virtualopensystems.com> */ +#include <linux/arm-smccc.h> #include <linux/bug.h> #include <linux/cpu_pm.h> #include <linux/errno.h> @@ -2638,6 +2639,22 @@ static int init_pkvm_host_sve_state(void) return 0; } +static int pkvm_check_sme_dvmsync_fw_call(void) +{ + struct arm_smccc_res res; + + if (!cpus_have_final_cap(ARM64_WORKAROUND_4193714)) + return 0; + + arm_smccc_1_1_smc(ARM_SMCCC_CPU_WORKAROUND_4193714, &res); + if (res.a0) { + kvm_err("pKVM requires firmware support for C1-Pro erratum 4193714\n"); + return -ENODEV; + } + + return 0; +} + /* * Finalizes the initialization of hyp mode, once everything else is initialized * and the initialziation process cannot fail. @@ -2838,6 +2855,10 @@ static int __init init_hyp_mode(void) if (err) goto out_err; + err = pkvm_check_sme_dvmsync_fw_call(); + if (err) + goto out_err; + err = kvm_hyp_init_protection(hyp_va_bits); if (err) { kvm_err("Failed to init hyp memory protection\n"); diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 98b2976837b1..bf0eb5e43427 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -245,7 +245,7 @@ static inline void __activate_traps_ich_hfgxtr(struct kvm_vcpu *vcpu) __activate_fgt(hctxt, vcpu, ICH_HFGITR_EL2); } -#define __deactivate_fgt(htcxt, vcpu, reg) \ +#define __deactivate_fgt(hctxt, vcpu, reg) \ do { \ write_sysreg_s(ctxt_sys_reg(hctxt, reg), \ SYS_ ## reg); \ diff --git a/arch/arm64/kvm/hyp/nvhe/clock.c b/arch/arm64/kvm/hyp/nvhe/clock.c index 32fc4313fe43..a7fc61976fd0 100644 --- a/arch/arm64/kvm/hyp/nvhe/clock.c +++ b/arch/arm64/kvm/hyp/nvhe/clock.c @@ -35,6 +35,9 @@ void trace_clock_update(u32 mult, u32 shift, u64 epoch_ns, u64 epoch_cyc) struct clock_data *clock = &trace_clock_data; u64 bank = clock->cur ^ 1; + if (!mult || shift >= 64) + return; + clock->data[bank].mult = mult; clock->data[bank].shift = shift; clock->data[bank].epoch_ns = epoch_ns; diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 28a471d1927c..25f04629014e 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -5,6 +5,7 @@ */ #include <linux/kvm_host.h> + #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> @@ -14,6 +15,7 @@ #include <hyp/fault.h> +#include <nvhe/arm-smccc.h> #include <nvhe/gfp.h> #include <nvhe/memory.h> #include <nvhe/mem_protect.h> @@ -29,6 +31,19 @@ static struct hyp_pool host_s2_pool; static DEFINE_PER_CPU(struct pkvm_hyp_vm *, __current_vm); #define current_vm (*this_cpu_ptr(&__current_vm)) +static void pkvm_sme_dvmsync_fw_call(void) +{ + if (alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714)) { + struct arm_smccc_res res; + + /* + * Ignore the return value. Probing for the workaround + * availability took place in init_hyp_mode(). + */ + hyp_smccc_1_1_smc(ARM_SMCCC_CPU_WORKAROUND_4193714, &res); + } +} + static void guest_lock_component(struct pkvm_hyp_vm *vm) { hyp_spin_lock(&vm->lock); @@ -574,8 +589,14 @@ static int host_stage2_set_owner_metadata_locked(phys_addr_t addr, u64 size, ret = host_stage2_try(kvm_pgtable_stage2_annotate, &host_mmu.pgt, addr, size, &host_s2_pool, KVM_HOST_INVALID_PTE_TYPE_DONATION, annotation); - if (!ret) + if (!ret) { + /* + * After stage2 maintenance has happened, but before the page + * owner has changed. + */ + pkvm_sme_dvmsync_fw_call(); __host_update_page_state(addr, size, PKVM_NOPAGE); + } return ret; } @@ -1369,6 +1390,22 @@ unlock: return ret && ret != -EHWPOISON ? ret : 0; } +/* + * share/donate install at most one stage-2 leaf (PAGE_SIZE, or one + * KVM_PGTABLE_LAST_LEVEL - 1 block for share). kvm_mmu_cache_min_pages() + * bounds the worst-case allocation: exact for the PAGE_SIZE leaf, + * conservative by one for the block. + */ +static int __guest_check_pgtable_memcache(struct pkvm_hyp_vcpu *vcpu) +{ + struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); + + if (vcpu->vcpu.arch.pkvm_memcache.nr_pages < kvm_mmu_cache_min_pages(vm->pgt.mmu)) + return -ENOMEM; + + return 0; +} + int __pkvm_host_donate_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu) { struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); @@ -1388,6 +1425,10 @@ int __pkvm_host_donate_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu) if (ret) goto unlock; + ret = __guest_check_pgtable_memcache(vcpu); + if (ret) + goto unlock; + meta = host_stage2_encode_gfn_meta(vm, gfn); WARN_ON(host_stage2_set_owner_metadata_locked(phys, PAGE_SIZE, PKVM_ID_GUEST, meta)); @@ -1453,6 +1494,10 @@ int __pkvm_host_share_guest(u64 pfn, u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu } } + ret = __guest_check_pgtable_memcache(vcpu); + if (ret) + goto unlock; + for_each_hyp_page(page, phys, size) { set_host_state(page, PKVM_PAGE_SHARED_OWNED); page->host_share_guest_count++; diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index e7496eb85628..eb1c10120f9f 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -752,16 +752,30 @@ static struct pkvm_hyp_vcpu selftest_vcpu = { struct pkvm_hyp_vcpu *init_selftest_vm(void *virt) { struct hyp_page *p = hyp_virt_to_page(virt); + unsigned long min_pages, seeded = 0; int i; selftest_vm.kvm.arch.mmu.vtcr = host_mmu.arch.mmu.vtcr; WARN_ON(kvm_guest_prepare_stage2(&selftest_vm, virt)); + /* + * Mirror pkvm_refill_memcache() for the share/donate pre-checks; + * the selftest invokes those functions directly and would + * otherwise see an empty memcache. + */ + min_pages = kvm_mmu_cache_min_pages(&selftest_vm.kvm.arch.mmu); + for (i = 0; i < pkvm_selftest_pages(); i++) { if (p[i].refcount) continue; p[i].refcount = 1; - hyp_put_page(&selftest_vm.pool, hyp_page_to_virt(&p[i])); + if (seeded < min_pages) { + push_hyp_memcache(&selftest_vcpu.vcpu.arch.pkvm_memcache, + hyp_page_to_virt(&p[i]), hyp_virt_to_phys); + seeded++; + } else { + hyp_put_page(&selftest_vm.pool, hyp_page_to_virt(&p[i])); + } } selftest_vm.kvm.arch.pkvm.handle = __pkvm_reserve_vm(); diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 9db3f11a4754..1e8995add14f 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -663,7 +663,8 @@ static void __noreturn __hyp_call_panic(u64 spsr, u64 elr, u64 par) host_ctxt = host_data_ptr(host_ctxt); vcpu = host_ctxt->__hyp_running_vcpu; - __deactivate_traps(vcpu); + if (vcpu) + __deactivate_traps(vcpu); sysreg_restore_host_state_vhe(host_ctxt); panic("HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n", diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index d089c107d9b7..4da9281312eb 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1576,21 +1576,24 @@ struct kvm_s2_fault_desc { static int gmem_abort(const struct kvm_s2_fault_desc *s2fd) { bool write_fault, exec_fault; + bool perm_fault = kvm_vcpu_trap_is_permission_fault(s2fd->vcpu); enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_SHARED; enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R; struct kvm_pgtable *pgt = s2fd->vcpu->arch.hw_mmu->pgt; unsigned long mmu_seq; struct page *page; struct kvm *kvm = s2fd->vcpu->kvm; - void *memcache; + void *memcache = NULL; kvm_pfn_t pfn; gfn_t gfn; int ret; - memcache = get_mmu_memcache(s2fd->vcpu); - ret = topup_mmu_memcache(s2fd->vcpu, memcache); - if (ret) - return ret; + if (!perm_fault) { + memcache = get_mmu_memcache(s2fd->vcpu); + ret = topup_mmu_memcache(s2fd->vcpu, memcache); + if (ret) + return ret; + } if (s2fd->nested) gfn = kvm_s2_trans_output(s2fd->nested) >> PAGE_SHIFT; @@ -1631,9 +1634,19 @@ static int gmem_abort(const struct kvm_s2_fault_desc *s2fd) goto out_unlock; } - ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, s2fd->fault_ipa, PAGE_SIZE, - __pfn_to_phys(pfn), prot, - memcache, flags); + if (perm_fault) { + /* + * Drop the SW bits in favour of those stored in the + * PTE, which will be preserved. + */ + prot &= ~KVM_NV_GUEST_MAP_SZ; + ret = KVM_PGT_FN(kvm_pgtable_stage2_relax_perms)(pgt, s2fd->fault_ipa, + prot, flags); + } else { + ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, s2fd->fault_ipa, PAGE_SIZE, + __pfn_to_phys(pfn), prot, + memcache, flags); + } out_unlock: kvm_release_faultin_page(kvm, page, !!ret, prot & KVM_PGTABLE_PROT_W); diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 07f59c3b9a7b..3bcdbbbb6891 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -3310,8 +3310,7 @@ static void aen_host_forward(unsigned long si) struct zpci_gaite *gaite; struct kvm *kvm; - gaite = (struct zpci_gaite *)aift->gait + - (si * sizeof(struct zpci_gaite)); + gaite = aift->gait + si; if (gaite->count == 0) return; if (gaite->aisb != 0) diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index 86d93e8dddae..5b075c38998e 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -166,7 +166,7 @@ static int kvm_zpci_set_airq(struct zpci_dev *zdev) fib.fmt0.noi = airq_iv_end(zdev->aibv); fib.fmt0.aibv = virt_to_phys(zdev->aibv->vector); fib.fmt0.aibvo = 0; - fib.fmt0.aisb = virt_to_phys(aift->sbv->vector + (zdev->aisb / 64) * 8); + fib.fmt0.aisb = virt_to_phys(aift->sbv->vector) + (zdev->aisb / 64) * 8; fib.fmt0.aisbo = zdev->aisb & 63; fib.gd = zdev->gisa; @@ -290,8 +290,7 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, phys_to_virt(fib->fmt0.aibv)); spin_lock_irq(&aift->gait_lock); - gaite = (struct zpci_gaite *)aift->gait + (zdev->aisb * - sizeof(struct zpci_gaite)); + gaite = aift->gait + zdev->aisb; /* If assist not requested, host will get all alerts */ if (assist) @@ -309,7 +308,7 @@ static int kvm_s390_pci_aif_enable(struct zpci_dev *zdev, struct zpci_fib *fib, /* Update guest FIB for re-issue */ fib->fmt0.aisbo = zdev->aisb & 63; - fib->fmt0.aisb = virt_to_phys(aift->sbv->vector + (zdev->aisb / 64) * 8); + fib->fmt0.aisb = virt_to_phys(aift->sbv->vector) + (zdev->aisb / 64) * 8; fib->fmt0.isc = gisc; /* Save some guest fib values in the host for later use */ @@ -357,8 +356,7 @@ static int kvm_s390_pci_aif_disable(struct zpci_dev *zdev, bool force) if (zdev->kzdev->fib.fmt0.aibv == 0) goto out; spin_lock_irq(&aift->gait_lock); - gaite = (struct zpci_gaite *)aift->gait + (zdev->aisb * - sizeof(struct zpci_gaite)); + gaite = aift->gait + zdev->aisb; isc = gaite->gisc; gaite->count--; if (gaite->count == 0) { diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index a14a0f43e04a..86554de9a3f5 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -803,9 +803,10 @@ #define MSR_AMD64_LBR_SELECT 0xc000010e /* Zen4 */ -#define MSR_ZEN4_BP_CFG 0xc001102e +#define MSR_ZEN4_BP_CFG 0xc001102e #define MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT 4 #define MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT 5 +#define MSR_ZEN2_BP_CFG_BUG_FIX_BIT 33 /* Fam 19h MSRs */ #define MSR_F19H_UMC_PERF_CTL 0xc0010800 diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c index d7c8ef1e354d..be4c5e9e5ff6 100644 --- a/arch/x86/kernel/acpi/cppc.c +++ b/arch/x86/kernel/acpi/cppc.c @@ -88,19 +88,19 @@ static void amd_set_max_freq_ratio(void) rc = cppc_get_perf_caps(0, &perf_caps); if (rc) { - pr_warn("Could not retrieve perf counters (%d)\n", rc); + pr_debug("Could not retrieve perf counters (%d)\n", rc); return; } rc = amd_get_boost_ratio_numerator(0, &numerator); if (rc) { - pr_warn("Could not retrieve highest performance (%d)\n", rc); + pr_debug("Could not retrieve highest performance (%d)\n", rc); return; } nominal_perf = perf_caps.nominal_perf; if (!nominal_perf) { - pr_warn("Could not retrieve nominal performance\n"); + pr_debug("Could not retrieve nominal performance\n"); return; } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 2d9ae6ab1701..2f8e8ff2d000 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -989,6 +989,9 @@ static void init_amd_zen2(struct cpuinfo_x86 *c) /* Correct misconfigured CPUID on some clients. */ clear_cpu_cap(c, X86_FEATURE_INVLPGB); + + if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) + msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN2_BP_CFG_BUG_FIX_BIT); } static void init_amd_zen3(struct cpuinfo_x86 *c) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index c8c6cc0406d6..8013dccb3110 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -4481,7 +4481,7 @@ static const struct opcode opcode_map_0f_38[256] = { X16(N), X16(N), /* 0x20 - 0x2f */ X8(N), - X2(N), GP(SrcReg | DstMem | ModRM | Mov | Aligned, &pfx_0f_e7_0f_38_2a), N, N, N, N, N, + X2(N), GP(SrcMem | DstReg | ModRM | Mov | Aligned, &pfx_0f_e7_0f_38_2a), N, N, N, N, N, /* 0x30 - 0x7f */ X16(N), X16(N), X16(N), X16(N), X16(N), /* 0x80 - 0xef */ diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 892246204435..f0144ae8d891 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2526,6 +2526,23 @@ static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator) __shadow_walk_next(iterator, *iterator->sptep); } +/* + * Note: while normally KVM uses a "bool flush" return value to let + * the caller batch flushes, __link_shadow_page() flushes immediately + * before populating the parent PTE with the new shadow page. The + * typical callers, direct_map() and FNAME(fetch)(), are not going + * to zap more than one huge SPTE anyway. + * + * The only exception, where @flush can be false, is when a huge SPTE + * is replaced with a shadow page SPTE with a fully populated page table, + * which can happen from shadow_mmu_split_huge_page(). In this case, + * no memory is unmapped across the change to the page tables and no + * immediate flush is needed for correctness. + * + * Even in that case, calls to kvm_mmu_commit_zap_page() are not + * batched. Doing so would require adding an invalid_list argument + * all the way down to __walk_slot_rmaps(). + */ static void __link_shadow_page(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, u64 *sptep, struct kvm_mmu_page *sp, bool flush) @@ -2541,8 +2558,10 @@ static void __link_shadow_page(struct kvm *kvm, parent_sp = sptep_to_sp(sptep); WARN_ON_ONCE(parent_sp->role.level == PG_LEVEL_4K); - mmu_page_zap_pte(kvm, parent_sp, sptep, &invalid_list); - kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, true); + if (mmu_page_zap_pte(kvm, parent_sp, sptep, &invalid_list)) + kvm_mmu_commit_zap_page(kvm, &invalid_list); + else if (flush) + kvm_flush_remote_tlbs_sptep(kvm, sptep); } spte = make_nonleaf_spte(sp->spt, sp_ad_disabled(sp)); diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 961804df5f45..b340dc9991ad 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -160,6 +160,16 @@ void nested_vmcb02_recalc_intercepts(struct vcpu_svm *svm) if (!intercept_smi) vmcb_clr_intercept(&vmcb02->control, INTERCEPT_SMI); + /* + * Intercept PAUSE if and only if L1 wants to. KVM intercepts PAUSE so + * that a vCPU that may be spinning waiting for a lock can be scheduled + * out in favor of the vCPU that holds said lock. KVM doesn't support + * yielding across L2 vCPUs, as KVM has limited visilibity into which + * L2 vCPUs are in the same L2 VM, i.e. may be contending for locks. + */ + if (!vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_PAUSE)) + vmcb_clr_intercept(&vmcb02->control, INTERCEPT_PAUSE); + if (nested_vmcb_needs_vls_intercept(svm)) { /* * If the virtual VMLOAD/VMSAVE is not enabled for the L2, @@ -819,7 +829,6 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) struct vmcb *vmcb02 = svm->nested.vmcb02.ptr; struct vmcb *vmcb01 = svm->vmcb01.ptr; struct kvm_vcpu *vcpu = &svm->vcpu; - u32 pause_count12, pause_thresh12; nested_svm_transition_tlb_flush(vcpu); @@ -947,31 +956,13 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) vmcb02->control.misc_ctl2 |= SVM_MISC2_ENABLE_V_VMLOAD_VMSAVE; if (guest_cpu_cap_has(vcpu, X86_FEATURE_PAUSEFILTER)) - pause_count12 = vmcb12_ctrl->pause_filter_count; + vmcb02->control.pause_filter_count = vmcb12_ctrl->pause_filter_count; else - pause_count12 = 0; + vmcb02->control.pause_filter_count = 0; if (guest_cpu_cap_has(vcpu, X86_FEATURE_PFTHRESHOLD)) - pause_thresh12 = vmcb12_ctrl->pause_filter_thresh; + vmcb02->control.pause_filter_thresh = vmcb12_ctrl->pause_filter_thresh; else - pause_thresh12 = 0; - if (kvm_pause_in_guest(svm->vcpu.kvm)) { - /* use guest values since host doesn't intercept PAUSE */ - vmcb02->control.pause_filter_count = pause_count12; - vmcb02->control.pause_filter_thresh = pause_thresh12; - - } else { - /* start from host values otherwise */ - vmcb02->control.pause_filter_count = vmcb01->control.pause_filter_count; - vmcb02->control.pause_filter_thresh = vmcb01->control.pause_filter_thresh; - - /* ... but ensure filtering is disabled if so requested. */ - if (vmcb12_is_intercept(vmcb12_ctrl, INTERCEPT_PAUSE)) { - if (!pause_count12) - vmcb02->control.pause_filter_count = 0; - if (!pause_thresh12) - vmcb02->control.pause_filter_thresh = 0; - } - } + vmcb02->control.pause_filter_thresh = 0; /* * Take ALLOW_LARGER_RAP from vmcb12 even though it should be safe to @@ -1298,12 +1289,6 @@ void nested_svm_vmexit(struct vcpu_svm *svm) /* in case we halted in L2 */ kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE); - if (!kvm_pause_in_guest(vcpu->kvm)) { - vmcb01->control.pause_filter_count = vmcb02->control.pause_filter_count; - vmcb_mark_dirty(vmcb01, VMCB_INTERCEPTS); - - } - /* * Invalidate last_bus_lock_rip unless KVM is still waiting for the * guest to make forward progress before re-enabling bus lock detection. diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index e7fdd7a9c280..e02a38da5296 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -913,7 +913,15 @@ static void grow_ple_window(struct kvm_vcpu *vcpu) struct vmcb_control_area *control = &svm->vmcb->control; int old = control->pause_filter_count; - if (kvm_pause_in_guest(vcpu->kvm)) + /* Adjusting pause_filter_count makes no sense if PLE is disabled. */ + WARN_ON_ONCE(kvm_pause_in_guest(vcpu->kvm)); + + /* + * While running L2, KVM should intercept PAUSE if and only if L1 wants + * to intercept PAUSE, and L1's intercept should take priority, i.e. + * KVM should never handle a PAUSE intercept from L2. + */ + if (WARN_ON_ONCE(is_guest_mode(vcpu))) return; control->pause_filter_count = __grow_ple_window(old, @@ -934,7 +942,10 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu) struct vmcb_control_area *control = &svm->vmcb->control; int old = control->pause_filter_count; - if (kvm_pause_in_guest(vcpu->kvm)) + /* Adjusting pause_filter_count makes no sense if PLE is disabled. */ + WARN_ON_ONCE(kvm_pause_in_guest(vcpu->kvm)); + + if (is_guest_mode(vcpu)) return; control->pause_filter_count = diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index e7fdbe9efc90..0db25bba17f6 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -154,7 +154,7 @@ TRACE_EVENT(kvm_xen_hypercall, __entry->a2 = a2; __entry->a3 = a3; __entry->a4 = a4; - __entry->a4 = a5; + __entry->a5 = a5; ), TP_printk("cpl %d nr 0x%lx a0 0x%lx a1 0x%lx a2 0x%lx a3 0x%lx a4 0x%lx a5 %lx", diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 56cacc06225e..31568274d8bb 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -14,6 +14,7 @@ extern bool __read_mostly flexpriority_enabled; extern bool __read_mostly enable_ept; extern bool __read_mostly enable_unrestricted_guest; extern bool __read_mostly enable_ept_ad_bits; +extern bool __read_mostly enable_cet; extern bool __read_mostly enable_pml; extern int __read_mostly pt_mode; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 5c2c33a5f7dc..49feecb286b2 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -108,6 +108,9 @@ module_param_named(unrestricted_guest, bool __read_mostly enable_ept_ad_bits = 1; module_param_named(eptad, enable_ept_ad_bits, bool, 0444); +bool __read_mostly enable_cet = 1; +module_param_named(cet, enable_cet, bool, 0444); + static bool __read_mostly emulate_invalid_guest_state = true; module_param(emulate_invalid_guest_state, bool, 0444); @@ -4476,7 +4479,7 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) * SSP is reloaded from IA32_PL3_SSP. Check SDM Vol.2A/B Chapter * 3 and 4 for details. */ - if (cpu_has_load_cet_ctrl()) { + if (enable_cet) { vmcs_writel(HOST_S_CET, kvm_host.s_cet); vmcs_writel(HOST_SSP, 0); vmcs_writel(HOST_INTR_SSP_TABLE, 0); @@ -4532,6 +4535,10 @@ static u32 vmx_get_initial_vmentry_ctrl(void) if (vmx_pt_mode_is_system()) vmentry_ctrl &= ~(VM_ENTRY_PT_CONCEAL_PIP | VM_ENTRY_LOAD_IA32_RTIT_CTL); + + if (!enable_cet) + vmentry_ctrl &= ~VM_ENTRY_LOAD_CET_STATE; + /* * IA32e mode, and loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically. */ @@ -4546,6 +4553,9 @@ static u32 vmx_get_initial_vmexit_ctrl(void) { u32 vmexit_ctrl = vmcs_config.vmexit_ctrl; + if (!enable_cet) + vmexit_ctrl &= ~VM_EXIT_LOAD_CET_STATE; + /* * Not used by KVM and never set in vmcs01 or vmcs02, but emulated for * nested virtualization and thus allowed to be set in vmcs12. @@ -8155,7 +8165,7 @@ static __init void vmx_set_cpu_caps(void) * VMX_BASIC[bit56] == 0, inject #CP at VMX entry with error code * fails, so disable CET in this case too. */ - if (!cpu_has_load_cet_ctrl() || !enable_unrestricted_guest || + if (!enable_cet || !enable_unrestricted_guest || !cpu_has_vmx_basic_no_hw_errcode_cc()) { kvm_cpu_cap_clear(X86_FEATURE_SHSTK); kvm_cpu_cap_clear(X86_FEATURE_IBT); @@ -8630,6 +8640,9 @@ __init int vmx_hardware_setup(void) !cpu_has_vmx_invept_global()) enable_ept = 0; + if (!cpu_has_load_cet_ctrl()) + enable_cet = 0; + /* NX support is required for shadow paging. */ if (!enable_ept && !boot_cpu_has(X86_FEATURE_NX)) { pr_err_ratelimited("NX (Execute Disable) not supported\n"); diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index c80d0058efd1..3eee5f84f8a7 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -2145,7 +2145,10 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) static void xen_enter_lazy_mmu(void) { - enter_lazy(XEN_LAZY_MMU); + preempt_disable(); + if (xen_get_lazy_mode() != XEN_LAZY_MMU) + enter_lazy(XEN_LAZY_MMU); + preempt_enable(); } static void xen_flush_lazy_mmu(void) @@ -2182,7 +2185,8 @@ static void xen_leave_lazy_mmu(void) { preempt_disable(); xen_mc_flush(); - leave_lazy(XEN_LAZY_MMU); + if (xen_get_lazy_mode() != XEN_LAZY_NONE) + leave_lazy(XEN_LAZY_MMU); preempt_enable(); } diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index bb95a05259b8..41251d4cf953 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -655,7 +655,7 @@ static void __init xen_e820_swap_entry_with_ram(struct e820_entry *swap_entry) /* Fill new entry (keep size and page offset). */ entry->type = swap_entry->type; entry->addr = entry_end - swap_size + - swap_addr - swap_entry->addr; + swap_entry->addr - swap_addr; entry->size = swap_entry->size; /* Convert old entry to RAM, align to pages. */ diff --git a/block/bio-integrity.c b/block/bio-integrity.c index e54c6e06e1cb..e796de1a749e 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -308,7 +308,6 @@ static int bio_integrity_copy_user(struct bio *bio, struct bio_vec *bvec, } bip->bip_flags |= BIP_COPY_USER; - bip->bip_vcnt = nr_vecs; return 0; free_bip: bio_integrity_free(bio); @@ -403,6 +402,24 @@ int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter) if (unlikely(ret < 0)) goto free_bvec; + /* + * Handle partial pinning. This can happen when pin_user_pages_fast() + * returns fewer pages than requested. + */ + if (user_backed_iter(iter) && unlikely(ret != bytes)) { + if (ret > 0) { + int npinned = DIV_ROUND_UP(offset + ret, PAGE_SIZE); + int i; + + for (i = 0; i < npinned; i++) + unpin_user_page(pages[i]); + } + if (pages != stack_pages) + kvfree(pages); + ret = -EFAULT; + goto free_bvec; + } + nr_bvecs = bvec_from_pages(bvec, pages, nr_vecs, bytes, offset, &is_p2p); if (pages != stack_pages) diff --git a/block/bio.c b/block/bio.c index b8972dba68a0..5f10900b3f42 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1279,11 +1279,12 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter, return bio_iov_iter_align_down(bio, iter, len_align_mask); } -static struct folio *folio_alloc_greedy(gfp_t gfp, size_t *size) +static struct folio *folio_alloc_greedy(gfp_t gfp, size_t *size, + size_t minsize) { struct folio *folio; - while (*size > PAGE_SIZE) { + while (*size > minsize) { folio = folio_alloc(gfp | __GFP_NORETRY, get_order(*size)); if (folio) return folio; @@ -1307,7 +1308,7 @@ static void bio_free_folios(struct bio *bio) } static int bio_iov_iter_bounce_write(struct bio *bio, struct iov_iter *iter, - size_t maxlen) + size_t maxlen, size_t minsize) { size_t total_len = min(maxlen, iov_iter_count(iter)); @@ -1322,13 +1323,13 @@ static int bio_iov_iter_bounce_write(struct bio *bio, struct iov_iter *iter, size_t this_len = min(total_len, SZ_1M); struct folio *folio; - if (this_len > PAGE_SIZE * 2) + if (this_len > minsize * 2) this_len = rounddown_pow_of_two(this_len); if (bio->bi_iter.bi_size > BIO_MAX_SIZE - this_len) break; - folio = folio_alloc_greedy(GFP_KERNEL, &this_len); + folio = folio_alloc_greedy(GFP_KERNEL, &this_len, minsize); if (!folio) break; bio_add_folio_nofail(bio, folio, this_len, 0); @@ -1344,16 +1345,16 @@ static int bio_iov_iter_bounce_write(struct bio *bio, struct iov_iter *iter, if (!bio->bi_iter.bi_size) return -ENOMEM; - return 0; + return bio_iov_iter_align_down(bio, iter, minsize - 1); } static int bio_iov_iter_bounce_read(struct bio *bio, struct iov_iter *iter, - size_t maxlen) + size_t maxlen, size_t minsize) { size_t len = min3(iov_iter_count(iter), maxlen, SZ_1M); struct folio *folio; - folio = folio_alloc_greedy(GFP_KERNEL, &len); + folio = folio_alloc_greedy(GFP_KERNEL, &len, minsize); if (!folio) return -ENOMEM; @@ -1382,7 +1383,7 @@ static int bio_iov_iter_bounce_read(struct bio *bio, struct iov_iter *iter, bvec_set_folio(&bio->bi_io_vec[0], folio, bio->bi_iter.bi_size, 0); if (iov_iter_extract_will_pin(iter)) bio_set_flag(bio, BIO_PAGE_PINNED); - return 0; + return bio_iov_iter_align_down(bio, iter, minsize - 1); } /** @@ -1390,6 +1391,7 @@ static int bio_iov_iter_bounce_read(struct bio *bio, struct iov_iter *iter, * @bio: bio to send * @iter: iter to read from / write into * @maxlen: maximum size to bounce + * @minsize: minimum folio allocation size * * Helper for direct I/O implementations that need to bounce buffer because * we need to checksum the data or perform other operations that require @@ -1397,11 +1399,12 @@ static int bio_iov_iter_bounce_read(struct bio *bio, struct iov_iter *iter, * copies the data into it. Needs to be paired with bio_iov_iter_unbounce() * called on completion. */ -int bio_iov_iter_bounce(struct bio *bio, struct iov_iter *iter, size_t maxlen) +int bio_iov_iter_bounce(struct bio *bio, struct iov_iter *iter, size_t maxlen, + size_t minsize) { if (op_is_write(bio_op(bio))) - return bio_iov_iter_bounce_write(bio, iter, maxlen); - return bio_iov_iter_bounce_read(bio, iter, maxlen); + return bio_iov_iter_bounce_write(bio, iter, maxlen, minsize); + return bio_iov_iter_bounce_read(bio, iter, maxlen, minsize); } static void bvec_unpin(struct bio_vec *bv, bool mark_dirty) diff --git a/block/blk-mq.c b/block/blk-mq.c index 4c5c16cce4f8..d0c37daf568f 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -3307,6 +3307,25 @@ blk_status_t blk_insert_cloned_request(struct request *rq) return BLK_STS_IOERR; } + /* + * Integrity segment counting depends on the same queue limits + * (virt_boundary_mask, seg_boundary_mask, max_segment_size) that + * vary across stacked queues, so recompute against the bottom + * queue just like nr_phys_segments above. + */ + if (blk_integrity_rq(rq) && rq->bio) { + unsigned short max_int_segs = queue_max_integrity_segments(q); + + rq->nr_integrity_segments = + blk_rq_count_integrity_sg(rq->q, rq->bio); + if (rq->nr_integrity_segments > max_int_segs) { + printk(KERN_ERR "%s: over max integrity segments limit. (%u > %u)\n", + __func__, rq->nr_integrity_segments, + max_int_segs); + return BLK_STS_IOERR; + } + } + if (q->disk && should_fail_request(q->disk->part0, blk_rq_bytes(rq))) return BLK_STS_IOERR; diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 30cad2bb9291..42ef830054dc 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -623,6 +623,28 @@ static void disk_mark_zone_wplug_dead(struct blk_zone_wplug *zwplug) } } +static inline bool disk_check_zone_wplug_dead(struct blk_zone_wplug *zwplug) +{ + if (!(zwplug->flags & BLK_ZONE_WPLUG_DEAD)) + return false; + + /* + * If a new write is received right after a zone reset completes and + * while the disk_zone_wplugs_worker() thread has not yet released the + * reference on the zone write plug after processing the last write to + * the zone, then the new write BIO will see the zone write plug marked + * as dead. This case is however a false positive and a perfectly valid + * pattern. In such case, restore the zone write plug to a live one. + */ + if (!zwplug->wp_offset && bio_list_empty(&zwplug->bio_list)) { + zwplug->flags &= ~BLK_ZONE_WPLUG_DEAD; + refcount_inc(&zwplug->ref); + return false; + } + + return true; +} + static bool disk_zone_wplug_submit_bio(struct gendisk *disk, struct blk_zone_wplug *zwplug); @@ -1444,12 +1466,12 @@ static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs) spin_lock_irqsave(&zwplug->lock, flags); /* - * If we got a zone write plug marked as dead, then the user is issuing - * writes to a full zone, or without synchronizing with zone reset or - * zone finish operations. In such case, fail the BIO to signal this - * invalid usage. + * Check if we got a zone write plug marked as dead. If yes, then the + * user is likely issuing writes to a full zone, or without + * synchronizing with zone reset or zone finish operations. In such + * case, fail the BIO to signal this invalid usage. */ - if (zwplug->flags & BLK_ZONE_WPLUG_DEAD) { + if (disk_check_zone_wplug_dead(zwplug)) { spin_unlock_irqrestore(&zwplug->lock, flags); disk_put_zone_wplug(zwplug); bio_io_error(bio); diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c index e9e970fd8f33..27f31744f29e 100644 --- a/drivers/acpi/ac.c +++ b/drivers/acpi/ac.c @@ -192,11 +192,15 @@ static const struct dmi_system_id ac_dmi_table[] __initconst = { static int acpi_ac_probe(struct platform_device *pdev) { - struct acpi_device *adev = ACPI_COMPANION(&pdev->dev); struct power_supply_config psy_cfg = {}; + struct acpi_device *adev; struct acpi_ac *ac; int result; + adev = ACPI_COMPANION(&pdev->dev); + if (!adev) + return -ENODEV; + ac = kzalloc_obj(struct acpi_ac); if (!ac) return -ENOMEM; diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c index 0a8e02bc8c8b..ec94b09bb747 100644 --- a/drivers/acpi/acpi_pad.c +++ b/drivers/acpi/acpi_pad.c @@ -423,7 +423,11 @@ static void acpi_pad_notify(acpi_handle handle, u32 event, void *data) static int acpi_pad_probe(struct platform_device *pdev) { - struct acpi_device *adev = ACPI_COMPANION(&pdev->dev); + struct acpi_device *adev; + + adev = ACPI_COMPANION(&pdev->dev); + if (!adev) + return -ENODEV; return acpi_dev_install_notify_handler(adev, ACPI_DEVICE_NOTIFY, acpi_pad_notify, adev); diff --git a/drivers/acpi/acpi_tad.c b/drivers/acpi/acpi_tad.c index cac07e997028..386fc1abcbdc 100644 --- a/drivers/acpi/acpi_tad.c +++ b/drivers/acpi/acpi_tad.c @@ -815,12 +815,16 @@ static void acpi_tad_remove(void *data) static int acpi_tad_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - acpi_handle handle = ACPI_HANDLE(dev); struct acpi_tad_driver_data *dd; + acpi_handle handle; acpi_status status; unsigned long long caps; int ret; + handle = ACPI_HANDLE(dev); + if (!handle) + return -ENODEV; + /* * Initialization failure messages are mostly about firmware issues, so * print them at the "info" level. diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c index b4c25474f42f..d4ae21a71007 100644 --- a/drivers/acpi/battery.c +++ b/drivers/acpi/battery.c @@ -1214,10 +1214,14 @@ static void sysfs_battery_cleanup(struct acpi_battery *battery) static int acpi_battery_probe(struct platform_device *pdev) { - struct acpi_device *device = ACPI_COMPANION(&pdev->dev); struct acpi_battery *battery; + struct acpi_device *device; int result; + device = ACPI_COMPANION(&pdev->dev); + if (!device) + return -ENODEV; + if (device->dep_unmet) return -EPROBE_DEFER; diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c index dc064a388c23..b47301ee4c8a 100644 --- a/drivers/acpi/button.c +++ b/drivers/acpi/button.c @@ -531,15 +531,20 @@ static int acpi_lid_input_open(struct input_dev *input) static int acpi_button_probe(struct platform_device *pdev) { - struct acpi_device *device = ACPI_COMPANION(&pdev->dev); acpi_notify_handler handler; + struct acpi_device *device; struct acpi_button *button; struct input_dev *input; - const char *hid = acpi_device_hid(device); acpi_status status; char *name, *class; + const char *hid; int error = 0; + device = ACPI_COMPANION(&pdev->dev); + if (!device) + return -ENODEV; + + hid = acpi_device_hid(device); if (!strcmp(hid, ACPI_BUTTON_HID_LID) && lid_init_state == ACPI_BUTTON_LID_INIT_DISABLED) return -ENODEV; diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 45204538ed87..64ad4cfa6208 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1676,10 +1676,14 @@ static int acpi_ec_setup(struct acpi_ec *ec, struct acpi_device *device, bool ca static int acpi_ec_probe(struct platform_device *pdev) { - struct acpi_device *device = ACPI_COMPANION(&pdev->dev); + struct acpi_device *device; struct acpi_ec *ec; int ret; + device = ACPI_COMPANION(&pdev->dev); + if (!device) + return -ENODEV; + if (boot_ec && (boot_ec->handle == device->handle || !strcmp(acpi_device_hid(device), ACPI_ECDT_HID))) { /* Fast path: this device corresponds to the boot EC. */ diff --git a/drivers/acpi/hed.c b/drivers/acpi/hed.c index 4d5e12ed6f3c..060e8d670f5d 100644 --- a/drivers/acpi/hed.c +++ b/drivers/acpi/hed.c @@ -50,9 +50,13 @@ static void acpi_hed_notify(acpi_handle handle, u32 event, void *data) static int acpi_hed_probe(struct platform_device *pdev) { - struct acpi_device *device = ACPI_COMPANION(&pdev->dev); + struct acpi_device *device; int err; + device = ACPI_COMPANION(&pdev->dev); + if (!device) + return -ENODEV; + /* Only one hardware error device */ if (hed_handle) return -EINVAL; diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index d13264fb9e02..9304ac996d41 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -3341,12 +3341,16 @@ static int acpi_nfit_probe(struct platform_device *pdev) struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL }; struct acpi_nfit_desc *acpi_desc; struct device *dev = &pdev->dev; - struct acpi_device *adev = ACPI_COMPANION(dev); struct acpi_table_header *tbl; + struct acpi_device *adev; acpi_status status = AE_OK; acpi_size sz; int rc = 0; + adev = ACPI_COMPANION(&pdev->dev); + if (!adev) + return -ENODEV; + rc = acpi_dev_install_notify_handler(adev, ACPI_DEVICE_NOTIFY, acpi_nfit_notify, dev); if (rc) diff --git a/drivers/acpi/pfr_telemetry.c b/drivers/acpi/pfr_telemetry.c index 32bdf8cbe8f2..2387376832a1 100644 --- a/drivers/acpi/pfr_telemetry.c +++ b/drivers/acpi/pfr_telemetry.c @@ -360,10 +360,14 @@ static void pfrt_log_put_idx(void *data) static int acpi_pfrt_log_probe(struct platform_device *pdev) { - acpi_handle handle = ACPI_HANDLE(&pdev->dev); struct pfrt_log_device *pfrt_log_dev; + acpi_handle handle; int ret; + handle = ACPI_HANDLE(&pdev->dev); + if (!handle) + return -ENODEV; + if (!acpi_has_method(handle, "_DSM")) { dev_dbg(&pdev->dev, "Missing _DSM\n"); return -ENODEV; diff --git a/drivers/acpi/pfr_update.c b/drivers/acpi/pfr_update.c index 11b1c2828005..6283105bb0e8 100644 --- a/drivers/acpi/pfr_update.c +++ b/drivers/acpi/pfr_update.c @@ -538,10 +538,14 @@ static void pfru_put_idx(void *data) static int acpi_pfru_probe(struct platform_device *pdev) { - acpi_handle handle = ACPI_HANDLE(&pdev->dev); struct pfru_device *pfru_dev; + acpi_handle handle; int ret; + handle = ACPI_HANDLE(&pdev->dev); + if (!handle) + return -ENODEV; + if (!acpi_has_method(handle, "_DSM")) { dev_dbg(&pdev->dev, "Missing _DSM\n"); return -ENODEV; diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c index 440f1d69aca8..86b7c7975852 100644 --- a/drivers/acpi/sbs.c +++ b/drivers/acpi/sbs.c @@ -629,11 +629,15 @@ static void acpi_sbs_callback(void *context) static int acpi_sbs_probe(struct platform_device *pdev) { - struct acpi_device *device = ACPI_COMPANION(&pdev->dev); + struct acpi_device *device; struct acpi_sbs *sbs; int result = 0; int id; + device = ACPI_COMPANION(&pdev->dev); + if (!device) + return -ENODEV; + sbs = kzalloc_obj(struct acpi_sbs); if (!sbs) { result = -ENOMEM; diff --git a/drivers/acpi/sbshc.c b/drivers/acpi/sbshc.c index f413270415b6..c0ffa267f96c 100644 --- a/drivers/acpi/sbshc.c +++ b/drivers/acpi/sbshc.c @@ -237,11 +237,15 @@ static int smbus_alarm(void *context) static int acpi_smbus_hc_probe(struct platform_device *pdev) { - struct acpi_device *device = ACPI_COMPANION(&pdev->dev); + struct acpi_device *device; int status; unsigned long long val; struct acpi_smb_hc *hc; + device = ACPI_COMPANION(&pdev->dev); + if (!device) + return -ENODEV; + status = acpi_evaluate_integer(device->handle, "_EC", NULL, &val); if (ACPI_FAILURE(status)) { pr_err("error obtaining _EC.\n"); diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c index b8b487d89d25..dfc7daa809b5 100644 --- a/drivers/acpi/thermal.c +++ b/drivers/acpi/thermal.c @@ -789,7 +789,7 @@ static int acpi_thermal_probe(struct platform_device *pdev) int i; if (!device) - return -EINVAL; + return -ENODEV; tz = kzalloc_obj(struct acpi_thermal); if (!tz) diff --git a/drivers/acpi/tiny-power-button.c b/drivers/acpi/tiny-power-button.c index 531e65b01bcb..92516ef84b02 100644 --- a/drivers/acpi/tiny-power-button.c +++ b/drivers/acpi/tiny-power-button.c @@ -38,9 +38,13 @@ static u32 acpi_tiny_power_button_event(void *not_used) static int acpi_tiny_power_button_probe(struct platform_device *pdev) { - struct acpi_device *device = ACPI_COMPANION(&pdev->dev); + struct acpi_device *device; acpi_status status; + device = ACPI_COMPANION(&pdev->dev); + if (!device) + return -ENODEV; + if (device->device_type == ACPI_BUS_TYPE_POWER_BUTTON) { status = acpi_install_fixed_event_handler(ACPI_EVENT_POWER_BUTTON, acpi_tiny_power_button_event, diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 6d13f1481de0..6c041eaebdb9 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -920,6 +920,9 @@ static int ublk_validate_params(const struct ublk_device *ub) if (p->max_sectors > (ub->dev_info.max_io_buf_bytes >> 9)) return -EINVAL; + if (p->max_sectors < PAGE_SECTORS) + return -EINVAL; + if (ublk_dev_is_zoned(ub) && !p->chunk_sectors) return -EINVAL; } else diff --git a/drivers/hid/bpf/hid_bpf_dispatch.c b/drivers/hid/bpf/hid_bpf_dispatch.c index 50c7b45c59e3..d0130658091b 100644 --- a/drivers/hid/bpf/hid_bpf_dispatch.c +++ b/drivers/hid/bpf/hid_bpf_dispatch.c @@ -24,7 +24,8 @@ EXPORT_SYMBOL(hid_ops); u8 * dispatch_hid_bpf_device_event(struct hid_device *hdev, enum hid_report_type type, u8 *data, - u32 *size, int interrupt, u64 source, bool from_bpf) + size_t *buf_size, u32 *size, int interrupt, u64 source, + bool from_bpf) { struct hid_bpf_ctx_kern ctx_kern = { .ctx = { @@ -74,6 +75,7 @@ dispatch_hid_bpf_device_event(struct hid_device *hdev, enum hid_report_type type *size = ret; } + *buf_size = ctx_kern.ctx.allocated_size; return ctx_kern.data; } EXPORT_SYMBOL_GPL(dispatch_hid_bpf_device_event); @@ -505,7 +507,7 @@ __hid_bpf_input_report(struct hid_bpf_ctx *ctx, enum hid_report_type type, u8 *b if (ret) return ret; - return hid_ops->hid_input_report(ctx->hid, type, buf, size, 0, (u64)(long)ctx, true, + return hid_ops->hid_input_report(ctx->hid, type, buf, size, size, 0, (u64)(long)ctx, true, lock_already_taken); } diff --git a/drivers/hid/hid-appletb-kbd.c b/drivers/hid/hid-appletb-kbd.c index 0fdc0968b9ef..462010a75899 100644 --- a/drivers/hid/hid-appletb-kbd.c +++ b/drivers/hid/hid-appletb-kbd.c @@ -17,7 +17,7 @@ #include <linux/module.h> #include <linux/string.h> #include <linux/backlight.h> -#include <linux/timer.h> +#include <linux/workqueue.h> #include <linux/input/sparse-keymap.h> #include "hid-ids.h" @@ -62,7 +62,8 @@ struct appletb_kbd { struct input_handle kbd_handle; struct input_handle tpd_handle; struct backlight_device *backlight_dev; - struct timer_list inactivity_timer; + struct delayed_work inactivity_work; + struct work_struct restore_brightness_work; bool has_dimmed; bool has_turned_off; u8 saved_mode; @@ -164,16 +165,18 @@ static int appletb_tb_key_to_slot(unsigned int code) } } -static void appletb_inactivity_timer(struct timer_list *t) +static void appletb_inactivity_work(struct work_struct *work) { - struct appletb_kbd *kbd = timer_container_of(kbd, t, inactivity_timer); + struct appletb_kbd *kbd = container_of(to_delayed_work(work), + struct appletb_kbd, + inactivity_work); if (kbd->backlight_dev && appletb_tb_autodim) { if (!kbd->has_dimmed) { backlight_device_set_brightness(kbd->backlight_dev, 1); kbd->has_dimmed = true; - mod_timer(&kbd->inactivity_timer, - jiffies + secs_to_jiffies(appletb_tb_idle_timeout)); + mod_delayed_work(system_wq, &kbd->inactivity_work, + secs_to_jiffies(appletb_tb_idle_timeout)); } else if (!kbd->has_turned_off) { backlight_device_set_brightness(kbd->backlight_dev, 0); kbd->has_turned_off = true; @@ -181,16 +184,25 @@ static void appletb_inactivity_timer(struct timer_list *t) } } +static void appletb_restore_brightness_work(struct work_struct *work) +{ + struct appletb_kbd *kbd = container_of(work, struct appletb_kbd, + restore_brightness_work); + + if (kbd->backlight_dev) + backlight_device_set_brightness(kbd->backlight_dev, 2); +} + static void reset_inactivity_timer(struct appletb_kbd *kbd) { if (kbd->backlight_dev && appletb_tb_autodim) { if (kbd->has_dimmed || kbd->has_turned_off) { - backlight_device_set_brightness(kbd->backlight_dev, 2); kbd->has_dimmed = false; kbd->has_turned_off = false; + schedule_work(&kbd->restore_brightness_work); } - mod_timer(&kbd->inactivity_timer, - jiffies + secs_to_jiffies(appletb_tb_dim_timeout)); + mod_delayed_work(system_wq, &kbd->inactivity_work, + secs_to_jiffies(appletb_tb_dim_timeout)); } } @@ -408,9 +420,11 @@ static int appletb_kbd_probe(struct hid_device *hdev, const struct hid_device_id dev_err_probe(dev, -ENODEV, "Failed to get backlight device\n"); } else { backlight_device_set_brightness(kbd->backlight_dev, 2); - timer_setup(&kbd->inactivity_timer, appletb_inactivity_timer, 0); - mod_timer(&kbd->inactivity_timer, - jiffies + secs_to_jiffies(appletb_tb_dim_timeout)); + INIT_DELAYED_WORK(&kbd->inactivity_work, appletb_inactivity_work); + INIT_WORK(&kbd->restore_brightness_work, + appletb_restore_brightness_work); + mod_delayed_work(system_wq, &kbd->inactivity_work, + secs_to_jiffies(appletb_tb_dim_timeout)); } kbd->inp_handler.event = appletb_kbd_inp_event; @@ -440,13 +454,14 @@ static int appletb_kbd_probe(struct hid_device *hdev, const struct hid_device_id unregister_handler: input_unregister_handler(&kbd->inp_handler); close_hw: - if (kbd->backlight_dev) { - put_device(&kbd->backlight_dev->dev); - timer_delete_sync(&kbd->inactivity_timer); - } hid_hw_close(hdev); stop_hw: hid_hw_stop(hdev); + if (kbd->backlight_dev) { + cancel_delayed_work_sync(&kbd->inactivity_work); + cancel_work_sync(&kbd->restore_brightness_work); + put_device(&kbd->backlight_dev->dev); + } return ret; } @@ -457,13 +472,14 @@ static void appletb_kbd_remove(struct hid_device *hdev) appletb_kbd_set_mode(kbd, APPLETB_KBD_MODE_OFF); input_unregister_handler(&kbd->inp_handler); + hid_hw_close(hdev); + hid_hw_stop(hdev); + if (kbd->backlight_dev) { + cancel_delayed_work_sync(&kbd->inactivity_work); + cancel_work_sync(&kbd->restore_brightness_work); put_device(&kbd->backlight_dev->dev); - timer_delete_sync(&kbd->inactivity_timer); } - - hid_hw_close(hdev); - hid_hw_stop(hdev); } static int appletb_kbd_suspend(struct hid_device *hdev, pm_message_t msg) diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 61afec5915ec..b3596851c719 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -2033,24 +2033,32 @@ int __hid_request(struct hid_device *hid, struct hid_report *report, } EXPORT_SYMBOL_GPL(__hid_request); -int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *data, u32 size, - int interrupt) +int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *data, + size_t bufsize, u32 size, int interrupt) { struct hid_report_enum *report_enum = hid->report_enum + type; struct hid_report *report; struct hid_driver *hdrv; int max_buffer_size = HID_MAX_BUFFER_SIZE; u32 rsize, csize = size; + size_t bsize = bufsize; u8 *cdata = data; int ret = 0; report = hid_get_report(report_enum, data); if (!report) - goto out; + return 0; + + if (unlikely(bsize < csize)) { + hid_warn_ratelimited(hid, "Event data for report %d is incorrect (%d vs %ld)\n", + report->id, csize, bsize); + return -EINVAL; + } if (report_enum->numbered) { cdata++; csize--; + bsize--; } rsize = hid_compute_report_size(report); @@ -2063,11 +2071,16 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 * else if (rsize > max_buffer_size) rsize = max_buffer_size; + if (bsize < rsize) { + hid_warn_ratelimited(hid, "Event data for report %d was too short (%d vs %ld)\n", + report->id, rsize, bsize); + return -EINVAL; + } + if (csize < rsize) { - hid_warn_ratelimited(hid, "Event data for report %d was too short (%d vs %d)\n", - report->id, rsize, csize); - ret = -EINVAL; - goto out; + dbg_hid("report %d is too short, (%d < %d)\n", report->id, + csize, rsize); + memset(cdata + csize, 0, rsize - csize); } if ((hid->claimed & HID_CLAIMED_HIDDEV) && hid->hiddev_report_event) @@ -2075,7 +2088,7 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 * if (hid->claimed & HID_CLAIMED_HIDRAW) { ret = hidraw_report_event(hid, data, size); if (ret) - goto out; + return ret; } if (hid->claimed != HID_CLAIMED_HIDRAW && report->maxfield) { @@ -2087,15 +2100,15 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 * if (hid->claimed & HID_CLAIMED_INPUT) hidinput_report_event(hid, report); -out: + return ret; } EXPORT_SYMBOL_GPL(hid_report_raw_event); static int __hid_input_report(struct hid_device *hid, enum hid_report_type type, - u8 *data, u32 size, int interrupt, u64 source, bool from_bpf, - bool lock_already_taken) + u8 *data, size_t bufsize, u32 size, int interrupt, u64 source, + bool from_bpf, bool lock_already_taken) { struct hid_report_enum *report_enum; struct hid_driver *hdrv; @@ -2120,7 +2133,8 @@ static int __hid_input_report(struct hid_device *hid, enum hid_report_type type, report_enum = hid->report_enum + type; hdrv = hid->driver; - data = dispatch_hid_bpf_device_event(hid, type, data, &size, interrupt, source, from_bpf); + data = dispatch_hid_bpf_device_event(hid, type, data, &bufsize, &size, interrupt, + source, from_bpf); if (IS_ERR(data)) { ret = PTR_ERR(data); goto unlock; @@ -2149,7 +2163,7 @@ static int __hid_input_report(struct hid_device *hid, enum hid_report_type type, goto unlock; } - ret = hid_report_raw_event(hid, type, data, size, interrupt); + ret = hid_report_raw_event(hid, type, data, bufsize, size, interrupt); unlock: if (!lock_already_taken) @@ -2167,16 +2181,41 @@ unlock: * @interrupt: distinguish between interrupt and control transfers * * This is data entry for lower layers. + * Legacy, please use hid_safe_input_report() instead. */ int hid_input_report(struct hid_device *hid, enum hid_report_type type, u8 *data, u32 size, int interrupt) { - return __hid_input_report(hid, type, data, size, interrupt, 0, + return __hid_input_report(hid, type, data, size, size, interrupt, 0, false, /* from_bpf */ false /* lock_already_taken */); } EXPORT_SYMBOL_GPL(hid_input_report); +/** + * hid_safe_input_report - report data from lower layer (usb, bt...) + * + * @hid: hid device + * @type: HID report type (HID_*_REPORT) + * @data: report contents + * @bufsize: allocated size of the data buffer + * @size: useful size of data parameter + * @interrupt: distinguish between interrupt and control transfers + * + * This is data entry for lower layers. + * Please use this function instead of the non safe version because we provide + * here the size of the buffer, allowing hid-core to make smarter decisions + * regarding the incoming buffer. + */ +int hid_safe_input_report(struct hid_device *hid, enum hid_report_type type, u8 *data, + size_t bufsize, u32 size, int interrupt) +{ + return __hid_input_report(hid, type, data, bufsize, size, interrupt, 0, + false, /* from_bpf */ + false /* lock_already_taken */); +} +EXPORT_SYMBOL_GPL(hid_safe_input_report); + bool hid_match_one_id(const struct hid_device *hdev, const struct hid_device_id *id) { diff --git a/drivers/hid/hid-elan.c b/drivers/hid/hid-elan.c index 76d93fc48f6a..0190ad567ce4 100644 --- a/drivers/hid/hid-elan.c +++ b/drivers/hid/hid-elan.c @@ -513,6 +513,7 @@ static const struct hid_device_id elan_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_HP_X2_10_COVER), .driver_data = ELAN_HAS_LED }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_TOSHIBA_CLICK_L9W) }, + { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_SB974D) }, { } }; MODULE_DEVICE_TABLE(hid, elan_devices); diff --git a/drivers/hid/hid-ft260.c b/drivers/hid/hid-ft260.c index 333341e80b0e..70e2eedb465a 100644 --- a/drivers/hid/hid-ft260.c +++ b/drivers/hid/hid-ft260.c @@ -1068,10 +1068,22 @@ static int ft260_raw_event(struct hid_device *hdev, struct hid_report *report, struct ft260_device *dev = hid_get_drvdata(hdev); struct ft260_i2c_input_report *xfer = (void *)data; + if (size < offsetof(struct ft260_i2c_input_report, data)) { + hid_err(hdev, "short report %d\n", size); + return -1; + } + if (xfer->report >= FT260_I2C_REPORT_MIN && xfer->report <= FT260_I2C_REPORT_MAX) { - ft260_dbg("i2c resp: rep %#02x len %d\n", xfer->report, - xfer->length); + ft260_dbg("i2c resp: rep %#02x len %d size %d\n", + xfer->report, xfer->length, size); + + if (xfer->length > size - + offsetof(struct ft260_i2c_input_report, data)) { + hid_err(hdev, "report %#02x: length %d exceeds HID report size\n", + xfer->report, xfer->length); + return -1; + } if ((dev->read_buf == NULL) || (xfer->length > dev->read_len - dev->read_idx)) { diff --git a/drivers/hid/hid-gfrm.c b/drivers/hid/hid-gfrm.c index 699186ff2349..d2a56bf92b41 100644 --- a/drivers/hid/hid-gfrm.c +++ b/drivers/hid/hid-gfrm.c @@ -66,7 +66,7 @@ static int gfrm_raw_event(struct hid_device *hdev, struct hid_report *report, switch (data[1]) { case GFRM100_SEARCH_KEY_DOWN: ret = hid_report_raw_event(hdev, HID_INPUT_REPORT, search_key_dn, - sizeof(search_key_dn), 1); + sizeof(search_key_dn), sizeof(search_key_dn), 1); break; case GFRM100_SEARCH_KEY_AUDIO_DATA: @@ -74,7 +74,7 @@ static int gfrm_raw_event(struct hid_device *hdev, struct hid_report *report, case GFRM100_SEARCH_KEY_UP: ret = hid_report_raw_event(hdev, HID_INPUT_REPORT, search_key_up, - sizeof(search_key_up), 1); + sizeof(search_key_up), sizeof(search_key_up), 1); break; default: diff --git a/drivers/hid/hid-google-hammer.c b/drivers/hid/hid-google-hammer.c index 1af477e58480..c99c3c0d442e 100644 --- a/drivers/hid/hid-google-hammer.c +++ b/drivers/hid/hid-google-hammer.c @@ -496,7 +496,7 @@ static int hammer_probe(struct hid_device *hdev, if (error) return error; - error = devm_add_action(&hdev->dev, hammer_stop, hdev); + error = devm_add_action_or_reset(&hdev->dev, hammer_stop, hdev); if (error) return error; diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 0cf63742315b..4657d96fb083 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -277,6 +277,9 @@ #define USB_VENDOR_ID_BIGBEN 0x146b #define USB_DEVICE_ID_BIGBEN_PS3OFMINIPAD 0x0902 +#define I2C_VENDOR_ID_BLTP 0x36b6 +#define I2C_PRODUCT_ID_BLTP7853 0xc001 + #define USB_VENDOR_ID_BTC 0x046e #define USB_DEVICE_ID_BTC_EMPREX_REMOTE 0x5578 #define USB_DEVICE_ID_BTC_EMPREX_REMOTE_2 0x5577 @@ -455,6 +458,7 @@ #define USB_DEVICE_ID_EDIFIER_QR30 0xa101 /* EDIFIER Hal0 2.0 SE */ #define USB_VENDOR_ID_ELAN 0x04f3 +#define USB_DEVICE_ID_SB974D 0x0400 #define USB_DEVICE_ID_TOSHIBA_CLICK_L9W 0x0401 #define USB_DEVICE_ID_HP_X2 0x074d #define USB_DEVICE_ID_HP_X2_10_COVER 0x0755 diff --git a/drivers/hid/hid-lenovo-go-s.c b/drivers/hid/hid-lenovo-go-s.c index 01c7bdd4fbe0..ff1782a75191 100644 --- a/drivers/hid/hid-lenovo-go-s.c +++ b/drivers/hid/hid-lenovo-go-s.c @@ -1369,6 +1369,14 @@ static void cfg_setup(struct work_struct *work) "Failed to retrieve IMU Manufacturer: %i\n", ret); return; } + + ret = mcu_property_out(drvdata.hdev, GET_GAMEPAD_CFG, FEATURE_OS_MODE, + NULL, 0); + if (ret) { + dev_err(&drvdata.hdev->dev, + "Failed to retrieve OS Mode: %i\n", ret); + return; + } } static int hid_gos_cfg_probe(struct hid_device *hdev, @@ -1427,6 +1435,27 @@ static void hid_gos_cfg_remove(struct hid_device *hdev) hid_set_drvdata(hdev, NULL); } +static int hid_gos_cfg_reset_resume(struct hid_device *hdev) +{ + u8 os_mode = drvdata.os_mode; + int ret; + + ret = mcu_property_out(drvdata.hdev, SET_GAMEPAD_CFG, + FEATURE_OS_MODE, &os_mode, 1); + if (ret < 0) + return ret; + + ret = mcu_property_out(drvdata.hdev, GET_GAMEPAD_CFG, + FEATURE_OS_MODE, NULL, 0); + if (ret < 0) + return ret; + + if (drvdata.os_mode != os_mode) + return -ENODEV; + + return 0; +} + static int hid_gos_probe(struct hid_device *hdev, const struct hid_device_id *id) { @@ -1481,6 +1510,20 @@ static void hid_gos_remove(struct hid_device *hdev) } } +static int hid_gos_reset_resume(struct hid_device *hdev) +{ + int ep = get_endpoint_address(hdev); + + switch (ep) { + case GO_S_CFG_INTF_IN: + return hid_gos_cfg_reset_resume(hdev); + default: + break; + } + + return 0; +} + static const struct hid_device_id hid_gos_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_QHE, USB_DEVICE_ID_LENOVO_LEGION_GO_S_XINPUT) }, @@ -1496,6 +1539,7 @@ static struct hid_driver hid_lenovo_go_s = { .probe = hid_gos_probe, .remove = hid_gos_remove, .raw_event = hid_gos_raw_event, + .reset_resume = hid_gos_reset_resume, }; module_hid_driver(hid_lenovo_go_s); diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index b1330d23bd2d..ccbf28869a96 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -3673,7 +3673,7 @@ static int hidpp10_consumer_keys_raw_event(struct hidpp_device *hidpp, memcpy(&consumer_report[1], &data[3], 4); /* We are called from atomic context */ hid_report_raw_event(hidpp->hid_dev, HID_INPUT_REPORT, - consumer_report, 5, 1); + consumer_report, sizeof(consumer_report), 5, 1); return 1; } @@ -4685,6 +4685,44 @@ static const struct hid_device_id hidpp_devices[] = { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb391) }, { /* MX Master 4 mouse over Bluetooth */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb042) }, + { /* Logitech Signature K650 over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb36f) }, + { /* Logitech Signature K650 B2B over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb370) }, + { /* Logitech Pebble Keys 2 K380S over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb377) }, + { /* Logitech Casa Pop-Up Desk over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb371) }, + { /* Logitech Casa Pop-Up Desk B2B over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb374) }, + { /* Logitech Wave Keys over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb383) }, + { /* Logitech Wave Keys B2B over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb384) }, + { /* Logitech Signature Slim K950 over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb386) }, + { /* Logitech Signature Slim K950 B2B over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb388) }, + { /* Logitech MX Keys S over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb378) }, + { /* Logitech MX Keys S B2B over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb380) }, + { /* Logitech Keys-To-Go 2 over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb38c) }, + { /* Logitech Pop Icon Keys over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb38f) }, + { /* Logitech MX Keys Mini over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb369) }, + { /* Logitech MX Keys Mini B2B over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb36e) }, + { /* Logitech Signature Slim Solar+ K980 B2B over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb394) }, + { /* Logitech Bluetooth Keyboard K250/K251 over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb397) }, + { /* Logitech Signature Comfort K880 over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb39c) }, + { /* Logitech Signature Comfort K880 B2B over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb39d) }, {} }; diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c index e70bd3dc07ab..802a3479e24b 100644 --- a/drivers/hid/hid-magicmouse.c +++ b/drivers/hid/hid-magicmouse.c @@ -390,6 +390,10 @@ static int magicmouse_raw_event(struct hid_device *hdev, struct input_dev *input = msc->input; int x = 0, y = 0, ii, clicks = 0, npoints; + /* Protect against zero sized recursive calls from DOUBLE_REPORT_ID */ + if (size < 1) + return 0; + switch (data[0]) { case TRACKPAD_REPORT_ID: case TRACKPAD2_BT_REPORT_ID: @@ -490,6 +494,18 @@ static int magicmouse_raw_event(struct hid_device *hdev, /* Sometimes the trackpad sends two touch reports in one * packet. */ + + /* Ensure that we have at least 2 elements (report type and size) */ + if (size < 2) + return 0; + + if (size < data[1] + 2) { + hid_warn(hdev, + "received report length (%d) was smaller than specified (%d)", + size, data[1] + 2); + return 0; + } + magicmouse_raw_event(hdev, report, data + 2, data[1]); magicmouse_raw_event(hdev, report, data + 2 + data[1], size - 2 - data[1]); diff --git a/drivers/hid/hid-mcp2221.c b/drivers/hid/hid-mcp2221.c index be80970ab48e..e4ddd8e9293b 100644 --- a/drivers/hid/hid-mcp2221.c +++ b/drivers/hid/hid-mcp2221.c @@ -128,6 +128,7 @@ struct mcp2221 { u8 *rxbuf; u8 txbuf[64]; int rxbuf_idx; + int rxbuf_size; int status; u8 cur_i2c_clk_div; struct gpio_chip *gc; @@ -330,12 +331,14 @@ static int mcp_i2c_smbus_read(struct mcp2221 *mcp, mcp->txbuf[3] = (u8)(msg->addr << 1); total_len = msg->len; mcp->rxbuf = msg->buf; + mcp->rxbuf_size = msg->len; } else { mcp->txbuf[1] = smbus_len; mcp->txbuf[2] = 0; mcp->txbuf[3] = (u8)(smbus_addr << 1); total_len = smbus_len; mcp->rxbuf = smbus_buf; + mcp->rxbuf_size = smbus_len; } ret = mcp_send_data_req_status(mcp, mcp->txbuf, 4); @@ -919,6 +922,10 @@ static int mcp2221_raw_event(struct hid_device *hdev, mcp->status = -EINVAL; break; } + if (mcp->rxbuf_idx + data[3] > mcp->rxbuf_size) { + mcp->status = -EINVAL; + break; + } buf = mcp->rxbuf; memcpy(&buf[mcp->rxbuf_idx], &data[4], data[3]); mcp->rxbuf_idx = mcp->rxbuf_idx + data[3]; diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index e82a3c4e5b44..eeab0b6e32cc 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -533,7 +533,7 @@ static void mt_get_feature(struct hid_device *hdev, struct hid_report *report) } ret = hid_report_raw_event(hdev, HID_FEATURE_REPORT, buf, - size, 0); + size, size, 0); if (ret) dev_warn(&hdev->dev, "failed to report feature\n"); } diff --git a/drivers/hid/hid-playstation.c b/drivers/hid/hid-playstation.c index c43caac20b61..e48537331675 100644 --- a/drivers/hid/hid-playstation.c +++ b/drivers/hid/hid-playstation.c @@ -2384,7 +2384,8 @@ static int dualshock4_parse_report(struct ps_device *ps_dev, struct hid_report * } ds4_report = &usb->common; - num_touch_reports = usb->num_touch_reports; + num_touch_reports = min_t(u8, usb->num_touch_reports, + ARRAY_SIZE(usb->touch_reports)); touch_reports = usb->touch_reports; } else if (hdev->bus == BUS_BLUETOOTH && report->id == DS4_INPUT_REPORT_BT && size == DS4_INPUT_REPORT_BT_SIZE) { @@ -2404,7 +2405,8 @@ static int dualshock4_parse_report(struct ps_device *ps_dev, struct hid_report * } ds4_report = &bt->common; - num_touch_reports = bt->num_touch_reports; + num_touch_reports = min_t(u8, bt->num_touch_reports, + ARRAY_SIZE(bt->touch_reports)); touch_reports = bt->touch_reports; } else if (hdev->bus == BUS_BLUETOOTH && report->id == DS4_INPUT_REPORT_BT_MINIMAL && diff --git a/drivers/hid/hid-primax.c b/drivers/hid/hid-primax.c index e44d79dff8de..8db054280afb 100644 --- a/drivers/hid/hid-primax.c +++ b/drivers/hid/hid-primax.c @@ -44,7 +44,7 @@ static int px_raw_event(struct hid_device *hid, struct hid_report *report, data[0] |= (1 << (data[idx] - 0xE0)); data[idx] = 0; } - hid_report_raw_event(hid, HID_INPUT_REPORT, data, size, 0); + hid_report_raw_event(hid, HID_INPUT_REPORT, data, size, size, 0); return 1; default: /* unknown report */ diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 9e88c9d6c6dc..512049963978 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -235,7 +235,7 @@ static const struct hid_device_id hid_quirks[] = { * used as a driver. See hid_scan_report(). */ static const struct hid_device_id hid_have_special_driver[] = { -#if IS_ENABLED(CONFIG_APPLEDISPLAY) +#if IS_ENABLED(CONFIG_USB_APPLEDISPLAY) { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, 0x9218) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, 0x9219) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, 0x921c) }, diff --git a/drivers/hid/hid-sjoy.c b/drivers/hid/hid-sjoy.c index bab93d71b760..963c45113204 100644 --- a/drivers/hid/hid-sjoy.c +++ b/drivers/hid/hid-sjoy.c @@ -91,17 +91,17 @@ static int sjoyff_init(struct hid_device *hid) set_bit(FF_RUMBLE, dev->ffbit); - error = input_ff_create_memless(dev, sjoyff, hid_sjoyff_play); - if (error) { - kfree(sjoyff); - return error; - } - sjoyff->report = report; sjoyff->report->field[0]->value[0] = 0x01; sjoyff->report->field[0]->value[1] = 0x00; sjoyff->report->field[0]->value[2] = 0x00; hid_hw_request(hid, sjoyff->report, HID_REQ_SET_REPORT); + + error = input_ff_create_memless(dev, sjoyff, hid_sjoyff_play); + if (error) { + kfree(sjoyff); + return error; + } } hid_info(hid, "Force feedback for SmartJoy PLUS PS2/USB adapter\n"); diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c index b5e724676c1d..315343415e8f 100644 --- a/drivers/hid/hid-sony.c +++ b/drivers/hid/hid-sony.c @@ -1169,10 +1169,9 @@ static int sony_raw_event(struct hid_device *hdev, struct hid_report *report, sixaxis_parse_report(sc, rd, size); } else if ((sc->quirks & MOTION_CONTROLLER_BT) && rd[0] == 0x01 && size == 49) { sixaxis_parse_report(sc, rd, size); - } else if ((sc->quirks & NAVIGATION_CONTROLLER) && rd[0] == 0x01 && - size == 49) { + } else if ((sc->quirks & NAVIGATION_CONTROLLER) && rd[0] == 0x01 && size == 49) { sixaxis_parse_report(sc, rd, size); - } else if ((sc->quirks & NSG_MRXU_REMOTE) && rd[0] == 0x02) { + } else if ((sc->quirks & NSG_MRXU_REMOTE) && rd[0] == 0x02 && size >= 12) { nsg_mrxu_parse_report(sc, rd, size); return 1; } else if ((sc->quirks & RB4_GUITAR_PS4_USB) && rd[0] == 0x01 && size == 64) { @@ -1189,7 +1188,7 @@ static int sony_raw_event(struct hid_device *hdev, struct hid_report *report, /* Rock Band 3 PS3 Pro instruments set rd[24] to 0xE0 when they're * sending full reports, and 0x02 when only sending navigation. */ - if ((sc->quirks & RB3_PRO_INSTRUMENT) && rd[24] == 0x02) { + if ((sc->quirks & RB3_PRO_INSTRUMENT) && size >= 25 && rd[24] == 0x02) { /* Only attempt to enable full report every 8 seconds */ if (time_after(jiffies, sc->rb3_pro_poke_jiffies)) { sc->rb3_pro_poke_jiffies = jiffies + secs_to_jiffies(8); @@ -1640,9 +1639,6 @@ static int sony_leds_init(struct sony_sc *sc) u8 max_brightness[MAX_LEDS] = { [0 ... (MAX_LEDS - 1)] = 1 }; u8 use_hw_blink[MAX_LEDS] = { 0 }; - if (WARN_ON(!(sc->quirks & SONY_LED_SUPPORT))) - return -EINVAL; - if (sc->quirks & BUZZ_CONTROLLER) { sc->led_count = 4; use_color_names = 0; @@ -2456,11 +2452,10 @@ static void sony_remove(struct hid_device *hdev) static int sony_suspend(struct hid_device *hdev, pm_message_t message) { #ifdef CONFIG_SONY_FF + struct sony_sc *sc = hid_get_drvdata(hdev); /* On suspend stop any running force-feedback events */ - if (SONY_FF_SUPPORT) { - struct sony_sc *sc = hid_get_drvdata(hdev); - + if (sc->quirks & SONY_FF_SUPPORT) { sc->left = sc->right = 0; sony_send_output_report(sc); } diff --git a/drivers/hid/hid-uclogic-core.c b/drivers/hid/hid-uclogic-core.c index bd7f93e96e4e..b73f09d26688 100644 --- a/drivers/hid/hid-uclogic-core.c +++ b/drivers/hid/hid-uclogic-core.c @@ -184,7 +184,9 @@ static int uclogic_input_configured(struct hid_device *hdev, suffix = "System Control"; break; } - } else { + } + + if (suffix) { hi->input->name = devm_kasprintf(&hdev->dev, GFP_KERNEL, "%s %s", hdev->name, suffix); if (!hi->input->name) diff --git a/drivers/hid/hid-vivaldi-common.c b/drivers/hid/hid-vivaldi-common.c index bf734055d4b6..b12bb5cc091a 100644 --- a/drivers/hid/hid-vivaldi-common.c +++ b/drivers/hid/hid-vivaldi-common.c @@ -85,7 +85,7 @@ void vivaldi_feature_mapping(struct hid_device *hdev, } ret = hid_report_raw_event(hdev, HID_FEATURE_REPORT, report_data, - report_len, 0); + report_len, report_len, 0); if (ret) { dev_warn(&hdev->dev, "failed to report feature %d\n", field->report->id); diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 5a183af3d5c6..3adb16366e93 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -149,6 +149,8 @@ static const struct i2c_hid_quirks { I2C_HID_QUIRK_BOGUS_IRQ }, { I2C_VENDOR_ID_GOODIX, I2C_DEVICE_ID_GOODIX_0D42, I2C_HID_QUIRK_DELAY_WAKEUP_AFTER_RESUME }, + { I2C_VENDOR_ID_BLTP, I2C_PRODUCT_ID_BLTP7853, + I2C_HID_QUIRK_NO_IRQ_AFTER_RESET }, { 0, 0 } }; @@ -574,9 +576,10 @@ static void i2c_hid_get_input(struct i2c_hid *ihid) if (ihid->hid->group != HID_GROUP_RMI) pm_wakeup_event(&ihid->client->dev, 0); - hid_input_report(ihid->hid, HID_INPUT_REPORT, - ihid->inbuf + sizeof(__le16), - ret_size - sizeof(__le16), 1); + hid_safe_input_report(ihid->hid, HID_INPUT_REPORT, + ihid->inbuf + sizeof(__le16), + ihid->bufsize - sizeof(__le16), + ret_size - sizeof(__le16), 1); } return; diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c index 16f780bc879b..cb19057f1191 100644 --- a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c +++ b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c @@ -94,7 +94,7 @@ static int quickspi_get_device_descriptor(struct quickspi_device *qsdev) dev_err_once(qsdev->dev, "Read DEVICE_DESCRIPTOR failed, ret = %d\n", ret); dev_err_once(qsdev->dev, "DEVICE_DESCRIPTOR expected len = %u, actual read = %u\n", input_len, read_len); - return ret; + return ret ?: -EINVAL; } input_rep_type = ((struct input_report_body_header *)read_buf)->input_report_type; @@ -318,7 +318,7 @@ int reset_tic(struct quickspi_device *qsdev) dev_err_once(qsdev->dev, "Read RESET_RESPONSE body failed, ret = %d\n", ret); dev_err_once(qsdev->dev, "RESET_RESPONSE body expected len = %u, actual = %u\n", read_len, actual_read_len); - return ret; + return ret ?: -EINVAL; } input_rep_type = FIELD_GET(HIDSPI_IN_REP_BDY_HDR_REP_TYPE, reset_response); diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index fbbfc0f60829..5af93b9b1fb5 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -283,9 +283,9 @@ static void hid_irq_in(struct urb *urb) break; usbhid_mark_busy(usbhid); if (!test_bit(HID_RESUME_RUNNING, &usbhid->iofl)) { - hid_input_report(urb->context, HID_INPUT_REPORT, - urb->transfer_buffer, - urb->actual_length, 1); + hid_safe_input_report(urb->context, HID_INPUT_REPORT, + urb->transfer_buffer, urb->transfer_buffer_length, + urb->actual_length, 1); /* * autosuspend refused while keys are pressed * because most keyboards don't wake up when @@ -482,9 +482,10 @@ static void hid_ctrl(struct urb *urb) switch (status) { case 0: /* success */ if (usbhid->ctrl[usbhid->ctrltail].dir == USB_DIR_IN) - hid_input_report(urb->context, + hid_safe_input_report(urb->context, usbhid->ctrl[usbhid->ctrltail].report->type, - urb->transfer_buffer, urb->actual_length, 0); + urb->transfer_buffer, urb->transfer_buffer_length, + urb->actual_length, 0); break; case -ESHUTDOWN: /* unplug */ unplug = 1; diff --git a/drivers/hid/usbhid/hid-pidff.c b/drivers/hid/usbhid/hid-pidff.c index aee8a4443305..c45f182d0448 100644 --- a/drivers/hid/usbhid/hid-pidff.c +++ b/drivers/hid/usbhid/hid-pidff.c @@ -11,6 +11,7 @@ #include "hid-pidff.h" #include <linux/hid.h> #include <linux/input.h> +#include <linux/math64.h> #include <linux/minmax.h> #include <linux/slab.h> #include <linux/stringify.h> @@ -326,8 +327,10 @@ static s32 pidff_clamp(s32 i, struct hid_field *field) */ static int pidff_rescale(int i, int max, struct hid_field *field) { - return i * (field->logical_maximum - field->logical_minimum) / max + - field->logical_minimum; + /* 64 bits needed for big values during rescale */ + s64 result = field->logical_maximum - field->logical_minimum; + + return div_s64(result * i, max) + field->logical_minimum; } /* diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index 0d1c6d90fe21..a32320b351e3 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -90,7 +90,7 @@ static void wacom_wac_queue_flush(struct hid_device *hdev, kfree(buf); continue; } - err = hid_report_raw_event(hdev, HID_INPUT_REPORT, buf, size, false); + err = hid_report_raw_event(hdev, HID_INPUT_REPORT, buf, size, size, false); if (err) { hid_warn(hdev, "%s: unable to flush event due to error %d\n", __func__, err); @@ -334,7 +334,7 @@ static void wacom_feature_mapping(struct hid_device *hdev, data, n, WAC_CMD_RETRIES); if (ret == n && features->type == HID_GENERIC) { ret = hid_report_raw_event(hdev, - HID_FEATURE_REPORT, data, n, 0); + HID_FEATURE_REPORT, data, n, n, 0); } else if (ret == 2 && features->type != HID_GENERIC) { features->touch_max = data[1]; } else { @@ -395,7 +395,7 @@ static void wacom_feature_mapping(struct hid_device *hdev, data, n, WAC_CMD_RETRIES); if (ret == n) { ret = hid_report_raw_event(hdev, HID_FEATURE_REPORT, - data, n, 0); + data, n, n, 0); } else { hid_warn(hdev, "%s: could not retrieve sensor offsets\n", __func__); diff --git a/drivers/iommu/amd/debugfs.c b/drivers/iommu/amd/debugfs.c index 4e66473d7cea..4c53b6361314 100644 --- a/drivers/iommu/amd/debugfs.c +++ b/drivers/iommu/amd/debugfs.c @@ -31,11 +31,12 @@ static ssize_t iommu_mmio_write(struct file *filp, const char __user *ubuf, if (cnt > OFS_IN_SZ) return -EINVAL; - ret = kstrtou32_from_user(ubuf, cnt, 0, &dbg_mmio_offset); + ret = kstrtos32_from_user(ubuf, cnt, 0, &dbg_mmio_offset); if (ret) return ret; - if (dbg_mmio_offset > iommu->mmio_phys_end - sizeof(u64)) + if (dbg_mmio_offset < 0 || dbg_mmio_offset > + iommu->mmio_phys_end - sizeof(u64)) return -EINVAL; iommu->dbg_mmio_offset = dbg_mmio_offset; @@ -71,12 +72,12 @@ static ssize_t iommu_capability_write(struct file *filp, const char __user *ubuf if (cnt > OFS_IN_SZ) return -EINVAL; - ret = kstrtou32_from_user(ubuf, cnt, 0, &dbg_cap_offset); + ret = kstrtos32_from_user(ubuf, cnt, 0, &dbg_cap_offset); if (ret) return ret; /* Capability register at offset 0x14 is the last IOMMU capability register. */ - if (dbg_cap_offset > 0x14) + if (dbg_cap_offset < 0 || dbg_cap_offset > 0x14) return -EINVAL; iommu->dbg_cap_offset = dbg_cap_offset; diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index f78e23f03938..57dc8fabc7d9 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -351,8 +351,12 @@ static struct amd_iommu *__rlookup_amd_iommu(u16 seg, u16 devid) struct amd_iommu_pci_seg *pci_seg; for_each_pci_segment(pci_seg) { - if (pci_seg->id == seg) - return pci_seg->rlookup_table[devid]; + if (pci_seg->id != seg) + continue; + /* IVRS may not describe every device on the bus */ + if (devid > pci_seg->last_bdf) + return NULL; + return pci_seg->rlookup_table[devid]; } return NULL; } diff --git a/drivers/iommu/generic_pt/iommu_pt.h b/drivers/iommu/generic_pt/iommu_pt.h index 19b6daf88f2a..dc91fb4e2f61 100644 --- a/drivers/iommu/generic_pt/iommu_pt.h +++ b/drivers/iommu/generic_pt/iommu_pt.h @@ -534,10 +534,12 @@ static int __map_range_leaf(struct pt_range *range, void *arg, struct pt_state pts = pt_init(range, level, table); struct pt_iommu_map_args *map = arg; unsigned int leaf_pgsize_lg2 = map->leaf_pgsize_lg2; + unsigned int leaves_avail; unsigned int start_index; pt_oaddr_t oa = map->oa; - unsigned int num_leaves; + pt_vaddr_t num_leaves; unsigned int orig_end; + unsigned int step_lg2; pt_vaddr_t last_va; unsigned int step; bool need_contig; @@ -546,21 +548,25 @@ static int __map_range_leaf(struct pt_range *range, void *arg, PT_WARN_ON(map->leaf_level != level); PT_WARN_ON(!pt_can_have_leaf(&pts)); - step = log2_to_int_t(unsigned int, - leaf_pgsize_lg2 - pt_table_item_lg2sz(&pts)); - need_contig = leaf_pgsize_lg2 != pt_table_item_lg2sz(&pts); + step_lg2 = leaf_pgsize_lg2 - pt_table_item_lg2sz(&pts); + step = log2_to_int_t(unsigned int, step_lg2); + need_contig = step_lg2 != 0; _pt_iter_first(&pts); start_index = pts.index; orig_end = pts.end_index; - if (pts.index + map->num_leaves < pts.end_index) { + leaves_avail = + log2_div_t(unsigned int, pts.end_index - pts.index, step_lg2); + if (map->num_leaves <= leaves_avail) { /* Need to stop in the middle of the table to change sizes */ - pts.end_index = pts.index + map->num_leaves; + pts.end_index = pts.index + log2_mul(map->num_leaves, step_lg2); num_leaves = 0; } else { - num_leaves = map->num_leaves - (pts.end_index - pts.index); + num_leaves = map->num_leaves - leaves_avail; } + PT_WARN_ON( + log2_mod_t(unsigned int, pts.end_index - pts.index, step_lg2)); do { pts.type = pt_load_entry_raw(&pts); if (pts.type != PT_ENTRY_EMPTY || need_contig) { @@ -920,8 +926,8 @@ static int NS(map_range)(struct pt_iommu *iommu_table, dma_addr_t iova, return ret; /* Calculate target page size and level for the leaves */ - if (pt_has_system_page_size(common) && len == PAGE_SIZE) { - PT_WARN_ON(!(pgsize_bitmap & PAGE_SIZE)); + if (pt_has_system_page_size(common) && len == PAGE_SIZE && + likely(pgsize_bitmap & PAGE_SIZE)) { if (log2_mod(iova | paddr, PAGE_SHIFT)) return -ENXIO; map.leaf_pgsize_lg2 = PAGE_SHIFT; diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index c3d18cd77d2f..4d0e65bc131d 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -3530,8 +3530,8 @@ void domain_remove_dev_pasid(struct iommu_domain *domain, if (!domain) return; - /* Identity domain has no meta data for pasid. */ - if (domain->type == IOMMU_DOMAIN_IDENTITY) + /* Identity domain and blocked domain have no meta data for pasid. */ + if (domain->type == IOMMU_DOMAIN_IDENTITY || domain->type == IOMMU_DOMAIN_BLOCKED) return; dmar_domain = to_dmar_domain(domain); @@ -3545,12 +3545,13 @@ void domain_remove_dev_pasid(struct iommu_domain *domain, } spin_unlock_irqrestore(&dmar_domain->lock, flags); + if (WARN_ON_ONCE(!dev_pasid)) + return; + cache_tag_unassign_domain(dmar_domain, dev, pasid); domain_detach_iommu(dmar_domain, iommu); - if (!WARN_ON_ONCE(!dev_pasid)) { - intel_iommu_debugfs_remove_dev_pasid(dev_pasid); - kfree(dev_pasid); - } + intel_iommu_debugfs_remove_dev_pasid(dev_pasid); + kfree(dev_pasid); } static int blocking_domain_set_dev_pasid(struct iommu_domain *domain, @@ -3937,6 +3938,9 @@ static void quirk_iommu_igfx(struct pci_dev *dev) disable_igfx_iommu = 1; } +/* Q35 integrated gfx dmar support is totally busted. */ +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x29b2, quirk_iommu_igfx); + /* G4x/GM45 integrated gfx dmar support is totally busted. */ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_igfx); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e00, quirk_iommu_igfx); diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 61c12ba78206..d1a9e713d3a0 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -62,14 +62,14 @@ struct iommu_group { int id; struct iommu_domain *default_domain; struct iommu_domain *blocking_domain; - /* - * During a group device reset, @resetting_domain points to the physical - * domain, while @domain points to the attached domain before the reset. - */ - struct iommu_domain *resetting_domain; struct iommu_domain *domain; struct list_head entry; unsigned int owner_cnt; + /* + * Number of devices in the group undergoing or awaiting recovery. + * If non-zero, concurrent domain attachments are rejected. + */ + unsigned int recovery_cnt; void *owner; }; @@ -77,12 +77,33 @@ struct group_device { struct list_head list; struct device *dev; char *name; + /* + * Device is blocked for a pending recovery while its group->domain is + * retained. This can happen when: + * - Device is undergoing a reset + */ + bool blocked; + unsigned int reset_depth; }; /* Iterate over each struct group_device in a struct iommu_group */ #define for_each_group_device(group, pos) \ list_for_each_entry(pos, &(group)->devices, list) +static struct group_device *__dev_to_gdev(struct device *dev) +{ + struct iommu_group *group = dev->iommu_group; + struct group_device *gdev; + + lockdep_assert_held(&group->mutex); + + for_each_group_device(group, gdev) { + if (gdev->dev == dev) + return gdev; + } + return NULL; +} + struct iommu_group_attribute { struct attribute attr; ssize_t (*show)(struct iommu_group *group, char *buf); @@ -2196,6 +2217,8 @@ EXPORT_SYMBOL_GPL(iommu_attach_device); int iommu_deferred_attach(struct device *dev, struct iommu_domain *domain) { + struct group_device *gdev; + /* * This is called on the dma mapping fast path so avoid locking. This is * racy, but we have an expectation that the driver will setup its DMAs @@ -2206,14 +2229,18 @@ int iommu_deferred_attach(struct device *dev, struct iommu_domain *domain) guard(mutex)(&dev->iommu_group->mutex); + gdev = __dev_to_gdev(dev); + if (WARN_ON(!gdev)) + return -ENODEV; + /* - * This is a concurrent attach during a device reset. Reject it until + * This is a concurrent attach during device recovery. Reject it until * pci_dev_reset_iommu_done() attaches the device to group->domain. * * Note that this might fail the iommu_dma_map(). But there's nothing * more we can do here. */ - if (dev->iommu_group->resetting_domain) + if (gdev->blocked) return -EBUSY; return __iommu_attach_device(domain, dev, NULL); } @@ -2270,19 +2297,24 @@ EXPORT_SYMBOL_GPL(iommu_get_domain_for_dev); struct iommu_domain *iommu_driver_get_domain_for_dev(struct device *dev) { struct iommu_group *group = dev->iommu_group; + struct group_device *gdev; lockdep_assert_held(&group->mutex); + gdev = __dev_to_gdev(dev); + if (WARN_ON(!gdev)) + return NULL; + /* * Driver handles the low-level __iommu_attach_device(), including the * one invoked by pci_dev_reset_iommu_done() re-attaching the device to * the cached group->domain. In this case, the driver must get the old - * domain from group->resetting_domain rather than group->domain. This + * domain from group->blocking_domain rather than group->domain. This * prevents it from re-attaching the device from group->domain (old) to * group->domain (new). */ - if (group->resetting_domain) - return group->resetting_domain; + if (gdev->blocked) + return group->blocking_domain; return group->domain; } @@ -2441,10 +2473,11 @@ static int __iommu_group_set_domain_internal(struct iommu_group *group, return -EINVAL; /* - * This is a concurrent attach during a device reset. Reject it until - * pci_dev_reset_iommu_done() attaches the device to group->domain. + * This is a concurrent attach during device recovery. Reject it until + * pci_dev_reset_iommu_done() attaches the device to group->domain, if + * IOMMU_SET_DOMAIN_MUST_SUCCEED is not set. */ - if (group->resetting_domain) + if (group->recovery_cnt && !(flags & IOMMU_SET_DOMAIN_MUST_SUCCEED)) return -EBUSY; /* @@ -2455,6 +2488,13 @@ static int __iommu_group_set_domain_internal(struct iommu_group *group, */ result = 0; for_each_group_device(group, gdev) { + /* + * Device under recovery is attached to group->blocking_domain. + * Don't change that. pci_dev_reset_iommu_done() will re-attach + * its domain to the updated group->domain, after the recovery. + */ + if (gdev->blocked) + continue; ret = __iommu_device_set_domain(group, gdev->dev, new_domain, group->domain, flags); if (ret) { @@ -2575,27 +2615,16 @@ out_set_count: static int __iommu_map_domain_pgtbl(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, - size_t size, int prot, gfp_t gfp) + size_t size, int prot, gfp_t gfp, + size_t *mapped) { const struct iommu_domain_ops *ops = domain->ops; - unsigned long orig_iova = iova; unsigned int min_pagesz; - size_t orig_size = size; int ret = 0; - might_sleep_if(gfpflags_allow_blocking(gfp)); - - if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING))) - return -EINVAL; - - if (WARN_ON(!ops->map_pages || domain->pgsize_bitmap == 0UL)) + if (WARN_ON(!ops->map_pages)) return -ENODEV; - /* Discourage passing strange GFP flags */ - if (WARN_ON_ONCE(gfp & (__GFP_COMP | __GFP_DMA | __GFP_DMA32 | - __GFP_HIGHMEM))) - return -EINVAL; - /* find out the minimum page size supported */ min_pagesz = 1 << __ffs(domain->pgsize_bitmap); @@ -2613,31 +2642,25 @@ static int __iommu_map_domain_pgtbl(struct iommu_domain *domain, pr_debug("map: iova 0x%lx pa %pa size 0x%zx\n", iova, &paddr, size); while (size) { - size_t pgsize, count, mapped = 0; + size_t pgsize, count, op_mapped = 0; pgsize = iommu_pgsize(domain, iova, paddr, size, &count); pr_debug("mapping: iova 0x%lx pa %pa pgsize 0x%zx count %zu\n", iova, &paddr, pgsize, count); ret = ops->map_pages(domain, iova, paddr, pgsize, count, prot, - gfp, &mapped); + gfp, &op_mapped); /* * Some pages may have been mapped, even if an error occurred, * so we should account for those so they can be unmapped. */ - size -= mapped; - + *mapped += op_mapped; if (ret) - break; - - iova += mapped; - paddr += mapped; - } + return ret; - /* unroll mapping in case something went wrong */ - if (ret) { - iommu_unmap(domain, orig_iova, orig_size - size); - return ret; + size -= op_mapped; + iova += op_mapped; + paddr += op_mapped; } return 0; } @@ -2655,25 +2678,31 @@ int iommu_map_nosync(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct pt_iommu *pt = iommupt_from_domain(domain); + size_t mapped = 0; int ret; - if (pt) { - size_t mapped = 0; + might_sleep_if(gfpflags_allow_blocking(gfp)); + /* Discourage passing strange GFP flags or illegal domains */ + if (WARN_ON_ONCE(!(domain->type & __IOMMU_DOMAIN_PAGING) || + !domain->pgsize_bitmap || + (gfp & (__GFP_COMP | __GFP_DMA | __GFP_DMA32 | + __GFP_HIGHMEM)))) + return -EINVAL; + + if (pt) ret = pt->ops->map_range(pt, iova, paddr, size, prot, gfp, &mapped); - if (ret) { - iommu_unmap(domain, iova, mapped); - return ret; - } - return 0; - } - ret = __iommu_map_domain_pgtbl(domain, iova, paddr, size, prot, gfp); - if (!ret) - return ret; + else + ret = __iommu_map_domain_pgtbl(domain, iova, paddr, size, prot, + gfp, &mapped); - trace_map(iova, paddr, size); - iommu_debug_map(domain, paddr, size); + trace_map(iova, paddr, mapped); + iommu_debug_map(domain, paddr, mapped); + if (ret) { + iommu_unmap(domain, iova, mapped); + return ret; + } return 0; } @@ -2702,10 +2731,7 @@ __iommu_unmap_domain_pgtbl(struct iommu_domain *domain, unsigned long iova, size_t unmapped_page, unmapped = 0; unsigned int min_pagesz; - if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING))) - return 0; - - if (WARN_ON(!ops->unmap_pages || domain->pgsize_bitmap == 0UL)) + if (WARN_ON(!ops->unmap_pages)) return 0; /* find out the minimum page size supported */ @@ -2724,8 +2750,6 @@ __iommu_unmap_domain_pgtbl(struct iommu_domain *domain, unsigned long iova, pr_debug("unmap this: iova 0x%lx size 0x%zx\n", iova, size); - iommu_debug_unmap_begin(domain, iova, size); - /* * Keep iterating until we either unmap 'size' bytes (or more) * or we hit an area that isn't mapped. @@ -2761,6 +2785,12 @@ static size_t __iommu_unmap(struct iommu_domain *domain, unsigned long iova, struct pt_iommu *pt = iommupt_from_domain(domain); size_t unmapped; + if (WARN_ON_ONCE(!(domain->type & __IOMMU_DOMAIN_PAGING) || + !domain->pgsize_bitmap)) + return 0; + + iommu_debug_unmap_begin(domain, iova, size); + if (pt) unmapped = pt->ops->unmap_range(pt, iova, size, iotlb_gather); else @@ -3570,7 +3600,12 @@ static void __iommu_remove_group_pasid(struct iommu_group *group, struct group_device *device; for_each_group_device(group, device) { - if (device->dev->iommu->max_pasids > 0) + /* + * A group-level detach cannot fail, even if there is a blocked + * device. In fact, blocked devices must be already detached for + * a pending device recovery. + */ + if (!device->blocked && device->dev->iommu->max_pasids > 0) iommu_remove_dev_pasid(device->dev, pasid, domain); } } @@ -3615,10 +3650,10 @@ int iommu_attach_device_pasid(struct iommu_domain *domain, mutex_lock(&group->mutex); /* - * This is a concurrent attach during a device reset. Reject it until + * This is a concurrent attach during device recovery. Reject it until * pci_dev_reset_iommu_done() attaches the device to group->domain. */ - if (group->resetting_domain) { + if (group->recovery_cnt) { ret = -EBUSY; goto out_unlock; } @@ -3708,10 +3743,10 @@ int iommu_replace_device_pasid(struct iommu_domain *domain, mutex_lock(&group->mutex); /* - * This is a concurrent attach during a device reset. Reject it until + * This is a concurrent attach during device recovery. Reject it until * pci_dev_reset_iommu_done() attaches the device to group->domain. */ - if (group->resetting_domain) { + if (group->recovery_cnt) { ret = -EBUSY; goto out_unlock; } @@ -3982,12 +4017,12 @@ EXPORT_SYMBOL_NS_GPL(iommu_replace_group_handle, "IOMMUFD_INTERNAL"); * routine wants to block any IOMMU activity: translation and ATS invalidation. * * This function attaches the device's RID/PASID(s) the group->blocking_domain, - * setting the group->resetting_domain. This allows the IOMMU driver pausing any + * incrementing the group->recovery_cnt, to allow the IOMMU driver pausing any * IOMMU activity while leaving the group->domain pointer intact. Later when the * reset is finished, pci_dev_reset_iommu_done() can restore everything. * * Caller must use pci_dev_reset_iommu_prepare() with pci_dev_reset_iommu_done() - * before/after the core-level reset routine, to unset the resetting_domain. + * before/after the core-level reset routine, to decrement the recovery_cnt. * * Return: 0 on success or negative error code if the preparation failed. * @@ -4000,6 +4035,7 @@ EXPORT_SYMBOL_NS_GPL(iommu_replace_group_handle, "IOMMUFD_INTERNAL"); int pci_dev_reset_iommu_prepare(struct pci_dev *pdev) { struct iommu_group *group = pdev->dev.iommu_group; + struct group_device *gdev; unsigned long pasid; void *entry; int ret; @@ -4009,45 +4045,99 @@ int pci_dev_reset_iommu_prepare(struct pci_dev *pdev) guard(mutex)(&group->mutex); - /* Re-entry is not allowed */ - if (WARN_ON(group->resetting_domain)) - return -EBUSY; + gdev = __dev_to_gdev(&pdev->dev); + if (WARN_ON(!gdev)) + return -ENODEV; + + if (gdev->reset_depth++) + return 0; ret = __iommu_group_alloc_blocking_domain(group); - if (ret) + if (ret) { + gdev->reset_depth--; return ret; + } /* Stage RID domain at blocking_domain while retaining group->domain */ if (group->domain != group->blocking_domain) { ret = __iommu_attach_device(group->blocking_domain, &pdev->dev, group->domain); - if (ret) + if (ret) { + gdev->reset_depth--; return ret; + } } /* + * Update gdev->blocked upon the domain change, as it is used to return + * the correct domain in iommu_driver_get_domain_for_dev() that might be + * called in a set_dev_pasid callback function. + */ + gdev->blocked = true; + + /* * Stage PASID domains at blocking_domain while retaining pasid_array. * * The pasid_array is mostly fenced by group->mutex, except one reader * in iommu_attach_handle_get(), so it's safe to read without xa_lock. */ - xa_for_each_start(&group->pasid_array, pasid, entry, 1) - iommu_remove_dev_pasid(&pdev->dev, pasid, - pasid_array_entry_to_domain(entry)); + if (pdev->dev.iommu->max_pasids > 0) { + xa_for_each_start(&group->pasid_array, pasid, entry, 1) { + struct iommu_domain *pasid_dom = + pasid_array_entry_to_domain(entry); + + iommu_remove_dev_pasid(&pdev->dev, pasid, pasid_dom); + } + } - group->resetting_domain = group->blocking_domain; + group->recovery_cnt++; return ret; } EXPORT_SYMBOL_GPL(pci_dev_reset_iommu_prepare); +static int __group_device_cmp_dma_alias(struct pci_dev *dev, u16 alias, + void *data) +{ + return alias == *(u16 *)data; +} + +static int group_device_cmp_dma_alias(struct pci_dev *dev, u16 alias, + void *data) +{ + return pci_for_each_dma_alias(data, __group_device_cmp_dma_alias, + &alias); +} + +static bool group_device_dma_alias_is_blocked(struct iommu_group *group, + struct group_device *gdev) +{ + struct group_device *sibling; + + lockdep_assert_held(&group->mutex); + + if (!dev_is_pci(gdev->dev)) + return false; + + for_each_group_device(group, sibling) { + if (sibling == gdev || !sibling->blocked || + !dev_is_pci(sibling->dev)) + continue; + if (pci_for_each_dma_alias(to_pci_dev(gdev->dev), + group_device_cmp_dma_alias, + to_pci_dev(sibling->dev))) + return true; + } + return false; +} + /** * pci_dev_reset_iommu_done() - Restore IOMMU after a PCI device reset is done * @pdev: PCI device that has finished a reset routine * * After a PCIe device finishes a reset routine, it wants to restore its IOMMU - * IOMMU activity, including new translation as well as cache invalidation, by - * re-attaching all RID/PASID of the device's back to the domains retained in - * the core-level structure. + * activity, including new translation and cache invalidation, by re-attaching + * all RID/PASID of the device back to the domains retained in the core-level + * structure. * * Caller must pair it with a successful pci_dev_reset_iommu_prepare(). * @@ -4057,6 +4147,7 @@ EXPORT_SYMBOL_GPL(pci_dev_reset_iommu_prepare); void pci_dev_reset_iommu_done(struct pci_dev *pdev) { struct iommu_group *group = pdev->dev.iommu_group; + struct group_device *gdev; unsigned long pasid; void *entry; @@ -4065,32 +4156,70 @@ void pci_dev_reset_iommu_done(struct pci_dev *pdev) guard(mutex)(&group->mutex); - /* pci_dev_reset_iommu_prepare() was bypassed for the device */ - if (!group->resetting_domain) + gdev = __dev_to_gdev(&pdev->dev); + if (WARN_ON(!gdev)) + return; + + /* Unbalanced done() calls would underflow the counter */ + if (WARN_ON(gdev->reset_depth == 0)) + return; + if (--gdev->reset_depth) return; - /* pci_dev_reset_iommu_prepare() was not successfully called */ if (WARN_ON(!group->blocking_domain)) return; - /* Re-attach RID domain back to group->domain */ - if (group->domain != group->blocking_domain) { + if (group_device_dma_alias_is_blocked(group, gdev)) { + /* + * FIXME: DMA aliased devices share the same RID, which would be + * convoluted to handle, as "gdev->blocked" is not sufficient: + * - "blocked" state is effectively shared across these devices + * - if the core skipped the blocking on the second device, the + * IOMMU driver's attachment state would diverge from the HW + * state + * For now, just warn and see whether real ATS use cases hit it. + */ + pci_warn(pdev, + "DMA-aliased sibling may be prematurely unblocked\n"); + } + + /* + * Re-attach RID domain back to group->domain + * + * Leave the device parked in the blocking_domain if group->domain isn't + * initialized yet + */ + if (group->domain && group->domain != group->blocking_domain) { WARN_ON(__iommu_attach_device(group->domain, &pdev->dev, group->blocking_domain)); } /* + * Update gdev->blocked upon the domain change, as it is used to return + * the correct domain in iommu_driver_get_domain_for_dev() that might be + * called in a set_dev_pasid callback function. + */ + gdev->blocked = false; + + /* * Re-attach PASID domains back to the domains retained in pasid_array. * * The pasid_array is mostly fenced by group->mutex, except one reader * in iommu_attach_handle_get(), so it's safe to read without xa_lock. */ - xa_for_each_start(&group->pasid_array, pasid, entry, 1) - WARN_ON(__iommu_set_group_pasid( - pasid_array_entry_to_domain(entry), group, pasid, - group->blocking_domain)); + if (pdev->dev.iommu->max_pasids > 0) { + xa_for_each_start(&group->pasid_array, pasid, entry, 1) { + struct iommu_domain *pasid_dom = + pasid_array_entry_to_domain(entry); + + WARN_ON(pasid_dom->ops->set_dev_pasid( + pasid_dom, &pdev->dev, pasid, + group->blocking_domain)); + } + } - group->resetting_domain = NULL; + if (!WARN_ON(group->recovery_cnt == 0)) + group->recovery_cnt--; } EXPORT_SYMBOL_GPL(pci_dev_reset_iommu_done); diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index e67b592e5697..8c86789d867a 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -1782,20 +1782,23 @@ void ena_com_phc_destroy(struct ena_com_dev *ena_dev) int ena_com_phc_get_timestamp(struct ena_com_dev *ena_dev, u64 *timestamp) { - volatile struct ena_admin_phc_resp *resp = ena_dev->phc.virt_addr; const ktime_t zero_system_time = ktime_set(0, 0); struct ena_com_phc_info *phc = &ena_dev->phc; + volatile struct ena_admin_phc_resp *resp; ktime_t expire_time; ktime_t block_time; unsigned long flags = 0; int ret = 0; + spin_lock_irqsave(&phc->lock, flags); + if (!phc->active) { + spin_unlock_irqrestore(&phc->lock, flags); netdev_err(ena_dev->net_device, "PHC feature is not active in the device\n"); return -EOPNOTSUPP; } - spin_lock_irqsave(&phc->lock, flags); + resp = ena_dev->phc.virt_addr; /* Check if PHC is in blocked state */ if (unlikely(ktime_compare(phc->system_time, zero_system_time))) { diff --git a/drivers/net/ethernet/amazon/ena/ena_phc.c b/drivers/net/ethernet/amazon/ena/ena_phc.c index 7867e893fd15..c2a3ff1ef645 100644 --- a/drivers/net/ethernet/amazon/ena/ena_phc.c +++ b/drivers/net/ethernet/amazon/ena/ena_phc.c @@ -46,9 +46,12 @@ static int ena_phc_gettimex64(struct ptp_clock_info *clock_info, spin_unlock_irqrestore(&phc_info->lock, flags); + if (rc) + return rc; + *ts = ns_to_timespec64(timestamp_nsec); - return rc; + return 0; } static int ena_phc_settime64(struct ptp_clock_info *clock_info, diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index b854b6b42d77..2926e1e59941 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -910,7 +910,9 @@ static int xgene_mdiobus_register(struct xgene_enet_pdata *pdata, return -ENXIO; } - return of_mdiobus_register(mdio, mdio_np); + ret = of_mdiobus_register(mdio, mdio_np); + of_node_put(mdio_np); + return ret; } /* Mask out all PHYs from auto probing. */ diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index e9e38af680c3..39e1b606a75a 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -371,7 +371,7 @@ static void aq_pci_shutdown(struct pci_dev *pdev) pci_disable_device(pdev); if (system_state == SYSTEM_POWER_OFF) { - pci_wake_from_d3(pdev, false); + pci_wake_from_d3(pdev, self->aq_hw->aq_nic_cfg->wol); pci_set_power_state(pdev, PCI_D3hot); } } diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c index fa5857923db4..b4bfd6c174e7 100644 --- a/drivers/net/ethernet/cirrus/cs89x0.c +++ b/drivers/net/ethernet/cirrus/cs89x0.c @@ -1271,7 +1271,6 @@ static const struct net_device_ops net_ops = { static void __init reset_chip(struct net_device *dev) { -#if !defined(CONFIG_MACH_MX31ADS) struct net_local *lp = netdev_priv(dev); unsigned long reset_start_time; @@ -1298,7 +1297,6 @@ static void __init reset_chip(struct net_device *dev) while ((readreg(dev, PP_SelfST) & INIT_DONE) == 0 && time_before(jiffies, reset_start_time + 2)) ; -#endif /* !CONFIG_MACH_MX31ADS */ } /* This is the real probe routine. diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 065cbbf52686..4c762229ce42 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -122,6 +122,9 @@ struct gemini_ethernet_port { struct napi_struct napi; struct hrtimer rx_coalesce_timer; unsigned int rx_coalesce_nsecs; + struct sk_buff *rx_skb; + unsigned int rx_frag_nr; + unsigned int freeq_refill; struct gmac_txq txq[TX_QUEUE_NUM]; unsigned int txq_order; @@ -1442,10 +1445,11 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) unsigned short m = (1 << port->rxq_order) - 1; struct gemini_ethernet *geth = port->geth; void __iomem *ptr_reg = port->rxq_rwptr; + unsigned int frag_nr = port->rx_frag_nr; + struct sk_buff *skb = port->rx_skb; unsigned int frame_len, frag_len; struct gmac_rxdesc *rx = NULL; struct gmac_queue_page *gpage; - static struct sk_buff *skb; union gmac_rxdesc_0 word0; union gmac_rxdesc_1 word1; union gmac_rxdesc_3 word3; @@ -1455,7 +1459,6 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) unsigned short r, w; union dma_rwptr rw; dma_addr_t mapping; - int frag_nr = 0; spin_lock_irqsave(&geth->irq_lock, flags); rw.bits32 = readl(ptr_reg); @@ -1491,10 +1494,11 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) gpage = gmac_get_queue_page(geth, port, mapping + PAGE_SIZE); if (!gpage) { dev_err(geth->dev, "could not find mapping\n"); + port->stats.rx_dropped++; if (skb) { napi_free_frags(&port->napi); - port->stats.rx_dropped++; skb = NULL; + frag_nr = 0; } continue; } @@ -1504,6 +1508,8 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) if (skb) { napi_free_frags(&port->napi); port->stats.rx_dropped++; + skb = NULL; + frag_nr = 0; } skb = gmac_skb_if_good_frame(port, word0, frame_len); @@ -1538,6 +1544,7 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) if (word3.bits32 & EOF_BIT) { napi_gro_frags(&port->napi); skb = NULL; + frag_nr = 0; --budget; } continue; @@ -1546,6 +1553,7 @@ err_drop: if (skb) { napi_free_frags(&port->napi); skb = NULL; + frag_nr = 0; } if (mapping) @@ -1554,6 +1562,8 @@ err_drop: port->stats.rx_dropped++; } + port->rx_skb = skb; + port->rx_frag_nr = frag_nr; writew(r, ptr_reg); return budget; } @@ -1881,6 +1891,8 @@ static int gmac_stop(struct net_device *netdev) gmac_disable_tx_rx(netdev); gmac_stop_dma(port); napi_disable(&port->napi); + port->rx_skb = NULL; + port->rx_frag_nr = 0; gmac_enable_irq(netdev, 0); gmac_cleanup_rxq(netdev); diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index dcb50c2e1aa2..83e780919ac9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -1318,6 +1318,7 @@ void i40e_ptp_restore_hw_time(struct i40e_pf *pf); void i40e_ptp_init(struct i40e_pf *pf); void i40e_ptp_stop(struct i40e_pf *pf); int i40e_ptp_alloc_pins(struct i40e_pf *pf); +void i40e_ptp_free_pins(struct i40e_pf *pf); int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset); int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi); int i40e_get_partition_bw_setting(struct i40e_pf *pf); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 028bd500603a..6d4f9218dc68 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -16108,9 +16108,11 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Unwind what we've done if something failed in the setup */ err_vsis: set_bit(__I40E_DOWN, pf->state); + i40e_ptp_stop(pf); i40e_clear_interrupt_scheme(pf); kfree(pf->vsi); err_switch_setup: + i40e_ptp_free_pins(pf); i40e_reset_interrupt_capability(pf); timer_shutdown_sync(&pf->service_timer); err_mac_addr: diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index 404a716db8da..7d07c389bb23 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -940,12 +940,13 @@ int i40e_ptp_hwtstamp_get(struct net_device *netdev, * * Release memory allocated for PTP pins. **/ -static void i40e_ptp_free_pins(struct i40e_pf *pf) +void i40e_ptp_free_pins(struct i40e_pf *pf) { if (i40e_is_ptp_pin_dev(&pf->hw)) { kfree(pf->ptp_pins); kfree(pf->ptp_caps.pin_config); pf->ptp_pins = NULL; + pf->ptp_caps.pin_config = NULL; } } diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index 16aa25535152..0bc6dd375687 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -537,14 +537,14 @@ void ice_dcb_rebuild(struct ice_pf *pf) struct ice_dcbx_cfg *err_cfg; int ret; + mutex_lock(&pf->tc_mutex); + ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL); if (ret) { dev_err(dev, "Query Port ETS failed\n"); goto dcb_error; } - mutex_lock(&pf->tc_mutex); - if (!pf->hw.port_info->qos_cfg.is_sw_lldp) ice_cfg_etsrec_defaults(pf->hw.port_info); diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index 27b460926bac..892bc7c2e28b 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -2523,6 +2523,8 @@ ice_dpll_rclk_state_on_pin_set(const struct dpll_pin *pin, void *pin_priv, if (hw_idx < 0) goto unlock; hw_idx -= pf->dplls.base_rclk_idx; + if (hw_idx >= ICE_DPLL_RCLK_NUM_MAX) + goto unlock; if ((enable && p->state[hw_idx] == DPLL_PIN_STATE_CONNECTED) || (!enable && p->state[hw_idx] == DPLL_PIN_STATE_DISCONNECTED)) { @@ -2586,6 +2588,9 @@ ice_dpll_rclk_state_on_pin_get(const struct dpll_pin *pin, void *pin_priv, hw_idx = ice_dpll_pin_get_parent_idx(p, parent_pin); if (hw_idx < 0) goto unlock; + hw_idx -= pf->dplls.base_rclk_idx; + if (hw_idx >= ICE_DPLL_RCLK_NUM_MAX) + goto unlock; ret = ice_dpll_pin_state_update(pf, p, ICE_DPLL_PIN_TYPE_RCLK_INPUT, extack); diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.h b/drivers/net/ethernet/intel/ice/ice_dpll.h index ae42cdea0ee1..8678575359b9 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.h +++ b/drivers/net/ethernet/intel/ice/ice_dpll.h @@ -8,6 +8,22 @@ #define ICE_DPLL_RCLK_NUM_MAX 4 +#define ICE_CGU_R10 0x28 +#define ICE_CGU_R10_SYNCE_CLKO_SEL GENMASK(8, 5) +#define ICE_CGU_R10_SYNCE_CLKODIV_M1 GENMASK(13, 9) +#define ICE_CGU_R10_SYNCE_CLKODIV_LOAD BIT(14) +#define ICE_CGU_R10_SYNCE_DCK_RST BIT(15) +#define ICE_CGU_R10_SYNCE_ETHCLKO_SEL GENMASK(18, 16) +#define ICE_CGU_R10_SYNCE_ETHDIV_M1 GENMASK(23, 19) +#define ICE_CGU_R10_SYNCE_ETHDIV_LOAD BIT(24) +#define ICE_CGU_R10_SYNCE_DCK2_RST BIT(25) +#define ICE_CGU_R10_SYNCE_S_REF_CLK GENMASK(31, 27) + +#define ICE_CGU_R11 0x2C +#define ICE_CGU_R11_SYNCE_S_BYP_CLK GENMASK(6, 1) + +#define ICE_CGU_BYPASS_MUX_OFFSET_E825C 3 + /** * enum ice_dpll_pin_sw - enumerate ice software pin indices: * @ICE_DPLL_PIN_SW_1_IDX: index of first SW pin @@ -157,19 +173,3 @@ static inline void ice_dpll_deinit(struct ice_pf *pf) { } #endif #endif - -#define ICE_CGU_R10 0x28 -#define ICE_CGU_R10_SYNCE_CLKO_SEL GENMASK(8, 5) -#define ICE_CGU_R10_SYNCE_CLKODIV_M1 GENMASK(13, 9) -#define ICE_CGU_R10_SYNCE_CLKODIV_LOAD BIT(14) -#define ICE_CGU_R10_SYNCE_DCK_RST BIT(15) -#define ICE_CGU_R10_SYNCE_ETHCLKO_SEL GENMASK(18, 16) -#define ICE_CGU_R10_SYNCE_ETHDIV_M1 GENMASK(23, 19) -#define ICE_CGU_R10_SYNCE_ETHDIV_LOAD BIT(24) -#define ICE_CGU_R10_SYNCE_DCK2_RST BIT(25) -#define ICE_CGU_R10_SYNCE_S_REF_CLK GENMASK(31, 27) - -#define ICE_CGU_R11 0x2C -#define ICE_CGU_R11_SYNCE_S_BYP_CLK GENMASK(6, 1) - -#define ICE_CGU_BYPASS_MUX_OFFSET_E825C 3 diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 1d1947a7fe11..c52c465280f7 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -8046,7 +8046,7 @@ int ice_set_rss_hfunc(struct ice_vsi *vsi, u8 hfunc) ctx->info.q_opt_rss |= FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_HASH_M, hfunc); ctx->info.q_opt_tc = vsi->info.q_opt_tc; - ctx->info.q_opt_flags = vsi->info.q_opt_rss; + ctx->info.q_opt_flags = vsi->info.q_opt_flags; err = ice_update_vsi(hw, vsi->idx, ctx, NULL); if (err) { diff --git a/drivers/net/ethernet/intel/idpf/idpf_idc.c b/drivers/net/ethernet/intel/idpf/idpf_idc.c index 7e4f4ac92653..b7d6b08fc89e 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_idc.c +++ b/drivers/net/ethernet/intel/idpf/idpf_idc.c @@ -90,7 +90,10 @@ static int idpf_plug_vport_aux_dev(struct iidc_rdma_core_dev_info *cdev_info, return 0; err_aux_dev_add: + ida_free(&idpf_idc_ida, adev->id); + vdev_info->adev = NULL; auxiliary_device_uninit(adev); + return ret; err_aux_dev_init: ida_free(&idpf_idc_ida, adev->id); err_ida_alloc: @@ -228,7 +231,10 @@ static int idpf_plug_core_aux_dev(struct iidc_rdma_core_dev_info *cdev_info) return 0; err_aux_dev_add: + ida_free(&idpf_idc_ida, adev->id); + cdev_info->adev = NULL; auxiliary_device_uninit(adev); + return ret; err_aux_dev_init: ida_free(&idpf_idc_ida, adev->id); err_ida_alloc: diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_ptp.c index eec91c4f0a75..4a51d2727547 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_ptp.c +++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.c @@ -952,6 +952,8 @@ int idpf_ptp_init(struct idpf_adapter *adapter) goto free_ptp; } + spin_lock_init(&adapter->ptp->read_dev_clk_lock); + err = idpf_ptp_create_clock(adapter); if (err) goto free_ptp; @@ -977,8 +979,6 @@ int idpf_ptp_init(struct idpf_adapter *adapter) goto remove_clock; } - spin_lock_init(&adapter->ptp->read_dev_clk_lock); - pci_dbg(adapter->pdev, "PTP init successful\n"); return 0; diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index 47752d3fde0b..1179a6e127c5 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -749,11 +749,10 @@ static void lan966x_cleanup_ports(struct lan966x *lan966x) for (p = 0; p < lan966x->num_phys_ports; p++) { port = lan966x->ports[p]; - if (!port) + if (!port || !port->dev) continue; - if (port->dev) - unregister_netdev(port->dev); + unregister_netdev(port->dev); lan966x_xdp_port_deinit(port); if (lan966x->fdma && lan966x->fdma_ndev == port->dev) @@ -873,6 +872,9 @@ static int lan966x_probe_port(struct lan966x *lan966x, u32 p, err = register_netdev(dev); if (err) { dev_err(lan966x->dev, "register_netdev failed\n"); + phylink_destroy(phylink); + port->phylink = NULL; + port->dev = NULL; return err; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 42c6dcfb1f0f..dd75c47758e1 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -5103,6 +5103,13 @@ static int qed_init_wfq_param(struct qed_hwfn *p_hwfn, return -EINVAL; } + /* All vports are already or become configured, nothing to distribute */ + if (non_requested_count == 0) { + p_hwfn->qm_info.wfq_data[vport_id].min_speed = req_rate; + p_hwfn->qm_info.wfq_data[vport_id].configured = true; + return 0; + } + total_left_rate = min_pf_rate - total_req_min_rate; left_rate_per_vp = total_left_rate / non_requested_count; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 1dbfadb2a881..5f88733094d0 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1108,9 +1108,12 @@ static int ravb_stop_dma(struct net_device *ndev) /* Request for transmission suspension */ ravb_modify(ndev, CCC, CCC_DTSR, CCC_DTSR); - error = ravb_wait(ndev, CSR, CSR_DTS, CSR_DTS); - if (error) - netdev_err(ndev, "failed to stop AXI BUS\n"); + /* Access to URAM will not be suspended if WoL is enabled. */ + if (!priv->wol_enabled) { + error = ravb_wait(ndev, CSR, CSR_DTS, CSR_DTS); + if (error) + netdev_err(ndev, "failed to stop AXI BUS\n"); + } /* Stop AVB-DMAC process */ return ravb_set_opmode(ndev, CCC_OPC_CONFIG); diff --git a/drivers/net/ethernet/ti/icssm/icssm_prueth.c b/drivers/net/ethernet/ti/icssm/icssm_prueth.c index 53bbd9290904..b7e94244355a 100644 --- a/drivers/net/ethernet/ti/icssm/icssm_prueth.c +++ b/drivers/net/ethernet/ti/icssm/icssm_prueth.c @@ -1825,6 +1825,7 @@ static int icssm_prueth_probe(struct platform_device *pdev) dev_err(dev, "%pOF error reading port_id %d\n", eth_node, ret); of_node_put(eth_node); + of_node_put(eth_ports_node); return ret; } diff --git a/drivers/net/fddi/defza.c b/drivers/net/fddi/defza.c index 064fa484f797..9bfecc87d6b2 100644 --- a/drivers/net/fddi/defza.c +++ b/drivers/net/fddi/defza.c @@ -984,7 +984,7 @@ static irqreturn_t fza_interrupt(int irq, void *dev_id) case FZA_STATE_UNINITIALIZED: netif_carrier_off(dev); - timer_delete_sync(&fp->reset_timer); + timer_delete_sync_try(&fp->reset_timer); fp->ring_cmd_index = 0; fp->ring_uns_index = 0; fp->ring_rmc_tx_index = 0; @@ -1018,7 +1018,9 @@ static irqreturn_t fza_interrupt(int irq, void *dev_id) fp->queue_active = 0; netif_stop_queue(dev); pr_debug("%s: queue stopped\n", fp->name); - timer_delete_sync(&fp->reset_timer); + + spin_lock(&fp->lock); + timer_delete(&fp->reset_timer); pr_warn("%s: halted, reason: %x\n", fp->name, FZA_STATUS_GET_HALT(status)); fza_regs_dump(fp); @@ -1027,6 +1029,8 @@ static irqreturn_t fza_interrupt(int irq, void *dev_id) fp->timer_state = 0; fp->reset_timer.expires = jiffies + 45 * HZ; add_timer(&fp->reset_timer); + spin_unlock(&fp->lock); + break; default: @@ -1046,7 +1050,9 @@ static irqreturn_t fza_interrupt(int irq, void *dev_id) static void fza_reset_timer(struct timer_list *t) { struct fza_private *fp = timer_container_of(fp, t, reset_timer); + unsigned long flags; + spin_lock_irqsave(&fp->lock, flags); if (!fp->timer_state) { pr_err("%s: RESET timed out!\n", fp->name); pr_info("%s: trying harder...\n", fp->name); @@ -1069,6 +1075,7 @@ static void fza_reset_timer(struct timer_list *t) fp->reset_timer.expires = jiffies + 45 * HZ; } add_timer(&fp->reset_timer); + spin_unlock_irqrestore(&fp->lock, flags); } static int fza_set_mac_address(struct net_device *dev, void *addr) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 6147ee8b1d78..f904f4d16b45 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -26,6 +26,8 @@ #include <uapi/linux/if_macsec.h> +static struct workqueue_struct *macsec_wq; + /* SecTAG length = macsec_eth_header without the optional SCI */ #define MACSEC_TAG_LEN 6 @@ -174,9 +176,10 @@ static void macsec_rxsc_put(struct macsec_rx_sc *sc) call_rcu(&sc->rcu_head, free_rx_sc_rcu); } -static void free_rxsa(struct rcu_head *head) +static void free_rxsa_work(struct work_struct *work) { - struct macsec_rx_sa *sa = container_of(head, struct macsec_rx_sa, rcu); + struct macsec_rx_sa *sa = + container_of(to_rcu_work(work), struct macsec_rx_sa, destroy_work); crypto_free_aead(sa->key.tfm); free_percpu(sa->stats); @@ -186,7 +189,7 @@ static void free_rxsa(struct rcu_head *head) static void macsec_rxsa_put(struct macsec_rx_sa *sa) { if (refcount_dec_and_test(&sa->refcnt)) - call_rcu(&sa->rcu, free_rxsa); + queue_rcu_work(macsec_wq, &sa->destroy_work); } static struct macsec_tx_sa *macsec_txsa_get(struct macsec_tx_sa __rcu *ptr) @@ -202,9 +205,10 @@ static struct macsec_tx_sa *macsec_txsa_get(struct macsec_tx_sa __rcu *ptr) return sa; } -static void free_txsa(struct rcu_head *head) +static void free_txsa_work(struct work_struct *work) { - struct macsec_tx_sa *sa = container_of(head, struct macsec_tx_sa, rcu); + struct macsec_tx_sa *sa = + container_of(to_rcu_work(work), struct macsec_tx_sa, destroy_work); crypto_free_aead(sa->key.tfm); free_percpu(sa->stats); @@ -214,7 +218,7 @@ static void free_txsa(struct rcu_head *head) static void macsec_txsa_put(struct macsec_tx_sa *sa) { if (refcount_dec_and_test(&sa->refcnt)) - call_rcu(&sa->rcu, free_txsa); + queue_rcu_work(macsec_wq, &sa->destroy_work); } static struct macsec_cb *macsec_skb_cb(struct sk_buff *skb) @@ -1407,6 +1411,7 @@ static int init_rx_sa(struct macsec_rx_sa *rx_sa, char *sak, int key_len, rx_sa->next_pn = 1; refcount_set(&rx_sa->refcnt, 1); spin_lock_init(&rx_sa->lock); + INIT_RCU_WORK(&rx_sa->destroy_work, free_rxsa_work); return 0; } @@ -1506,6 +1511,7 @@ static int init_tx_sa(struct macsec_tx_sa *tx_sa, char *sak, int key_len, tx_sa->active = false; refcount_set(&tx_sa->refcnt, 1); spin_lock_init(&tx_sa->lock); + INIT_RCU_WORK(&tx_sa->destroy_work, free_txsa_work); return 0; } @@ -4505,25 +4511,35 @@ static int __init macsec_init(void) { int err; + macsec_wq = alloc_workqueue("macsec", WQ_UNBOUND, 0); + if (!macsec_wq) + return -ENOMEM; + pr_info("MACsec IEEE 802.1AE\n"); err = register_netdevice_notifier(&macsec_notifier); if (err) - return err; + goto err_destroy_wq; err = rtnl_link_register(&macsec_link_ops); if (err) - goto notifier; + goto err_notifier; err = genl_register_family(&macsec_fam); if (err) - goto rtnl; + goto err_rtnl; return 0; -rtnl: +err_rtnl: rtnl_link_unregister(&macsec_link_ops); -notifier: +err_notifier: unregister_netdevice_notifier(&macsec_notifier); +err_destroy_wq: + /* Precautionary, mirrors macsec_exit() to stay safe if work + * ever becomes queueable before this point in the future. + */ + rcu_barrier(); + destroy_workqueue(macsec_wq); return err; } @@ -4533,6 +4549,7 @@ static void __exit macsec_exit(void) rtnl_link_unregister(&macsec_link_ops); unregister_netdevice_notifier(&macsec_notifier); rcu_barrier(); + destroy_workqueue(macsec_wq); } module_init(macsec_init); diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c index d0361aaf25ef..3f7d31033bae 100644 --- a/drivers/net/net_failover.c +++ b/drivers/net/net_failover.c @@ -502,7 +502,7 @@ static int net_failover_slave_register(struct net_device *slave_dev, /* Align MTU of slave with failover dev */ orig_mtu = slave_dev->mtu; - err = dev_set_mtu(slave_dev, failover_dev->mtu); + err = netif_set_mtu(slave_dev, failover_dev->mtu); if (err) { netdev_err(failover_dev, "unable to change mtu of %s to %u register failed\n", slave_dev->name, failover_dev->mtu); @@ -512,11 +512,11 @@ static int net_failover_slave_register(struct net_device *slave_dev, dev_hold(slave_dev); if (netif_running(failover_dev)) { - err = dev_open(slave_dev, NULL); + err = netif_open(slave_dev, NULL); if (err && (err != -EBUSY)) { netdev_err(failover_dev, "Opening slave %s failed err:%d\n", slave_dev->name, err); - goto err_dev_open; + goto err_netif_open; } } @@ -562,10 +562,10 @@ static int net_failover_slave_register(struct net_device *slave_dev, err_vlan_add: dev_uc_unsync(slave_dev, failover_dev); dev_mc_unsync(slave_dev, failover_dev); - dev_close(slave_dev); -err_dev_open: + netif_close(slave_dev); +err_netif_open: dev_put(slave_dev); - dev_set_mtu(slave_dev, orig_mtu); + netif_set_mtu(slave_dev, orig_mtu); done: return err; } diff --git a/drivers/net/phy/dp83tc811.c b/drivers/net/phy/dp83tc811.c index e480c2a07450..252fb12b3e68 100644 --- a/drivers/net/phy/dp83tc811.c +++ b/drivers/net/phy/dp83tc811.c @@ -393,6 +393,7 @@ static struct phy_driver dp83811_driver[] = { .config_init = dp83811_config_init, .config_aneg = dp83811_config_aneg, .soft_reset = dp83811_phy_reset, + .get_features = genphy_c45_pma_read_ext_abilities, .get_wol = dp83811_get_wol, .set_wol = dp83811_set_wol, .config_intr = dp83811_config_intr, diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c index 15bfb78381d4..809f21fb93f5 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.c +++ b/drivers/net/wan/fsl_ucc_hdlc.c @@ -740,6 +740,8 @@ static int uhdlc_open(struct net_device *dev) static void uhdlc_memclean(struct ucc_hdlc_private *priv) { + int i; + qe_muram_free(ioread16be(&priv->ucc_pram->riptr)); qe_muram_free(ioread16be(&priv->ucc_pram->tiptr)); @@ -770,6 +772,11 @@ static void uhdlc_memclean(struct ucc_hdlc_private *priv) kfree(priv->rx_skbuff); priv->rx_skbuff = NULL; + for (i = 0; i < TX_BD_RING_LEN; i++) { + dev_kfree_skb(priv->tx_skbuff[i]); + priv->tx_skbuff[i] = NULL; + } + kfree(priv->tx_skbuff); priv->tx_skbuff = NULL; diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c index 423c9c628e7b..c692fc73babf 100644 --- a/drivers/nvme/host/apple.c +++ b/drivers/nvme/host/apple.c @@ -1009,6 +1009,7 @@ static void apple_nvme_init_queue(struct apple_nvme_queue *q) unsigned int depth = apple_nvme_queue_depth(q); struct apple_nvme *anv = queue_to_apple_nvme(q); + q->sq_tail = 0; q->cq_head = 0; q->cq_phase = 1; if (anv->hw->has_lsq_nvmmu) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index dc388e24caad..c3032d6ad6b1 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3749,6 +3749,10 @@ int nvme_init_ctrl_finish(struct nvme_ctrl *ctrl, bool was_suspended) ret = nvme_hwmon_init(ctrl); if (ret == -EINTR) return ret; + + if (!nvme_ctrl_sgl_supported(ctrl)) + dev_info(ctrl->device, + "passthrough uses implicit buffer lengths\n"); } clear_bit(NVME_CTRL_DIRTY_CAPABILITY, &ctrl->flags); @@ -5041,8 +5045,8 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl) nvme_mpath_update(ctrl); } - nvme_change_uevent(ctrl, "NVME_EVENT=connected"); set_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags); + nvme_change_uevent(ctrl, "NVME_EVENT=connected"); } EXPORT_SYMBOL_GPL(nvme_start_ctrl); diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 9597a87cf05d..08889b20e5d8 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -120,21 +120,11 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer, struct nvme_ns *ns = q->queuedata; struct block_device *bdev = ns ? ns->disk->part0 : NULL; bool supports_metadata = bdev && blk_get_integrity(bdev->bd_disk); - struct nvme_ctrl *ctrl = nvme_req(req)->ctrl; bool has_metadata = meta_buffer && meta_len; - struct bio *bio = NULL; int ret; - if (!nvme_ctrl_sgl_supported(ctrl)) - dev_warn_once(ctrl->device, "using unchecked data buffer\n"); - if (has_metadata) { - if (!supports_metadata) - return -EINVAL; - - if (!nvme_ctrl_meta_sgl_supported(ctrl)) - dev_warn_once(ctrl->device, - "using unchecked metadata buffer\n"); - } + if (has_metadata && !supports_metadata) + return -EINVAL; if (iter) ret = blk_rq_map_user_iov(q, req, NULL, iter, GFP_KERNEL); @@ -154,8 +144,8 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer, return ret; out_unmap: - if (bio) - blk_rq_unmap_user(bio); + if (req->bio) + blk_rq_unmap_user(req->bio); return ret; } diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 9fd04cd7c5cb..139a10cd687f 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2533,11 +2533,13 @@ static void nvme_free_host_mem_multi(struct nvme_dev *dev) static void nvme_free_host_mem(struct nvme_dev *dev) { - if (dev->hmb_sgt) + if (dev->hmb_sgt) { dma_free_noncontiguous(dev->dev, dev->host_mem_size, dev->hmb_sgt, DMA_BIDIRECTIONAL); - else + dev->hmb_sgt = NULL; + } else { nvme_free_host_mem_multi(dev); + } dma_free_coherent(dev->dev, dev->host_mem_descs_size, dev->host_mem_descs, dev->host_mem_descs_dma); @@ -4107,8 +4109,6 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, }, { PCI_DEVICE(0x1c5f, 0x0555), /* Memblaze Pblaze5 adapter */ .driver_data = NVME_QUIRK_NO_NS_DESC_LIST, }, - { PCI_DEVICE(0x144d, 0xa808), /* Samsung PM981/983 */ - .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_DEVICE(0x144d, 0xa821), /* Samsung PM1725 */ .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, }, { PCI_DEVICE(0x144d, 0xa822), /* Samsung PM1725a */ diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig index 4904097dfd49..69bde270115e 100644 --- a/drivers/nvme/target/Kconfig +++ b/drivers/nvme/target/Kconfig @@ -117,6 +117,15 @@ config NVME_TARGET_AUTH If unsure, say N. +config NVME_TARGET_AUTH_DEBUG + bool "NVMe over Fabrics In-band Authentication debug messages" + depends on NVME_TARGET_AUTH + help + This enables additional debug messages including the generated + DH-HMAC-CHAP secrets to help debugging authentication failures. + + If unsure, say N. + config NVME_TARGET_PCI_EPF tristate "NVMe PCI Endpoint Function target support" depends on NVME_TARGET && PCI_ENDPOINT diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c index 9a2eccdc8b13..edb9627d97b0 100644 --- a/drivers/nvme/target/auth.c +++ b/drivers/nvme/target/auth.c @@ -144,7 +144,6 @@ u8 nvmet_setup_auth(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq, bool reset) goto out_unlock; list_for_each_entry(p, &ctrl->subsys->hosts, entry) { - pr_debug("check %s\n", nvmet_host_name(p->host)); if (strcmp(nvmet_host_name(p->host), ctrl->hostnqn)) continue; host = p->host; @@ -189,11 +188,12 @@ u8 nvmet_setup_auth(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq, bool reset) ctrl->host_key = NULL; goto out_free_hash; } +#ifdef CONFIG_NVME_TARGET_AUTH_DEBUG pr_debug("%s: using hash %s key %*ph\n", __func__, ctrl->host_key->hash > 0 ? nvme_auth_hmac_name(ctrl->host_key->hash) : "none", (int)ctrl->host_key->len, ctrl->host_key->key); - +#endif nvme_auth_free_key(ctrl->ctrl_key); if (!host->dhchap_ctrl_secret) { ctrl->ctrl_key = NULL; @@ -207,11 +207,12 @@ u8 nvmet_setup_auth(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq, bool reset) ctrl->ctrl_key = NULL; goto out_free_hash; } +#ifdef CONFIG_NVME_TARGET_AUTH_DEBUG pr_debug("%s: using ctrl hash %s key %*ph\n", __func__, ctrl->ctrl_key->hash > 0 ? nvme_auth_hmac_name(ctrl->ctrl_key->hash) : "none", (int)ctrl->ctrl_key->len, ctrl->ctrl_key->key); - +#endif out_free_hash: if (ret) { if (ctrl->host_key) { @@ -317,7 +318,6 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response, if (ret) goto out_free_challenge; } - pr_debug("ctrl %d qid %d host response seq %u transaction %d\n", ctrl->cntlid, req->sq->qid, req->sq->dhchap_s1, req->sq->dhchap_tid); @@ -434,8 +434,10 @@ int nvmet_auth_ctrl_exponential(struct nvmet_req *req, ret = -EINVAL; } else { memcpy(buf, ctrl->dh_key, buf_size); +#ifdef CONFIG_NVME_TARGET_AUTH_DEBUG pr_debug("%s: ctrl %d public key %*ph\n", __func__, ctrl->cntlid, (int)buf_size, buf); +#endif } return ret; @@ -458,11 +460,12 @@ int nvmet_auth_ctrl_sesskey(struct nvmet_req *req, ctrl->shash_id); if (ret) pr_debug("failed to compute session key, err %d\n", ret); +#ifdef CONFIG_NVME_TARGET_AUTH_DEBUG else pr_debug("%s: session key %*ph\n", __func__, (int)req->sq->dhchap_skey_len, req->sq->dhchap_skey); - +#endif return ret; } diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 164a564ba3b4..20f150d17a96 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -1321,8 +1321,10 @@ static int nvmet_tcp_try_recv_ddgst(struct nvmet_tcp_queue *queue) queue->idx, cmd->req.cmd->common.command_id, queue->pdu.cmd.hdr.type, le32_to_cpu(cmd->recv_ddgst), le32_to_cpu(cmd->exp_ddgst)); - if (!(cmd->flags & NVMET_TCP_F_INIT_FAILED)) + if (!(cmd->flags & NVMET_TCP_F_INIT_FAILED)) { + cmd->req.cqe->status = NVME_SC_CMD_SEQ_ERROR; nvmet_req_uninit(&cmd->req); + } nvmet_tcp_free_cmd_buffers(cmd); ret = -EPROTO; goto out; diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index b4677c5bba5b..8005c088e9ee 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -546,6 +546,15 @@ static const struct dmi_system_id asus_quirks[] = { }, { .callback = dmi_matched, + .ident = "ASUS Zenbook Duo UX8407AA", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUS"), + DMI_MATCH(DMI_PRODUCT_NAME, "Zenbook Duo UX8407AA"), + }, + .driver_data = &quirk_asus_zenbook_duo_kbd, + }, + { + .callback = dmi_matched, .ident = "ASUS ROG Z13", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUS"), diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c index 24c151289dd3..6950bec2a9d8 100644 --- a/drivers/platform/x86/hp/hp-wmi.c +++ b/drivers/platform/x86/hp/hp-wmi.c @@ -206,6 +206,10 @@ static const struct dmi_system_id victus_s_thermal_profile_boards[] __initconst .driver_data = (void *)&victus_s_thermal_params, }, { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "8BC2") }, + .driver_data = (void *)&omen_v1_thermal_params, + }, + { .matches = { DMI_MATCH(DMI_BOARD_NAME, "8BCA") }, .driver_data = (void *)&omen_v1_thermal_params, }, diff --git a/drivers/platform/x86/intel/plr_tpmi.c b/drivers/platform/x86/intel/plr_tpmi.c index 05727169f49c..8faecc311038 100644 --- a/drivers/platform/x86/intel/plr_tpmi.c +++ b/drivers/platform/x86/intel/plr_tpmi.c @@ -22,6 +22,7 @@ #include <linux/module.h> #include <linux/mod_devicetable.h> #include <linux/mutex.h> +#include <linux/notifier.h> #include <linux/seq_file.h> #include <linux/sprintf.h> #include <linux/types.h> @@ -60,6 +61,8 @@ struct tpmi_plr { struct tpmi_plr_die *die_info; int num_dies; struct auxiliary_device *auxdev; + struct notifier_block nb; + struct mutex lock; /* Protect access to dbgfs_dir */ }; static const char * const plr_coarse_reasons[] = { @@ -255,6 +258,30 @@ static ssize_t plr_status_write(struct file *filp, const char __user *ubuf, } DEFINE_SHOW_STORE_ATTRIBUTE(plr_status); +static int intel_plr_notify(struct notifier_block *self, unsigned long action, void *data) +{ + struct tpmi_plr *plr = container_of(self, struct tpmi_plr, nb); + + if (action == TPMI_CORE_EXIT) { + guard(mutex)(&plr->lock); + plr->dbgfs_dir = NULL; + } + + return NOTIFY_DONE; +} + +static int intel_plr_register_notifier(struct notifier_block *nb) +{ + nb->notifier_call = intel_plr_notify; + nb->priority = 0; + return tpmi_register_notifier(nb); +} + +static void intel_plr_unregister_notifier(struct notifier_block *nb) +{ + tpmi_unregister_notifier(nb); +} + static int intel_plr_probe(struct auxiliary_device *auxdev, const struct auxiliary_device_id *id) { struct oobmsm_plat_info *plat_info; @@ -282,10 +309,18 @@ static int intel_plr_probe(struct auxiliary_device *auxdev, const struct auxilia if (!plr) return -ENOMEM; + err = devm_mutex_init(&auxdev->dev, &plr->lock); + if (err) + return err; + + intel_plr_register_notifier(&plr->nb); + plr->die_info = devm_kcalloc(&auxdev->dev, num_resources, sizeof(*plr->die_info), GFP_KERNEL); - if (!plr->die_info) - return -ENOMEM; + if (!plr->die_info) { + err = -ENOMEM; + goto err_notify; + } plr->num_dies = num_resources; plr->dbgfs_dir = debugfs_create_dir("plr", dentry); @@ -326,6 +361,9 @@ static int intel_plr_probe(struct auxiliary_device *auxdev, const struct auxilia err: debugfs_remove_recursive(plr->dbgfs_dir); +err_notify: + intel_plr_unregister_notifier(&plr->nb); + return err; } @@ -333,6 +371,9 @@ static void intel_plr_remove(struct auxiliary_device *auxdev) { struct tpmi_plr *plr = auxiliary_get_drvdata(auxdev); + intel_plr_unregister_notifier(&plr->nb); + + guard(mutex)(&plr->lock); debugfs_remove_recursive(plr->dbgfs_dir); } diff --git a/drivers/platform/x86/intel/vsec_tpmi.c b/drivers/platform/x86/intel/vsec_tpmi.c index 7fc6ff8d1040..16fd7aa41f20 100644 --- a/drivers/platform/x86/intel/vsec_tpmi.c +++ b/drivers/platform/x86/intel/vsec_tpmi.c @@ -56,6 +56,7 @@ #include <linux/io.h> #include <linux/iopoll.h> #include <linux/module.h> +#include <linux/notifier.h> #include <linux/pci.h> #include <linux/security.h> #include <linux/sizes.h> @@ -188,6 +189,20 @@ struct tpmi_feature_state { /* Used during auxbus device creation */ static DEFINE_IDA(intel_vsec_tpmi_ida); +static BLOCKING_NOTIFIER_HEAD(tpmi_notify_list); + +int tpmi_register_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&tpmi_notify_list, nb); +} +EXPORT_SYMBOL_NS_GPL(tpmi_register_notifier, "INTEL_TPMI"); + +int tpmi_unregister_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&tpmi_notify_list, nb); +} +EXPORT_SYMBOL_NS_GPL(tpmi_unregister_notifier, "INTEL_TPMI"); + struct oobmsm_plat_info *tpmi_get_platform_data(struct auxiliary_device *auxdev) { struct intel_vsec_device *vsec_dev = auxdev_to_ivdev(auxdev); @@ -817,10 +832,6 @@ static int intel_vsec_tpmi_init(struct auxiliary_device *auxdev) auxiliary_set_drvdata(auxdev, tpmi_info); - ret = tpmi_create_devices(tpmi_info); - if (ret) - return ret; - /* * Allow debugfs when security policy allows. Everything this debugfs * interface provides, can also be done via /dev/mem access. If @@ -830,6 +841,14 @@ static int intel_vsec_tpmi_init(struct auxiliary_device *auxdev) if (!security_locked_down(LOCKDOWN_DEV_MEM) && capable(CAP_SYS_RAWIO)) tpmi_dbgfs_register(tpmi_info); + ret = tpmi_create_devices(tpmi_info); + if (ret) { + debugfs_remove_recursive(tpmi_info->dbgfs_dir); + return ret; + } + + blocking_notifier_call_chain(&tpmi_notify_list, TPMI_CORE_INIT, auxdev); + return 0; } @@ -843,6 +862,8 @@ static void tpmi_remove(struct auxiliary_device *auxdev) { struct intel_tpmi_info *tpmi_info = auxiliary_get_drvdata(auxdev); + blocking_notifier_call_chain(&tpmi_notify_list, TPMI_CORE_EXIT, auxdev); + debugfs_remove_recursive(tpmi_info->dbgfs_dir); } diff --git a/drivers/platform/x86/lenovo/Kconfig b/drivers/platform/x86/lenovo/Kconfig index f885127b007f..09b1b055d2e0 100644 --- a/drivers/platform/x86/lenovo/Kconfig +++ b/drivers/platform/x86/lenovo/Kconfig @@ -252,7 +252,6 @@ config LENOVO_WMI_GAMEZONE select ACPI_PLATFORM_PROFILE select LENOVO_WMI_EVENTS select LENOVO_WMI_HELPERS - select LENOVO_WMI_TUNING help Say Y here if you have a WMI aware Lenovo Legion device and would like to use the platform-profile firmware interface to manage power usage. diff --git a/drivers/platform/x86/lenovo/wmi-capdata.c b/drivers/platform/x86/lenovo/wmi-capdata.c index b73d378f0e8b..714aa6fd6f1f 100644 --- a/drivers/platform/x86/lenovo/wmi-capdata.c +++ b/drivers/platform/x86/lenovo/wmi-capdata.c @@ -27,7 +27,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/acpi.h> -#include <linux/bitfield.h> #include <linux/bug.h> #include <linux/cleanup.h> #include <linux/component.h> @@ -48,6 +47,7 @@ #include <linux/wmi.h> #include "wmi-capdata.h" +#include "wmi-helpers.h" #define LENOVO_CAPABILITY_DATA_00_GUID "362A3AFE-3D96-4665-8530-96DAD5BB300E" #define LENOVO_CAPABILITY_DATA_01_GUID "7A8F5407-CB67-4D6E-B547-39B3BE018154" @@ -57,9 +57,9 @@ #define LWMI_FEATURE_ID_FAN_TEST 0x05 -#define LWMI_ATTR_ID_FAN_TEST \ - (FIELD_PREP(LWMI_ATTR_DEV_ID_MASK, LWMI_DEVICE_ID_FAN) | \ - FIELD_PREP(LWMI_ATTR_FEAT_ID_MASK, LWMI_FEATURE_ID_FAN_TEST)) +#define LWMI_ATTR_ID_FAN_TEST \ + lwmi_attr_id(LWMI_DEVICE_ID_FAN, LWMI_FEATURE_ID_FAN_TEST, \ + LWMI_GZ_THERMAL_MODE_NONE, LWMI_TYPE_ID_NONE) enum lwmi_cd_type { LENOVO_CAPABILITY_DATA_00, diff --git a/drivers/platform/x86/lenovo/wmi-capdata.h b/drivers/platform/x86/lenovo/wmi-capdata.h index 8c1df3efcc55..c3e760b8c3c3 100644 --- a/drivers/platform/x86/lenovo/wmi-capdata.h +++ b/drivers/platform/x86/lenovo/wmi-capdata.h @@ -6,6 +6,7 @@ #define _LENOVO_WMI_CAPDATA_H_ #include <linux/bits.h> +#include <linux/bitfield.h> #include <linux/types.h> #define LWMI_SUPP_VALID BIT(0) @@ -19,6 +20,8 @@ #define LWMI_DEVICE_ID_FAN 0x04 +#define LWMI_TYPE_ID_NONE 0x00 + struct component_match; struct device; struct cd_list; @@ -57,6 +60,23 @@ struct lwmi_cd_binder { cd_list_cb_t cd_fan_list_cb; }; +/** + * lwmi_attr_id() - Formats a capability data attribute ID + * @dev_id: The u8 corresponding to the device ID. + * @feat_id: The u8 corresponding to the feature ID on the device. + * @mode_id: The u8 corresponding to the wmi-gamezone mode for set/get. + * @type_id: The u8 corresponding to the sub-device. + * + * Return: encoded capability data attribute ID. + */ +static inline u32 lwmi_attr_id(u8 dev_id, u8 feat_id, u8 mode_id, u8 type_id) +{ + return (FIELD_PREP(LWMI_ATTR_DEV_ID_MASK, dev_id) | + FIELD_PREP(LWMI_ATTR_FEAT_ID_MASK, feat_id) | + FIELD_PREP(LWMI_ATTR_MODE_ID_MASK, mode_id) | + FIELD_PREP(LWMI_ATTR_TYPE_ID_MASK, type_id)); +} + void lwmi_cd_match_add_all(struct device *master, struct component_match **matchptr); int lwmi_cd00_get_data(struct cd_list *list, u32 attribute_id, struct capdata00 *output); int lwmi_cd01_get_data(struct cd_list *list, u32 attribute_id, struct capdata01 *output); diff --git a/drivers/platform/x86/lenovo/wmi-events.c b/drivers/platform/x86/lenovo/wmi-events.c index 4a6a2c82413a..fc25bba68a7c 100644 --- a/drivers/platform/x86/lenovo/wmi-events.c +++ b/drivers/platform/x86/lenovo/wmi-events.c @@ -17,7 +17,7 @@ #include <linux/wmi.h> #include "wmi-events.h" -#include "wmi-gamezone.h" +#include "wmi-helpers.h" #define THERMAL_MODE_EVENT_GUID "D320289E-8FEA-41E0-86F9-911D83151B5F" diff --git a/drivers/platform/x86/lenovo/wmi-gamezone.c b/drivers/platform/x86/lenovo/wmi-gamezone.c index c7fe7e3c9f17..109c0b564a9f 100644 --- a/drivers/platform/x86/lenovo/wmi-gamezone.c +++ b/drivers/platform/x86/lenovo/wmi-gamezone.c @@ -21,9 +21,7 @@ #include <linux/wmi.h> #include "wmi-events.h" -#include "wmi-gamezone.h" #include "wmi-helpers.h" -#include "wmi-other.h" #define LENOVO_GAMEZONE_GUID "887B54E3-DDDC-4B2C-8B88-68A26A8835D0" @@ -201,7 +199,7 @@ static int lwmi_gz_profile_set(struct device *dev, enum platform_profile_option profile) { struct lwmi_gz_priv *priv = dev_get_drvdata(dev); - struct wmi_method_args_32 args; + struct wmi_method_args_32 args = {}; enum thermal_mode mode; int ret; @@ -383,7 +381,7 @@ static int lwmi_gz_probe(struct wmi_device *wdev, const void *context) return ret; priv->mode_nb.notifier_call = lwmi_gz_mode_call; - return devm_lwmi_om_register_notifier(&wdev->dev, &priv->mode_nb); + return devm_lwmi_tm_register_notifier(&wdev->dev, &priv->mode_nb); } static const struct wmi_device_id lwmi_gz_id_table[] = { @@ -405,7 +403,6 @@ module_wmi_driver(lwmi_gz_driver); MODULE_IMPORT_NS("LENOVO_WMI_EVENTS"); MODULE_IMPORT_NS("LENOVO_WMI_HELPERS"); -MODULE_IMPORT_NS("LENOVO_WMI_OTHER"); MODULE_DEVICE_TABLE(wmi, lwmi_gz_id_table); MODULE_AUTHOR("Derek J. Clark <derekjohn.clark@gmail.com>"); MODULE_DESCRIPTION("Lenovo GameZone WMI Driver"); diff --git a/drivers/platform/x86/lenovo/wmi-gamezone.h b/drivers/platform/x86/lenovo/wmi-gamezone.h deleted file mode 100644 index 6b163a5eeb95..000000000000 --- a/drivers/platform/x86/lenovo/wmi-gamezone.h +++ /dev/null @@ -1,20 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ - -/* Copyright (C) 2025 Derek J. Clark <derekjohn.clark@gmail.com> */ - -#ifndef _LENOVO_WMI_GAMEZONE_H_ -#define _LENOVO_WMI_GAMEZONE_H_ - -enum gamezone_events_type { - LWMI_GZ_GET_THERMAL_MODE = 1, -}; - -enum thermal_mode { - LWMI_GZ_THERMAL_MODE_QUIET = 0x01, - LWMI_GZ_THERMAL_MODE_BALANCED = 0x02, - LWMI_GZ_THERMAL_MODE_PERFORMANCE = 0x03, - LWMI_GZ_THERMAL_MODE_EXTREME = 0xE0, /* Ver 6+ */ - LWMI_GZ_THERMAL_MODE_CUSTOM = 0xFF, -}; - -#endif /* !_LENOVO_WMI_GAMEZONE_H_ */ diff --git a/drivers/platform/x86/lenovo/wmi-helpers.c b/drivers/platform/x86/lenovo/wmi-helpers.c index 7379defac500..7a198259e393 100644 --- a/drivers/platform/x86/lenovo/wmi-helpers.c +++ b/drivers/platform/x86/lenovo/wmi-helpers.c @@ -21,11 +21,15 @@ #include <linux/errno.h> #include <linux/export.h> #include <linux/module.h> +#include <linux/notifier.h> #include <linux/unaligned.h> #include <linux/wmi.h> #include "wmi-helpers.h" +/* Thermal mode notifier chain. */ +static BLOCKING_NOTIFIER_HEAD(tm_chain_head); + /** * lwmi_dev_evaluate_int() - Helper function for calling WMI methods that * return an integer. @@ -46,7 +50,6 @@ int lwmi_dev_evaluate_int(struct wmi_device *wdev, u8 instance, u32 method_id, unsigned char *buf, size_t size, u32 *retval) { struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL }; - union acpi_object *ret_obj __free(kfree) = NULL; struct acpi_buffer input = { size, buf }; acpi_status status; @@ -55,8 +58,9 @@ int lwmi_dev_evaluate_int(struct wmi_device *wdev, u8 instance, u32 method_id, if (ACPI_FAILURE(status)) return -EIO; + union acpi_object *ret_obj __free(kfree) = output.pointer; + if (retval) { - ret_obj = output.pointer; if (!ret_obj) return -ENODATA; @@ -84,6 +88,103 @@ int lwmi_dev_evaluate_int(struct wmi_device *wdev, u8 instance, u32 method_id, }; EXPORT_SYMBOL_NS_GPL(lwmi_dev_evaluate_int, "LENOVO_WMI_HELPERS"); +/** + * lwmi_tm_register_notifier() - Add a notifier to the blocking notifier chain + * @nb: The notifier_block struct to register + * + * Call blocking_notifier_chain_register to register the notifier block to the + * thermal mode notifier chain. + * + * Return: 0 on success, %-EEXIST on error. + */ +int lwmi_tm_register_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&tm_chain_head, nb); +} +EXPORT_SYMBOL_NS_GPL(lwmi_tm_register_notifier, "LENOVO_WMI_HELPERS"); + +/** + * lwmi_tm_unregister_notifier() - Remove a notifier from the blocking notifier + * chain. + * @nb: The notifier_block struct to register + * + * Call blocking_notifier_chain_unregister to unregister the notifier block from the + * thermal mode notifier chain. + * + * Return: 0 on success, %-ENOENT on error. + */ +int lwmi_tm_unregister_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&tm_chain_head, nb); +} +EXPORT_SYMBOL_NS_GPL(lwmi_tm_unregister_notifier, "LENOVO_WMI_HELPERS"); + +/** + * devm_lwmi_tm_unregister_notifier() - Remove a notifier from the blocking + * notifier chain. + * @data: Void pointer to the notifier_block struct to register. + * + * Call lwmi_tm_unregister_notifier to unregister the notifier block from the + * thermal mode notifier chain. + * + * Return: 0 on success, %-ENOENT on error. + */ +static void devm_lwmi_tm_unregister_notifier(void *data) +{ + struct notifier_block *nb = data; + + lwmi_tm_unregister_notifier(nb); +} + +/** + * devm_lwmi_tm_register_notifier() - Add a notifier to the blocking notifier + * chain. + * @dev: The parent device of the notifier_block struct. + * @nb: The notifier_block struct to register + * + * Call lwmi_tm_register_notifier to register the notifier block to the + * thermal mode notifier chain. Then add devm_lwmi_tm_unregister_notifier + * as a device managed action to automatically unregister the notifier block + * upon parent device removal. + * + * Return: 0 on success, or an error code. + */ +int devm_lwmi_tm_register_notifier(struct device *dev, + struct notifier_block *nb) +{ + int ret; + + ret = lwmi_tm_register_notifier(nb); + if (ret < 0) + return ret; + + return devm_add_action_or_reset(dev, devm_lwmi_tm_unregister_notifier, + nb); +} +EXPORT_SYMBOL_NS_GPL(devm_lwmi_tm_register_notifier, "LENOVO_WMI_HELPERS"); + +/** + * lwmi_tm_notifier_call() - Call functions for the notifier call chain. + * @mode: Pointer to a thermal mode enum to retrieve the data from. + * + * Call blocking_notifier_call_chain to retrieve the thermal mode from the + * lenovo-wmi-gamezone driver. + * + * Return: 0 on success, or an error code. + */ +int lwmi_tm_notifier_call(enum thermal_mode *mode) +{ + int ret; + + ret = blocking_notifier_call_chain(&tm_chain_head, + LWMI_GZ_GET_THERMAL_MODE, &mode); + if ((ret & ~NOTIFY_STOP_MASK) != NOTIFY_OK) + return -EINVAL; + + return 0; +} +EXPORT_SYMBOL_NS_GPL(lwmi_tm_notifier_call, "LENOVO_WMI_HELPERS"); + MODULE_AUTHOR("Derek J. Clark <derekjohn.clark@gmail.com>"); MODULE_DESCRIPTION("Lenovo WMI Helpers Driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/lenovo/wmi-helpers.h b/drivers/platform/x86/lenovo/wmi-helpers.h index 20fd21749803..ed7db3ebba6c 100644 --- a/drivers/platform/x86/lenovo/wmi-helpers.h +++ b/drivers/platform/x86/lenovo/wmi-helpers.h @@ -7,6 +7,8 @@ #include <linux/types.h> +struct device; +struct notifier_block; struct wmi_device; struct wmi_method_args_32 { @@ -14,7 +16,26 @@ struct wmi_method_args_32 { u32 arg1; }; +enum lwmi_event_type { + LWMI_GZ_GET_THERMAL_MODE = 0x01, +}; + +enum thermal_mode { + LWMI_GZ_THERMAL_MODE_NONE = 0x00, + LWMI_GZ_THERMAL_MODE_QUIET = 0x01, + LWMI_GZ_THERMAL_MODE_BALANCED = 0x02, + LWMI_GZ_THERMAL_MODE_PERFORMANCE = 0x03, + LWMI_GZ_THERMAL_MODE_EXTREME = 0xE0, /* Ver 6+ */ + LWMI_GZ_THERMAL_MODE_CUSTOM = 0xFF, +}; + int lwmi_dev_evaluate_int(struct wmi_device *wdev, u8 instance, u32 method_id, unsigned char *buf, size_t size, u32 *retval); +int lwmi_tm_register_notifier(struct notifier_block *nb); +int lwmi_tm_unregister_notifier(struct notifier_block *nb); +int devm_lwmi_tm_register_notifier(struct device *dev, + struct notifier_block *nb); +int lwmi_tm_notifier_call(enum thermal_mode *mode); + #endif /* !_LENOVO_WMI_HELPERS_H_ */ diff --git a/drivers/platform/x86/lenovo/wmi-other.c b/drivers/platform/x86/lenovo/wmi-other.c index 6c2febe1a595..d318ba432fdc 100644 --- a/drivers/platform/x86/lenovo/wmi-other.c +++ b/drivers/platform/x86/lenovo/wmi-other.c @@ -40,16 +40,13 @@ #include <linux/kobject.h> #include <linux/limits.h> #include <linux/module.h> -#include <linux/notifier.h> #include <linux/platform_profile.h> #include <linux/types.h> #include <linux/wmi.h> #include "wmi-capdata.h" #include "wmi-events.h" -#include "wmi-gamezone.h" #include "wmi-helpers.h" -#include "wmi-other.h" #include "../firmware_attributes_class.h" #define LENOVO_OTHER_MODE_GUID "DC2A8805-3A8C-41BA-A6F7-092E0089CD3B" @@ -62,8 +59,6 @@ #define LWMI_FEATURE_ID_FAN_RPM 0x03 -#define LWMI_TYPE_ID_NONE 0x00 - #define LWMI_FEATURE_VALUE_GET 17 #define LWMI_FEATURE_VALUE_SET 18 @@ -71,17 +66,15 @@ #define LWMI_FAN_NR 4 #define LWMI_FAN_ID(x) ((x) + LWMI_FAN_ID_BASE) -#define LWMI_ATTR_ID_FAN_RPM(x) \ - (FIELD_PREP(LWMI_ATTR_DEV_ID_MASK, LWMI_DEVICE_ID_FAN) | \ - FIELD_PREP(LWMI_ATTR_FEAT_ID_MASK, LWMI_FEATURE_ID_FAN_RPM) | \ - FIELD_PREP(LWMI_ATTR_TYPE_ID_MASK, LWMI_FAN_ID(x))) - #define LWMI_FAN_DIV 100 +#define LWMI_ATTR_ID_FAN_RPM(x) \ + lwmi_attr_id(LWMI_DEVICE_ID_FAN, LWMI_FEATURE_ID_FAN_RPM, \ + LWMI_GZ_THERMAL_MODE_NONE, LWMI_FAN_ID(x)) + #define LWMI_OM_FW_ATTR_BASE_PATH "lenovo-wmi-other" #define LWMI_OM_HWMON_NAME "lenovo_wmi_other" -static BLOCKING_NOTIFIER_HEAD(om_chain_head); static DEFINE_IDA(lwmi_om_ida); enum attribute_property { @@ -109,7 +102,6 @@ struct lwmi_om_priv { struct device *hwmon_dev; struct device *fw_attr_dev; struct kset *fw_attr_kset; - struct notifier_block nb; struct wmi_device *wdev; int ida_id; @@ -166,7 +158,7 @@ MODULE_PARM_DESC(relax_fan_constraint, */ static int lwmi_om_fan_get_set(struct lwmi_om_priv *priv, int channel, u32 *val, bool set) { - struct wmi_method_args_32 args; + struct wmi_method_args_32 args = {}; u32 method_id, retval; int err; @@ -548,13 +540,26 @@ out: /* ======== fw_attributes (component: lenovo-wmi-capdata 01) ======== */ struct tunable_attr_01 { - struct capdata01 *capdata; struct device *dev; - u32 feature_id; - u32 device_id; - u32 type_id; + u8 feature_id; + u8 device_id; + u8 type_id; + u8 cd_mode_id; /* mode arg for searching capdata */ + u8 cv_mode_id; /* mode arg for set/get current_value */ }; +/** + * tunable_attr_01_id() - Formats a tunable_attr_01 to a capdata attribute ID + * @attr: The tunable_attr_01 to format. + * @mode: The u8 corresponding to the wmi-gamezone mode for set/get. + * + * Return: encoded capability data attribute ID. + */ +static u32 tunable_attr_01_id(struct tunable_attr_01 *attr, u8 mode) +{ + return lwmi_attr_id(attr->device_id, attr->feature_id, mode, attr->type_id); +} + static struct tunable_attr_01 ppt_pl1_spl = { .device_id = LWMI_DEVICE_ID_CPU, .feature_id = LWMI_FEATURE_ID_CPU_SPL, @@ -578,102 +583,6 @@ struct capdata01_attr_group { struct tunable_attr_01 *tunable_attr; }; -/** - * lwmi_om_register_notifier() - Add a notifier to the blocking notifier chain - * @nb: The notifier_block struct to register - * - * Call blocking_notifier_chain_register to register the notifier block to the - * lenovo-wmi-other driver notifier chain. - * - * Return: 0 on success, %-EEXIST on error. - */ -int lwmi_om_register_notifier(struct notifier_block *nb) -{ - return blocking_notifier_chain_register(&om_chain_head, nb); -} -EXPORT_SYMBOL_NS_GPL(lwmi_om_register_notifier, "LENOVO_WMI_OTHER"); - -/** - * lwmi_om_unregister_notifier() - Remove a notifier from the blocking notifier - * chain. - * @nb: The notifier_block struct to register - * - * Call blocking_notifier_chain_unregister to unregister the notifier block from the - * lenovo-wmi-other driver notifier chain. - * - * Return: 0 on success, %-ENOENT on error. - */ -int lwmi_om_unregister_notifier(struct notifier_block *nb) -{ - return blocking_notifier_chain_unregister(&om_chain_head, nb); -} -EXPORT_SYMBOL_NS_GPL(lwmi_om_unregister_notifier, "LENOVO_WMI_OTHER"); - -/** - * devm_lwmi_om_unregister_notifier() - Remove a notifier from the blocking - * notifier chain. - * @data: Void pointer to the notifier_block struct to register. - * - * Call lwmi_om_unregister_notifier to unregister the notifier block from the - * lenovo-wmi-other driver notifier chain. - * - * Return: 0 on success, %-ENOENT on error. - */ -static void devm_lwmi_om_unregister_notifier(void *data) -{ - struct notifier_block *nb = data; - - lwmi_om_unregister_notifier(nb); -} - -/** - * devm_lwmi_om_register_notifier() - Add a notifier to the blocking notifier - * chain. - * @dev: The parent device of the notifier_block struct. - * @nb: The notifier_block struct to register - * - * Call lwmi_om_register_notifier to register the notifier block to the - * lenovo-wmi-other driver notifier chain. Then add devm_lwmi_om_unregister_notifier - * as a device managed action to automatically unregister the notifier block - * upon parent device removal. - * - * Return: 0 on success, or an error code. - */ -int devm_lwmi_om_register_notifier(struct device *dev, - struct notifier_block *nb) -{ - int ret; - - ret = lwmi_om_register_notifier(nb); - if (ret < 0) - return ret; - - return devm_add_action_or_reset(dev, devm_lwmi_om_unregister_notifier, - nb); -} -EXPORT_SYMBOL_NS_GPL(devm_lwmi_om_register_notifier, "LENOVO_WMI_OTHER"); - -/** - * lwmi_om_notifier_call() - Call functions for the notifier call chain. - * @mode: Pointer to a thermal mode enum to retrieve the data from. - * - * Call blocking_notifier_call_chain to retrieve the thermal mode from the - * lenovo-wmi-gamezone driver. - * - * Return: 0 on success, or an error code. - */ -static int lwmi_om_notifier_call(enum thermal_mode *mode) -{ - int ret; - - ret = blocking_notifier_call_chain(&om_chain_head, - LWMI_GZ_GET_THERMAL_MODE, &mode); - if ((ret & ~NOTIFY_STOP_MASK) != NOTIFY_OK) - return -EINVAL; - - return 0; -} - /* Attribute Methods */ /** @@ -718,12 +627,7 @@ static ssize_t attr_capdata01_show(struct kobject *kobj, u32 attribute_id; int value, ret; - attribute_id = - FIELD_PREP(LWMI_ATTR_DEV_ID_MASK, tunable_attr->device_id) | - FIELD_PREP(LWMI_ATTR_FEAT_ID_MASK, tunable_attr->feature_id) | - FIELD_PREP(LWMI_ATTR_MODE_ID_MASK, - LWMI_GZ_THERMAL_MODE_CUSTOM) | - FIELD_PREP(LWMI_ATTR_TYPE_ID_MASK, tunable_attr->type_id); + attribute_id = tunable_attr_01_id(tunable_attr, tunable_attr->cd_mode_id); ret = lwmi_cd01_get_data(priv->cd01_list, attribute_id, &capdata); if (ret) @@ -775,27 +679,22 @@ static ssize_t attr_current_value_store(struct kobject *kobj, struct tunable_attr_01 *tunable_attr) { struct lwmi_om_priv *priv = dev_get_drvdata(tunable_attr->dev); - struct wmi_method_args_32 args; + struct wmi_method_args_32 args = {}; struct capdata01 capdata; enum thermal_mode mode; - u32 attribute_id; u32 value; int ret; - ret = lwmi_om_notifier_call(&mode); + ret = lwmi_tm_notifier_call(&mode); if (ret) return ret; if (mode != LWMI_GZ_THERMAL_MODE_CUSTOM) return -EBUSY; - attribute_id = - FIELD_PREP(LWMI_ATTR_DEV_ID_MASK, tunable_attr->device_id) | - FIELD_PREP(LWMI_ATTR_FEAT_ID_MASK, tunable_attr->feature_id) | - FIELD_PREP(LWMI_ATTR_MODE_ID_MASK, mode) | - FIELD_PREP(LWMI_ATTR_TYPE_ID_MASK, tunable_attr->type_id); + args.arg0 = tunable_attr_01_id(tunable_attr, tunable_attr->cd_mode_id); - ret = lwmi_cd01_get_data(priv->cd01_list, attribute_id, &capdata); + ret = lwmi_cd01_get_data(priv->cd01_list, args.arg0, &capdata); if (ret) return ret; @@ -806,7 +705,7 @@ static ssize_t attr_current_value_store(struct kobject *kobj, if (value < capdata.min_value || value > capdata.max_value) return -EINVAL; - args.arg0 = attribute_id; + args.arg0 = tunable_attr_01_id(tunable_attr, tunable_attr->cv_mode_id); args.arg1 = value; ret = lwmi_dev_evaluate_int(priv->wdev, 0x0, LWMI_FEATURE_VALUE_SET, @@ -838,23 +737,20 @@ static ssize_t attr_current_value_show(struct kobject *kobj, struct tunable_attr_01 *tunable_attr) { struct lwmi_om_priv *priv = dev_get_drvdata(tunable_attr->dev); - struct wmi_method_args_32 args; + struct wmi_method_args_32 args = {}; enum thermal_mode mode; - u32 attribute_id; int retval; int ret; - ret = lwmi_om_notifier_call(&mode); + ret = lwmi_tm_notifier_call(&mode); if (ret) return ret; - attribute_id = - FIELD_PREP(LWMI_ATTR_DEV_ID_MASK, tunable_attr->device_id) | - FIELD_PREP(LWMI_ATTR_FEAT_ID_MASK, tunable_attr->feature_id) | - FIELD_PREP(LWMI_ATTR_MODE_ID_MASK, mode) | - FIELD_PREP(LWMI_ATTR_TYPE_ID_MASK, tunable_attr->type_id); + /* If "no-mode" is the supported mode, ensure we never send current mode */ + if (tunable_attr->cv_mode_id == LWMI_GZ_THERMAL_MODE_NONE) + mode = tunable_attr->cv_mode_id; - args.arg0 = attribute_id; + args.arg0 = tunable_attr_01_id(tunable_attr, mode); ret = lwmi_dev_evaluate_int(priv->wdev, 0x0, LWMI_FEATURE_VALUE_GET, (unsigned char *)&args, sizeof(args), @@ -865,6 +761,81 @@ static ssize_t attr_current_value_show(struct kobject *kobj, return sysfs_emit(buf, "%d\n", retval); } +/** + * lwmi_attr_01_is_supported() - Determine if the given attribute is supported. + * @tunable_attr: The attribute to verify. + * + * For an attribute to be supported it must have a functional get/set method, + * as well as associated capability data stored in the capdata01 table. + * + * First check if the attribute has a corresponding data table under custom mode + * (0xff), then under no mode (0x00). If either of those passes, check if the + * supported field of the capdata struct is > 0. If it is supported, store the + * successful mode in the cd_mode_id field of tunable_attr. + * + * If the attribute capdata shows it is supported, attempt to determine the mode + * for the current value property get/set methods using a similar pattern to the + * capdata table check. If the value returned by either mode is 0 or an error, + * assume that mode is not supported. Otherwise, store the successful mode in the + * cv_mode_id field of tunable_attr. + * + * If any of the above checks fail then the attribute is not fully supported. + * + * Return: true if capdata and set/get modes are found, otherwise false. + */ +static bool lwmi_attr_01_is_supported(struct tunable_attr_01 *tunable_attr) +{ + u8 modes[2] = { LWMI_GZ_THERMAL_MODE_CUSTOM, LWMI_GZ_THERMAL_MODE_NONE }; + struct lwmi_om_priv *priv = dev_get_drvdata(tunable_attr->dev); + struct wmi_method_args_32 args = {}; + bool cd_mode_found = false; + bool cv_mode_found = false; + struct capdata01 capdata; + int retval, ret, i; + + /* Determine tunable_attr->cd_mode_id */ + for (i = 0; i < ARRAY_SIZE(modes); i++) { + args.arg0 = tunable_attr_01_id(tunable_attr, modes[i]); + + ret = lwmi_cd01_get_data(priv->cd01_list, args.arg0, &capdata); + if (ret || !capdata.supported) + continue; + + tunable_attr->cd_mode_id = modes[i]; + cd_mode_found = true; + break; + } + + if (!cd_mode_found) + return cd_mode_found; + + dev_dbg(tunable_attr->dev, + "cd_mode_id: %#010x\n", args.arg0); + + /* Determine tunable_attr->cv_mode_id, returns 1 if supported */ + for (i = 0; i < ARRAY_SIZE(modes); i++) { + args.arg0 = tunable_attr_01_id(tunable_attr, modes[i]); + + ret = lwmi_dev_evaluate_int(priv->wdev, 0x0, LWMI_FEATURE_VALUE_GET, + (u8 *)&args, sizeof(args), + &retval); + if (ret || !retval) + continue; + + tunable_attr->cv_mode_id = modes[i]; + cv_mode_found = true; + break; + } + + if (!cv_mode_found) + return cv_mode_found; + + dev_dbg(tunable_attr->dev, "cv_mode_id: %#010x, attribute support level: %#010x\n", + args.arg0, capdata.supported); + + return capdata.supported > 0; +} + /* Lenovo WMI Other Mode Attribute macros */ #define __LWMI_ATTR_RO(_func, _name) \ { \ @@ -959,17 +930,17 @@ static struct capdata01_attr_group cd01_attr_groups[] = { /** * lwmi_om_fw_attr_add() - Register all firmware_attributes_class members * @priv: The Other Mode driver data. - * - * Return: Either 0, or an error code. */ -static int lwmi_om_fw_attr_add(struct lwmi_om_priv *priv) +static void lwmi_om_fw_attr_add(struct lwmi_om_priv *priv) { unsigned int i; int err; - priv->ida_id = ida_alloc(&lwmi_om_ida, GFP_KERNEL); - if (priv->ida_id < 0) - return priv->ida_id; + err = ida_alloc(&lwmi_om_ida, GFP_KERNEL); + if (err < 0) + goto err_no_ida; + + priv->ida_id = err; priv->fw_attr_dev = device_create(&firmware_attributes_class, NULL, MKDEV(0, 0), NULL, "%s-%u", @@ -988,14 +959,16 @@ static int lwmi_om_fw_attr_add(struct lwmi_om_priv *priv) } for (i = 0; i < ARRAY_SIZE(cd01_attr_groups) - 1; i++) { + cd01_attr_groups[i].tunable_attr->dev = &priv->wdev->dev; + if (!lwmi_attr_01_is_supported(cd01_attr_groups[i].tunable_attr)) + continue; + err = sysfs_create_group(&priv->fw_attr_kset->kobj, cd01_attr_groups[i].attr_group); if (err) goto err_remove_groups; - - cd01_attr_groups[i].tunable_attr->dev = &priv->wdev->dev; } - return 0; + return; err_remove_groups: while (i--) @@ -1009,7 +982,12 @@ err_destroy_classdev: err_free_ida: ida_free(&lwmi_om_ida, priv->ida_id); - return err; + +err_no_ida: + priv->ida_id = -EIDRM; + + dev_warn(&priv->wdev->dev, + "failed to register firmware-attributes device: %d\n", err); } /** @@ -1018,12 +996,17 @@ err_free_ida: */ static void lwmi_om_fw_attr_remove(struct lwmi_om_priv *priv) { + if (priv->ida_id < 0) + return; + for (unsigned int i = 0; i < ARRAY_SIZE(cd01_attr_groups) - 1; i++) sysfs_remove_group(&priv->fw_attr_kset->kobj, cd01_attr_groups[i].attr_group); kset_unregister(priv->fw_attr_kset); device_unregister(priv->fw_attr_dev); + ida_free(&lwmi_om_ida, priv->ida_id); + priv->ida_id = -EIDRM; } /* ======== Self (master: lenovo-wmi-other) ======== */ @@ -1060,12 +1043,17 @@ static int lwmi_om_master_bind(struct device *dev) priv->cd00_list = binder.cd00_list; priv->cd01_list = binder.cd01_list; - if (!priv->cd00_list || !priv->cd01_list) + if (!priv->cd00_list || !priv->cd01_list) { + component_unbind_all(dev, NULL); + return -ENODEV; + } lwmi_om_fan_info_collect_cd00(priv); - return lwmi_om_fw_attr_add(priv); + lwmi_om_fw_attr_add(priv); + + return 0; } /** @@ -1117,13 +1105,7 @@ static int lwmi_other_probe(struct wmi_device *wdev, const void *context) static void lwmi_other_remove(struct wmi_device *wdev) { - struct lwmi_om_priv *priv = dev_get_drvdata(&wdev->dev); - component_master_del(&wdev->dev, &lwmi_om_master_ops); - - /* No IDA to free if the driver is never bound to its components. */ - if (priv->ida_id >= 0) - ida_free(&lwmi_om_ida, priv->ida_id); } static const struct wmi_device_id lwmi_other_id_table[] = { diff --git a/drivers/platform/x86/lenovo/wmi-other.h b/drivers/platform/x86/lenovo/wmi-other.h deleted file mode 100644 index 8ebf5602bb99..000000000000 --- a/drivers/platform/x86/lenovo/wmi-other.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ - -/* Copyright (C) 2025 Derek J. Clark <derekjohn.clark@gmail.com> */ - -#ifndef _LENOVO_WMI_OTHER_H_ -#define _LENOVO_WMI_OTHER_H_ - -struct device; -struct notifier_block; - -int lwmi_om_register_notifier(struct notifier_block *nb); -int lwmi_om_unregister_notifier(struct notifier_block *nb); -int devm_lwmi_om_register_notifier(struct device *dev, - struct notifier_block *nb); - -#endif /* !_LENOVO_WMI_OTHER_H_ */ diff --git a/drivers/platform/x86/samsung-galaxybook.c b/drivers/platform/x86/samsung-galaxybook.c index 755cb82bdb60..6382af0b106c 100644 --- a/drivers/platform/x86/samsung-galaxybook.c +++ b/drivers/platform/x86/samsung-galaxybook.c @@ -53,7 +53,7 @@ struct samsung_galaxybook { void *i8042_filter_ptr; struct work_struct block_recording_hotkey_work; - struct input_dev *camera_lens_cover_switch; + struct input_dev *input; struct acpi_battery_hook battery_hook; @@ -197,6 +197,9 @@ static const guid_t performance_mode_guid = #define GB_ACPI_NOTIFY_DEVICE_ON_TABLE 0x6c #define GB_ACPI_NOTIFY_DEVICE_OFF_TABLE 0x6d #define GB_ACPI_NOTIFY_HOTKEY_PERFORMANCE_MODE 0x70 +#define GB_ACPI_NOTIFY_HOTKEY_KBD_BACKLIGHT 0x7d +#define GB_ACPI_NOTIFY_HOTKEY_MICMUTE 0x6e +#define GB_ACPI_NOTIFY_HOTKEY_CAMERA 0x6f #define GB_KEY_KBD_BACKLIGHT_KEYDOWN 0x2c #define GB_KEY_KBD_BACKLIGHT_KEYUP 0xac @@ -859,13 +862,29 @@ static int block_recording_acpi_set(struct samsung_galaxybook *galaxybook, const if (err) return err; - input_report_switch(galaxybook->camera_lens_cover_switch, + input_report_switch(galaxybook->input, SW_CAMERA_LENS_COVER, value ? 1 : 0); - input_sync(galaxybook->camera_lens_cover_switch); + input_sync(galaxybook->input); return 0; } +static int galaxybook_input_init(struct samsung_galaxybook *galaxybook) +{ + galaxybook->input = devm_input_allocate_device(&galaxybook->platform->dev); + if (!galaxybook->input) + return -ENOMEM; + + galaxybook->input->name = "Samsung Galaxy Book Camera Lens Cover"; + galaxybook->input->phys = DRIVER_NAME "/input0"; + galaxybook->input->id.bustype = BUS_HOST; + + input_set_capability(galaxybook->input, EV_KEY, KEY_MICMUTE); + input_set_capability(galaxybook->input, EV_SW, SW_CAMERA_LENS_COVER); + + return input_register_device(galaxybook->input); +} + static int galaxybook_block_recording_init(struct samsung_galaxybook *galaxybook) { bool value; @@ -887,24 +906,8 @@ static int galaxybook_block_recording_init(struct samsung_galaxybook *galaxybook return GB_NOT_SUPPORTED; } - galaxybook->camera_lens_cover_switch = - devm_input_allocate_device(&galaxybook->platform->dev); - if (!galaxybook->camera_lens_cover_switch) - return -ENOMEM; - - galaxybook->camera_lens_cover_switch->name = "Samsung Galaxy Book Camera Lens Cover"; - galaxybook->camera_lens_cover_switch->phys = DRIVER_NAME "/input0"; - galaxybook->camera_lens_cover_switch->id.bustype = BUS_HOST; - - input_set_capability(galaxybook->camera_lens_cover_switch, EV_SW, SW_CAMERA_LENS_COVER); - - err = input_register_device(galaxybook->camera_lens_cover_switch); - if (err) - return err; - - input_report_switch(galaxybook->camera_lens_cover_switch, - SW_CAMERA_LENS_COVER, value ? 1 : 0); - input_sync(galaxybook->camera_lens_cover_switch); + input_report_switch(galaxybook->input, SW_CAMERA_LENS_COVER, value ? 1 : 0); + input_sync(galaxybook->input); return 0; } @@ -1260,6 +1263,25 @@ static void galaxybook_acpi_notify(acpi_handle handle, u32 event, void *data) if (galaxybook->has_performance_mode) platform_profile_cycle(); break; + case GB_ACPI_NOTIFY_HOTKEY_KBD_BACKLIGHT: + if (galaxybook->has_kbd_backlight) + schedule_work(&galaxybook->kbd_backlight_hotkey_work); + break; + case GB_ACPI_NOTIFY_HOTKEY_MICMUTE: + input_report_key(galaxybook->input, KEY_MICMUTE, 1); + input_sync(galaxybook->input); + input_report_key(galaxybook->input, KEY_MICMUTE, 0); + input_sync(galaxybook->input); + break; + case GB_ACPI_NOTIFY_HOTKEY_CAMERA: + if (galaxybook->has_block_recording) { + schedule_work(&galaxybook->block_recording_hotkey_work); + } else { + input_report_switch(galaxybook->input, SW_CAMERA_LENS_COVER, + !test_bit(SW_CAMERA_LENS_COVER, galaxybook->input->sw)); + input_sync(galaxybook->input); + } + break; default: dev_warn(&galaxybook->platform->dev, "unknown ACPI notification event: 0x%x\n", event); @@ -1392,6 +1414,11 @@ static int galaxybook_probe(struct platform_device *pdev) return dev_err_probe(&galaxybook->platform->dev, err, "failed to initialize kbd_backlight\n"); + err = galaxybook_input_init(galaxybook); + if (err) + return dev_err_probe(&galaxybook->platform->dev, err, + "failed to initialize input device\n"); + err = galaxybook_fw_attrs_init(galaxybook); if (err) return dev_err_probe(&galaxybook->platform->dev, err, diff --git a/drivers/resctrl/mpam_devices.c b/drivers/resctrl/mpam_devices.c index 41b14344b16f..988fc291241d 100644 --- a/drivers/resctrl/mpam_devices.c +++ b/drivers/resctrl/mpam_devices.c @@ -164,11 +164,17 @@ static void mpam_free_garbage(void) /* * Once mpam is enabled, new requestors cannot further reduce the available * partid. Assert that the size is fixed, and new requestors will be turned - * away. + * away. This is needed when walking over structures sized by PARTID. + * + * During mpam_disable() these structures are not fixed, but the MSC state + * is still reset using whatever sizes have been discovered so far. As only + * PARTID 0 will be used after mpam_disable(), any race would be benign. + * Skip the check if a mpam_disable_reason has been set. */ static void mpam_assert_partid_sizes_fixed(void) { - WARN_ON_ONCE(!partid_max_published); + if (!mpam_disable_reason) + WARN_ON_ONCE(!partid_max_published); } static u32 __mpam_read_reg(struct mpam_msc *msc, u16 reg) @@ -728,10 +734,9 @@ static void mpam_enable_quirks(struct mpam_msc *msc) * Try and see what values stick in this bit. If we can write either value, * its probably not implemented by hardware. */ -static bool _mpam_ris_hw_probe_hw_nrdy(struct mpam_msc_ris *ris, u32 mon_reg) +static bool mpam_ris_hw_probe_csu_nrdy(struct mpam_msc_ris *ris) { - u32 now; - u64 mon_sel; + u32 now, mon_sel, ctl_val; bool can_set, can_clear; struct mpam_msc *msc = ris->vmsc->msc; @@ -740,23 +745,30 @@ static bool _mpam_ris_hw_probe_hw_nrdy(struct mpam_msc_ris *ris, u32 mon_reg) mon_sel = FIELD_PREP(MSMON_CFG_MON_SEL_MON_SEL, 0) | FIELD_PREP(MSMON_CFG_MON_SEL_RIS, ris->ris_idx); - _mpam_write_monsel_reg(msc, mon_reg, mon_sel); + mpam_write_monsel_reg(msc, CFG_MON_SEL, mon_sel); + + /* Hardware might ignore nrdy if it's not enabled */ + ctl_val = MSMON_CFG_CSU_CTL_TYPE_CSU; + ctl_val |= MSMON_CFG_x_CTL_MATCH_PARTID; + ctl_val |= MSMON_CFG_x_CTL_MATCH_PMG; + ctl_val |= MSMON_CFG_x_CTL_EN; + mpam_write_monsel_reg(msc, CFG_CSU_FLT, 0); + mpam_write_monsel_reg(msc, CFG_CSU_CTL, ctl_val); - _mpam_write_monsel_reg(msc, mon_reg, MSMON___NRDY); - now = _mpam_read_monsel_reg(msc, mon_reg); + _mpam_write_monsel_reg(msc, MSMON_CSU, MSMON___NRDY); + now = _mpam_read_monsel_reg(msc, MSMON_CSU); can_set = now & MSMON___NRDY; - _mpam_write_monsel_reg(msc, mon_reg, 0); - now = _mpam_read_monsel_reg(msc, mon_reg); + _mpam_write_monsel_reg(msc, MSMON_CSU, 0); + /* Configuration change to try and coax hardware into setting nrdy */ + mpam_write_monsel_reg(msc, CFG_CSU_FLT, 0x1); + now = _mpam_read_monsel_reg(msc, MSMON_CSU); can_clear = !(now & MSMON___NRDY); mpam_mon_sel_unlock(msc); return (!can_set || !can_clear); } -#define mpam_ris_hw_probe_hw_nrdy(_ris, _mon_reg) \ - _mpam_ris_hw_probe_hw_nrdy(_ris, MSMON_##_mon_reg) - static void mpam_ris_hw_probe(struct mpam_msc_ris *ris) { int err; @@ -873,20 +885,18 @@ static void mpam_ris_hw_probe(struct mpam_msc_ris *ris) mpam_set_feature(mpam_feat_msmon_csu_xcl, props); /* Is NRDY hardware managed? */ - hw_managed = mpam_ris_hw_probe_hw_nrdy(ris, CSU); - if (hw_managed) - mpam_set_feature(mpam_feat_msmon_csu_hw_nrdy, props); - } + hw_managed = mpam_ris_hw_probe_csu_nrdy(ris); - /* - * Accept the missing firmware property if NRDY appears - * un-implemented. - */ - if (err && mpam_has_feature(mpam_feat_msmon_csu_hw_nrdy, props)) - dev_err_once(dev, "Counters are not usable because not-ready timeout was not provided by firmware."); + /* + * Accept the missing firmware property if NRDY appears + * un-implemented. + */ + if (err && hw_managed) + dev_err_once(dev, "Counters are not usable because not-ready timeout was not provided by firmware."); + } } if (FIELD_GET(MPAMF_MSMON_IDR_MSMON_MBWU, msmon_features)) { - bool has_long, hw_managed; + bool has_long; u32 mbwumon_idr = mpam_read_partsel_reg(msc, MBWUMON_IDR); props->num_mbwu_mon = FIELD_GET(MPAMF_MBWUMON_IDR_NUM_MON, mbwumon_idr); @@ -905,16 +915,6 @@ static void mpam_ris_hw_probe(struct mpam_msc_ris *ris) } else { mpam_set_feature(mpam_feat_msmon_mbwu_31counter, props); } - - /* Is NRDY hardware managed? */ - hw_managed = mpam_ris_hw_probe_hw_nrdy(ris, MBWU); - if (hw_managed) - mpam_set_feature(mpam_feat_msmon_mbwu_hw_nrdy, props); - - /* - * Don't warn about any missing firmware property for - * MBWU NRDY - it doesn't make any sense! - */ } } } @@ -1197,7 +1197,6 @@ static void __ris_msmon_read(void *arg) bool reset_on_next_read = false; struct mpam_msc_ris *ris = m->ris; struct msmon_mbwu_state *mbwu_state; - struct mpam_props *rprops = &ris->props; struct mpam_msc *msc = m->ris->vmsc->msc; u32 mon_sel, ctl_val, flt_val, cur_ctl, cur_flt; @@ -1253,8 +1252,7 @@ static void __ris_msmon_read(void *arg) switch (m->type) { case mpam_feat_msmon_csu: now = mpam_read_monsel_reg(msc, CSU); - if (mpam_has_feature(mpam_feat_msmon_csu_hw_nrdy, rprops)) - nrdy = now & MSMON___NRDY; + nrdy = now & MSMON___NRDY; now = FIELD_GET(MSMON___VALUE, now); if (mpam_has_quirk(IGNORE_CSU_NRDY, msc) && m->waited_timeout) @@ -1266,8 +1264,7 @@ static void __ris_msmon_read(void *arg) case mpam_feat_msmon_mbwu_63counter: if (m->type != mpam_feat_msmon_mbwu_31counter) { now = mpam_msc_read_mbwu_l(msc); - if (mpam_has_feature(mpam_feat_msmon_mbwu_hw_nrdy, rprops)) - nrdy = now & MSMON___L_NRDY; + nrdy = now & MSMON___L_NRDY; if (m->type == mpam_feat_msmon_mbwu_63counter) now = FIELD_GET(MSMON___LWD_VALUE, now); @@ -1275,8 +1272,7 @@ static void __ris_msmon_read(void *arg) now = FIELD_GET(MSMON___L_VALUE, now); } else { now = mpam_read_monsel_reg(msc, MBWU); - if (mpam_has_feature(mpam_feat_msmon_mbwu_hw_nrdy, rprops)) - nrdy = now & MSMON___NRDY; + nrdy = now & MSMON___NRDY; now = FIELD_GET(MSMON___VALUE, now); } @@ -2585,6 +2581,9 @@ static void __destroy_component_cfg(struct mpam_component *comp) lockdep_assert_held(&mpam_list_lock); + if (!comp->cfg) + return; + add_to_garbage(comp->cfg); list_for_each_entry(vmsc, &comp->vmsc, comp_list) { msc = vmsc->msc; diff --git a/drivers/resctrl/mpam_internal.h b/drivers/resctrl/mpam_internal.h index 1914aefdcba9..04d1a59f02af 100644 --- a/drivers/resctrl/mpam_internal.h +++ b/drivers/resctrl/mpam_internal.h @@ -181,14 +181,12 @@ enum mpam_device_features { mpam_feat_msmon_csu, mpam_feat_msmon_csu_capture, mpam_feat_msmon_csu_xcl, - mpam_feat_msmon_csu_hw_nrdy, mpam_feat_msmon_mbwu, mpam_feat_msmon_mbwu_31counter, mpam_feat_msmon_mbwu_44counter, mpam_feat_msmon_mbwu_63counter, mpam_feat_msmon_mbwu_capture, mpam_feat_msmon_mbwu_rwbw, - mpam_feat_msmon_mbwu_hw_nrdy, mpam_feat_partid_nrw, MPAM_FEATURE_LAST }; diff --git a/drivers/staging/greybus/hid.c b/drivers/staging/greybus/hid.c index 1f58c907c036..f1f9f6fbc00e 100644 --- a/drivers/staging/greybus/hid.c +++ b/drivers/staging/greybus/hid.c @@ -201,7 +201,7 @@ static void gb_hid_init_report(struct gb_hid *ghid, struct hid_report *report) * we just need to setup the input fields, so using * hid_report_raw_event is safe. */ - hid_report_raw_event(ghid->hid, report->type, ghid->inbuf, size, 1); + hid_report_raw_event(ghid->hid, report->type, ghid->inbuf, ghid->bufsize, size, 1); } static void gb_hid_init_reports(struct gb_hid *ghid) diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 3f8d093aacf8..050e7542952e 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -483,6 +483,40 @@ static int vfio_pci_core_runtime_resume(struct device *dev) #endif /* CONFIG_PM */ /* + * Eager-request BAR resources, and iomap them. Soft failures are + * allowed, and consumers must check the barmap before use in order to + * give compatible user-visible behaviour with the previous on-demand + * allocation method. + */ +static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev) +{ + struct pci_dev *pdev = vdev->pdev; + int i; + + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + int bar = i + PCI_STD_RESOURCES; + + vdev->barmap[bar] = IOMEM_ERR_PTR(-ENODEV); + + if (!pci_resource_len(pdev, i)) + continue; + + if (pci_request_selected_regions(pdev, 1 << bar, "vfio")) { + pci_dbg(pdev, "Failed to reserve region %d\n", bar); + vdev->barmap[bar] = IOMEM_ERR_PTR(-EBUSY); + continue; + } + + vdev->barmap[bar] = pci_iomap(pdev, bar, 0); + if (!vdev->barmap[bar]) { + pci_dbg(pdev, "Failed to iomap region %d\n", bar); + pci_release_selected_regions(pdev, 1 << bar); + vdev->barmap[bar] = IOMEM_ERR_PTR(-ENOMEM); + } + } +} + +/* * The pci-driver core runtime PM routines always save the device state * before going into suspended state. If the device is going into low power * state with only with runtime PM ops, then no explicit handling is needed @@ -568,6 +602,7 @@ int vfio_pci_core_enable(struct vfio_pci_core_device *vdev) if (!vfio_vga_disabled() && vfio_pci_is_vga(pdev)) vdev->has_vga = true; + vfio_pci_core_map_bars(vdev); return 0; @@ -648,7 +683,7 @@ void vfio_pci_core_disable(struct vfio_pci_core_device *vdev) for (i = 0; i < PCI_STD_NUM_BARS; i++) { bar = i + PCI_STD_RESOURCES; - if (!vdev->barmap[bar]) + if (IS_ERR_OR_NULL(vdev->barmap[bar])) continue; pci_iounmap(pdev, vdev->barmap[bar]); pci_release_selected_regions(pdev, 1 << bar); diff --git a/drivers/vfio/pci/vfio_pci_dmabuf.c b/drivers/vfio/pci/vfio_pci_dmabuf.c index f87fd32e4a01..1a177ce7de54 100644 --- a/drivers/vfio/pci/vfio_pci_dmabuf.c +++ b/drivers/vfio/pci/vfio_pci_dmabuf.c @@ -244,9 +244,11 @@ int vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device *vdev, u32 flags, return -EINVAL; /* - * For PCI the region_index is the BAR number like everything else. + * For PCI the region_index is the BAR number like everything + * else. Check that PCI resources have been claimed for it. */ - if (get_dma_buf.region_index >= VFIO_PCI_ROM_REGION_INDEX) + if (get_dma_buf.region_index >= VFIO_PCI_ROM_REGION_INDEX || + vfio_pci_core_setup_barmap(vdev, get_dma_buf.region_index)) return -ENODEV; dma_ranges = memdup_array_user(&arg->dma_ranges, get_dma_buf.nr_ranges, @@ -354,19 +356,18 @@ void vfio_pci_dma_buf_move(struct vfio_pci_core_device *vdev, bool revoked) if (revoked) { kref_put(&priv->kref, vfio_pci_dma_buf_done); wait_for_completion(&priv->comp); - } else { /* - * Kref is initialize again, because when revoke - * was performed the reference counter was decreased - * to zero to trigger completion. + * Re-arm the registered kref reference and the + * completion so the post-revoke state matches the + * post-creation state. An un-revoke followed by a + * new mapping needs the kref to be non-zero before + * kref_get(), and vfio_pci_dma_buf_cleanup() + * delegates its drain back through this revoke + * path on a possibly-already-revoked dma-buf. */ kref_init(&priv->kref); - /* - * There is no need to wait as no mapping was - * performed when the previous status was - * priv->revoked == true. - */ reinit_completion(&priv->comp); + } else { dma_resv_lock(priv->dmabuf->resv, NULL); priv->revoked = false; dma_resv_unlock(priv->dmabuf->resv); @@ -382,21 +383,22 @@ void vfio_pci_dma_buf_cleanup(struct vfio_pci_core_device *vdev) struct vfio_pci_dma_buf *tmp; down_write(&vdev->memory_lock); + + /* + * Drain any active mappings via the revoke path. The move is + * idempotent for dma-bufs already in the revoked state and + * leaves every priv with the kref re-armed and the completion + * ready, so cleanup itself does not need to participate in kref + * bookkeeping. + */ + vfio_pci_dma_buf_move(vdev, true); + list_for_each_entry_safe(priv, tmp, &vdev->dmabufs, dmabufs_elm) { if (!get_file_active(&priv->dmabuf->file)) continue; - dma_resv_lock(priv->dmabuf->resv, NULL); list_del_init(&priv->dmabufs_elm); priv->vdev = NULL; - priv->revoked = true; - dma_buf_invalidate_mappings(priv->dmabuf); - dma_resv_wait_timeout(priv->dmabuf->resv, - DMA_RESV_USAGE_BOOKKEEP, false, - MAX_SCHEDULE_TIMEOUT); - dma_resv_unlock(priv->dmabuf->resv); - kref_put(&priv->kref, vfio_pci_dma_buf_done); - wait_for_completion(&priv->comp); vfio_device_put_registration(&vdev->vdev); fput(priv->dmabuf->file); } diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c index 4251ee03e146..3bfbb879a005 100644 --- a/drivers/vfio/pci/vfio_pci_rdwr.c +++ b/drivers/vfio/pci/vfio_pci_rdwr.c @@ -198,27 +198,15 @@ ssize_t vfio_pci_core_do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem, } EXPORT_SYMBOL_GPL(vfio_pci_core_do_io_rw); +/* + * The barmap is set up in vfio_pci_core_enable(). Callers use this + * function to check that the BAR resources are requested or that the + * pci_iomap() was done. + */ int vfio_pci_core_setup_barmap(struct vfio_pci_core_device *vdev, int bar) { - struct pci_dev *pdev = vdev->pdev; - int ret; - void __iomem *io; - - if (vdev->barmap[bar]) - return 0; - - ret = pci_request_selected_regions(pdev, 1 << bar, "vfio"); - if (ret) - return ret; - - io = pci_iomap(pdev, bar, 0); - if (!io) { - pci_release_selected_regions(pdev, 1 << bar); - return -ENOMEM; - } - - vdev->barmap[bar] = io; - + if (IS_ERR(vdev->barmap[bar])) + return PTR_ERR(vdev->barmap[bar]); return 0; } EXPORT_SYMBOL_GPL(vfio_pci_core_setup_barmap); diff --git a/drivers/xen/xen-acpi-pad.c b/drivers/xen/xen-acpi-pad.c index 75a39862c1df..5b98e0e93807 100644 --- a/drivers/xen/xen-acpi-pad.c +++ b/drivers/xen/xen-acpi-pad.c @@ -110,9 +110,13 @@ static void acpi_pad_notify(acpi_handle handle, u32 event, static int acpi_pad_probe(struct platform_device *pdev) { - struct acpi_device *device = ACPI_COMPANION(&pdev->dev); + struct acpi_device *device; acpi_status status; + device = ACPI_COMPANION(&pdev->dev); + if (!device) + return -ENODEV; + strcpy(acpi_device_name(device), ACPI_PROCESSOR_AGGREGATOR_DEVICE_NAME); strcpy(acpi_device_class(device), ACPI_PROCESSOR_AGGREGATOR_CLASS); diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index e6f5a17a13e3..b611c64119db 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -2412,29 +2412,25 @@ static struct btrfs_block_group *btrfs_create_block_group( */ static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info) { - u64 start = 0; + struct rb_node *node; int ret = 0; - while (1) { + /* + * This is called during mount from btrfs_read_block_groups(), before + * any background threads are started, so no concurrent writers can + * modify the mapping_tree. No lock is needed here. + */ + for (node = rb_first_cached(&fs_info->mapping_tree); node; node = rb_next(node)) { struct btrfs_chunk_map *map; struct btrfs_block_group *bg; - /* - * btrfs_find_chunk_map() will return the first chunk map - * intersecting the range, so setting @length to 1 is enough to - * get the first chunk. - */ - map = btrfs_find_chunk_map(fs_info, start, 1); - if (!map) - break; - + map = rb_entry(node, struct btrfs_chunk_map, rb_node); bg = btrfs_lookup_block_group(fs_info, map->start); if (unlikely(!bg)) { btrfs_err(fs_info, "chunk start=%llu len=%llu doesn't have corresponding block group", map->start, map->chunk_len); ret = -EUCLEAN; - btrfs_free_chunk_map(map); break; } if (unlikely(bg->start != map->start || bg->length != map->chunk_len || @@ -2447,12 +2443,9 @@ static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info) bg->start, bg->length, bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK); ret = -EUCLEAN; - btrfs_free_chunk_map(map); btrfs_put_block_group(bg); break; } - start = map->start + map->chunk_len; - btrfs_free_chunk_map(map); btrfs_put_block_group(bg); } return ret; diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index b2393a48a8fe..a02b62e0a8f3 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -407,22 +407,18 @@ static noinline int add_ra_bio_pages(struct inode *inode, end_index = (i_size_read(inode) - 1) >> PAGE_SHIFT; - /* - * Avoid direct reclaim when the caller does not allow it. Since - * add_ra_bio_pages() is always speculative, suppress allocation warnings - * in either case. - */ + /* Avoid direct reclaim when the caller does not allow it. */ + constraint_gfp = ~__GFP_FS; + cache_gfp = GFP_NOFS | __GFP_NOWARN; if (!direct_reclaim) { - constraint_gfp = ~(__GFP_FS | __GFP_DIRECT_RECLAIM) | __GFP_NOWARN; - cache_gfp = (GFP_NOFS & ~__GFP_DIRECT_RECLAIM) | __GFP_NOWARN; - } else { - constraint_gfp = (~__GFP_FS) | __GFP_NOWARN; - cache_gfp = GFP_NOFS | __GFP_NOWARN; + constraint_gfp &= ~__GFP_DIRECT_RECLAIM; + cache_gfp &= ~__GFP_DIRECT_RECLAIM; } while (cur < compressed_end) { pgoff_t page_end; pgoff_t pg_index = cur >> PAGE_SHIFT; + gfp_t masked_constraint_gfp; u32 add_size; if (pg_index > end_index) @@ -449,8 +445,14 @@ static noinline int add_ra_bio_pages(struct inode *inode, continue; } - folio = filemap_alloc_folio(mapping_gfp_constraint(mapping, constraint_gfp), - 0, NULL); + /* + * Since add_ra_bio_pages() is always speculative, suppress + * allocation warnings. + */ + masked_constraint_gfp = mapping_gfp_constraint(mapping, constraint_gfp); + masked_constraint_gfp |= __GFP_NOWARN; + + folio = filemap_alloc_folio(masked_constraint_gfp, 0, NULL); if (!folio) break; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 8a11be02eeb9..c0a30bb213d7 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4686,6 +4686,7 @@ static void btrfs_destroy_marked_extents(struct btrfs_fs_info *fs_info, free_extent_buffer_stale(eb); } } + btrfs_extent_io_tree_release(dirty_pages); } static void btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 906d5c21ebc4..75136a172710 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9299,10 +9299,38 @@ next: if (!(mode & FALLOC_FL_KEEP_SIZE) && (actual_len > inode->i_size) && (cur_offset > inode->i_size)) { + u64 range_start; + u64 range_end; + if (cur_offset > actual_len) i_size = actual_len; else i_size = cur_offset; + + /* + * Make sure the file_extent_tree covers the entire + * range [old_i_size, new_i_size) before we update + * disk_i_size. Without this, a previous KEEP_SIZE + * prealloc that extended past i_size (and was lost + * across umount/mount because file_extent_tree is + * only populated up to round_up(i_size) on inode + * load) can leave a gap inside this range. That gap + * would cause btrfs_inode_safe_disk_i_size_write() + * (via find_contiguous_extent_bit() starting at 0) + * to truncate disk_i_size to the start of the gap, + * making the persisted size smaller than i_size. + */ + range_start = round_down(inode->i_size, fs_info->sectorsize); + range_end = round_up(i_size, fs_info->sectorsize); + ret = btrfs_inode_set_file_extent_range(BTRFS_I(inode), + range_start, range_end - range_start); + if (ret) { + btrfs_abort_transaction(trans, ret); + if (own_trans) + btrfs_end_transaction(trans); + break; + } + i_size_write(inode, i_size); btrfs_inode_safe_disk_i_size_write(BTRFS_I(inode), 0); } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 248adb785051..194f581b36f3 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1293,14 +1293,13 @@ static int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans) blk_finish_plug(&plug); ret2 = btrfs_wait_extents(fs_info, dirty_pages); - btrfs_extent_io_tree_release(&trans->transaction->dirty_pages); - if (ret) return ret; - else if (ret2) + if (ret2) return ret2; - else - return 0; + + btrfs_extent_io_tree_release(&trans->transaction->dirty_pages); + return 0; } /* diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 1454760332ff..0a86f672cc09 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1336,6 +1336,7 @@ void ceph_process_folio_batch(struct address_space *mapping, ceph_wbc, folio); if (rc == -ENODATA) { folio_unlock(folio); + folio_put(folio); ceph_wbc->fbatch.folios[i] = NULL; continue; } else if (rc == -E2BIG) { @@ -1346,6 +1347,7 @@ void ceph_process_folio_batch(struct address_space *mapping, if (!folio_clear_dirty_for_io(folio)) { doutc(cl, "%p !folio_clear_dirty_for_io\n", folio); folio_unlock(folio); + folio_put(folio); ceph_wbc->fbatch.folios[i] = NULL; continue; } diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c index 4dc9426643e8..053d5bf0c9f0 100644 --- a/fs/ceph/quota.c +++ b/fs/ceph/quota.c @@ -228,12 +228,19 @@ static int get_quota_realm(struct ceph_mds_client *mdsc, struct inode *inode, restart: realm = ceph_inode(inode)->i_snap_realm; - if (realm) + if (realm) { ceph_get_snap_realm(mdsc, realm); - else - pr_err_ratelimited_client(cl, - "%p %llx.%llx null i_snap_realm\n", - inode, ceph_vinop(inode)); + } else { + /* + * i_snap_realm is NULL when all caps have been released, e.g. + * after an MDS session rejection. This is a transient state; + * the realm will be restored once caps are re-granted. + * Treat it as "no quota realm found". + */ + doutc(cl, "%p %llx.%llx null i_snap_realm\n", + inode, ceph_vinop(inode)); + } + while (realm) { bool has_inode; @@ -340,12 +347,19 @@ static bool check_quota_exceeded(struct inode *inode, enum quota_check_op op, down_read(&mdsc->snap_rwsem); restart: realm = ceph_inode(inode)->i_snap_realm; - if (realm) + if (realm) { ceph_get_snap_realm(mdsc, realm); - else - pr_err_ratelimited_client(cl, - "%p %llx.%llx null i_snap_realm\n", - inode, ceph_vinop(inode)); + } else { + /* + * i_snap_realm is NULL when all caps have been released, e.g. + * after an MDS session rejection. This is a transient state; + * the realm will be restored once caps are re-granted. + * Treat it as "quota not exceeded". + */ + doutc(cl, "%p %llx.%llx null i_snap_realm\n", + inode, ceph_vinop(inode)); + } + while (realm) { bool has_inode; @@ -496,6 +510,9 @@ bool ceph_quota_update_statfs(struct ceph_fs_client *fsc, struct kstatfs *buf) u64 total = 0, used, free; bool is_updated = false; + if (!ceph_has_realms_with_quotas(d_inode(fsc->sb->s_root))) + return false; + down_read(&mdsc->snap_rwsem); get_quota_realm(mdsc, d_inode(fsc->sb->s_root), QUOTA_GET_MAX_BYTES, &realm, true); diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 5f87f62091a1..e773be07f767 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -1254,6 +1254,22 @@ retry: ceph_vinop(inode), name, ceph_cap_string(issued)); __build_xattrs(inode); + /* + * __build_xattrs() may have released and reacquired i_ceph_lock, + * during which handle_cap_grant() could have replaced i_xattrs.blob + * with a newer MDS-provided blob and bumped i_xattrs.version. If that + * caused __build_xattrs() to rebuild the rb-tree from the new blob, + * count/names_size/vals_size may now be larger than when + * required_blob_size was computed above. Recompute it here so the + * prealloc_blob size check below reflects the current tree state. + */ + required_blob_size = __get_required_blob_size(ci, name_len, val_len); + if (required_blob_size > mdsc->mdsmap->m_max_xattr_size) { + doutc(cl, "sync (size too large): %d > %llu\n", + required_blob_size, mdsc->mdsmap->m_max_xattr_size); + goto do_sync; + } + if (!ci->i_xattrs.prealloc_blob || required_blob_size > ci->i_xattrs.prealloc_blob->alloc_len) { struct ceph_buffer *blob; @@ -1294,6 +1310,7 @@ retry: do_sync: spin_unlock(&ci->i_ceph_lock); + ceph_buffer_put(old_blob); do_sync_unlocked: if (lock_snap_rwsem) up_read(&mdsc->snap_rwsem); diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index b0a6549b3848..b36ee619cdcd 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -355,7 +355,7 @@ static ssize_t iomap_dio_bio_iter_one(struct iomap_iter *iter, if (dio->flags & IOMAP_DIO_BOUNCE) ret = bio_iov_iter_bounce(bio, dio->submit.iter, - iomap_max_bio_size(&iter->iomap)); + iomap_max_bio_size(&iter->iomap), alignment); else ret = bio_iov_iter_get_pages(bio, dio->submit.iter, alignment - 1); diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 85e94c30285a..ab39ec885440 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1413,6 +1413,9 @@ nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, dst, clone->cl_dst_pos, clone->cl_count, EX_ISSYNC(cstate->current_fh.fh_export)); + if (!status && (READ_ONCE(dst->nf_file->f_mode) & FMODE_NOCMTIME) != 0) + nfsd_update_cmtime_attr(dst->nf_file, 0); + nfsd_file_put(dst); nfsd_file_put(src); out: @@ -2118,8 +2121,10 @@ do_callback: set_bit(NFSD4_COPY_F_COMPLETED, ©->cp_flags); trace_nfsd_copy_async_done(copy); - nfsd4_send_cb_offload(copy); atomic_dec(©->cp_nn->pending_async_copies); + if (copy->cp_res.wr_bytes_written > 0 && copy->attr_update) + nfsd_update_cmtime_attr(copy->nf_dst->nf_file, 0); + nfsd4_send_cb_offload(copy); return 0; } @@ -2179,6 +2184,9 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, memcpy(&result->cb_stateid, ©->cp_stateid.cs_stid, sizeof(result->cb_stateid)); dup_copy_fields(copy, async_copy); + if ((READ_ONCE(copy->nf_dst->nf_file->f_mode) & + FMODE_NOCMTIME) != 0) + async_copy->attr_update = true; memcpy(async_copy->cp_cb_offload.co_referring_sessionid.data, cstate->session->se_sessionid.data, NFS4_MAX_SESSIONID_LEN); @@ -2197,6 +2205,10 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, } else { status = nfsd4_do_copy(copy, copy->nf_src->nf_file, copy->nf_dst->nf_file, true); + if ((READ_ONCE(copy->nf_dst->nf_file->f_mode) & + FMODE_NOCMTIME) != 0 && + copy->cp_res.wr_bytes_written > 0) + nfsd_update_cmtime_attr(copy->nf_dst->nf_file, 0); } out: trace_nfsd_copy_done(copy, status); @@ -2535,10 +2547,6 @@ nfsd4_get_dir_delegation(struct svc_rqst *rqstp, dd = nfsd_get_dir_deleg(cstate, gdd, nf); nfsd_file_put(nf); if (IS_ERR(dd)) { - int err = PTR_ERR(dd); - - if (err != -EAGAIN) - return nfserrno(err); gdd->gddrnf_status = GDD4_UNAVAIL; return nfs_ok; } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c2d13b26a687..6837b63d9864 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1221,10 +1221,6 @@ static void put_deleg_file(struct nfs4_file *fp) static void nfsd4_finalize_deleg_timestamps(struct nfs4_delegation *dp, struct file *f) { - struct iattr ia = { .ia_valid = ATTR_ATIME | ATTR_CTIME | ATTR_MTIME | ATTR_DELEG }; - struct inode *inode = file_inode(f); - int ret; - /* don't do anything if FMODE_NOCMTIME isn't set */ if ((READ_ONCE(f->f_mode) & FMODE_NOCMTIME) == 0) return; @@ -1242,17 +1238,7 @@ static void nfsd4_finalize_deleg_timestamps(struct nfs4_delegation *dp, struct f return; /* Stamp everything to "now" */ - inode_lock(inode); - ret = notify_change(&nop_mnt_idmap, f->f_path.dentry, &ia, NULL); - inode_unlock(inode); - if (ret) { - struct inode *inode = file_inode(f); - - pr_notice_ratelimited("nfsd: Unable to update timestamps on inode %02x:%02x:%llu: %d\n", - MAJOR(inode->i_sb->s_dev), - MINOR(inode->i_sb->s_dev), - inode->i_ino, ret); - } + nfsd_update_cmtime_attr(f, ATTR_ATIME); } static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp) @@ -1865,6 +1851,13 @@ void nfsd4_revoke_states(struct nfsd_net *nn, struct super_block *sb) break; case SC_TYPE_LAYOUT: ls = layoutstateid(stid); + spin_lock(&clp->cl_lock); + if (stid->sc_status == 0) { + stid->sc_status |= + SC_STATUS_ADMIN_REVOKED; + atomic_inc(&clp->cl_admin_revoked); + } + spin_unlock(&clp->cl_lock); nfsd4_close_layout(ls); break; } @@ -6378,7 +6371,6 @@ nfs4_open_delegation(struct svc_rqst *rqstp, struct nfsd4_open *open, } open->op_delegate_type = deleg_ts ? OPEN_DELEGATE_WRITE_ATTRS_DELEG : OPEN_DELEGATE_WRITE; - dp->dl_cb_fattr.ncf_cur_fsize = stat.size; dp->dl_cb_fattr.ncf_initial_cinfo = nfsd4_change_attribute(&stat); dp->dl_atime = stat.atime; dp->dl_ctime = stat.ctime; @@ -9429,11 +9421,15 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry, if (status != nfserr_jukebox || !nfsd_wait_for_delegreturn(rqstp, inode)) goto out_status; + status = nfs_ok; + goto out_status; + } + if (!ncf->ncf_file_modified) { + if (ncf->ncf_initial_cinfo != ncf->ncf_cb_change) + ncf->ncf_file_modified = true; + else if (i_size_read(inode) != ncf->ncf_cb_fsize) + ncf->ncf_file_modified = true; } - if (!ncf->ncf_file_modified && - (ncf->ncf_initial_cinfo != ncf->ncf_cb_change || - ncf->ncf_cur_fsize != ncf->ncf_cb_fsize)) - ncf->ncf_file_modified = true; if (ncf->ncf_file_modified) { int err; @@ -9560,3 +9556,31 @@ out_delegees: put_nfs4_file(fp); return ERR_PTR(status); } + +/** + * nfsd_update_cmtime_attr - update file's delegated ctime/mtime, + * and optionally other attributes (ie ATTR_ATIME). + * @f: pointer to an opened file + * @flags: any additional flags that should be updated + * + * Given upon opening a file delegated attributes were issues, update + * @f attributes to current times. + */ +void nfsd_update_cmtime_attr(struct file *f, unsigned int flags) +{ + int ret; + struct inode *inode = file_inode(f); + struct iattr attr = { + .ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_DELEG | flags, + }; + + inode_lock(inode); + ret = notify_change(&nop_mnt_idmap, f->f_path.dentry, &attr, NULL); + inode_unlock(inode); + if (ret) + pr_notice_ratelimited("nfsd: Unable to update timestamps on " + "inode %02x:%02x:%llu: %d\n", + MAJOR(inode->i_sb->s_dev), + MINOR(inode->i_sb->s_dev), + inode->i_ino, ret); +} diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 953675eba5c3..c5ccea64c281 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -843,6 +843,7 @@ extern void nfsd4_shutdown_copy(struct nfs4_client *clp); void nfsd4_put_client(struct nfs4_client *clp); void nfsd4_async_copy_reaper(struct nfsd_net *nn); bool nfsd4_has_active_async_copies(struct nfs4_client *clp); +void nfsd_update_cmtime_attr(struct file *f, unsigned int flags); extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(struct xdr_netobj name, struct xdr_netobj princhash, struct nfsd_net *nn); extern bool nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn); diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 417e9ad9fbb3..9a4124c77e04 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -752,6 +752,7 @@ struct nfsd4_copy { struct nfsd_file *nf_src; struct nfsd_file *nf_dst; + bool attr_update; copy_stateid_t cp_stateid; diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index b63ec7ab6e51..4c8b1b9ade8b 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -736,7 +736,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, static int smb3_fs_context_parse_monolithic(struct fs_context *fc, void *data); static int smb3_get_tree(struct fs_context *fc); -static void smb3_sync_ses_chan_max(struct cifs_ses *ses, unsigned int max_channels); +static void smb3_sync_ses_chan_max(struct cifs_ses *ses, size_t max_channels); static int smb3_reconfigure(struct fs_context *fc); static const struct fs_context_operations smb3_fs_context_ops = { @@ -1010,25 +1010,34 @@ do { \ int smb3_sync_session_ctx_passwords(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses) { + char *password = NULL, *password2 = NULL; + if (ses->password && cifs_sb->ctx->password && strcmp(ses->password, cifs_sb->ctx->password)) { - kfree_sensitive(cifs_sb->ctx->password); - cifs_sb->ctx->password = kstrdup(ses->password, GFP_KERNEL); - if (!cifs_sb->ctx->password) + password = kstrdup(ses->password, GFP_KERNEL); + if (!password) return -ENOMEM; } if (ses->password2 && cifs_sb->ctx->password2 && strcmp(ses->password2, cifs_sb->ctx->password2)) { - kfree_sensitive(cifs_sb->ctx->password2); - cifs_sb->ctx->password2 = kstrdup(ses->password2, GFP_KERNEL); - if (!cifs_sb->ctx->password2) { - kfree_sensitive(cifs_sb->ctx->password); - cifs_sb->ctx->password = NULL; + password2 = kstrdup(ses->password2, GFP_KERNEL); + if (!password2) { + kfree_sensitive(password); return -ENOMEM; } } + + if (password) { + kfree_sensitive(cifs_sb->ctx->password); + cifs_sb->ctx->password = password; + } + if (password2) { + kfree_sensitive(cifs_sb->ctx->password2); + cifs_sb->ctx->password2 = password2; + } + return 0; } @@ -1041,7 +1050,7 @@ int smb3_sync_session_ctx_passwords(struct cifs_sb_info *cifs_sb, struct cifs_se * with the session's channel lock. This should be called whenever the maximum * allowed channels for a session changes (e.g., after a remount or reconfigure). */ -static void smb3_sync_ses_chan_max(struct cifs_ses *ses, unsigned int max_channels) +static void smb3_sync_ses_chan_max(struct cifs_ses *ses, size_t max_channels) { spin_lock(&ses->chan_lock); ses->chan_max = max_channels; @@ -1051,12 +1060,15 @@ static void smb3_sync_ses_chan_max(struct cifs_ses *ses, unsigned int max_channe static int smb3_reconfigure(struct fs_context *fc) { struct smb3_fs_context *ctx = smb3_fc2context(fc); + struct smb3_fs_context *new_ctx = NULL; + struct smb3_fs_context *old_ctx = NULL; struct dentry *root = fc->root; struct cifs_sb_info *cifs_sb = CIFS_SB(root->d_sb); struct cifs_ses *ses = cifs_sb_master_tcon(cifs_sb)->ses; unsigned int rsize = ctx->rsize, wsize = ctx->wsize; char *new_password = NULL, *new_password2 = NULL; bool need_recon = false; + bool need_mchan_update; int rc; if (ses->expired_pwd) @@ -1066,6 +1078,16 @@ static int smb3_reconfigure(struct fs_context *fc) if (rc) return rc; + old_ctx = kzalloc_obj(*old_ctx); + if (!old_ctx) + return -ENOMEM; + + rc = smb3_fs_context_dup(old_ctx, cifs_sb->ctx); + if (rc) { + kfree(old_ctx); + return rc; + } + /* * We can not change UNC/username/password/domainname/ * workstation_name/nodename/iocharset @@ -1075,16 +1097,22 @@ static int smb3_reconfigure(struct fs_context *fc) STEAL_STRING(cifs_sb, ctx, UNC); STEAL_STRING(cifs_sb, ctx, source); STEAL_STRING(cifs_sb, ctx, username); + STEAL_STRING(cifs_sb, ctx, domainname); + STEAL_STRING(cifs_sb, ctx, nodename); + STEAL_STRING(cifs_sb, ctx, iocharset); - if (need_recon == false) + if (!need_recon) { STEAL_STRING_SENSITIVE(cifs_sb, ctx, password); - else { + } else { if (ctx->password) { new_password = kstrdup(ctx->password, GFP_KERNEL); - if (!new_password) - return -ENOMEM; - } else + if (!new_password) { + rc = -ENOMEM; + goto restore_ctx; + } + } else { STEAL_STRING_SENSITIVE(cifs_sb, ctx, password); + } } /* @@ -1094,11 +1122,29 @@ static int smb3_reconfigure(struct fs_context *fc) if (ctx->password2) { new_password2 = kstrdup(ctx->password2, GFP_KERNEL); if (!new_password2) { - kfree_sensitive(new_password); - return -ENOMEM; + rc = -ENOMEM; + goto restore_ctx; } - } else + } else { STEAL_STRING_SENSITIVE(cifs_sb, ctx, password2); + } + + /* if rsize or wsize not passed in on remount, use previous values */ + ctx->rsize = rsize ? CIFS_ALIGN_RSIZE(fc, rsize) : cifs_sb->ctx->rsize; + ctx->wsize = wsize ? CIFS_ALIGN_WSIZE(fc, wsize) : cifs_sb->ctx->wsize; + + new_ctx = kzalloc_obj(*new_ctx); + if (!new_ctx) { + rc = -ENOMEM; + goto restore_ctx; + } + + rc = smb3_fs_context_dup(new_ctx, ctx); + if (rc) + goto restore_ctx; + + need_mchan_update = ctx->multichannel != cifs_sb->ctx->multichannel || + ctx->max_channels != cifs_sb->ctx->max_channels; /* * we may update the passwords in the ses struct below. Make sure we do @@ -1109,54 +1155,55 @@ static int smb3_reconfigure(struct fs_context *fc) /* * smb2_reconnect may swap password and password2 in case session setup * failed. First get ctx passwords in sync with ses passwords. It should - * be okay to do this even if this function were to return an error at a - * later stage + * be done before committing new passwords. */ rc = smb3_sync_session_ctx_passwords(cifs_sb, ses); if (rc) { mutex_unlock(&ses->session_mutex); - kfree_sensitive(new_password); - kfree_sensitive(new_password2); - return rc; + goto cleanup_new_ctx; + } + + /* + * If multichannel or max_channels has changed, update the session's channels accordingly. + * This may add or remove channels to match the new configuration. + */ + if (need_mchan_update) { + /* Prevent concurrent scaling operations */ + spin_lock(&ses->ses_lock); + if (ses->flags & CIFS_SES_FLAG_SCALE_CHANNELS) { + spin_unlock(&ses->ses_lock); + mutex_unlock(&ses->session_mutex); + rc = -EINVAL; + goto cleanup_new_ctx; + } + ses->flags |= CIFS_SES_FLAG_SCALE_CHANNELS; + spin_unlock(&ses->ses_lock); } /* - * now that allocations for passwords are done, commit them + * Commit session passwords before any channel work so newly added + * channels authenticate with the new credentials. */ if (new_password) { kfree_sensitive(ses->password); ses->password = new_password; + new_password = NULL; } if (new_password2) { kfree_sensitive(ses->password2); ses->password2 = new_password2; + new_password2 = NULL; } - /* - * If multichannel or max_channels has changed, update the session's channels accordingly. - * This may add or remove channels to match the new configuration. - */ - if ((ctx->multichannel != cifs_sb->ctx->multichannel) || - (ctx->max_channels != cifs_sb->ctx->max_channels)) { - + if (need_mchan_update) { /* Synchronize ses->chan_max with the new mount context */ smb3_sync_ses_chan_max(ses, ctx->max_channels); - /* Now update the session's channels to match the new configuration */ - /* Prevent concurrent scaling operations */ - spin_lock(&ses->ses_lock); - if (ses->flags & CIFS_SES_FLAG_SCALE_CHANNELS) { - spin_unlock(&ses->ses_lock); - mutex_unlock(&ses->session_mutex); - return -EINVAL; - } - ses->flags |= CIFS_SES_FLAG_SCALE_CHANNELS; - spin_unlock(&ses->ses_lock); mutex_unlock(&ses->session_mutex); - rc = smb3_update_ses_channels(ses, ses->server, - false /* from_reconnect */, - false /* disable_mchan */); + smb3_update_ses_channels(ses, ses->server, + false /* from_reconnect */, + false /* disable_mchan */); /* Clear scaling flag after operation */ spin_lock(&ses->ses_lock); @@ -1166,16 +1213,12 @@ static int smb3_reconfigure(struct fs_context *fc) mutex_unlock(&ses->session_mutex); } - STEAL_STRING(cifs_sb, ctx, domainname); - STEAL_STRING(cifs_sb, ctx, nodename); - STEAL_STRING(cifs_sb, ctx, iocharset); - - /* if rsize or wsize not passed in on remount, use previous values */ - ctx->rsize = rsize ? CIFS_ALIGN_RSIZE(fc, rsize) : cifs_sb->ctx->rsize; - ctx->wsize = wsize ? CIFS_ALIGN_WSIZE(fc, wsize) : cifs_sb->ctx->wsize; - smb3_cleanup_fs_context_contents(cifs_sb->ctx); - rc = smb3_fs_context_dup(cifs_sb->ctx, ctx); + memcpy(cifs_sb->ctx, new_ctx, sizeof(*new_ctx)); + kfree(new_ctx); + new_ctx = NULL; + smb3_cleanup_fs_context(old_ctx); + old_ctx = NULL; smb3_update_mnt_flags(cifs_sb); #ifdef CONFIG_CIFS_DFS_UPCALL if (!rc) @@ -1183,6 +1226,18 @@ static int smb3_reconfigure(struct fs_context *fc) #endif return rc; + +cleanup_new_ctx: + smb3_cleanup_fs_context_contents(new_ctx); +restore_ctx: + kfree(new_ctx); + kfree_sensitive(new_password); + kfree_sensitive(new_password2); + smb3_cleanup_fs_context_contents(cifs_sb->ctx); + memcpy(cifs_sb->ctx, old_ctx, sizeof(*old_ctx)); + kfree(old_ctx); + + return rc; } static int smb3_fs_context_parse_param(struct fs_context *fc, diff --git a/fs/smb/client/smb2file.c b/fs/smb/client/smb2file.c index b292aa94a593..6860eff31693 100644 --- a/fs/smb/client/smb2file.c +++ b/fs/smb/client/smb2file.c @@ -49,6 +49,9 @@ static struct smb2_symlink_err_rsp *symlink_data(const struct kvec *iov) __func__, le32_to_cpu(p->ErrorId)); len = ALIGN(le32_to_cpu(p->ErrorDataLength), 8); + if (len > end - ((u8 *)p + sizeof(*p))) + return ERR_PTR(-EINVAL); + p = (struct smb2_error_context_rsp *)(p->ErrorContextData + len); } } else if (le32_to_cpu(err->ByteCount) >= sizeof(*sym) && diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index e6cb9b144530..3738204984f5 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -4721,6 +4721,7 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, { unsigned int data_offset; unsigned int data_len; + unsigned int end_off; unsigned int cur_off; unsigned int cur_page_idx; unsigned int pad_len; @@ -4836,7 +4837,8 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, } rdata->got_bytes = buffer_len; - } else if (buf_len >= data_offset + data_len) { + } else if (!check_add_overflow(data_offset, data_len, &end_off) && + buf_len >= end_off) { /* read response payload is in buf */ WARN_ONCE(buffer, "read data can be either in buf or in buffer"); copied = copy_to_iter(buf + data_offset, data_len, &rdata->subreq.io_iter); diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index 05f8099047e1..fdf4e50c27ce 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -1158,7 +1158,7 @@ int cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) { int length, len; - unsigned int data_offset, data_len; + unsigned int data_offset, data_len, end_off; struct cifs_io_subrequest *rdata = mid->callback_data; char *buf = server->smallbuf; unsigned int buflen = server->pdu_size; @@ -1256,11 +1256,14 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) use_rdma_mr = rdata->mr; #endif data_len = server->ops->read_data_length(buf, use_rdma_mr); - if (!use_rdma_mr && (data_offset + data_len > buflen)) { - /* data_len is corrupt -- discard frame */ - rdata->result = smb_EIO2(smb_eio_trace_read_rsp_malformed, - data_offset + data_len, buflen); - return cifs_readv_discard(server, mid); + if (!use_rdma_mr) { + if (check_add_overflow(data_offset, data_len, &end_off) || + end_off > buflen) { + /* data_len is corrupt -- discard frame */ + rdata->result = smb_EIO2(smb_eio_trace_read_rsp_malformed, + end_off, buflen); + return cifs_readv_discard(server, mid); + } } #ifdef CONFIG_CIFS_SMB_DIRECT diff --git a/fs/smb/common/fscc.h b/fs/smb/common/fscc.h index b4ccddca9256..bc3012cc295d 100644 --- a/fs/smb/common/fscc.h +++ b/fs/smb/common/fscc.h @@ -260,12 +260,12 @@ typedef struct { char FileName[]; } __packed FILE_DIRECTORY_INFO; /* level 0x101 FF resp data */ -/* See MS-FSCC 2.4.13 */ +/* See MS-FSCC 2.4.14 */ struct smb2_file_eof_info { /* encoding of request for level 10 */ __le64 EndOfFile; /* new end of file value */ } __packed; /* level 20 Set */ -/* See MS-FSCC 2.4.14 */ +/* See MS-FSCC 2.4.15 */ typedef struct { __le32 NextEntryOffset; __u32 FileIndex; diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h index a4b12eb8df81..aeb0a245c532 100644 --- a/fs/smb/common/smb2pdu.h +++ b/fs/smb/common/smb2pdu.h @@ -1566,6 +1566,10 @@ struct validate_negotiate_info_rsp { #define FILE_STANDARD_LINK_INFORMATION 54 #define FILE_ID_INFORMATION 59 #define FILE_ID_EXTD_DIRECTORY_INFORMATION 60 /* also for QUERY_DIR */ +#define FileId64ExtdDirectoryInformation 78 /* also for QUERY_DIR */ +#define FileId64ExtdBothDirectoryInformation 79 /* also for QUERY_DIR */ +#define FileIdAllExtdDirectoryInformation 80 /* also for QUERY_DIR */ +#define FileIdAllExtdBothDirectoryInformation 81 /* also for QUERY_DIR */ /* Used for Query Info and Find File POSIX Info for SMB3.1.1 and SMB1 */ #define SMB_FIND_FILE_POSIX_INFO 0x064 diff --git a/fs/smb/smbdirect/connection.c b/fs/smb/smbdirect/connection.c index fe9912e53da6..8adf58097534 100644 --- a/fs/smb/smbdirect/connection.c +++ b/fs/smb/smbdirect/connection.c @@ -2168,7 +2168,7 @@ static ssize_t smbdirect_map_sges_from_iter(struct iov_iter *iter, size_t len, if (ret < 0) { while (state->num_sge > before) { - struct ib_sge *sge = &state->sge[state->num_sge--]; + struct ib_sge *sge = &state->sge[--state->num_sge]; ib_dma_unmap_page(state->device, sge->addr, diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c index 80ba94f51e5c..aecbab61014c 100644 --- a/fs/xfs/libxfs/xfs_dir2_data.c +++ b/fs/xfs/libxfs/xfs_dir2_data.c @@ -382,6 +382,7 @@ xfs_dir3_data_write_verify( struct xfs_mount *mp = bp->b_mount; struct xfs_buf_log_item *bip = bp->b_log_item; struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr; + struct xfs_dir3_data_hdr *datahdr3 = bp->b_addr; xfs_failaddr_t fa; fa = xfs_dir3_data_verify(bp); @@ -396,6 +397,11 @@ xfs_dir3_data_write_verify( if (bip) hdr3->lsn = cpu_to_be64(bip->bli_item.li_lsn); + /* + * Zero padding that may be stale from old kernels. + */ + datahdr3->pad = 0; + xfs_buf_update_cksum(bp, XFS_DIR3_DATA_CRC_OFF); } @@ -728,7 +734,6 @@ xfs_dir3_data_init( struct xfs_dir2_data_unused *dup; struct xfs_dir2_data_free *bf; int error; - int i; /* * Get the buffer set up for the block. @@ -741,13 +746,16 @@ xfs_dir3_data_init( xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DIR_DATA_BUF); /* - * Initialize the header. + * Initialize the whole directory header region to zero + * so that all padding, bestfree entries, and any + * future header fields are clean. */ hdr = bp->b_addr; + memset(hdr, 0, geo->data_entry_offset); + if (xfs_has_crc(mp)) { struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr; - memset(hdr3, 0, sizeof(*hdr3)); hdr3->magic = cpu_to_be32(XFS_DIR3_DATA_MAGIC); hdr3->blkno = cpu_to_be64(xfs_buf_daddr(bp)); hdr3->owner = cpu_to_be64(args->owner); @@ -759,10 +767,6 @@ xfs_dir3_data_init( bf = xfs_dir2_data_bestfree_p(mp, hdr); bf[0].offset = cpu_to_be16(geo->data_entry_offset); bf[0].length = cpu_to_be16(geo->blksize - geo->data_entry_offset); - for (i = 1; i < XFS_DIR2_DATA_FD_COUNT; i++) { - bf[i].length = 0; - bf[i].offset = 0; - } /* * Set up an unused entry for the block's body. diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 40c7f0ff6cf3..0ec6ccd8b4dc 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -1414,8 +1414,7 @@ xfs_refcount_finish_one( if (rcur == NULL) { struct xfs_perag *pag = to_perag(ri->ri_group); - error = xfs_alloc_read_agf(pag, tp, - XFS_ALLOC_FLAG_FREEING, &agbp); + error = xfs_alloc_read_agf(pag, tp, 0, &agbp); if (error) return error; diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index 20e63069088b..3d40cb0b2496 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -251,6 +251,17 @@ xchk_ino_set_preen( trace_xchk_ino_preen(sc, ino, __return_address); } +/* Record a block indexed by a file fork that could be optimized. */ +void +xchk_fblock_set_preen( + struct xfs_scrub *sc, + int whichfork, + xfs_fileoff_t offset) +{ + sc->sm->sm_flags |= XFS_SCRUB_OFLAG_PREEN; + trace_xchk_fblock_preen(sc, whichfork, offset, __return_address); +} + /* Record something being wrong with the filesystem primary superblock. */ void xchk_set_corrupt( diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index f2ecc68538f0..b494d747c008 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -25,6 +25,8 @@ bool xchk_fblock_xref_process_error(struct xfs_scrub *sc, void xchk_block_set_preen(struct xfs_scrub *sc, struct xfs_buf *bp); void xchk_ino_set_preen(struct xfs_scrub *sc, xfs_ino_t ino); +void xchk_fblock_set_preen(struct xfs_scrub *sc, + int whichfork, xfs_fileoff_t offset); void xchk_set_corrupt(struct xfs_scrub *sc); void xchk_block_set_corrupt(struct xfs_scrub *sc, diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c index 1a71d36898b1..c2d6ad59d03e 100644 --- a/fs/xfs/scrub/dabtree.c +++ b/fs/xfs/scrub/dabtree.c @@ -454,7 +454,12 @@ xchk_da_btree_block( } } - /* XXX: Check hdr3.pad32 once we know how to fix it. */ + if (xfs_has_crc(ip->i_mount)) { + struct xfs_da3_node_hdr *nodehdr3 = blk->bp->b_addr; + + if (nodehdr3->__pad32) + xchk_da_set_preen(ds, level); + } break; default: xchk_da_set_corrupt(ds, level); diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c index e09724cd3725..09715a4aa154 100644 --- a/fs/xfs/scrub/dir.c +++ b/fs/xfs/scrub/dir.c @@ -492,7 +492,12 @@ xchk_directory_data_bestfree( goto out; xchk_buffer_recheck(sc, bp); - /* XXX: Check xfs_dir3_data_hdr.pad is zero once we start setting it. */ + if (xfs_has_crc(sc->mp)) { + struct xfs_dir3_data_hdr *hdr3 = bp->b_addr; + + if (hdr3->pad) + xchk_fblock_set_preen(sc, XFS_DATA_FORK, lblk); + } if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) goto out_buf; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index beaa26ec62da..9978ac1422fc 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -699,12 +699,6 @@ xfs_create( */ error = xfs_trans_alloc_icreate(mp, tres, udqp, gdqp, pdqp, resblks, &tp); - if (error == -ENOSPC) { - /* flush outstanding delalloc blocks and retry */ - xfs_flush_inodes(mp); - error = xfs_trans_alloc_icreate(mp, tres, udqp, gdqp, pdqp, - resblks, &tp); - } if (error) goto out_parent; diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c index 64c8afb935c2..b994ff15d5e4 100644 --- a/fs/xfs/xfs_notify_failure.c +++ b/fs/xfs/xfs_notify_failure.c @@ -350,7 +350,7 @@ xfs_dax_notify_dev_failure( /* * Shutdown fs from a force umount in pre-remove case which won't fail, * so errors can be ignored. Otherwise, shutdown the filesystem with - * CORRUPT flag if error occured or notify.want_shutdown was set during + * CORRUPT flag if error occurred or notify.want_shutdown was set during * RMAP querying. */ if (mf_flags & MF_MEM_PRE_REMOVE) diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index bcc470f56e46..148cc32449c1 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -1199,10 +1199,21 @@ xfs_trans_alloc_icreate( { struct xfs_trans *tp; bool retried = false; + bool flushed = false; int error; retry: error = xfs_trans_alloc(mp, resv, dblocks, 0, 0, &tp); + if (error == -ENOSPC && !flushed) { + /* + * Flush all delalloc blocks to reclaim space from speculative + * preallocation. This is similar to the quota retry below + * but targets FS-wide ENOSPC. + */ + xfs_flush_inodes(mp); + flushed = true; + goto retry; + } if (error) return error; diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c index a851b98143c0..5e297b75a85f 100644 --- a/fs/xfs/xfs_zone_alloc.c +++ b/fs/xfs/xfs_zone_alloc.c @@ -1170,7 +1170,7 @@ xfs_calc_open_zones( if (bdev_open_zones && bdev_open_zones < mp->m_max_open_zones) { mp->m_max_open_zones = bdev_open_zones; - xfs_info(mp, "limiting open zones to %u due to hardware limit.\n", + xfs_info(mp, "limiting open zones to %u due to hardware limit.", bdev_open_zones); } @@ -1217,7 +1217,7 @@ xfs_alloc_zone_info( return zi; out_free_bitmaps: - while (--i > 0) + while (--i >= 0) kvfree(zi->zi_used_bucket_bitmap[i]); kfree(zi); return NULL; diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c index fedcc47048af..c8a1d5c0332c 100644 --- a/fs/xfs/xfs_zone_gc.c +++ b/fs/xfs/xfs_zone_gc.c @@ -1221,7 +1221,7 @@ out_put_oz: if (data->oz) xfs_open_zone_put(data->oz); out_free_gc_data: - kfree(data); + xfs_zone_gc_data_free(data); return error; } diff --git a/include/asm-generic/kprobes.h b/include/asm-generic/kprobes.h index 060eab094e5a..5290a2b2e15a 100644 --- a/include/asm-generic/kprobes.h +++ b/include/asm-generic/kprobes.h @@ -14,7 +14,7 @@ static unsigned long __used \ _kbl_addr_##fname = (unsigned long)fname; # define NOKPROBE_SYMBOL(fname) __NOKPROBE_SYMBOL(fname) /* Use this to forbid a kprobes attach on very low level functions */ -# define __kprobes __section(".kprobes.text") +# define __kprobes notrace __section(".kprobes.text") # define nokprobe_inline __always_inline #else # define NOKPROBE_SYMBOL(fname) diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 50b47eba7d01..e7195750d21b 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -105,6 +105,12 @@ ARM_SMCCC_SMC_32, \ 0, 0x3fff) +/* C1-Pro erratum 4193714: SME DVMSync early acknowledgement */ +#define ARM_SMCCC_CPU_WORKAROUND_4193714 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_CPU, 0x10) + #define ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID \ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ ARM_SMCCC_SMC_32, \ diff --git a/include/linux/bio.h b/include/linux/bio.h index 97d747320b35..dc17780d6c1e 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -475,7 +475,8 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty); extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); -int bio_iov_iter_bounce(struct bio *bio, struct iov_iter *iter, size_t maxlen); +int bio_iov_iter_bounce(struct bio *bio, struct iov_iter *iter, size_t maxlen, + size_t minsize); void bio_iov_iter_unbounce(struct bio *bio, bool is_error, bool mark_dirty); extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter, diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h index 0a3bcd1718f3..be1b38c981d4 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -94,6 +94,7 @@ int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num); int register_fprobe_syms(struct fprobe *fp, const char **syms, int num); int unregister_fprobe(struct fprobe *fp); +int unregister_fprobe_async(struct fprobe *fp); bool fprobe_is_registered(struct fprobe *fp); int fprobe_count_ips_from_filter(const char *filter, const char *notfilter); #else @@ -113,6 +114,10 @@ static inline int unregister_fprobe(struct fprobe *fp) { return -EOPNOTSUPP; } +static inline int unregister_fprobe_async(struct fprobe *fp) +{ + return -EOPNOTSUPP; +} static inline bool fprobe_is_registered(struct fprobe *fp) { return false; diff --git a/include/linux/hid.h b/include/linux/hid.h index 442a80d79e89..bfb9859f391e 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -1030,6 +1030,8 @@ struct hid_field *hid_find_field(struct hid_device *hdev, unsigned int report_ty int hid_set_field(struct hid_field *, unsigned, __s32); int hid_input_report(struct hid_device *hid, enum hid_report_type type, u8 *data, u32 size, int interrupt); +int hid_safe_input_report(struct hid_device *hid, enum hid_report_type type, u8 *data, + size_t bufsize, u32 size, int interrupt); struct hid_field *hidinput_get_led_field(struct hid_device *hid); unsigned int hidinput_count_leds(struct hid_device *hid); __s32 hidinput_calc_abs_res(const struct hid_field *field, __u16 code); @@ -1298,8 +1300,8 @@ static inline u32 hid_report_len(struct hid_report *report) return DIV_ROUND_UP(report->size, 8) + (report->id > 0); } -int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *data, u32 size, - int interrupt); +int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *data, + size_t bufsize, u32 size, int interrupt); /* HID quirks API */ unsigned long hid_lookup_quirk(const struct hid_device *hdev); diff --git a/include/linux/hid_bpf.h b/include/linux/hid_bpf.h index a2e47dbcf82c..19fffa4574a4 100644 --- a/include/linux/hid_bpf.h +++ b/include/linux/hid_bpf.h @@ -72,8 +72,8 @@ struct hid_ops { int (*hid_hw_output_report)(struct hid_device *hdev, __u8 *buf, size_t len, u64 source, bool from_bpf); int (*hid_input_report)(struct hid_device *hid, enum hid_report_type type, - u8 *data, u32 size, int interrupt, u64 source, bool from_bpf, - bool lock_already_taken); + u8 *data, size_t bufsize, u32 size, int interrupt, u64 source, + bool from_bpf, bool lock_already_taken); struct module *owner; const struct bus_type *bus_type; }; @@ -200,7 +200,8 @@ struct hid_bpf { #ifdef CONFIG_HID_BPF u8 *dispatch_hid_bpf_device_event(struct hid_device *hid, enum hid_report_type type, u8 *data, - u32 *size, int interrupt, u64 source, bool from_bpf); + size_t *buf_size, u32 *size, int interrupt, u64 source, + bool from_bpf); int dispatch_hid_bpf_raw_requests(struct hid_device *hdev, unsigned char reportnum, __u8 *buf, u32 size, enum hid_report_type rtype, @@ -215,8 +216,11 @@ int hid_bpf_device_init(struct hid_device *hid); const u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, const u8 *rdesc, unsigned int *size); #else /* CONFIG_HID_BPF */ static inline u8 *dispatch_hid_bpf_device_event(struct hid_device *hid, enum hid_report_type type, - u8 *data, u32 *size, int interrupt, - u64 source, bool from_bpf) { return data; } + u8 *data, size_t *buf_size, u32 *size, + int interrupt, u64 source, bool from_bpf) +{ + return data; +} static inline int dispatch_hid_bpf_raw_requests(struct hid_device *hdev, unsigned char reportnum, u8 *buf, u32 size, enum hid_report_type rtype, diff --git a/include/linux/intel_tpmi.h b/include/linux/intel_tpmi.h index 94c06bf214fb..15f02422e9ca 100644 --- a/include/linux/intel_tpmi.h +++ b/include/linux/intel_tpmi.h @@ -28,6 +28,12 @@ enum intel_tpmi_id { TPMI_INFO_ID = 0x81, /* Special ID for PCI BDF and Package ID information */ }; +#define TPMI_CORE_INIT 0 +#define TPMI_CORE_EXIT 1 + +int tpmi_register_notifier(struct notifier_block *nb); +int tpmi_unregister_notifier(struct notifier_block *nb); + struct oobmsm_plat_info *tpmi_get_platform_data(struct auxiliary_device *auxdev); struct resource *tpmi_get_resource_at_index(struct auxiliary_device *auxdev, int index); int tpmi_get_resource_count(struct auxiliary_device *auxdev); diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index a81b46af5118..5a1c5c336fa4 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -305,9 +305,11 @@ struct xt_counters *xt_counters_alloc(unsigned int counters); struct xt_table *xt_register_table(struct net *net, const struct xt_table *table, + const struct nf_hook_ops *template_ops, struct xt_table_info *bootstrap, struct xt_table_info *newinfo); -void *xt_unregister_table(struct xt_table *table); +void xt_unregister_table_pre_exit(struct net *net, u8 af, const char *name); +struct xt_table *xt_unregister_table_exit(struct net *net, u8 af, const char *name); struct xt_table_info *xt_replace_table(struct xt_table *table, unsigned int num_counters, diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index a40aaf645fa4..05631a25e622 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -53,7 +53,6 @@ int arpt_register_table(struct net *net, const struct xt_table *table, const struct arpt_replace *repl, const struct nf_hook_ops *ops); void arpt_unregister_table(struct net *net, const char *name); -void arpt_unregister_table_pre_exit(struct net *net, const char *name); extern unsigned int arpt_do_table(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index 132b0e4a6d4d..13593391d605 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -26,7 +26,6 @@ int ipt_register_table(struct net *net, const struct xt_table *table, const struct ipt_replace *repl, const struct nf_hook_ops *ops); -void ipt_unregister_table_pre_exit(struct net *net, const char *name); void ipt_unregister_table_exit(struct net *net, const char *name); /* Standard entry. */ diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 8b8885a73c76..c6d5b927830d 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -27,7 +27,6 @@ extern void *ip6t_alloc_initial_table(const struct xt_table *); int ip6t_register_table(struct net *net, const struct xt_table *table, const struct ip6t_replace *repl, const struct nf_hook_ops *ops); -void ip6t_unregister_table_pre_exit(struct net *net, const char *name); void ip6t_unregister_table_exit(struct net *net, const char *name); extern unsigned int ip6t_do_table(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); diff --git a/include/linux/sched.h b/include/linux/sched.h index 368c7b4d7cb5..ee06cba5c6f5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1002,6 +1002,9 @@ struct task_struct { unsigned sched_rt_mutex:1; #endif + /* Save user-dumpable when mm goes away */ + unsigned user_dumpable:1; + /* Bit to tell TOMOYO we're in execve(): */ unsigned in_execve:1; unsigned in_iowait:1; diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index 1198138cb839..273538200a44 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -33,6 +33,15 @@ struct root_domain; extern void dl_add_task_root_domain(struct task_struct *p); extern void dl_clear_root_domain(struct root_domain *rd); extern void dl_clear_root_domain_cpu(int cpu); +/* + * Return whether moving DL task @p to @new_mask requires moving DL + * bandwidth accounting between root domains. This helper is specific to + * DL bandwidth move accounting semantics and is shared by + * cpuset_can_attach() and set_cpus_allowed_dl() so both paths use the + * same source root-domain test. + */ +extern bool dl_task_needs_bw_move(struct task_struct *p, + const struct cpumask *new_mask); extern u64 dl_cookie; extern bool dl_bw_visited(int cpu, u64 cookie); diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index adb9a4de068a..2129e18ada58 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -101,24 +101,27 @@ enum scx_ent_flags { SCX_TASK_DEQD_FOR_SLEEP = 1 << 3, /* last dequeue was for SLEEP */ SCX_TASK_SUB_INIT = 1 << 4, /* task being initialized for a sub sched */ SCX_TASK_IMMED = 1 << 5, /* task is on local DSQ with %SCX_ENQ_IMMED */ - SCX_TASK_OFF_TASKS = 1 << 6, /* removed from scx_tasks by sched_ext_dead() */ /* - * Bits 8 and 9 are used to carry task state: + * Bits 8 to 10 are used to carry task state: * * NONE ops.init_task() not called yet + * INIT_BEGIN ops.init_task() in flight; see sched_ext_dead() * INIT ops.init_task() succeeded, but task can be cancelled * READY fully initialized, but not in sched_ext * ENABLED fully initialized and in sched_ext + * DEAD terminal state set by sched_ext_dead() */ - SCX_TASK_STATE_SHIFT = 8, /* bits 8 and 9 are used to carry task state */ - SCX_TASK_STATE_BITS = 2, + SCX_TASK_STATE_SHIFT = 8, + SCX_TASK_STATE_BITS = 3, SCX_TASK_STATE_MASK = ((1 << SCX_TASK_STATE_BITS) - 1) << SCX_TASK_STATE_SHIFT, SCX_TASK_NONE = 0 << SCX_TASK_STATE_SHIFT, - SCX_TASK_INIT = 1 << SCX_TASK_STATE_SHIFT, - SCX_TASK_READY = 2 << SCX_TASK_STATE_SHIFT, - SCX_TASK_ENABLED = 3 << SCX_TASK_STATE_SHIFT, + SCX_TASK_INIT_BEGIN = 1 << SCX_TASK_STATE_SHIFT, + SCX_TASK_INIT = 2 << SCX_TASK_STATE_SHIFT, + SCX_TASK_READY = 3 << SCX_TASK_STATE_SHIFT, + SCX_TASK_ENABLED = 4 << SCX_TASK_STATE_SHIFT, + SCX_TASK_DEAD = 5 << SCX_TASK_STATE_SHIFT, /* * Bits 12 and 13 are used to carry reenqueue reason. In addition to diff --git a/include/linux/slab.h b/include/linux/slab.h index 15a60b501b95..2b5ab488e96b 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -1234,6 +1234,9 @@ void *kvrealloc_node_align_noprof(const void *p, size_t size, unsigned long alig extern void kvfree(const void *addr); DEFINE_FREE(kvfree, void *, if (!IS_ERR_OR_NULL(_T)) kvfree(_T)) +extern void kvfree_atomic(const void *addr); +DEFINE_FREE(kvfree_atomic, void *, if (!IS_ERR_OR_NULL(_T)) kvfree_atomic(_T)) + extern void kvfree_sensitive(const void *addr, size_t len); unsigned int kmem_cache_size(struct kmem_cache *s); diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 2ebba746c18f..89165b769e5c 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -21,7 +21,7 @@ #define VFIO_PCI_CORE_H #define VFIO_PCI_OFFSET_SHIFT 40 -#define VFIO_PCI_OFFSET_TO_INDEX(off) (off >> VFIO_PCI_OFFSET_SHIFT) +#define VFIO_PCI_OFFSET_TO_INDEX(off) ((u64)(off) >> VFIO_PCI_OFFSET_SHIFT) #define VFIO_PCI_INDEX_TO_OFFSET(index) ((u64)(index) << VFIO_PCI_OFFSET_SHIFT) #define VFIO_PCI_OFFSET_MASK (((u64)(1) << VFIO_PCI_OFFSET_SHIFT) - 1) diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 7b84f2cef8b1..d70510ac31ab 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -489,8 +489,10 @@ genlmsg_multicast_netns_filtered(const struct genl_family *family, netlink_filter_fn filter, void *filter_data) { - if (WARN_ON_ONCE(group >= family->n_mcgrps)) + if (WARN_ON_ONCE(group >= family->n_mcgrps)) { + nlmsg_free(skb); return -EINVAL; + } group = family->mcgrp_offset + group; return nlmsg_multicast_filtered(net->genl_sock, skb, portid, group, flags, filter, filter_data); diff --git a/include/net/macsec.h b/include/net/macsec.h index bc7de5b53e54..d962093ee923 100644 --- a/include/net/macsec.h +++ b/include/net/macsec.h @@ -9,6 +9,7 @@ #include <linux/u64_stats_sync.h> #include <linux/if_vlan.h> +#include <linux/workqueue.h> #include <uapi/linux/if_link.h> #include <uapi/linux/if_macsec.h> @@ -123,6 +124,7 @@ struct macsec_dev_stats { * @key: key structure * @ssci: short secure channel identifier * @stats: per-SA stats + * @destroy_work: deferred work to free the SA in process context after RCU grace period */ struct macsec_rx_sa { struct macsec_key key; @@ -136,7 +138,7 @@ struct macsec_rx_sa { bool active; struct macsec_rx_sa_stats __percpu *stats; struct macsec_rx_sc *sc; - struct rcu_head rcu; + struct rcu_work destroy_work; }; struct pcpu_rx_sc_stats { @@ -174,6 +176,7 @@ struct macsec_rx_sc { * @key: key structure * @ssci: short secure channel identifier * @stats: per-SA stats + * @destroy_work: deferred work to free the SA in process context after RCU grace period */ struct macsec_tx_sa { struct macsec_key key; @@ -186,7 +189,7 @@ struct macsec_tx_sa { refcount_t refcnt; bool active; struct macsec_tx_sa_stats __percpu *stats; - struct rcu_head rcu; + struct rcu_work destroy_work; }; /** diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index e9a8350e7ccf..80f50fd0f7ad 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -45,9 +45,12 @@ struct nf_conntrack_expect { void (*expectfn)(struct nf_conn *new, struct nf_conntrack_expect *this); - /* Helper to assign to new connection */ + /* Helper that created this expectation */ struct nf_conntrack_helper __rcu *helper; + /* Helper to assign to new connection */ + struct nf_conntrack_helper __rcu *assign_helper; + /* The conntrack of the master connection */ struct nf_conn *master; diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 499e4288170f..875916d60bfe 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -119,6 +119,7 @@ struct netns_ipv6 { struct fib_notifier_ops *notifier_ops; struct fib_notifier_ops *ip6mr_notifier_ops; atomic_t ipmr_seq; + int flowlabel_count; struct { struct hlist_head head; spinlock_t lock; diff --git a/include/net/nsh.h b/include/net/nsh.h index 16a751093896..15a26c590815 100644 --- a/include/net/nsh.h +++ b/include/net/nsh.h @@ -247,10 +247,10 @@ struct nshhdr { #define NSH_M_TYPE1_LEN 24 /* NSH header maximum Length. */ -#define NSH_HDR_MAX_LEN 256 +#define NSH_HDR_MAX_LEN ((NSH_LEN_MASK >> NSH_LEN_SHIFT) * 4) /* NSH context headers maximum Length. */ -#define NSH_CTX_HDRS_MAX_LEN 248 +#define NSH_CTX_HDRS_MAX_LEN (NSH_HDR_MAX_LEN - NSH_BASE_HDR_LEN) static inline struct nshhdr *nsh_hdr(struct sk_buff *skb) { diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 8ad7a2d76c1d..ec1df8b94517 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -771,10 +771,8 @@ TRACE_EVENT(btrfs_sync_file, TP_fast_assign( struct dentry *dentry = file_dentry(file); struct inode *inode = file_inode(file); - struct dentry *parent = dget_parent(dentry); - struct inode *parent_inode = d_inode(parent); + struct inode *parent_inode = d_inode(dentry->d_parent); - dput(parent); TP_fast_assign_fsid(btrfs_sb(inode->i_sb)); __entry->ino = btrfs_ino(BTRFS_I(inode)); __entry->parent = btrfs_ino(BTRFS_I(parent_inode)); diff --git a/include/xen/arm/interface.h b/include/xen/arm/interface.h index c3eada2642aa..61360b89da40 100644 --- a/include/xen/arm/interface.h +++ b/include/xen/arm/interface.h @@ -30,7 +30,7 @@ #define __HYPERVISOR_platform_op_raw __HYPERVISOR_platform_op -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ /* Explicitly size integers that represent pfns in the interface with * Xen so that we can have one ABI that works for 32 and 64 bit guests. * Note that this means that the xen_pfn_t type may be capable of diff --git a/io_uring/cancel.c b/io_uring/cancel.c index 5e5eb9cfc7cd..4aa3103ba9c3 100644 --- a/io_uring/cancel.c +++ b/io_uring/cancel.c @@ -561,8 +561,8 @@ __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx, ret |= io_waitid_remove_all(ctx, tctx, cancel_all); ret |= io_futex_remove_all(ctx, tctx, cancel_all); ret |= io_uring_try_cancel_uring_cmd(ctx, tctx, cancel_all); - mutex_unlock(&ctx->uring_lock); ret |= io_kill_timeouts(ctx, tctx, cancel_all); + mutex_unlock(&ctx->uring_lock); if (tctx) ret |= io_run_task_work() > 0; else diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c index c2d3e45544bb..001fb542dc11 100644 --- a/io_uring/fdinfo.c +++ b/io_uring/fdinfo.c @@ -190,8 +190,9 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) get_task_struct(tsk); rcu_read_unlock(); usec = io_sq_cpu_usec(tsk); + sq_pid = task_pid_nr_ns(tsk, + proc_pid_ns(file_inode(m->file)->i_sb)); put_task_struct(tsk); - sq_pid = sq->task_pid; sq_cpu = sq->sq_cpu; sq_total_time = usec; sq_work_time = sq->work_time; diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 7a9f94a0ce6f..8cc7b47d3089 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -1124,7 +1124,8 @@ static inline void io_wq_remove_pending(struct io_wq *wq, if (io_wq_is_hashed(work) && work == wq->hash_tail[hash]) { if (prev) prev_work = container_of(prev, struct io_wq_work, list); - if (prev_work && io_get_work_hash(prev_work) == hash) + if (prev_work && io_wq_is_hashed(prev_work) && + io_get_work_hash(prev_work) == hash) wq->hash_tail[hash] = prev_work; else wq->hash_tail[hash] = NULL; diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 4ed998d60c09..036145ee466c 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -687,12 +687,26 @@ static struct io_overflow_cqe *io_alloc_ocqe(struct io_ring_ctx *ctx, } /* + * Compute queued CQEs for free-space calculation, clamped to cq_entries. + */ +static unsigned int io_cqring_queued(struct io_ring_ctx *ctx) +{ + struct io_rings *rings = io_get_rings(ctx); + int diff; + + diff = (int)(ctx->cached_cq_tail - READ_ONCE(rings->cq.head)); + if (diff >= 0) + return min((unsigned int)diff, ctx->cq_entries); + return 0; +} + +/* * Fill an empty dummy CQE, in case alignment is off for posting a 32b CQE * because the ring is a single 16b entry away from wrapping. */ static bool io_fill_nop_cqe(struct io_ring_ctx *ctx, unsigned int off) { - if (__io_cqring_events(ctx) < ctx->cq_entries) { + if (io_cqring_queued(ctx) < ctx->cq_entries) { struct io_uring_cqe *cqe = &ctx->rings->cqes[off]; cqe->user_data = 0; @@ -713,7 +727,7 @@ bool io_cqe_cache_refill(struct io_ring_ctx *ctx, bool overflow, bool cqe32) { struct io_rings *rings = ctx->rings; unsigned int off = ctx->cached_cq_tail & (ctx->cq_entries - 1); - unsigned int free, queued, len; + unsigned int free, len; /* * Posting into the CQ when there are pending overflowed CQEs may break @@ -733,9 +747,7 @@ bool io_cqe_cache_refill(struct io_ring_ctx *ctx, bool overflow, bool cqe32) off = 0; } - /* userspace may cheat modifying the tail, be safe and do min */ - queued = min(__io_cqring_events(ctx), ctx->cq_entries); - free = ctx->cq_entries - queued; + free = ctx->cq_entries - io_cqring_queued(ctx); /* we need a contiguous range, limit based on the current array offset */ len = min(free, ctx->cq_entries - off); if (len < (cqe32 + 1)) @@ -1452,8 +1464,13 @@ struct io_wq_work *io_wq_free_work(struct io_wq_work *work) struct io_kiocb *nxt = NULL; if (req_ref_put_and_test_atomic(req)) { - if (req->flags & IO_REQ_LINK_FLAGS) + if (req->flags & IO_REQ_LINK_FLAGS) { + struct io_ring_ctx *ctx = req->ctx; + + mutex_lock(&ctx->uring_lock); nxt = io_req_find_next(req); + mutex_unlock(&ctx->uring_lock); + } io_free_req(req); } return nxt ? &nxt->work : NULL; diff --git a/io_uring/rw.c b/io_uring/rw.c index e729e0e7657e..0c4834645279 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -230,7 +230,7 @@ static inline void io_meta_restore(struct io_async_rw *io, struct kiocb *kiocb) } static int io_prep_rw_pi(struct io_kiocb *req, struct io_rw *rw, int ddir, - u64 attr_ptr, u64 attr_type_mask) + u64 attr_ptr) { struct io_uring_attr_pi pi_attr; struct io_async_rw *io; @@ -305,7 +305,7 @@ static int __io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, return -EINVAL; attr_ptr = READ_ONCE(sqe->attr_ptr); - return io_prep_rw_pi(req, rw, ddir, attr_ptr, attr_type_mask); + return io_prep_rw_pi(req, rw, ddir, attr_ptr); } return 0; } diff --git a/io_uring/timeout.c b/io_uring/timeout.c index e2595cae2b07..6353a4d979dc 100644 --- a/io_uring/timeout.c +++ b/io_uring/timeout.c @@ -284,6 +284,10 @@ static struct io_kiocb *__io_disarm_linked_timeout(struct io_kiocb *req, struct io_timeout *timeout = io_kiocb_to_cmd(link, struct io_timeout); io_remove_next_linked(req); + + /* If this is NULL, then timer already claimed it and will complete it */ + if (!timeout->head) + return NULL; timeout->head = NULL; if (hrtimer_try_to_cancel(&io->timer) != -1) { list_del(&timeout->list); @@ -367,6 +371,14 @@ static void io_req_task_link_timeout(struct io_tw_req tw_req, io_tw_token_t tw) int ret; if (prev) { + /* + * splice the linked timeout out of prev's chain if the regular + * completion path didn't already do it. + */ + if (prev->link == req) + prev->link = req->link; + req->link = NULL; + if (!tw.cancel) { struct io_cancel_data cd = { .ctx = req->ctx, @@ -401,10 +413,10 @@ static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) /* * We don't expect the list to be empty, that will only happen if we - * race with the completion of the linked work. + * race with the completion of the linked work. Splice of prev is + * done in io_req_task_link_timeout(), if needed. */ if (prev) { - io_remove_next_linked(prev); if (!req_ref_inc_not_zero(prev)) prev = NULL; } diff --git a/kernel/audit.c b/kernel/audit.c index e1d489bc2dff..34dc7cb246ff 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1468,6 +1468,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh, err = audit_list_rules_send(skb, seq); break; case AUDIT_TRIM: + if (audit_enabled == AUDIT_LOCKED) + return -EPERM; audit_trim_trees(); audit_log_common_recv_msg(audit_context(), &ab, AUDIT_CONFIG_CHANGE); @@ -1480,6 +1482,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh, size_t msglen = data_len; char *old, *new; + if (audit_enabled == AUDIT_LOCKED) + return -EPERM; err = -EINVAL; if (msglen < 2 * sizeof(u32)) break; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index ab54fccba215..abdf8da3be93 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -2786,7 +2786,7 @@ void __audit_log_capset(const struct cred *new, const struct cred *old) context->capset.pid = task_tgid_nr(current); context->capset.cap.effective = new->cap_effective; - context->capset.cap.inheritable = new->cap_effective; + context->capset.cap.inheritable = new->cap_inheritable; context->capset.cap.permitted = new->cap_permitted; context->capset.cap.ambient = new->cap_ambient; context->type = AUDIT_CAPSET; diff --git a/kernel/cgroup/cpuset-internal.h b/kernel/cgroup/cpuset-internal.h index bb4e692bea30..f7aaf01f7cd5 100644 --- a/kernel/cgroup/cpuset-internal.h +++ b/kernel/cgroup/cpuset-internal.h @@ -167,6 +167,7 @@ struct cpuset { */ int nr_deadline_tasks; int nr_migrate_dl_tasks; + /* DL bandwidth that needs destination reservation for this attach. */ u64 sum_migrate_dl_bw; /* * CPU used for temporary DL bandwidth allocation during attach; diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index e3a081a07c6d..5c33ab20cc20 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1718,7 +1718,8 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, */ if (is_partition_valid(parent)) adding = cpumask_and(tmp->addmask, - xcpus, parent->effective_xcpus); + cs->effective_xcpus, + parent->effective_xcpus); if (old_prs > 0) new_prs = -old_prs; @@ -2993,7 +2994,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) struct cpuset *cs, *oldcs; struct task_struct *task; bool setsched_check; - int ret; + int cpu, ret; /* used later by cpuset_attach() */ cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css)); @@ -3038,31 +3039,31 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) } if (dl_task(task)) { + /* + * Count all migrating DL tasks for cpuset task accounting. + * Only tasks that need a root-domain bandwidth move + * contribute to sum_migrate_dl_bw. + */ cs->nr_migrate_dl_tasks++; - cs->sum_migrate_dl_bw += task->dl.dl_bw; + if (dl_task_needs_bw_move(task, cs->effective_cpus)) + cs->sum_migrate_dl_bw += task->dl.dl_bw; } } - if (!cs->nr_migrate_dl_tasks) + if (!cs->sum_migrate_dl_bw) goto out_success; - if (!cpumask_intersects(oldcs->effective_cpus, cs->effective_cpus)) { - int cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus); - - if (unlikely(cpu >= nr_cpu_ids)) { - reset_migrate_dl_data(cs); - ret = -EINVAL; - goto out_unlock; - } + cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus); + if (unlikely(cpu >= nr_cpu_ids)) { + ret = -EINVAL; + goto out_unlock; + } - ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw); - if (ret) { - reset_migrate_dl_data(cs); - goto out_unlock; - } + ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw); + if (ret) + goto out_unlock; - cs->dl_bw_cpu = cpu; - } + cs->dl_bw_cpu = cpu; out_success: /* @@ -3070,7 +3071,10 @@ out_success: * changes which zero cpus/mems_allowed. */ cs->attach_in_progress++; + out_unlock: + if (ret) + reset_migrate_dl_data(cs); mutex_unlock(&cpuset_mutex); return ret; } @@ -4176,11 +4180,11 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) * current's mems_allowed, yes. If it's not a __GFP_HARDWALL request and this * node is set in the nearest hardwalled cpuset ancestor to current's cpuset, * yes. If current has access to memory reserves as an oom victim, yes. - * Otherwise, no. + * If the current task is PF_EXITING, yes. Otherwise, no. * * GFP_USER allocations are marked with the __GFP_HARDWALL bit, * and do not allow allocations outside the current tasks cpuset - * unless the task has been OOM killed. + * unless the task has been OOM killed or is exiting. * GFP_KERNEL allocations are not so marked, so can escape to the * nearest enclosing hardwalled ancestor cpuset. * @@ -4194,7 +4198,9 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) * The first call here from mm/page_alloc:get_page_from_freelist() * has __GFP_HARDWALL set in gfp_mask, enforcing hardwall cpusets, * so no allocation on a node outside the cpuset is allowed (unless - * in interrupt, of course). + * in interrupt, of course). The PF_EXITING check must therefore + * come before the __GFP_HARDWALL check, otherwise a dying task + * would be blocked on the fast path. * * The second pass through get_page_from_freelist() doesn't even call * here for GFP_ATOMIC calls. For those calls, the __alloc_pages() @@ -4204,6 +4210,7 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) * in_interrupt - any node ok (current task context irrelevant) * GFP_ATOMIC - any node ok * tsk_is_oom_victim - any node ok + * PF_EXITING - any node ok (let dying task exit quickly) * GFP_KERNEL - any node in enclosing hardwalled cpuset ok * GFP_USER - only nodes in current tasks mems allowed ok. */ @@ -4223,11 +4230,10 @@ bool cpuset_current_node_allowed(int node, gfp_t gfp_mask) */ if (unlikely(tsk_is_oom_victim(current))) return true; - if (gfp_mask & __GFP_HARDWALL) /* If hardwall request, stop here */ - return false; - if (current->flags & PF_EXITING) /* Let dying task have memory */ return true; + if (gfp_mask & __GFP_HARDWALL) /* If hardwall request, stop here */ + return false; /* Not hardwall and node outside mems_allowed: scan up cpusets */ spin_lock_irqsave(&callback_lock, flags); diff --git a/kernel/cgroup/dmem.c b/kernel/cgroup/dmem.c index 1ab1fb47f271..4753a67d0f0f 100644 --- a/kernel/cgroup/dmem.c +++ b/kernel/cgroup/dmem.c @@ -602,6 +602,7 @@ get_cg_pool_unlocked(struct dmemcg_state *cg, struct dmem_cgroup_region *region) pool = NULL; continue; } + pool = ERR_PTR(-ENOMEM); } } diff --git a/kernel/exit.c b/kernel/exit.c index 25e9cb6de7e7..f50d73c272d6 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -571,6 +571,7 @@ static void exit_mm(void) */ smp_mb__after_spinlock(); local_irq_disable(); + current->user_dumpable = (get_dumpable(mm) == SUID_DUMP_USER); current->mm = NULL; membarrier_update_current_mm(NULL); enter_lazy_tlb(mm, current); @@ -1073,6 +1074,7 @@ void __noreturn make_task_dead(int signr) futex_exit_recursive(tsk); tsk->exit_state = EXIT_DEAD; refcount_inc(&tsk->rcu_users); + preempt_disable(); do_task_dead(); } diff --git a/kernel/liveupdate/kexec_handover.c b/kernel/liveupdate/kexec_handover.c index 18509d8082ea..2592f7ca16e2 100644 --- a/kernel/liveupdate/kexec_handover.c +++ b/kernel/liveupdate/kexec_handover.c @@ -1707,7 +1707,7 @@ int kho_fill_kimage(struct kimage *image) int err = 0; struct kexec_buf scratch; - if (!kho_enable) + if (!kho_enable || image->type == KEXEC_TYPE_CRASH) return 0; image->kho.fdt = virt_to_phys(kho_out.fdt); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 68c17daef8d4..130043bfc209 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -272,11 +272,24 @@ static bool ptrace_has_cap(struct user_namespace *ns, unsigned int mode) return ns_capable(ns, CAP_SYS_PTRACE); } +static bool task_still_dumpable(struct task_struct *task, unsigned int mode) +{ + struct mm_struct *mm = task->mm; + if (mm) { + if (get_dumpable(mm) == SUID_DUMP_USER) + return true; + return ptrace_has_cap(mm->user_ns, mode); + } + + if (task->user_dumpable) + return true; + return ptrace_has_cap(&init_user_ns, mode); +} + /* Returns 0 on success, -errno on denial. */ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) { const struct cred *cred = current_cred(), *tcred; - struct mm_struct *mm; kuid_t caller_uid; kgid_t caller_gid; @@ -337,11 +350,8 @@ ok: * Pairs with a write barrier in commit_creds(). */ smp_rmb(); - mm = task->mm; - if (mm && - ((get_dumpable(mm) != SUID_DUMP_USER) && - !ptrace_has_cap(mm->user_ns, mode))) - return -EPERM; + if (!task_still_dumpable(task, mode)) + return -EPERM; return security_ptrace_access_check(task, mode); } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index edca7849b165..7db4c87df83b 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -3107,20 +3107,18 @@ static void task_woken_dl(struct rq *rq, struct task_struct *p) static void set_cpus_allowed_dl(struct task_struct *p, struct affinity_context *ctx) { - struct root_domain *src_rd; struct rq *rq; WARN_ON_ONCE(!dl_task(p)); rq = task_rq(p); - src_rd = rq->rd; /* * Migrating a SCHED_DEADLINE task between exclusive * cpusets (different root_domains) entails a bandwidth * update. We already made space for us in the destination * domain (see cpuset_can_attach()). */ - if (!cpumask_intersects(src_rd->span, ctx->new_mask)) { + if (dl_task_needs_bw_move(p, ctx->new_mask)) { struct dl_bw *src_dl_b; src_dl_b = dl_bw_of(cpu_of(rq)); @@ -3137,6 +3135,15 @@ static void set_cpus_allowed_dl(struct task_struct *p, set_cpus_allowed_common(p, ctx); } +bool dl_task_needs_bw_move(struct task_struct *p, + const struct cpumask *new_mask) +{ + if (!dl_task(p)) + return false; + + return !cpumask_intersects(task_rq(p)->rd->span, new_mask); +} + /* Assumes rq->lock is held */ static void rq_online_dl(struct rq *rq) { diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 38d90baf78cf..d3ce708991c3 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -297,7 +297,6 @@ static void scx_set_task_sched(struct task_struct *p, struct scx_sched *sch) #else /* CONFIG_EXT_SUB_SCHED */ static struct scx_sched *scx_parent(struct scx_sched *sch) { return NULL; } static struct scx_sched *scx_next_descendant_pre(struct scx_sched *pos, struct scx_sched *root) { return pos ? NULL : root; } -static struct scx_sched *scx_find_sub_sched(u64 cgroup_id) { return NULL; } static void scx_set_task_sched(struct task_struct *p, struct scx_sched *sch) {} #endif /* CONFIG_EXT_SUB_SCHED */ @@ -712,6 +711,51 @@ struct bpf_iter_scx_dsq { } __attribute__((aligned(8))); +static u32 scx_get_task_state(const struct task_struct *p) +{ + return p->scx.flags & SCX_TASK_STATE_MASK; +} + +static void scx_set_task_state(struct task_struct *p, u32 state) +{ + u32 prev_state = scx_get_task_state(p); + bool warn = false; + + switch (state) { + case SCX_TASK_NONE: + warn = prev_state == SCX_TASK_DEAD; + break; + case SCX_TASK_INIT_BEGIN: + warn = prev_state != SCX_TASK_NONE; + break; + case SCX_TASK_INIT: + warn = prev_state != SCX_TASK_INIT_BEGIN; + p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT; + break; + case SCX_TASK_READY: + warn = !(prev_state == SCX_TASK_INIT || + prev_state == SCX_TASK_ENABLED); + break; + case SCX_TASK_ENABLED: + warn = prev_state != SCX_TASK_READY; + break; + case SCX_TASK_DEAD: + warn = !(prev_state == SCX_TASK_NONE || + prev_state == SCX_TASK_INIT_BEGIN); + break; + default: + WARN_ONCE(1, "sched_ext: Invalid task state %d -> %d for %s[%d]", + prev_state, state, p->comm, p->pid); + return; + } + + WARN_ONCE(warn, "sched_ext: Invalid task state transition 0x%x -> 0x%x for %s[%d]", + prev_state, state, p->comm, p->pid); + + p->scx.flags &= ~SCX_TASK_STATE_MASK; + p->scx.flags |= state; +} + /* * SCX task iterator. */ @@ -937,11 +981,11 @@ static struct task_struct *scx_task_iter_next_locked(struct scx_task_iter *iter) /* * cgroup_task_dead() removes the dead tasks from cset->tasks * after sched_ext_dead() and cgroup iteration may see tasks - * which already finished sched_ext_dead(). %SCX_TASK_OFF_TASKS - * is set by sched_ext_dead() under @p's rq lock. Test it to + * which already finished sched_ext_dead(). %SCX_TASK_DEAD is + * set by sched_ext_dead() under @p's rq lock. Test it to * avoid visiting tasks which are already dead from SCX POV. */ - if (p->scx.flags & SCX_TASK_OFF_TASKS) { + if (scx_get_task_state(p) == SCX_TASK_DEAD) { __scx_task_iter_rq_unlock(iter); continue; } @@ -3500,41 +3544,6 @@ static struct cgroup *tg_cgrp(struct task_group *tg) #endif /* CONFIG_EXT_GROUP_SCHED */ -static u32 scx_get_task_state(const struct task_struct *p) -{ - return p->scx.flags & SCX_TASK_STATE_MASK; -} - -static void scx_set_task_state(struct task_struct *p, u32 state) -{ - u32 prev_state = scx_get_task_state(p); - bool warn = false; - - switch (state) { - case SCX_TASK_NONE: - break; - case SCX_TASK_INIT: - warn = prev_state != SCX_TASK_NONE; - break; - case SCX_TASK_READY: - warn = prev_state == SCX_TASK_NONE; - break; - case SCX_TASK_ENABLED: - warn = prev_state != SCX_TASK_READY; - break; - default: - WARN_ONCE(1, "sched_ext: Invalid task state %d -> %d for %s[%d]", - prev_state, state, p->comm, p->pid); - return; - } - - WARN_ONCE(warn, "sched_ext: Invalid task state transition 0x%x -> 0x%x for %s[%d]", - prev_state, state, p->comm, p->pid); - - p->scx.flags &= ~SCX_TASK_STATE_MASK; - p->scx.flags |= state; -} - static int __scx_init_task(struct scx_sched *sch, struct task_struct *p, bool fork) { int ret; @@ -3586,22 +3595,6 @@ static int __scx_init_task(struct scx_sched *sch, struct task_struct *p, bool fo return 0; } -static int scx_init_task(struct scx_sched *sch, struct task_struct *p, bool fork) -{ - int ret; - - ret = __scx_init_task(sch, p, fork); - if (!ret) { - /* - * While @p's rq is not locked. @p is not visible to the rest of - * SCX yet and it's safe to update the flags and state. - */ - p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT; - scx_set_task_state(p, SCX_TASK_INIT); - } - return ret; -} - static void __scx_enable_task(struct scx_sched *sch, struct task_struct *p) { struct rq *rq = task_rq(p); @@ -3716,7 +3709,8 @@ static void scx_disable_and_exit_task(struct scx_sched *sch, * If set, @p exited between __scx_init_task() and scx_enable_task() in * scx_sub_enable() and is initialized for both the associated sched and * its parent. Exit for the child too - scx_enable_task() never ran for - * it, so undo only init_task. + * it, so undo only init_task. The flag is only set on the sub-enable + * path, so it's always clear when @p arrives here in %SCX_TASK_NONE. */ if (p->scx.flags & SCX_TASK_SUB_INIT) { if (!WARN_ON_ONCE(!scx_enabling_sub_sched)) @@ -3764,10 +3758,14 @@ int scx_fork(struct task_struct *p, struct kernel_clone_args *kargs) #else struct scx_sched *sch = scx_root; #endif - ret = scx_init_task(sch, p, true); - if (!ret) - scx_set_task_sched(p, sch); - return ret; + scx_set_task_state(p, SCX_TASK_INIT_BEGIN); + ret = __scx_init_task(sch, p, true); + if (unlikely(ret)) { + scx_set_task_state(p, SCX_TASK_NONE); + return ret; + } + scx_set_task_state(p, SCX_TASK_INIT); + scx_set_task_sched(p, sch); } return 0; @@ -3862,18 +3860,23 @@ void sched_ext_dead(struct task_struct *p) * @p is off scx_tasks and wholly ours. scx_root_enable()'s READY -> * ENABLED transitions can't race us. Disable ops for @p. * - * %SCX_TASK_OFF_TASKS synchronizes against cgroup task iteration - see + * %SCX_TASK_DEAD synchronizes against cgroup task iteration - see * scx_task_iter_next_locked(). NONE tasks need no marking: cgroup * iteration is only used from sub-sched paths, which require root * enabled. Root enable transitions every live task to at least READY. + * + * %INIT_BEGIN means ops.init_task() is running for @p. Don't call + * into ops; transition to %DEAD so the post-init recheck unwinds + * via scx_sub_init_cancel_task(). */ if (scx_get_task_state(p) != SCX_TASK_NONE) { struct rq_flags rf; struct rq *rq; rq = task_rq_lock(p, &rf); - scx_disable_and_exit_task(scx_task_sched(p), p); - p->scx.flags |= SCX_TASK_OFF_TASKS; + if (scx_get_task_state(p) != SCX_TASK_INIT_BEGIN) + scx_disable_and_exit_task(scx_task_sched(p), p); + scx_set_task_state(p, SCX_TASK_DEAD); task_rq_unlock(rq, p, &rf); } } @@ -3919,6 +3922,16 @@ static void switched_from_scx(struct rq *rq, struct task_struct *p) if (task_dead_and_done(p)) return; + /* + * %NONE means SCX is no longer tracking @p at the task level (e.g. + * scx_fail_parent() handed @p back to the parent at NONE pending the + * parent's own teardown). There is nothing to disable; calling + * scx_disable_task() would WARN on the non-%ENABLED state and trigger a + * NONE -> READY validation failure. + */ + if (scx_get_task_state(p) == SCX_TASK_NONE) + return; + scx_disable_task(scx_task_sched(p), p); } @@ -4808,6 +4821,8 @@ static void scx_sched_free_rcu_work(struct work_struct *work) kfree(sch->cgrp_path); if (sch_cgroup(sch)) cgroup_put(sch_cgroup(sch)); + if (sch->sub_kset) + kobject_put(&sch->sub_kset->kobj); #endif /* CONFIG_EXT_SUB_SCHED */ for_each_possible_cpu(cpu) { @@ -5585,10 +5600,12 @@ static void refresh_watchdog(void) static s32 scx_link_sched(struct scx_sched *sch) { + const char *err_msg = ""; + s32 ret = 0; + scoped_guard(raw_spinlock_irq, &scx_sched_lock) { #ifdef CONFIG_EXT_SUB_SCHED struct scx_sched *parent = scx_parent(sch); - s32 ret; if (parent) { /* @@ -5598,15 +5615,16 @@ static s32 scx_link_sched(struct scx_sched *sch) * parent can shoot us down. */ if (atomic_read(&parent->exit_kind) != SCX_EXIT_NONE) { - scx_error(sch, "parent disabled"); - return -ENOENT; + err_msg = "parent disabled"; + ret = -ENOENT; + break; } ret = rhashtable_lookup_insert_fast(&scx_sched_hash, &sch->hash_node, scx_sched_hash_params); if (ret) { - scx_error(sch, "failed to insert into scx_sched_hash (%d)", ret); - return ret; + err_msg = "failed to insert into scx_sched_hash"; + break; } list_add_tail(&sch->sibling, &parent->children); @@ -5616,6 +5634,15 @@ static s32 scx_link_sched(struct scx_sched *sch) list_add_tail_rcu(&sch->all, &scx_sched_all); } + /* + * scx_error() takes scx_sched_lock via scx_claim_exit(), so it must run after + * the guard above is released. + */ + if (ret) { + scx_error(sch, "%s (%d)", err_msg, ret); + return ret; + } + refresh_watchdog(); return 0; } @@ -5685,7 +5712,7 @@ static void scx_fail_parent(struct scx_sched *sch, scoped_guard (sched_change, p, DEQUEUE_SAVE | DEQUEUE_MOVE) { scx_disable_and_exit_task(sch, p); - rcu_assign_pointer(p->scx.sched, parent); + scx_set_task_sched(p, parent); } } scx_task_iter_stop(&sti); @@ -5763,6 +5790,21 @@ static void scx_sub_disable(struct scx_sched *sch) } rq = task_rq_lock(p, &rf); + + if (scx_get_task_state(p) == SCX_TASK_DEAD) { + /* + * sched_ext_dead() raced us between __scx_init_task() + * and this rq lock and ran exit_task() on @sch (the + * sched @p was on at that point), not on $parent. + * $parent's just-completed init is owed an exit_task() + * and we issue it here. + */ + scx_sub_init_cancel_task(parent, p); + task_rq_unlock(rq, p, &rf); + put_task_struct(p); + continue; + } + scoped_guard (sched_change, p, DEQUEUE_SAVE | DEQUEUE_MOVE) { /* * $p is initialized for $parent and still attached to @@ -5771,13 +5813,14 @@ static void scx_sub_disable(struct scx_sched *sch) * $p having already been initialized, and then enable. */ scx_disable_and_exit_task(sch, p); + scx_set_task_state(p, SCX_TASK_INIT_BEGIN); scx_set_task_state(p, SCX_TASK_INIT); - rcu_assign_pointer(p->scx.sched, parent); + scx_set_task_sched(p, parent); scx_set_task_state(p, SCX_TASK_READY); scx_enable_task(parent, p); } - task_rq_unlock(rq, p, &rf); + task_rq_unlock(rq, p, &rf); put_task_struct(p); } scx_task_iter_stop(&sti); @@ -5820,7 +5863,7 @@ static void scx_sub_disable(struct scx_sched *sch) if (sch->ops.exit) SCX_CALL_OP(sch, exit, NULL, sch->exit_info); if (sch->sub_kset) - kset_unregister(sch->sub_kset); + kobject_del(&sch->sub_kset->kobj); kobject_del(&sch->kobj); } #else /* CONFIG_EXT_SUB_SCHED */ @@ -5954,7 +5997,7 @@ static void scx_root_disable(struct scx_sched *sch) */ #ifdef CONFIG_EXT_SUB_SCHED if (sch->sub_kset) - kset_unregister(sch->sub_kset); + kobject_del(&sch->sub_kset->kobj); #endif kobject_del(&sch->kobj); @@ -6578,7 +6621,7 @@ static struct scx_sched *scx_alloc_and_add_sched(struct sched_ext_ops *ops, sch->slice_dfl = SCX_SLICE_DFL; atomic_set(&sch->exit_kind, SCX_EXIT_NONE); - init_irq_work(&sch->disable_irq_work, scx_disable_irq_workfn); + sch->disable_irq_work = IRQ_WORK_INIT_HARD(scx_disable_irq_workfn); kthread_init_work(&sch->disable_work, scx_disable_workfn); timer_setup(&sch->bypass_lb_timer, scx_bypass_lb_timerfn, 0); @@ -6594,6 +6637,7 @@ static struct scx_sched *scx_alloc_and_add_sched(struct sched_ext_ops *ops, rcu_assign_pointer(ops->priv, sch); sch->kobj.kset = scx_kset; + INIT_LIST_HEAD(&sch->all); #ifdef CONFIG_EXT_SUB_SCHED char *buf = kzalloc(PATH_MAX, GFP_KERNEL); @@ -6621,6 +6665,7 @@ static struct scx_sched *scx_alloc_and_add_sched(struct sched_ext_ops *ops, ret = kobject_init_and_add(&sch->kobj, &scx_ktype, NULL, "root"); if (ret < 0) { + RCU_INIT_POINTER(ops->priv, NULL); kobject_put(&sch->kobj); return ERR_PTR(ret); } @@ -6628,6 +6673,7 @@ static struct scx_sched *scx_alloc_and_add_sched(struct sched_ext_ops *ops, if (ops->sub_attach) { sch->sub_kset = kset_create_and_add("sub", NULL, &sch->kobj); if (!sch->sub_kset) { + RCU_INIT_POINTER(ops->priv, NULL); kobject_put(&sch->kobj); return ERR_PTR(-ENOMEM); } @@ -6635,14 +6681,18 @@ static struct scx_sched *scx_alloc_and_add_sched(struct sched_ext_ops *ops, #else /* CONFIG_EXT_SUB_SCHED */ ret = kobject_init_and_add(&sch->kobj, &scx_ktype, NULL, "root"); if (ret < 0) { + RCU_INIT_POINTER(ops->priv, NULL); kobject_put(&sch->kobj); return ERR_PTR(ret); } #endif /* CONFIG_EXT_SUB_SCHED */ return sch; +#ifdef CONFIG_EXT_SUB_SCHED err_free_lb_resched: + RCU_INIT_POINTER(ops->priv, NULL); free_cpumask_var(sch->bypass_lb_resched_cpumask); +#endif err_free_lb_cpumask: free_cpumask_var(sch->bypass_lb_donee_cpumask); err_stop_helper: @@ -6752,6 +6802,19 @@ static void scx_root_enable_workfn(struct kthread_work *work) goto err_unlock; } + /* + * @ops->priv binds @ops to its scx_sched instance. It is set here by + * scx_alloc_and_add_sched() and cleared at the tail of bpf_scx_unreg(), + * which runs after scx_root_disable() has dropped scx_enable_mutex. If + * it's still non-NULL here, a previous attachment on @ops has not + * finished tearing down; proceeding would let the in-flight unreg's + * RCU_INIT_POINTER(NULL) clobber the @ops->priv we are about to assign. + */ + if (rcu_access_pointer(ops->priv)) { + ret = -EBUSY; + goto err_unlock; + } + ret = alloc_kick_syncs(); if (ret) goto err_unlock; @@ -6874,6 +6937,9 @@ static void scx_root_enable_workfn(struct kthread_work *work) scx_task_iter_start(&sti, NULL); while ((p = scx_task_iter_next_locked(&sti))) { + struct rq_flags rf; + struct rq *rq; + /* * @p may already be dead, have lost all its usages counts and * be waiting for RCU grace period before being freed. @p can't @@ -6882,20 +6948,47 @@ static void scx_root_enable_workfn(struct kthread_work *work) if (!tryget_task_struct(p)) continue; + /* + * Set %INIT_BEGIN under the iter's rq lock so that a concurrent + * sched_ext_dead() does not call ops.exit_task() on @p while + * ops.init_task() is running. If sched_ext_dead() runs before + * this store, it has already removed @p from scx_tasks and the + * iter won't visit @p; if it runs after, it observes + * %INIT_BEGIN and transitions to %DEAD without calling ops, + * leaving the post-init recheck below to unwind. + */ + scx_set_task_state(p, SCX_TASK_INIT_BEGIN); scx_task_iter_unlock(&sti); - ret = scx_init_task(sch, p, false); - if (ret) { - put_task_struct(p); + ret = __scx_init_task(sch, p, false); + + rq = task_rq_lock(p, &rf); + + if (unlikely(ret)) { + if (scx_get_task_state(p) != SCX_TASK_DEAD) + scx_set_task_state(p, SCX_TASK_NONE); + task_rq_unlock(rq, p, &rf); scx_task_iter_stop(&sti); scx_error(sch, "ops.init_task() failed (%d) for %s[%d]", ret, p->comm, p->pid); + put_task_struct(p); goto err_disable_unlock_all; } - scx_set_task_sched(p, sch); - scx_set_task_state(p, SCX_TASK_READY); + if (scx_get_task_state(p) == SCX_TASK_DEAD) { + /* + * sched_ext_dead() observed %INIT_BEGIN and set %DEAD. + * ops.exit_task() is owed to the sched __scx_init_task() + * ran against; call it now. + */ + scx_sub_init_cancel_task(sch, p); + } else { + scx_set_task_state(p, SCX_TASK_INIT); + scx_set_task_sched(p, sch); + scx_set_task_state(p, SCX_TASK_READY); + } + task_rq_unlock(rq, p, &rf); put_task_struct(p); } scx_task_iter_stop(&sti); @@ -7039,6 +7132,12 @@ static void scx_sub_enable_workfn(struct kthread_work *work) goto out_unlock; } + /* See scx_root_enable_workfn() for the @ops->priv check. */ + if (rcu_access_pointer(ops->priv)) { + ret = -EBUSY; + goto out_unlock; + } + cgrp = cgroup_get_from_id(ops->sub_cgroup_id); if (IS_ERR(cgrp)) { ret = PTR_ERR(cgrp); @@ -7165,6 +7264,21 @@ static void scx_sub_enable_workfn(struct kthread_work *work) goto abort; rq = task_rq_lock(p, &rf); + + if (scx_get_task_state(p) == SCX_TASK_DEAD) { + /* + * sched_ext_dead() raced us between __scx_init_task() + * and this rq lock and ran exit_task() on $parent (the + * sched @p was on at that point), not on @sch. @sch's + * just-completed init is owed an exit_task() and we + * issue it here. + */ + scx_sub_init_cancel_task(sch, p); + task_rq_unlock(rq, p, &rf); + put_task_struct(p); + continue; + } + p->scx.flags |= SCX_TASK_SUB_INIT; task_rq_unlock(rq, p, &rf); @@ -7199,7 +7313,7 @@ static void scx_sub_enable_workfn(struct kthread_work *work) * $p is now only initialized for @sch and READY, which * is what we want. Assign it to @sch and enable. */ - rcu_assign_pointer(p->scx.sched, sch); + scx_set_task_sched(p, sch); scx_enable_task(sch, p); p->scx.flags &= ~SCX_TASK_SUB_INIT; @@ -7301,8 +7415,7 @@ static s32 scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) static DEFINE_MUTEX(helper_mutex); struct scx_enable_cmd cmd; - if (!cpumask_equal(housekeeping_cpumask(HK_TYPE_DOMAIN), - cpu_possible_mask)) { + if (housekeeping_enabled(HK_TYPE_DOMAIN_BOOT)) { pr_err("sched_ext: Not compatible with \"isolcpus=\" domain isolation\n"); return -EINVAL; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index af7079aa0f36..a02bd258677e 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2384,7 +2384,8 @@ static void bpf_kprobe_multi_link_release(struct bpf_link *link) struct bpf_kprobe_multi_link *kmulti_link; kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link); - unregister_fprobe(&kmulti_link->fp); + /* Don't wait for RCU GP here. */ + unregister_fprobe_async(&kmulti_link->fp); kprobe_multi_put_modules(kmulti_link->mods, kmulti_link->mods_cnt); } diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index cc49ebd2a773..f378613ad120 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -1093,14 +1093,15 @@ static int unregister_fprobe_nolock(struct fprobe *fp) } /** - * unregister_fprobe() - Unregister fprobe. + * unregister_fprobe_async() - Unregister fprobe without RCU GP wait * @fp: A fprobe data structure to be unregistered. * * Unregister fprobe (and remove ftrace hooks from the function entries). + * This function will NOT wait until the fprobe is no longer used. * * Return 0 if @fp is unregistered successfully, -errno if not. */ -int unregister_fprobe(struct fprobe *fp) +int unregister_fprobe_async(struct fprobe *fp) { guard(mutex)(&fprobe_mutex); if (!fp || !fprobe_registered(fp)) @@ -1108,6 +1109,24 @@ int unregister_fprobe(struct fprobe *fp) return unregister_fprobe_nolock(fp); } + +/** + * unregister_fprobe() - Unregister fprobe with RCU GP wait + * @fp: A fprobe data structure to be unregistered. + * + * Unregister fprobe (and remove ftrace hooks from the function entries). + * This function will block until the fprobe is no longer used. + * + * Return 0 if @fp is unregistered successfully, -errno if not. + */ +int unregister_fprobe(struct fprobe *fp) +{ + int ret = unregister_fprobe_async(fp); + + if (!ret) + synchronize_rcu(); + return ret; +} EXPORT_SYMBOL_GPL(unregister_fprobe); static int __init fprobe_initcall(void) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 3d2e3b2ec528..33b721a9af02 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2296,6 +2296,18 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, if (unlikely(wq->flags & (__WQ_DESTROYING | __WQ_DRAINING) && WARN_ONCE(!is_chained_work(wq), "workqueue: cannot queue %ps on wq %s\n", work->func, wq->name))) { + struct work_offq_data offqd; + + /* + * State on entry: PENDING is set, work is off-queue (no + * insert_work() has run). + * + * Returning without clearing PENDING would leave the work + * in a weird state (PENDING=1, PWQ=0, entry empty) + */ + work_offqd_unpack(&offqd, *work_data_bits(work)); + set_work_pool_and_clear_pending(work, offqd.pool_id, + work_offqd_pack_flags(&offqd)); return; } rcu_read_lock(); @@ -5642,7 +5654,9 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq) ret = apply_workqueue_attrs_locked(wq, unbound_std_wq_attrs[highpri]); } - return ret; + if (ret) + goto enomem; + return 0; enomem: if (wq->cpu_pwq) { diff --git a/lib/kunit/Kconfig b/lib/kunit/Kconfig index 498cc51e493d..94ff8e4089bf 100644 --- a/lib/kunit/Kconfig +++ b/lib/kunit/Kconfig @@ -16,8 +16,9 @@ menuconfig KUNIT if KUNIT config KUNIT_DEBUGFS - bool "KUnit - Enable /sys/kernel/debug/kunit debugfs representation" if !KUNIT_ALL_TESTS - default KUNIT_ALL_TESTS + bool "KUnit - Enable /sys/kernel/debug/kunit debugfs representation" + depends on DEBUG_FS + default y help Enable debugfs representation for kunit. Currently this consists of /sys/kernel/debug/kunit/<test_suite>/results files for each diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 7a67ef5b67b6..04b3a808fca9 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -114,6 +114,14 @@ static void bucket_table_free(const struct bucket_table *tbl) kvfree(tbl); } +static void bucket_table_free_atomic(const struct bucket_table *tbl) +{ + if (tbl->nest) + nested_bucket_table_free(tbl); + + kvfree_atomic(tbl); +} + static void bucket_table_free_rcu(struct rcu_head *head) { bucket_table_free(container_of(head, struct bucket_table, rcu)); @@ -496,7 +504,7 @@ static int rhashtable_insert_rehash(struct rhashtable *ht, err = rhashtable_rehash_attach(ht, tbl, new_tbl); if (err) { - bucket_table_free(new_tbl); + bucket_table_free_atomic(new_tbl); if (err == -EEXIST) err = 0; } else @@ -1166,6 +1174,11 @@ static void rhashtable_free_one(struct rhashtable *ht, struct rhash_head *obj, * This function will eventually sleep to wait for an async resize * to complete. The caller is responsible that no further write operations * occurs in parallel. + * + * After cancel_work_sync() has returned, the deferred rehash worker is + * quiesced and, per the contract above, no other concurrent access to the + * rhashtable is possible. The tables are therefore owned exclusively by + * this function and can be walked without ht->mutex held. */ void rhashtable_free_and_destroy(struct rhashtable *ht, void (*free_fn)(void *ptr, void *arg), @@ -1177,8 +1190,15 @@ void rhashtable_free_and_destroy(struct rhashtable *ht, irq_work_sync(&ht->run_irq_work); cancel_work_sync(&ht->run_work); - mutex_lock(&ht->mutex); - tbl = rht_dereference(ht->tbl, ht); + /* + * Do NOT take ht->mutex here. The rehash worker establishes + * ht->mutex -> fs_reclaim via GFP_KERNEL bucket allocation under + * the mutex; callers on the reclaim path (e.g. simple_xattr_ht_free() + * from evict() under the dcache shrinker for shmem/kernfs/pidfs + * inodes) would otherwise close a circular dependency + * fs_reclaim -> ht->mutex. + */ + tbl = rcu_dereference_raw(ht->tbl); restart: if (free_fn) { for (i = 0; i < tbl->size; i++) { @@ -1187,22 +1207,21 @@ restart: cond_resched(); for (pos = rht_ptr_exclusive(rht_bucket(tbl, i)), next = !rht_is_a_nulls(pos) ? - rht_dereference(pos->next, ht) : NULL; + rcu_dereference_raw(pos->next) : NULL; !rht_is_a_nulls(pos); pos = next, next = !rht_is_a_nulls(pos) ? - rht_dereference(pos->next, ht) : NULL) + rcu_dereference_raw(pos->next) : NULL) rhashtable_free_one(ht, pos, free_fn, arg); } } - next_tbl = rht_dereference(tbl->future_tbl, ht); + next_tbl = rcu_dereference_raw(tbl->future_tbl); bucket_table_free(tbl); if (next_tbl) { tbl = next_tbl; goto restart; } - mutex_unlock(&ht->mutex); } EXPORT_SYMBOL_GPL(rhashtable_free_and_destroy); diff --git a/lib/tests/test_kprobes.c b/lib/tests/test_kprobes.c index b7582010125c..06e729e4de05 100644 --- a/lib/tests/test_kprobes.c +++ b/lib/tests/test_kprobes.c @@ -12,6 +12,12 @@ #define div_factor 3 +#define KP_CLEAR(_kp) \ +do { \ + (_kp).addr = NULL; \ + (_kp).flags = 0; \ +} while (0) + static u32 rand1, preh_val, posth_val; static u32 (*target)(u32 value); static u32 (*recursed_target)(u32 value); @@ -125,10 +131,6 @@ static void test_kprobes(struct kunit *test) current_test = test; - /* addr and flags should be cleard for reusing kprobe. */ - kp.addr = NULL; - kp.flags = 0; - KUNIT_EXPECT_EQ(test, 0, register_kprobes(kps, 2)); preh_val = 0; posth_val = 0; @@ -226,9 +228,6 @@ static void test_kretprobes(struct kunit *test) struct kretprobe *rps[2] = {&rp, &rp2}; current_test = test; - /* addr and flags should be cleard for reusing kprobe. */ - rp.kp.addr = NULL; - rp.kp.flags = 0; KUNIT_EXPECT_EQ(test, 0, register_kretprobes(rps, 2)); krph_val = 0; @@ -290,8 +289,6 @@ static void test_stacktrace_on_kretprobe(struct kunit *test) unsigned long myretaddr = (unsigned long)__builtin_return_address(0); current_test = test; - rp3.kp.addr = NULL; - rp3.kp.flags = 0; /* * Run the stacktrace_driver() to record correct return address in @@ -352,8 +349,6 @@ static void test_stacktrace_on_nested_kretprobe(struct kunit *test) struct kretprobe *rps[2] = {&rp3, &rp4}; current_test = test; - rp3.kp.addr = NULL; - rp3.kp.flags = 0; //KUNIT_ASSERT_NE(test, myretaddr, stacktrace_driver()); @@ -367,6 +362,18 @@ static void test_stacktrace_on_nested_kretprobe(struct kunit *test) static int kprobes_test_init(struct kunit *test) { + KP_CLEAR(kp); + KP_CLEAR(kp2); + KP_CLEAR(kp_missed); +#ifdef CONFIG_KRETPROBES + KP_CLEAR(rp.kp); + KP_CLEAR(rp2.kp); +#ifdef CONFIG_ARCH_CORRECT_STACKTRACE_ON_KRETPROBE + KP_CLEAR(rp3.kp); + KP_CLEAR(rp4.kp); +#endif +#endif + target = kprobe_target; target2 = kprobe_target2; recursed_target = kprobe_recursed_target; diff --git a/mm/memfd_luo.c b/mm/memfd_luo.c index b02b503c750d..59de210bee5f 100644 --- a/mm/memfd_luo.c +++ b/mm/memfd_luo.c @@ -50,6 +50,11 @@ * memfds are always opened with ``O_RDWR`` and ``O_LARGEFILE``. This property * is maintained. * + * Seals + * File seals set on the memfd are preserved and re-applied on restore. + * Only seals known to this LUO version (see ``MEMFD_LUO_ALL_SEALS``) may + * be present; preservation fails with ``-EOPNOTSUPP`` otherwise. + * * Non-Preserved Properties * ======================== * @@ -61,10 +66,6 @@ * A memfd can be created with the ``MFD_CLOEXEC`` flag that sets the * ``FD_CLOEXEC`` on the file. This flag is not preserved and must be set * again after restore via ``fcntl()``. - * - * Seals - * File seals are not preserved. The file is unsealed on restore and if - * needed, must be sealed again via ``fcntl()``. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -259,7 +260,7 @@ static int memfd_luo_preserve(struct liveupdate_file_op_args *args) struct inode *inode = file_inode(args->file); struct memfd_luo_folio_ser *folios_ser; struct memfd_luo_ser *ser; - u64 nr_folios; + u64 nr_folios, inode_size; int err = 0, seals; inode_lock(inode); @@ -285,7 +286,18 @@ static int memfd_luo_preserve(struct liveupdate_file_op_args *args) } ser->pos = args->file->f_pos; - ser->size = i_size_read(inode); + inode_size = i_size_read(inode); + + /* + * memfd_pin_folios() caps at UINT_MAX folios; refuse larger + * files to avoid silently preserving only a prefix. + */ + if (DIV_ROUND_UP_ULL(inode_size, PAGE_SIZE) > UINT_MAX) { + err = -EFBIG; + goto err_free_ser; + } + + ser->size = inode_size; ser->seals = seals; err = memfd_luo_preserve_folios(args->file, &ser->folios, @@ -427,6 +439,7 @@ static int memfd_luo_retrieve_folios(struct file *file, if (!folio) { pr_err("Unable to restore folio at physical address: %llx\n", phys); + err = -EIO; goto put_folios; } index = pfolio->index; diff --git a/mm/slub.c b/mm/slub.c index 0baa906f39ab..8f9004536729 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -6883,6 +6883,22 @@ void kvfree(const void *addr) EXPORT_SYMBOL(kvfree); /** + * kvfree_atomic() - Free memory. + * @addr: Pointer to allocated memory. + * + * Same as kvfree(), but uses vfree_atomic() for vmalloc + * backed memory. Must not be called from NMI context. + */ +void kvfree_atomic(const void *addr) +{ + if (is_vmalloc_addr(addr)) + vfree_atomic(addr); + else + kfree(addr); +} +EXPORT_SYMBOL(kvfree_atomic); + +/** * kvfree_sensitive - Free a data object containing sensitive information. * @addr: address of the data object to be freed. * @len: length of the data object. diff --git a/net/atm/signaling.c b/net/atm/signaling.c index 358fbe5e4d1d..b991d937205a 100644 --- a/net/atm/signaling.c +++ b/net/atm/signaling.c @@ -179,6 +179,7 @@ as_indicate_complete: break; default: pr_alert("bad message type %d\n", (int)msg->type); + dev_kfree_skb(skb); /* Paired with find_get_vcc(msg->vcc) above */ sock_put(sk); return -EINVAL; diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index f28e9cbf8ad5..74ef7dc2b2f9 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -173,19 +173,12 @@ free_orig_node_hash: static struct batadv_neigh_node * batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface, const u8 *neigh_addr, - struct batadv_orig_node *orig_node, - struct batadv_orig_node *orig_neigh) + struct batadv_orig_node *orig_node) { struct batadv_neigh_node *neigh_node; neigh_node = batadv_neigh_node_get_or_create(orig_node, hard_iface, neigh_addr); - if (!neigh_node) - goto out; - - neigh_node->orig_node = orig_neigh; - -out: return neigh_node; } @@ -335,7 +328,7 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet, struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface); const char *fwd_str; u8 packet_num; - s16 buff_pos; + int buff_pos; struct batadv_ogm_packet *batadv_ogm_packet; struct sk_buff *skb; u8 *packet_pos; @@ -907,6 +900,31 @@ static u8 batadv_iv_orig_ifinfo_sum(struct batadv_orig_node *orig_node, } /** + * batadv_iv_ogm_neigh_ifinfo_sum() - Get bcast_own sum for a last-hop neighbor + * @bat_priv: the bat priv with all the mesh interface information + * @neigh_node: last-hop neighbor of an originator + * + * Return: Number of replied (rebroadcasted) OGMs for the originator currently + * announced by the neighbor. Returns 0 if the neighbor's originator entry is + * not available anymore. + */ +static u8 batadv_iv_ogm_neigh_ifinfo_sum(struct batadv_priv *bat_priv, + const struct batadv_neigh_node *neigh_node) +{ + struct batadv_orig_node *orig_neigh; + u8 sum; + + orig_neigh = batadv_orig_hash_find(bat_priv, neigh_node->addr); + if (!orig_neigh) + return 0; + + sum = batadv_iv_orig_ifinfo_sum(orig_neigh, neigh_node->if_incoming); + batadv_orig_node_put(orig_neigh); + + return sum; +} + +/** * batadv_iv_ogm_orig_update() - use OGM to update corresponding data in an * originator * @bat_priv: the bat priv with all the mesh interface information @@ -975,17 +993,9 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, } if (!neigh_node) { - struct batadv_orig_node *orig_tmp; - - orig_tmp = batadv_iv_ogm_orig_get(bat_priv, ethhdr->h_source); - if (!orig_tmp) - goto unlock; - neigh_node = batadv_iv_ogm_neigh_new(if_incoming, ethhdr->h_source, - orig_node, orig_tmp); - - batadv_orig_node_put(orig_tmp); + orig_node); if (!neigh_node) goto unlock; } else { @@ -1037,10 +1047,9 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, */ if (router_ifinfo && neigh_ifinfo->bat_iv.tq_avg == router_ifinfo->bat_iv.tq_avg) { - sum_orig = batadv_iv_orig_ifinfo_sum(router->orig_node, - router->if_incoming); - sum_neigh = batadv_iv_orig_ifinfo_sum(neigh_node->orig_node, - neigh_node->if_incoming); + sum_orig = batadv_iv_ogm_neigh_ifinfo_sum(bat_priv, router); + sum_neigh = batadv_iv_ogm_neigh_ifinfo_sum(bat_priv, + neigh_node); if (sum_orig >= sum_neigh) goto out; } @@ -1106,7 +1115,6 @@ static bool batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, if (!neigh_node) neigh_node = batadv_iv_ogm_neigh_new(if_incoming, orig_neigh_node->orig, - orig_neigh_node, orig_neigh_node); if (!neigh_node) @@ -1303,6 +1311,32 @@ out: } /** + * batadv_orig_to_direct_router() - get direct next hop neighbor to an orig address + * @bat_priv: the bat priv with all the mesh interface information + * @orig_addr: the originator MAC address to search the best next hop router for + * @if_outgoing: the interface where the OGM should be sent to + * + * Return: A neighbor node which is the best router towards the given originator + * address. Bonding candidates are ignored. + */ +static struct batadv_neigh_node * +batadv_orig_to_direct_router(struct batadv_priv *bat_priv, u8 *orig_addr, + struct batadv_hard_iface *if_outgoing) +{ + struct batadv_neigh_node *neigh_node; + struct batadv_orig_node *orig_node; + + orig_node = batadv_orig_hash_find(bat_priv, orig_addr); + if (!orig_node) + return NULL; + + neigh_node = batadv_orig_router_get(orig_node, if_outgoing); + batadv_orig_node_put(orig_node); + + return neigh_node; +} + +/** * batadv_iv_ogm_process_per_outif() - process a batman iv OGM for an outgoing * interface * @skb: the skb containing the OGM @@ -1372,8 +1406,9 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset, router = batadv_orig_router_get(orig_node, if_outgoing); if (router) { - router_router = batadv_orig_router_get(router->orig_node, - if_outgoing); + router_router = batadv_orig_to_direct_router(bat_priv, + router->addr, + if_outgoing); router_ifinfo = batadv_neigh_ifinfo_get(router, if_outgoing); } diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 51fe028b9088..cec11f1251d6 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -318,8 +318,8 @@ batadv_bla_del_backbone_claims(struct batadv_bla_backbone_gw *backbone_gw) if (claim->backbone_gw != backbone_gw) continue; - batadv_claim_put(claim); hlist_del_rcu(&claim->hash_entry); + batadv_claim_put(claim); } spin_unlock_bh(list_lock); } @@ -723,6 +723,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, if (unlikely(hash_added != 0)) { /* only local changes happened. */ + batadv_backbone_gw_put(backbone_gw); kfree(claim); return; } @@ -1288,6 +1289,13 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, rcu_read_lock(); hlist_for_each_entry_rcu(claim, head, hash_entry) { + /* only purge claims not currently in the process of being released. + * Such claims could otherwise have a NULL-ptr backbone_gw set because + * they already went through batadv_claim_release() + */ + if (!kref_get_unless_zero(&claim->refcount)) + continue; + backbone_gw = batadv_bla_claim_get_backbone_gw(claim); if (now) goto purge_now; @@ -1313,6 +1321,7 @@ purge_now: claim->addr, claim->vid); skip: batadv_backbone_gw_put(backbone_gw); + batadv_claim_put(claim); } rcu_read_unlock(); } diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 3a35aadd8b41..a4d33ee0fda5 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -249,6 +249,7 @@ void batadv_mesh_free(struct net_device *mesh_iface) atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); batadv_purge_outstanding_packets(bat_priv, NULL); + batadv_tp_stop_all(bat_priv); batadv_gw_node_free(bat_priv); diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index 2e42f6b348c8..066c76113fc4 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -12,6 +12,7 @@ #include <linux/byteorder/generic.h> #include <linux/cache.h> #include <linux/compiler.h> +#include <linux/completion.h> #include <linux/container_of.h> #include <linux/err.h> #include <linux/etherdevice.h> @@ -365,23 +366,38 @@ static void batadv_tp_vars_put(struct batadv_tp_vars *tp_vars) } /** - * batadv_tp_sender_cleanup() - cleanup sender data and drop and timer - * @bat_priv: the bat priv with all the mesh interface information - * @tp_vars: the private data of the current TP meter session to cleanup + * batadv_tp_list_detach() - remove tp session from mesh session list once + * @tp_vars: the private data of the current TP meter session */ -static void batadv_tp_sender_cleanup(struct batadv_priv *bat_priv, - struct batadv_tp_vars *tp_vars) +static void batadv_tp_list_detach(struct batadv_tp_vars *tp_vars) { - cancel_delayed_work(&tp_vars->finish_work); + bool detached = false; spin_lock_bh(&tp_vars->bat_priv->tp_list_lock); - hlist_del_rcu(&tp_vars->list); + if (!hlist_unhashed(&tp_vars->list)) { + hlist_del_init_rcu(&tp_vars->list); + detached = true; + } spin_unlock_bh(&tp_vars->bat_priv->tp_list_lock); + if (!detached) + return; + + atomic_dec(&tp_vars->bat_priv->tp_num); + /* drop list reference */ batadv_tp_vars_put(tp_vars); +} - atomic_dec(&tp_vars->bat_priv->tp_num); +/** + * batadv_tp_sender_cleanup() - cleanup sender data and drop and timer + * @tp_vars: the private data of the current TP meter session to cleanup + */ +static void batadv_tp_sender_cleanup(struct batadv_tp_vars *tp_vars) +{ + cancel_delayed_work_sync(&tp_vars->finish_work); + + batadv_tp_list_detach(tp_vars); /* kill the timer and remove its reference */ timer_delete_sync(&tp_vars->timer); @@ -886,7 +902,8 @@ out: batadv_orig_node_put(orig_node); batadv_tp_sender_end(bat_priv, tp_vars); - batadv_tp_sender_cleanup(bat_priv, tp_vars); + batadv_tp_sender_cleanup(tp_vars); + complete(&tp_vars->finished); batadv_tp_vars_put(tp_vars); @@ -918,7 +935,8 @@ static void batadv_tp_start_kthread(struct batadv_tp_vars *tp_vars) batadv_tp_vars_put(tp_vars); /* cleanup of failed tp meter variables */ - batadv_tp_sender_cleanup(bat_priv, tp_vars); + batadv_tp_sender_cleanup(tp_vars); + complete(&tp_vars->finished); return; } @@ -947,6 +965,13 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst, /* look for an already existing test towards this node */ spin_lock_bh(&bat_priv->tp_list_lock); + if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) { + spin_unlock_bh(&bat_priv->tp_list_lock); + batadv_tp_batctl_error_notify(BATADV_TP_REASON_DST_UNREACHABLE, + dst, bat_priv, session_cookie); + return; + } + tp_vars = batadv_tp_list_find(bat_priv, dst); if (tp_vars) { spin_unlock_bh(&bat_priv->tp_list_lock); @@ -969,6 +994,7 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst, tp_vars = kmalloc_obj(*tp_vars, GFP_ATOMIC); if (!tp_vars) { + atomic_dec(&bat_priv->tp_num); spin_unlock_bh(&bat_priv->tp_list_lock); batadv_dbg(BATADV_DBG_TP_METER, bat_priv, "Meter: %s cannot allocate list elements\n", @@ -1017,6 +1043,7 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst, tp_vars->start_time = jiffies; init_waitqueue_head(&tp_vars->more_bytes); + init_completion(&tp_vars->finished); spin_lock_init(&tp_vars->unacked_lock); INIT_LIST_HEAD(&tp_vars->unacked_list); @@ -1119,14 +1146,7 @@ static void batadv_tp_receiver_shutdown(struct timer_list *t) "Shutting down for inactivity (more than %dms) from %pM\n", BATADV_TP_RECV_TIMEOUT, tp_vars->other_end); - spin_lock_bh(&tp_vars->bat_priv->tp_list_lock); - hlist_del_rcu(&tp_vars->list); - spin_unlock_bh(&tp_vars->bat_priv->tp_list_lock); - - /* drop list reference */ - batadv_tp_vars_put(tp_vars); - - atomic_dec(&bat_priv->tp_num); + batadv_tp_list_detach(tp_vars); spin_lock_bh(&tp_vars->unacked_lock); list_for_each_entry_safe(un, safe, &tp_vars->unacked_list, list) { @@ -1329,9 +1349,12 @@ static struct batadv_tp_vars * batadv_tp_init_recv(struct batadv_priv *bat_priv, const struct batadv_icmp_tp_packet *icmp) { - struct batadv_tp_vars *tp_vars; + struct batadv_tp_vars *tp_vars = NULL; spin_lock_bh(&bat_priv->tp_list_lock); + if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) + goto out_unlock; + tp_vars = batadv_tp_list_find_session(bat_priv, icmp->orig, icmp->session); if (tp_vars) @@ -1344,8 +1367,10 @@ batadv_tp_init_recv(struct batadv_priv *bat_priv, } tp_vars = kmalloc_obj(*tp_vars, GFP_ATOMIC); - if (!tp_vars) + if (!tp_vars) { + atomic_dec(&bat_priv->tp_num); goto out_unlock; + } ether_addr_copy(tp_vars->other_end, icmp->orig); tp_vars->role = BATADV_TP_RECEIVER; @@ -1464,6 +1489,9 @@ void batadv_tp_meter_recv(struct batadv_priv *bat_priv, struct sk_buff *skb) { struct batadv_icmp_tp_packet *icmp; + if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) + goto out; + icmp = (struct batadv_icmp_tp_packet *)skb->data; switch (icmp->subtype) { @@ -1478,10 +1506,58 @@ void batadv_tp_meter_recv(struct batadv_priv *bat_priv, struct sk_buff *skb) "Received unknown TP Metric packet type %u\n", icmp->subtype); } + +out: consume_skb(skb); } /** + * batadv_tp_stop_all() - stop all currently running tp meter sessions + * @bat_priv: the bat priv with all the mesh interface information + */ +void batadv_tp_stop_all(struct batadv_priv *bat_priv) +{ + struct batadv_tp_vars *tp_vars[BATADV_TP_MAX_NUM]; + struct batadv_tp_vars *tp_var; + size_t count = 0; + size_t i; + + spin_lock_bh(&bat_priv->tp_list_lock); + hlist_for_each_entry(tp_var, &bat_priv->tp_list, list) { + if (WARN_ON_ONCE(count >= BATADV_TP_MAX_NUM)) + break; + + if (!kref_get_unless_zero(&tp_var->refcount)) + continue; + + tp_vars[count++] = tp_var; + } + spin_unlock_bh(&bat_priv->tp_list_lock); + + for (i = 0; i < count; i++) { + tp_var = tp_vars[i]; + + switch (tp_var->role) { + case BATADV_TP_SENDER: + batadv_tp_sender_shutdown(tp_var, + BATADV_TP_REASON_CANCEL); + wake_up(&tp_var->more_bytes); + wait_for_completion(&tp_var->finished); + break; + case BATADV_TP_RECEIVER: + batadv_tp_list_detach(tp_var); + if (timer_shutdown_sync(&tp_var->timer)) + batadv_tp_vars_put(tp_var); + break; + } + + batadv_tp_vars_put(tp_var); + } + + synchronize_net(); +} + +/** * batadv_tp_meter_init() - initialize global tp_meter structures */ void __init batadv_tp_meter_init(void) diff --git a/net/batman-adv/tp_meter.h b/net/batman-adv/tp_meter.h index f0046d366eac..4e97cd10cd02 100644 --- a/net/batman-adv/tp_meter.h +++ b/net/batman-adv/tp_meter.h @@ -17,6 +17,7 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst, u32 test_length, u32 *cookie); void batadv_tp_stop(struct batadv_priv *bat_priv, const u8 *dst, u8 return_value); +void batadv_tp_stop_all(struct batadv_priv *bat_priv); void batadv_tp_meter_recv(struct batadv_priv *bat_priv, struct sk_buff *skb); #endif /* _NET_BATMAN_ADV_TP_METER_H_ */ diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 8fc5fe0e9b05..daa06f421154 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -14,6 +14,7 @@ #include <linux/average.h> #include <linux/bitops.h> #include <linux/compiler.h> +#include <linux/completion.h> #include <linux/if.h> #include <linux/if_ether.h> #include <linux/kref.h> @@ -1328,6 +1329,9 @@ struct batadv_tp_vars { /** @finish_work: work item for the finishing procedure */ struct delayed_work finish_work; + /** @finished: completion signaled when a sender thread exits */ + struct completion finished; + /** @test_length: test length in milliseconds */ u32 test_length; diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index 741360219552..f05c79f215ea 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -112,24 +112,22 @@ static struct pernet_operations broute_net_ops = { static int __init ebtable_broute_init(void) { - int ret = ebt_register_template(&broute_table, broute_table_init); + int ret = register_pernet_subsys(&broute_net_ops); if (ret) return ret; - ret = register_pernet_subsys(&broute_net_ops); - if (ret) { - ebt_unregister_template(&broute_table); - return ret; - } + ret = ebt_register_template(&broute_table, broute_table_init); + if (ret) + unregister_pernet_subsys(&broute_net_ops); - return 0; + return ret; } static void __exit ebtable_broute_fini(void) { - unregister_pernet_subsys(&broute_net_ops); ebt_unregister_template(&broute_table); + unregister_pernet_subsys(&broute_net_ops); } module_init(ebtable_broute_init); diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index dacd81b12e62..0fc03b07e62a 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -93,24 +93,22 @@ static struct pernet_operations frame_filter_net_ops = { static int __init ebtable_filter_init(void) { - int ret = ebt_register_template(&frame_filter, frame_filter_table_init); + int ret = register_pernet_subsys(&frame_filter_net_ops); if (ret) return ret; - ret = register_pernet_subsys(&frame_filter_net_ops); - if (ret) { - ebt_unregister_template(&frame_filter); - return ret; - } + ret = ebt_register_template(&frame_filter, frame_filter_table_init); + if (ret) + unregister_pernet_subsys(&frame_filter_net_ops); - return 0; + return ret; } static void __exit ebtable_filter_fini(void) { - unregister_pernet_subsys(&frame_filter_net_ops); ebt_unregister_template(&frame_filter); + unregister_pernet_subsys(&frame_filter_net_ops); } module_init(ebtable_filter_init); diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 0f2a8c6118d4..8a10375d8909 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -93,24 +93,22 @@ static struct pernet_operations frame_nat_net_ops = { static int __init ebtable_nat_init(void) { - int ret = ebt_register_template(&frame_nat, frame_nat_table_init); + int ret = register_pernet_subsys(&frame_nat_net_ops); if (ret) return ret; - ret = register_pernet_subsys(&frame_nat_net_ops); - if (ret) { - ebt_unregister_template(&frame_nat); - return ret; - } + ret = ebt_register_template(&frame_nat, frame_nat_table_init); + if (ret) + unregister_pernet_subsys(&frame_nat_net_ops); return ret; } static void __exit ebtable_nat_fini(void) { - unregister_pernet_subsys(&frame_nat_net_ops); ebt_unregister_template(&frame_nat); + unregister_pernet_subsys(&frame_nat_net_ops); } module_init(ebtable_nat_init); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index aea3e19875c6..b9f4daac09af 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -42,6 +42,7 @@ struct ebt_pernet { struct list_head tables; + struct list_head dead_tables; }; struct ebt_template { @@ -1162,11 +1163,6 @@ free_newinfo: static void __ebt_unregister_table(struct net *net, struct ebt_table *table) { - mutex_lock(&ebt_mutex); - list_del(&table->list); - mutex_unlock(&ebt_mutex); - audit_log_nfcfg(table->name, AF_BRIDGE, table->private->nentries, - AUDIT_XT_OP_UNREGISTER, GFP_KERNEL); EBT_ENTRY_ITERATE(table->private->entries, table->private->entries_size, ebt_cleanup_entry, net, NULL); if (table->private->nentries) @@ -1267,13 +1263,15 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table, for (i = 0; i < num_ops; i++) ops[i].priv = table; - list_add(&table->list, &ebt_net->tables); - mutex_unlock(&ebt_mutex); - table->ops = ops; ret = nf_register_net_hooks(net, ops, num_ops); - if (ret) + if (ret) { + synchronize_rcu(); __ebt_unregister_table(net, table); + } else { + list_add(&table->list, &ebt_net->tables); + } + mutex_unlock(&ebt_mutex); audit_log_nfcfg(repl->name, AF_BRIDGE, repl->nentries, AUDIT_XT_OP_REGISTER, GFP_KERNEL); @@ -1339,7 +1337,7 @@ void ebt_unregister_template(const struct ebt_table *t) } EXPORT_SYMBOL(ebt_unregister_template); -static struct ebt_table *__ebt_find_table(struct net *net, const char *name) +void ebt_unregister_table_pre_exit(struct net *net, const char *name) { struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id); struct ebt_table *t; @@ -1348,30 +1346,36 @@ static struct ebt_table *__ebt_find_table(struct net *net, const char *name) list_for_each_entry(t, &ebt_net->tables, list) { if (strcmp(t->name, name) == 0) { + list_move(&t->list, &ebt_net->dead_tables); mutex_unlock(&ebt_mutex); - return t; + nf_unregister_net_hooks(net, t->ops, hweight32(t->valid_hooks)); + return; } } mutex_unlock(&ebt_mutex); - return NULL; -} - -void ebt_unregister_table_pre_exit(struct net *net, const char *name) -{ - struct ebt_table *table = __ebt_find_table(net, name); - - if (table) - nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); } EXPORT_SYMBOL(ebt_unregister_table_pre_exit); void ebt_unregister_table(struct net *net, const char *name) { - struct ebt_table *table = __ebt_find_table(net, name); + struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id); + struct ebt_table *t; - if (table) - __ebt_unregister_table(net, table); + mutex_lock(&ebt_mutex); + + list_for_each_entry(t, &ebt_net->dead_tables, list) { + if (strcmp(t->name, name) == 0) { + list_del(&t->list); + audit_log_nfcfg(t->name, AF_BRIDGE, t->private->nentries, + AUDIT_XT_OP_UNREGISTER, GFP_KERNEL); + __ebt_unregister_table(net, t); + mutex_unlock(&ebt_mutex); + return; + } + } + + mutex_unlock(&ebt_mutex); } /* userspace just supplied us with counters */ @@ -2556,11 +2560,21 @@ static int __net_init ebt_pernet_init(struct net *net) struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id); INIT_LIST_HEAD(&ebt_net->tables); + INIT_LIST_HEAD(&ebt_net->dead_tables); return 0; } +static void __net_exit ebt_pernet_exit(struct net *net) +{ + struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id); + + WARN_ON_ONCE(!list_empty(&ebt_net->tables)); + WARN_ON_ONCE(!list_empty(&ebt_net->dead_tables)); +} + static struct pernet_operations ebt_net_ops = { .init = ebt_pernet_init, + .exit = ebt_pernet_exit, .id = &ebt_pernet_id, .size = sizeof(struct ebt_pernet), }; @@ -2569,19 +2583,20 @@ static int __init ebtables_init(void) { int ret; - ret = xt_register_target(&ebt_standard_target); + ret = register_pernet_subsys(&ebt_net_ops); if (ret < 0) return ret; - ret = nf_register_sockopt(&ebt_sockopts); + + ret = xt_register_target(&ebt_standard_target); if (ret < 0) { - xt_unregister_target(&ebt_standard_target); + unregister_pernet_subsys(&ebt_net_ops); return ret; } - ret = register_pernet_subsys(&ebt_net_ops); + ret = nf_register_sockopt(&ebt_sockopts); if (ret < 0) { - nf_unregister_sockopt(&ebt_sockopts); xt_unregister_target(&ebt_standard_target); + unregister_pernet_subsys(&ebt_net_ops); return ret; } diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c index 692e0b868822..9e64e82d0b63 100644 --- a/net/ceph/auth_x.c +++ b/net/ceph/auth_x.c @@ -115,6 +115,11 @@ static int __ceph_x_decrypt(const struct ceph_crypto_key *key, int usage_slot, if (ret) return ret; + if (plaintext_len < sizeof(*hdr)) { + pr_err("%s plaintext too small %d\n", __func__, plaintext_len); + return -EINVAL; + } + hdr = p + ceph_crypt_data_offset(key); if (le64_to_cpu(hdr->magic) != CEPHX_ENC_MAGIC) { pr_err("%s bad magic\n", __func__); diff --git a/net/ceph/crush/crush.c b/net/ceph/crush/crush.c index 254ded0b05f6..521aec1d5fc0 100644 --- a/net/ceph/crush/crush.c +++ b/net/ceph/crush/crush.c @@ -47,7 +47,6 @@ int crush_get_bucket_item_weight(const struct crush_bucket *b, int p) void crush_destroy_bucket_uniform(struct crush_bucket_uniform *b) { kfree(b->h.items); - kfree(b); } void crush_destroy_bucket_list(struct crush_bucket_list *b) @@ -55,14 +54,12 @@ void crush_destroy_bucket_list(struct crush_bucket_list *b) kfree(b->item_weights); kfree(b->sum_weights); kfree(b->h.items); - kfree(b); } void crush_destroy_bucket_tree(struct crush_bucket_tree *b) { kfree(b->h.items); kfree(b->node_weights); - kfree(b); } void crush_destroy_bucket_straw(struct crush_bucket_straw *b) @@ -70,14 +67,12 @@ void crush_destroy_bucket_straw(struct crush_bucket_straw *b) kfree(b->straws); kfree(b->item_weights); kfree(b->h.items); - kfree(b); } void crush_destroy_bucket_straw2(struct crush_bucket_straw2 *b) { kfree(b->item_weights); kfree(b->h.items); - kfree(b); } void crush_destroy_bucket(struct crush_bucket *b) @@ -99,6 +94,7 @@ void crush_destroy_bucket(struct crush_bucket *b) crush_destroy_bucket_straw2((struct crush_bucket_straw2 *)b); break; } + kfree(b); } /** diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index c89e66d4fcb7..8b5b0587a0cf 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -72,8 +72,7 @@ static int crush_decode_uniform_bucket(void **p, void *end, struct crush_bucket_uniform *b) { dout("crush_decode_uniform_bucket %p to %p\n", *p, end); - ceph_decode_need(p, end, (1+b->h.size) * sizeof(u32), bad); - b->item_weight = ceph_decode_32(p); + ceph_decode_32_safe(p, end, b->item_weight, bad); return 0; bad: return -EINVAL; @@ -389,11 +388,15 @@ static int decode_choose_args(void **p, void *end, struct crush_map *c) goto fail; if (arg->ids_size && - arg->ids_size != c->buckets[bucket_index]->size) + (!c->buckets[bucket_index] || + arg->ids_size != c->buckets[bucket_index]->size)) goto e_inval; } - insert_choose_arg_map(&c->choose_args, arg_map); + if (!__insert_choose_arg_map(&c->choose_args, arg_map)) { + ret = -EEXIST; + goto fail; + } } return 0; @@ -516,6 +519,10 @@ static struct crush_map *crush_decode(void *pbyval, void *end) b->id = ceph_decode_32(p); b->type = ceph_decode_16(p); b->alg = ceph_decode_8(p); + if (b->alg != alg) { + b->alg = 0; + goto bad; + } b->hash = ceph_decode_8(p); b->weight = ceph_decode_32(p); b->size = ceph_decode_32(p); @@ -1702,7 +1709,7 @@ static int osdmap_decode(void **p, void *end, bool msgr2, ceph_decode_need(p, end, 3*sizeof(u32) + map->max_osd*(struct_v >= 5 ? sizeof(u32) : sizeof(u8)) + - sizeof(*map->osd_weight), e_inval); + map->max_osd*sizeof(*map->osd_weight), e_inval); if (ceph_decode_32(p) != map->max_osd) goto e_inval; diff --git a/net/core/dev.c b/net/core/dev.c index 8bfa8313ef62..0c6c270d9f7d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6862,9 +6862,9 @@ static void skb_defer_free_flush(void) #if defined(CONFIG_NET_RX_BUSY_POLL) -static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule) +static void __busy_poll_stop(struct napi_struct *napi, unsigned long timeout) { - if (!skip_schedule) { + if (!timeout) { gro_normal_list(&napi->gro); __napi_schedule(napi); return; @@ -6874,6 +6874,8 @@ static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule) gro_flush_normal(&napi->gro, HZ >= 1000); clear_bit(NAPI_STATE_SCHED, &napi->state); + hrtimer_start(&napi->timer, ns_to_ktime(timeout), + HRTIMER_MODE_REL_PINNED); } enum { @@ -6885,8 +6887,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, unsigned flags, u16 budget) { struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; - bool skip_schedule = false; - unsigned long timeout; + unsigned long timeout = 0; int rc; /* Busy polling means there is a high chance device driver hard irq @@ -6906,10 +6907,12 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, if (flags & NAPI_F_PREFER_BUSY_POLL) { napi->defer_hard_irqs_count = napi_get_defer_hard_irqs(napi); - timeout = napi_get_gro_flush_timeout(napi); - if (napi->defer_hard_irqs_count && timeout) { - hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); - skip_schedule = true; + if (napi->defer_hard_irqs_count) { + /* A short enough gro flush timeout and long enough + * poll can result in timer firing too early. + * Timer will be armed later if necessary. + */ + timeout = napi_get_gro_flush_timeout(napi); } } @@ -6924,7 +6927,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, trace_napi_poll(napi, rc, budget); netpoll_poll_unlock(have_poll_lock); if (rc == budget) - __busy_poll_stop(napi, skip_schedule); + __busy_poll_stop(napi, timeout); bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); } diff --git a/net/core/failover.c b/net/core/failover.c index 11bb183c7a1b..e43c59cd6868 100644 --- a/net/core/failover.c +++ b/net/core/failover.c @@ -12,6 +12,7 @@ #include <uapi/linux/if_arp.h> #include <linux/rtnetlink.h> #include <linux/if_vlan.h> +#include <net/netdev_lock.h> #include <net/failover.h> static LIST_HEAD(failover_list); @@ -221,8 +222,11 @@ failover_existing_slave_register(struct net_device *failover_dev) for_each_netdev(net, dev) { if (netif_is_failover(dev)) continue; - if (ether_addr_equal(failover_dev->perm_addr, dev->perm_addr)) + if (ether_addr_equal(failover_dev->perm_addr, dev->perm_addr)) { + netdev_lock_ops(dev); failover_slave_register(dev); + netdev_unlock_ops(dev); + } } rtnl_unlock(); } diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c index 8bb98d3ea3db..a3a2cc6480a0 100644 --- a/net/ethtool/bitset.c +++ b/net/ethtool/bitset.c @@ -92,7 +92,7 @@ static bool ethnl_bitmap32_not_zero(const u32 *map, unsigned int start, u32 mask; if (end <= start) - return true; + return false; if (start % 32) { mask = ethnl_upper_bits(start); @@ -105,11 +105,11 @@ static bool ethnl_bitmap32_not_zero(const u32 *map, unsigned int start, start_word++; } - if (!memchr_inv(map + start_word, '\0', - (end_word - start_word) * sizeof(u32))) + if (memchr_inv(map + start_word, '\0', + (end_word - start_word) * sizeof(u32))) return true; if (end % 32 == 0) - return true; + return false; return map[end_word] & ethnl_lower_bits(end); } diff --git a/net/ethtool/phy.c b/net/ethtool/phy.c index d4e6887055ab..ddc6eab701ed 100644 --- a/net/ethtool/phy.c +++ b/net/ethtool/phy.c @@ -76,6 +76,7 @@ static int phy_prepare_data(const struct ethnl_req_info *req_info, struct nlattr **tb = info->attrs; struct phy_device_node *pdn; struct phy_device *phydev; + int ret; /* RTNL is held by the caller */ phydev = ethnl_req_get_phydev(req_info, tb, ETHTOOL_A_PHY_HEADER, @@ -88,8 +89,19 @@ static int phy_prepare_data(const struct ethnl_req_info *req_info, return -EOPNOTSUPP; rep_data->phyindex = phydev->phyindex; + rep_data->name = kstrdup(dev_name(&phydev->mdio.dev), GFP_KERNEL); - rep_data->drvname = kstrdup(phydev->drv->name, GFP_KERNEL); + if (!rep_data->name) + return -ENOMEM; + + if (phydev->drv) { + rep_data->drvname = kstrdup(phydev->drv->name, GFP_KERNEL); + if (!rep_data->drvname) { + ret = -ENOMEM; + goto err_free_name; + } + } + rep_data->upstream_type = pdn->upstream_type; if (pdn->upstream_type == PHY_UPSTREAM_PHY) { @@ -97,15 +109,33 @@ static int phy_prepare_data(const struct ethnl_req_info *req_info, rep_data->upstream_index = upstream->phyindex; } - if (pdn->parent_sfp_bus) + if (pdn->parent_sfp_bus) { rep_data->upstream_sfp_name = kstrdup(sfp_get_name(pdn->parent_sfp_bus), GFP_KERNEL); + if (!rep_data->upstream_sfp_name) { + ret = -ENOMEM; + goto err_free_drvname; + } + } - if (phydev->sfp_bus) + if (phydev->sfp_bus) { rep_data->downstream_sfp_name = kstrdup(sfp_get_name(phydev->sfp_bus), GFP_KERNEL); + if (!rep_data->downstream_sfp_name) { + ret = -ENOMEM; + goto err_free_upstream_sfp; + } + } return 0; + +err_free_upstream_sfp: + kfree(rep_data->upstream_sfp_name); +err_free_drvname: + kfree(rep_data->drvname); +err_free_name: + kfree(rep_data->name); + return ret; } static int phy_fill_reply(struct sk_buff *skb, diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index d09875b33588..124619920d38 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -889,7 +889,10 @@ int hsr_get_node_data(struct hsr_priv *hsr, if (node->addr_B_port != HSR_PT_NONE) { port = hsr_port_get_hsr(hsr, node->addr_B_port); - *addr_b_ifindex = port->dev->ifindex; + if (port) + *addr_b_ifindex = port->dev->ifindex; + else + *addr_b_ifindex = -1; } else { *addr_b_ifindex = -1; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 928654c34156..dbcd37dfdc15 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1108,7 +1108,7 @@ static void reqsk_timer_handler(struct timer_list *t) if (!inet_ehash_insert(req_to_sk(nreq), req_to_sk(oreq), NULL)) { /* delete timer */ - __inet_csk_reqsk_queue_drop(sk_listener, nreq, true); + __inet_csk_reqsk_queue_drop(sk_listener, nreq, false); goto no_ownership; } @@ -1134,7 +1134,7 @@ no_ownership: } drop: - __inet_csk_reqsk_queue_drop(sk_listener, oreq, true); + __inet_csk_reqsk_queue_drop(oreq->rsk_listener, oreq, true); reqsk_put(oreq); } diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 97ead883e4a1..ad2259678c78 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1501,13 +1501,11 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len static void __arpt_unregister_table(struct net *net, struct xt_table *table) { - struct xt_table_info *private; - void *loc_cpu_entry; + struct xt_table_info *private = table->private; struct module *table_owner = table->me; + void *loc_cpu_entry; struct arpt_entry *iter; - private = xt_unregister_table(table); - /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries; xt_entry_foreach(iter, loc_cpu_entry, private->size) @@ -1515,6 +1513,7 @@ static void __arpt_unregister_table(struct net *net, struct xt_table *table) if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); + kfree(table); } int arpt_register_table(struct net *net, @@ -1522,13 +1521,11 @@ int arpt_register_table(struct net *net, const struct arpt_replace *repl, const struct nf_hook_ops *template_ops) { - struct nf_hook_ops *ops; - unsigned int num_ops; - int ret, i; - struct xt_table_info *newinfo; struct xt_table_info bootstrap = {0}; - void *loc_cpu_entry; + struct xt_table_info *newinfo; struct xt_table *new_table; + void *loc_cpu_entry; + int ret; newinfo = xt_alloc_table_info(repl->size); if (!newinfo) @@ -1543,7 +1540,7 @@ int arpt_register_table(struct net *net, return ret; } - new_table = xt_register_table(net, table, &bootstrap, newinfo); + new_table = xt_register_table(net, table, template_ops, &bootstrap, newinfo); if (IS_ERR(new_table)) { struct arpt_entry *iter; @@ -1553,46 +1550,12 @@ int arpt_register_table(struct net *net, return PTR_ERR(new_table); } - num_ops = hweight32(table->valid_hooks); - if (num_ops == 0) { - ret = -EINVAL; - goto out_free; - } - - ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL); - if (!ops) { - ret = -ENOMEM; - goto out_free; - } - - for (i = 0; i < num_ops; i++) - ops[i].priv = new_table; - - new_table->ops = ops; - - ret = nf_register_net_hooks(net, ops, num_ops); - if (ret != 0) - goto out_free; - return ret; - -out_free: - __arpt_unregister_table(net, new_table); - return ret; -} - -void arpt_unregister_table_pre_exit(struct net *net, const char *name) -{ - struct xt_table *table = xt_find_table(net, NFPROTO_ARP, name); - - if (table) - nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); } -EXPORT_SYMBOL(arpt_unregister_table_pre_exit); void arpt_unregister_table(struct net *net, const char *name) { - struct xt_table *table = xt_find_table(net, NFPROTO_ARP, name); + struct xt_table *table = xt_unregister_table_exit(net, NFPROTO_ARP, name); if (table) __arpt_unregister_table(net, table); diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index 78cd5ee24448..370b635e3523 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -43,7 +43,7 @@ static int arptable_filter_table_init(struct net *net) static void __net_exit arptable_filter_net_pre_exit(struct net *net) { - arpt_unregister_table_pre_exit(net, "filter"); + xt_unregister_table_pre_exit(net, NFPROTO_ARP, "filter"); } static void __net_exit arptable_filter_net_exit(struct net *net) @@ -58,32 +58,33 @@ static struct pernet_operations arptable_filter_net_ops = { static int __init arptable_filter_init(void) { - int ret = xt_register_template(&packet_filter, - arptable_filter_table_init); - - if (ret < 0) - return ret; + int ret; arpfilter_ops = xt_hook_ops_alloc(&packet_filter, arpt_do_table); - if (IS_ERR(arpfilter_ops)) { - xt_unregister_template(&packet_filter); + if (IS_ERR(arpfilter_ops)) return PTR_ERR(arpfilter_ops); - } ret = register_pernet_subsys(&arptable_filter_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(&packet_filter, + arptable_filter_table_init); if (ret < 0) { - xt_unregister_template(&packet_filter); - kfree(arpfilter_ops); - return ret; + unregister_pernet_subsys(&arptable_filter_net_ops); + goto err_free; } + return 0; +err_free: + kfree(arpfilter_ops); return ret; } static void __exit arptable_filter_fini(void) { - unregister_pernet_subsys(&arptable_filter_net_ops); xt_unregister_template(&packet_filter); + unregister_pernet_subsys(&arptable_filter_net_ops); kfree(arpfilter_ops); } diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 23c8deff8095..5cbdb0815857 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1704,12 +1704,10 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) static void __ipt_unregister_table(struct net *net, struct xt_table *table) { - struct xt_table_info *private; - void *loc_cpu_entry; + struct xt_table_info *private = table->private; struct module *table_owner = table->me; struct ipt_entry *iter; - - private = xt_unregister_table(table); + void *loc_cpu_entry; /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries; @@ -1718,19 +1716,18 @@ static void __ipt_unregister_table(struct net *net, struct xt_table *table) if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); + kfree(table); } int ipt_register_table(struct net *net, const struct xt_table *table, const struct ipt_replace *repl, const struct nf_hook_ops *template_ops) { - struct nf_hook_ops *ops; - unsigned int num_ops; - int ret, i; - struct xt_table_info *newinfo; struct xt_table_info bootstrap = {0}; - void *loc_cpu_entry; + struct xt_table_info *newinfo; struct xt_table *new_table; + void *loc_cpu_entry; + int ret; newinfo = xt_alloc_table_info(repl->size); if (!newinfo) @@ -1745,7 +1742,7 @@ int ipt_register_table(struct net *net, const struct xt_table *table, return ret; } - new_table = xt_register_table(net, table, &bootstrap, newinfo); + new_table = xt_register_table(net, table, template_ops, &bootstrap, newinfo); if (IS_ERR(new_table)) { struct ipt_entry *iter; @@ -1755,51 +1752,12 @@ int ipt_register_table(struct net *net, const struct xt_table *table, return PTR_ERR(new_table); } - /* No template? No need to do anything. This is used by 'nat' table, it registers - * with the nat core instead of the netfilter core. - */ - if (!template_ops) - return 0; - - num_ops = hweight32(table->valid_hooks); - if (num_ops == 0) { - ret = -EINVAL; - goto out_free; - } - - ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL); - if (!ops) { - ret = -ENOMEM; - goto out_free; - } - - for (i = 0; i < num_ops; i++) - ops[i].priv = new_table; - - new_table->ops = ops; - - ret = nf_register_net_hooks(net, ops, num_ops); - if (ret != 0) - goto out_free; - return ret; - -out_free: - __ipt_unregister_table(net, new_table); - return ret; -} - -void ipt_unregister_table_pre_exit(struct net *net, const char *name) -{ - struct xt_table *table = xt_find_table(net, NFPROTO_IPV4, name); - - if (table) - nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); } void ipt_unregister_table_exit(struct net *net, const char *name) { - struct xt_table *table = xt_find_table(net, NFPROTO_IPV4, name); + struct xt_table *table = xt_unregister_table_exit(net, NFPROTO_IPV4, name); if (table) __ipt_unregister_table(net, table); @@ -1887,7 +1845,6 @@ static void __exit ip_tables_fini(void) } EXPORT_SYMBOL(ipt_register_table); -EXPORT_SYMBOL(ipt_unregister_table_pre_exit); EXPORT_SYMBOL(ipt_unregister_table_exit); EXPORT_SYMBOL(ipt_do_table); module_init(ip_tables_init); diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 3ab908b74795..672d7da1071d 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -61,7 +61,7 @@ static int __net_init iptable_filter_net_init(struct net *net) static void __net_exit iptable_filter_net_pre_exit(struct net *net) { - ipt_unregister_table_pre_exit(net, "filter"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "filter"); } static void __net_exit iptable_filter_net_exit(struct net *net) @@ -77,32 +77,33 @@ static struct pernet_operations iptable_filter_net_ops = { static int __init iptable_filter_init(void) { - int ret = xt_register_template(&packet_filter, - iptable_filter_table_init); - - if (ret < 0) - return ret; + int ret; filter_ops = xt_hook_ops_alloc(&packet_filter, ipt_do_table); - if (IS_ERR(filter_ops)) { - xt_unregister_template(&packet_filter); + if (IS_ERR(filter_ops)) return PTR_ERR(filter_ops); - } ret = register_pernet_subsys(&iptable_filter_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(&packet_filter, + iptable_filter_table_init); if (ret < 0) { - xt_unregister_template(&packet_filter); - kfree(filter_ops); - return ret; + unregister_pernet_subsys(&iptable_filter_net_ops); + goto err_free; } return 0; +err_free: + kfree(filter_ops); + return ret; } static void __exit iptable_filter_fini(void) { - unregister_pernet_subsys(&iptable_filter_net_ops); xt_unregister_template(&packet_filter); + unregister_pernet_subsys(&iptable_filter_net_ops); kfree(filter_ops); } diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 385d945d8ebe..13d25d9a4610 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -96,7 +96,7 @@ static int iptable_mangle_table_init(struct net *net) static void __net_exit iptable_mangle_net_pre_exit(struct net *net) { - ipt_unregister_table_pre_exit(net, "mangle"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "mangle"); } static void __net_exit iptable_mangle_net_exit(struct net *net) @@ -111,32 +111,33 @@ static struct pernet_operations iptable_mangle_net_ops = { static int __init iptable_mangle_init(void) { - int ret = xt_register_template(&packet_mangler, - iptable_mangle_table_init); - if (ret < 0) - return ret; + int ret; mangle_ops = xt_hook_ops_alloc(&packet_mangler, iptable_mangle_hook); - if (IS_ERR(mangle_ops)) { - xt_unregister_template(&packet_mangler); - ret = PTR_ERR(mangle_ops); - return ret; - } + if (IS_ERR(mangle_ops)) + return PTR_ERR(mangle_ops); ret = register_pernet_subsys(&iptable_mangle_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(&packet_mangler, + iptable_mangle_table_init); if (ret < 0) { - xt_unregister_template(&packet_mangler); - kfree(mangle_ops); - return ret; + unregister_pernet_subsys(&iptable_mangle_net_ops); + goto err_free; } + return 0; +err_free: + kfree(mangle_ops); return ret; } static void __exit iptable_mangle_fini(void) { - unregister_pernet_subsys(&iptable_mangle_net_ops); xt_unregister_template(&packet_mangler); + unregister_pernet_subsys(&iptable_mangle_net_ops); kfree(mangle_ops); } diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index 625a1ca13b1b..a0df72554025 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -119,8 +119,11 @@ static int iptable_nat_table_init(struct net *net) } ret = ipt_nat_register_lookups(net); - if (ret < 0) + if (ret < 0) { + xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "nat"); + synchronize_rcu(); ipt_unregister_table_exit(net, "nat"); + } kfree(repl); return ret; @@ -129,6 +132,7 @@ static int iptable_nat_table_init(struct net *net) static void __net_exit iptable_nat_net_pre_exit(struct net *net) { ipt_nat_unregister_lookups(net); + xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "nat"); } static void __net_exit iptable_nat_net_exit(struct net *net) diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 0e7f53964d0a..2745c22f4034 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -53,7 +53,7 @@ static int iptable_raw_table_init(struct net *net) static void __net_exit iptable_raw_net_pre_exit(struct net *net) { - ipt_unregister_table_pre_exit(net, "raw"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "raw"); } static void __net_exit iptable_raw_net_exit(struct net *net) @@ -77,32 +77,32 @@ static int __init iptable_raw_init(void) pr_info("Enabling raw table before defrag\n"); } - ret = xt_register_template(table, - iptable_raw_table_init); - if (ret < 0) - return ret; - rawtable_ops = xt_hook_ops_alloc(table, ipt_do_table); - if (IS_ERR(rawtable_ops)) { - xt_unregister_template(table); + if (IS_ERR(rawtable_ops)) return PTR_ERR(rawtable_ops); - } ret = register_pernet_subsys(&iptable_raw_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(table, + iptable_raw_table_init); if (ret < 0) { - xt_unregister_template(table); - kfree(rawtable_ops); - return ret; + unregister_pernet_subsys(&iptable_raw_net_ops); + goto err_free; } + return 0; +err_free: + kfree(rawtable_ops); return ret; } static void __exit iptable_raw_fini(void) { + xt_unregister_template(&packet_raw); unregister_pernet_subsys(&iptable_raw_net_ops); kfree(rawtable_ops); - xt_unregister_template(&packet_raw); } module_init(iptable_raw_init); diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index d885443cb267..491894511c54 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -50,7 +50,7 @@ static int iptable_security_table_init(struct net *net) static void __net_exit iptable_security_net_pre_exit(struct net *net) { - ipt_unregister_table_pre_exit(net, "security"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV4, "security"); } static void __net_exit iptable_security_net_exit(struct net *net) @@ -65,33 +65,34 @@ static struct pernet_operations iptable_security_net_ops = { static int __init iptable_security_init(void) { - int ret = xt_register_template(&security_table, - iptable_security_table_init); - - if (ret < 0) - return ret; + int ret; sectbl_ops = xt_hook_ops_alloc(&security_table, ipt_do_table); - if (IS_ERR(sectbl_ops)) { - xt_unregister_template(&security_table); + if (IS_ERR(sectbl_ops)) return PTR_ERR(sectbl_ops); - } ret = register_pernet_subsys(&iptable_security_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(&security_table, + iptable_security_table_init); if (ret < 0) { - xt_unregister_template(&security_table); - kfree(sectbl_ops); - return ret; + unregister_pernet_subsys(&iptable_security_net_ops); + goto err_free; } + return 0; +err_free: + kfree(sectbl_ops); return ret; } static void __exit iptable_security_fini(void) { + xt_unregister_template(&security_table); unregister_pernet_subsys(&iptable_security_net_ops); kfree(sectbl_ops); - xt_unregister_template(&security_table); } module_init(iptable_security_init); diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index a97cdf3e6af4..0a4b38b315fe 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -116,7 +116,8 @@ struct tcp_ao_key *tcp_ao_established_key(const struct sock *sk, { struct tcp_ao_key *key; - hlist_for_each_entry_rcu(key, &ao->head, node, lockdep_sock_is_held(sk)) { + hlist_for_each_entry_rcu(key, &ao->head, node, + sk_fullsock(sk) && lockdep_sock_is_held(sk)) { if ((sndid >= 0 && key->sndid != sndid) || (rcvid >= 0 && key->rcvid != rcvid)) continue; diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index c92f98c6f6ec..b1ccdf0dc646 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -36,11 +36,11 @@ /* FL hash table */ #define FL_MAX_PER_SOCK 32 -#define FL_MAX_SIZE 4096 +#define FL_MAX_SIZE 8192 #define FL_HASH_MASK 255 #define FL_HASH(l) (ntohl(l)&FL_HASH_MASK) -static atomic_t fl_size = ATOMIC_INIT(0); +static int fl_size; static struct ip6_flowlabel __rcu *fl_ht[FL_HASH_MASK+1]; static void ip6_fl_gc(struct timer_list *unused); @@ -162,8 +162,9 @@ static void ip6_fl_gc(struct timer_list *unused) ttd = fl->expires; if (time_after_eq(now, ttd)) { *flp = fl->next; + fl_size--; + fl->fl_net->ipv6.flowlabel_count--; fl_free(fl); - atomic_dec(&fl_size); continue; } if (!sched || time_before(ttd, sched)) @@ -172,7 +173,7 @@ static void ip6_fl_gc(struct timer_list *unused) flp = &fl->next; } } - if (!sched && atomic_read(&fl_size)) + if (!sched && fl_size) sched = now + FL_MAX_LINGER; if (sched) { mod_timer(&ip6_fl_gc_timer, sched); @@ -196,7 +197,8 @@ static void __net_exit ip6_fl_purge(struct net *net) atomic_read(&fl->users) == 0) { *flp = fl->next; fl_free(fl); - atomic_dec(&fl_size); + fl_size--; + net->ipv6.flowlabel_count--; continue; } flp = &fl->next; @@ -210,10 +212,10 @@ static struct ip6_flowlabel *fl_intern(struct net *net, { struct ip6_flowlabel *lfl; + lockdep_assert_held(&ip6_fl_lock); + fl->label = label & IPV6_FLOWLABEL_MASK; - rcu_read_lock(); - spin_lock_bh(&ip6_fl_lock); if (label == 0) { for (;;) { fl->label = htonl(get_random_u32())&IPV6_FLOWLABEL_MASK; @@ -235,8 +237,6 @@ static struct ip6_flowlabel *fl_intern(struct net *net, lfl = __fl_lookup(net, fl->label); if (lfl) { atomic_inc(&lfl->users); - spin_unlock_bh(&ip6_fl_lock); - rcu_read_unlock(); return lfl; } } @@ -244,9 +244,8 @@ static struct ip6_flowlabel *fl_intern(struct net *net, fl->lastuse = jiffies; fl->next = fl_ht[FL_HASH(fl->label)]; rcu_assign_pointer(fl_ht[FL_HASH(fl->label)], fl); - atomic_inc(&fl_size); - spin_unlock_bh(&ip6_fl_lock); - rcu_read_unlock(); + fl_size++; + net->ipv6.flowlabel_count++; return NULL; } @@ -464,10 +463,17 @@ done: static int mem_check(struct sock *sk) { - int room = FL_MAX_SIZE - atomic_read(&fl_size); + const int unpriv_total_limit = FL_MAX_SIZE - (FL_MAX_SIZE / 4); + const int unpriv_user_limit = unpriv_total_limit / 2; + struct net *net = sock_net(sk); + int room; struct ipv6_fl_socklist *sfl; int count = 0; + lockdep_assert_held(&ip6_fl_lock); + + room = FL_MAX_SIZE - fl_size; + if (room > FL_MAX_SIZE - FL_MAX_PER_SOCK) return 0; @@ -478,7 +484,9 @@ static int mem_check(struct sock *sk) if (room <= 0 || ((count >= FL_MAX_PER_SOCK || - (count > 0 && room < FL_MAX_SIZE/2) || room < FL_MAX_SIZE/4) && + (count > 0 && room < FL_MAX_SIZE / 2) || + room < FL_MAX_SIZE / 4 || + net->ipv6.flowlabel_count >= unpriv_user_limit) && !capable(CAP_NET_ADMIN))) return -ENOBUFS; @@ -692,11 +700,19 @@ release: if (!sfl1) goto done; + rcu_read_lock(); + spin_lock_bh(&ip6_fl_lock); err = mem_check(sk); + if (err == 0) + fl1 = fl_intern(net, fl, freq->flr_label); + else + fl1 = NULL; + spin_unlock_bh(&ip6_fl_lock); + rcu_read_unlock(); + if (err != 0) goto done; - fl1 = fl_intern(net, fl, freq->flr_label); if (fl1) goto recheck; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index d585ac3c1113..9d9c3763f2f5 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1713,12 +1713,10 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) static void __ip6t_unregister_table(struct net *net, struct xt_table *table) { - struct xt_table_info *private; - void *loc_cpu_entry; + struct xt_table_info *private = table->private; struct module *table_owner = table->me; struct ip6t_entry *iter; - - private = xt_unregister_table(table); + void *loc_cpu_entry; /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries; @@ -1727,19 +1725,18 @@ static void __ip6t_unregister_table(struct net *net, struct xt_table *table) if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); + kfree(table); } int ip6t_register_table(struct net *net, const struct xt_table *table, const struct ip6t_replace *repl, const struct nf_hook_ops *template_ops) { - struct nf_hook_ops *ops; - unsigned int num_ops; - int ret, i; - struct xt_table_info *newinfo; struct xt_table_info bootstrap = {0}; - void *loc_cpu_entry; + struct xt_table_info *newinfo; struct xt_table *new_table; + void *loc_cpu_entry; + int ret; newinfo = xt_alloc_table_info(repl->size); if (!newinfo) @@ -1754,7 +1751,7 @@ int ip6t_register_table(struct net *net, const struct xt_table *table, return ret; } - new_table = xt_register_table(net, table, &bootstrap, newinfo); + new_table = xt_register_table(net, table, template_ops, &bootstrap, newinfo); if (IS_ERR(new_table)) { struct ip6t_entry *iter; @@ -1764,48 +1761,12 @@ int ip6t_register_table(struct net *net, const struct xt_table *table, return PTR_ERR(new_table); } - if (!template_ops) - return 0; - - num_ops = hweight32(table->valid_hooks); - if (num_ops == 0) { - ret = -EINVAL; - goto out_free; - } - - ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL); - if (!ops) { - ret = -ENOMEM; - goto out_free; - } - - for (i = 0; i < num_ops; i++) - ops[i].priv = new_table; - - new_table->ops = ops; - - ret = nf_register_net_hooks(net, ops, num_ops); - if (ret != 0) - goto out_free; - return ret; - -out_free: - __ip6t_unregister_table(net, new_table); - return ret; -} - -void ip6t_unregister_table_pre_exit(struct net *net, const char *name) -{ - struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name); - - if (table) - nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); } void ip6t_unregister_table_exit(struct net *net, const char *name) { - struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name); + struct xt_table *table = xt_unregister_table_exit(net, NFPROTO_IPV6, name); if (table) __ip6t_unregister_table(net, table); @@ -1894,7 +1855,6 @@ static void __exit ip6_tables_fini(void) } EXPORT_SYMBOL(ip6t_register_table); -EXPORT_SYMBOL(ip6t_unregister_table_pre_exit); EXPORT_SYMBOL(ip6t_unregister_table_exit); EXPORT_SYMBOL(ip6t_do_table); diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index e8992693e14a..b074fc477676 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -60,7 +60,7 @@ static int __net_init ip6table_filter_net_init(struct net *net) static void __net_exit ip6table_filter_net_pre_exit(struct net *net) { - ip6t_unregister_table_pre_exit(net, "filter"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "filter"); } static void __net_exit ip6table_filter_net_exit(struct net *net) @@ -76,32 +76,32 @@ static struct pernet_operations ip6table_filter_net_ops = { static int __init ip6table_filter_init(void) { - int ret = xt_register_template(&packet_filter, - ip6table_filter_table_init); - - if (ret < 0) - return ret; + int ret; filter_ops = xt_hook_ops_alloc(&packet_filter, ip6t_do_table); - if (IS_ERR(filter_ops)) { - xt_unregister_template(&packet_filter); + if (IS_ERR(filter_ops)) return PTR_ERR(filter_ops); - } ret = register_pernet_subsys(&ip6table_filter_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(&packet_filter, ip6table_filter_table_init); if (ret < 0) { - xt_unregister_template(&packet_filter); - kfree(filter_ops); - return ret; + unregister_pernet_subsys(&ip6table_filter_net_ops); + goto err_free; } + return 0; +err_free: + kfree(filter_ops); return ret; } static void __exit ip6table_filter_fini(void) { - unregister_pernet_subsys(&ip6table_filter_net_ops); xt_unregister_template(&packet_filter); + unregister_pernet_subsys(&ip6table_filter_net_ops); kfree(filter_ops); } diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 8dd4cd0c47bd..e6ee036a9b2c 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -89,7 +89,7 @@ static int ip6table_mangle_table_init(struct net *net) static void __net_exit ip6table_mangle_net_pre_exit(struct net *net) { - ip6t_unregister_table_pre_exit(net, "mangle"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "mangle"); } static void __net_exit ip6table_mangle_net_exit(struct net *net) @@ -104,32 +104,33 @@ static struct pernet_operations ip6table_mangle_net_ops = { static int __init ip6table_mangle_init(void) { - int ret = xt_register_template(&packet_mangler, - ip6table_mangle_table_init); - - if (ret < 0) - return ret; + int ret; mangle_ops = xt_hook_ops_alloc(&packet_mangler, ip6table_mangle_hook); - if (IS_ERR(mangle_ops)) { - xt_unregister_template(&packet_mangler); + if (IS_ERR(mangle_ops)) return PTR_ERR(mangle_ops); - } ret = register_pernet_subsys(&ip6table_mangle_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(&packet_mangler, + ip6table_mangle_table_init); if (ret < 0) { - xt_unregister_template(&packet_mangler); - kfree(mangle_ops); - return ret; + unregister_pernet_subsys(&ip6table_mangle_net_ops); + goto err_free; } + return 0; +err_free: + kfree(mangle_ops); return ret; } static void __exit ip6table_mangle_fini(void) { - unregister_pernet_subsys(&ip6table_mangle_net_ops); xt_unregister_template(&packet_mangler); + unregister_pernet_subsys(&ip6table_mangle_net_ops); kfree(mangle_ops); } diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index 5be723232df8..c2394e2c94b5 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -121,8 +121,11 @@ static int ip6table_nat_table_init(struct net *net) } ret = ip6t_nat_register_lookups(net); - if (ret < 0) + if (ret < 0) { + xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "nat"); + synchronize_rcu(); ip6t_unregister_table_exit(net, "nat"); + } kfree(repl); return ret; @@ -131,6 +134,7 @@ static int ip6table_nat_table_init(struct net *net) static void __net_exit ip6table_nat_net_pre_exit(struct net *net) { ip6t_nat_unregister_lookups(net); + xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "nat"); } static void __net_exit ip6table_nat_net_exit(struct net *net) diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index fc9f6754028f..3b161ee875bc 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -52,7 +52,7 @@ static int ip6table_raw_table_init(struct net *net) static void __net_exit ip6table_raw_net_pre_exit(struct net *net) { - ip6t_unregister_table_pre_exit(net, "raw"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "raw"); } static void __net_exit ip6table_raw_net_exit(struct net *net) @@ -75,31 +75,31 @@ static int __init ip6table_raw_init(void) pr_info("Enabling raw table before defrag\n"); } - ret = xt_register_template(table, ip6table_raw_table_init); - if (ret < 0) - return ret; - /* Register hooks */ rawtable_ops = xt_hook_ops_alloc(table, ip6t_do_table); - if (IS_ERR(rawtable_ops)) { - xt_unregister_template(table); + if (IS_ERR(rawtable_ops)) return PTR_ERR(rawtable_ops); - } ret = register_pernet_subsys(&ip6table_raw_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(table, ip6table_raw_table_init); if (ret < 0) { - kfree(rawtable_ops); - xt_unregister_template(table); - return ret; + unregister_pernet_subsys(&ip6table_raw_net_ops); + goto err_free; } + return 0; +err_free: + kfree(rawtable_ops); return ret; } static void __exit ip6table_raw_fini(void) { - unregister_pernet_subsys(&ip6table_raw_net_ops); xt_unregister_template(&packet_raw); + unregister_pernet_subsys(&ip6table_raw_net_ops); kfree(rawtable_ops); } diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index 4df14a9bae78..4bd5d97b8ab6 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -49,7 +49,7 @@ static int ip6table_security_table_init(struct net *net) static void __net_exit ip6table_security_net_pre_exit(struct net *net) { - ip6t_unregister_table_pre_exit(net, "security"); + xt_unregister_table_pre_exit(net, NFPROTO_IPV6, "security"); } static void __net_exit ip6table_security_net_exit(struct net *net) @@ -64,32 +64,33 @@ static struct pernet_operations ip6table_security_net_ops = { static int __init ip6table_security_init(void) { - int ret = xt_register_template(&security_table, - ip6table_security_table_init); - - if (ret < 0) - return ret; + int ret; sectbl_ops = xt_hook_ops_alloc(&security_table, ip6t_do_table); - if (IS_ERR(sectbl_ops)) { - xt_unregister_template(&security_table); + if (IS_ERR(sectbl_ops)) return PTR_ERR(sectbl_ops); - } ret = register_pernet_subsys(&ip6table_security_net_ops); + if (ret < 0) + goto err_free; + + ret = xt_register_template(&security_table, + ip6table_security_table_init); if (ret < 0) { - kfree(sectbl_ops); - xt_unregister_template(&security_table); - return ret; + unregister_pernet_subsys(&ip6table_security_net_ops); + goto err_free; } + return 0; +err_free: + kfree(sectbl_ops); return ret; } static void __exit ip6table_security_fini(void) { - unregister_pernet_subsys(&ip6table_security_net_ops); xt_unregister_template(&security_table); + unregister_pernet_subsys(&ip6table_security_net_ops); kfree(sectbl_ops); } diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c index 4f39bf7c843f..75e53fde6b29 100644 --- a/net/netfilter/nf_conntrack_broadcast.c +++ b/net/netfilter/nf_conntrack_broadcast.c @@ -72,6 +72,7 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb, exp->flags = NF_CT_EXPECT_PERMANENT; exp->class = NF_CT_EXPECT_CLASS_DEFAULT; rcu_assign_pointer(exp->helper, helper); + rcu_assign_pointer(exp->assign_helper, NULL); write_pnet(&exp->net, net); #ifdef CONFIG_NF_CONNTRACK_ZONES exp->zone = ct->zone; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index b08189226320..8ba5b22a1eef 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1811,14 +1811,17 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, spin_lock_bh(&nf_conntrack_expect_lock); exp = nf_ct_find_expectation(net, zone, tuple, !tmpl || nf_ct_is_confirmed(tmpl)); if (exp) { + struct nf_conntrack_helper *assign_helper; + /* Welcome, Mr. Bond. We've been expecting you... */ __set_bit(IPS_EXPECTED_BIT, &ct->status); /* exp->master safe, refcnt bumped in nf_ct_find_expectation */ ct->master = exp->master; - if (exp->helper) { + assign_helper = rcu_dereference(exp->assign_helper); + if (assign_helper) { help = nf_ct_helper_ext_add(ct, GFP_ATOMIC); if (help) - rcu_assign_pointer(help->helper, exp->helper); + rcu_assign_pointer(help->helper, assign_helper); } #ifdef CONFIG_NF_CONNTRACK_MARK diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 24d0576d84b7..8e943efbdf0a 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -344,6 +344,7 @@ void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class, helper = rcu_dereference(help->helper); rcu_assign_pointer(exp->helper, helper); + rcu_assign_pointer(exp->assign_helper, NULL); write_pnet(&exp->net, net); #ifdef CONFIG_NF_CONNTRACK_ZONES exp->zone = ct->zone; diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 3f5c50455b71..b2fe6554b9cf 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -643,7 +643,7 @@ static int expect_h245(struct sk_buff *skb, struct nf_conn *ct, &ct->tuplehash[!dir].tuple.src.u3, &ct->tuplehash[!dir].tuple.dst.u3, IPPROTO_TCP, NULL, &port); - rcu_assign_pointer(exp->helper, &nf_conntrack_helper_h245); + rcu_assign_pointer(exp->assign_helper, &nf_conntrack_helper_h245); nathook = rcu_dereference(nfct_h323_nat_hook); if (memcmp(&ct->tuplehash[dir].tuple.src.u3, @@ -767,7 +767,7 @@ static int expect_callforwarding(struct sk_buff *skb, nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct), &ct->tuplehash[!dir].tuple.src.u3, &addr, IPPROTO_TCP, NULL, &port); - rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931); + rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931); nathook = rcu_dereference(nfct_h323_nat_hook); if (memcmp(&ct->tuplehash[dir].tuple.src.u3, @@ -1234,7 +1234,7 @@ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct, &ct->tuplehash[!dir].tuple.src.u3 : NULL, &ct->tuplehash[!dir].tuple.dst.u3, IPPROTO_TCP, NULL, &port); - rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931); + rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931); exp->flags = NF_CT_EXPECT_PERMANENT; /* Accept multiple calls */ nathook = rcu_dereference(nfct_h323_nat_hook); @@ -1306,7 +1306,7 @@ static int process_gcf(struct sk_buff *skb, struct nf_conn *ct, nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct), &ct->tuplehash[!dir].tuple.src.u3, &addr, IPPROTO_UDP, NULL, &port); - rcu_assign_pointer(exp->helper, nf_conntrack_helper_ras); + rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_ras); if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect RAS "); @@ -1523,7 +1523,7 @@ static int process_acf(struct sk_buff *skb, struct nf_conn *ct, &ct->tuplehash[!dir].tuple.src.u3, &addr, IPPROTO_TCP, NULL, &port); exp->flags = NF_CT_EXPECT_PERMANENT; - rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931); + rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931); if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect Q.931 "); @@ -1577,7 +1577,7 @@ static int process_lcf(struct sk_buff *skb, struct nf_conn *ct, &ct->tuplehash[!dir].tuple.src.u3, &addr, IPPROTO_TCP, NULL, &port); exp->flags = NF_CT_EXPECT_PERMANENT; - rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931); + rcu_assign_pointer(exp->assign_helper, nf_conntrack_helper_q931); if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect Q.931 "); diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index a715304a53d8..b594cd244fe1 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -400,6 +400,11 @@ static bool expect_iter_me(struct nf_conntrack_expect *exp, void *data) this = rcu_dereference_protected(exp->helper, lockdep_is_held(&nf_conntrack_expect_lock)); + if (this == me) + return true; + + this = rcu_dereference_protected(exp->assign_helper, + lockdep_is_held(&nf_conntrack_expect_lock)); return this == me; } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index eda5fe4a75c8..befa7e83ee49 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2634,6 +2634,7 @@ static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = { static struct nf_conntrack_expect * ctnetlink_alloc_expect(const struct nlattr *const cda[], struct nf_conn *ct, + const struct nf_conntrack_helper *assign_helper, struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *mask); @@ -2860,6 +2861,7 @@ static int ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, u32 portid, u32 report) { + struct nf_conntrack_helper *assign_helper = NULL; struct nlattr *cda[CTA_EXPECT_MAX+1]; struct nf_conntrack_tuple tuple, mask; struct nf_conntrack_expect *exp; @@ -2870,13 +2872,26 @@ ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, if (err < 0) return err; + if (!cda[CTA_EXPECT_TUPLE] || !cda[CTA_EXPECT_MASK]) + return -EINVAL; + err = ctnetlink_glue_exp_parse((const struct nlattr * const *)cda, ct, &tuple, &mask); if (err < 0) return err; + if (cda[CTA_EXPECT_HELP_NAME]) { + const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]); + + assign_helper = __nf_conntrack_helper_find(helpname, + nf_ct_l3num(ct), + tuple.dst.protonum); + if (!assign_helper) + return -EOPNOTSUPP; + } + exp = ctnetlink_alloc_expect((const struct nlattr * const *)cda, ct, - &tuple, &mask); + assign_helper, &tuple, &mask); if (IS_ERR(exp)) return PTR_ERR(exp); @@ -3515,6 +3530,7 @@ ctnetlink_parse_expect_nat(const struct nlattr *attr, static struct nf_conntrack_expect * ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct, + const struct nf_conntrack_helper *assign_helper, struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *mask) { @@ -3568,6 +3584,7 @@ ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct, exp->zone = ct->zone; #endif rcu_assign_pointer(exp->helper, helper); + rcu_assign_pointer(exp->assign_helper, assign_helper); exp->tuple = *tuple; exp->mask.src.u3 = mask->src.u3; exp->mask.src.u.all = mask->src.u.all; @@ -3623,7 +3640,7 @@ ctnetlink_create_expect(struct net *net, ct = nf_ct_tuplehash_to_ctrack(h); rcu_read_lock(); - exp = ctnetlink_alloc_expect(cda, ct, &tuple, &mask); + exp = ctnetlink_alloc_expect(cda, ct, NULL, &tuple, &mask); if (IS_ERR(exp)) { err = PTR_ERR(exp); goto err_rcu; diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 1eb55907d470..e69941f1a101 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1366,6 +1366,10 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff, goto store_cseq; } + helper = rcu_dereference(nfct_help(ct)->helper); + if (!helper) + return NF_DROP; + exp = nf_ct_expect_alloc(ct); if (!exp) { nf_ct_helper_log(skb, ct, "cannot alloc expectation"); @@ -1376,14 +1380,10 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff, if (sip_direct_signalling) saddr = &ct->tuplehash[!dir].tuple.src.u3; - helper = rcu_dereference(nfct_help(ct)->helper); - if (!helper) - return NF_DROP; - nf_ct_expect_init(exp, SIP_EXPECT_SIGNALLING, nf_ct_l3num(ct), saddr, &daddr, proto, NULL, &port); exp->timeout.expires = sip_timeout * HZ; - rcu_assign_pointer(exp->helper, helper); + rcu_assign_pointer(exp->assign_helper, helper); exp->flags = NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE; hooks = rcu_dereference(nf_nat_sip_hooks); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 60ee8d932fcb..fa2cc556331c 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -1334,6 +1334,8 @@ static void nft_ct_expect_obj_eval(struct nft_object *obj, if (nf_ct_expect_related(exp, 0) != 0) regs->verdict.code = NF_DROP; + + nf_ct_expect_put(exp); } static const struct nla_policy nft_ct_expect_policy[NFTA_CT_EXPECT_MAX + 1] = { diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 2c67c2e6b132..4e6708c23922 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -55,6 +55,9 @@ static struct list_head xt_templates[NFPROTO_NUMPROTO]; struct xt_pernet { struct list_head tables[NFPROTO_NUMPROTO]; + + /* stash area used during netns exit */ + struct list_head dead_tables[NFPROTO_NUMPROTO]; }; struct compat_delta { @@ -1472,11 +1475,9 @@ struct xt_counters *xt_counters_alloc(unsigned int counters) } EXPORT_SYMBOL(xt_counters_alloc); -struct xt_table_info * -xt_replace_table(struct xt_table *table, - unsigned int num_counters, - struct xt_table_info *newinfo, - int *error) +static struct xt_table_info * +do_replace_table(struct xt_table *table, unsigned int num_counters, + struct xt_table_info *newinfo, int *error) { struct xt_table_info *private; unsigned int cpu; @@ -1531,30 +1532,54 @@ xt_replace_table(struct xt_table *table, } } - audit_log_nfcfg(table->name, table->af, private->number, - !private->number ? AUDIT_XT_OP_REGISTER : - AUDIT_XT_OP_REPLACE, - GFP_KERNEL); + return private; +} + +struct xt_table_info * +xt_replace_table(struct xt_table *table, unsigned int num_counters, + struct xt_table_info *newinfo, + int *error) +{ + struct xt_table_info *private; + + private = do_replace_table(table, num_counters, newinfo, error); + if (private) + audit_log_nfcfg(table->name, table->af, private->number, + AUDIT_XT_OP_REPLACE, + GFP_KERNEL); + return private; } EXPORT_SYMBOL_GPL(xt_replace_table); struct xt_table *xt_register_table(struct net *net, const struct xt_table *input_table, + const struct nf_hook_ops *template_ops, struct xt_table_info *bootstrap, struct xt_table_info *newinfo) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); + struct xt_table *t, *table = NULL; + struct nf_hook_ops *ops = NULL; struct xt_table_info *private; - struct xt_table *t, *table; - int ret; + unsigned int num_ops; + int ret = -EINVAL; + + num_ops = hweight32(input_table->valid_hooks); + if (num_ops == 0) + goto out; + + ret = -ENOMEM; + if (template_ops) { + ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL); + if (!ops) + goto out; + } /* Don't add one object to multiple lists. */ table = kmemdup(input_table, sizeof(struct xt_table), GFP_KERNEL); - if (!table) { - ret = -ENOMEM; + if (!table) goto out; - } mutex_lock(&xt[table->af].mutex); /* Don't autoload: we'd eat our tail... */ @@ -1568,7 +1593,7 @@ struct xt_table *xt_register_table(struct net *net, /* Simplifies replace_table code. */ table->private = bootstrap; - if (!xt_replace_table(table, 0, newinfo, &ret)) + if (!do_replace_table(table, 0, newinfo, &ret)) goto unlock; private = table->private; @@ -1577,34 +1602,122 @@ struct xt_table *xt_register_table(struct net *net, /* save number of initial entries */ private->initial_entries = private->number; + if (ops) { + int i; + + for (i = 0; i < num_ops; i++) + ops[i].priv = table; + + ret = nf_register_net_hooks(net, ops, num_ops); + if (ret != 0) { + mutex_unlock(&xt[table->af].mutex); + /* nf_register_net_hooks() might have published a + * base chain before internal error unwind. + */ + synchronize_rcu(); + goto out; + } + + table->ops = ops; + } + + audit_log_nfcfg(table->name, table->af, private->number, + AUDIT_XT_OP_REGISTER, GFP_KERNEL); + list_add(&table->list, &xt_net->tables[table->af]); mutex_unlock(&xt[table->af].mutex); return table; unlock: mutex_unlock(&xt[table->af].mutex); - kfree(table); out: + kfree(table); + kfree(ops); return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(xt_register_table); -void *xt_unregister_table(struct xt_table *table) +/** + * xt_unregister_table_pre_exit - pre-shutdown unregister of a table + * @net: network namespace + * @af: address family (e.g., NFPROTO_IPV4, NFPROTO_IPV6) + * @name: name of the table to unregister + * + * Unregisters the specified netfilter table from the given network namespace + * and also unregisters the hooks from netfilter core: no new packets will be + * processed. + * + * This must be called prior to xt_unregister_table_exit() from the pernet + * .pre_exit callback. After this call, the table is no longer visible to + * the get/setsockopt path. In case of rmmod, module exit path must have + * called xt_unregister_template() prior to unregistering pernet ops to + * prevent re-instantiation of the table. + * + * See also: xt_unregister_table_exit() + */ +void xt_unregister_table_pre_exit(struct net *net, u8 af, const char *name) { - struct xt_table_info *private; + struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); + struct xt_table *t; - mutex_lock(&xt[table->af].mutex); - private = table->private; - list_del(&table->list); - mutex_unlock(&xt[table->af].mutex); - audit_log_nfcfg(table->name, table->af, private->number, - AUDIT_XT_OP_UNREGISTER, GFP_KERNEL); - kfree(table->ops); - kfree(table); + mutex_lock(&xt[af].mutex); + list_for_each_entry(t, &xt_net->tables[af], list) { + if (strcmp(t->name, name) == 0) { + list_move(&t->list, &xt_net->dead_tables[af]); + mutex_unlock(&xt[af].mutex); - return private; + if (t->ops) /* nat table registers with nat core, t->ops is NULL. */ + nf_unregister_net_hooks(net, t->ops, hweight32(t->valid_hooks)); + return; + } + } + mutex_unlock(&xt[af].mutex); +} +EXPORT_SYMBOL(xt_unregister_table_pre_exit); + +/** + * xt_unregister_table_exit - remove a table during namespace teardown + * @net: the network namespace from which to unregister the table + * @af: address family (e.g., NFPROTO_IPV4, NFPROTO_IPV6) + * @name: name of the table to unregister + * + * Completes the unregister process for a table. This must be called from + * the pernet ops .exit callback. This is the second stage after + * xt_unregister_table_pre_exit(). + * + * pair with xt_unregister_table_pre_exit() during namespace shutdown. + * + * Return: the unregistered table or NULL if the table was never + * instantiated. The caller needs to kfree() the table after it + * has removed the family specific matches/targets. + */ +struct xt_table *xt_unregister_table_exit(struct net *net, u8 af, const char *name) +{ + struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); + struct xt_table *table; + + mutex_lock(&xt[af].mutex); + list_for_each_entry(table, &xt_net->dead_tables[af], list) { + struct nf_hook_ops *ops = NULL; + + if (strcmp(table->name, name) != 0) + continue; + + list_del(&table->list); + + audit_log_nfcfg(table->name, table->af, table->private->number, + AUDIT_XT_OP_UNREGISTER, GFP_KERNEL); + swap(table->ops, ops); + mutex_unlock(&xt[af].mutex); + + kfree(ops); + return table; + } + mutex_unlock(&xt[af].mutex); + + return NULL; } -EXPORT_SYMBOL_GPL(xt_unregister_table); +EXPORT_SYMBOL_GPL(xt_unregister_table_exit); #endif #ifdef CONFIG_PROC_FS @@ -2051,8 +2164,10 @@ static int __net_init xt_net_init(struct net *net) struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); int i; - for (i = 0; i < NFPROTO_NUMPROTO; i++) + for (i = 0; i < NFPROTO_NUMPROTO; i++) { INIT_LIST_HEAD(&xt_net->tables[i]); + INIT_LIST_HEAD(&xt_net->dead_tables[i]); + } return 0; } @@ -2061,8 +2176,10 @@ static void __net_exit xt_net_exit(struct net *net) struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); int i; - for (i = 0; i < NFPROTO_NUMPROTO; i++) + for (i = 0; i < NFPROTO_NUMPROTO; i++) { WARN_ON_ONCE(!list_empty(&xt_net->tables[i])); + WARN_ON_ONCE(!list_empty(&xt_net->dead_tables[i])); + } } static struct pernet_operations xt_net_ops = { diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index d251d894afd4..0da39eaed255 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1972,8 +1972,10 @@ int genlmsg_multicast_allns(const struct genl_family *family, struct sk_buff *skb, u32 portid, unsigned int group) { - if (WARN_ON_ONCE(group >= family->n_mcgrps)) + if (WARN_ON_ONCE(group >= family->n_mcgrps)) { + kfree_skb(skb); return -EINVAL; + } group = family->mcgrp_offset + group; return genlmsg_mcast(skb, portid, group); @@ -1986,8 +1988,10 @@ void genl_notify(const struct genl_family *family, struct sk_buff *skb, struct net *net = genl_info_net(info); struct sock *sk = net->genl_sock; - if (WARN_ON_ONCE(group >= family->n_mcgrps)) + if (WARN_ON_ONCE(group >= family->n_mcgrps)) { + kfree_skb(skb); return; + } group = family->mcgrp_offset + group; nlmsg_notify(sk, skb, info->snd_portid, group, diff --git a/net/rds/message.c b/net/rds/message.c index 25fedcb3cd00..7feb0eb6537d 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -448,6 +448,7 @@ static int rds_message_zcopy_from_user(struct rds_message *rm, struct iov_iter * for (i = 0; i < rm->data.op_nents; i++) put_page(sg_page(&rm->data.op_sg[i])); + rm->data.op_nents = 0; mmp = &rm->data.op_mmp_znotifier->z_mmp; mm_unaccount_pinned_pages(mmp); ret = -EFAULT; diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index 8c9a0400c862..0f953bd46b58 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -243,6 +243,20 @@ static struct sk_buff *cbs_dequeue(struct Qdisc *sch) return q->dequeue(sch); } +static void cbs_reset(struct Qdisc *sch) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + + /* Nothing to do if we couldn't create the underlying qdisc */ + if (!q->qdisc) + return; + + qdisc_reset(q->qdisc); + qdisc_watchdog_cancel(&q->watchdog); + q->credits = 0; + q->last = 0; +} + static const struct nla_policy cbs_policy[TCA_CBS_MAX + 1] = { [TCA_CBS_PARMS] = { .len = sizeof(struct tc_cbs_qopt) }, }; @@ -540,7 +554,7 @@ static struct Qdisc_ops cbs_qdisc_ops __read_mostly = { .dequeue = cbs_dequeue, .peek = qdisc_peek_dequeued, .init = cbs_init, - .reset = qdisc_reset_queue, + .reset = cbs_reset, .destroy = cbs_destroy, .change = cbs_change, .dump = cbs_dump, diff --git a/net/sched/sch_dualpi2.c b/net/sched/sch_dualpi2.c index 241e6a46bd00..a22489c14458 100644 --- a/net/sched/sch_dualpi2.c +++ b/net/sched/sch_dualpi2.c @@ -938,6 +938,8 @@ static int dualpi2_init(struct Qdisc *sch, struct nlattr *opt, int err; sch->flags |= TCQ_F_DEQUEUE_DROPS; + hrtimer_setup(&q->pi2_timer, dualpi2_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_ABS_PINNED_SOFT); q->l_queue = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, TC_H_MAKE(sch->handle, 1), extack); @@ -950,8 +952,6 @@ static int dualpi2_init(struct Qdisc *sch, struct nlattr *opt, q->sch = sch; dualpi2_reset_default(sch); - hrtimer_setup(&q->pi2_timer, dualpi2_timer, CLOCK_MONOTONIC, - HRTIMER_MODE_ABS_PINNED_SOFT); if (opt && nla_len(opt)) { err = dualpi2_change(sch, opt, extack); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 58d0d9747f0b..1d2568bb6bc2 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1986,6 +1986,15 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) goto out_unlock; iov_iter_revert(&msg->msg_iter, err); + + /* sctp_sendmsg_to_asoc() may have released the socket + * lock (sctp_wait_for_sndbuf), during which other + * associations on ep->asocs could have been peeled + * off or freed. @asoc itself is revalidated by the + * base.dead and base.sk checks in sctp_wait_for_sndbuf, + * so re-derive the cached cursor from it. + */ + tmp = list_next_entry(asoc, asocs); } goto out_unlock; diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c index 94bc9c7382ea..b1c65110f04d 100644 --- a/net/shaper/shaper.c +++ b/net/shaper/shaper.c @@ -21,6 +21,8 @@ #define NET_SHAPER_ID_UNSPEC NET_SHAPER_ID_MASK +static_assert(NET_SHAPER_ID_UNSPEC == NET_SHAPER_MAX_HANDLE_ID + 1); + struct net_shaper_hierarchy { struct xarray shapers; }; @@ -90,6 +92,12 @@ static int net_shaper_handle_size(void) nla_total_size(sizeof(u32))); } +static int net_shaper_group_reply_size(void) +{ + return nla_total_size(sizeof(u32)) + /* NET_SHAPER_A_IFINDEX */ + net_shaper_handle_size(); /* NET_SHAPER_A_HANDLE */ +} + static int net_shaper_fill_binding(struct sk_buff *msg, const struct net_shaper_binding *binding, u32 type) @@ -275,11 +283,13 @@ static void net_shaper_default_parent(const struct net_shaper_handle *handle, parent->id = 0; } -/* - * MARK_0 is already in use due to XA_FLAGS_ALLOC, can't reuse such flag as - * it's cleared by xa_store(). +/* MARK_0 is already in use due to XA_FLAGS_ALLOC. The VALID mark is set on + * an entry only after the device-side configuration has completed + * successfully (see net_shaper_commit()). Lookups and dumps must filter on + * this mark to avoid exposing tentative entries inserted by + * net_shaper_pre_insert() while the driver call is still in flight. */ -#define NET_SHAPER_NOT_VALID XA_MARK_1 +#define NET_SHAPER_VALID XA_MARK_1 static struct net_shaper * net_shaper_lookup(struct net_shaper_binding *binding, @@ -289,10 +299,14 @@ net_shaper_lookup(struct net_shaper_binding *binding, struct net_shaper_hierarchy *hierarchy; hierarchy = net_shaper_hierarchy_rcu(binding); - if (!hierarchy || xa_get_mark(&hierarchy->shapers, index, - NET_SHAPER_NOT_VALID)) + if (!hierarchy || !xa_get_mark(&hierarchy->shapers, index, + NET_SHAPER_VALID)) return NULL; + /* Pairs with smp_wmb() in net_shaper_commit(): if the entry is + * valid, its contents must be visible too. + */ + smp_rmb(); return xa_load(&hierarchy->shapers, index); } @@ -348,7 +362,7 @@ static int net_shaper_pre_insert(struct net_shaper_binding *binding, handle->id == NET_SHAPER_ID_UNSPEC) { u32 min, max; - handle->id = NET_SHAPER_ID_MASK - 1; + handle->id = NET_SHAPER_MAX_HANDLE_ID; max = net_shaper_handle_to_index(handle); handle->id = 0; min = net_shaper_handle_to_index(handle); @@ -370,13 +384,10 @@ static int net_shaper_pre_insert(struct net_shaper_binding *binding, goto free_id; } - /* Mark 'tentative' shaper inside the hierarchy container. - * xa_set_mark is a no-op if the previous store fails. + /* Insert as 'tentative' (no VALID mark). The mark will be set by + * net_shaper_commit() once the driver-side configuration succeeds. */ - xa_lock(&hierarchy->shapers); - prev = __xa_store(&hierarchy->shapers, index, cur, GFP_KERNEL); - __xa_set_mark(&hierarchy->shapers, index, NET_SHAPER_NOT_VALID); - xa_unlock(&hierarchy->shapers); + prev = xa_store(&hierarchy->shapers, index, cur, GFP_KERNEL); if (xa_err(prev)) { NL_SET_ERR_MSG(extack, "Can't insert shaper into device store"); kfree_rcu(cur, rcu); @@ -413,9 +424,9 @@ static void net_shaper_commit(struct net_shaper_binding *binding, /* Successful update: drop the tentative mark * and update the hierarchy container. */ - __xa_clear_mark(&hierarchy->shapers, index, - NET_SHAPER_NOT_VALID); *cur = shapers[i]; + smp_wmb(); + __xa_set_mark(&hierarchy->shapers, index, NET_SHAPER_VALID); } xa_unlock(&hierarchy->shapers); } @@ -431,8 +442,9 @@ static void net_shaper_rollback(struct net_shaper_binding *binding) return; xa_lock(&hierarchy->shapers); - xa_for_each_marked(&hierarchy->shapers, index, cur, - NET_SHAPER_NOT_VALID) { + xa_for_each(&hierarchy->shapers, index, cur) { + if (xa_get_mark(&hierarchy->shapers, index, NET_SHAPER_VALID)) + continue; __xa_erase(&hierarchy->shapers, index); kfree(cur); } @@ -465,10 +477,21 @@ static int net_shaper_parse_handle(const struct nlattr *attr, * shaper (any other value). */ id_attr = tb[NET_SHAPER_A_HANDLE_ID]; - if (id_attr) + if (id_attr) { id = nla_get_u32(id_attr); - else if (handle->scope == NET_SHAPER_SCOPE_NODE) + } else if (handle->scope == NET_SHAPER_SCOPE_NODE) { id = NET_SHAPER_ID_UNSPEC; + } else if (handle->scope == NET_SHAPER_SCOPE_QUEUE) { + NL_SET_ERR_ATTR_MISS(info->extack, attr, + NET_SHAPER_A_HANDLE_ID); + return -EINVAL; + } + + if (id && handle->scope == NET_SHAPER_SCOPE_NETDEV) { + NL_SET_ERR_MSG_ATTR(info->extack, id_attr, + "Netdev scope is a singleton, must use ID 0"); + return -EINVAL; + } handle->id = id; return 0; @@ -836,7 +859,12 @@ int net_shaper_nl_get_dumpit(struct sk_buff *skb, goto out_unlock; for (; (shaper = xa_find(&hierarchy->shapers, &ctx->start_index, - U32_MAX, XA_PRESENT)); ctx->start_index++) { + U32_MAX, NET_SHAPER_VALID)); + ctx->start_index++) { + /* Pairs with smp_wmb() in net_shaper_commit(): the entry + * is marked VALID, so its contents must be visible too. + */ + smp_rmb(); ret = net_shaper_fill_one(skb, binding, shaper, info); if (ret) break; @@ -932,6 +960,46 @@ static int net_shaper_handle_cmp(const struct net_shaper_handle *a, return memcmp(a, b, sizeof(*a)); } +static int net_shaper_parse_leaves(struct net_shaper_binding *binding, + struct genl_info *info, + const struct net_shaper *node, + struct net_shaper *leaves, + int leaves_count) +{ + struct nlattr *attr; + int i, j, ret, rem; + + i = 0; + nla_for_each_attr_type(attr, NET_SHAPER_A_LEAVES, + genlmsg_data(info->genlhdr), + genlmsg_len(info->genlhdr), rem) { + if (WARN_ON_ONCE(i >= leaves_count)) + return -EINVAL; + + ret = net_shaper_parse_leaf(binding, attr, info, + node, &leaves[i]); + if (ret) + return ret; + + /* Reject duplicates */ + for (j = 0; j < i; j++) { + if (net_shaper_handle_cmp(&leaves[i].handle, + &leaves[j].handle)) + continue; + + NL_SET_ERR_MSG_ATTR_FMT(info->extack, attr, + "Duplicate leaf shaper %d:%d", + leaves[i].handle.scope, + leaves[i].handle.id); + return -EINVAL; + } + + i++; + } + + return 0; +} + static int net_shaper_parent_from_leaves(int leaves_count, const struct net_shaper *leaves, struct net_shaper *node, @@ -964,15 +1032,22 @@ static int __net_shaper_group(struct net_shaper_binding *binding, int i, ret; if (node->handle.scope == NET_SHAPER_SCOPE_NODE) { + struct net_shaper *cur = NULL; + new_node = node->handle.id == NET_SHAPER_ID_UNSPEC; - if (!new_node && !net_shaper_lookup(binding, &node->handle)) { - /* The related attribute is not available when - * reaching here from the delete() op. - */ - NL_SET_ERR_MSG_FMT(extack, "Node shaper %d:%d does not exists", - node->handle.scope, node->handle.id); - return -ENOENT; + if (!new_node) { + cur = net_shaper_lookup(binding, &node->handle); + if (!cur) { + /* The related attribute is not available + * when reaching here from the delete() op. + */ + NL_SET_ERR_MSG_FMT(extack, + "Node shaper %d:%d does not exist", + node->handle.scope, + node->handle.id); + return -ENOENT; + } } /* When unspecified, the node parent scope is inherited from @@ -986,6 +1061,15 @@ static int __net_shaper_group(struct net_shaper_binding *binding, return ret; } + if (cur && net_shaper_handle_cmp(&cur->parent, + &node->parent)) { + NL_SET_ERR_MSG_FMT(extack, + "Cannot reparent node shaper %d:%d", + node->handle.scope, + node->handle.id); + return -EOPNOTSUPP; + } + } else { net_shaper_default_parent(&node->handle, &node->parent); } @@ -1162,7 +1246,7 @@ static int net_shaper_group_send_reply(struct net_shaper_binding *binding, free_msg: /* Should never happen as msg is pre-allocated with enough space. */ WARN_ONCE(true, "calculated message payload length (%d)", - net_shaper_handle_size()); + net_shaper_group_reply_size()); nlmsg_free(msg); return -EMSGSIZE; } @@ -1172,10 +1256,9 @@ int net_shaper_nl_group_doit(struct sk_buff *skb, struct genl_info *info) struct net_shaper **old_nodes, *leaves, node = {}; struct net_shaper_hierarchy *hierarchy; struct net_shaper_binding *binding; - int i, ret, rem, leaves_count; + int i, ret, leaves_count; int old_nodes_count = 0; struct sk_buff *msg; - struct nlattr *attr; if (GENL_REQ_ATTR_CHECK(info, NET_SHAPER_A_LEAVES)) return -EINVAL; @@ -1203,26 +1286,19 @@ int net_shaper_nl_group_doit(struct sk_buff *skb, struct genl_info *info) if (ret) goto free_leaves; - i = 0; - nla_for_each_attr_type(attr, NET_SHAPER_A_LEAVES, - genlmsg_data(info->genlhdr), - genlmsg_len(info->genlhdr), rem) { - if (WARN_ON_ONCE(i >= leaves_count)) - goto free_leaves; - - ret = net_shaper_parse_leaf(binding, attr, info, - &node, &leaves[i]); - if (ret) - goto free_leaves; - i++; - } + ret = net_shaper_parse_leaves(binding, info, &node, + leaves, leaves_count); + if (ret) + goto free_leaves; /* Prepare the msg reply in advance, to avoid device operation * rollback on allocation failure. */ - msg = genlmsg_new(net_shaper_handle_size(), GFP_KERNEL); - if (!msg) + msg = genlmsg_new(net_shaper_group_reply_size(), GFP_KERNEL); + if (!msg) { + ret = -ENOMEM; goto free_leaves; + } hierarchy = net_shaper_hierarchy_setup(binding); if (!hierarchy) { diff --git a/net/shaper/shaper_nl_gen.c b/net/shaper/shaper_nl_gen.c index 9b29be3ef19a..76eff85ec66d 100644 --- a/net/shaper/shaper_nl_gen.c +++ b/net/shaper/shaper_nl_gen.c @@ -11,10 +11,15 @@ #include <uapi/linux/net_shaper.h> +/* Integer value ranges */ +static const struct netlink_range_validation net_shaper_a_handle_id_range = { + .max = NET_SHAPER_MAX_HANDLE_ID, +}; + /* Common nested types */ const struct nla_policy net_shaper_handle_nl_policy[NET_SHAPER_A_HANDLE_ID + 1] = { [NET_SHAPER_A_HANDLE_SCOPE] = NLA_POLICY_MAX(NLA_U32, 3), - [NET_SHAPER_A_HANDLE_ID] = { .type = NLA_U32, }, + [NET_SHAPER_A_HANDLE_ID] = NLA_POLICY_FULL_RANGE(NLA_U32, &net_shaper_a_handle_id_range), }; const struct nla_policy net_shaper_leaf_info_nl_policy[NET_SHAPER_A_WEIGHT + 1] = { diff --git a/net/shaper/shaper_nl_gen.h b/net/shaper/shaper_nl_gen.h index 42c46c52c775..2406652a9014 100644 --- a/net/shaper/shaper_nl_gen.h +++ b/net/shaper/shaper_nl_gen.h @@ -12,6 +12,8 @@ #include <uapi/linux/net_shaper.h> +#define NET_SHAPER_MAX_HANDLE_ID 67108862 + /* Common nested types */ extern const struct nla_policy net_shaper_handle_nl_policy[NET_SHAPER_A_HANDLE_ID + 1]; extern const struct nla_policy net_shaper_leaf_info_nl_policy[NET_SHAPER_A_WEIGHT + 1]; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 185dbed7de5d..dffbd529762d 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1400,7 +1400,8 @@ smc_v2_determine_accepted_chid(struct smc_clc_msg_accept_confirm *aclc, int i; for (i = 0; i < ini->ism_offered_cnt + 1; i++) { - if (ini->ism_chid[i] == ntohs(aclc->d1.chid)) { + if (ini->ism_dev[i] && + ini->ism_chid[i] == ntohs(aclc->d1.chid)) { ini->ism_selected = i; return 0; } @@ -3054,18 +3055,17 @@ static int __smc_setsockopt(struct socket *sock, int level, int optname, smc = smc_sk(sk); + /* pre-fetch user data outside the lock */ + if (optname == SMC_LIMIT_HS) { + if (optlen < sizeof(int)) + return -EINVAL; + if (copy_from_sockptr(&val, optval, sizeof(int))) + return -EFAULT; + } + lock_sock(sk); switch (optname) { case SMC_LIMIT_HS: - if (optlen < sizeof(int)) { - rc = -EINVAL; - break; - } - if (copy_from_sockptr(&val, optval, sizeof(int))) { - rc = -EFAULT; - break; - } - smc->limit_smc_hs = !!val; rc = 0; break; diff --git a/net/smc/smc_tracepoint.h b/net/smc/smc_tracepoint.h index a9a6e3c1113a..53da84f57fd6 100644 --- a/net/smc/smc_tracepoint.h +++ b/net/smc/smc_tracepoint.h @@ -51,7 +51,7 @@ DECLARE_EVENT_CLASS(smc_msg_event, __field(const void *, smc) __field(u64, net_cookie) __field(size_t, len) - __string(name, smc->conn.lnk->ibname) + __string(name, smc->conn.lnk ? smc->conn.lnk->ibname : "") ), TP_fast_assign( diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 7081c1214e6c..b5474ce534fb 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -403,7 +403,7 @@ void sunrpc_init_cache_detail(struct cache_detail *cd) INIT_LIST_HEAD(&cd->readers); spin_lock_init(&cd->queue_lock); init_waitqueue_head(&cd->queue_wait); - cd->next_seqno = 0; + cd->next_seqno = 1; spin_lock(&cache_list_lock); cd->nextcheck = 0; cd->entries = 0; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 2590e855f6a5..3bfdaf5e64f5 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -789,23 +789,33 @@ static int tls_push_record(struct sock *sk, int flags, i = msg_pl->sg.end; sk_msg_iter_var_prev(i); + /* msg_pl->sg.data is a ring; data[MAX+1] is reserved for the wrap + * link (frags won't use it). 'i' is now the last filled entry: + * + * i end start + * v v v [ rsv ] + * [ d ][ d ][ ][ ]...[ ][ d ][ d ][ d ][chain] + * ^ END v + * `-----------------------------------------' + * + * Note that SGL does not allow chain-after-chain, so for TLS 1.3, + * we must make sure we don't create the wrap entry and then chain + * link to content_type immediately at index 0. + */ + if (i < msg_pl->sg.start) + sg_chain(msg_pl->sg.data, ARRAY_SIZE(msg_pl->sg.data), + msg_pl->sg.data); + rec->content_type = record_type; if (prot->version == TLS_1_3_VERSION) { /* Add content type to end of message. No padding added */ sg_set_buf(&rec->sg_content_type, &rec->content_type, 1); sg_mark_end(&rec->sg_content_type); - sg_chain(msg_pl->sg.data, msg_pl->sg.end + 1, - &rec->sg_content_type); + sg_chain(msg_pl->sg.data, i + 2, &rec->sg_content_type); } else { sg_mark_end(sk_msg_elem(msg_pl, i)); } - if (msg_pl->sg.end < msg_pl->sg.start) { - sg_chain(&msg_pl->sg.data[msg_pl->sg.start], - MAX_SKB_FRAGS - msg_pl->sg.start + 1, - msg_pl->sg.data); - } - i = msg_pl->sg.start; sg_chain(rec->sg_aead_in, 2, &msg_pl->sg.data[i]); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 9b8014516f4f..989cc252d3d3 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -136,27 +136,6 @@ static void virtio_transport_init_hdr(struct sk_buff *skb, hdr->fwd_cnt = cpu_to_le32(0); } -static void virtio_transport_copy_nonlinear_skb(const struct sk_buff *skb, - void *dst, - size_t len) -{ - struct iov_iter iov_iter = { 0 }; - struct kvec kvec; - size_t to_copy; - - kvec.iov_base = dst; - kvec.iov_len = len; - - iov_iter.iter_type = ITER_KVEC; - iov_iter.kvec = &kvec; - iov_iter.nr_segs = 1; - - to_copy = min_t(size_t, len, skb->len); - - skb_copy_datagram_iter(skb, VIRTIO_VSOCK_SKB_CB(skb)->offset, - &iov_iter, to_copy); -} - /* Packet capture */ static struct sk_buff *virtio_transport_build_skb(void *opaque) { @@ -166,12 +145,12 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) struct sk_buff *skb; size_t payload_len; - /* A packet could be split to fit the RX buffer, so we can retrieve - * the payload length from the header and the buffer pointer taking - * care of the offset in the original packet. + /* A packet could be split to fit the RX buffer, so we use + * the payload length from the header, which has been updated + * by the sender to reflect the fragment size. */ pkt_hdr = virtio_vsock_hdr(pkt); - payload_len = pkt->len; + payload_len = le32_to_cpu(pkt_hdr->len); skb = alloc_skb(sizeof(*hdr) + sizeof(*pkt_hdr) + payload_len, GFP_ATOMIC); @@ -214,12 +193,18 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) skb_put_data(skb, pkt_hdr, sizeof(*pkt_hdr)); if (payload_len) { - if (skb_is_nonlinear(pkt)) { - void *data = skb_put(skb, payload_len); - - virtio_transport_copy_nonlinear_skb(pkt, data, payload_len); - } else { - skb_put_data(skb, pkt->data, payload_len); + struct iov_iter iov_iter; + struct kvec kvec; + void *data = skb_put(skb, payload_len); + + kvec.iov_base = data; + kvec.iov_len = payload_len; + iov_iter_kvec(&iov_iter, ITER_DEST, &kvec, 1, payload_len); + + if (skb_copy_datagram_iter(pkt, VIRTIO_VSOCK_SKB_CB(pkt)->offset, + &iov_iter, payload_len)) { + kfree_skb(skb); + return NULL; } } diff --git a/scripts/gcc-plugins/gcc-common.h b/scripts/gcc-plugins/gcc-common.h index 8f1b3500f8e2..abb1964c44d4 100644 --- a/scripts/gcc-plugins/gcc-common.h +++ b/scripts/gcc-plugins/gcc-common.h @@ -309,7 +309,9 @@ typedef const gimple *const_gimple_ptr; #define gimple gimple_ptr #define const_gimple const_gimple_ptr #undef CONST_CAST_GIMPLE -#define CONST_CAST_GIMPLE(X) CONST_CAST(gimple, (X)) +#define CONST_CAST_GIMPLE(X) const_cast<gimple>((X)) +#undef CONST_CAST_TREE +#define CONST_CAST_TREE(X) const_cast<tree>((X)) /* gimple related */ static inline gimple gimple_build_assign_with_ops(enum tree_code subcode, tree lhs, tree op1, tree op2 MEM_STAT_DECL) diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 6673601246b3..eff29645719b 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -793,9 +793,10 @@ #define MSR_AMD64_LBR_SELECT 0xc000010e /* Zen4 */ -#define MSR_ZEN4_BP_CFG 0xc001102e +#define MSR_ZEN4_BP_CFG 0xc001102e #define MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT 4 #define MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT 5 +#define MSR_ZEN2_BP_CFG_BUG_FIX_BIT 33 /* Fam 19h MSRs */ #define MSR_F19H_UMC_PERF_CTL 0xc0010800 diff --git a/tools/net/ynl/Makefile.deps b/tools/net/ynl/Makefile.deps index 08205f9fc525..cc53b2f21c44 100644 --- a/tools/net/ynl/Makefile.deps +++ b/tools/net/ynl/Makefile.deps @@ -15,9 +15,11 @@ UAPI_PATH:=../../../../include/uapi/ get_hdr_inc=-D$(1) -include $(UAPI_PATH)/linux/$(2) get_hdr_inc2=-D$(1) -D$(2) -include $(UAPI_PATH)/linux/$(3) +CFLAGS_dev-energymodel:=$(call get_hdr_inc,_LINUX_DEV_ENERGYMODEL_H,dev_energymodel.h) CFLAGS_devlink:=$(call get_hdr_inc,_LINUX_DEVLINK_H_,devlink.h) CFLAGS_dpll:=$(call get_hdr_inc,_LINUX_DPLL_H,dpll.h) -CFLAGS_ethtool:=$(call get_hdr_inc,_LINUX_ETHTOOL_H,ethtool.h) \ +CFLAGS_ethtool:=$(call get_hdr_inc,_LINUX_TYPELIMITS_H,typelimits.h) \ + $(call get_hdr_inc,_LINUX_ETHTOOL_H,ethtool.h) \ $(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_H_,ethtool_netlink.h) \ $(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_GENERATED_H,ethtool_netlink_generated.h) CFLAGS_handshake:=$(call get_hdr_inc,_LINUX_HANDSHAKE_H,handshake.h) diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py index 0e1e486c1185..cdc3646f2642 100755 --- a/tools/net/ynl/pyynl/ynl_gen_c.py +++ b/tools/net/ynl/pyynl/ynl_gen_c.py @@ -3212,6 +3212,8 @@ def render_uapi(family, cw): for const in family['definitions']: if const.get('header'): continue + if const.get('scope', 'uapi') != 'uapi': + continue if const['type'] != 'const': cw.writes_defines(defines) @@ -3339,6 +3341,25 @@ def render_uapi(family, cw): cw.p(f'#endif /* {hdr_prot} */') +def render_scoped_consts(family, cw, scope): + defines = [] + for const in family['definitions']: + if const['type'] != 'const': + continue + if const.get('header'): + continue + if const.get('scope') != scope: + continue + name_pfx = const.get('name-prefix', f"{family.ident_name}-") + defines.append([ + c_upper(family.get('c-define-name', + f"{name_pfx}{const['name']}")), + const['value']]) + if defines: + cw.writes_defines(defines) + cw.nl() + + def _render_user_ntf_entry(ri, op): if not ri.family.is_classic(): ri.cw.block_start(line=f"[{op.enum_name}] = ") @@ -3504,8 +3525,12 @@ def main(): cw.p('#include "ynl.h"') headers = [] for definition in parsed['definitions'] + parsed['attribute-sets']: - if 'header' in definition: - headers.append(definition['header']) + if 'header' not in definition: + continue + scope = definition.get('scope', 'uapi') + if scope != 'uapi' and scope != args.mode: + continue + headers.append(definition['header']) if args.mode == 'user': headers.append(parsed.uapi_header) seen_header = [] @@ -3522,6 +3547,7 @@ def main(): for one in args.user_header: cw.p(f'#include "{one}"') else: + render_scoped_consts(parsed, cw, 'user') cw.p('struct ynl_sock;') cw.nl() render_user_family(parsed, cw, True) @@ -3529,6 +3555,7 @@ def main(): if args.mode == "kernel": if args.header: + render_scoped_consts(parsed, cw, 'kernel') for _, struct in sorted(parsed.pure_nested_structs.items()): if struct.request: cw.p('/* Common nested types */') diff --git a/tools/testing/selftests/cgroup/lib/cgroup_util.c b/tools/testing/selftests/cgroup/lib/cgroup_util.c index 6a7295347e90..42f54936f4bb 100644 --- a/tools/testing/selftests/cgroup/lib/cgroup_util.c +++ b/tools/testing/selftests/cgroup/lib/cgroup_util.c @@ -106,8 +106,9 @@ int cg_read_strcmp(const char *cgroup, const char *control, /* Handle the case of comparing against empty string */ if (!expected) return -1; - else - size = strlen(expected) + 1; + + /* needs size > 1, otherwise cg_read() reads 0 bytes */ + size = (expected[0] == '\0') ? 2 : strlen(expected) + 1; buf = malloc(size); if (!buf) diff --git a/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh b/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh index 42a6628fb8bc..1c0444729e70 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh @@ -18,7 +18,7 @@ write_test() { echo "testing $interface $value" echo $value > $dir/$interface new=$(cat $dir/$interface) - [[ $value -ne $(cat $dir/$interface) ]] && { + [[ "$value" != "$new" ]] && { echo "$interface write $value failed: new:$new" exit 1 } diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c index eeabd34bf083..12f59925500b 100644 --- a/tools/testing/selftests/cgroup/test_kmem.c +++ b/tools/testing/selftests/cgroup/test_kmem.c @@ -368,11 +368,15 @@ static int test_percpu_basic(const char *root) for (i = 0; i < 1000; i++) { child = cg_name_indexed(parent, "child", i); - if (!child) - return -1; + if (!child) { + ret = -1; + goto cleanup_children; + } - if (cg_create(child)) + if (cg_create(child)) { + free(child); goto cleanup_children; + } free(child); } diff --git a/tools/testing/selftests/drivers/net/shaper.py b/tools/testing/selftests/drivers/net/shaper.py index 11310f19bfa0..e39d270e688d 100755 --- a/tools/testing/selftests/drivers/net/shaper.py +++ b/tools/testing/selftests/drivers/net/shaper.py @@ -1,7 +1,10 @@ #!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 -from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_true, KsftSkipEx +import errno + +from lib.py import ksft_run, ksft_exit +from lib.py import ksft_eq, ksft_raises, ksft_true, KsftSkipEx from lib.py import EthtoolFamily, NetshaperFamily from lib.py import NetDrvEnv from lib.py import NlError @@ -438,6 +441,21 @@ def queue_update(cfg, nl_shaper) -> None: nl_shaper.delete({'ifindex': cfg.ifindex, 'handle': {'scope': 'queue', 'id': i}}) +def dup_leaves(cfg, nl_shaper) -> None: + """ Ensure that the kernel rejects duplicate leaves. """ + if not cfg.groups: + raise KsftSkipEx("device does not support node scope") + + with ksft_raises(NlError) as cm: + nl_shaper.group({ + 'ifindex': cfg.ifindex, + 'leaves':[{'handle': {'scope': 'queue', 'id': 0}}, + {'handle': {'scope': 'queue', 'id': 0}}], + 'handle': {'scope':'node'}, + 'metric': 'bps', + 'bw-max': 10000}) + ksft_eq(cm.exception.error, errno.EINVAL) + def main() -> None: with NetDrvEnv(__file__, queue_count=4) as cfg: cfg.queues = False @@ -453,7 +471,9 @@ def main() -> None: basic_groups, qgroups, delegation, - queue_update], args=(cfg, NetshaperFamily())) + dup_leaves, + queue_update], + args=(cfg, NetshaperFamily())) ksft_exit() diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index d6528c6f5e03..253e748c1d4a 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -510,7 +510,12 @@ static void test_guest_memfd_guest(void) "Default VM type should support INIT_SHARED, supported flags = 0x%x", vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_FLAGS)); - size = vm->page_size; + /* + * Use the max of the host or guest page size for all operations, as + * KVM requires guest_memfd files and memslots to be sized to multiples + * of the host page size. + */ + size = max_t(size_t, vm->page_size, page_size); fd = vm_create_guest_memfd(vm, size, GUEST_MEMFD_FLAG_MMAP | GUEST_MEMFD_FLAG_INIT_SHARED); vm_set_user_memory_region2(vm, slot, KVM_MEM_GUEST_MEMFD, gpa, size, NULL, fd, 0); @@ -519,7 +524,7 @@ static void test_guest_memfd_guest(void) memset(mem, 0xaa, size); kvm_munmap(mem, size); - virt_pg_map(vm, gpa, gpa); + virt_map(vm, gpa, gpa, size / vm->page_size); vcpu_args_set(vcpu, 2, gpa, size); vcpu_run(vcpu); diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index 7df2bc8eec02..76fcdd1fd3cb 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -220,6 +220,8 @@ static void check_steal_time_uapi(void) }; vcpu_ioctl(vcpu, KVM_HAS_DEVICE_ATTR, &dev); + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, ST_GPA_BASE, 1, 1, 0); + virt_map(vm, ST_GPA_BASE, ST_GPA_BASE, 1); st_ipa = (ulong)ST_GPA_BASE | 1; ret = __vcpu_ioctl(vcpu, KVM_SET_DEVICE_ATTR, &dev); diff --git a/tools/testing/selftests/sched_ext/dequeue.c b/tools/testing/selftests/sched_ext/dequeue.c index 4e93262703ca..383d06e972a4 100644 --- a/tools/testing/selftests/sched_ext/dequeue.c +++ b/tools/testing/selftests/sched_ext/dequeue.c @@ -33,6 +33,7 @@ static void worker_fn(int id) /* Do some work to trigger scheduling events */ for (j = 0; j < 10000; j++) sum += j; + asm volatile("" : : "r"(sum)); /* Sleep to trigger dequeue */ usleep(1000 + (id * 100)); diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json index b1f856cf62c1..848696c373fc 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json @@ -1284,5 +1284,46 @@ "teardown": [ "$TC qdisc del dev $DUMMY handle 1: root" ] + }, + { + "id": "3a62", + "name": "Try to create a qlen underflow with QFQ/CBS", + "category": [ + "qdisc", + "qfq", + "cbs" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.10.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: qfq", + "$TC class add dev $DUMMY classid 1:1 parent 1: qfq", + "$TC class add dev $DUMMY classid 1:2 parent 1: qfq", + "$TC qdisc add dev $DUMMY handle 2: parent 1:1 cbs", + "$TC qdisc add dev $DUMMY handle 3: parent 2: netem delay 5000000000", + "$TC filter add dev $DUMMY parent 1: prio 1 u32 match ip dst 10.10.10.1 classid 1:1 action ok", + "$TC filter add dev $DUMMY parent 1: prio 2 u32 match ip dst 10.10.10.2 classid 1:2 action ok", + "ping -c 1 10.10.10.1 -W0.01 -I$DUMMY || true", + "$IP l set $DUMMY down", + "$IP l set $DUMMY up", + "$TC qdisc replace dev $DUMMY handle 4: parent 2: pfifo" + ], + "cmdUnderTest": "ping -c 1 10.10.10.2 -W0.01 -I$DUMMY", + "expExitCode": "1", + "verifyCmd": "$TC -s -j qdisc ls dev $DUMMY parent 1:1", + "matchJSON": [ + { + "kind": "cbs", + "handle": "2:", + "bytes": 0, + "packets": 0 + } + ], + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] } ] diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c index fbd9b1e7342a..0b23c09daea5 100644 --- a/tools/testing/selftests/ublk/kublk.c +++ b/tools/testing/selftests/ublk/kublk.c @@ -1735,6 +1735,17 @@ static int __cmd_dev_add(const struct dev_ctx *ctx) goto fail; } + /* + * The kernel may reduce nr_hw_queues (e.g. capped to nr_cpu_ids). + * Cap nthreads to the actual queue count to avoid creating extra + * handler threads that will hang during device removal. + * + * per_io_tasks mode is excluded: threads interleave across all + * queues so nthreads > nr_hw_queues is valid and intentional. + */ + if (!ctx->per_io_tasks && dev->nthreads > info->nr_hw_queues) + dev->nthreads = info->nr_hw_queues; + ret = ublk_start_daemon(ctx, dev); ublk_dbg(UBLK_DBG_DEV, "%s: daemon exit %d\n", __func__, ret); if (ret < 0) diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c index 02bc6b00d76c..572b854edf74 100644 --- a/virt/kvm/dirty_ring.c +++ b/virt/kvm/dirty_ring.c @@ -63,7 +63,8 @@ static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask) memslot = id_to_memslot(__kvm_memslots(kvm, as_id), id); - if (!memslot || (offset + __fls(mask)) >= memslot->npages) + if (!memslot || offset >= memslot->npages || + offset + __fls(mask) >= memslot->npages) return; KVM_MMU_LOCK(kvm); |