diff options
826 files changed, 9210 insertions, 4673 deletions
@@ -121,6 +121,8 @@ Ben Widawsky <bwidawsk@kernel.org> <benjamin.widawsky@intel.com> Benjamin Poirier <benjamin.poirier@gmail.com> <bpoirier@suse.de> Benjamin Tissoires <bentiss@kernel.org> <benjamin.tissoires@gmail.com> Benjamin Tissoires <bentiss@kernel.org> <benjamin.tissoires@redhat.com> +Bingwu Zhang <xtex@aosc.io> <xtexchooser@duck.com> +Bingwu Zhang <xtex@aosc.io> <xtex@xtexx.eu.org> Bjorn Andersson <andersson@kernel.org> <bjorn@kryo.se> Bjorn Andersson <andersson@kernel.org> <bjorn.andersson@linaro.org> Bjorn Andersson <andersson@kernel.org> <bjorn.andersson@sonymobile.com> @@ -435,7 +437,7 @@ Martin Kepplinger <martink@posteo.de> <martin.kepplinger@ginzinger.com> Martin Kepplinger <martink@posteo.de> <martin.kepplinger@puri.sm> Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com> Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com> <martyna.szapar-mudlaw@intel.com> -Mathieu Othacehe <m.othacehe@gmail.com> <othacehe@gnu.org> +Mathieu Othacehe <othacehe@gnu.org> <m.othacehe@gmail.com> Mat Martineau <martineau@kernel.org> <mathew.j.martineau@linux.intel.com> Mat Martineau <martineau@kernel.org> <mathewm@codeaurora.org> Matthew Wilcox <willy@infradead.org> <matthew.r.wilcox@intel.com> @@ -735,6 +737,7 @@ Wolfram Sang <wsa@kernel.org> <w.sang@pengutronix.de> Wolfram Sang <wsa@kernel.org> <wsa@the-dreams.de> Yakir Yang <kuankuan.y@gmail.com> <ykk@rock-chips.com> Yanteng Si <si.yanteng@linux.dev> <siyanteng@loongson.cn> +Ying Huang <huang.ying.caritas@gmail.com> <ying.huang@intel.com> Yusuke Goda <goda.yusuke@renesas.com> Zack Rusin <zack.rusin@broadcom.com> <zackr@vmware.com> Zhu Yanjun <zyjzyj2000@gmail.com> <yanjunz@nvidia.com> @@ -20,6 +20,10 @@ N: Thomas Abraham E: thomas.ab@samsung.com D: Samsung pin controller driver +N: Jose Abreu +E: jose.abreu@synopsys.com +D: Synopsys DesignWare XPCS MDIO/PCS driver. + N: Dragos Acostachioaie E: dragos@iname.com W: http://www.arbornet.org/~dragos @@ -1428,6 +1432,10 @@ S: 8124 Constitution Apt. 7 S: Sterling Heights, Michigan 48313 S: USA +N: Andy Gospodarek +E: andy@greyhouse.net +D: Maintenance and contributions to the network interface bonding driver. + N: Wolfgang Grandegger E: wg@grandegger.com D: Controller Area Network (device drivers) @@ -1812,6 +1820,10 @@ D: Author/maintainer of most DRM drivers (especially ATI, MGA) D: Core DRM templates, general DRM and 3D-related hacking S: No fixed address +N: Woojung Huh +E: woojung.huh@microchip.com +D: Microchip LAN78XX USB Ethernet driver + N: Kenn Humborg E: kenn@wombat.ie D: Mods to loop device to support sparse backing files diff --git a/Documentation/admin-guide/laptops/thinkpad-acpi.rst b/Documentation/admin-guide/laptops/thinkpad-acpi.rst index 7f674a6cfa8a..4ab0fef7d440 100644 --- a/Documentation/admin-guide/laptops/thinkpad-acpi.rst +++ b/Documentation/admin-guide/laptops/thinkpad-acpi.rst @@ -445,8 +445,10 @@ event code Key Notes 0x1008 0x07 FN+F8 IBM: toggle screen expand Lenovo: configure UltraNav, or toggle screen expand. - On newer platforms (2024+) - replaced by 0x131f (see below) + On 2024 platforms replaced by + 0x131f (see below) and on newer + platforms (2025 +) keycode is + replaced by 0x1401 (see below). 0x1009 0x08 FN+F9 - @@ -506,9 +508,11 @@ event code Key Notes 0x1019 0x18 unknown -0x131f ... FN+F8 Platform Mode change. +0x131f ... FN+F8 Platform Mode change (2024 systems). Implemented in driver. +0x1401 ... FN+F8 Platform Mode change (2025 + systems). + Implemented in driver. ... ... ... 0x1020 0x1F unknown diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index 5034915f4e8e..8872203df088 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -436,7 +436,7 @@ AnonHugePmdMapped). The number of file transparent huge pages mapped to userspace is available by reading ShmemPmdMapped and ShmemHugePages fields in ``/proc/meminfo``. To identify what applications are mapping file transparent huge pages, it -is necessary to read ``/proc/PID/smaps`` and count the FileHugeMapped fields +is necessary to read ``/proc/PID/smaps`` and count the FilePmdMapped fields for each mapping. Note that reading the smaps file is expensive and reading it diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst index 210a808b74ec..412423c54f25 100644 --- a/Documentation/admin-guide/pm/amd-pstate.rst +++ b/Documentation/admin-guide/pm/amd-pstate.rst @@ -251,9 +251,7 @@ performance supported in `AMD CPPC Performance Capability <perf_cap_>`_). In some ASICs, the highest CPPC performance is not the one in the ``_CPC`` table, so we need to expose it to sysfs. If boost is not active, but still supported, this maximum frequency will be larger than the one in -``cpuinfo``. On systems that support preferred core, the driver will have -different values for some cores than others and this will reflect the values -advertised by the platform at bootup. +``cpuinfo``. This attribute is read-only. ``amd_pstate_lowest_nonlinear_freq`` diff --git a/Documentation/devicetree/bindings/crypto/fsl,sec-v4.0.yaml b/Documentation/devicetree/bindings/crypto/fsl,sec-v4.0.yaml index 9c8c9991f29a..f0c4a7c83568 100644 --- a/Documentation/devicetree/bindings/crypto/fsl,sec-v4.0.yaml +++ b/Documentation/devicetree/bindings/crypto/fsl,sec-v4.0.yaml @@ -114,8 +114,9 @@ patternProperties: table that specifies the PPID to LIODN mapping. Needed if the PAMU is used. Value is a 12 bit value where value is a LIODN ID for this JR. This property is normally set by boot firmware. - $ref: /schemas/types.yaml#/definitions/uint32 - maximum: 0xfff + $ref: /schemas/types.yaml#/definitions/uint32-array + items: + - maximum: 0xfff '^rtic@[0-9a-f]+$': type: object @@ -186,8 +187,9 @@ patternProperties: Needed if the PAMU is used. Value is a 12 bit value where value is a LIODN ID for this JR. This property is normally set by boot firmware. - $ref: /schemas/types.yaml#/definitions/uint32 - maximum: 0xfff + $ref: /schemas/types.yaml#/definitions/uint32-array + items: + - maximum: 0xfff fsl,rtic-region: description: diff --git a/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml b/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml index df20a3c9c744..ec89115c74e4 100644 --- a/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml +++ b/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml @@ -90,7 +90,7 @@ properties: adi,dsi-lanes: description: Number of DSI data lanes connected to the DSI host. $ref: /schemas/types.yaml#/definitions/uint32 - enum: [ 1, 2, 3, 4 ] + enum: [ 2, 3, 4 ] "#sound-dai-cells": const: 0 diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,dp.yaml b/Documentation/devicetree/bindings/display/mediatek/mediatek,dp.yaml index 2aef1eb32e11..75ce92f4a5fd 100644 --- a/Documentation/devicetree/bindings/display/mediatek/mediatek,dp.yaml +++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,dp.yaml @@ -42,6 +42,9 @@ properties: interrupts: maxItems: 1 + '#sound-dai-cells': + const: 0 + ports: $ref: /schemas/graph.yaml#/properties/ports properties: @@ -85,7 +88,21 @@ required: - ports - max-linkrate-mhz -additionalProperties: false +allOf: + - $ref: /schemas/sound/dai-common.yaml# + - if: + not: + properties: + compatible: + contains: + enum: + - mediatek,mt8188-dp-tx + - mediatek,mt8195-dp-tx + then: + properties: + '#sound-dai-cells': false + +unevaluatedProperties: false examples: - | diff --git a/Documentation/devicetree/bindings/iio/st,st-sensors.yaml b/Documentation/devicetree/bindings/iio/st,st-sensors.yaml index 71c1ee33a393..e955eb8e8797 100644 --- a/Documentation/devicetree/bindings/iio/st,st-sensors.yaml +++ b/Documentation/devicetree/bindings/iio/st,st-sensors.yaml @@ -65,6 +65,7 @@ properties: - st,lsm9ds0-gyro - description: STMicroelectronics Magnetometers enum: + - st,iis2mdc - st,lis2mdl - st,lis3mdl-magn - st,lsm303agr-magn diff --git a/Documentation/devicetree/bindings/mtd/partitions/fixed-partitions.yaml b/Documentation/devicetree/bindings/mtd/partitions/fixed-partitions.yaml index 058253d6d889..62086366837c 100644 --- a/Documentation/devicetree/bindings/mtd/partitions/fixed-partitions.yaml +++ b/Documentation/devicetree/bindings/mtd/partitions/fixed-partitions.yaml @@ -82,7 +82,7 @@ examples: uimage@100000 { reg = <0x0100000 0x200000>; - compress = "lzma"; + compression = "lzma"; }; }; diff --git a/Documentation/devicetree/bindings/net/pse-pd/pse-controller.yaml b/Documentation/devicetree/bindings/net/pse-pd/pse-controller.yaml index a12cda8aa764..cd09560e0aea 100644 --- a/Documentation/devicetree/bindings/net/pse-pd/pse-controller.yaml +++ b/Documentation/devicetree/bindings/net/pse-pd/pse-controller.yaml @@ -81,7 +81,7 @@ properties: List of phandles, each pointing to the power supply for the corresponding pairset named in 'pairset-names'. This property aligns with IEEE 802.3-2022, Section 33.2.3 and 145.2.4. - PSE Pinout Alternatives (as per IEEE 802.3-2022 Table 145\u20133) + PSE Pinout Alternatives (as per IEEE 802.3-2022 Table 145-3) |-----------|---------------|---------------|---------------|---------------| | Conductor | Alternative A | Alternative A | Alternative B | Alternative B | | | (MDI-X) | (MDI) | (X) | (S) | diff --git a/Documentation/devicetree/bindings/soc/fsl/fsl,qman-portal.yaml b/Documentation/devicetree/bindings/soc/fsl/fsl,qman-portal.yaml index 17016184143f..e459fec02ba8 100644 --- a/Documentation/devicetree/bindings/soc/fsl/fsl,qman-portal.yaml +++ b/Documentation/devicetree/bindings/soc/fsl/fsl,qman-portal.yaml @@ -35,6 +35,7 @@ properties: fsl,liodn: $ref: /schemas/types.yaml#/definitions/uint32-array + maxItems: 2 description: See pamu.txt. Two LIODN(s). DQRR LIODN (DLIODN) and Frame LIODN (FLIODN) @@ -69,6 +70,7 @@ patternProperties: type: object properties: fsl,liodn: + $ref: /schemas/types.yaml#/definitions/uint32-array description: See pamu.txt, PAMU property used for static LIODN assignment fsl,iommu-parent: diff --git a/Documentation/mm/process_addrs.rst b/Documentation/mm/process_addrs.rst index e8618fbc62c9..1d416658d7f5 100644 --- a/Documentation/mm/process_addrs.rst +++ b/Documentation/mm/process_addrs.rst @@ -3,3 +3,853 @@ ================= Process Addresses ================= + +.. toctree:: + :maxdepth: 3 + + +Userland memory ranges are tracked by the kernel via Virtual Memory Areas or +'VMA's of type :c:struct:`!struct vm_area_struct`. + +Each VMA describes a virtually contiguous memory range with identical +attributes, each described by a :c:struct:`!struct vm_area_struct` +object. Userland access outside of VMAs is invalid except in the case where an +adjacent stack VMA could be extended to contain the accessed address. + +All VMAs are contained within one and only one virtual address space, described +by a :c:struct:`!struct mm_struct` object which is referenced by all tasks (that is, +threads) which share the virtual address space. We refer to this as the +:c:struct:`!mm`. + +Each mm object contains a maple tree data structure which describes all VMAs +within the virtual address space. + +.. note:: An exception to this is the 'gate' VMA which is provided by + architectures which use :c:struct:`!vsyscall` and is a global static + object which does not belong to any specific mm. + +------- +Locking +------- + +The kernel is designed to be highly scalable against concurrent read operations +on VMA **metadata** so a complicated set of locks are required to ensure memory +corruption does not occur. + +.. note:: Locking VMAs for their metadata does not have any impact on the memory + they describe nor the page tables that map them. + +Terminology +----------- + +* **mmap locks** - Each MM has a read/write semaphore :c:member:`!mmap_lock` + which locks at a process address space granularity which can be acquired via + :c:func:`!mmap_read_lock`, :c:func:`!mmap_write_lock` and variants. +* **VMA locks** - The VMA lock is at VMA granularity (of course) which behaves + as a read/write semaphore in practice. A VMA read lock is obtained via + :c:func:`!lock_vma_under_rcu` (and unlocked via :c:func:`!vma_end_read`) and a + write lock via :c:func:`!vma_start_write` (all VMA write locks are unlocked + automatically when the mmap write lock is released). To take a VMA write lock + you **must** have already acquired an :c:func:`!mmap_write_lock`. +* **rmap locks** - When trying to access VMAs through the reverse mapping via a + :c:struct:`!struct address_space` or :c:struct:`!struct anon_vma` object + (reachable from a folio via :c:member:`!folio->mapping`). VMAs must be stabilised via + :c:func:`!anon_vma_[try]lock_read` or :c:func:`!anon_vma_[try]lock_write` for + anonymous memory and :c:func:`!i_mmap_[try]lock_read` or + :c:func:`!i_mmap_[try]lock_write` for file-backed memory. We refer to these + locks as the reverse mapping locks, or 'rmap locks' for brevity. + +We discuss page table locks separately in the dedicated section below. + +The first thing **any** of these locks achieve is to **stabilise** the VMA +within the MM tree. That is, guaranteeing that the VMA object will not be +deleted from under you nor modified (except for some specific fields +described below). + +Stabilising a VMA also keeps the address space described by it around. + +Lock usage +---------- + +If you want to **read** VMA metadata fields or just keep the VMA stable, you +must do one of the following: + +* Obtain an mmap read lock at the MM granularity via :c:func:`!mmap_read_lock` (or a + suitable variant), unlocking it with a matching :c:func:`!mmap_read_unlock` when + you're done with the VMA, *or* +* Try to obtain a VMA read lock via :c:func:`!lock_vma_under_rcu`. This tries to + acquire the lock atomically so might fail, in which case fall-back logic is + required to instead obtain an mmap read lock if this returns :c:macro:`!NULL`, + *or* +* Acquire an rmap lock before traversing the locked interval tree (whether + anonymous or file-backed) to obtain the required VMA. + +If you want to **write** VMA metadata fields, then things vary depending on the +field (we explore each VMA field in detail below). For the majority you must: + +* Obtain an mmap write lock at the MM granularity via :c:func:`!mmap_write_lock` (or a + suitable variant), unlocking it with a matching :c:func:`!mmap_write_unlock` when + you're done with the VMA, *and* +* Obtain a VMA write lock via :c:func:`!vma_start_write` for each VMA you wish to + modify, which will be released automatically when :c:func:`!mmap_write_unlock` is + called. +* If you want to be able to write to **any** field, you must also hide the VMA + from the reverse mapping by obtaining an **rmap write lock**. + +VMA locks are special in that you must obtain an mmap **write** lock **first** +in order to obtain a VMA **write** lock. A VMA **read** lock however can be +obtained without any other lock (:c:func:`!lock_vma_under_rcu` will acquire then +release an RCU lock to lookup the VMA for you). + +This constrains the impact of writers on readers, as a writer can interact with +one VMA while a reader interacts with another simultaneously. + +.. note:: The primary users of VMA read locks are page fault handlers, which + means that without a VMA write lock, page faults will run concurrent with + whatever you are doing. + +Examining all valid lock states: + +.. table:: + + ========= ======== ========= ======= ===== =========== ========== + mmap lock VMA lock rmap lock Stable? Read? Write most? Write all? + ========= ======== ========= ======= ===== =========== ========== + \- \- \- N N N N + \- R \- Y Y N N + \- \- R/W Y Y N N + R/W \-/R \-/R/W Y Y N N + W W \-/R Y Y Y N + W W W Y Y Y Y + ========= ======== ========= ======= ===== =========== ========== + +.. warning:: While it's possible to obtain a VMA lock while holding an mmap read lock, + attempting to do the reverse is invalid as it can result in deadlock - if + another task already holds an mmap write lock and attempts to acquire a VMA + write lock that will deadlock on the VMA read lock. + +All of these locks behave as read/write semaphores in practice, so you can +obtain either a read or a write lock for each of these. + +.. note:: Generally speaking, a read/write semaphore is a class of lock which + permits concurrent readers. However a write lock can only be obtained + once all readers have left the critical region (and pending readers + made to wait). + + This renders read locks on a read/write semaphore concurrent with other + readers and write locks exclusive against all others holding the semaphore. + +VMA fields +^^^^^^^^^^ + +We can subdivide :c:struct:`!struct vm_area_struct` fields by their purpose, which makes it +easier to explore their locking characteristics: + +.. note:: We exclude VMA lock-specific fields here to avoid confusion, as these + are in effect an internal implementation detail. + +.. table:: Virtual layout fields + + ===================== ======================================== =========== + Field Description Write lock + ===================== ======================================== =========== + :c:member:`!vm_start` Inclusive start virtual address of range mmap write, + VMA describes. VMA write, + rmap write. + :c:member:`!vm_end` Exclusive end virtual address of range mmap write, + VMA describes. VMA write, + rmap write. + :c:member:`!vm_pgoff` Describes the page offset into the file, mmap write, + the original page offset within the VMA write, + virtual address space (prior to any rmap write. + :c:func:`!mremap`), or PFN if a PFN map + and the architecture does not support + :c:macro:`!CONFIG_ARCH_HAS_PTE_SPECIAL`. + ===================== ======================================== =========== + +These fields describes the size, start and end of the VMA, and as such cannot be +modified without first being hidden from the reverse mapping since these fields +are used to locate VMAs within the reverse mapping interval trees. + +.. table:: Core fields + + ============================ ======================================== ========================= + Field Description Write lock + ============================ ======================================== ========================= + :c:member:`!vm_mm` Containing mm_struct. None - written once on + initial map. + :c:member:`!vm_page_prot` Architecture-specific page table mmap write, VMA write. + protection bits determined from VMA + flags. + :c:member:`!vm_flags` Read-only access to VMA flags describing N/A + attributes of the VMA, in union with + private writable + :c:member:`!__vm_flags`. + :c:member:`!__vm_flags` Private, writable access to VMA flags mmap write, VMA write. + field, updated by + :c:func:`!vm_flags_*` functions. + :c:member:`!vm_file` If the VMA is file-backed, points to a None - written once on + struct file object describing the initial map. + underlying file, if anonymous then + :c:macro:`!NULL`. + :c:member:`!vm_ops` If the VMA is file-backed, then either None - Written once on + the driver or file-system provides a initial map by + :c:struct:`!struct vm_operations_struct` :c:func:`!f_ops->mmap()`. + object describing callbacks to be + invoked on VMA lifetime events. + :c:member:`!vm_private_data` A :c:member:`!void *` field for Handled by driver. + driver-specific metadata. + ============================ ======================================== ========================= + +These are the core fields which describe the MM the VMA belongs to and its attributes. + +.. table:: Config-specific fields + + ================================= ===================== ======================================== =============== + Field Configuration option Description Write lock + ================================= ===================== ======================================== =============== + :c:member:`!anon_name` CONFIG_ANON_VMA_NAME A field for storing a mmap write, + :c:struct:`!struct anon_vma_name` VMA write. + object providing a name for anonymous + mappings, or :c:macro:`!NULL` if none + is set or the VMA is file-backed. The + underlying object is reference counted + and can be shared across multiple VMAs + for scalability. + :c:member:`!swap_readahead_info` CONFIG_SWAP Metadata used by the swap mechanism mmap read, + to perform readahead. This field is swap-specific + accessed atomically. lock. + :c:member:`!vm_policy` CONFIG_NUMA :c:type:`!mempolicy` object which mmap write, + describes the NUMA behaviour of the VMA write. + VMA. The underlying object is reference + counted. + :c:member:`!numab_state` CONFIG_NUMA_BALANCING :c:type:`!vma_numab_state` object which mmap read, + describes the current state of numab-specific + NUMA balancing in relation to this VMA. lock. + Updated under mmap read lock by + :c:func:`!task_numa_work`. + :c:member:`!vm_userfaultfd_ctx` CONFIG_USERFAULTFD Userfaultfd context wrapper object of mmap write, + type :c:type:`!vm_userfaultfd_ctx`, VMA write. + either of zero size if userfaultfd is + disabled, or containing a pointer + to an underlying + :c:type:`!userfaultfd_ctx` object which + describes userfaultfd metadata. + ================================= ===================== ======================================== =============== + +These fields are present or not depending on whether the relevant kernel +configuration option is set. + +.. table:: Reverse mapping fields + + =================================== ========================================= ============================ + Field Description Write lock + =================================== ========================================= ============================ + :c:member:`!shared.rb` A red/black tree node used, if the mmap write, VMA write, + mapping is file-backed, to place the VMA i_mmap write. + in the + :c:member:`!struct address_space->i_mmap` + red/black interval tree. + :c:member:`!shared.rb_subtree_last` Metadata used for management of the mmap write, VMA write, + interval tree if the VMA is file-backed. i_mmap write. + :c:member:`!anon_vma_chain` List of pointers to both forked/CoW’d mmap read, anon_vma write. + :c:type:`!anon_vma` objects and + :c:member:`!vma->anon_vma` if it is + non-:c:macro:`!NULL`. + :c:member:`!anon_vma` :c:type:`!anon_vma` object used by When :c:macro:`NULL` and + anonymous folios mapped exclusively to setting non-:c:macro:`NULL`: + this VMA. Initially set by mmap read, page_table_lock. + :c:func:`!anon_vma_prepare` serialised + by the :c:macro:`!page_table_lock`. This When non-:c:macro:`NULL` and + is set as soon as any page is faulted in. setting :c:macro:`NULL`: + mmap write, VMA write, + anon_vma write. + =================================== ========================================= ============================ + +These fields are used to both place the VMA within the reverse mapping, and for +anonymous mappings, to be able to access both related :c:struct:`!struct anon_vma` objects +and the :c:struct:`!struct anon_vma` in which folios mapped exclusively to this VMA should +reside. + +.. note:: If a file-backed mapping is mapped with :c:macro:`!MAP_PRIVATE` set + then it can be in both the :c:type:`!anon_vma` and :c:type:`!i_mmap` + trees at the same time, so all of these fields might be utilised at + once. + +Page tables +----------- + +We won't speak exhaustively on the subject but broadly speaking, page tables map +virtual addresses to physical ones through a series of page tables, each of +which contain entries with physical addresses for the next page table level +(along with flags), and at the leaf level the physical addresses of the +underlying physical data pages or a special entry such as a swap entry, +migration entry or other special marker. Offsets into these pages are provided +by the virtual address itself. + +In Linux these are divided into five levels - PGD, P4D, PUD, PMD and PTE. Huge +pages might eliminate one or two of these levels, but when this is the case we +typically refer to the leaf level as the PTE level regardless. + +.. note:: In instances where the architecture supports fewer page tables than + five the kernel cleverly 'folds' page table levels, that is stubbing + out functions related to the skipped levels. This allows us to + conceptually act as if there were always five levels, even if the + compiler might, in practice, eliminate any code relating to missing + ones. + +There are four key operations typically performed on page tables: + +1. **Traversing** page tables - Simply reading page tables in order to traverse + them. This only requires that the VMA is kept stable, so a lock which + establishes this suffices for traversal (there are also lockless variants + which eliminate even this requirement, such as :c:func:`!gup_fast`). +2. **Installing** page table mappings - Whether creating a new mapping or + modifying an existing one in such a way as to change its identity. This + requires that the VMA is kept stable via an mmap or VMA lock (explicitly not + rmap locks). +3. **Zapping/unmapping** page table entries - This is what the kernel calls + clearing page table mappings at the leaf level only, whilst leaving all page + tables in place. This is a very common operation in the kernel performed on + file truncation, the :c:macro:`!MADV_DONTNEED` operation via + :c:func:`!madvise`, and others. This is performed by a number of functions + including :c:func:`!unmap_mapping_range` and :c:func:`!unmap_mapping_pages`. + The VMA need only be kept stable for this operation. +4. **Freeing** page tables - When finally the kernel removes page tables from a + userland process (typically via :c:func:`!free_pgtables`) extreme care must + be taken to ensure this is done safely, as this logic finally frees all page + tables in the specified range, ignoring existing leaf entries (it assumes the + caller has both zapped the range and prevented any further faults or + modifications within it). + +.. note:: Modifying mappings for reclaim or migration is performed under rmap + lock as it, like zapping, does not fundamentally modify the identity + of what is being mapped. + +**Traversing** and **zapping** ranges can be performed holding any one of the +locks described in the terminology section above - that is the mmap lock, the +VMA lock or either of the reverse mapping locks. + +That is - as long as you keep the relevant VMA **stable** - you are good to go +ahead and perform these operations on page tables (though internally, kernel +operations that perform writes also acquire internal page table locks to +serialise - see the page table implementation detail section for more details). + +When **installing** page table entries, the mmap or VMA lock must be held to +keep the VMA stable. We explore why this is in the page table locking details +section below. + +.. warning:: Page tables are normally only traversed in regions covered by VMAs. + If you want to traverse page tables in areas that might not be + covered by VMAs, heavier locking is required. + See :c:func:`!walk_page_range_novma` for details. + +**Freeing** page tables is an entirely internal memory management operation and +has special requirements (see the page freeing section below for more details). + +.. warning:: When **freeing** page tables, it must not be possible for VMAs + containing the ranges those page tables map to be accessible via + the reverse mapping. + + The :c:func:`!free_pgtables` function removes the relevant VMAs + from the reverse mappings, but no other VMAs can be permitted to be + accessible and span the specified range. + +Lock ordering +------------- + +As we have multiple locks across the kernel which may or may not be taken at the +same time as explicit mm or VMA locks, we have to be wary of lock inversion, and +the **order** in which locks are acquired and released becomes very important. + +.. note:: Lock inversion occurs when two threads need to acquire multiple locks, + but in doing so inadvertently cause a mutual deadlock. + + For example, consider thread 1 which holds lock A and tries to acquire lock B, + while thread 2 holds lock B and tries to acquire lock A. + + Both threads are now deadlocked on each other. However, had they attempted to + acquire locks in the same order, one would have waited for the other to + complete its work and no deadlock would have occurred. + +The opening comment in :c:macro:`!mm/rmap.c` describes in detail the required +ordering of locks within memory management code: + +.. code-block:: + + inode->i_rwsem (while writing or truncating, not reading or faulting) + mm->mmap_lock + mapping->invalidate_lock (in filemap_fault) + folio_lock + hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share, see hugetlbfs below) + vma_start_write + mapping->i_mmap_rwsem + anon_vma->rwsem + mm->page_table_lock or pte_lock + swap_lock (in swap_duplicate, swap_info_get) + mmlist_lock (in mmput, drain_mmlist and others) + mapping->private_lock (in block_dirty_folio) + i_pages lock (widely used) + lruvec->lru_lock (in folio_lruvec_lock_irq) + inode->i_lock (in set_page_dirty's __mark_inode_dirty) + bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) + sb_lock (within inode_lock in fs/fs-writeback.c) + i_pages lock (widely used, in set_page_dirty, + in arch-dependent flush_dcache_mmap_lock, + within bdi.wb->list_lock in __sync_single_inode) + +There is also a file-system specific lock ordering comment located at the top of +:c:macro:`!mm/filemap.c`: + +.. code-block:: + + ->i_mmap_rwsem (truncate_pagecache) + ->private_lock (__free_pte->block_dirty_folio) + ->swap_lock (exclusive_swap_page, others) + ->i_pages lock + + ->i_rwsem + ->invalidate_lock (acquired by fs in truncate path) + ->i_mmap_rwsem (truncate->unmap_mapping_range) + + ->mmap_lock + ->i_mmap_rwsem + ->page_table_lock or pte_lock (various, mainly in memory.c) + ->i_pages lock (arch-dependent flush_dcache_mmap_lock) + + ->mmap_lock + ->invalidate_lock (filemap_fault) + ->lock_page (filemap_fault, access_process_vm) + + ->i_rwsem (generic_perform_write) + ->mmap_lock (fault_in_readable->do_page_fault) + + bdi->wb.list_lock + sb_lock (fs/fs-writeback.c) + ->i_pages lock (__sync_single_inode) + + ->i_mmap_rwsem + ->anon_vma.lock (vma_merge) + + ->anon_vma.lock + ->page_table_lock or pte_lock (anon_vma_prepare and various) + + ->page_table_lock or pte_lock + ->swap_lock (try_to_unmap_one) + ->private_lock (try_to_unmap_one) + ->i_pages lock (try_to_unmap_one) + ->lruvec->lru_lock (follow_page_mask->mark_page_accessed) + ->lruvec->lru_lock (check_pte_range->folio_isolate_lru) + ->private_lock (folio_remove_rmap_pte->set_page_dirty) + ->i_pages lock (folio_remove_rmap_pte->set_page_dirty) + bdi.wb->list_lock (folio_remove_rmap_pte->set_page_dirty) + ->inode->i_lock (folio_remove_rmap_pte->set_page_dirty) + bdi.wb->list_lock (zap_pte_range->set_page_dirty) + ->inode->i_lock (zap_pte_range->set_page_dirty) + ->private_lock (zap_pte_range->block_dirty_folio) + +Please check the current state of these comments which may have changed since +the time of writing of this document. + +------------------------------ +Locking Implementation Details +------------------------------ + +.. warning:: Locking rules for PTE-level page tables are very different from + locking rules for page tables at other levels. + +Page table locking details +-------------------------- + +In addition to the locks described in the terminology section above, we have +additional locks dedicated to page tables: + +* **Higher level page table locks** - Higher level page tables, that is PGD, P4D + and PUD each make use of the process address space granularity + :c:member:`!mm->page_table_lock` lock when modified. + +* **Fine-grained page table locks** - PMDs and PTEs each have fine-grained locks + either kept within the folios describing the page tables or allocated + separated and pointed at by the folios if :c:macro:`!ALLOC_SPLIT_PTLOCKS` is + set. The PMD spin lock is obtained via :c:func:`!pmd_lock`, however PTEs are + mapped into higher memory (if a 32-bit system) and carefully locked via + :c:func:`!pte_offset_map_lock`. + +These locks represent the minimum required to interact with each page table +level, but there are further requirements. + +Importantly, note that on a **traversal** of page tables, sometimes no such +locks are taken. However, at the PTE level, at least concurrent page table +deletion must be prevented (using RCU) and the page table must be mapped into +high memory, see below. + +Whether care is taken on reading the page table entries depends on the +architecture, see the section on atomicity below. + +Locking rules +^^^^^^^^^^^^^ + +We establish basic locking rules when interacting with page tables: + +* When changing a page table entry the page table lock for that page table + **must** be held, except if you can safely assume nobody can access the page + tables concurrently (such as on invocation of :c:func:`!free_pgtables`). +* Reads from and writes to page table entries must be *appropriately* + atomic. See the section on atomicity below for details. +* Populating previously empty entries requires that the mmap or VMA locks are + held (read or write), doing so with only rmap locks would be dangerous (see + the warning below). +* As mentioned previously, zapping can be performed while simply keeping the VMA + stable, that is holding any one of the mmap, VMA or rmap locks. + +.. warning:: Populating previously empty entries is dangerous as, when unmapping + VMAs, :c:func:`!vms_clear_ptes` has a window of time between + zapping (via :c:func:`!unmap_vmas`) and freeing page tables (via + :c:func:`!free_pgtables`), where the VMA is still visible in the + rmap tree. :c:func:`!free_pgtables` assumes that the zap has + already been performed and removes PTEs unconditionally (along with + all other page tables in the freed range), so installing new PTE + entries could leak memory and also cause other unexpected and + dangerous behaviour. + +There are additional rules applicable when moving page tables, which we discuss +in the section on this topic below. + +PTE-level page tables are different from page tables at other levels, and there +are extra requirements for accessing them: + +* On 32-bit architectures, they may be in high memory (meaning they need to be + mapped into kernel memory to be accessible). +* When empty, they can be unlinked and RCU-freed while holding an mmap lock or + rmap lock for reading in combination with the PTE and PMD page table locks. + In particular, this happens in :c:func:`!retract_page_tables` when handling + :c:macro:`!MADV_COLLAPSE`. + So accessing PTE-level page tables requires at least holding an RCU read lock; + but that only suffices for readers that can tolerate racing with concurrent + page table updates such that an empty PTE is observed (in a page table that + has actually already been detached and marked for RCU freeing) while another + new page table has been installed in the same location and filled with + entries. Writers normally need to take the PTE lock and revalidate that the + PMD entry still refers to the same PTE-level page table. + +To access PTE-level page tables, a helper like :c:func:`!pte_offset_map_lock` or +:c:func:`!pte_offset_map` can be used depending on stability requirements. +These map the page table into kernel memory if required, take the RCU lock, and +depending on variant, may also look up or acquire the PTE lock. +See the comment on :c:func:`!__pte_offset_map_lock`. + +Atomicity +^^^^^^^^^ + +Regardless of page table locks, the MMU hardware concurrently updates accessed +and dirty bits (perhaps more, depending on architecture). Additionally, page +table traversal operations in parallel (though holding the VMA stable) and +functionality like GUP-fast locklessly traverses (that is reads) page tables, +without even keeping the VMA stable at all. + +When performing a page table traversal and keeping the VMA stable, whether a +read must be performed once and only once or not depends on the architecture +(for instance x86-64 does not require any special precautions). + +If a write is being performed, or if a read informs whether a write takes place +(on an installation of a page table entry say, for instance in +:c:func:`!__pud_install`), special care must always be taken. In these cases we +can never assume that page table locks give us entirely exclusive access, and +must retrieve page table entries once and only once. + +If we are reading page table entries, then we need only ensure that the compiler +does not rearrange our loads. This is achieved via :c:func:`!pXXp_get` +functions - :c:func:`!pgdp_get`, :c:func:`!p4dp_get`, :c:func:`!pudp_get`, +:c:func:`!pmdp_get`, and :c:func:`!ptep_get`. + +Each of these uses :c:func:`!READ_ONCE` to guarantee that the compiler reads +the page table entry only once. + +However, if we wish to manipulate an existing page table entry and care about +the previously stored data, we must go further and use an hardware atomic +operation as, for example, in :c:func:`!ptep_get_and_clear`. + +Equally, operations that do not rely on the VMA being held stable, such as +GUP-fast (see :c:func:`!gup_fast` and its various page table level handlers like +:c:func:`!gup_fast_pte_range`), must very carefully interact with page table +entries, using functions such as :c:func:`!ptep_get_lockless` and equivalent for +higher level page table levels. + +Writes to page table entries must also be appropriately atomic, as established +by :c:func:`!set_pXX` functions - :c:func:`!set_pgd`, :c:func:`!set_p4d`, +:c:func:`!set_pud`, :c:func:`!set_pmd`, and :c:func:`!set_pte`. + +Equally functions which clear page table entries must be appropriately atomic, +as in :c:func:`!pXX_clear` functions - :c:func:`!pgd_clear`, +:c:func:`!p4d_clear`, :c:func:`!pud_clear`, :c:func:`!pmd_clear`, and +:c:func:`!pte_clear`. + +Page table installation +^^^^^^^^^^^^^^^^^^^^^^^ + +Page table installation is performed with the VMA held stable explicitly by an +mmap or VMA lock in read or write mode (see the warning in the locking rules +section for details as to why). + +When allocating a P4D, PUD or PMD and setting the relevant entry in the above +PGD, P4D or PUD, the :c:member:`!mm->page_table_lock` must be held. This is +acquired in :c:func:`!__p4d_alloc`, :c:func:`!__pud_alloc` and +:c:func:`!__pmd_alloc` respectively. + +.. note:: :c:func:`!__pmd_alloc` actually invokes :c:func:`!pud_lock` and + :c:func:`!pud_lockptr` in turn, however at the time of writing it ultimately + references the :c:member:`!mm->page_table_lock`. + +Allocating a PTE will either use the :c:member:`!mm->page_table_lock` or, if +:c:macro:`!USE_SPLIT_PMD_PTLOCKS` is defined, a lock embedded in the PMD +physical page metadata in the form of a :c:struct:`!struct ptdesc`, acquired by +:c:func:`!pmd_ptdesc` called from :c:func:`!pmd_lock` and ultimately +:c:func:`!__pte_alloc`. + +Finally, modifying the contents of the PTE requires special treatment, as the +PTE page table lock must be acquired whenever we want stable and exclusive +access to entries contained within a PTE, especially when we wish to modify +them. + +This is performed via :c:func:`!pte_offset_map_lock` which carefully checks to +ensure that the PTE hasn't changed from under us, ultimately invoking +:c:func:`!pte_lockptr` to obtain a spin lock at PTE granularity contained within +the :c:struct:`!struct ptdesc` associated with the physical PTE page. The lock +must be released via :c:func:`!pte_unmap_unlock`. + +.. note:: There are some variants on this, such as + :c:func:`!pte_offset_map_rw_nolock` when we know we hold the PTE stable but + for brevity we do not explore this. See the comment for + :c:func:`!__pte_offset_map_lock` for more details. + +When modifying data in ranges we typically only wish to allocate higher page +tables as necessary, using these locks to avoid races or overwriting anything, +and set/clear data at the PTE level as required (for instance when page faulting +or zapping). + +A typical pattern taken when traversing page table entries to install a new +mapping is to optimistically determine whether the page table entry in the table +above is empty, if so, only then acquiring the page table lock and checking +again to see if it was allocated underneath us. + +This allows for a traversal with page table locks only being taken when +required. An example of this is :c:func:`!__pud_alloc`. + +At the leaf page table, that is the PTE, we can't entirely rely on this pattern +as we have separate PMD and PTE locks and a THP collapse for instance might have +eliminated the PMD entry as well as the PTE from under us. + +This is why :c:func:`!__pte_offset_map_lock` locklessly retrieves the PMD entry +for the PTE, carefully checking it is as expected, before acquiring the +PTE-specific lock, and then *again* checking that the PMD entry is as expected. + +If a THP collapse (or similar) were to occur then the lock on both pages would +be acquired, so we can ensure this is prevented while the PTE lock is held. + +Installing entries this way ensures mutual exclusion on write. + +Page table freeing +^^^^^^^^^^^^^^^^^^ + +Tearing down page tables themselves is something that requires significant +care. There must be no way that page tables designated for removal can be +traversed or referenced by concurrent tasks. + +It is insufficient to simply hold an mmap write lock and VMA lock (which will +prevent racing faults, and rmap operations), as a file-backed mapping can be +truncated under the :c:struct:`!struct address_space->i_mmap_rwsem` alone. + +As a result, no VMA which can be accessed via the reverse mapping (either +through the :c:struct:`!struct anon_vma->rb_root` or the :c:member:`!struct +address_space->i_mmap` interval trees) can have its page tables torn down. + +The operation is typically performed via :c:func:`!free_pgtables`, which assumes +either the mmap write lock has been taken (as specified by its +:c:member:`!mm_wr_locked` parameter), or that the VMA is already unreachable. + +It carefully removes the VMA from all reverse mappings, however it's important +that no new ones overlap these or any route remain to permit access to addresses +within the range whose page tables are being torn down. + +Additionally, it assumes that a zap has already been performed and steps have +been taken to ensure that no further page table entries can be installed between +the zap and the invocation of :c:func:`!free_pgtables`. + +Since it is assumed that all such steps have been taken, page table entries are +cleared without page table locks (in the :c:func:`!pgd_clear`, :c:func:`!p4d_clear`, +:c:func:`!pud_clear`, and :c:func:`!pmd_clear` functions. + +.. note:: It is possible for leaf page tables to be torn down independent of + the page tables above it as is done by + :c:func:`!retract_page_tables`, which is performed under the i_mmap + read lock, PMD, and PTE page table locks, without this level of care. + +Page table moving +^^^^^^^^^^^^^^^^^ + +Some functions manipulate page table levels above PMD (that is PUD, P4D and PGD +page tables). Most notable of these is :c:func:`!mremap`, which is capable of +moving higher level page tables. + +In these instances, it is required that **all** locks are taken, that is +the mmap lock, the VMA lock and the relevant rmap locks. + +You can observe this in the :c:func:`!mremap` implementation in the functions +:c:func:`!take_rmap_locks` and :c:func:`!drop_rmap_locks` which perform the rmap +side of lock acquisition, invoked ultimately by :c:func:`!move_page_tables`. + +VMA lock internals +------------------ + +Overview +^^^^^^^^ + +VMA read locking is entirely optimistic - if the lock is contended or a competing +write has started, then we do not obtain a read lock. + +A VMA **read** lock is obtained by :c:func:`!lock_vma_under_rcu`, which first +calls :c:func:`!rcu_read_lock` to ensure that the VMA is looked up in an RCU +critical section, then attempts to VMA lock it via :c:func:`!vma_start_read`, +before releasing the RCU lock via :c:func:`!rcu_read_unlock`. + +VMA read locks hold the read lock on the :c:member:`!vma->vm_lock` semaphore for +their duration and the caller of :c:func:`!lock_vma_under_rcu` must release it +via :c:func:`!vma_end_read`. + +VMA **write** locks are acquired via :c:func:`!vma_start_write` in instances where a +VMA is about to be modified, unlike :c:func:`!vma_start_read` the lock is always +acquired. An mmap write lock **must** be held for the duration of the VMA write +lock, releasing or downgrading the mmap write lock also releases the VMA write +lock so there is no :c:func:`!vma_end_write` function. + +Note that a semaphore write lock is not held across a VMA lock. Rather, a +sequence number is used for serialisation, and the write semaphore is only +acquired at the point of write lock to update this. + +This ensures the semantics we require - VMA write locks provide exclusive write +access to the VMA. + +Implementation details +^^^^^^^^^^^^^^^^^^^^^^ + +The VMA lock mechanism is designed to be a lightweight means of avoiding the use +of the heavily contended mmap lock. It is implemented using a combination of a +read/write semaphore and sequence numbers belonging to the containing +:c:struct:`!struct mm_struct` and the VMA. + +Read locks are acquired via :c:func:`!vma_start_read`, which is an optimistic +operation, i.e. it tries to acquire a read lock but returns false if it is +unable to do so. At the end of the read operation, :c:func:`!vma_end_read` is +called to release the VMA read lock. + +Invoking :c:func:`!vma_start_read` requires that :c:func:`!rcu_read_lock` has +been called first, establishing that we are in an RCU critical section upon VMA +read lock acquisition. Once acquired, the RCU lock can be released as it is only +required for lookup. This is abstracted by :c:func:`!lock_vma_under_rcu` which +is the interface a user should use. + +Writing requires the mmap to be write-locked and the VMA lock to be acquired via +:c:func:`!vma_start_write`, however the write lock is released by the termination or +downgrade of the mmap write lock so no :c:func:`!vma_end_write` is required. + +All this is achieved by the use of per-mm and per-VMA sequence counts, which are +used in order to reduce complexity, especially for operations which write-lock +multiple VMAs at once. + +If the mm sequence count, :c:member:`!mm->mm_lock_seq` is equal to the VMA +sequence count :c:member:`!vma->vm_lock_seq` then the VMA is write-locked. If +they differ, then it is not. + +Each time the mmap write lock is released in :c:func:`!mmap_write_unlock` or +:c:func:`!mmap_write_downgrade`, :c:func:`!vma_end_write_all` is invoked which +also increments :c:member:`!mm->mm_lock_seq` via +:c:func:`!mm_lock_seqcount_end`. + +This way, we ensure that, regardless of the VMA's sequence number, a write lock +is never incorrectly indicated and that when we release an mmap write lock we +efficiently release **all** VMA write locks contained within the mmap at the +same time. + +Since the mmap write lock is exclusive against others who hold it, the automatic +release of any VMA locks on its release makes sense, as you would never want to +keep VMAs locked across entirely separate write operations. It also maintains +correct lock ordering. + +Each time a VMA read lock is acquired, we acquire a read lock on the +:c:member:`!vma->vm_lock` read/write semaphore and hold it, while checking that +the sequence count of the VMA does not match that of the mm. + +If it does, the read lock fails. If it does not, we hold the lock, excluding +writers, but permitting other readers, who will also obtain this lock under RCU. + +Importantly, maple tree operations performed in :c:func:`!lock_vma_under_rcu` +are also RCU safe, so the whole read lock operation is guaranteed to function +correctly. + +On the write side, we acquire a write lock on the :c:member:`!vma->vm_lock` +read/write semaphore, before setting the VMA's sequence number under this lock, +also simultaneously holding the mmap write lock. + +This way, if any read locks are in effect, :c:func:`!vma_start_write` will sleep +until these are finished and mutual exclusion is achieved. + +After setting the VMA's sequence number, the lock is released, avoiding +complexity with a long-term held write lock. + +This clever combination of a read/write semaphore and sequence count allows for +fast RCU-based per-VMA lock acquisition (especially on page fault, though +utilised elsewhere) with minimal complexity around lock ordering. + +mmap write lock downgrading +--------------------------- + +When an mmap write lock is held one has exclusive access to resources within the +mmap (with the usual caveats about requiring VMA write locks to avoid races with +tasks holding VMA read locks). + +It is then possible to **downgrade** from a write lock to a read lock via +:c:func:`!mmap_write_downgrade` which, similar to :c:func:`!mmap_write_unlock`, +implicitly terminates all VMA write locks via :c:func:`!vma_end_write_all`, but +importantly does not relinquish the mmap lock while downgrading, therefore +keeping the locked virtual address space stable. + +An interesting consequence of this is that downgraded locks are exclusive +against any other task possessing a downgraded lock (since a racing task would +have to acquire a write lock first to downgrade it, and the downgraded lock +prevents a new write lock from being obtained until the original lock is +released). + +For clarity, we map read (R)/downgraded write (D)/write (W) locks against one +another showing which locks exclude the others: + +.. list-table:: Lock exclusivity + :widths: 5 5 5 5 + :header-rows: 1 + :stub-columns: 1 + + * - + - R + - D + - W + * - R + - N + - N + - Y + * - D + - N + - Y + - Y + * - W + - Y + - Y + - Y + +Here a Y indicates the locks in the matching row/column are mutually exclusive, +and N indicates that they are not. + +Stack expansion +--------------- + +Stack expansion throws up additional complexities in that we cannot permit there +to be racing page faults, as a result we invoke :c:func:`!vma_start_write` to +prevent this in :c:func:`!expand_downwards` or :c:func:`!expand_upwards`. diff --git a/Documentation/netlink/specs/mptcp_pm.yaml b/Documentation/netlink/specs/mptcp_pm.yaml index dc190bf838fe..dfd017780d2f 100644 --- a/Documentation/netlink/specs/mptcp_pm.yaml +++ b/Documentation/netlink/specs/mptcp_pm.yaml @@ -22,65 +22,67 @@ definitions: doc: unused event - name: created - doc: - token, family, saddr4 | saddr6, daddr4 | daddr6, sport, dport + doc: >- A new MPTCP connection has been created. It is the good time to allocate memory and send ADD_ADDR if needed. Depending on the traffic-patterns it can take a long time until the MPTCP_EVENT_ESTABLISHED is sent. + Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, sport, + dport, server-side. - name: established - doc: - token, family, saddr4 | saddr6, daddr4 | daddr6, sport, dport + doc: >- A MPTCP connection is established (can start new subflows). + Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, sport, + dport, server-side. - name: closed - doc: - token + doc: >- A MPTCP connection has stopped. + Attribute: token. - name: announced value: 6 - doc: - token, rem_id, family, daddr4 | daddr6 [, dport] + doc: >- A new address has been announced by the peer. + Attributes: token, rem_id, family, daddr4 | daddr6 [, dport]. - name: removed - doc: - token, rem_id + doc: >- An address has been lost by the peer. + Attributes: token, rem_id. - name: sub-established value: 10 - doc: - token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | daddr6, sport, - dport, backup, if_idx [, error] + doc: >- A new subflow has been established. 'error' should not be set. + Attributes: token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | + daddr6, sport, dport, backup, if_idx [, error]. - name: sub-closed - doc: - token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | daddr6, sport, - dport, backup, if_idx [, error] + doc: >- A subflow has been closed. An error (copy of sk_err) could be set if an error has been detected for this subflow. + Attributes: token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | + daddr6, sport, dport, backup, if_idx [, error]. - name: sub-priority value: 13 - doc: - token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | daddr6, sport, - dport, backup, if_idx [, error] + doc: >- The priority of a subflow has changed. 'error' should not be set. + Attributes: token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | + daddr6, sport, dport, backup, if_idx [, error]. - name: listener-created value: 15 - doc: - family, sport, saddr4 | saddr6 + doc: >- A new PM listener is created. + Attributes: family, sport, saddr4 | saddr6. - name: listener-closed - doc: - family, sport, saddr4 | saddr6 + doc: >- A PM listener is closed. + Attributes: family, sport, saddr4 | saddr6. attribute-sets: - @@ -306,8 +308,8 @@ operations: attributes: - addr - - name: flush-addrs - doc: flush addresses + name: flush-addrs + doc: Flush addresses attribute-set: endpoint dont-validate: [ strict ] flags: [ uns-admin-perm ] @@ -351,7 +353,7 @@ operations: - addr-remote - name: announce - doc: announce new sf + doc: Announce new address attribute-set: attr dont-validate: [ strict ] flags: [ uns-admin-perm ] @@ -362,7 +364,7 @@ operations: - token - name: remove - doc: announce removal + doc: Announce removal attribute-set: attr dont-validate: [ strict ] flags: [ uns-admin-perm ] @@ -373,7 +375,7 @@ operations: - loc-id - name: subflow-create - doc: todo + doc: Create subflow attribute-set: attr dont-validate: [ strict ] flags: [ uns-admin-perm ] @@ -385,7 +387,7 @@ operations: - addr-remote - name: subflow-destroy - doc: todo + doc: Destroy subflow attribute-set: attr dont-validate: [ strict ] flags: [ uns-admin-perm ] diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 454c2aaa155e..f15b61317aad 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -1914,6 +1914,9 @@ No flags are specified so far, the corresponding field must be set to zero. #define KVM_IRQ_ROUTING_HV_SINT 4 #define KVM_IRQ_ROUTING_XEN_EVTCHN 5 +On s390, adding a KVM_IRQ_ROUTING_S390_ADAPTER is rejected on ucontrol VMs with +error -EINVAL. + flags: - KVM_MSI_VALID_DEVID: used along with KVM_IRQ_ROUTING_MSI routing entry diff --git a/Documentation/virt/kvm/devices/s390_flic.rst b/Documentation/virt/kvm/devices/s390_flic.rst index ea96559ba501..b784f8016748 100644 --- a/Documentation/virt/kvm/devices/s390_flic.rst +++ b/Documentation/virt/kvm/devices/s390_flic.rst @@ -58,11 +58,15 @@ Groups: Enables async page faults for the guest. So in case of a major page fault the host is allowed to handle this async and continues the guest. + -EINVAL is returned when called on the FLIC of a ucontrol VM. + KVM_DEV_FLIC_APF_DISABLE_WAIT Disables async page faults for the guest and waits until already pending async page faults are done. This is necessary to trigger a completion interrupt for every init interrupt before migrating the interrupt list. + -EINVAL is returned when called on the FLIC of a ucontrol VM. + KVM_DEV_FLIC_ADAPTER_REGISTER Register an I/O adapter interrupt source. Takes a kvm_s390_io_adapter describing the adapter to register:: diff --git a/MAINTAINERS b/MAINTAINERS index 69c26c22349f..0fa7c5728f1e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -949,7 +949,6 @@ AMAZON ETHERNET DRIVERS M: Shay Agroskin <shayagr@amazon.com> M: Arthur Kiyanovski <akiyano@amazon.com> R: David Arinzon <darinzon@amazon.com> -R: Noam Dagan <ndagan@amazon.com> R: Saeed Bishara <saeedb@amazon.com> L: netdev@vger.kernel.org S: Supported @@ -1797,7 +1796,6 @@ F: include/uapi/linux/if_arcnet.h ARM AND ARM64 SoC SUB-ARCHITECTURES (COMMON PARTS) M: Arnd Bergmann <arnd@arndb.de> -M: Olof Johansson <olof@lixom.net> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: soc@lists.linux.dev S: Maintained @@ -2691,7 +2689,6 @@ N: at91 N: atmel ARM/Microchip Sparx5 SoC support -M: Lars Povlsen <lars.povlsen@microchip.com> M: Steen Hegelund <Steen.Hegelund@microchip.com> M: Daniel Machon <daniel.machon@microchip.com> M: UNGLinuxDriver@microchip.com @@ -3608,6 +3605,7 @@ F: drivers/phy/qualcomm/phy-ath79-usb.c ATHEROS ATH GENERIC UTILITIES M: Kalle Valo <kvalo@kernel.org> +M: Jeff Johnson <jjohnson@kernel.org> L: linux-wireless@vger.kernel.org S: Supported F: drivers/net/wireless/ath/* @@ -4058,7 +4056,6 @@ F: net/bluetooth/ BONDING DRIVER M: Jay Vosburgh <jv@jvosburgh.net> -M: Andy Gospodarek <andy@greyhouse.net> L: netdev@vger.kernel.org S: Maintained F: Documentation/networking/bonding.rst @@ -4131,7 +4128,6 @@ S: Odd Fixes F: drivers/net/ethernet/netronome/nfp/bpf/ BPF JIT for POWERPC (32-BIT AND 64-BIT) -M: Michael Ellerman <mpe@ellerman.id.au> M: Hari Bathini <hbathini@linux.ibm.com> M: Christophe Leroy <christophe.leroy@csgroup.eu> R: Naveen N Rao <naveen@kernel.org> @@ -7348,7 +7344,7 @@ F: drivers/gpu/drm/panel/panel-novatek-nt36672a.c DRM DRIVER FOR NVIDIA GEFORCE/QUADRO GPUS M: Karol Herbst <kherbst@redhat.com> M: Lyude Paul <lyude@redhat.com> -M: Danilo Krummrich <dakr@redhat.com> +M: Danilo Krummrich <dakr@kernel.org> L: dri-devel@lists.freedesktop.org L: nouveau@lists.freedesktop.org S: Supported @@ -8454,7 +8450,7 @@ F: include/video/s1d13xxxfb.h EROFS FILE SYSTEM M: Gao Xiang <xiang@kernel.org> M: Chao Yu <chao@kernel.org> -R: Yue Hu <huyue2@coolpad.com> +R: Yue Hu <zbestahu@gmail.com> R: Jeffle Xu <jefflexu@linux.alibaba.com> R: Sandeep Dhavale <dhavale@google.com> L: linux-erofs@lists.ozlabs.org @@ -8925,7 +8921,7 @@ F: include/linux/arm_ffa.h FIRMWARE LOADER (request_firmware) M: Luis Chamberlain <mcgrof@kernel.org> M: Russ Weight <russ.weight@linux.dev> -M: Danilo Krummrich <dakr@redhat.com> +M: Danilo Krummrich <dakr@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/firmware_class/ @@ -12633,7 +12629,7 @@ F: arch/mips/include/uapi/asm/kvm* F: arch/mips/kvm/ KERNEL VIRTUAL MACHINE FOR POWERPC (KVM/powerpc) -M: Michael Ellerman <mpe@ellerman.id.au> +M: Madhavan Srinivasan <maddy@linux.ibm.com> R: Nicholas Piggin <npiggin@gmail.com> L: linuxppc-dev@lists.ozlabs.org L: kvm@vger.kernel.org @@ -13212,11 +13208,11 @@ X: drivers/macintosh/adb-iop.c X: drivers/macintosh/via-macii.c LINUX FOR POWERPC (32-BIT AND 64-BIT) +M: Madhavan Srinivasan <maddy@linux.ibm.com> M: Michael Ellerman <mpe@ellerman.id.au> R: Nicholas Piggin <npiggin@gmail.com> R: Christophe Leroy <christophe.leroy@csgroup.eu> R: Naveen N Rao <naveen@kernel.org> -M: Madhavan Srinivasan <maddy@linux.ibm.com> L: linuxppc-dev@lists.ozlabs.org S: Supported W: https://github.com/linuxppc/wiki/wiki @@ -14567,7 +14563,6 @@ F: drivers/dma/mediatek/ MEDIATEK ETHERNET DRIVER M: Felix Fietkau <nbd@nbd.name> M: Sean Wang <sean.wang@mediatek.com> -M: Mark Lee <Mark-MC.Lee@mediatek.com> M: Lorenzo Bianconi <lorenzo@kernel.org> L: netdev@vger.kernel.org S: Maintained @@ -14757,7 +14752,7 @@ F: drivers/memory/mtk-smi.c F: include/soc/mediatek/smi.h MEDIATEK SWITCH DRIVER -M: Arınç ÃœNAL <arinc.unal@arinc9.com> +M: Chester A. Unal <chester.a.unal@arinc9.com> M: Daniel Golle <daniel@makrotopia.org> M: DENG Qingfang <dqfext@gmail.com> M: Sean Wang <sean.wang@mediatek.com> @@ -18461,7 +18456,7 @@ F: Documentation/devicetree/bindings/pinctrl/mediatek,mt8183-pinctrl.yaml F: drivers/pinctrl/mediatek/ PIN CONTROLLER - MEDIATEK MIPS -M: Arınç ÃœNAL <arinc.unal@arinc9.com> +M: Chester A. Unal <chester.a.unal@arinc9.com> M: Sergio Paracuellos <sergio.paracuellos@gmail.com> L: linux-mediatek@lists.infradead.org (moderated for non-subscribers) L: linux-mips@vger.kernel.org @@ -19505,7 +19500,7 @@ S: Maintained F: arch/mips/ralink RALINK MT7621 MIPS ARCHITECTURE -M: Arınç ÃœNAL <arinc.unal@arinc9.com> +M: Chester A. Unal <chester.a.unal@arinc9.com> M: Sergio Paracuellos <sergio.paracuellos@gmail.com> L: linux-mips@vger.kernel.org S: Maintained @@ -20908,6 +20903,8 @@ F: kernel/sched/ SCHEDULER - SCHED_EXT R: Tejun Heo <tj@kernel.org> R: David Vernet <void@manifault.com> +R: Andrea Righi <arighi@nvidia.com> +R: Changwoo Min <changwoo@igalia.com> L: linux-kernel@vger.kernel.org S: Maintained W: https://github.com/sched-ext/scx @@ -22503,11 +22500,8 @@ F: Documentation/devicetree/bindings/phy/st,stm32mp25-combophy.yaml F: drivers/phy/st/phy-stm32-combophy.c STMMAC ETHERNET DRIVER -M: Alexandre Torgue <alexandre.torgue@foss.st.com> -M: Jose Abreu <joabreu@synopsys.com> L: netdev@vger.kernel.org -S: Supported -W: http://www.stlinux.com +S: Orphan F: Documentation/networking/device_drivers/ethernet/stmicro/ F: drivers/net/ethernet/stmicro/stmmac/ @@ -22739,9 +22733,8 @@ S: Supported F: drivers/net/ethernet/synopsys/ SYNOPSYS DESIGNWARE ETHERNET XPCS DRIVER -M: Jose Abreu <Jose.Abreu@synopsys.com> L: netdev@vger.kernel.org -S: Supported +S: Orphan F: drivers/net/pcs/pcs-xpcs.c F: drivers/net/pcs/pcs-xpcs.h F: include/linux/pcs/pcs-xpcs.h @@ -23649,7 +23642,6 @@ F: tools/testing/selftests/timers/ TIPC NETWORK LAYER M: Jon Maloy <jmaloy@redhat.com> -M: Ying Xue <ying.xue@windriver.com> L: netdev@vger.kernel.org (core kernel code) L: tipc-discussion@lists.sourceforge.net (user apps, general discussion) S: Maintained @@ -24255,7 +24247,8 @@ F: Documentation/devicetree/bindings/usb/nxp,isp1760.yaml F: drivers/usb/isp1760/* USB LAN78XX ETHERNET DRIVER -M: Woojung Huh <woojung.huh@microchip.com> +M: Thangaraj Samynathan <Thangaraj.S@microchip.com> +M: Rengarajan Sundararajan <Rengarajan.S@microchip.com> M: UNGLinuxDriver@microchip.com L: netdev@vger.kernel.org S: Maintained @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 13 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc7 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index ea5a1dcb133b..4f2eeda907ec 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -6,6 +6,7 @@ config ARC def_bool y select ARC_TIMERS + select ARCH_HAS_CPU_CACHE_ALIASING select ARCH_HAS_CACHE_LINE_SIZE select ARCH_HAS_DEBUG_VM_PGTABLE select ARCH_HAS_DMA_PREP_COHERENT diff --git a/arch/arc/include/asm/cachetype.h b/arch/arc/include/asm/cachetype.h new file mode 100644 index 000000000000..acd3b6cb4bf5 --- /dev/null +++ b/arch/arc/include/asm/cachetype.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_ARC_CACHETYPE_H +#define __ASM_ARC_CACHETYPE_H + +#define cpu_dcache_is_aliasing() false +#define cpu_icache_is_aliasing() true + +#endif diff --git a/arch/arm/boot/dts/nxp/imx/imxrt1050.dtsi b/arch/arm/boot/dts/nxp/imx/imxrt1050.dtsi index dd714d235d5f..b0bad0d1ba36 100644 --- a/arch/arm/boot/dts/nxp/imx/imxrt1050.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imxrt1050.dtsi @@ -87,7 +87,7 @@ reg = <0x402c0000 0x4000>; interrupts = <110>; clocks = <&clks IMXRT1050_CLK_IPG_PDOF>, - <&clks IMXRT1050_CLK_OSC>, + <&clks IMXRT1050_CLK_AHB_PODF>, <&clks IMXRT1050_CLK_USDHC1>; clock-names = "ipg", "ahb", "per"; bus-width = <4>; diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index 0beecdde55f5..f25eadcba5e6 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -323,6 +323,7 @@ CONFIG_SND_SOC_IMX_SGTL5000=y CONFIG_SND_SOC_FSL_ASOC_CARD=y CONFIG_SND_SOC_AC97_CODEC=y CONFIG_SND_SOC_CS42XX8_I2C=y +CONFIG_SND_SOC_SPDIF=y CONFIG_SND_SOC_TLV320AIC3X_I2C=y CONFIG_SND_SOC_WM8960=y CONFIG_SND_SOC_WM8962=y diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig index e4fe059cd861..dc47b2312127 100644 --- a/arch/arm/mach-imx/Kconfig +++ b/arch/arm/mach-imx/Kconfig @@ -6,6 +6,7 @@ menuconfig ARCH_MXC select CLKSRC_IMX_GPT select GENERIC_IRQ_CHIP select GPIOLIB + select PINCTRL select PM_OPP if PM select SOC_BUS select SRAM diff --git a/arch/arm64/boot/dts/arm/fvp-base-revc.dts b/arch/arm64/boot/dts/arm/fvp-base-revc.dts index 19973ab4ea6b..9e10d7a6b5a2 100644 --- a/arch/arm64/boot/dts/arm/fvp-base-revc.dts +++ b/arch/arm64/boot/dts/arm/fvp-base-revc.dts @@ -233,7 +233,7 @@ #interrupt-cells = <0x1>; compatible = "pci-host-ecam-generic"; device_type = "pci"; - bus-range = <0x0 0x1>; + bus-range = <0x0 0xff>; reg = <0x0 0x40000000 0x0 0x10000000>; ranges = <0x2000000 0x0 0x50000000 0x0 0x50000000 0x0 0x10000000>; interrupt-map = <0 0 0 1 &gic 0 0 GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi index 6e5a984c1d4e..26a29e5e5078 100644 --- a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi +++ b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi @@ -67,7 +67,7 @@ l2_cache_l0: l2-cache-l0 { compatible = "cache"; cache-size = <0x80000>; - cache-line-size = <128>; + cache-line-size = <64>; cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set cache-level = <2>; cache-unified; @@ -91,7 +91,7 @@ l2_cache_l1: l2-cache-l1 { compatible = "cache"; cache-size = <0x80000>; - cache-line-size = <128>; + cache-line-size = <64>; cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set cache-level = <2>; cache-unified; @@ -115,7 +115,7 @@ l2_cache_l2: l2-cache-l2 { compatible = "cache"; cache-size = <0x80000>; - cache-line-size = <128>; + cache-line-size = <64>; cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set cache-level = <2>; cache-unified; @@ -139,7 +139,7 @@ l2_cache_l3: l2-cache-l3 { compatible = "cache"; cache-size = <0x80000>; - cache-line-size = <128>; + cache-line-size = <64>; cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set cache-level = <2>; cache-unified; diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi index a60ebb718789..c32a6947ae9c 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi @@ -165,7 +165,7 @@ audio_subsys: bus@59000000 { }; esai0: esai@59010000 { - compatible = "fsl,imx8qm-esai"; + compatible = "fsl,imx8qm-esai", "fsl,imx6ull-esai"; reg = <0x59010000 0x10000>; interrupts = <GIC_SPI 409 IRQ_TYPE_LEVEL_HIGH>; clocks = <&esai0_lpcg IMX_LPCG_CLK_4>, diff --git a/arch/arm64/boot/dts/freescale/imx8qm-ss-audio.dtsi b/arch/arm64/boot/dts/freescale/imx8qm-ss-audio.dtsi index e24e639b98ee..c9b55f02497a 100644 --- a/arch/arm64/boot/dts/freescale/imx8qm-ss-audio.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8qm-ss-audio.dtsi @@ -134,7 +134,7 @@ }; esai1: esai@59810000 { - compatible = "fsl,imx8qm-esai"; + compatible = "fsl,imx8qm-esai", "fsl,imx6ull-esai"; reg = <0x59810000 0x10000>; interrupts = <GIC_SPI 411 IRQ_TYPE_LEVEL_HIGH>; clocks = <&esai1_lpcg IMX_LPCG_CLK_0>, diff --git a/arch/arm64/boot/dts/freescale/imx95.dtsi b/arch/arm64/boot/dts/freescale/imx95.dtsi index d10f62eacfe0..e9c7a8265d71 100644 --- a/arch/arm64/boot/dts/freescale/imx95.dtsi +++ b/arch/arm64/boot/dts/freescale/imx95.dtsi @@ -1673,7 +1673,7 @@ netcmix_blk_ctrl: syscon@4c810000 { compatible = "nxp,imx95-netcmix-blk-ctrl", "syscon"; - reg = <0x0 0x4c810000 0x0 0x10000>; + reg = <0x0 0x4c810000 0x0 0x8>; #clock-cells = <1>; clocks = <&scmi_clk IMX95_CLK_BUSNETCMIX>; assigned-clocks = <&scmi_clk IMX95_CLK_BUSNETCMIX>; diff --git a/arch/arm64/boot/dts/qcom/sa8775p.dtsi b/arch/arm64/boot/dts/qcom/sa8775p.dtsi index 9f315a51a7c1..9da62d7c4d27 100644 --- a/arch/arm64/boot/dts/qcom/sa8775p.dtsi +++ b/arch/arm64/boot/dts/qcom/sa8775p.dtsi @@ -2440,6 +2440,7 @@ qcom,cmb-element-bits = <32>; qcom,cmb-msrs-num = <32>; + status = "disabled"; out-ports { port { @@ -6092,7 +6093,7 @@ <0x0 0x40000000 0x0 0xf20>, <0x0 0x40000f20 0x0 0xa8>, <0x0 0x40001000 0x0 0x4000>, - <0x0 0x40200000 0x0 0x100000>, + <0x0 0x40200000 0x0 0x1fe00000>, <0x0 0x01c03000 0x0 0x1000>, <0x0 0x40005000 0x0 0x2000>; reg-names = "parf", "dbi", "elbi", "atu", "addr_space", @@ -6250,7 +6251,7 @@ <0x0 0x60000000 0x0 0xf20>, <0x0 0x60000f20 0x0 0xa8>, <0x0 0x60001000 0x0 0x4000>, - <0x0 0x60200000 0x0 0x100000>, + <0x0 0x60200000 0x0 0x1fe00000>, <0x0 0x01c13000 0x0 0x1000>, <0x0 0x60005000 0x0 0x2000>; reg-names = "parf", "dbi", "elbi", "atu", "addr_space", diff --git a/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts b/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts index 975550139e10..66513fc8e67a 100644 --- a/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts +++ b/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts @@ -773,6 +773,10 @@ status = "okay"; }; +&usb_1_ss0_dwc3 { + dr_mode = "host"; +}; + &usb_1_ss0_dwc3_hs { remote-endpoint = <&pmic_glink_ss0_hs_in>; }; @@ -801,6 +805,10 @@ status = "okay"; }; +&usb_1_ss1_dwc3 { + dr_mode = "host"; +}; + &usb_1_ss1_dwc3_hs { remote-endpoint = <&pmic_glink_ss1_hs_in>; }; diff --git a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts index 39f9d9cdc10d..d51a9bdcf67f 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts +++ b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts @@ -1197,6 +1197,10 @@ status = "okay"; }; +&usb_1_ss0_dwc3 { + dr_mode = "host"; +}; + &usb_1_ss0_dwc3_hs { remote-endpoint = <&pmic_glink_ss0_hs_in>; }; @@ -1225,6 +1229,10 @@ status = "okay"; }; +&usb_1_ss1_dwc3 { + dr_mode = "host"; +}; + &usb_1_ss1_dwc3_hs { remote-endpoint = <&pmic_glink_ss1_hs_in>; }; @@ -1253,6 +1261,10 @@ status = "okay"; }; +&usb_1_ss2_dwc3 { + dr_mode = "host"; +}; + &usb_1_ss2_dwc3_hs { remote-endpoint = <&pmic_glink_ss2_hs_in>; }; diff --git a/arch/arm64/boot/dts/qcom/x1e80100.dtsi b/arch/arm64/boot/dts/qcom/x1e80100.dtsi index 88805629ed2b..7e4f46ad8edd 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100.dtsi +++ b/arch/arm64/boot/dts/qcom/x1e80100.dtsi @@ -2924,7 +2924,7 @@ #address-cells = <3>; #size-cells = <2>; ranges = <0x01000000 0x0 0x00000000 0x0 0x70200000 0x0 0x100000>, - <0x02000000 0x0 0x70300000 0x0 0x70300000 0x0 0x1d00000>; + <0x02000000 0x0 0x70300000 0x0 0x70300000 0x0 0x3d00000>; bus-range = <0x00 0xff>; dma-coherent; @@ -4066,8 +4066,6 @@ dma-coherent; - usb-role-switch; - ports { #address-cells = <1>; #size-cells = <0>; @@ -4321,8 +4319,6 @@ dma-coherent; - usb-role-switch; - ports { #address-cells = <1>; #size-cells = <0>; @@ -4421,8 +4417,6 @@ dma-coherent; - usb-role-switch; - ports { #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index 0597de415fe0..7d992c3c01ce 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -333,6 +333,7 @@ power-domain@RK3328_PD_HEVC { reg = <RK3328_PD_HEVC>; + clocks = <&cru SCLK_VENC_CORE>; #power-domain-cells = <0>; }; power-domain@RK3328_PD_VIDEO { diff --git a/arch/arm64/boot/dts/rockchip/rk3568.dtsi b/arch/arm64/boot/dts/rockchip/rk3568.dtsi index ecaefe208e3e..695cccbdab0f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3568.dtsi @@ -350,6 +350,7 @@ assigned-clocks = <&pmucru CLK_PCIEPHY0_REF>; assigned-clock-rates = <100000000>; resets = <&cru SRST_PIPEPHY0>; + reset-names = "phy"; rockchip,pipe-grf = <&pipegrf>; rockchip,pipe-phy-grf = <&pipe_phy_grf0>; #phy-cells = <1>; diff --git a/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi b/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi index 62be06f3b863..e55390629114 100644 --- a/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi @@ -1681,6 +1681,7 @@ assigned-clocks = <&pmucru CLK_PCIEPHY1_REF>; assigned-clock-rates = <100000000>; resets = <&cru SRST_PIPEPHY1>; + reset-names = "phy"; rockchip,pipe-grf = <&pipegrf>; rockchip,pipe-phy-grf = <&pipe_phy_grf1>; #phy-cells = <1>; @@ -1697,6 +1698,7 @@ assigned-clocks = <&pmucru CLK_PCIEPHY2_REF>; assigned-clock-rates = <100000000>; resets = <&cru SRST_PIPEPHY2>; + reset-names = "phy"; rockchip,pipe-grf = <&pipegrf>; rockchip,pipe-phy-grf = <&pipe_phy_grf2>; #phy-cells = <1>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts index c44d001da169..d597112f1d5b 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts @@ -72,7 +72,7 @@ rfkill { compatible = "rfkill-gpio"; - label = "rfkill-pcie-wlan"; + label = "rfkill-m2-wlan"; radio-type = "wlan"; shutdown-gpios = <&gpio4 RK_PA2 GPIO_ACTIVE_HIGH>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6.dtsi b/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6.dtsi index 76a6e8e517e9..c9749cb50076 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6.dtsi @@ -434,6 +434,7 @@ &sdmmc { bus-width = <4>; cap-sd-highspeed; + cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>; disable-wp; max-frequency = <150000000>; no-mmc; diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 37e24f1bd227..99ea26d400ff 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -36,15 +36,8 @@ #include <asm/traps.h> #include <asm/vdso.h> -#ifdef CONFIG_ARM64_GCS #define GCS_SIGNAL_CAP(addr) (((unsigned long)addr) & GCS_CAP_ADDR_MASK) -static bool gcs_signal_cap_valid(u64 addr, u64 val) -{ - return val == GCS_SIGNAL_CAP(addr); -} -#endif - /* * Do a signal return; undo the signal stack. These are aligned to 128-bit. */ @@ -1062,8 +1055,7 @@ static int restore_sigframe(struct pt_regs *regs, #ifdef CONFIG_ARM64_GCS static int gcs_restore_signal(void) { - unsigned long __user *gcspr_el0; - u64 cap; + u64 gcspr_el0, cap; int ret; if (!system_supports_gcs()) @@ -1072,7 +1064,7 @@ static int gcs_restore_signal(void) if (!(current->thread.gcs_el0_mode & PR_SHADOW_STACK_ENABLE)) return 0; - gcspr_el0 = (unsigned long __user *)read_sysreg_s(SYS_GCSPR_EL0); + gcspr_el0 = read_sysreg_s(SYS_GCSPR_EL0); /* * Ensure that any changes to the GCS done via GCS operations @@ -1087,22 +1079,23 @@ static int gcs_restore_signal(void) * then faults will be generated on GCS operations - the main * concern is to protect GCS pages. */ - ret = copy_from_user(&cap, gcspr_el0, sizeof(cap)); + ret = copy_from_user(&cap, (unsigned long __user *)gcspr_el0, + sizeof(cap)); if (ret) return -EFAULT; /* * Check that the cap is the actual GCS before replacing it. */ - if (!gcs_signal_cap_valid((u64)gcspr_el0, cap)) + if (cap != GCS_SIGNAL_CAP(gcspr_el0)) return -EINVAL; /* Invalidate the token to prevent reuse */ - put_user_gcs(0, (__user void*)gcspr_el0, &ret); + put_user_gcs(0, (unsigned long __user *)gcspr_el0, &ret); if (ret != 0) return -EFAULT; - write_sysreg_s(gcspr_el0 + 1, SYS_GCSPR_EL0); + write_sysreg_s(gcspr_el0 + 8, SYS_GCSPR_EL0); return 0; } @@ -1421,7 +1414,7 @@ static int get_sigframe(struct rt_sigframe_user_layout *user, static int gcs_signal_entry(__sigrestore_t sigtramp, struct ksignal *ksig) { - unsigned long __user *gcspr_el0; + u64 gcspr_el0; int ret = 0; if (!system_supports_gcs()) @@ -1434,18 +1427,20 @@ static int gcs_signal_entry(__sigrestore_t sigtramp, struct ksignal *ksig) * We are entering a signal handler, current register state is * active. */ - gcspr_el0 = (unsigned long __user *)read_sysreg_s(SYS_GCSPR_EL0); + gcspr_el0 = read_sysreg_s(SYS_GCSPR_EL0); /* * Push a cap and the GCS entry for the trampoline onto the GCS. */ - put_user_gcs((unsigned long)sigtramp, gcspr_el0 - 2, &ret); - put_user_gcs(GCS_SIGNAL_CAP(gcspr_el0 - 1), gcspr_el0 - 1, &ret); + put_user_gcs((unsigned long)sigtramp, + (unsigned long __user *)(gcspr_el0 - 16), &ret); + put_user_gcs(GCS_SIGNAL_CAP(gcspr_el0 - 8), + (unsigned long __user *)(gcspr_el0 - 8), &ret); if (ret != 0) return ret; - gcspr_el0 -= 2; - write_sysreg_s((unsigned long)gcspr_el0, SYS_GCSPR_EL0); + gcspr_el0 -= 16; + write_sysreg_s(gcspr_el0, SYS_GCSPR_EL0); return 0; } diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index caba3e4bd09e..e75374d682f4 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -783,9 +783,6 @@ static int hyp_ack_unshare(u64 addr, const struct pkvm_mem_transition *tx) if (tx->initiator.id == PKVM_ID_HOST && hyp_page_count((void *)addr)) return -EBUSY; - if (__hyp_ack_skip_pgtable_check(tx)) - return 0; - return __hyp_check_page_state_range(addr, size, PKVM_PAGE_SHARED_BORROWED); } diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 456102bc0b55..6c5950b9ceac 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -24,6 +24,7 @@ static DEFINE_MUTEX(arm_pmus_lock); static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc); static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc); +static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc); static struct kvm_vcpu *kvm_pmc_to_vcpu(const struct kvm_pmc *pmc) { @@ -327,48 +328,25 @@ u64 kvm_pmu_implemented_counter_mask(struct kvm_vcpu *vcpu) return GENMASK(val - 1, 0) | BIT(ARMV8_PMU_CYCLE_IDX); } -/** - * kvm_pmu_enable_counter_mask - enable selected PMU counters - * @vcpu: The vcpu pointer - * @val: the value guest writes to PMCNTENSET register - * - * Call perf_event_enable to start counting the perf event - */ -void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) +static void kvm_pmc_enable_perf_event(struct kvm_pmc *pmc) { - int i; - if (!kvm_vcpu_has_pmu(vcpu)) - return; - - if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E) || !val) + if (!pmc->perf_event) { + kvm_pmu_create_perf_event(pmc); return; + } - for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) { - struct kvm_pmc *pmc; - - if (!(val & BIT(i))) - continue; - - pmc = kvm_vcpu_idx_to_pmc(vcpu, i); + perf_event_enable(pmc->perf_event); + if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE) + kvm_debug("fail to enable perf event\n"); +} - if (!pmc->perf_event) { - kvm_pmu_create_perf_event(pmc); - } else { - perf_event_enable(pmc->perf_event); - if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE) - kvm_debug("fail to enable perf event\n"); - } - } +static void kvm_pmc_disable_perf_event(struct kvm_pmc *pmc) +{ + if (pmc->perf_event) + perf_event_disable(pmc->perf_event); } -/** - * kvm_pmu_disable_counter_mask - disable selected PMU counters - * @vcpu: The vcpu pointer - * @val: the value guest writes to PMCNTENCLR register - * - * Call perf_event_disable to stop counting the perf event - */ -void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) +void kvm_pmu_reprogram_counter_mask(struct kvm_vcpu *vcpu, u64 val) { int i; @@ -376,16 +354,18 @@ void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) return; for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) { - struct kvm_pmc *pmc; + struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, i); if (!(val & BIT(i))) continue; - pmc = kvm_vcpu_idx_to_pmc(vcpu, i); - - if (pmc->perf_event) - perf_event_disable(pmc->perf_event); + if (kvm_pmu_counter_is_enabled(pmc)) + kvm_pmc_enable_perf_event(pmc); + else + kvm_pmc_disable_perf_event(pmc); } + + kvm_vcpu_pmu_restore_guest(vcpu); } /* @@ -626,27 +606,28 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) if (!kvm_has_feat(vcpu->kvm, ID_AA64DFR0_EL1, PMUVer, V3P5)) val &= ~ARMV8_PMU_PMCR_LP; + /* Request a reload of the PMU to enable/disable affected counters */ + if ((__vcpu_sys_reg(vcpu, PMCR_EL0) ^ val) & ARMV8_PMU_PMCR_E) + kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); + /* The reset bits don't indicate any state, and shouldn't be saved. */ __vcpu_sys_reg(vcpu, PMCR_EL0) = val & ~(ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_P); - if (val & ARMV8_PMU_PMCR_E) { - kvm_pmu_enable_counter_mask(vcpu, - __vcpu_sys_reg(vcpu, PMCNTENSET_EL0)); - } else { - kvm_pmu_disable_counter_mask(vcpu, - __vcpu_sys_reg(vcpu, PMCNTENSET_EL0)); - } - if (val & ARMV8_PMU_PMCR_C) kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0); if (val & ARMV8_PMU_PMCR_P) { - unsigned long mask = kvm_pmu_accessible_counter_mask(vcpu); - mask &= ~BIT(ARMV8_PMU_CYCLE_IDX); + /* + * Unlike other PMU sysregs, the controls in PMCR_EL0 always apply + * to the 'guest' range of counters and never the 'hyp' range. + */ + unsigned long mask = kvm_pmu_implemented_counter_mask(vcpu) & + ~kvm_pmu_hyp_counter_mask(vcpu) & + ~BIT(ARMV8_PMU_CYCLE_IDX); + for_each_set_bit(i, &mask, 32) kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, i), 0, true); } - kvm_vcpu_pmu_restore_guest(vcpu); } static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc) @@ -910,11 +891,11 @@ void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu) { u64 mask = kvm_pmu_implemented_counter_mask(vcpu); - kvm_pmu_handle_pmcr(vcpu, kvm_vcpu_read_pmcr(vcpu)); - __vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= mask; __vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= mask; __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= mask; + + kvm_pmu_reprogram_counter_mask(vcpu, mask); } int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index e2a5c2918d9e..634ff18a59a1 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1208,16 +1208,14 @@ static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p, mask = kvm_pmu_accessible_counter_mask(vcpu); if (p->is_write) { val = p->regval & mask; - if (r->Op2 & 0x1) { + if (r->Op2 & 0x1) /* accessing PMCNTENSET_EL0 */ __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) |= val; - kvm_pmu_enable_counter_mask(vcpu, val); - kvm_vcpu_pmu_restore_guest(vcpu); - } else { + else /* accessing PMCNTENCLR_EL0 */ __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= ~val; - kvm_pmu_disable_counter_mask(vcpu, val); - } + + kvm_pmu_reprogram_counter_mask(vcpu, val); } else { p->regval = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); } @@ -2450,6 +2448,26 @@ static unsigned int s1pie_el2_visibility(const struct kvm_vcpu *vcpu, return __el2_visibility(vcpu, rd, s1pie_visibility); } +static bool access_mdcr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + u64 old = __vcpu_sys_reg(vcpu, MDCR_EL2); + + if (!access_rw(vcpu, p, r)) + return false; + + /* + * Request a reload of the PMU to enable/disable the counters affected + * by HPME. + */ + if ((old ^ __vcpu_sys_reg(vcpu, MDCR_EL2)) & MDCR_EL2_HPME) + kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); + + return true; +} + + /* * Architected system registers. * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2 @@ -2983,7 +3001,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { EL2_REG(SCTLR_EL2, access_rw, reset_val, SCTLR_EL2_RES1), EL2_REG(ACTLR_EL2, access_rw, reset_val, 0), EL2_REG_VNCR(HCR_EL2, reset_hcr, 0), - EL2_REG(MDCR_EL2, access_rw, reset_val, 0), + EL2_REG(MDCR_EL2, access_mdcr, reset_val, 0), EL2_REG(CPTR_EL2, access_rw, reset_val, CPTR_NVHE_EL2_RES1), EL2_REG_VNCR(HSTR_EL2, reset_val, 0), EL2_REG_VNCR(HFGRTR_EL2, reset_val, 0), diff --git a/arch/hexagon/Makefile b/arch/hexagon/Makefile index 92d005958dfb..ff172cbe5881 100644 --- a/arch/hexagon/Makefile +++ b/arch/hexagon/Makefile @@ -32,3 +32,9 @@ KBUILD_LDFLAGS += $(ldflags-y) TIR_NAME := r19 KBUILD_CFLAGS += -ffixed-$(TIR_NAME) -DTHREADINFO_REG=$(TIR_NAME) -D__linux__ KBUILD_AFLAGS += -DTHREADINFO_REG=$(TIR_NAME) + +# Disable HexagonConstExtenders pass for LLVM versions prior to 19.1.0 +# https://github.com/llvm/llvm-project/issues/99714 +ifneq ($(call clang-min-version, 190100),y) +KBUILD_CFLAGS += -mllvm -hexagon-cext=false +endif diff --git a/arch/nios2/kernel/cpuinfo.c b/arch/nios2/kernel/cpuinfo.c index 338849c430a5..7b1e8f9128e9 100644 --- a/arch/nios2/kernel/cpuinfo.c +++ b/arch/nios2/kernel/cpuinfo.c @@ -143,11 +143,11 @@ static int show_cpuinfo(struct seq_file *m, void *v) " DIV:\t\t%s\n" " BMX:\t\t%s\n" " CDX:\t\t%s\n", - cpuinfo.has_mul ? "yes" : "no", - cpuinfo.has_mulx ? "yes" : "no", - cpuinfo.has_div ? "yes" : "no", - cpuinfo.has_bmx ? "yes" : "no", - cpuinfo.has_cdx ? "yes" : "no"); + str_yes_no(cpuinfo.has_mul), + str_yes_no(cpuinfo.has_mulx), + str_yes_no(cpuinfo.has_div), + str_yes_no(cpuinfo.has_bmx), + str_yes_no(cpuinfo.has_cdx)); seq_printf(m, "Icache:\t\t%ukB, line length: %u\n", diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig index 57ded82c2840..e8b3f67bf3f5 100644 --- a/arch/powerpc/configs/pmac32_defconfig +++ b/arch/powerpc/configs/pmac32_defconfig @@ -208,6 +208,7 @@ CONFIG_FB_ATY=y CONFIG_FB_ATY_CT=y CONFIG_FB_ATY_GX=y CONFIG_FB_3DFX=y +CONFIG_BACKLIGHT_CLASS_DEVICE=y # CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 4d77e17541e9..ca0c90e95837 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -716,6 +716,7 @@ CONFIG_FB_TRIDENT=m CONFIG_FB_SM501=m CONFIG_FB_IBM_GXT4500=y CONFIG_LCD_PLATFORM=m +CONFIG_BACKLIGHT_CLASS_DEVICE=y CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y CONFIG_LOGO=y diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index 6d0d329cbb35..f9acf866c709 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -34,6 +34,8 @@ enum vcpu_ftr { #define E500_TLB_BITMAP (1 << 30) /* TLB1 entry is mapped by host TLB0 */ #define E500_TLB_TLB0 (1 << 29) +/* entry is writable on the host */ +#define E500_TLB_WRITABLE (1 << 28) /* bits [6-5] MAS2_X1 and MAS2_X0 and [4-0] bits for WIMGE */ #define E500_TLB_MAS2_ATTR (0x7f) diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index e5a145b578a4..06caf8bbbe2b 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -45,11 +45,14 @@ static inline unsigned int tlb1_max_shadow_size(void) return host_tlb_params[1].entries - tlbcam_index - 1; } -static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode) +static inline u32 e500_shadow_mas3_attrib(u32 mas3, bool writable, int usermode) { /* Mask off reserved bits. */ mas3 &= MAS3_ATTRIB_MASK; + if (!writable) + mas3 &= ~(MAS3_UW|MAS3_SW); + #ifndef CONFIG_KVM_BOOKE_HV if (!usermode) { /* Guest is in supervisor mode, @@ -242,17 +245,18 @@ static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe) return tlbe->mas7_3 & (MAS3_SW|MAS3_UW); } -static inline bool kvmppc_e500_ref_setup(struct tlbe_ref *ref, +static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, struct kvm_book3e_206_tlb_entry *gtlbe, - kvm_pfn_t pfn, unsigned int wimg) + kvm_pfn_t pfn, unsigned int wimg, + bool writable) { ref->pfn = pfn; ref->flags = E500_TLB_VALID; + if (writable) + ref->flags |= E500_TLB_WRITABLE; /* Use guest supplied MAS2_G and MAS2_E */ ref->flags |= (gtlbe->mas2 & MAS2_ATTRIB_MASK) | wimg; - - return tlbe_is_writable(gtlbe); } static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref) @@ -305,6 +309,7 @@ static void kvmppc_e500_setup_stlbe( { kvm_pfn_t pfn = ref->pfn; u32 pr = vcpu->arch.shared->msr & MSR_PR; + bool writable = !!(ref->flags & E500_TLB_WRITABLE); BUG_ON(!(ref->flags & E500_TLB_VALID)); @@ -312,7 +317,7 @@ static void kvmppc_e500_setup_stlbe( stlbe->mas1 = MAS1_TSIZE(tsize) | get_tlb_sts(gtlbe) | MAS1_VALID; stlbe->mas2 = (gvaddr & MAS2_EPN) | (ref->flags & E500_TLB_MAS2_ATTR); stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) | - e500_shadow_mas3_attrib(gtlbe->mas7_3, pr); + e500_shadow_mas3_attrib(gtlbe->mas7_3, writable, pr); } static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, @@ -321,15 +326,14 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, struct tlbe_ref *ref) { struct kvm_memory_slot *slot; - unsigned long pfn = 0; /* silence GCC warning */ + unsigned int psize; + unsigned long pfn; struct page *page = NULL; unsigned long hva; - int pfnmap = 0; int tsize = BOOK3E_PAGESZ_4K; int ret = 0; unsigned long mmu_seq; struct kvm *kvm = vcpu_e500->vcpu.kvm; - unsigned long tsize_pages = 0; pte_t *ptep; unsigned int wimg = 0; pgd_t *pgdir; @@ -351,110 +355,12 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, slot = gfn_to_memslot(vcpu_e500->vcpu.kvm, gfn); hva = gfn_to_hva_memslot(slot, gfn); - if (tlbsel == 1) { - struct vm_area_struct *vma; - mmap_read_lock(kvm->mm); - - vma = find_vma(kvm->mm, hva); - if (vma && hva >= vma->vm_start && - (vma->vm_flags & VM_PFNMAP)) { - /* - * This VMA is a physically contiguous region (e.g. - * /dev/mem) that bypasses normal Linux page - * management. Find the overlap between the - * vma and the memslot. - */ - - unsigned long start, end; - unsigned long slot_start, slot_end; - - pfnmap = 1; - - start = vma->vm_pgoff; - end = start + - vma_pages(vma); - - pfn = start + ((hva - vma->vm_start) >> PAGE_SHIFT); - - slot_start = pfn - (gfn - slot->base_gfn); - slot_end = slot_start + slot->npages; - - if (start < slot_start) - start = slot_start; - if (end > slot_end) - end = slot_end; - - tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >> - MAS1_TSIZE_SHIFT; - - /* - * e500 doesn't implement the lowest tsize bit, - * or 1K pages. - */ - tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1); - - /* - * Now find the largest tsize (up to what the guest - * requested) that will cover gfn, stay within the - * range, and for which gfn and pfn are mutually - * aligned. - */ - - for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) { - unsigned long gfn_start, gfn_end; - tsize_pages = 1UL << (tsize - 2); - - gfn_start = gfn & ~(tsize_pages - 1); - gfn_end = gfn_start + tsize_pages; - - if (gfn_start + pfn - gfn < start) - continue; - if (gfn_end + pfn - gfn > end) - continue; - if ((gfn & (tsize_pages - 1)) != - (pfn & (tsize_pages - 1))) - continue; - - gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); - pfn &= ~(tsize_pages - 1); - break; - } - } else if (vma && hva >= vma->vm_start && - is_vm_hugetlb_page(vma)) { - unsigned long psize = vma_kernel_pagesize(vma); - - tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >> - MAS1_TSIZE_SHIFT; - - /* - * Take the largest page size that satisfies both host - * and guest mapping - */ - tsize = min(__ilog2(psize) - 10, tsize); - - /* - * e500 doesn't implement the lowest tsize bit, - * or 1K pages. - */ - tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1); - } - - mmap_read_unlock(kvm->mm); - } - - if (likely(!pfnmap)) { - tsize_pages = 1UL << (tsize + 10 - PAGE_SHIFT); - pfn = __kvm_faultin_pfn(slot, gfn, FOLL_WRITE, NULL, &page); - if (is_error_noslot_pfn(pfn)) { - if (printk_ratelimit()) - pr_err("%s: real page not found for gfn %lx\n", - __func__, (long)gfn); - return -EINVAL; - } - - /* Align guest and physical address to page map boundaries */ - pfn &= ~(tsize_pages - 1); - gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); + pfn = __kvm_faultin_pfn(slot, gfn, FOLL_WRITE, &writable, &page); + if (is_error_noslot_pfn(pfn)) { + if (printk_ratelimit()) + pr_err("%s: real page not found for gfn %lx\n", + __func__, (long)gfn); + return -EINVAL; } spin_lock(&kvm->mmu_lock); @@ -472,14 +378,13 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, * can't run hence pfn won't change. */ local_irq_save(flags); - ptep = find_linux_pte(pgdir, hva, NULL, NULL); + ptep = find_linux_pte(pgdir, hva, NULL, &psize); if (ptep) { pte_t pte = READ_ONCE(*ptep); if (pte_present(pte)) { wimg = (pte_val(pte) >> PTE_WIMGE_SHIFT) & MAS2_WIMGE_MASK; - local_irq_restore(flags); } else { local_irq_restore(flags); pr_err_ratelimited("%s: pte not present: gfn %lx,pfn %lx\n", @@ -488,10 +393,72 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, goto out; } } - writable = kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg); + local_irq_restore(flags); + + if (psize && tlbsel == 1) { + unsigned long psize_pages, tsize_pages; + unsigned long start, end; + unsigned long slot_start, slot_end; + + psize_pages = 1UL << (psize - PAGE_SHIFT); + start = pfn & ~(psize_pages - 1); + end = start + psize_pages; + + slot_start = pfn - (gfn - slot->base_gfn); + slot_end = slot_start + slot->npages; + + if (start < slot_start) + start = slot_start; + if (end > slot_end) + end = slot_end; + + tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >> + MAS1_TSIZE_SHIFT; + + /* + * Any page size that doesn't satisfy the host mapping + * will fail the start and end tests. + */ + tsize = min(psize - PAGE_SHIFT + BOOK3E_PAGESZ_4K, tsize); + + /* + * e500 doesn't implement the lowest tsize bit, + * or 1K pages. + */ + tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1); + + /* + * Now find the largest tsize (up to what the guest + * requested) that will cover gfn, stay within the + * range, and for which gfn and pfn are mutually + * aligned. + */ + + for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) { + unsigned long gfn_start, gfn_end; + tsize_pages = 1UL << (tsize - 2); + + gfn_start = gfn & ~(tsize_pages - 1); + gfn_end = gfn_start + tsize_pages; + + if (gfn_start + pfn - gfn < start) + continue; + if (gfn_end + pfn - gfn > end) + continue; + if ((gfn & (tsize_pages - 1)) != + (pfn & (tsize_pages - 1))) + continue; + + gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); + pfn &= ~(tsize_pages - 1); + break; + } + } + kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg, writable); kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize, ref, gvaddr, stlbe); + writable = tlbe_is_writable(stlbe); /* Clear i-cache for new pages */ kvmppc_mmu_flush_icache(pfn); diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c index f381b177ea06..0b6365d85d11 100644 --- a/arch/powerpc/platforms/book3s/vas-api.c +++ b/arch/powerpc/platforms/book3s/vas-api.c @@ -464,7 +464,43 @@ static vm_fault_t vas_mmap_fault(struct vm_fault *vmf) return VM_FAULT_SIGBUS; } +/* + * During mmap() paste address, mapping VMA is saved in VAS window + * struct which is used to unmap during migration if the window is + * still open. But the user space can remove this mapping with + * munmap() before closing the window and the VMA address will + * be invalid. Set VAS window VMA to NULL in this function which + * is called before VMA free. + */ +static void vas_mmap_close(struct vm_area_struct *vma) +{ + struct file *fp = vma->vm_file; + struct coproc_instance *cp_inst = fp->private_data; + struct vas_window *txwin; + + /* Should not happen */ + if (!cp_inst || !cp_inst->txwin) { + pr_err("No attached VAS window for the paste address mmap\n"); + return; + } + + txwin = cp_inst->txwin; + /* + * task_ref.vma is set in coproc_mmap() during mmap paste + * address. So it has to be the same VMA that is getting freed. + */ + if (WARN_ON(txwin->task_ref.vma != vma)) { + pr_err("Invalid paste address mmaping\n"); + return; + } + + mutex_lock(&txwin->task_ref.mmap_mutex); + txwin->task_ref.vma = NULL; + mutex_unlock(&txwin->task_ref.mmap_mutex); +} + static const struct vm_operations_struct vas_vm_ops = { + .close = vas_mmap_close, .fault = vas_mmap_fault, }; diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 71aabc5c6713..125f5ecd9565 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -122,6 +122,7 @@ struct kernel_mapping { extern struct kernel_mapping kernel_map; extern phys_addr_t phys_ram_base; +extern unsigned long vmemmap_start_pfn; #define is_kernel_mapping(x) \ ((x) >= kernel_map.virt_addr && (x) < (kernel_map.virt_addr + kernel_map.size)) diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index d4e99eef90ac..050fdc49b5ad 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -87,7 +87,7 @@ * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled. */ -#define vmemmap ((struct page *)VMEMMAP_START - (phys_ram_base >> PAGE_SHIFT)) +#define vmemmap ((struct page *)VMEMMAP_START - vmemmap_start_pfn) #define PCI_IO_SIZE SZ_16M #define PCI_IO_END VMEMMAP_START diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h index 6c82318065cf..3d250824178b 100644 --- a/arch/riscv/include/asm/sbi.h +++ b/arch/riscv/include/asm/sbi.h @@ -159,6 +159,7 @@ struct riscv_pmu_snapshot_data { }; #define RISCV_PMU_RAW_EVENT_MASK GENMASK_ULL(47, 0) +#define RISCV_PMU_PLAT_FW_EVENT_MASK GENMASK_ULL(61, 0) #define RISCV_PMU_RAW_EVENT_IDX 0x20000 #define RISCV_PLAT_FW_EVENT 0xFFFF diff --git a/arch/riscv/include/asm/spinlock.h b/arch/riscv/include/asm/spinlock.h index e5121b89acea..52f11bfd0079 100644 --- a/arch/riscv/include/asm/spinlock.h +++ b/arch/riscv/include/asm/spinlock.h @@ -3,8 +3,11 @@ #ifndef __ASM_RISCV_SPINLOCK_H #define __ASM_RISCV_SPINLOCK_H -#ifdef CONFIG_RISCV_COMBO_SPINLOCKS +#ifdef CONFIG_QUEUED_SPINLOCKS #define _Q_PENDING_LOOPS (1 << 9) +#endif + +#ifdef CONFIG_RISCV_COMBO_SPINLOCKS #define __no_arch_spinlock_redefine #include <asm/ticket_spinlock.h> diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index c200d329d4bd..33a5a9f2a0d4 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -23,21 +23,21 @@ REG_S a0, TASK_TI_A0(tp) csrr a0, CSR_CAUSE /* Exclude IRQs */ - blt a0, zero, _new_vmalloc_restore_context_a0 + blt a0, zero, .Lnew_vmalloc_restore_context_a0 REG_S a1, TASK_TI_A1(tp) /* Only check new_vmalloc if we are in page/protection fault */ li a1, EXC_LOAD_PAGE_FAULT - beq a0, a1, _new_vmalloc_kernel_address + beq a0, a1, .Lnew_vmalloc_kernel_address li a1, EXC_STORE_PAGE_FAULT - beq a0, a1, _new_vmalloc_kernel_address + beq a0, a1, .Lnew_vmalloc_kernel_address li a1, EXC_INST_PAGE_FAULT - bne a0, a1, _new_vmalloc_restore_context_a1 + bne a0, a1, .Lnew_vmalloc_restore_context_a1 -_new_vmalloc_kernel_address: +.Lnew_vmalloc_kernel_address: /* Is it a kernel address? */ csrr a0, CSR_TVAL - bge a0, zero, _new_vmalloc_restore_context_a1 + bge a0, zero, .Lnew_vmalloc_restore_context_a1 /* Check if a new vmalloc mapping appeared that could explain the trap */ REG_S a2, TASK_TI_A2(tp) @@ -69,7 +69,7 @@ _new_vmalloc_kernel_address: /* Check the value of new_vmalloc for this cpu */ REG_L a2, 0(a0) and a2, a2, a1 - beq a2, zero, _new_vmalloc_restore_context + beq a2, zero, .Lnew_vmalloc_restore_context /* Atomically reset the current cpu bit in new_vmalloc */ amoxor.d a0, a1, (a0) @@ -83,11 +83,11 @@ _new_vmalloc_kernel_address: csrw CSR_SCRATCH, x0 sret -_new_vmalloc_restore_context: +.Lnew_vmalloc_restore_context: REG_L a2, TASK_TI_A2(tp) -_new_vmalloc_restore_context_a1: +.Lnew_vmalloc_restore_context_a1: REG_L a1, TASK_TI_A1(tp) -_new_vmalloc_restore_context_a0: +.Lnew_vmalloc_restore_context_a0: REG_L a0, TASK_TI_A0(tp) .endm @@ -278,6 +278,7 @@ SYM_CODE_START_NOALIGN(ret_from_exception) #else sret #endif +SYM_INNER_LABEL(ret_from_exception_end, SYM_L_GLOBAL) SYM_CODE_END(ret_from_exception) ASM_NOKPROBE(ret_from_exception) diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c index 1cd461f3d872..47d0ebeec93c 100644 --- a/arch/riscv/kernel/module.c +++ b/arch/riscv/kernel/module.c @@ -23,7 +23,7 @@ struct used_bucket { struct relocation_head { struct hlist_node node; - struct list_head *rel_entry; + struct list_head rel_entry; void *location; }; @@ -634,7 +634,7 @@ process_accumulated_relocations(struct module *me, location = rel_head_iter->location; list_for_each_entry_safe(rel_entry_iter, rel_entry_iter_tmp, - rel_head_iter->rel_entry, + &rel_head_iter->rel_entry, head) { curr_type = rel_entry_iter->type; reloc_handlers[curr_type].reloc_handler( @@ -704,16 +704,7 @@ static int add_relocation_to_accumulate(struct module *me, int type, return -ENOMEM; } - rel_head->rel_entry = - kmalloc(sizeof(struct list_head), GFP_KERNEL); - - if (!rel_head->rel_entry) { - kfree(entry); - kfree(rel_head); - return -ENOMEM; - } - - INIT_LIST_HEAD(rel_head->rel_entry); + INIT_LIST_HEAD(&rel_head->rel_entry); rel_head->location = location; INIT_HLIST_NODE(&rel_head->node); if (!current_head->first) { @@ -722,7 +713,6 @@ static int add_relocation_to_accumulate(struct module *me, int type, if (!bucket) { kfree(entry); - kfree(rel_head->rel_entry); kfree(rel_head); return -ENOMEM; } @@ -735,7 +725,7 @@ static int add_relocation_to_accumulate(struct module *me, int type, } /* Add relocation to head of discovered rel_head */ - list_add_tail(&entry->head, rel_head->rel_entry); + list_add_tail(&entry->head, &rel_head->rel_entry); return 0; } diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c index 380a0e8cecc0..c0738d6c6498 100644 --- a/arch/riscv/kernel/probes/kprobes.c +++ b/arch/riscv/kernel/probes/kprobes.c @@ -30,7 +30,7 @@ static void __kprobes arch_prepare_ss_slot(struct kprobe *p) p->ainsn.api.restore = (unsigned long)p->addr + len; patch_text_nosync(p->ainsn.api.insn, &p->opcode, len); - patch_text_nosync(p->ainsn.api.insn + len, &insn, GET_INSN_LENGTH(insn)); + patch_text_nosync((void *)p->ainsn.api.insn + len, &insn, GET_INSN_LENGTH(insn)); } static void __kprobes arch_prepare_simulate(struct kprobe *p) diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 153a2db4c5fa..d4355c770c36 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -17,6 +17,7 @@ #ifdef CONFIG_FRAME_POINTER extern asmlinkage void handle_exception(void); +extern unsigned long ret_from_exception_end; static inline int fp_is_valid(unsigned long fp, unsigned long sp) { @@ -71,7 +72,8 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, fp = frame->fp; pc = ftrace_graph_ret_addr(current, &graph_idx, frame->ra, &frame->ra); - if (pc == (unsigned long)handle_exception) { + if (pc >= (unsigned long)handle_exception && + pc < (unsigned long)&ret_from_exception_end) { if (unlikely(!__kernel_text_address(pc) || !fn(arg, pc))) break; diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 51ebfd23e007..8ff8e8b36524 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -35,7 +35,7 @@ int show_unhandled_signals = 1; -static DEFINE_SPINLOCK(die_lock); +static DEFINE_RAW_SPINLOCK(die_lock); static int copy_code(struct pt_regs *regs, u16 *val, const u16 *insns) { @@ -81,7 +81,7 @@ void die(struct pt_regs *regs, const char *str) oops_enter(); - spin_lock_irqsave(&die_lock, flags); + raw_spin_lock_irqsave(&die_lock, flags); console_verbose(); bust_spinlocks(1); @@ -100,7 +100,7 @@ void die(struct pt_regs *regs, const char *str) bust_spinlocks(0); add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); - spin_unlock_irqrestore(&die_lock, flags); + raw_spin_unlock_irqrestore(&die_lock, flags); oops_exit(); if (in_interrupt()) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index fc53ce748c80..8d167e09f1fe 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -33,6 +33,7 @@ #include <asm/pgtable.h> #include <asm/sections.h> #include <asm/soc.h> +#include <asm/sparsemem.h> #include <asm/tlbflush.h> #include "../kernel/head.h" @@ -62,6 +63,13 @@ EXPORT_SYMBOL(pgtable_l5_enabled); phys_addr_t phys_ram_base __ro_after_init; EXPORT_SYMBOL(phys_ram_base); +#ifdef CONFIG_SPARSEMEM_VMEMMAP +#define VMEMMAP_ADDR_ALIGN (1ULL << SECTION_SIZE_BITS) + +unsigned long vmemmap_start_pfn __ro_after_init; +EXPORT_SYMBOL(vmemmap_start_pfn); +#endif + unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; EXPORT_SYMBOL(empty_zero_page); @@ -240,8 +248,12 @@ static void __init setup_bootmem(void) * Make sure we align the start of the memory on a PMD boundary so that * at worst, we map the linear mapping with PMD mappings. */ - if (!IS_ENABLED(CONFIG_XIP_KERNEL)) + if (!IS_ENABLED(CONFIG_XIP_KERNEL)) { phys_ram_base = memblock_start_of_DRAM() & PMD_MASK; +#ifdef CONFIG_SPARSEMEM_VMEMMAP + vmemmap_start_pfn = round_down(phys_ram_base, VMEMMAP_ADDR_ALIGN) >> PAGE_SHIFT; +#endif + } /* * In 64-bit, any use of __va/__pa before this point is wrong as we @@ -1101,6 +1113,9 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom); phys_ram_base = CONFIG_PHYS_RAM_BASE; +#ifdef CONFIG_SPARSEMEM_VMEMMAP + vmemmap_start_pfn = round_down(phys_ram_base, VMEMMAP_ADDR_ALIGN) >> PAGE_SHIFT; +#endif kernel_map.phys_addr = (uintptr_t)CONFIG_PHYS_RAM_BASE; kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_start); diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index abe6e6c0ab98..6087d38c7235 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -234,6 +234,8 @@ static unsigned long get_vmem_size(unsigned long identity_size, vsize = round_up(SZ_2G + max_mappable, rte_size) + round_up(vmemmap_size, rte_size) + FIXMAP_SIZE + MODULES_LEN + KASLR_LEN; + if (IS_ENABLED(CONFIG_KMSAN)) + vsize += MODULES_LEN * 2; return size_add(vsize, vmalloc_size); } diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index 145035f84a0e..3fa28db2fe59 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -306,7 +306,7 @@ static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long e pages++; } } - if (mode == POPULATE_DIRECT) + if (mode == POPULATE_IDENTITY) update_page_count(PG_DIRECT_MAP_4K, pages); } @@ -339,7 +339,7 @@ static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long e } pgtable_pte_populate(pmd, addr, next, mode); } - if (mode == POPULATE_DIRECT) + if (mode == POPULATE_IDENTITY) update_page_count(PG_DIRECT_MAP_1M, pages); } @@ -372,7 +372,7 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e } pgtable_pmd_populate(pud, addr, next, mode); } - if (mode == POPULATE_DIRECT) + if (mode == POPULATE_IDENTITY) update_page_count(PG_DIRECT_MAP_2G, pages); } diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index edbb52ce3f1e..7d12a1305fc9 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -270,7 +270,7 @@ static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj, \ if (len >= sizeof(_value)) \ return -E2BIG; \ len = strscpy(_value, buf, sizeof(_value)); \ - if (len < 0) \ + if ((ssize_t)len < 0) \ return len; \ strim(_value); \ return len; \ diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index ea8dce299954..d4f031e086fc 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -2678,9 +2678,13 @@ static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) kvm_s390_clear_float_irqs(dev->kvm); break; case KVM_DEV_FLIC_APF_ENABLE: + if (kvm_is_ucontrol(dev->kvm)) + return -EINVAL; dev->kvm->arch.gmap->pfault_enabled = 1; break; case KVM_DEV_FLIC_APF_DISABLE_WAIT: + if (kvm_is_ucontrol(dev->kvm)) + return -EINVAL; dev->kvm->arch.gmap->pfault_enabled = 0; /* * Make sure no async faults are in transition when @@ -2894,6 +2898,8 @@ int kvm_set_routing_entry(struct kvm *kvm, switch (ue->type) { /* we store the userspace addresses instead of the guest addresses */ case KVM_IRQ_ROUTING_S390_ADAPTER: + if (kvm_is_ucontrol(kvm)) + return -EINVAL; e->set = set_adapter_int; uaddr = gmap_translate(kvm->arch.gmap, ue->u.adapter.summary_addr); if (uaddr == -EFAULT) diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 150b9387860a..a687695d8f68 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -854,7 +854,7 @@ unpin: static void unpin_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page, gpa_t gpa) { - hpa_t hpa = (hpa_t) vsie_page->scb_o; + hpa_t hpa = virt_to_phys(vsie_page->scb_o); if (hpa) unpin_guest_page(vcpu->kvm, gpa, hpa); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 2e1e26846050..99c590da0ae2 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -429,6 +429,16 @@ static struct event_constraint intel_lnc_event_constraints[] = { EVENT_CONSTRAINT_END }; +static struct extra_reg intel_lnc_extra_regs[] __read_mostly = { + INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0xfffffffffffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0xfffffffffffull, RSP_1), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), + INTEL_UEVENT_EXTRA_REG(0x02c6, MSR_PEBS_FRONTEND, 0x9, FE), + INTEL_UEVENT_EXTRA_REG(0x03c6, MSR_PEBS_FRONTEND, 0x7fff1f, FE), + INTEL_UEVENT_EXTRA_REG(0x40ad, MSR_PEBS_FRONTEND, 0xf, FE), + INTEL_UEVENT_EXTRA_REG(0x04c2, MSR_PEBS_FRONTEND, 0x8, FE), + EVENT_EXTRA_END +}; EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3"); EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3"); @@ -6422,7 +6432,7 @@ static __always_inline void intel_pmu_init_lnc(struct pmu *pmu) intel_pmu_init_glc(pmu); hybrid(pmu, event_constraints) = intel_lnc_event_constraints; hybrid(pmu, pebs_constraints) = intel_lnc_pebs_event_constraints; - hybrid(pmu, extra_regs) = intel_rwc_extra_regs; + hybrid(pmu, extra_regs) = intel_lnc_extra_regs; } static __always_inline void intel_pmu_init_skt(struct pmu *pmu) diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 1a4b326ca2ce..6ba6549f26fa 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -2517,6 +2517,7 @@ void __init intel_ds_init(void) x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME; break; + case 6: case 5: x86_pmu.pebs_ept = 1; fallthrough; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index d98fac567684..e7aba7349231 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1910,6 +1910,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_VFM(INTEL_ATOM_GRACEMONT, &adl_uncore_init), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, &gnr_uncore_init), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT, &gnr_uncore_init), + X86_MATCH_VFM(INTEL_ATOM_DARKMONT_X, &gnr_uncore_init), {}, }; MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match); diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 17b6590748c0..645aa360628d 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -452,6 +452,7 @@ #define X86_FEATURE_SME_COHERENT (19*32+10) /* AMD hardware-enforced cache coherency */ #define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" AMD SEV-ES full debug state swap support */ #define X86_FEATURE_SVSM (19*32+28) /* "svsm" SVSM present */ +#define X86_FEATURE_HV_INUSE_WR_ALLOWED (19*32+30) /* Allow Write to in-use hypervisor-owned pages */ /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */ #define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* No Nested Data Breakpoints */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index c0975815980c..20e6009381ed 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -230,6 +230,8 @@ static inline unsigned long long l1tf_pfn_limit(void) return BIT_ULL(boot_cpu_data.x86_cache_bits - 1 - PAGE_SHIFT); } +void init_cpu_devs(void); +void get_cpu_vendor(struct cpuinfo_x86 *c); extern void early_cpu_init(void); extern void identify_secondary_cpu(struct cpuinfo_x86 *); extern void print_cpu_info(struct cpuinfo_x86 *); diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index 125c407e2abe..41502bd2afd6 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -65,4 +65,19 @@ extern bool __static_call_fixup(void *tramp, u8 op, void *dest); +extern void __static_call_update_early(void *tramp, void *func); + +#define static_call_update_early(name, _func) \ +({ \ + typeof(&STATIC_CALL_TRAMP(name)) __F = (_func); \ + if (static_call_initialized) { \ + __static_call_update(&STATIC_CALL_KEY(name), \ + STATIC_CALL_TRAMP_ADDR(name), __F);\ + } else { \ + WRITE_ONCE(STATIC_CALL_KEY(name).func, _func); \ + __static_call_update_early(STATIC_CALL_TRAMP_ADDR(name),\ + __F); \ + } \ +}) + #endif /* _ASM_STATIC_CALL_H */ diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h index ab7382f92aff..96bda43538ee 100644 --- a/arch/x86/include/asm/sync_core.h +++ b/arch/x86/include/asm/sync_core.h @@ -8,7 +8,7 @@ #include <asm/special_insns.h> #ifdef CONFIG_X86_32 -static inline void iret_to_self(void) +static __always_inline void iret_to_self(void) { asm volatile ( "pushfl\n\t" @@ -19,7 +19,7 @@ static inline void iret_to_self(void) : ASM_CALL_CONSTRAINT : : "memory"); } #else -static inline void iret_to_self(void) +static __always_inline void iret_to_self(void) { unsigned int tmp; @@ -55,7 +55,7 @@ static inline void iret_to_self(void) * Like all of Linux's memory ordering operations, this is a * compiler barrier as well. */ -static inline void sync_core(void) +static __always_inline void sync_core(void) { /* * The SERIALIZE instruction is the most straightforward way to diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index a2dd24947eb8..97771b9d33af 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -39,9 +39,11 @@ #include <linux/string.h> #include <linux/types.h> #include <linux/pgtable.h> +#include <linux/instrumentation.h> #include <trace/events/xen.h> +#include <asm/alternative.h> #include <asm/page.h> #include <asm/smap.h> #include <asm/nospec-branch.h> @@ -86,11 +88,20 @@ struct xen_dm_op_buf; * there aren't more than 5 arguments...) */ -extern struct { char _entry[32]; } hypercall_page[]; +void xen_hypercall_func(void); +DECLARE_STATIC_CALL(xen_hypercall, xen_hypercall_func); -#define __HYPERCALL "call hypercall_page+%c[offset]" -#define __HYPERCALL_ENTRY(x) \ - [offset] "i" (__HYPERVISOR_##x * sizeof(hypercall_page[0])) +#ifdef MODULE +#define __ADDRESSABLE_xen_hypercall +#else +#define __ADDRESSABLE_xen_hypercall __ADDRESSABLE_ASM_STR(__SCK__xen_hypercall) +#endif + +#define __HYPERCALL \ + __ADDRESSABLE_xen_hypercall \ + "call __SCT__xen_hypercall" + +#define __HYPERCALL_ENTRY(x) "a" (x) #ifdef CONFIG_X86_32 #define __HYPERCALL_RETREG "eax" @@ -148,7 +159,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_0ARG(); \ asm volatile (__HYPERCALL \ : __HYPERCALL_0PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER0); \ (type)__res; \ }) @@ -159,7 +170,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_1ARG(a1); \ asm volatile (__HYPERCALL \ : __HYPERCALL_1PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER1); \ (type)__res; \ }) @@ -170,7 +181,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_2ARG(a1, a2); \ asm volatile (__HYPERCALL \ : __HYPERCALL_2PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER2); \ (type)__res; \ }) @@ -181,7 +192,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_3ARG(a1, a2, a3); \ asm volatile (__HYPERCALL \ : __HYPERCALL_3PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER3); \ (type)__res; \ }) @@ -192,7 +203,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_4ARG(a1, a2, a3, a4); \ asm volatile (__HYPERCALL \ : __HYPERCALL_4PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER4); \ (type)__res; \ }) @@ -206,12 +217,9 @@ xen_single_call(unsigned int call, __HYPERCALL_DECLS; __HYPERCALL_5ARG(a1, a2, a3, a4, a5); - if (call >= PAGE_SIZE / sizeof(hypercall_page[0])) - return -EINVAL; - - asm volatile(CALL_NOSPEC + asm volatile(__HYPERCALL : __HYPERCALL_5PARAM - : [thunk_target] "a" (&hypercall_page[call]) + : __HYPERCALL_ENTRY(call) : __HYPERCALL_CLOBBER5); return (long)__res; diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index 465647456753..f17d16607882 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -143,11 +143,6 @@ static bool skip_addr(void *dest) dest < (void*)relocate_kernel + KEXEC_CONTROL_CODE_MAX_SIZE) return true; #endif -#ifdef CONFIG_XEN - if (dest >= (void *)hypercall_page && - dest < (void*)hypercall_page + PAGE_SIZE) - return true; -#endif return false; } diff --git a/arch/x86/kernel/cet.c b/arch/x86/kernel/cet.c index d2c732a34e5d..303bf74d175b 100644 --- a/arch/x86/kernel/cet.c +++ b/arch/x86/kernel/cet.c @@ -81,6 +81,34 @@ static void do_user_cp_fault(struct pt_regs *regs, unsigned long error_code) static __ro_after_init bool ibt_fatal = true; +/* + * By definition, all missing-ENDBRANCH #CPs are a result of WFE && !ENDBR. + * + * For the kernel IBT no ENDBR selftest where #CPs are deliberately triggered, + * the WFE state of the interrupted context needs to be cleared to let execution + * continue. Otherwise when the CPU resumes from the instruction that just + * caused the previous #CP, another missing-ENDBRANCH #CP is raised and the CPU + * enters a dead loop. + * + * This is not a problem with IDT because it doesn't preserve WFE and IRET doesn't + * set WFE. But FRED provides space on the entry stack (in an expanded CS area) + * to save and restore the WFE state, thus the WFE state is no longer clobbered, + * so software must clear it. + */ +static void ibt_clear_fred_wfe(struct pt_regs *regs) +{ + /* + * No need to do any FRED checks. + * + * For IDT event delivery, the high-order 48 bits of CS are pushed + * as 0s into the stack, and later IRET ignores these bits. + * + * For FRED, a test to check if fred_cs.wfe is set would be dropped + * by compilers. + */ + regs->fred_cs.wfe = 0; +} + static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code) { if ((error_code & CP_EC) != CP_ENDBR) { @@ -90,6 +118,7 @@ static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code) if (unlikely(regs->ip == (unsigned long)&ibt_selftest_noendbr)) { regs->ax = 0; + ibt_clear_fred_wfe(regs); return; } @@ -97,6 +126,7 @@ static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code) if (!ibt_fatal) { printk(KERN_DEFAULT CUT_HERE); __warn(__FILE__, __LINE__, (void *)regs->ip, TAINT_WARN, regs, NULL); + ibt_clear_fred_wfe(regs); return; } BUG(); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index a5c28975c608..3e9037690814 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -867,7 +867,7 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c) tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]); } -static void get_cpu_vendor(struct cpuinfo_x86 *c) +void get_cpu_vendor(struct cpuinfo_x86 *c) { char *v = c->x86_vendor_id; int i; @@ -1649,15 +1649,11 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) detect_nopl(); } -void __init early_cpu_init(void) +void __init init_cpu_devs(void) { const struct cpu_dev *const *cdev; int count = 0; -#ifdef CONFIG_PROCESSOR_SELECT - pr_info("KERNEL supported cpus:\n"); -#endif - for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) { const struct cpu_dev *cpudev = *cdev; @@ -1665,20 +1661,30 @@ void __init early_cpu_init(void) break; cpu_devs[count] = cpudev; count++; + } +} +void __init early_cpu_init(void) +{ #ifdef CONFIG_PROCESSOR_SELECT - { - unsigned int j; - - for (j = 0; j < 2; j++) { - if (!cpudev->c_ident[j]) - continue; - pr_info(" %s %s\n", cpudev->c_vendor, - cpudev->c_ident[j]); - } - } + unsigned int i, j; + + pr_info("KERNEL supported cpus:\n"); #endif + + init_cpu_devs(); + +#ifdef CONFIG_PROCESSOR_SELECT + for (i = 0; i < X86_VENDOR_NUM && cpu_devs[i]; i++) { + for (j = 0; j < 2; j++) { + if (!cpu_devs[i]->c_ident[j]) + continue; + pr_info(" %s %s\n", cpu_devs[i]->c_vendor, + cpu_devs[i]->c_ident[j]); + } } +#endif + early_identify_cpu(&boot_cpu_data); } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index d18078834ded..dc12fe5ef3ca 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -223,6 +223,63 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs) hyperv_cleanup(); } #endif /* CONFIG_CRASH_DUMP */ + +static u64 hv_ref_counter_at_suspend; +static void (*old_save_sched_clock_state)(void); +static void (*old_restore_sched_clock_state)(void); + +/* + * Hyper-V clock counter resets during hibernation. Save and restore clock + * offset during suspend/resume, while also considering the time passed + * before suspend. This is to make sure that sched_clock using hv tsc page + * based clocksource, proceeds from where it left off during suspend and + * it shows correct time for the timestamps of kernel messages after resume. + */ +static void save_hv_clock_tsc_state(void) +{ + hv_ref_counter_at_suspend = hv_read_reference_counter(); +} + +static void restore_hv_clock_tsc_state(void) +{ + /* + * Adjust the offsets used by hv tsc clocksource to + * account for the time spent before hibernation. + * adjusted value = reference counter (time) at suspend + * - reference counter (time) now. + */ + hv_adj_sched_clock_offset(hv_ref_counter_at_suspend - hv_read_reference_counter()); +} + +/* + * Functions to override save_sched_clock_state and restore_sched_clock_state + * functions of x86_platform. The Hyper-V clock counter is reset during + * suspend-resume and the offset used to measure time needs to be + * corrected, post resume. + */ +static void hv_save_sched_clock_state(void) +{ + old_save_sched_clock_state(); + save_hv_clock_tsc_state(); +} + +static void hv_restore_sched_clock_state(void) +{ + restore_hv_clock_tsc_state(); + old_restore_sched_clock_state(); +} + +static void __init x86_setup_ops_for_tsc_pg_clock(void) +{ + if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) + return; + + old_save_sched_clock_state = x86_platform.save_sched_clock_state; + x86_platform.save_sched_clock_state = hv_save_sched_clock_state; + + old_restore_sched_clock_state = x86_platform.restore_sched_clock_state; + x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state; +} #endif /* CONFIG_HYPERV */ static uint32_t __init ms_hyperv_platform(void) @@ -579,6 +636,7 @@ static void __init ms_hyperv_init_platform(void) /* Register Hyper-V specific clocksource */ hv_init_clocksource(); + x86_setup_ops_for_tsc_pg_clock(); hv_vtl_init_platform(); #endif /* diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 6bc1eb2a21bd..887b0b8e21e3 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -190,7 +190,8 @@ int ssp_get(struct task_struct *target, const struct user_regset *regset, struct fpu *fpu = &target->thread.fpu; struct cet_user_state *cetregs; - if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK)) + if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) || + !ssp_active(target, regset)) return -ENODEV; sync_fpstate(fpu); diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 4eefaac64c6c..9e51242ed125 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -172,6 +172,14 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail) } EXPORT_SYMBOL_GPL(arch_static_call_transform); +noinstr void __static_call_update_early(void *tramp, void *func) +{ + BUG_ON(system_state != SYSTEM_BOOTING); + BUG_ON(static_call_initialized); + __text_gen_insn(tramp, JMP32_INSN_OPCODE, tramp, func, JMP32_INSN_SIZE); + sync_core(); +} + #ifdef CONFIG_MITIGATION_RETHUNK /* * This is called by apply_returns() to fix up static call trampolines, diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index fab3ac9a4574..6a17396c8174 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -519,14 +519,10 @@ INIT_PER_CPU(irq_stack_backing_store); * linker will never mark as relocatable. (Using just ABSOLUTE() is not * sufficient for that). */ -#ifdef CONFIG_XEN #ifdef CONFIG_XEN_PV xen_elfnote_entry_value = ABSOLUTE(xen_elfnote_entry) + ABSOLUTE(startup_xen); #endif -xen_elfnote_hypercall_page_value = - ABSOLUTE(xen_elfnote_hypercall_page) + ABSOLUTE(hypercall_page); -#endif #ifdef CONFIG_PVH xen_elfnote_phys32_entry_value = ABSOLUTE(xen_elfnote_phys32_entry) + ABSOLUTE(pvh_start_xen - LOAD_OFFSET); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 22e7ad235123..2401606db260 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3364,18 +3364,6 @@ static bool fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, return true; } -static bool is_access_allowed(struct kvm_page_fault *fault, u64 spte) -{ - if (fault->exec) - return is_executable_pte(spte); - - if (fault->write) - return is_writable_pte(spte); - - /* Fault was on Read access */ - return spte & PT_PRESENT_MASK; -} - /* * Returns the last level spte pointer of the shadow page walk for the given * gpa, and sets *spte to the spte value. This spte may be non-preset. If no diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index f332b33bc817..af10bc0380a3 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -462,6 +462,23 @@ static inline bool is_mmu_writable_spte(u64 spte) } /* + * Returns true if the access indicated by @fault is allowed by the existing + * SPTE protections. Note, the caller is responsible for checking that the + * SPTE is a shadow-present, leaf SPTE (either before or after). + */ +static inline bool is_access_allowed(struct kvm_page_fault *fault, u64 spte) +{ + if (fault->exec) + return is_executable_pte(spte); + + if (fault->write) + return is_writable_pte(spte); + + /* Fault was on Read access */ + return spte & PT_PRESENT_MASK; +} + +/* * If the MMU-writable flag is cleared, i.e. the SPTE is write-protected for * write-tracking, remote TLBs must be flushed, even if the SPTE was read-only, * as KVM allows stale Writable TLB entries to exist. When dirty logging, KVM diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 4508d868f1cd..2f15e0e33903 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -985,6 +985,11 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, if (fault->prefetch && is_shadow_present_pte(iter->old_spte)) return RET_PF_SPURIOUS; + if (is_shadow_present_pte(iter->old_spte) && + is_access_allowed(fault, iter->old_spte) && + is_last_spte(iter->old_spte, iter->level)) + return RET_PF_SPURIOUS; + if (unlikely(!fault->slot)) new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL); else diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 4b74ea91f4e6..65fd245a9953 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -1199,6 +1199,12 @@ bool avic_hardware_setup(void) return false; } + if (cc_platform_has(CC_ATTR_HOST_SEV_SNP) && + !boot_cpu_has(X86_FEATURE_HV_INUSE_WR_ALLOWED)) { + pr_warn("AVIC disabled: missing HvInUseWrAllowed on SNP-enabled system\n"); + return false; + } + if (boot_cpu_has(X86_FEATURE_AVIC)) { pr_info("AVIC enabled\n"); } else if (force_avic) { diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index dd15cc635655..21dacd312779 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3201,15 +3201,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) if (data & ~supported_de_cfg) return 1; - /* - * Don't let the guest change the host-programmed value. The - * MSR is very model specific, i.e. contains multiple bits that - * are completely unknown to KVM, and the one bit known to KVM - * is simply a reflection of hardware capabilities. - */ - if (!msr->host_initiated && data != svm->msr_decfg) - return 1; - svm->msr_decfg = data; break; } diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h index 1715d2ab07be..ad9116a99bcc 100644 --- a/arch/x86/kvm/vmx/posted_intr.h +++ b/arch/x86/kvm/vmx/posted_intr.h @@ -2,7 +2,7 @@ #ifndef __KVM_X86_VMX_POSTED_INTR_H #define __KVM_X86_VMX_POSTED_INTR_H -#include <linux/find.h> +#include <linux/bitmap.h> #include <asm/posted_intr.h> void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c8160baf3838..c79a8cc57ba4 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9976,7 +9976,7 @@ static int complete_hypercall_exit(struct kvm_vcpu *vcpu) { u64 ret = vcpu->run->hypercall.ret; - if (!is_64_bit_mode(vcpu)) + if (!is_64_bit_hypercall(vcpu)) ret = (u32)ret; kvm_rax_write(vcpu, ret); ++vcpu->stat.hypercalls; @@ -12724,6 +12724,13 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_hv_init_vm(kvm); kvm_xen_init_vm(kvm); + if (ignore_msrs && !report_ignored_msrs) { + pr_warn_once("Running KVM with ignore_msrs=1 and report_ignored_msrs=0 is not a\n" + "a supported configuration. Lying to the guest about the existence of MSRs\n" + "may cause the guest operating system to hang or produce errors. If a guest\n" + "does not run without ignore_msrs=1, please report it to kvm@vger.kernel.org.\n"); + } + return 0; out_uninit_mmu: diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index c6d29f283001..62aa4d66a032 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -1080,7 +1080,8 @@ struct execmem_info __init *execmem_arch_setup(void) start = MODULES_VADDR + offset; - if (IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX)) { + if (IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) && + cpu_feature_enabled(X86_FEATURE_PSE)) { pgprot = PAGE_KERNEL_ROX; flags = EXECMEM_KASAN_SHADOW | EXECMEM_ROX_CACHE; } else { diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 84e5adbd0925..43dcd8c7badc 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -2,6 +2,7 @@ #include <linux/console.h> #include <linux/cpu.h> +#include <linux/instrumentation.h> #include <linux/kexec.h> #include <linux/memblock.h> #include <linux/slab.h> @@ -21,7 +22,8 @@ #include "xen-ops.h" -EXPORT_SYMBOL_GPL(hypercall_page); +DEFINE_STATIC_CALL(xen_hypercall, xen_hypercall_hvm); +EXPORT_STATIC_CALL_TRAMP(xen_hypercall); /* * Pointer to the xen_vcpu_info structure or @@ -68,6 +70,67 @@ EXPORT_SYMBOL(xen_start_flags); */ struct shared_info *HYPERVISOR_shared_info = &xen_dummy_shared_info; +static __ref void xen_get_vendor(void) +{ + init_cpu_devs(); + cpu_detect(&boot_cpu_data); + get_cpu_vendor(&boot_cpu_data); +} + +void xen_hypercall_setfunc(void) +{ + if (static_call_query(xen_hypercall) != xen_hypercall_hvm) + return; + + if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) + static_call_update(xen_hypercall, xen_hypercall_amd); + else + static_call_update(xen_hypercall, xen_hypercall_intel); +} + +/* + * Evaluate processor vendor in order to select the correct hypercall + * function for HVM/PVH guests. + * Might be called very early in boot before vendor has been set by + * early_cpu_init(). + */ +noinstr void *__xen_hypercall_setfunc(void) +{ + void (*func)(void); + + /* + * Xen is supported only on CPUs with CPUID, so testing for + * X86_FEATURE_CPUID is a test for early_cpu_init() having been + * run. + * + * Note that __xen_hypercall_setfunc() is noinstr only due to a nasty + * dependency chain: it is being called via the xen_hypercall static + * call when running as a PVH or HVM guest. Hypercalls need to be + * noinstr due to PV guests using hypercalls in noinstr code. So we + * can safely tag the function body as "instrumentation ok", since + * the PV guest requirement is not of interest here (xen_get_vendor() + * calls noinstr functions, and static_call_update_early() might do + * so, too). + */ + instrumentation_begin(); + + if (!boot_cpu_has(X86_FEATURE_CPUID)) + xen_get_vendor(); + + if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) + func = xen_hypercall_amd; + else + func = xen_hypercall_intel; + + static_call_update_early(xen_hypercall, func); + + instrumentation_end(); + + return func; +} + static int xen_cpu_up_online(unsigned int cpu) { xen_init_lock_cpu(cpu); diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 24d2957a4726..fe57ff85d004 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -106,15 +106,8 @@ static void __init init_hvm_pv_info(void) /* PVH set up hypercall page in xen_prepare_pvh(). */ if (xen_pvh_domain()) pv_info.name = "Xen PVH"; - else { - u64 pfn; - uint32_t msr; - + else pv_info.name = "Xen HVM"; - msr = cpuid_ebx(base + 2); - pfn = __pa(hypercall_page); - wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); - } xen_setup_features(); @@ -300,6 +293,10 @@ static uint32_t __init xen_platform_hvm(void) if (xen_pv_domain()) return 0; + /* Set correct hypercall function. */ + if (xen_domain) + xen_hypercall_setfunc(); + if (xen_pvh_domain() && nopv) { /* Guest booting via the Xen-PVH boot entry goes here */ pr_info("\"nopv\" parameter is ignored in PVH guest\n"); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index d6818c6cafda..a8eb7e0c473c 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1341,6 +1341,9 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si) xen_domain_type = XEN_PV_DOMAIN; xen_start_flags = xen_start_info->flags; + /* Interrupts are guaranteed to be off initially. */ + early_boot_irqs_disabled = true; + static_call_update_early(xen_hypercall, xen_hypercall_pv); xen_setup_features(); @@ -1431,7 +1434,6 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si) WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_pv, xen_cpu_dead_pv)); local_irq_disable(); - early_boot_irqs_disabled = true; xen_raw_console_write("mapping kernel into physical memory\n"); xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base, diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index bf68c329fc01..0e3d930bcb89 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -129,17 +129,10 @@ static void __init pvh_arch_setup(void) void __init xen_pvh_init(struct boot_params *boot_params) { - u32 msr; - u64 pfn; - xen_pvh = 1; xen_domain_type = XEN_HVM_DOMAIN; xen_start_flags = pvh_start_info.flags; - msr = cpuid_ebx(xen_cpuid_base() + 2); - pfn = __pa(hypercall_page); - wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); - x86_init.oem.arch_setup = pvh_arch_setup; x86_init.oem.banner = xen_banner; diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 83189cf5cdce..b518f36d1ca2 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -20,10 +20,33 @@ #include <linux/init.h> #include <linux/linkage.h> +#include <linux/objtool.h> #include <../entry/calling.h> .pushsection .noinstr.text, "ax" /* + * PV hypercall interface to the hypervisor. + * + * Called via inline asm(), so better preserve %rcx and %r11. + * + * Input: + * %eax: hypercall number + * %rdi, %rsi, %rdx, %r10, %r8: args 1..5 for the hypercall + * Output: %rax + */ +SYM_FUNC_START(xen_hypercall_pv) + ANNOTATE_NOENDBR + push %rcx + push %r11 + UNWIND_HINT_SAVE + syscall + UNWIND_HINT_RESTORE + pop %r11 + pop %rcx + RET +SYM_FUNC_END(xen_hypercall_pv) + +/* * Disabling events is simply a matter of making the event mask * non-zero. */ @@ -176,7 +199,6 @@ SYM_CODE_START(xen_early_idt_handler_array) SYM_CODE_END(xen_early_idt_handler_array) __FINIT -hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 /* * Xen64 iret frame: * @@ -186,17 +208,28 @@ hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 * cs * rip <-- standard iret frame * - * flags + * flags <-- xen_iret must push from here on * - * rcx } - * r11 }<-- pushed by hypercall page - * rsp->rax } + * rcx + * r11 + * rsp->rax */ +.macro xen_hypercall_iret + pushq $0 /* Flags */ + push %rcx + push %r11 + push %rax + mov $__HYPERVISOR_iret, %eax + syscall /* Do the IRET. */ +#ifdef CONFIG_MITIGATION_SLS + int3 +#endif +.endm + SYM_CODE_START(xen_iret) UNWIND_HINT_UNDEFINED ANNOTATE_NOENDBR - pushq $0 - jmp hypercall_iret + xen_hypercall_iret SYM_CODE_END(xen_iret) /* @@ -301,8 +334,7 @@ SYM_CODE_START(xen_entry_SYSENTER_compat) ENDBR lea 16(%rsp), %rsp /* strip %rcx, %r11 */ mov $-ENOSYS, %rax - pushq $0 - jmp hypercall_iret + xen_hypercall_iret SYM_CODE_END(xen_entry_SYSENTER_compat) SYM_CODE_END(xen_entry_SYSCALL_compat) diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 7f6c69dbb816..9252652afe59 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -6,9 +6,11 @@ #include <linux/elfnote.h> #include <linux/init.h> +#include <linux/instrumentation.h> #include <asm/boot.h> #include <asm/asm.h> +#include <asm/frame.h> #include <asm/msr.h> #include <asm/page_types.h> #include <asm/percpu.h> @@ -20,28 +22,6 @@ #include <xen/interface/xen-mca.h> #include <asm/xen/interface.h> -.pushsection .noinstr.text, "ax" - .balign PAGE_SIZE -SYM_CODE_START(hypercall_page) - .rept (PAGE_SIZE / 32) - UNWIND_HINT_FUNC - ANNOTATE_NOENDBR - ANNOTATE_UNRET_SAFE - ret - /* - * Xen will write the hypercall page, and sort out ENDBR. - */ - .skip 31, 0xcc - .endr - -#define HYPERCALL(n) \ - .equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \ - .type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32 -#include <asm/xen-hypercalls.h> -#undef HYPERCALL -SYM_CODE_END(hypercall_page) -.popsection - #ifdef CONFIG_XEN_PV __INIT SYM_CODE_START(startup_xen) @@ -87,6 +67,87 @@ SYM_CODE_END(xen_cpu_bringup_again) #endif #endif + .pushsection .noinstr.text, "ax" +/* + * Xen hypercall interface to the hypervisor. + * + * Input: + * %eax: hypercall number + * 32-bit: + * %ebx, %ecx, %edx, %esi, %edi: args 1..5 for the hypercall + * 64-bit: + * %rdi, %rsi, %rdx, %r10, %r8: args 1..5 for the hypercall + * Output: %[er]ax + */ +SYM_FUNC_START(xen_hypercall_hvm) + ENDBR + FRAME_BEGIN + /* Save all relevant registers (caller save and arguments). */ +#ifdef CONFIG_X86_32 + push %eax + push %ebx + push %ecx + push %edx + push %esi + push %edi +#else + push %rax + push %rcx + push %rdx + push %rdi + push %rsi + push %r11 + push %r10 + push %r9 + push %r8 +#ifdef CONFIG_FRAME_POINTER + pushq $0 /* Dummy push for stack alignment. */ +#endif +#endif + /* Set the vendor specific function. */ + call __xen_hypercall_setfunc + /* Set ZF = 1 if AMD, Restore saved registers. */ +#ifdef CONFIG_X86_32 + lea xen_hypercall_amd, %ebx + cmp %eax, %ebx + pop %edi + pop %esi + pop %edx + pop %ecx + pop %ebx + pop %eax +#else + lea xen_hypercall_amd(%rip), %rbx + cmp %rax, %rbx +#ifdef CONFIG_FRAME_POINTER + pop %rax /* Dummy pop. */ +#endif + pop %r8 + pop %r9 + pop %r10 + pop %r11 + pop %rsi + pop %rdi + pop %rdx + pop %rcx + pop %rax +#endif + /* Use correct hypercall function. */ + jz xen_hypercall_amd + jmp xen_hypercall_intel +SYM_FUNC_END(xen_hypercall_hvm) + +SYM_FUNC_START(xen_hypercall_amd) + vmmcall + RET +SYM_FUNC_END(xen_hypercall_amd) + +SYM_FUNC_START(xen_hypercall_intel) + vmcall + RET +SYM_FUNC_END(xen_hypercall_intel) + .popsection + ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux") ELFNOTE(Xen, XEN_ELFNOTE_GUEST_VERSION, .asciz "2.6") ELFNOTE(Xen, XEN_ELFNOTE_XEN_VERSION, .asciz "xen-3.0") @@ -116,8 +177,6 @@ SYM_CODE_END(xen_cpu_bringup_again) #else # define FEATURES_DOM0 0 #endif - ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, .globl xen_elfnote_hypercall_page; - xen_elfnote_hypercall_page: _ASM_PTR xen_elfnote_hypercall_page_value - .) ELFNOTE(Xen, XEN_ELFNOTE_SUPPORTED_FEATURES, .long FEATURES_PV | FEATURES_PVH | FEATURES_DOM0) ELFNOTE(Xen, XEN_ELFNOTE_LOADER, .asciz "generic") diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index e1b782e823e6..63c13a2ccf55 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -326,4 +326,13 @@ static inline void xen_smp_intr_free_pv(unsigned int cpu) {} static inline void xen_smp_count_cpus(void) { } #endif /* CONFIG_SMP */ +#ifdef CONFIG_XEN_PV +void xen_hypercall_pv(void); +#endif +void xen_hypercall_hvm(void); +void xen_hypercall_amd(void); +void xen_hypercall_intel(void); +void xen_hypercall_setfunc(void); +void *__xen_hypercall_setfunc(void); + #endif /* XEN_OPS_H */ diff --git a/block/bdev.c b/block/bdev.c index 738e3c8457e7..9d73a8fbf7f9 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -155,8 +155,7 @@ int set_blocksize(struct file *file, int size) struct inode *inode = file->f_mapping->host; struct block_device *bdev = I_BDEV(inode); - /* Size must be a power of two, and between 512 and PAGE_SIZE */ - if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size)) + if (blk_validate_block_size(size)) return -EINVAL; /* Size cannot be smaller than the size supported by the device */ diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 95dd7b795935..cad16c163611 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -6844,16 +6844,24 @@ static struct bfq_queue *bfq_waker_bfqq(struct bfq_queue *bfqq) if (new_bfqq == waker_bfqq) { /* * If waker_bfqq is in the merge chain, and current - * is the only procress. + * is the only process, waker_bfqq can be freed. */ if (bfqq_process_refs(waker_bfqq) == 1) return NULL; - break; + + return waker_bfqq; } new_bfqq = new_bfqq->new_bfqq; } + /* + * If waker_bfqq is not in the merge chain, and it's procress reference + * is 0, waker_bfqq can be freed. + */ + if (bfqq_process_refs(waker_bfqq) == 0) + return NULL; + return waker_bfqq; } diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index cd5ea6eaa76b..156e9bb07abf 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -275,13 +275,15 @@ void blk_mq_sysfs_unregister_hctxs(struct request_queue *q) struct blk_mq_hw_ctx *hctx; unsigned long i; - lockdep_assert_held(&q->sysfs_dir_lock); - + mutex_lock(&q->sysfs_dir_lock); if (!q->mq_sysfs_init_done) - return; + goto unlock; queue_for_each_hw_ctx(q, hctx, i) blk_mq_unregister_hctx(hctx); + +unlock: + mutex_unlock(&q->sysfs_dir_lock); } int blk_mq_sysfs_register_hctxs(struct request_queue *q) @@ -290,10 +292,9 @@ int blk_mq_sysfs_register_hctxs(struct request_queue *q) unsigned long i; int ret = 0; - lockdep_assert_held(&q->sysfs_dir_lock); - + mutex_lock(&q->sysfs_dir_lock); if (!q->mq_sysfs_init_done) - return ret; + goto unlock; queue_for_each_hw_ctx(q, hctx, i) { ret = blk_mq_register_hctx(hctx); @@ -301,5 +302,8 @@ int blk_mq_sysfs_register_hctxs(struct request_queue *q) break; } +unlock: + mutex_unlock(&q->sysfs_dir_lock); + return ret; } diff --git a/block/blk-mq.c b/block/blk-mq.c index 6b6111513986..8ac19d4ae3c0 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -4412,6 +4412,15 @@ struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q, } EXPORT_SYMBOL(blk_mq_alloc_disk_for_queue); +/* + * Only hctx removed from cpuhp list can be reused + */ +static bool blk_mq_hctx_is_reusable(struct blk_mq_hw_ctx *hctx) +{ + return hlist_unhashed(&hctx->cpuhp_online) && + hlist_unhashed(&hctx->cpuhp_dead); +} + static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx( struct blk_mq_tag_set *set, struct request_queue *q, int hctx_idx, int node) @@ -4421,7 +4430,7 @@ static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx( /* reuse dead hctx first */ spin_lock(&q->unused_hctx_lock); list_for_each_entry(tmp, &q->unused_hctx_list, hctx_list) { - if (tmp->numa_node == node) { + if (tmp->numa_node == node && blk_mq_hctx_is_reusable(tmp)) { hctx = tmp; break; } @@ -4453,8 +4462,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, unsigned long i, j; /* protect against switching io scheduler */ - lockdep_assert_held(&q->sysfs_lock); - + mutex_lock(&q->sysfs_lock); for (i = 0; i < set->nr_hw_queues; i++) { int old_node; int node = blk_mq_get_hctx_node(set, i); @@ -4487,6 +4495,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, xa_for_each_start(&q->hctx_table, j, hctx, j) blk_mq_exit_hctx(q, set, hctx, j); + mutex_unlock(&q->sysfs_lock); /* unregister cpuhp callbacks for exited hctxs */ blk_mq_remove_hw_queues_cpuhp(q); @@ -4518,14 +4527,10 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, xa_init(&q->hctx_table); - mutex_lock(&q->sysfs_lock); - blk_mq_realloc_hw_ctxs(set, q); if (!q->nr_hw_queues) goto err_hctxs; - mutex_unlock(&q->sysfs_lock); - INIT_WORK(&q->timeout_work, blk_mq_timeout_work); blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ); @@ -4544,7 +4549,6 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, return 0; err_hctxs: - mutex_unlock(&q->sysfs_lock); blk_mq_release(q); err_exit: q->mq_ops = NULL; @@ -4925,12 +4929,12 @@ static bool blk_mq_elv_switch_none(struct list_head *head, return false; /* q->elevator needs protection from ->sysfs_lock */ - lockdep_assert_held(&q->sysfs_lock); + mutex_lock(&q->sysfs_lock); /* the check has to be done with holding sysfs_lock */ if (!q->elevator) { kfree(qe); - goto out; + goto unlock; } INIT_LIST_HEAD(&qe->node); @@ -4940,7 +4944,9 @@ static bool blk_mq_elv_switch_none(struct list_head *head, __elevator_get(qe->type); list_add(&qe->node, head); elevator_disable(q); -out: +unlock: + mutex_unlock(&q->sysfs_lock); + return true; } @@ -4969,9 +4975,11 @@ static void blk_mq_elv_switch_back(struct list_head *head, list_del(&qe->node); kfree(qe); + mutex_lock(&q->sysfs_lock); elevator_switch(q, t); /* drop the reference acquired in blk_mq_elv_switch_none */ elevator_put(t); + mutex_unlock(&q->sysfs_lock); } static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, @@ -4991,11 +4999,8 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, if (set->nr_maps == 1 && nr_hw_queues == set->nr_hw_queues) return; - list_for_each_entry(q, &set->tag_list, tag_set_list) { - mutex_lock(&q->sysfs_dir_lock); - mutex_lock(&q->sysfs_lock); + list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_freeze_queue(q); - } /* * Switch IO scheduler to 'none', cleaning up the data associated * with the previous scheduler. We will switch back once we are done @@ -5051,11 +5056,8 @@ switch_back: list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_elv_switch_back(&head, q); - list_for_each_entry(q, &set->tag_list, tag_set_list) { + list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_unfreeze_queue(q); - mutex_unlock(&q->sysfs_lock); - mutex_unlock(&q->sysfs_dir_lock); - } /* Free the excess tags when nr_hw_queues shrink. */ for (i = set->nr_hw_queues; i < prev_nr_hw_queues; i++) diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 64f70c713d2f..767598e719ab 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -706,11 +706,11 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr, if (entry->load_module) entry->load_module(disk, page, length); - mutex_lock(&q->sysfs_lock); blk_mq_freeze_queue(q); + mutex_lock(&q->sysfs_lock); res = entry->store(disk, page, length); - blk_mq_unfreeze_queue(q); mutex_unlock(&q->sysfs_lock); + blk_mq_unfreeze_queue(q); return res; } diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c index d8e97a760fbc..16178054e629 100644 --- a/drivers/accel/ivpu/ivpu_gem.c +++ b/drivers/accel/ivpu/ivpu_gem.c @@ -409,7 +409,7 @@ static void ivpu_bo_print_info(struct ivpu_bo *bo, struct drm_printer *p) mutex_lock(&bo->lock); drm_printf(p, "%-9p %-3u 0x%-12llx %-10lu 0x%-8x %-4u", - bo, bo->ctx->id, bo->vpu_addr, bo->base.base.size, + bo, bo->ctx ? bo->ctx->id : 0, bo->vpu_addr, bo->base.base.size, bo->flags, kref_read(&bo->base.base.refcount)); if (bo->base.pages) diff --git a/drivers/accel/ivpu/ivpu_mmu_context.c b/drivers/accel/ivpu/ivpu_mmu_context.c index 891967a95bc3..0af614dfb6f9 100644 --- a/drivers/accel/ivpu/ivpu_mmu_context.c +++ b/drivers/accel/ivpu/ivpu_mmu_context.c @@ -612,18 +612,22 @@ int ivpu_mmu_reserved_context_init(struct ivpu_device *vdev) if (!ivpu_mmu_ensure_pgd(vdev, &vdev->rctx.pgtable)) { ivpu_err(vdev, "Failed to allocate root page table for reserved context\n"); ret = -ENOMEM; - goto unlock; + goto err_ctx_fini; } ret = ivpu_mmu_cd_set(vdev, vdev->rctx.id, &vdev->rctx.pgtable); if (ret) { ivpu_err(vdev, "Failed to set context descriptor for reserved context\n"); - goto unlock; + goto err_ctx_fini; } -unlock: mutex_unlock(&vdev->rctx.lock); return ret; + +err_ctx_fini: + mutex_unlock(&vdev->rctx.lock); + ivpu_mmu_context_fini(vdev, &vdev->rctx); + return ret; } void ivpu_mmu_reserved_context_fini(struct ivpu_device *vdev) diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c index dbc0711e28d1..949f4233946c 100644 --- a/drivers/accel/ivpu/ivpu_pm.c +++ b/drivers/accel/ivpu/ivpu_pm.c @@ -378,6 +378,7 @@ void ivpu_pm_init(struct ivpu_device *vdev) pm_runtime_use_autosuspend(dev); pm_runtime_set_autosuspend_delay(dev, delay); + pm_runtime_set_active(dev); ivpu_dbg(vdev, PM, "Autosuspend delay = %d\n", delay); } @@ -392,7 +393,6 @@ void ivpu_pm_enable(struct ivpu_device *vdev) { struct device *dev = vdev->drm.dev; - pm_runtime_set_active(dev); pm_runtime_allow(dev); pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index d65cd08ba8e1..d81b55f5068c 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -135,10 +135,10 @@ config ACPI_REV_OVERRIDE_POSSIBLE config ACPI_EC bool "Embedded Controller" depends on HAS_IOPORT - default X86 + default X86 || LOONGARCH help This driver handles communication with the microcontroller - on many x86 laptops and other machines. + on many x86/LoongArch laptops and other machines. config ACPI_EC_DEBUGFS tristate "EC read/write access through /sys/kernel/debug/ec" diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 821867de43be..90aaec923889 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -441,6 +441,13 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = { }, }, { + /* Asus Vivobook X1504VAP */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BOARD_NAME, "X1504VAP"), + }, + }, + { /* Asus Vivobook X1704VAP */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), @@ -646,6 +653,17 @@ static const struct dmi_system_id irq1_edge_low_force_override[] = { DMI_MATCH(DMI_BOARD_NAME, "GMxHGxx"), }, }, + { + /* + * TongFang GM5HG0A in case of the SKIKK Vanaheim relabel the + * board-name is changed, so check OEM strings instead. Note + * OEM string matches are always exact matches. + * https://bugzilla.kernel.org/show_bug.cgi?id=219614 + */ + .matches = { + DMI_EXACT_MATCH(DMI_OEM_STRING, "GM5HG0A"), + }, + }, { } }; @@ -671,11 +689,11 @@ static bool acpi_dev_irq_override(u32 gsi, u8 triggering, u8 polarity, for (i = 0; i < ARRAY_SIZE(override_table); i++) { const struct irq_override_cmp *entry = &override_table[i]; - if (dmi_check_system(entry->system) && - entry->irq == gsi && + if (entry->irq == gsi && entry->triggering == triggering && entry->polarity == polarity && - entry->shareable == shareable) + entry->shareable == shareable && + dmi_check_system(entry->system)) return entry->override; } diff --git a/drivers/auxdisplay/Kconfig b/drivers/auxdisplay/Kconfig index 21545ffba065..8934e6ad5772 100644 --- a/drivers/auxdisplay/Kconfig +++ b/drivers/auxdisplay/Kconfig @@ -489,7 +489,7 @@ config IMG_ASCII_LCD config HT16K33 tristate "Holtek Ht16K33 LED controller with keyscan" - depends on FB && I2C && INPUT + depends on FB && I2C && INPUT && BACKLIGHT_CLASS_DEVICE select FB_SYSMEM_HELPERS select INPUT_MATRIXKMAP select FB_BACKLIGHT diff --git a/drivers/base/topology.c b/drivers/base/topology.c index cf160dd2c27b..b962da263eee 100644 --- a/drivers/base/topology.c +++ b/drivers/base/topology.c @@ -27,9 +27,17 @@ static ssize_t name##_read(struct file *file, struct kobject *kobj, \ loff_t off, size_t count) \ { \ struct device *dev = kobj_to_dev(kobj); \ + cpumask_var_t mask; \ + ssize_t n; \ \ - return cpumap_print_bitmask_to_buf(buf, topology_##mask(dev->id), \ - off, count); \ + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) \ + return -ENOMEM; \ + \ + cpumask_copy(mask, topology_##mask(dev->id)); \ + n = cpumap_print_bitmask_to_buf(buf, mask, off, count); \ + free_cpumask_var(mask); \ + \ + return n; \ } \ \ static ssize_t name##_list_read(struct file *file, struct kobject *kobj, \ @@ -37,9 +45,17 @@ static ssize_t name##_list_read(struct file *file, struct kobject *kobj, \ loff_t off, size_t count) \ { \ struct device *dev = kobj_to_dev(kobj); \ + cpumask_var_t mask; \ + ssize_t n; \ + \ + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) \ + return -ENOMEM; \ + \ + cpumask_copy(mask, topology_##mask(dev->id)); \ + n = cpumap_print_list_to_buf(buf, mask, off, count); \ + free_cpumask_var(mask); \ \ - return cpumap_print_list_to_buf(buf, topology_##mask(dev->id), \ - off, count); \ + return n; \ } define_id_show_func(physical_package_id, "%d"); diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index d4aed12dd436..934ab9332c80 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1618,6 +1618,21 @@ static void ublk_unquiesce_dev(struct ublk_device *ub) blk_mq_kick_requeue_list(ub->ub_disk->queue); } +static struct gendisk *ublk_detach_disk(struct ublk_device *ub) +{ + struct gendisk *disk; + + /* Sync with ublk_abort_queue() by holding the lock */ + spin_lock(&ub->lock); + disk = ub->ub_disk; + ub->dev_info.state = UBLK_S_DEV_DEAD; + ub->dev_info.ublksrv_pid = -1; + ub->ub_disk = NULL; + spin_unlock(&ub->lock); + + return disk; +} + static void ublk_stop_dev(struct ublk_device *ub) { struct gendisk *disk; @@ -1631,14 +1646,7 @@ static void ublk_stop_dev(struct ublk_device *ub) ublk_unquiesce_dev(ub); } del_gendisk(ub->ub_disk); - - /* Sync with ublk_abort_queue() by holding the lock */ - spin_lock(&ub->lock); - disk = ub->ub_disk; - ub->dev_info.state = UBLK_S_DEV_DEAD; - ub->dev_info.ublksrv_pid = -1; - ub->ub_disk = NULL; - spin_unlock(&ub->lock); + disk = ublk_detach_disk(ub); put_disk(disk); unlock: mutex_unlock(&ub->mutex); @@ -2336,7 +2344,7 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd) out_put_cdev: if (ret) { - ub->dev_info.state = UBLK_S_DEV_DEAD; + ublk_detach_disk(ub); ublk_put_device(ub); } if (ret) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 3dee026988dc..7903a4da40ac 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -614,6 +614,12 @@ static ssize_t backing_dev_store(struct device *dev, } nr_pages = i_size_read(inode) >> PAGE_SHIFT; + /* Refuse to use zero sized device (also prevents self reference) */ + if (!nr_pages) { + err = -EINVAL; + goto out; + } + bitmap_sz = BITS_TO_LONGS(nr_pages) * sizeof(long); bitmap = kvzalloc(bitmap_sz, GFP_KERNEL); if (!bitmap) { @@ -1438,12 +1444,16 @@ static void zram_meta_free(struct zram *zram, u64 disksize) size_t num_pages = disksize >> PAGE_SHIFT; size_t index; + if (!zram->table) + return; + /* Free all pages that are still in this zram device */ for (index = 0; index < num_pages; index++) zram_free_page(zram, index); zs_destroy_pool(zram->mem_pool); vfree(zram->table); + zram->table = NULL; } static bool zram_meta_alloc(struct zram *zram, u64 disksize) @@ -1458,6 +1468,7 @@ static bool zram_meta_alloc(struct zram *zram, u64 disksize) zram->mem_pool = zs_create_pool(zram->disk->disk_name); if (!zram->mem_pool) { vfree(zram->table); + zram->table = NULL; return false; } @@ -2320,11 +2331,6 @@ static void zram_reset_device(struct zram *zram) zram->limit_pages = 0; - if (!init_done(zram)) { - up_write(&zram->init_lock); - return; - } - set_capacity_and_notify(zram->disk, 0); part_stat_set_all(zram->disk->part0, 0); diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index 7fd9d5ddce02..224eafc27dbe 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -1472,10 +1472,15 @@ EXPORT_SYMBOL_GPL(btmtk_usb_setup); int btmtk_usb_shutdown(struct hci_dev *hdev) { + struct btmtk_data *data = hci_get_priv(hdev); struct btmtk_hci_wmt_params wmt_params; u8 param = 0; int err; + err = usb_autopm_get_interface(data->intf); + if (err < 0) + return err; + /* Disable the device */ wmt_params.op = BTMTK_WMT_FUNC_CTRL; wmt_params.flag = 0; @@ -1486,9 +1491,11 @@ int btmtk_usb_shutdown(struct hci_dev *hdev) err = btmtk_usb_hci_wmt_sync(hdev, &wmt_params); if (err < 0) { bt_dev_err(hdev, "Failed to send wmt func ctrl (%d)", err); + usb_autopm_put_interface(data->intf); return err; } + usb_autopm_put_interface(data->intf); return 0; } EXPORT_SYMBOL_GPL(btmtk_usb_shutdown); diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c index 569f5b7d6e46..1230045d78a5 100644 --- a/drivers/bluetooth/btnxpuart.c +++ b/drivers/bluetooth/btnxpuart.c @@ -1381,6 +1381,7 @@ static void btnxpuart_tx_work(struct work_struct *work) while ((skb = nxp_dequeue(nxpdev))) { len = serdev_device_write_buf(serdev, skb->data, skb->len); + serdev_device_wait_until_sent(serdev, 0); hdev->stat.byte_tx += len; skb_pull(skb, len); diff --git a/drivers/bus/mhi/host/pci_generic.c b/drivers/bus/mhi/host/pci_generic.c index 07645ce2119a..56ba4192c89c 100644 --- a/drivers/bus/mhi/host/pci_generic.c +++ b/drivers/bus/mhi/host/pci_generic.c @@ -917,7 +917,7 @@ static int mhi_pci_claim(struct mhi_controller *mhi_cntrl, return err; } - mhi_cntrl->regs = pcim_iomap_region(pdev, 1 << bar_num, pci_name(pdev)); + mhi_cntrl->regs = pcim_iomap_region(pdev, bar_num, pci_name(pdev)); if (IS_ERR(mhi_cntrl->regs)) { err = PTR_ERR(mhi_cntrl->regs); dev_err(&pdev->dev, "failed to map pci region: %d\n", err); diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 6a99a459b80b..51745ed1bbab 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -1106,7 +1106,7 @@ int open_for_data(struct cdrom_device_info *cdi) } } - cd_dbg(CD_OPEN, "all seems well, opening the devicen"); + cd_dbg(CD_OPEN, "all seems well, opening the device\n"); /* all seems well, we can open the device */ ret = cdo->open(cdi, 0); /* open for data */ diff --git a/drivers/clk/imx/clk-imx8mp-audiomix.c b/drivers/clk/imx/clk-imx8mp-audiomix.c index b2cb157703c5..c409fc7e0618 100644 --- a/drivers/clk/imx/clk-imx8mp-audiomix.c +++ b/drivers/clk/imx/clk-imx8mp-audiomix.c @@ -278,7 +278,8 @@ static int clk_imx8mp_audiomix_reset_controller_register(struct device *dev, #else /* !CONFIG_RESET_CONTROLLER */ -static int clk_imx8mp_audiomix_reset_controller_register(struct clk_imx8mp_audiomix_priv *priv) +static int clk_imx8mp_audiomix_reset_controller_register(struct device *dev, + struct clk_imx8mp_audiomix_priv *priv) { return 0; } diff --git a/drivers/clk/thead/clk-th1520-ap.c b/drivers/clk/thead/clk-th1520-ap.c index 17e32ae08720..1015fab95251 100644 --- a/drivers/clk/thead/clk-th1520-ap.c +++ b/drivers/clk/thead/clk-th1520-ap.c @@ -779,6 +779,13 @@ static struct ccu_div dpu1_clk = { }, }; +static CLK_FIXED_FACTOR_HW(emmc_sdio_ref_clk, "emmc-sdio-ref", + &video_pll_clk.common.hw, 4, 1, 0); + +static const struct clk_parent_data emmc_sdio_ref_clk_pd[] = { + { .hw = &emmc_sdio_ref_clk.hw }, +}; + static CCU_GATE(CLK_BROM, brom_clk, "brom", ahb2_cpusys_hclk_pd, 0x100, BIT(4), 0); static CCU_GATE(CLK_BMU, bmu_clk, "bmu", axi4_cpusys2_aclk_pd, 0x100, BIT(5), 0); static CCU_GATE(CLK_AON2CPU_A2X, aon2cpu_a2x_clk, "aon2cpu-a2x", axi4_cpusys2_aclk_pd, @@ -798,7 +805,7 @@ static CCU_GATE(CLK_PERISYS_APB4_HCLK, perisys_apb4_hclk, "perisys-apb4-hclk", p 0x150, BIT(12), 0); static CCU_GATE(CLK_NPU_AXI, npu_axi_clk, "npu-axi", axi_aclk_pd, 0x1c8, BIT(5), 0); static CCU_GATE(CLK_CPU2VP, cpu2vp_clk, "cpu2vp", axi_aclk_pd, 0x1e0, BIT(13), 0); -static CCU_GATE(CLK_EMMC_SDIO, emmc_sdio_clk, "emmc-sdio", video_pll_clk_pd, 0x204, BIT(30), 0); +static CCU_GATE(CLK_EMMC_SDIO, emmc_sdio_clk, "emmc-sdio", emmc_sdio_ref_clk_pd, 0x204, BIT(30), 0); static CCU_GATE(CLK_GMAC1, gmac1_clk, "gmac1", gmac_pll_clk_pd, 0x204, BIT(26), 0); static CCU_GATE(CLK_PADCTRL1, padctrl1_clk, "padctrl1", perisys_apb_pclk_pd, 0x204, BIT(24), 0); static CCU_GATE(CLK_DSMART, dsmart_clk, "dsmart", perisys_apb_pclk_pd, 0x204, BIT(23), 0); @@ -1059,6 +1066,10 @@ static int th1520_clk_probe(struct platform_device *pdev) return ret; priv->hws[CLK_PLL_GMAC_100M] = &gmac_pll_clk_100m.hw; + ret = devm_clk_hw_register(dev, &emmc_sdio_ref_clk.hw); + if (ret) + return ret; + ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get, priv); if (ret) return ret; diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index 99177835cade..b39dee7b93af 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -27,7 +27,8 @@ #include <asm/mshyperv.h> static struct clock_event_device __percpu *hv_clock_event; -static u64 hv_sched_clock_offset __ro_after_init; +/* Note: offset can hold negative values after hibernation. */ +static u64 hv_sched_clock_offset __read_mostly; /* * If false, we're using the old mechanism for stimer0 interrupts @@ -470,6 +471,17 @@ static void resume_hv_clock_tsc(struct clocksource *arg) hv_set_msr(HV_MSR_REFERENCE_TSC, tsc_msr.as_uint64); } +/* + * Called during resume from hibernation, from overridden + * x86_platform.restore_sched_clock_state routine. This is to adjust offsets + * used to calculate time for hv tsc page based sched_clock, to account for + * time spent before hibernation. + */ +void hv_adj_sched_clock_offset(u64 offset) +{ + hv_sched_clock_offset -= offset; +} + #ifdef HAVE_VDSO_CLOCKMODE_HVCLOCK static int hv_cs_enable(struct clocksource *cs) { diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index d7630bab2516..66e5dfc711c0 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -374,15 +374,19 @@ static inline int amd_pstate_cppc_enable(bool enable) static int msr_init_perf(struct amd_cpudata *cpudata) { - u64 cap1; + u64 cap1, numerator; int ret = rdmsrl_safe_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1, &cap1); if (ret) return ret; - WRITE_ONCE(cpudata->highest_perf, AMD_CPPC_HIGHEST_PERF(cap1)); - WRITE_ONCE(cpudata->max_limit_perf, AMD_CPPC_HIGHEST_PERF(cap1)); + ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator); + if (ret) + return ret; + + WRITE_ONCE(cpudata->highest_perf, numerator); + WRITE_ONCE(cpudata->max_limit_perf, numerator); WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1)); WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1)); WRITE_ONCE(cpudata->lowest_perf, AMD_CPPC_LOWEST_PERF(cap1)); @@ -394,13 +398,18 @@ static int msr_init_perf(struct amd_cpudata *cpudata) static int shmem_init_perf(struct amd_cpudata *cpudata) { struct cppc_perf_caps cppc_perf; + u64 numerator; int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); if (ret) return ret; - WRITE_ONCE(cpudata->highest_perf, cppc_perf.highest_perf); - WRITE_ONCE(cpudata->max_limit_perf, cppc_perf.highest_perf); + ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator); + if (ret) + return ret; + + WRITE_ONCE(cpudata->highest_perf, numerator); + WRITE_ONCE(cpudata->max_limit_perf, numerator); WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf); WRITE_ONCE(cpudata->lowest_nonlinear_perf, cppc_perf.lowest_nonlinear_perf); @@ -561,16 +570,13 @@ static int amd_pstate_verify(struct cpufreq_policy_data *policy_data) static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy) { - u32 max_limit_perf, min_limit_perf, lowest_perf, max_perf; + u32 max_limit_perf, min_limit_perf, lowest_perf, max_perf, max_freq; struct amd_cpudata *cpudata = policy->driver_data; - if (cpudata->boost_supported && !policy->boost_enabled) - max_perf = READ_ONCE(cpudata->nominal_perf); - else - max_perf = READ_ONCE(cpudata->highest_perf); - - max_limit_perf = div_u64(policy->max * max_perf, policy->cpuinfo.max_freq); - min_limit_perf = div_u64(policy->min * max_perf, policy->cpuinfo.max_freq); + max_perf = READ_ONCE(cpudata->highest_perf); + max_freq = READ_ONCE(cpudata->max_freq); + max_limit_perf = div_u64(policy->max * max_perf, max_freq); + min_limit_perf = div_u64(policy->min * max_perf, max_freq); lowest_perf = READ_ONCE(cpudata->lowest_perf); if (min_limit_perf < lowest_perf) @@ -889,7 +895,6 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata) { int ret; u32 min_freq, max_freq; - u64 numerator; u32 nominal_perf, nominal_freq; u32 lowest_nonlinear_perf, lowest_nonlinear_freq; u32 boost_ratio, lowest_nonlinear_ratio; @@ -911,10 +916,7 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata) nominal_perf = READ_ONCE(cpudata->nominal_perf); - ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator); - if (ret) - return ret; - boost_ratio = div_u64(numerator << SCHED_CAPACITY_SHIFT, nominal_perf); + boost_ratio = div_u64(cpudata->highest_perf << SCHED_CAPACITY_SHIFT, nominal_perf); max_freq = (nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT) * 1000; lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf); @@ -1869,18 +1871,18 @@ static int __init amd_pstate_init(void) static_call_update(amd_pstate_update_perf, shmem_update_perf); } - ret = amd_pstate_register_driver(cppc_state); - if (ret) { - pr_err("failed to register with return %d\n", ret); - return ret; - } - if (amd_pstate_prefcore) { ret = amd_detect_prefcore(&amd_pstate_prefcore); if (ret) return ret; } + ret = amd_pstate_register_driver(cppc_state); + if (ret) { + pr_err("failed to register with return %d\n", ret); + return ret; + } + dev_root = bus_get_dev_root(&cpu_subsys); if (dev_root) { ret = sysfs_create_group(&dev_root->kobj, &amd_pstate_global_attr_group); diff --git a/drivers/cpuidle/cpuidle-riscv-sbi.c b/drivers/cpuidle/cpuidle-riscv-sbi.c index 14462c092039..0c92a628bbd4 100644 --- a/drivers/cpuidle/cpuidle-riscv-sbi.c +++ b/drivers/cpuidle/cpuidle-riscv-sbi.c @@ -504,12 +504,12 @@ static int sbi_cpuidle_probe(struct platform_device *pdev) int cpu, ret; struct cpuidle_driver *drv; struct cpuidle_device *dev; - struct device_node *np, *pds_node; + struct device_node *pds_node; /* Detect OSI support based on CPU DT nodes */ sbi_cpuidle_use_osi = true; for_each_possible_cpu(cpu) { - np = of_cpu_device_node_get(cpu); + struct device_node *np __free(device_node) = of_cpu_device_node_get(cpu); if (np && of_property_present(np, "power-domains") && of_property_present(np, "power-domain-names")) { diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index d77899650798..b98b1ccffd1c 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -1295,6 +1295,7 @@ static int cxl_port_setup_targets(struct cxl_port *port, struct cxl_region_params *p = &cxlr->params; struct cxl_decoder *cxld = cxl_rr->decoder; struct cxl_switch_decoder *cxlsd; + struct cxl_port *iter = port; u16 eig, peig; u8 eiw, peiw; @@ -1311,16 +1312,26 @@ static int cxl_port_setup_targets(struct cxl_port *port, cxlsd = to_cxl_switch_decoder(&cxld->dev); if (cxl_rr->nr_targets_set) { - int i, distance; + int i, distance = 1; + struct cxl_region_ref *cxl_rr_iter; /* - * Passthrough decoders impose no distance requirements between - * peers + * The "distance" between peer downstream ports represents which + * endpoint positions in the region interleave a given port can + * host. + * + * For example, at the root of a hierarchy the distance is + * always 1 as every index targets a different host-bridge. At + * each subsequent switch level those ports map every Nth region + * position where N is the width of the switch == distance. */ - if (cxl_rr->nr_targets == 1) - distance = 0; - else - distance = p->nr_targets / cxl_rr->nr_targets; + do { + cxl_rr_iter = cxl_rr_load(iter, cxlr); + distance *= cxl_rr_iter->nr_targets; + iter = to_cxl_port(iter->dev.parent); + } while (!is_cxl_root(iter)); + distance *= cxlrd->cxlsd.cxld.interleave_ways; + for (i = 0; i < cxl_rr->nr_targets_set; i++) if (ep->dport == cxlsd->target[i]) { rc = check_last_peer(cxled, ep, cxl_rr, diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 0241d1d7133a..6d94ff4a4f1a 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -836,6 +836,9 @@ static ssize_t rcd_pcie_cap_emit(struct device *dev, u16 offset, char *buf, size if (!root_dev) return -ENXIO; + if (!dport->regs.rcd_pcie_cap) + return -ENXIO; + guard(device)(root_dev); if (!root_dev->driver) return -ENXIO; @@ -1032,8 +1035,7 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (rc) return rc; - rc = cxl_pci_ras_unmask(pdev); - if (rc) + if (cxl_pci_ras_unmask(pdev)) dev_dbg(&pdev->dev, "No RAS reporting unmasked\n"); pci_save_state(pdev); diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 7eeee3a38202..5baa83b85515 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -60,7 +60,7 @@ static void __dma_buf_debugfs_list_add(struct dma_buf *dmabuf) { } -static void __dma_buf_debugfs_list_del(struct file *file) +static void __dma_buf_debugfs_list_del(struct dma_buf *dmabuf) { } #endif diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c index 8ce1f074c2d3..cc7398cc17d6 100644 --- a/drivers/dma-buf/udmabuf.c +++ b/drivers/dma-buf/udmabuf.c @@ -297,7 +297,7 @@ static const struct dma_buf_ops udmabuf_ops = { }; #define SEALS_WANTED (F_SEAL_SHRINK) -#define SEALS_DENIED (F_SEAL_WRITE) +#define SEALS_DENIED (F_SEAL_WRITE|F_SEAL_FUTURE_WRITE) static int check_memfd_seals(struct file *memfd) { @@ -317,12 +317,10 @@ static int check_memfd_seals(struct file *memfd) return 0; } -static int export_udmabuf(struct udmabuf *ubuf, - struct miscdevice *device, - u32 flags) +static struct dma_buf *export_udmabuf(struct udmabuf *ubuf, + struct miscdevice *device) { DEFINE_DMA_BUF_EXPORT_INFO(exp_info); - struct dma_buf *buf; ubuf->device = device; exp_info.ops = &udmabuf_ops; @@ -330,11 +328,7 @@ static int export_udmabuf(struct udmabuf *ubuf, exp_info.priv = ubuf; exp_info.flags = O_RDWR; - buf = dma_buf_export(&exp_info); - if (IS_ERR(buf)) - return PTR_ERR(buf); - - return dma_buf_fd(buf, flags); + return dma_buf_export(&exp_info); } static long udmabuf_pin_folios(struct udmabuf *ubuf, struct file *memfd, @@ -391,6 +385,7 @@ static long udmabuf_create(struct miscdevice *device, struct folio **folios = NULL; pgoff_t pgcnt = 0, pglimit; struct udmabuf *ubuf; + struct dma_buf *dmabuf; long ret = -EINVAL; u32 i, flags; @@ -436,23 +431,39 @@ static long udmabuf_create(struct miscdevice *device, goto err; } + /* + * Take the inode lock to protect against concurrent + * memfd_add_seals(), which takes this lock in write mode. + */ + inode_lock_shared(file_inode(memfd)); ret = check_memfd_seals(memfd); - if (ret < 0) { - fput(memfd); - goto err; - } + if (ret) + goto out_unlock; ret = udmabuf_pin_folios(ubuf, memfd, list[i].offset, list[i].size, folios); +out_unlock: + inode_unlock_shared(file_inode(memfd)); fput(memfd); if (ret) goto err; } flags = head->flags & UDMABUF_FLAGS_CLOEXEC ? O_CLOEXEC : 0; - ret = export_udmabuf(ubuf, device, flags); - if (ret < 0) + dmabuf = export_udmabuf(ubuf, device); + if (IS_ERR(dmabuf)) { + ret = PTR_ERR(dmabuf); goto err; + } + /* + * Ownership of ubuf is held by the dmabuf from here. + * If the following dma_buf_fd() fails, dma_buf_put() cleans up both the + * dmabuf and the ubuf (through udmabuf_ops.release). + */ + + ret = dma_buf_fd(dmabuf, flags); + if (ret < 0) + dma_buf_put(dmabuf); kvfree(folios); return ret; diff --git a/drivers/dma/amd/qdma/qdma.c b/drivers/dma/amd/qdma/qdma.c index 6d9079458fe9..66f00ad67351 100644 --- a/drivers/dma/amd/qdma/qdma.c +++ b/drivers/dma/amd/qdma/qdma.c @@ -7,9 +7,9 @@ #include <linux/bitfield.h> #include <linux/bitops.h> #include <linux/dmaengine.h> +#include <linux/dma-mapping.h> #include <linux/module.h> #include <linux/mod_devicetable.h> -#include <linux/dma-map-ops.h> #include <linux/platform_device.h> #include <linux/platform_data/amd_qdma.h> #include <linux/regmap.h> @@ -492,18 +492,9 @@ static int qdma_device_verify(struct qdma_device *qdev) static int qdma_device_setup(struct qdma_device *qdev) { - struct device *dev = &qdev->pdev->dev; u32 ring_sz = QDMA_DEFAULT_RING_SIZE; int ret = 0; - while (dev && get_dma_ops(dev)) - dev = dev->parent; - if (!dev) { - qdma_err(qdev, "dma device not found"); - return -EINVAL; - } - set_dma_ops(&qdev->pdev->dev, get_dma_ops(dev)); - ret = qdma_setup_fmap_context(qdev); if (ret) { qdma_err(qdev, "Failed setup fmap context"); @@ -548,11 +539,12 @@ static void qdma_free_queue_resources(struct dma_chan *chan) { struct qdma_queue *queue = to_qdma_queue(chan); struct qdma_device *qdev = queue->qdev; - struct device *dev = qdev->dma_dev.dev; + struct qdma_platdata *pdata; qdma_clear_queue_context(queue); vchan_free_chan_resources(&queue->vchan); - dma_free_coherent(dev, queue->ring_size * QDMA_MM_DESC_SIZE, + pdata = dev_get_platdata(&qdev->pdev->dev); + dma_free_coherent(pdata->dma_dev, queue->ring_size * QDMA_MM_DESC_SIZE, queue->desc_base, queue->dma_desc_base); } @@ -565,6 +557,7 @@ static int qdma_alloc_queue_resources(struct dma_chan *chan) struct qdma_queue *queue = to_qdma_queue(chan); struct qdma_device *qdev = queue->qdev; struct qdma_ctxt_sw_desc desc; + struct qdma_platdata *pdata; size_t size; int ret; @@ -572,8 +565,9 @@ static int qdma_alloc_queue_resources(struct dma_chan *chan) if (ret) return ret; + pdata = dev_get_platdata(&qdev->pdev->dev); size = queue->ring_size * QDMA_MM_DESC_SIZE; - queue->desc_base = dma_alloc_coherent(qdev->dma_dev.dev, size, + queue->desc_base = dma_alloc_coherent(pdata->dma_dev, size, &queue->dma_desc_base, GFP_KERNEL); if (!queue->desc_base) { @@ -588,7 +582,7 @@ static int qdma_alloc_queue_resources(struct dma_chan *chan) if (ret) { qdma_err(qdev, "Failed to setup SW desc ctxt for %s", chan->name); - dma_free_coherent(qdev->dma_dev.dev, size, queue->desc_base, + dma_free_coherent(pdata->dma_dev, size, queue->desc_base, queue->dma_desc_base); return ret; } @@ -948,8 +942,9 @@ static int qdma_init_error_irq(struct qdma_device *qdev) static int qdmam_alloc_qintr_rings(struct qdma_device *qdev) { - u32 ctxt[QDMA_CTXT_REGMAP_LEN]; + struct qdma_platdata *pdata = dev_get_platdata(&qdev->pdev->dev); struct device *dev = &qdev->pdev->dev; + u32 ctxt[QDMA_CTXT_REGMAP_LEN]; struct qdma_intr_ring *ring; struct qdma_ctxt_intr intr_ctxt; u32 vector; @@ -969,7 +964,8 @@ static int qdmam_alloc_qintr_rings(struct qdma_device *qdev) ring->msix_id = qdev->err_irq_idx + i + 1; ring->ridx = i; ring->color = 1; - ring->base = dmam_alloc_coherent(dev, QDMA_INTR_RING_SIZE, + ring->base = dmam_alloc_coherent(pdata->dma_dev, + QDMA_INTR_RING_SIZE, &ring->dev_base, GFP_KERNEL); if (!ring->base) { qdma_err(qdev, "Failed to alloc intr ring %d", i); diff --git a/drivers/dma/apple-admac.c b/drivers/dma/apple-admac.c index c499173d80b2..bd49f0374291 100644 --- a/drivers/dma/apple-admac.c +++ b/drivers/dma/apple-admac.c @@ -153,6 +153,8 @@ static int admac_alloc_sram_carveout(struct admac_data *ad, { struct admac_sram *sram; int i, ret = 0, nblocks; + ad->txcache.size = readl_relaxed(ad->base + REG_TX_SRAM_SIZE); + ad->rxcache.size = readl_relaxed(ad->base + REG_RX_SRAM_SIZE); if (dir == DMA_MEM_TO_DEV) sram = &ad->txcache; @@ -912,12 +914,7 @@ static int admac_probe(struct platform_device *pdev) goto free_irq; } - ad->txcache.size = readl_relaxed(ad->base + REG_TX_SRAM_SIZE); - ad->rxcache.size = readl_relaxed(ad->base + REG_RX_SRAM_SIZE); - dev_info(&pdev->dev, "Audio DMA Controller\n"); - dev_info(&pdev->dev, "imprint %x TX cache %u RX cache %u\n", - readl_relaxed(ad->base + REG_IMPRINT), ad->txcache.size, ad->rxcache.size); return 0; diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 9c7b40220004..ba25c23164e7 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -1363,6 +1363,8 @@ at_xdmac_prep_dma_memset(struct dma_chan *chan, dma_addr_t dest, int value, return NULL; desc = at_xdmac_memset_create_desc(chan, atchan, dest, len, value); + if (!desc) + return NULL; list_add_tail(&desc->desc_node, &desc->descs_list); desc->tx_dma_desc.cookie = -EBUSY; diff --git a/drivers/dma/dw/acpi.c b/drivers/dma/dw/acpi.c index c510c109d2c3..b6452fffa657 100644 --- a/drivers/dma/dw/acpi.c +++ b/drivers/dma/dw/acpi.c @@ -8,13 +8,15 @@ static bool dw_dma_acpi_filter(struct dma_chan *chan, void *param) { + struct dw_dma *dw = to_dw_dma(chan->device); + struct dw_dma_chip_pdata *data = dev_get_drvdata(dw->dma.dev); struct acpi_dma_spec *dma_spec = param; struct dw_dma_slave slave = { .dma_dev = dma_spec->dev, .src_id = dma_spec->slave_id, .dst_id = dma_spec->slave_id, - .m_master = 0, - .p_master = 1, + .m_master = data->m_master, + .p_master = data->p_master, }; return dw_dma_filter(chan, &slave); diff --git a/drivers/dma/dw/internal.h b/drivers/dma/dw/internal.h index 563ce73488db..f1bd06a20cd6 100644 --- a/drivers/dma/dw/internal.h +++ b/drivers/dma/dw/internal.h @@ -51,11 +51,15 @@ struct dw_dma_chip_pdata { int (*probe)(struct dw_dma_chip *chip); int (*remove)(struct dw_dma_chip *chip); struct dw_dma_chip *chip; + u8 m_master; + u8 p_master; }; static __maybe_unused const struct dw_dma_chip_pdata dw_dma_chip_pdata = { .probe = dw_dma_probe, .remove = dw_dma_remove, + .m_master = 0, + .p_master = 1, }; static const struct dw_dma_platform_data idma32_pdata = { @@ -72,6 +76,8 @@ static __maybe_unused const struct dw_dma_chip_pdata idma32_chip_pdata = { .pdata = &idma32_pdata, .probe = idma32_dma_probe, .remove = idma32_dma_remove, + .m_master = 0, + .p_master = 0, }; static const struct dw_dma_platform_data xbar_pdata = { @@ -88,6 +94,8 @@ static __maybe_unused const struct dw_dma_chip_pdata xbar_chip_pdata = { .pdata = &xbar_pdata, .probe = idma32_dma_probe, .remove = idma32_dma_remove, + .m_master = 0, + .p_master = 0, }; #endif /* _DMA_DW_INTERNAL_H */ diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c index ad2d4d012cf7..e8a0eb81726a 100644 --- a/drivers/dma/dw/pci.c +++ b/drivers/dma/dw/pci.c @@ -56,10 +56,10 @@ static int dw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *pid) if (ret) return ret; - dw_dma_acpi_controller_register(chip->dw); - pci_set_drvdata(pdev, data); + dw_dma_acpi_controller_register(chip->dw); + return 0; } diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h index ce37e1ee9c46..fe8f103d4a63 100644 --- a/drivers/dma/fsl-edma-common.h +++ b/drivers/dma/fsl-edma-common.h @@ -166,6 +166,7 @@ struct fsl_edma_chan { struct work_struct issue_worker; struct platform_device *pdev; struct device *pd_dev; + struct device_link *pd_dev_link; u32 srcid; struct clk *clk; int priority; diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c index 60de1003193a..1a613236b3e4 100644 --- a/drivers/dma/fsl-edma-main.c +++ b/drivers/dma/fsl-edma-main.c @@ -417,10 +417,33 @@ static const struct of_device_id fsl_edma_dt_ids[] = { }; MODULE_DEVICE_TABLE(of, fsl_edma_dt_ids); +static void fsl_edma3_detach_pd(struct fsl_edma_engine *fsl_edma) +{ + struct fsl_edma_chan *fsl_chan; + int i; + + for (i = 0; i < fsl_edma->n_chans; i++) { + if (fsl_edma->chan_masked & BIT(i)) + continue; + fsl_chan = &fsl_edma->chans[i]; + if (fsl_chan->pd_dev_link) + device_link_del(fsl_chan->pd_dev_link); + if (fsl_chan->pd_dev) { + dev_pm_domain_detach(fsl_chan->pd_dev, false); + pm_runtime_dont_use_autosuspend(fsl_chan->pd_dev); + pm_runtime_set_suspended(fsl_chan->pd_dev); + } + } +} + +static void devm_fsl_edma3_detach_pd(void *data) +{ + fsl_edma3_detach_pd(data); +} + static int fsl_edma3_attach_pd(struct platform_device *pdev, struct fsl_edma_engine *fsl_edma) { struct fsl_edma_chan *fsl_chan; - struct device_link *link; struct device *pd_chan; struct device *dev; int i; @@ -436,15 +459,16 @@ static int fsl_edma3_attach_pd(struct platform_device *pdev, struct fsl_edma_eng pd_chan = dev_pm_domain_attach_by_id(dev, i); if (IS_ERR_OR_NULL(pd_chan)) { dev_err(dev, "Failed attach pd %d\n", i); - return -EINVAL; + goto detach; } - link = device_link_add(dev, pd_chan, DL_FLAG_STATELESS | + fsl_chan->pd_dev_link = device_link_add(dev, pd_chan, DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE); - if (!link) { + if (!fsl_chan->pd_dev_link) { dev_err(dev, "Failed to add device_link to %d\n", i); - return -EINVAL; + dev_pm_domain_detach(pd_chan, false); + goto detach; } fsl_chan->pd_dev = pd_chan; @@ -455,6 +479,10 @@ static int fsl_edma3_attach_pd(struct platform_device *pdev, struct fsl_edma_eng } return 0; + +detach: + fsl_edma3_detach_pd(fsl_edma); + return -EINVAL; } static int fsl_edma_probe(struct platform_device *pdev) @@ -544,6 +572,9 @@ static int fsl_edma_probe(struct platform_device *pdev) ret = fsl_edma3_attach_pd(pdev, fsl_edma); if (ret) return ret; + ret = devm_add_action_or_reset(&pdev->dev, devm_fsl_edma3_detach_pd, fsl_edma); + if (ret) + return ret; } if (drvdata->flags & FSL_EDMA_DRV_TCD64) diff --git a/drivers/dma/loongson2-apb-dma.c b/drivers/dma/loongson2-apb-dma.c index 367ed34ce4da..c528f02b9f84 100644 --- a/drivers/dma/loongson2-apb-dma.c +++ b/drivers/dma/loongson2-apb-dma.c @@ -31,7 +31,7 @@ #define LDMA_ASK_VALID BIT(2) #define LDMA_START BIT(3) /* DMA start operation */ #define LDMA_STOP BIT(4) /* DMA stop operation */ -#define LDMA_CONFIG_MASK GENMASK(4, 0) /* DMA controller config bits mask */ +#define LDMA_CONFIG_MASK GENMASK_ULL(4, 0) /* DMA controller config bits mask */ /* Bitfields in ndesc_addr field of HW descriptor */ #define LDMA_DESC_EN BIT(0) /*1: The next descriptor is valid */ diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c index 43efce77bb57..40b76b40bc30 100644 --- a/drivers/dma/mv_xor.c +++ b/drivers/dma/mv_xor.c @@ -1388,6 +1388,7 @@ static int mv_xor_probe(struct platform_device *pdev) irq = irq_of_parse_and_map(np, 0); if (!irq) { ret = -ENODEV; + of_node_put(np); goto err_channel_add; } @@ -1396,6 +1397,7 @@ static int mv_xor_probe(struct platform_device *pdev) if (IS_ERR(chan)) { ret = PTR_ERR(chan); irq_dispose_mapping(irq); + of_node_put(np); goto err_channel_add; } diff --git a/drivers/dma/tegra186-gpc-dma.c b/drivers/dma/tegra186-gpc-dma.c index cacf3757adc2..4d6fe0efa76e 100644 --- a/drivers/dma/tegra186-gpc-dma.c +++ b/drivers/dma/tegra186-gpc-dma.c @@ -231,6 +231,7 @@ struct tegra_dma_channel { bool config_init; char name[30]; enum dma_transfer_direction sid_dir; + enum dma_status status; int id; int irq; int slave_id; @@ -393,6 +394,8 @@ static int tegra_dma_pause(struct tegra_dma_channel *tdc) tegra_dma_dump_chan_regs(tdc); } + tdc->status = DMA_PAUSED; + return ret; } @@ -419,6 +422,8 @@ static void tegra_dma_resume(struct tegra_dma_channel *tdc) val = tdc_read(tdc, TEGRA_GPCDMA_CHAN_CSRE); val &= ~TEGRA_GPCDMA_CHAN_CSRE_PAUSE; tdc_write(tdc, TEGRA_GPCDMA_CHAN_CSRE, val); + + tdc->status = DMA_IN_PROGRESS; } static int tegra_dma_device_resume(struct dma_chan *dc) @@ -544,6 +549,7 @@ static void tegra_dma_xfer_complete(struct tegra_dma_channel *tdc) tegra_dma_sid_free(tdc); tdc->dma_desc = NULL; + tdc->status = DMA_COMPLETE; } static void tegra_dma_chan_decode_error(struct tegra_dma_channel *tdc, @@ -716,6 +722,7 @@ static int tegra_dma_terminate_all(struct dma_chan *dc) tdc->dma_desc = NULL; } + tdc->status = DMA_COMPLETE; tegra_dma_sid_free(tdc); vchan_get_all_descriptors(&tdc->vc, &head); spin_unlock_irqrestore(&tdc->vc.lock, flags); @@ -769,6 +776,9 @@ static enum dma_status tegra_dma_tx_status(struct dma_chan *dc, if (ret == DMA_COMPLETE) return ret; + if (tdc->status == DMA_PAUSED) + ret = DMA_PAUSED; + spin_lock_irqsave(&tdc->vc.lock, flags); vd = vchan_find_desc(&tdc->vc, cookie); if (vd) { diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c index eb17d03b66fe..dfda5ffc14db 100644 --- a/drivers/firmware/arm_ffa/bus.c +++ b/drivers/firmware/arm_ffa/bus.c @@ -187,13 +187,18 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev) return valid; } -struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, - const struct ffa_ops *ops) +struct ffa_device * +ffa_device_register(const struct ffa_partition_info *part_info, + const struct ffa_ops *ops) { int id, ret; + uuid_t uuid; struct device *dev; struct ffa_device *ffa_dev; + if (!part_info) + return NULL; + id = ida_alloc_min(&ffa_bus_id, 1, GFP_KERNEL); if (id < 0) return NULL; @@ -210,9 +215,11 @@ struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, dev_set_name(&ffa_dev->dev, "arm-ffa-%d", id); ffa_dev->id = id; - ffa_dev->vm_id = vm_id; + ffa_dev->vm_id = part_info->id; + ffa_dev->properties = part_info->properties; ffa_dev->ops = ops; - uuid_copy(&ffa_dev->uuid, uuid); + import_uuid(&uuid, (u8 *)part_info->uuid); + uuid_copy(&ffa_dev->uuid, &uuid); ret = device_register(&ffa_dev->dev); if (ret) { diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index b14cbdae94e8..2c2ec3c35f15 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -1387,7 +1387,6 @@ static struct notifier_block ffa_bus_nb = { static int ffa_setup_partitions(void) { int count, idx, ret; - uuid_t uuid; struct ffa_device *ffa_dev; struct ffa_dev_part_info *info; struct ffa_partition_info *pbuf, *tpbuf; @@ -1406,23 +1405,19 @@ static int ffa_setup_partitions(void) xa_init(&drv_info->partition_info); for (idx = 0, tpbuf = pbuf; idx < count; idx++, tpbuf++) { - import_uuid(&uuid, (u8 *)tpbuf->uuid); - /* Note that if the UUID will be uuid_null, that will require * ffa_bus_notifier() to find the UUID of this partition id * with help of ffa_device_match_uuid(). FF-A v1.1 and above * provides UUID here for each partition as part of the * discovery API and the same is passed. */ - ffa_dev = ffa_device_register(&uuid, tpbuf->id, &ffa_drv_ops); + ffa_dev = ffa_device_register(tpbuf, &ffa_drv_ops); if (!ffa_dev) { pr_err("%s: failed to register partition ID 0x%x\n", __func__, tpbuf->id); continue; } - ffa_dev->properties = tpbuf->properties; - if (drv_info->version > FFA_VERSION_1_0 && !(tpbuf->properties & FFA_PARTITION_AARCH64_EXEC)) ffa_mode_32bit_set(ffa_dev); diff --git a/drivers/firmware/arm_scmi/vendors/imx/Kconfig b/drivers/firmware/arm_scmi/vendors/imx/Kconfig index 2883ed24a84d..a01bf5e47301 100644 --- a/drivers/firmware/arm_scmi/vendors/imx/Kconfig +++ b/drivers/firmware/arm_scmi/vendors/imx/Kconfig @@ -15,6 +15,7 @@ config IMX_SCMI_BBM_EXT config IMX_SCMI_MISC_EXT tristate "i.MX SCMI MISC EXTENSION" depends on ARM_SCMI_PROTOCOL || (COMPILE_TEST && OF) + depends on IMX_SCMI_MISC_DRV default y if ARCH_MXC help This enables i.MX System MISC control logic such as gpio expander diff --git a/drivers/firmware/imx/Kconfig b/drivers/firmware/imx/Kconfig index 477d3f32d99a..907cd149c40a 100644 --- a/drivers/firmware/imx/Kconfig +++ b/drivers/firmware/imx/Kconfig @@ -25,7 +25,6 @@ config IMX_SCU config IMX_SCMI_MISC_DRV tristate "IMX SCMI MISC Protocol driver" - depends on IMX_SCMI_MISC_EXT || COMPILE_TEST default y if ARCH_MXC help The System Controller Management Interface firmware (SCMI FW) is diff --git a/drivers/firmware/microchip/mpfs-auto-update.c b/drivers/firmware/microchip/mpfs-auto-update.c index 38a03698cec9..e194f7acb2a9 100644 --- a/drivers/firmware/microchip/mpfs-auto-update.c +++ b/drivers/firmware/microchip/mpfs-auto-update.c @@ -402,10 +402,10 @@ static int mpfs_auto_update_available(struct mpfs_auto_update_priv *priv) return -EIO; /* - * Bit 5 of byte 1 is "UL_Auto Update" & if it is set, Auto Update is + * Bit 5 of byte 1 is "UL_IAP" & if it is set, Auto Update is * not possible. */ - if (response_msg[1] & AUTO_UPDATE_FEATURE_ENABLED) + if ((((u8 *)response_msg)[1] & AUTO_UPDATE_FEATURE_ENABLED)) return -EPERM; return 0; diff --git a/drivers/gpio/gpio-loongson-64bit.c b/drivers/gpio/gpio-loongson-64bit.c index 6749d4dd6d64..7f4d78fd800e 100644 --- a/drivers/gpio/gpio-loongson-64bit.c +++ b/drivers/gpio/gpio-loongson-64bit.c @@ -237,9 +237,9 @@ static const struct loongson_gpio_chip_data loongson_gpio_ls2k2000_data1 = { static const struct loongson_gpio_chip_data loongson_gpio_ls2k2000_data2 = { .label = "ls2k2000_gpio", .mode = BIT_CTRL_MODE, - .conf_offset = 0x84, - .in_offset = 0x88, - .out_offset = 0x80, + .conf_offset = 0x4, + .in_offset = 0x8, + .out_offset = 0x0, }; static const struct loongson_gpio_chip_data loongson_gpio_ls3a5000_data = { diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c index f387dad81f29..686ae3d11ba3 100644 --- a/drivers/gpio/gpio-sim.c +++ b/drivers/gpio/gpio-sim.c @@ -1027,6 +1027,30 @@ static void gpio_sim_device_deactivate(struct gpio_sim_device *dev) dev->pdev = NULL; } +static void +gpio_sim_device_lockup_configfs(struct gpio_sim_device *dev, bool lock) +{ + struct configfs_subsystem *subsys = dev->group.cg_subsys; + struct gpio_sim_bank *bank; + struct gpio_sim_line *line; + + /* + * The device only needs to depend on leaf line entries. This is + * sufficient to lock up all the configfs entries that the + * instantiated, alive device depends on. + */ + list_for_each_entry(bank, &dev->bank_list, siblings) { + list_for_each_entry(line, &bank->line_list, siblings) { + if (lock) + WARN_ON(configfs_depend_item_unlocked( + subsys, &line->group.cg_item)); + else + configfs_undepend_item_unlocked( + &line->group.cg_item); + } + } +} + static ssize_t gpio_sim_device_config_live_store(struct config_item *item, const char *page, size_t count) @@ -1039,14 +1063,24 @@ gpio_sim_device_config_live_store(struct config_item *item, if (ret) return ret; - guard(mutex)(&dev->lock); + if (live) + gpio_sim_device_lockup_configfs(dev, true); - if (live == gpio_sim_device_is_live(dev)) - ret = -EPERM; - else if (live) - ret = gpio_sim_device_activate(dev); - else - gpio_sim_device_deactivate(dev); + scoped_guard(mutex, &dev->lock) { + if (live == gpio_sim_device_is_live(dev)) + ret = -EPERM; + else if (live) + ret = gpio_sim_device_activate(dev); + else + gpio_sim_device_deactivate(dev); + } + + /* + * Undepend is required only if device disablement (live == 0) + * succeeds or if device enablement (live == 1) fails. + */ + if (live == !!ret) + gpio_sim_device_lockup_configfs(dev, false); return ret ?: count; } diff --git a/drivers/gpio/gpio-virtuser.c b/drivers/gpio/gpio-virtuser.c index 91b6352c957c..e89f299f2140 100644 --- a/drivers/gpio/gpio-virtuser.c +++ b/drivers/gpio/gpio-virtuser.c @@ -1410,7 +1410,7 @@ gpio_virtuser_make_lookup_table(struct gpio_virtuser_device *dev) size_t num_entries = gpio_virtuser_get_lookup_count(dev); struct gpio_virtuser_lookup_entry *entry; struct gpio_virtuser_lookup *lookup; - unsigned int i = 0; + unsigned int i = 0, idx; lockdep_assert_held(&dev->lock); @@ -1424,12 +1424,12 @@ gpio_virtuser_make_lookup_table(struct gpio_virtuser_device *dev) return -ENOMEM; list_for_each_entry(lookup, &dev->lookup_list, siblings) { + idx = 0; list_for_each_entry(entry, &lookup->entry_list, siblings) { - table->table[i] = + table->table[i++] = GPIO_LOOKUP_IDX(entry->key, entry->offset < 0 ? U16_MAX : entry->offset, - lookup->con_id, i, entry->flags); - i++; + lookup->con_id, idx++, entry->flags); } } @@ -1439,6 +1439,15 @@ gpio_virtuser_make_lookup_table(struct gpio_virtuser_device *dev) return 0; } +static void +gpio_virtuser_remove_lookup_table(struct gpio_virtuser_device *dev) +{ + gpiod_remove_lookup_table(dev->lookup_table); + kfree(dev->lookup_table->dev_id); + kfree(dev->lookup_table); + dev->lookup_table = NULL; +} + static struct fwnode_handle * gpio_virtuser_make_device_swnode(struct gpio_virtuser_device *dev) { @@ -1487,10 +1496,8 @@ gpio_virtuser_device_activate(struct gpio_virtuser_device *dev) pdevinfo.fwnode = swnode; ret = gpio_virtuser_make_lookup_table(dev); - if (ret) { - fwnode_remove_software_node(swnode); - return ret; - } + if (ret) + goto err_remove_swnode; reinit_completion(&dev->probe_completion); dev->driver_bound = false; @@ -1498,23 +1505,31 @@ gpio_virtuser_device_activate(struct gpio_virtuser_device *dev) pdev = platform_device_register_full(&pdevinfo); if (IS_ERR(pdev)) { + ret = PTR_ERR(pdev); bus_unregister_notifier(&platform_bus_type, &dev->bus_notifier); - fwnode_remove_software_node(swnode); - return PTR_ERR(pdev); + goto err_remove_lookup_table; } wait_for_completion(&dev->probe_completion); bus_unregister_notifier(&platform_bus_type, &dev->bus_notifier); if (!dev->driver_bound) { - platform_device_unregister(pdev); - fwnode_remove_software_node(swnode); - return -ENXIO; + ret = -ENXIO; + goto err_unregister_pdev; } dev->pdev = pdev; return 0; + +err_unregister_pdev: + platform_device_unregister(pdev); +err_remove_lookup_table: + gpio_virtuser_remove_lookup_table(dev); +err_remove_swnode: + fwnode_remove_software_node(swnode); + + return ret; } static void @@ -1526,10 +1541,33 @@ gpio_virtuser_device_deactivate(struct gpio_virtuser_device *dev) swnode = dev_fwnode(&dev->pdev->dev); platform_device_unregister(dev->pdev); + gpio_virtuser_remove_lookup_table(dev); fwnode_remove_software_node(swnode); dev->pdev = NULL; - gpiod_remove_lookup_table(dev->lookup_table); - kfree(dev->lookup_table); +} + +static void +gpio_virtuser_device_lockup_configfs(struct gpio_virtuser_device *dev, bool lock) +{ + struct configfs_subsystem *subsys = dev->group.cg_subsys; + struct gpio_virtuser_lookup_entry *entry; + struct gpio_virtuser_lookup *lookup; + + /* + * The device only needs to depend on leaf lookup entries. This is + * sufficient to lock up all the configfs entries that the + * instantiated, alive device depends on. + */ + list_for_each_entry(lookup, &dev->lookup_list, siblings) { + list_for_each_entry(entry, &lookup->entry_list, siblings) { + if (lock) + WARN_ON(configfs_depend_item_unlocked( + subsys, &entry->group.cg_item)); + else + configfs_undepend_item_unlocked( + &entry->group.cg_item); + } + } } static ssize_t @@ -1544,15 +1582,24 @@ gpio_virtuser_device_config_live_store(struct config_item *item, if (ret) return ret; - guard(mutex)(&dev->lock); + if (live) + gpio_virtuser_device_lockup_configfs(dev, true); - if (live == gpio_virtuser_device_is_live(dev)) - return -EPERM; + scoped_guard(mutex, &dev->lock) { + if (live == gpio_virtuser_device_is_live(dev)) + ret = -EPERM; + else if (live) + ret = gpio_virtuser_device_activate(dev); + else + gpio_virtuser_device_deactivate(dev); + } - if (live) - ret = gpio_virtuser_device_activate(dev); - else - gpio_virtuser_device_deactivate(dev); + /* + * Undepend is required only if device disablement (live == 0) + * succeeds or if device enablement (live == 1) fails. + */ + if (live == !!ret) + gpio_virtuser_device_lockup_configfs(dev, false); return ret ?: count; } diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 5504721007cc..772fc7625639 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -99,6 +99,7 @@ config DRM_KUNIT_TEST config DRM_KMS_HELPER tristate depends on DRM + select FB_CORE if DRM_FBDEV_EMULATION help CRTC helpers for KMS drivers. @@ -358,6 +359,7 @@ config DRM_TTM_HELPER tristate depends on DRM select DRM_TTM + select FB_CORE if DRM_FBDEV_EMULATION select FB_SYSMEM_HELPERS_DEFERRED if DRM_FBDEV_EMULATION help Helpers for ttm-based gem objects @@ -365,6 +367,7 @@ config DRM_TTM_HELPER config DRM_GEM_DMA_HELPER tristate depends on DRM + select FB_CORE if DRM_FBDEV_EMULATION select FB_DMAMEM_HELPERS_DEFERRED if DRM_FBDEV_EMULATION help Choose this if you need the GEM DMA helper functions @@ -372,6 +375,7 @@ config DRM_GEM_DMA_HELPER config DRM_GEM_SHMEM_HELPER tristate depends on DRM && MMU + select FB_CORE if DRM_FBDEV_EMULATION select FB_SYSMEM_HELPERS_DEFERRED if DRM_FBDEV_EMULATION help Choose this if you need the GEM shmem helper functions diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c index 946c48829f19..824f9da5b6ce 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c @@ -343,11 +343,10 @@ void amdgpu_coredump(struct amdgpu_device *adev, bool skip_vram_check, coredump->skip_vram_check = skip_vram_check; coredump->reset_vram_lost = vram_lost; - if (job && job->vm) { - struct amdgpu_vm *vm = job->vm; + if (job && job->pasid) { struct amdgpu_task_info *ti; - ti = amdgpu_vm_get_task_info_vm(vm); + ti = amdgpu_vm_get_task_info_pasid(adev, job->pasid); if (ti) { coredump->reset_task_info = *ti; amdgpu_vm_put_task_info(ti); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index d272d95dd5b2..cd4fac120834 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -417,6 +417,9 @@ bool amdgpu_device_supports_boco(struct drm_device *dev) { struct amdgpu_device *adev = drm_to_adev(dev); + if (!IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)) + return false; + if (adev->has_pr3 || ((adev->flags & AMD_IS_PX) && amdgpu_is_atpx_hybrid())) return true; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index b9d08bc96581..a21c510c408e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -255,7 +255,6 @@ void amdgpu_job_set_resources(struct amdgpu_job *job, struct amdgpu_bo *gds, void amdgpu_job_free_resources(struct amdgpu_job *job) { - struct amdgpu_ring *ring = to_amdgpu_ring(job->base.sched); struct dma_fence *f; unsigned i; @@ -268,7 +267,7 @@ void amdgpu_job_free_resources(struct amdgpu_job *job) f = NULL; for (i = 0; i < job->num_ibs; ++i) - amdgpu_ib_free(ring->adev, &job->ibs[i], f); + amdgpu_ib_free(NULL, &job->ibs[i], f); } static void amdgpu_job_free_cb(struct drm_sched_job *s_job) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index ddd7f05e4db9..c9c48b782ec1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1266,10 +1266,9 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, * next command submission. */ if (amdgpu_vm_is_bo_always_valid(vm, bo)) { - uint32_t mem_type = bo->tbo.resource->mem_type; - - if (!(bo->preferred_domains & - amdgpu_mem_type_to_domain(mem_type))) + if (bo->tbo.resource && + !(bo->preferred_domains & + amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type))) amdgpu_vm_bo_evicted(&bo_va->base); else amdgpu_vm_bo_idle(&bo_va->base); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 7d26a962f811..ff5e52025266 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -567,7 +567,6 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, else remaining_size -= size; } - mutex_unlock(&mgr->lock); if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS && adjust_dcc_size) { struct drm_buddy_block *dcc_block; @@ -584,6 +583,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, (u64)vres->base.size, &vres->blocks); } + mutex_unlock(&mgr->lock); vres->base.start = 0; size = max_t(u64, amdgpu_vram_mgr_blocks_size(&vres->blocks), diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c index fe7c48f2fb2a..da327ab48a57 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c @@ -4123,7 +4123,7 @@ static int gfx_v12_0_set_clockgating_state(void *handle, if (amdgpu_sriov_vf(adev)) return 0; - switch (adev->ip_versions[GC_HWIP][0]) { + switch (amdgpu_ip_version(adev, GC_HWIP, 0)) { case IP_VERSION(12, 0, 0): case IP_VERSION(12, 0, 1): gfx_v12_0_update_gfx_clock_gating(adev, diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v4_1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v4_1_0.c index 0fbc3be81f14..f2ab5001b492 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v4_1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v4_1_0.c @@ -108,7 +108,7 @@ mmhub_v4_1_0_print_l2_protection_fault_status(struct amdgpu_device *adev, dev_err(adev->dev, "MMVM_L2_PROTECTION_FAULT_STATUS_LO32:0x%08X\n", status); - switch (adev->ip_versions[MMHUB_HWIP][0]) { + switch (amdgpu_ip_version(adev, MMHUB_HWIP, 0)) { case IP_VERSION(4, 1, 0): mmhub_cid = mmhub_client_ids_v4_1_0[cid][rw]; break; diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c index b1b57dcc5a73..d1032e9992b4 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c @@ -271,8 +271,19 @@ const struct nbio_hdp_flush_reg nbio_v7_0_hdp_flush_reg = { .ref_and_mask_sdma1 = GPU_HDP_FLUSH_DONE__SDMA1_MASK, }; +#define regRCC_DEV0_EPF6_STRAP4 0xd304 +#define regRCC_DEV0_EPF6_STRAP4_BASE_IDX 5 + static void nbio_v7_0_init_registers(struct amdgpu_device *adev) { + uint32_t data; + + switch (amdgpu_ip_version(adev, NBIO_HWIP, 0)) { + case IP_VERSION(2, 5, 0): + data = RREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF6_STRAP4) & ~BIT(23); + WREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF6_STRAP4, data); + break; + } } #define MMIO_REG_HOLE_OFFSET (0x80000 - PAGE_SIZE) diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c index 814ab59fdd4a..41421da63a08 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c @@ -275,7 +275,7 @@ static void nbio_v7_11_init_registers(struct amdgpu_device *adev) if (def != data) WREG32_SOC15(NBIO, 0, regBIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3, data); - switch (adev->ip_versions[NBIO_HWIP][0]) { + switch (amdgpu_ip_version(adev, NBIO_HWIP, 0)) { case IP_VERSION(7, 11, 0): case IP_VERSION(7, 11, 1): case IP_VERSION(7, 11, 2): diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c index 1ac730328516..3fb6d2aa7e3b 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c @@ -247,7 +247,7 @@ static void nbio_v7_7_init_registers(struct amdgpu_device *adev) if (def != data) WREG32_SOC15(NBIO, 0, regBIF0_PCIE_MST_CTRL_3, data); - switch (adev->ip_versions[NBIO_HWIP][0]) { + switch (amdgpu_ip_version(adev, NBIO_HWIP, 0)) { case IP_VERSION(7, 7, 0): data = RREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF5_STRAP4) & ~BIT(23); WREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF5_STRAP4, data); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c index 312dfa84f29f..a8abc3091801 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c @@ -350,10 +350,27 @@ int kfd_dbg_set_mes_debug_mode(struct kfd_process_device *pdd, bool sq_trap_en) { uint32_t spi_dbg_cntl = pdd->spi_dbg_override | pdd->spi_dbg_launch_mode; uint32_t flags = pdd->process->dbg_flags; + struct amdgpu_device *adev = pdd->dev->adev; + int r; if (!kfd_dbg_is_per_vmid_supported(pdd->dev)) return 0; + if (!pdd->proc_ctx_cpu_ptr) { + r = amdgpu_amdkfd_alloc_gtt_mem(adev, + AMDGPU_MES_PROC_CTX_SIZE, + &pdd->proc_ctx_bo, + &pdd->proc_ctx_gpu_addr, + &pdd->proc_ctx_cpu_ptr, + false); + if (r) { + dev_err(adev->dev, + "failed to allocate process context bo\n"); + return r; + } + memset(pdd->proc_ctx_cpu_ptr, 0, AMDGPU_MES_PROC_CTX_SIZE); + } + return amdgpu_mes_set_shader_debugger(pdd->dev->adev, pdd->proc_ctx_gpu_addr, spi_dbg_cntl, pdd->watch_points, flags, sq_trap_en); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index d0ee173acf82..edfe0b4788f4 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1160,7 +1160,8 @@ static void kfd_process_wq_release(struct work_struct *work) */ synchronize_rcu(); ef = rcu_access_pointer(p->ef); - dma_fence_signal(ef); + if (ef) + dma_fence_signal(ef); kfd_process_remove_sysfs(p); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 48be917e7bc5..cd16dae534dc 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -8400,16 +8400,6 @@ static void manage_dm_interrupts(struct amdgpu_device *adev, struct amdgpu_crtc *acrtc, struct dm_crtc_state *acrtc_state) { - /* - * We have no guarantee that the frontend index maps to the same - * backend index - some even map to more than one. - * - * TODO: Use a different interrupt or check DC itself for the mapping. - */ - int irq_type = - amdgpu_display_crtc_idx_to_irq_type( - adev, - acrtc->crtc_id); struct drm_vblank_crtc_config config = {0}; struct dc_crtc_timing *timing; int offdelay; @@ -8435,28 +8425,7 @@ static void manage_dm_interrupts(struct amdgpu_device *adev, drm_crtc_vblank_on_config(&acrtc->base, &config); - - amdgpu_irq_get( - adev, - &adev->pageflip_irq, - irq_type); -#if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) - amdgpu_irq_get( - adev, - &adev->vline0_irq, - irq_type); -#endif } else { -#if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) - amdgpu_irq_put( - adev, - &adev->vline0_irq, - irq_type); -#endif - amdgpu_irq_put( - adev, - &adev->pageflip_irq, - irq_type); drm_crtc_vblank_off(&acrtc->base); } } @@ -11155,8 +11124,8 @@ dm_get_plane_scale(struct drm_plane_state *plane_state, int plane_src_w, plane_src_h; dm_get_oriented_plane_size(plane_state, &plane_src_w, &plane_src_h); - *out_plane_scale_w = plane_state->crtc_w * 1000 / plane_src_w; - *out_plane_scale_h = plane_state->crtc_h * 1000 / plane_src_h; + *out_plane_scale_w = plane_src_w ? plane_state->crtc_w * 1000 / plane_src_w : 0; + *out_plane_scale_h = plane_src_h ? plane_state->crtc_h * 1000 / plane_src_h : 0; } /* diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 49fe7dcf9372..2723558049d6 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -4510,7 +4510,7 @@ static bool commit_minimal_transition_based_on_current_context(struct dc *dc, struct pipe_split_policy_backup policy; struct dc_state *intermediate_context; struct dc_state *old_current_state = dc->current_state; - struct dc_surface_update srf_updates[MAX_SURFACE_NUM] = {0}; + struct dc_surface_update srf_updates[MAX_SURFACES] = {0}; int surface_count; /* diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c index e006f816ff2f..1b2cce127981 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c @@ -483,9 +483,9 @@ bool dc_state_add_plane( if (stream_status == NULL) { dm_error("Existing stream not found; failed to attach surface!\n"); goto out; - } else if (stream_status->plane_count == MAX_SURFACE_NUM) { + } else if (stream_status->plane_count == MAX_SURFACES) { dm_error("Surface: can not attach plane_state %p! Maximum is: %d\n", - plane_state, MAX_SURFACE_NUM); + plane_state, MAX_SURFACES); goto out; } else if (!otg_master_pipe) { goto out; @@ -600,7 +600,7 @@ bool dc_state_rem_all_planes_for_stream( { int i, old_plane_count; struct dc_stream_status *stream_status = NULL; - struct dc_plane_state *del_planes[MAX_SURFACE_NUM] = { 0 }; + struct dc_plane_state *del_planes[MAX_SURFACES] = { 0 }; for (i = 0; i < state->stream_count; i++) if (state->streams[i] == stream) { @@ -875,7 +875,7 @@ bool dc_state_rem_all_phantom_planes_for_stream( { int i, old_plane_count; struct dc_stream_status *stream_status = NULL; - struct dc_plane_state *del_planes[MAX_SURFACE_NUM] = { 0 }; + struct dc_plane_state *del_planes[MAX_SURFACES] = { 0 }; for (i = 0; i < state->stream_count; i++) if (state->streams[i] == phantom_stream) { diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index e9b9126c0401..08c5a315b3a6 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -57,7 +57,7 @@ struct dmub_notification; #define DC_VER "3.2.310" -#define MAX_SURFACES 3 +#define MAX_SURFACES 4 #define MAX_PLANES 6 #define MAX_STREAMS 6 #define MIN_VIEWPORT_SIZE 12 @@ -1398,7 +1398,7 @@ struct dc_scratch_space { * store current value in plane states so we can still recover * a valid current state during dc update. */ - struct dc_plane_state plane_states[MAX_SURFACE_NUM]; + struct dc_plane_state plane_states[MAX_SURFACES]; struct dc_stream_state stream_state; }; diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index 413970588a26..860506c6bda4 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -56,7 +56,7 @@ struct dc_stream_status { int plane_count; int audio_inst; struct timing_sync_info timing_sync_info; - struct dc_plane_state *plane_states[MAX_SURFACE_NUM]; + struct dc_plane_state *plane_states[MAX_SURFACES]; bool is_abm_supported; struct mall_stream_config mall_stream_config; bool fpo_in_use; diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h index edf4df1d03b5..9466b63644d5 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_types.h @@ -76,7 +76,6 @@ struct dc_perf_trace { unsigned long last_entry_write; }; -#define MAX_SURFACE_NUM 6 #define NUM_PIXEL_FORMATS 10 enum tiling_mode { diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h b/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h index 072bd0539605..6b2ab4ec2b5f 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h @@ -66,11 +66,15 @@ static inline double dml_max5(double a, double b, double c, double d, double e) static inline double dml_ceil(double a, double granularity) { + if (granularity == 0) + return 0; return (double) dcn_bw_ceil2(a, granularity); } static inline double dml_floor(double a, double granularity) { + if (granularity == 0) + return 0; return (double) dcn_bw_floor2(a, granularity); } @@ -114,11 +118,15 @@ static inline double dml_ceil_2(double f) static inline double dml_ceil_ex(double x, double granularity) { + if (granularity == 0) + return 0; return (double) dcn_bw_ceil2(x, granularity); } static inline double dml_floor_ex(double x, double granularity) { + if (granularity == 0) + return 0; return (double) dcn_bw_floor2(x, granularity); } diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_mall_phantom.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_mall_phantom.c index 3d29169dd6bb..6b3b8803e0ae 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_mall_phantom.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_mall_phantom.c @@ -813,7 +813,7 @@ static bool remove_all_phantom_planes_for_stream(struct dml2_context *ctx, struc { int i, old_plane_count; struct dc_stream_status *stream_status = NULL; - struct dc_plane_state *del_planes[MAX_SURFACE_NUM] = { 0 }; + struct dc_plane_state *del_planes[MAX_SURFACES] = { 0 }; for (i = 0; i < context->stream_count; i++) if (context->streams[i] == stream) { diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index ae3563d71fa0..356d9422b411 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -303,5 +303,7 @@ int smu_v13_0_set_wbrf_exclusion_ranges(struct smu_context *smu, int smu_v13_0_get_boot_freq_by_index(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t *value); + +void smu_v13_0_interrupt_work(struct smu_context *smu); #endif #endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index 2bfea740dace..2d1e7ebd1bac 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -1320,11 +1320,11 @@ static int smu_v13_0_set_irq_state(struct amdgpu_device *adev, return 0; } -static int smu_v13_0_ack_ac_dc_interrupt(struct smu_context *smu) +void smu_v13_0_interrupt_work(struct smu_context *smu) { - return smu_cmn_send_smc_msg(smu, - SMU_MSG_ReenableAcDcInterrupt, - NULL); + smu_cmn_send_smc_msg(smu, + SMU_MSG_ReenableAcDcInterrupt, + NULL); } #define THM_11_0__SRCID__THM_DIG_THERM_L2H 0 /* ASIC_TEMP > CG_THERMAL_INT.DIG_THERM_INTH */ @@ -1377,12 +1377,12 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev, switch (ctxid) { case SMU_IH_INTERRUPT_CONTEXT_ID_AC: dev_dbg(adev->dev, "Switched to AC mode!\n"); - smu_v13_0_ack_ac_dc_interrupt(smu); + schedule_work(&smu->interrupt_work); adev->pm.ac_power = true; break; case SMU_IH_INTERRUPT_CONTEXT_ID_DC: dev_dbg(adev->dev, "Switched to DC mode!\n"); - smu_v13_0_ack_ac_dc_interrupt(smu); + schedule_work(&smu->interrupt_work); adev->pm.ac_power = false; break; case SMU_IH_INTERRUPT_CONTEXT_ID_THERMAL_THROTTLING: diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 3aa705aae4c0..2a09b27788e8 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -3219,6 +3219,7 @@ static const struct pptable_funcs smu_v13_0_0_ppt_funcs = { .is_asic_wbrf_supported = smu_v13_0_0_wbrf_support_check, .enable_uclk_shadow = smu_v13_0_enable_uclk_shadow, .set_wbrf_exclusion_ranges = smu_v13_0_set_wbrf_exclusion_ranges, + .interrupt_work = smu_v13_0_interrupt_work, }; void smu_v13_0_0_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index aabb94796005..55ef18517b0f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -2797,6 +2797,7 @@ static const struct pptable_funcs smu_v13_0_7_ppt_funcs = { .is_asic_wbrf_supported = smu_v13_0_7_wbrf_support_check, .enable_uclk_shadow = smu_v13_0_enable_uclk_shadow, .set_wbrf_exclusion_ranges = smu_v13_0_set_wbrf_exclusion_ranges, + .interrupt_work = smu_v13_0_interrupt_work, }; void smu_v13_0_7_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c index 6a565ce74d5b..5cad09c5f2ff 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c @@ -2096,7 +2096,7 @@ static int smu_v14_0_2_enable_gfx_features(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; - if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(14, 0, 2)) + if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 2)) return smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_EnableAllSmuFeatures, FEATURE_PWR_GFX, NULL); else diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c b/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c index 61f4a38e7d2b..8f786592143b 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c @@ -153,7 +153,16 @@ static int adv7511_hdmi_hw_params(struct device *dev, void *data, ADV7511_AUDIO_CFG3_LEN_MASK, len); regmap_update_bits(adv7511->regmap, ADV7511_REG_I2C_FREQ_ID_CFG, ADV7511_I2C_FREQ_ID_CFG_RATE_MASK, rate << 4); - regmap_write(adv7511->regmap, 0x73, 0x1); + + /* send current Audio infoframe values while updating */ + regmap_update_bits(adv7511->regmap, ADV7511_REG_INFOFRAME_UPDATE, + BIT(5), BIT(5)); + + regmap_write(adv7511->regmap, ADV7511_REG_AUDIO_INFOFRAME(0), 0x1); + + /* use Audio infoframe updated info */ + regmap_update_bits(adv7511->regmap, ADV7511_REG_INFOFRAME_UPDATE, + BIT(5), 0); return 0; } @@ -184,8 +193,9 @@ static int audio_startup(struct device *dev, void *data) regmap_update_bits(adv7511->regmap, ADV7511_REG_GC(0), BIT(7) | BIT(6), BIT(7)); /* use Audio infoframe updated info */ - regmap_update_bits(adv7511->regmap, ADV7511_REG_GC(1), + regmap_update_bits(adv7511->regmap, ADV7511_REG_INFOFRAME_UPDATE, BIT(5), 0); + /* enable SPDIF receiver */ if (adv7511->audio_source == ADV7511_AUDIO_SOURCE_SPDIF) regmap_update_bits(adv7511->regmap, ADV7511_REG_AUDIO_CONFIG, diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index eb5919b38263..a13b3d8ab6ac 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -1241,8 +1241,10 @@ static int adv7511_probe(struct i2c_client *i2c) return ret; ret = adv7511_init_regulators(adv7511); - if (ret) - return dev_err_probe(dev, ret, "failed to init regulators\n"); + if (ret) { + dev_err_probe(dev, ret, "failed to init regulators\n"); + goto err_of_node_put; + } /* * The power down GPIO is optional. If present, toggle it from active to @@ -1363,6 +1365,8 @@ err_i2c_unregister_edid: i2c_unregister_device(adv7511->i2c_edid); uninit_regulators: adv7511_uninit_regulators(adv7511); +err_of_node_put: + of_node_put(adv7511->host_node); return ret; } @@ -1371,6 +1375,8 @@ static void adv7511_remove(struct i2c_client *i2c) { struct adv7511 *adv7511 = i2c_get_clientdata(i2c); + of_node_put(adv7511->host_node); + adv7511_uninit_regulators(adv7511); drm_bridge_remove(&adv7511->bridge); diff --git a/drivers/gpu/drm/bridge/adv7511/adv7533.c b/drivers/gpu/drm/bridge/adv7511/adv7533.c index 4481489aaf5e..122ad91e8a32 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7533.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7533.c @@ -172,7 +172,7 @@ int adv7533_parse_dt(struct device_node *np, struct adv7511 *adv) of_property_read_u32(np, "adi,dsi-lanes", &num_lanes); - if (num_lanes < 1 || num_lanes > 4) + if (num_lanes < 2 || num_lanes > 4) return -EINVAL; adv->num_dsi_lanes = num_lanes; @@ -181,8 +181,6 @@ int adv7533_parse_dt(struct device_node *np, struct adv7511 *adv) if (!adv->host_node) return -ENODEV; - of_node_put(adv->host_node); - adv->use_timing_gen = !of_property_read_bool(np, "adi,disable-timing-generator"); diff --git a/drivers/gpu/drm/display/drm_dp_tunnel.c b/drivers/gpu/drm/display/drm_dp_tunnel.c index 48b2df120086..90fe07a89260 100644 --- a/drivers/gpu/drm/display/drm_dp_tunnel.c +++ b/drivers/gpu/drm/display/drm_dp_tunnel.c @@ -1896,8 +1896,8 @@ static void destroy_mgr(struct drm_dp_tunnel_mgr *mgr) * * Creates a DP tunnel manager for @dev. * - * Returns a pointer to the tunnel manager if created successfully or NULL in - * case of an error. + * Returns a pointer to the tunnel manager if created successfully or error + * pointer in case of failure. */ struct drm_dp_tunnel_mgr * drm_dp_tunnel_mgr_create(struct drm_device *dev, int max_group_count) @@ -1907,7 +1907,7 @@ drm_dp_tunnel_mgr_create(struct drm_device *dev, int max_group_count) mgr = kzalloc(sizeof(*mgr), GFP_KERNEL); if (!mgr) - return NULL; + return ERR_PTR(-ENOMEM); mgr->dev = dev; init_waitqueue_head(&mgr->bw_req_queue); @@ -1916,7 +1916,7 @@ drm_dp_tunnel_mgr_create(struct drm_device *dev, int max_group_count) if (!mgr->groups) { kfree(mgr); - return NULL; + return ERR_PTR(-ENOMEM); } #ifdef CONFIG_DRM_DISPLAY_DP_TUNNEL_STATE_DEBUG @@ -1927,7 +1927,7 @@ drm_dp_tunnel_mgr_create(struct drm_device *dev, int max_group_count) if (!init_group(mgr, &mgr->groups[i])) { destroy_mgr(mgr); - return NULL; + return ERR_PTR(-ENOMEM); } mgr->group_count++; diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index 6ba167a33461..71573b85d924 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -1287,14 +1287,11 @@ EXPORT_SYMBOL(drm_mode_set_name); */ int drm_mode_vrefresh(const struct drm_display_mode *mode) { - unsigned int num, den; + unsigned int num = 1, den = 1; if (mode->htotal == 0 || mode->vtotal == 0) return 0; - num = mode->clock; - den = mode->htotal * mode->vtotal; - if (mode->flags & DRM_MODE_FLAG_INTERLACE) num *= 2; if (mode->flags & DRM_MODE_FLAG_DBLSCAN) @@ -1302,6 +1299,12 @@ int drm_mode_vrefresh(const struct drm_display_mode *mode) if (mode->vscan > 1) den *= mode->vscan; + if (check_mul_overflow(mode->clock, num, &num)) + return 0; + + if (check_mul_overflow(mode->htotal * mode->vtotal, den, &den)) + return 0; + return DIV_ROUND_CLOSEST_ULL(mul_u32_u32(num, 1000), den); } EXPORT_SYMBOL(drm_mode_vrefresh); diff --git a/drivers/gpu/drm/i915/display/intel_cx0_phy.c b/drivers/gpu/drm/i915/display/intel_cx0_phy.c index 71dc659228ab..0c7aee13495a 100644 --- a/drivers/gpu/drm/i915/display/intel_cx0_phy.c +++ b/drivers/gpu/drm/i915/display/intel_cx0_phy.c @@ -2115,14 +2115,6 @@ static void intel_c10_pll_program(struct intel_display *display, 0, C10_VDR_CTRL_MSGBUS_ACCESS, MB_WRITE_COMMITTED); - /* Custom width needs to be programmed to 0 for both the phy lanes */ - intel_cx0_rmw(encoder, INTEL_CX0_BOTH_LANES, PHY_C10_VDR_CUSTOM_WIDTH, - C10_VDR_CUSTOM_WIDTH_MASK, C10_VDR_CUSTOM_WIDTH_8_10, - MB_WRITE_COMMITTED); - intel_cx0_rmw(encoder, INTEL_CX0_BOTH_LANES, PHY_C10_VDR_CONTROL(1), - 0, C10_VDR_CTRL_UPDATE_CFG, - MB_WRITE_COMMITTED); - /* Program the pll values only for the master lane */ for (i = 0; i < ARRAY_SIZE(pll_state->pll); i++) intel_cx0_write(encoder, INTEL_CX0_LANE0, PHY_C10_VDR_PLL(i), @@ -2132,6 +2124,10 @@ static void intel_c10_pll_program(struct intel_display *display, intel_cx0_write(encoder, INTEL_CX0_LANE0, PHY_C10_VDR_CMN(0), pll_state->cmn, MB_WRITE_COMMITTED); intel_cx0_write(encoder, INTEL_CX0_LANE0, PHY_C10_VDR_TX(0), pll_state->tx, MB_WRITE_COMMITTED); + /* Custom width needs to be programmed to 0 for both the phy lanes */ + intel_cx0_rmw(encoder, INTEL_CX0_BOTH_LANES, PHY_C10_VDR_CUSTOM_WIDTH, + C10_VDR_CUSTOM_WIDTH_MASK, C10_VDR_CUSTOM_WIDTH_8_10, + MB_WRITE_COMMITTED); intel_cx0_rmw(encoder, INTEL_CX0_LANE0, PHY_C10_VDR_CONTROL(1), 0, C10_VDR_CTRL_MASTER_LANE | C10_VDR_CTRL_UPDATE_CFG, MB_WRITE_COMMITTED); diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c index f57e4dba2873..8fee26d791f4 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_hdcp.c @@ -1158,9 +1158,15 @@ static int intel_hdcp_check_link(struct intel_connector *connector) goto out; } - intel_hdcp_update_value(connector, - DRM_MODE_CONTENT_PROTECTION_DESIRED, - true); + ret = intel_hdcp1_enable(connector); + if (ret) { + drm_err(display->drm, "Failed to enable hdcp (%d)\n", ret); + intel_hdcp_update_value(connector, + DRM_MODE_CONTENT_PROTECTION_DESIRED, + true); + goto out; + } + out: mutex_unlock(&dig_port->hdcp_mutex); mutex_unlock(&hdcp->mutex); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index ba55c059063d..fe1f85e5dda3 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -343,6 +343,11 @@ struct intel_engine_guc_stats { * @start_gt_clk: GT clock time of last idle to active transition. */ u64 start_gt_clk; + + /** + * @total: The last value of total returned + */ + u64 total; }; union intel_engine_tlb_inv_reg { diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c index c864d101faf9..9378d5901c49 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6.c +++ b/drivers/gpu/drm/i915/gt/intel_rc6.c @@ -133,7 +133,7 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6) GEN9_MEDIA_PG_ENABLE | GEN11_MEDIA_SAMPLER_PG_ENABLE; - if (GRAPHICS_VER(gt->i915) >= 12) { + if (GRAPHICS_VER(gt->i915) >= 12 && !IS_DG1(gt->i915)) { for (i = 0; i < I915_MAX_VCS; i++) if (HAS_ENGINE(gt, _VCS(i))) pg_enable |= (VDN_HCP_POWERGATE_ENABLE(i) | diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 9ede6f240d79..c0bd730383f2 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1243,6 +1243,21 @@ static void __get_engine_usage_record(struct intel_engine_cs *engine, } while (++i < 6); } +static void __set_engine_usage_record(struct intel_engine_cs *engine, + u32 last_in, u32 id, u32 total) +{ + struct iosys_map rec_map = intel_guc_engine_usage_record_map(engine); + +#define record_write(map_, field_, val_) \ + iosys_map_wr_field(map_, 0, struct guc_engine_usage_record, field_, val_) + + record_write(&rec_map, last_switch_in_stamp, last_in); + record_write(&rec_map, current_context_index, id); + record_write(&rec_map, total_runtime, total); + +#undef record_write +} + static void guc_update_engine_gt_clks(struct intel_engine_cs *engine) { struct intel_engine_guc_stats *stats = &engine->stats.guc; @@ -1363,9 +1378,12 @@ static ktime_t guc_engine_busyness(struct intel_engine_cs *engine, ktime_t *now) total += intel_gt_clock_interval_to_ns(gt, clk); } + if (total > stats->total) + stats->total = total; + spin_unlock_irqrestore(&guc->timestamp.lock, flags); - return ns_to_ktime(total); + return ns_to_ktime(stats->total); } static void guc_enable_busyness_worker(struct intel_guc *guc) @@ -1431,8 +1449,21 @@ static void __reset_guc_busyness_stats(struct intel_guc *guc) guc_update_pm_timestamp(guc, &unused); for_each_engine(engine, gt, id) { + struct intel_engine_guc_stats *stats = &engine->stats.guc; + guc_update_engine_gt_clks(engine); - engine->stats.guc.prev_total = 0; + + /* + * If resetting a running context, accumulate the active + * time as well since there will be no context switch. + */ + if (stats->running) { + u64 clk = guc->timestamp.gt_stamp - stats->start_gt_clk; + + stats->total_gt_clks += clk; + } + stats->prev_total = 0; + stats->running = 0; } spin_unlock_irqrestore(&guc->timestamp.lock, flags); @@ -1543,6 +1574,9 @@ err_trylock: static int guc_action_enable_usage_stats(struct intel_guc *guc) { + struct intel_gt *gt = guc_to_gt(guc); + struct intel_engine_cs *engine; + enum intel_engine_id id; u32 offset = intel_guc_engine_usage_offset(guc); u32 action[] = { INTEL_GUC_ACTION_SET_ENG_UTIL_BUFF, @@ -1550,6 +1584,9 @@ static int guc_action_enable_usage_stats(struct intel_guc *guc) 0, }; + for_each_engine(engine, gt, id) + __set_engine_usage_record(engine, 0, 0xffffffff, 0); + return intel_guc_send(guc, action, ARRAY_SIZE(action)); } diff --git a/drivers/gpu/drm/mediatek/Kconfig b/drivers/gpu/drm/mediatek/Kconfig index f496e6cfdfe0..e47debd60619 100644 --- a/drivers/gpu/drm/mediatek/Kconfig +++ b/drivers/gpu/drm/mediatek/Kconfig @@ -14,9 +14,6 @@ config DRM_MEDIATEK select DRM_BRIDGE_CONNECTOR select DRM_MIPI_DSI select DRM_PANEL - select MEMORY - select MTK_SMI - select PHY_MTK_MIPI_DSI select VIDEOMODE_HELPERS help Choose this option if you have a Mediatek SoCs. @@ -27,7 +24,6 @@ config DRM_MEDIATEK config DRM_MEDIATEK_DP tristate "DRM DPTX Support for MediaTek SoCs" depends on DRM_MEDIATEK - select PHY_MTK_DP select DRM_DISPLAY_HELPER select DRM_DISPLAY_DP_HELPER select DRM_DISPLAY_DP_AUX_BUS @@ -38,6 +34,5 @@ config DRM_MEDIATEK_HDMI tristate "DRM HDMI Support for Mediatek SoCs" depends on DRM_MEDIATEK select SND_SOC_HDMI_CODEC if SND_SOC - select PHY_MTK_HDMI help DRM/KMS HDMI driver for Mediatek SoCs diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.c b/drivers/gpu/drm/mediatek/mtk_crtc.c index eb0e1233ad04..5674f5707cca 100644 --- a/drivers/gpu/drm/mediatek/mtk_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_crtc.c @@ -112,6 +112,11 @@ static void mtk_drm_finish_page_flip(struct mtk_crtc *mtk_crtc) drm_crtc_handle_vblank(&mtk_crtc->base); +#if IS_REACHABLE(CONFIG_MTK_CMDQ) + if (mtk_crtc->cmdq_client.chan) + return; +#endif + spin_lock_irqsave(&mtk_crtc->config_lock, flags); if (!mtk_crtc->config_updating && mtk_crtc->pending_needs_vblank) { mtk_crtc_finish_page_flip(mtk_crtc); @@ -284,10 +289,8 @@ static void ddp_cmdq_cb(struct mbox_client *cl, void *mssg) state = to_mtk_crtc_state(mtk_crtc->base.state); spin_lock_irqsave(&mtk_crtc->config_lock, flags); - if (mtk_crtc->config_updating) { - spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); + if (mtk_crtc->config_updating) goto ddp_cmdq_cb_out; - } state->pending_config = false; @@ -315,10 +318,15 @@ static void ddp_cmdq_cb(struct mbox_client *cl, void *mssg) mtk_crtc->pending_async_planes = false; } - spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); - ddp_cmdq_cb_out: + if (mtk_crtc->pending_needs_vblank) { + mtk_crtc_finish_page_flip(mtk_crtc); + mtk_crtc->pending_needs_vblank = false; + } + + spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); + mtk_crtc->cmdq_vblank_cnt = 0; wake_up(&mtk_crtc->cb_blocking_queue); } @@ -606,13 +614,18 @@ static void mtk_crtc_update_config(struct mtk_crtc *mtk_crtc, bool needs_vblank) */ mtk_crtc->cmdq_vblank_cnt = 3; + spin_lock_irqsave(&mtk_crtc->config_lock, flags); + mtk_crtc->config_updating = false; + spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); + mbox_send_message(mtk_crtc->cmdq_client.chan, cmdq_handle); mbox_client_txdone(mtk_crtc->cmdq_client.chan, 0); } -#endif +#else spin_lock_irqsave(&mtk_crtc->config_lock, flags); mtk_crtc->config_updating = false; spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); +#endif mutex_unlock(&mtk_crtc->hw_lock); } diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c index f731d4fbe8b6..df82cea4bb79 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c @@ -460,6 +460,29 @@ static unsigned int mtk_ovl_fmt_convert(struct mtk_disp_ovl *ovl, } } +static void mtk_ovl_afbc_layer_config(struct mtk_disp_ovl *ovl, + unsigned int idx, + struct mtk_plane_pending_state *pending, + struct cmdq_pkt *cmdq_pkt) +{ + unsigned int pitch_msb = pending->pitch >> 16; + unsigned int hdr_pitch = pending->hdr_pitch; + unsigned int hdr_addr = pending->hdr_addr; + + if (pending->modifier != DRM_FORMAT_MOD_LINEAR) { + mtk_ddp_write_relaxed(cmdq_pkt, hdr_addr, &ovl->cmdq_reg, ovl->regs, + DISP_REG_OVL_HDR_ADDR(ovl, idx)); + mtk_ddp_write_relaxed(cmdq_pkt, + OVL_PITCH_MSB_2ND_SUBBUF | pitch_msb, + &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH_MSB(idx)); + mtk_ddp_write_relaxed(cmdq_pkt, hdr_pitch, &ovl->cmdq_reg, ovl->regs, + DISP_REG_OVL_HDR_PITCH(ovl, idx)); + } else { + mtk_ddp_write_relaxed(cmdq_pkt, pitch_msb, + &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH_MSB(idx)); + } +} + void mtk_ovl_layer_config(struct device *dev, unsigned int idx, struct mtk_plane_state *state, struct cmdq_pkt *cmdq_pkt) @@ -467,25 +490,14 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx, struct mtk_disp_ovl *ovl = dev_get_drvdata(dev); struct mtk_plane_pending_state *pending = &state->pending; unsigned int addr = pending->addr; - unsigned int hdr_addr = pending->hdr_addr; - unsigned int pitch = pending->pitch; - unsigned int hdr_pitch = pending->hdr_pitch; + unsigned int pitch_lsb = pending->pitch & GENMASK(15, 0); unsigned int fmt = pending->format; + unsigned int rotation = pending->rotation; unsigned int offset = (pending->y << 16) | pending->x; unsigned int src_size = (pending->height << 16) | pending->width; unsigned int blend_mode = state->base.pixel_blend_mode; unsigned int ignore_pixel_alpha = 0; unsigned int con; - bool is_afbc = pending->modifier != DRM_FORMAT_MOD_LINEAR; - union overlay_pitch { - struct split_pitch { - u16 lsb; - u16 msb; - } split_pitch; - u32 pitch; - } overlay_pitch; - - overlay_pitch.pitch = pitch; if (!pending->enable) { mtk_ovl_layer_off(dev, idx, cmdq_pkt); @@ -513,22 +525,30 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx, ignore_pixel_alpha = OVL_CONST_BLEND; } - if (pending->rotation & DRM_MODE_REFLECT_Y) { + /* + * Treat rotate 180 as flip x + flip y, and XOR the original rotation value + * to flip x + flip y to support both in the same time. + */ + if (rotation & DRM_MODE_ROTATE_180) + rotation ^= DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y; + + if (rotation & DRM_MODE_REFLECT_Y) { con |= OVL_CON_VIRT_FLIP; addr += (pending->height - 1) * pending->pitch; } - if (pending->rotation & DRM_MODE_REFLECT_X) { + if (rotation & DRM_MODE_REFLECT_X) { con |= OVL_CON_HORZ_FLIP; addr += pending->pitch - 1; } if (ovl->data->supports_afbc) - mtk_ovl_set_afbc(ovl, cmdq_pkt, idx, is_afbc); + mtk_ovl_set_afbc(ovl, cmdq_pkt, idx, + pending->modifier != DRM_FORMAT_MOD_LINEAR); mtk_ddp_write_relaxed(cmdq_pkt, con, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_CON(idx)); - mtk_ddp_write_relaxed(cmdq_pkt, overlay_pitch.split_pitch.lsb | ignore_pixel_alpha, + mtk_ddp_write_relaxed(cmdq_pkt, pitch_lsb | ignore_pixel_alpha, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH(idx)); mtk_ddp_write_relaxed(cmdq_pkt, src_size, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_SRC_SIZE(idx)); @@ -537,19 +557,8 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx, mtk_ddp_write_relaxed(cmdq_pkt, addr, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_ADDR(ovl, idx)); - if (is_afbc) { - mtk_ddp_write_relaxed(cmdq_pkt, hdr_addr, &ovl->cmdq_reg, ovl->regs, - DISP_REG_OVL_HDR_ADDR(ovl, idx)); - mtk_ddp_write_relaxed(cmdq_pkt, - OVL_PITCH_MSB_2ND_SUBBUF | overlay_pitch.split_pitch.msb, - &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH_MSB(idx)); - mtk_ddp_write_relaxed(cmdq_pkt, hdr_pitch, &ovl->cmdq_reg, ovl->regs, - DISP_REG_OVL_HDR_PITCH(ovl, idx)); - } else { - mtk_ddp_write_relaxed(cmdq_pkt, - overlay_pitch.split_pitch.msb, - &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH_MSB(idx)); - } + if (ovl->data->supports_afbc) + mtk_ovl_afbc_layer_config(ovl, idx, pending, cmdq_pkt); mtk_ovl_set_bit_depth(dev, idx, fmt, cmdq_pkt); mtk_ovl_layer_on(dev, idx, cmdq_pkt); diff --git a/drivers/gpu/drm/mediatek/mtk_dp.c b/drivers/gpu/drm/mediatek/mtk_dp.c index 36713c176cfc..3b0993abfdc3 100644 --- a/drivers/gpu/drm/mediatek/mtk_dp.c +++ b/drivers/gpu/drm/mediatek/mtk_dp.c @@ -543,18 +543,16 @@ static int mtk_dp_set_color_format(struct mtk_dp *mtk_dp, enum dp_pixelformat color_format) { u32 val; - - /* update MISC0 */ - mtk_dp_update_bits(mtk_dp, MTK_DP_ENC0_P0_3034, - color_format << DP_TEST_COLOR_FORMAT_SHIFT, - DP_TEST_COLOR_FORMAT_MASK); + u32 misc0_color; switch (color_format) { case DP_PIXELFORMAT_YUV422: val = PIXEL_ENCODE_FORMAT_DP_ENC0_P0_YCBCR422; + misc0_color = DP_COLOR_FORMAT_YCbCr422; break; case DP_PIXELFORMAT_RGB: val = PIXEL_ENCODE_FORMAT_DP_ENC0_P0_RGB; + misc0_color = DP_COLOR_FORMAT_RGB; break; default: drm_warn(mtk_dp->drm_dev, "Unsupported color format: %d\n", @@ -562,6 +560,11 @@ static int mtk_dp_set_color_format(struct mtk_dp *mtk_dp, return -EINVAL; } + /* update MISC0 */ + mtk_dp_update_bits(mtk_dp, MTK_DP_ENC0_P0_3034, + misc0_color, + DP_TEST_COLOR_FORMAT_MASK); + mtk_dp_update_bits(mtk_dp, MTK_DP_ENC0_P0_303C, val, PIXEL_ENCODE_FORMAT_DP_ENC0_P0_MASK); return 0; @@ -2100,7 +2103,6 @@ static enum drm_connector_status mtk_dp_bdg_detect(struct drm_bridge *bridge) struct mtk_dp *mtk_dp = mtk_dp_from_bridge(bridge); enum drm_connector_status ret = connector_status_disconnected; bool enabled = mtk_dp->enabled; - u8 sink_count = 0; if (!mtk_dp->train_info.cable_plugged_in) return ret; @@ -2115,8 +2117,8 @@ static enum drm_connector_status mtk_dp_bdg_detect(struct drm_bridge *bridge) * function, we just need to check the HPD connection to check * whether we connect to a sink device. */ - drm_dp_dpcd_readb(&mtk_dp->aux, DP_SINK_COUNT, &sink_count); - if (DP_GET_SINK_COUNT(sink_count)) + + if (drm_dp_read_sink_count(&mtk_dp->aux) > 0) ret = connector_status_connected; if (!enabled) @@ -2408,12 +2410,19 @@ mtk_dp_bridge_mode_valid(struct drm_bridge *bridge, { struct mtk_dp *mtk_dp = mtk_dp_from_bridge(bridge); u32 bpp = info->color_formats & DRM_COLOR_FORMAT_YCBCR422 ? 16 : 24; - u32 rate = min_t(u32, drm_dp_max_link_rate(mtk_dp->rx_cap) * - drm_dp_max_lane_count(mtk_dp->rx_cap), - drm_dp_bw_code_to_link_rate(mtk_dp->max_linkrate) * - mtk_dp->max_lanes); + u32 lane_count_min = mtk_dp->train_info.lane_count; + u32 rate = drm_dp_bw_code_to_link_rate(mtk_dp->train_info.link_rate) * + lane_count_min; - if (rate < mode->clock * bpp / 8) + /* + *FEC overhead is approximately 2.4% from DP 1.4a spec 2.2.1.4.2. + *The down-spread amplitude shall either be disabled (0.0%) or up + *to 0.5% from 1.4a 3.5.2.6. Add up to approximately 3% total overhead. + * + *Because rate is already divided by 10, + *mode->clock does not need to be multiplied by 10 + */ + if ((rate * 97 / 100) < (mode->clock * bpp / 8)) return MODE_CLOCK_HIGH; return MODE_OK; @@ -2454,10 +2463,9 @@ static u32 *mtk_dp_bridge_atomic_get_input_bus_fmts(struct drm_bridge *bridge, struct drm_display_mode *mode = &crtc_state->adjusted_mode; struct drm_display_info *display_info = &conn_state->connector->display_info; - u32 rate = min_t(u32, drm_dp_max_link_rate(mtk_dp->rx_cap) * - drm_dp_max_lane_count(mtk_dp->rx_cap), - drm_dp_bw_code_to_link_rate(mtk_dp->max_linkrate) * - mtk_dp->max_lanes); + u32 lane_count_min = mtk_dp->train_info.lane_count; + u32 rate = drm_dp_bw_code_to_link_rate(mtk_dp->train_info.link_rate) * + lane_count_min; *num_input_fmts = 0; @@ -2466,8 +2474,8 @@ static u32 *mtk_dp_bridge_atomic_get_input_bus_fmts(struct drm_bridge *bridge, * datarate of YUV422 and sink device supports YUV422, we output YUV422 * format. Use this condition, we can support more resolution. */ - if ((rate < (mode->clock * 24 / 8)) && - (rate > (mode->clock * 16 / 8)) && + if (((rate * 97 / 100) < (mode->clock * 24 / 8)) && + ((rate * 97 / 100) > (mode->clock * 16 / 8)) && (display_info->color_formats & DRM_COLOR_FORMAT_YCBCR422)) { input_fmts = kcalloc(1, sizeof(*input_fmts), GFP_KERNEL); if (!input_fmts) diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 0829ceb9967c..b037616d3342 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -373,11 +373,12 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev) struct mtk_drm_private *temp_drm_priv; struct device_node *phandle = dev->parent->of_node; const struct of_device_id *of_id; + struct device_node *node; struct device *drm_dev; unsigned int cnt = 0; int i, j; - for_each_child_of_node_scoped(phandle->parent, node) { + for_each_child_of_node(phandle->parent, node) { struct platform_device *pdev; of_id = of_match_node(mtk_drm_of_ids, node); @@ -406,8 +407,10 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev) if (temp_drm_priv->mtk_drm_bound) cnt++; - if (cnt == MAX_CRTC) + if (cnt == MAX_CRTC) { + of_node_put(node); break; + } } if (drm_priv->data->mmsys_dev_num == cnt) { @@ -673,6 +676,8 @@ err_deinit: err_free: private->drm = NULL; drm_dev_put(drm); + for (i = 0; i < private->data->mmsys_dev_num; i++) + private->all_drm_private[i]->drm = NULL; return ret; } @@ -900,7 +905,7 @@ static int mtk_drm_of_ddp_path_build_one(struct device *dev, enum mtk_crtc_path const unsigned int **out_path, unsigned int *out_path_len) { - struct device_node *next, *prev, *vdo = dev->parent->of_node; + struct device_node *next = NULL, *prev, *vdo = dev->parent->of_node; unsigned int temp_path[DDP_COMPONENT_DRM_ID_MAX] = { 0 }; unsigned int *final_ddp_path; unsigned short int idx = 0; @@ -1089,7 +1094,7 @@ static int mtk_drm_probe(struct platform_device *pdev) /* No devicetree graphs support: go with hardcoded paths if present */ dev_dbg(dev, "Using hardcoded paths for MMSYS %u\n", mtk_drm_data->mmsys_id); private->data = mtk_drm_data; - }; + } private->all_drm_private = devm_kmalloc_array(dev, private->data->mmsys_dev_num, sizeof(*private->all_drm_private), diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index e61b9bc68e9a..40752f232054 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -139,11 +139,11 @@ #define CLK_HS_POST GENMASK(15, 8) #define CLK_HS_EXIT GENMASK(23, 16) -#define DSI_VM_CMD_CON 0x130 +/* DSI_VM_CMD_CON */ #define VM_CMD_EN BIT(0) #define TS_VFP_EN BIT(5) -#define DSI_SHADOW_DEBUG 0x190U +/* DSI_SHADOW_DEBUG */ #define FORCE_COMMIT BIT(0) #define BYPASS_SHADOW BIT(1) @@ -187,6 +187,8 @@ struct phy; struct mtk_dsi_driver_data { const u32 reg_cmdq_off; + const u32 reg_vm_cmd_off; + const u32 reg_shadow_dbg_off; bool has_shadow_ctl; bool has_size_ctl; bool cmdq_long_packet_ctl; @@ -246,23 +248,22 @@ static void mtk_dsi_phy_timconfig(struct mtk_dsi *dsi) u32 data_rate_mhz = DIV_ROUND_UP(dsi->data_rate, HZ_PER_MHZ); struct mtk_phy_timing *timing = &dsi->phy_timing; - timing->lpx = (80 * data_rate_mhz / (8 * 1000)) + 1; - timing->da_hs_prepare = (59 * data_rate_mhz + 4 * 1000) / 8000 + 1; - timing->da_hs_zero = (163 * data_rate_mhz + 11 * 1000) / 8000 + 1 - + timing->lpx = (60 * data_rate_mhz / (8 * 1000)) + 1; + timing->da_hs_prepare = (80 * data_rate_mhz + 4 * 1000) / 8000; + timing->da_hs_zero = (170 * data_rate_mhz + 10 * 1000) / 8000 + 1 - timing->da_hs_prepare; - timing->da_hs_trail = (78 * data_rate_mhz + 7 * 1000) / 8000 + 1; + timing->da_hs_trail = timing->da_hs_prepare + 1; - timing->ta_go = 4 * timing->lpx; - timing->ta_sure = 3 * timing->lpx / 2; - timing->ta_get = 5 * timing->lpx; - timing->da_hs_exit = (118 * data_rate_mhz / (8 * 1000)) + 1; + timing->ta_go = 4 * timing->lpx - 2; + timing->ta_sure = timing->lpx + 2; + timing->ta_get = 4 * timing->lpx; + timing->da_hs_exit = 2 * timing->lpx + 1; - timing->clk_hs_prepare = (57 * data_rate_mhz / (8 * 1000)) + 1; - timing->clk_hs_post = (65 * data_rate_mhz + 53 * 1000) / 8000 + 1; - timing->clk_hs_trail = (78 * data_rate_mhz + 7 * 1000) / 8000 + 1; - timing->clk_hs_zero = (330 * data_rate_mhz / (8 * 1000)) + 1 - - timing->clk_hs_prepare; - timing->clk_hs_exit = (118 * data_rate_mhz / (8 * 1000)) + 1; + timing->clk_hs_prepare = 70 * data_rate_mhz / (8 * 1000); + timing->clk_hs_post = timing->clk_hs_prepare + 8; + timing->clk_hs_trail = timing->clk_hs_prepare; + timing->clk_hs_zero = timing->clk_hs_trail * 4; + timing->clk_hs_exit = 2 * timing->clk_hs_trail; timcon0 = FIELD_PREP(LPX, timing->lpx) | FIELD_PREP(HS_PREP, timing->da_hs_prepare) | @@ -367,8 +368,8 @@ static void mtk_dsi_set_mode(struct mtk_dsi *dsi) static void mtk_dsi_set_vm_cmd(struct mtk_dsi *dsi) { - mtk_dsi_mask(dsi, DSI_VM_CMD_CON, VM_CMD_EN, VM_CMD_EN); - mtk_dsi_mask(dsi, DSI_VM_CMD_CON, TS_VFP_EN, TS_VFP_EN); + mtk_dsi_mask(dsi, dsi->driver_data->reg_vm_cmd_off, VM_CMD_EN, VM_CMD_EN); + mtk_dsi_mask(dsi, dsi->driver_data->reg_vm_cmd_off, TS_VFP_EN, TS_VFP_EN); } static void mtk_dsi_rxtx_control(struct mtk_dsi *dsi) @@ -714,7 +715,7 @@ static int mtk_dsi_poweron(struct mtk_dsi *dsi) if (dsi->driver_data->has_shadow_ctl) writel(FORCE_COMMIT | BYPASS_SHADOW, - dsi->regs + DSI_SHADOW_DEBUG); + dsi->regs + dsi->driver_data->reg_shadow_dbg_off); mtk_dsi_reset_engine(dsi); mtk_dsi_phy_timconfig(dsi); @@ -1263,26 +1264,36 @@ static void mtk_dsi_remove(struct platform_device *pdev) static const struct mtk_dsi_driver_data mt8173_dsi_driver_data = { .reg_cmdq_off = 0x200, + .reg_vm_cmd_off = 0x130, + .reg_shadow_dbg_off = 0x190 }; static const struct mtk_dsi_driver_data mt2701_dsi_driver_data = { .reg_cmdq_off = 0x180, + .reg_vm_cmd_off = 0x130, + .reg_shadow_dbg_off = 0x190 }; static const struct mtk_dsi_driver_data mt8183_dsi_driver_data = { .reg_cmdq_off = 0x200, + .reg_vm_cmd_off = 0x130, + .reg_shadow_dbg_off = 0x190, .has_shadow_ctl = true, .has_size_ctl = true, }; static const struct mtk_dsi_driver_data mt8186_dsi_driver_data = { .reg_cmdq_off = 0xd00, + .reg_vm_cmd_off = 0x200, + .reg_shadow_dbg_off = 0xc00, .has_shadow_ctl = true, .has_size_ctl = true, }; static const struct mtk_dsi_driver_data mt8188_dsi_driver_data = { .reg_cmdq_off = 0xd00, + .reg_vm_cmd_off = 0x200, + .reg_shadow_dbg_off = 0xc00, .has_shadow_ctl = true, .has_size_ctl = true, .cmdq_long_packet_ctl = true, diff --git a/drivers/gpu/drm/panel/panel-himax-hx83102.c b/drivers/gpu/drm/panel/panel-himax-hx83102.c index 8b48bba18131..3644a7544b93 100644 --- a/drivers/gpu/drm/panel/panel-himax-hx83102.c +++ b/drivers/gpu/drm/panel/panel-himax-hx83102.c @@ -565,6 +565,8 @@ static int hx83102_get_modes(struct drm_panel *panel, struct drm_display_mode *mode; mode = drm_mode_duplicate(connector->dev, m); + if (!mode) + return -ENOMEM; mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; drm_mode_set_name(mode); diff --git a/drivers/gpu/drm/panel/panel-novatek-nt35950.c b/drivers/gpu/drm/panel/panel-novatek-nt35950.c index b036208f9356..08b22b592ab0 100644 --- a/drivers/gpu/drm/panel/panel-novatek-nt35950.c +++ b/drivers/gpu/drm/panel/panel-novatek-nt35950.c @@ -481,9 +481,9 @@ static int nt35950_probe(struct mipi_dsi_device *dsi) return dev_err_probe(dev, -EPROBE_DEFER, "Cannot get secondary DSI host\n"); nt->dsi[1] = mipi_dsi_device_register_full(dsi_r_host, info); - if (!nt->dsi[1]) { + if (IS_ERR(nt->dsi[1])) { dev_err(dev, "Cannot get secondary DSI node\n"); - return -ENODEV; + return PTR_ERR(nt->dsi[1]); } num_dsis++; } diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7701.c b/drivers/gpu/drm/panel/panel-sitronix-st7701.c index eef03d04e0cd..1f72ef7ca74c 100644 --- a/drivers/gpu/drm/panel/panel-sitronix-st7701.c +++ b/drivers/gpu/drm/panel/panel-sitronix-st7701.c @@ -1177,6 +1177,7 @@ static int st7701_probe(struct device *dev, int connector_type) return dev_err_probe(dev, ret, "Failed to get orientation\n"); drm_panel_init(&st7701->panel, dev, &st7701_funcs, connector_type); + st7701->panel.prepare_prev_first = true; /** * Once sleep out has been issued, ST7701 IC required to wait 120ms diff --git a/drivers/gpu/drm/panel/panel-synaptics-r63353.c b/drivers/gpu/drm/panel/panel-synaptics-r63353.c index 169c629746c7..17349825543f 100644 --- a/drivers/gpu/drm/panel/panel-synaptics-r63353.c +++ b/drivers/gpu/drm/panel/panel-synaptics-r63353.c @@ -325,7 +325,7 @@ static void r63353_panel_shutdown(struct mipi_dsi_device *dsi) { struct r63353_panel *rpanel = mipi_dsi_get_drvdata(dsi); - r63353_panel_unprepare(&rpanel->base); + drm_panel_unprepare(&rpanel->base); } static const struct r63353_desc sharp_ls068b3sx02_data = { diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 7ce25281c74c..57da84908752 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -1355,7 +1355,8 @@ EXPORT_SYMBOL(drm_sched_init); * drm_sched_backend_ops.run_job(). Consequently, drm_sched_backend_ops.free_job() * will not be called for all jobs still in drm_gpu_scheduler.pending_list. * There is no solution for this currently. Thus, it is up to the driver to make - * sure that + * sure that: + * * a) drm_sched_fini() is only called after for all submitted jobs * drm_sched_backend_ops.free_job() has been called or that * b) the jobs for which drm_sched_backend_ops.free_job() has not been called diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index ae6b337cdc54..f61a8ef38094 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -724,7 +724,7 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, new_mem->mem_type == XE_PL_SYSTEM) { long timeout = dma_resv_wait_timeout(ttm_bo->base.resv, DMA_RESV_USAGE_BOOKKEEP, - true, + false, MAX_SCHEDULE_TIMEOUT); if (timeout < 0) { ret = timeout; @@ -848,8 +848,16 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, out: if ((!ttm_bo->resource || ttm_bo->resource->mem_type == XE_PL_SYSTEM) && - ttm_bo->ttm) + ttm_bo->ttm) { + long timeout = dma_resv_wait_timeout(ttm_bo->base.resv, + DMA_RESV_USAGE_KERNEL, + false, + MAX_SCHEDULE_TIMEOUT); + if (timeout < 0) + ret = timeout; + xe_tt_unmap_sg(ttm_bo->ttm); + } return ret; } diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c index f8947e7e917e..21a50d539426 100644 --- a/drivers/gpu/drm/xe/xe_devcoredump.c +++ b/drivers/gpu/drm/xe/xe_devcoredump.c @@ -109,7 +109,11 @@ static ssize_t __xe_devcoredump_read(char *buffer, size_t count, drm_puts(&p, "\n**** GuC CT ****\n"); xe_guc_ct_snapshot_print(ss->guc.ct, &p); - drm_puts(&p, "\n**** Contexts ****\n"); + /* + * Don't add a new section header here because the mesa debug decoder + * tool expects the context information to be in the 'GuC CT' section. + */ + /* drm_puts(&p, "\n**** Contexts ****\n"); */ xe_guc_exec_queue_snapshot_print(ss->ge, &p); drm_puts(&p, "\n**** Job ****\n"); @@ -363,6 +367,15 @@ void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix, char buff[ASCII85_BUFSZ], *line_buff; size_t line_pos = 0; + /* + * Splitting blobs across multiple lines is not compatible with the mesa + * debug decoder tool. Note that even dropping the explicit '\n' below + * doesn't help because the GuC log is so big some underlying implementation + * still splits the lines at 512K characters. So just bail completely for + * the moment. + */ + return; + #define DMESG_MAX_LINE_LEN 800 #define MIN_SPACE (ASCII85_BUFSZ + 2) /* 85 + "\n\0" */ diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index fd0f3b3c9101..268cd3123be9 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -8,6 +8,7 @@ #include <linux/nospec.h> #include <drm/drm_device.h> +#include <drm/drm_drv.h> #include <drm/drm_file.h> #include <uapi/drm/xe_drm.h> @@ -762,9 +763,11 @@ bool xe_exec_queue_is_idle(struct xe_exec_queue *q) */ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q) { + struct xe_device *xe = gt_to_xe(q->gt); struct xe_file *xef; struct xe_lrc *lrc; u32 old_ts, new_ts; + int idx; /* * Jobs that are run during driver load may use an exec_queue, but are @@ -774,6 +777,10 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q) if (!q->vm || !q->vm->xef) return; + /* Synchronize with unbind while holding the xe file open */ + if (!drm_dev_enter(&xe->drm, &idx)) + return; + xef = q->vm->xef; /* @@ -787,6 +794,8 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q) lrc = q->lrc[0]; new_ts = xe_lrc_update_timestamp(lrc, &old_ts); xef->run_ticks[q->class] += (new_ts - old_ts) * q->width; + + drm_dev_exit(idx); } /** diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index d6744be01a68..94d468d01253 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -387,6 +387,10 @@ int xe_gt_init_early(struct xe_gt *gt) xe_force_wake_init_gt(gt, gt_to_fw(gt)); spin_lock_init(>->global_invl_lock); + err = xe_gt_tlb_invalidation_init_early(gt); + if (err) + return err; + return 0; } @@ -588,10 +592,6 @@ int xe_gt_init(struct xe_gt *gt) xe_hw_fence_irq_init(>->fence_irq[i]); } - err = xe_gt_tlb_invalidation_init(gt); - if (err) - return err; - err = xe_gt_pagefault_init(gt); if (err) return err; diff --git a/drivers/gpu/drm/xe/xe_gt_idle.c b/drivers/gpu/drm/xe/xe_gt_idle.c index fd80afeef56a..ffd3ba7f6656 100644 --- a/drivers/gpu/drm/xe/xe_gt_idle.c +++ b/drivers/gpu/drm/xe/xe_gt_idle.c @@ -122,10 +122,12 @@ void xe_gt_idle_enable_pg(struct xe_gt *gt) if (!xe_gt_is_media_type(gt)) gtidle->powergate_enable |= RENDER_POWERGATE_ENABLE; - for (i = XE_HW_ENGINE_VCS0, j = 0; i <= XE_HW_ENGINE_VCS7; ++i, ++j) { - if ((gt->info.engine_mask & BIT(i))) - gtidle->powergate_enable |= (VDN_HCP_POWERGATE_ENABLE(j) | - VDN_MFXVDENC_POWERGATE_ENABLE(j)); + if (xe->info.platform != XE_DG1) { + for (i = XE_HW_ENGINE_VCS0, j = 0; i <= XE_HW_ENGINE_VCS7; ++i, ++j) { + if ((gt->info.engine_mask & BIT(i))) + gtidle->powergate_enable |= (VDN_HCP_POWERGATE_ENABLE(j) | + VDN_MFXVDENC_POWERGATE_ENABLE(j)); + } } fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT); diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c index 192643d63d22..ca49860168f6 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c @@ -2046,7 +2046,7 @@ static int pf_validate_vf_config(struct xe_gt *gt, unsigned int vfid) valid_any = valid_any || (valid_ggtt && is_primary); if (IS_DGFX(xe)) { - bool valid_lmem = pf_get_vf_config_ggtt(primary_gt, vfid); + bool valid_lmem = pf_get_vf_config_lmem(primary_gt, vfid); valid_any = valid_any || (valid_lmem && is_primary); valid_all = valid_all && valid_lmem; diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c index 6146d1776bda..0a0af413770e 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c @@ -106,7 +106,7 @@ static void xe_gt_tlb_fence_timeout(struct work_struct *work) } /** - * xe_gt_tlb_invalidation_init - Initialize GT TLB invalidation state + * xe_gt_tlb_invalidation_init_early - Initialize GT TLB invalidation state * @gt: graphics tile * * Initialize GT TLB invalidation state, purely software initialization, should @@ -114,7 +114,7 @@ static void xe_gt_tlb_fence_timeout(struct work_struct *work) * * Return: 0 on success, negative error code on error. */ -int xe_gt_tlb_invalidation_init(struct xe_gt *gt) +int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt) { gt->tlb_invalidation.seqno = 1; INIT_LIST_HEAD(>->tlb_invalidation.pending_fences); diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h index 00b1c6c01e8d..672acfcdf0d7 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h @@ -14,7 +14,8 @@ struct xe_gt; struct xe_guc; struct xe_vma; -int xe_gt_tlb_invalidation_init(struct xe_gt *gt); +int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt); + void xe_gt_tlb_invalidation_reset(struct xe_gt *gt); int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt); int xe_gt_tlb_invalidation_vma(struct xe_gt *gt, diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c index 8dd55798ab31..5cc0f6f9bc11 100644 --- a/drivers/gpu/drm/xe/xe_oa.c +++ b/drivers/gpu/drm/xe/xe_oa.c @@ -74,12 +74,6 @@ struct xe_oa_config { struct rcu_head rcu; }; -struct flex { - struct xe_reg reg; - u32 offset; - u32 value; -}; - struct xe_oa_open_param { struct xe_file *xef; u32 oa_unit_id; @@ -596,19 +590,38 @@ static __poll_t xe_oa_poll(struct file *file, poll_table *wait) return ret; } +static void xe_oa_lock_vma(struct xe_exec_queue *q) +{ + if (q->vm) { + down_read(&q->vm->lock); + xe_vm_lock(q->vm, false); + } +} + +static void xe_oa_unlock_vma(struct xe_exec_queue *q) +{ + if (q->vm) { + xe_vm_unlock(q->vm); + up_read(&q->vm->lock); + } +} + static struct dma_fence *xe_oa_submit_bb(struct xe_oa_stream *stream, enum xe_oa_submit_deps deps, struct xe_bb *bb) { + struct xe_exec_queue *q = stream->exec_q ?: stream->k_exec_q; struct xe_sched_job *job; struct dma_fence *fence; int err = 0; - /* Kernel configuration is issued on stream->k_exec_q, not stream->exec_q */ - job = xe_bb_create_job(stream->k_exec_q, bb); + xe_oa_lock_vma(q); + + job = xe_bb_create_job(q, bb); if (IS_ERR(job)) { err = PTR_ERR(job); goto exit; } + job->ggtt = true; if (deps == XE_OA_SUBMIT_ADD_DEPS) { for (int i = 0; i < stream->num_syncs && !err; i++) @@ -623,10 +636,13 @@ static struct dma_fence *xe_oa_submit_bb(struct xe_oa_stream *stream, enum xe_oa fence = dma_fence_get(&job->drm.s_fence->finished); xe_sched_job_push(job); + xe_oa_unlock_vma(q); + return fence; err_put_job: xe_sched_job_put(job); exit: + xe_oa_unlock_vma(q); return ERR_PTR(err); } @@ -675,63 +691,19 @@ static void xe_oa_free_configs(struct xe_oa_stream *stream) dma_fence_put(stream->last_fence); } -static void xe_oa_store_flex(struct xe_oa_stream *stream, struct xe_lrc *lrc, - struct xe_bb *bb, const struct flex *flex, u32 count) -{ - u32 offset = xe_bo_ggtt_addr(lrc->bo); - - do { - bb->cs[bb->len++] = MI_STORE_DATA_IMM | MI_SDI_GGTT | MI_SDI_NUM_DW(1); - bb->cs[bb->len++] = offset + flex->offset * sizeof(u32); - bb->cs[bb->len++] = 0; - bb->cs[bb->len++] = flex->value; - - } while (flex++, --count); -} - -static int xe_oa_modify_ctx_image(struct xe_oa_stream *stream, struct xe_lrc *lrc, - const struct flex *flex, u32 count) -{ - struct dma_fence *fence; - struct xe_bb *bb; - int err; - - bb = xe_bb_new(stream->gt, 4 * count, false); - if (IS_ERR(bb)) { - err = PTR_ERR(bb); - goto exit; - } - - xe_oa_store_flex(stream, lrc, bb, flex, count); - - fence = xe_oa_submit_bb(stream, XE_OA_SUBMIT_NO_DEPS, bb); - if (IS_ERR(fence)) { - err = PTR_ERR(fence); - goto free_bb; - } - xe_bb_free(bb, fence); - dma_fence_put(fence); - - return 0; -free_bb: - xe_bb_free(bb, NULL); -exit: - return err; -} - -static int xe_oa_load_with_lri(struct xe_oa_stream *stream, struct xe_oa_reg *reg_lri) +static int xe_oa_load_with_lri(struct xe_oa_stream *stream, struct xe_oa_reg *reg_lri, u32 count) { struct dma_fence *fence; struct xe_bb *bb; int err; - bb = xe_bb_new(stream->gt, 3, false); + bb = xe_bb_new(stream->gt, 2 * count + 1, false); if (IS_ERR(bb)) { err = PTR_ERR(bb); goto exit; } - write_cs_mi_lri(bb, reg_lri, 1); + write_cs_mi_lri(bb, reg_lri, count); fence = xe_oa_submit_bb(stream, XE_OA_SUBMIT_NO_DEPS, bb); if (IS_ERR(fence)) { @@ -751,71 +723,55 @@ exit: static int xe_oa_configure_oar_context(struct xe_oa_stream *stream, bool enable) { const struct xe_oa_format *format = stream->oa_buffer.format; - struct xe_lrc *lrc = stream->exec_q->lrc[0]; - u32 regs_offset = xe_lrc_regs_offset(lrc) / sizeof(u32); u32 oacontrol = __format_to_oactrl(format, OAR_OACONTROL_COUNTER_SEL_MASK) | (enable ? OAR_OACONTROL_COUNTER_ENABLE : 0); - struct flex regs_context[] = { + struct xe_oa_reg reg_lri[] = { { OACTXCONTROL(stream->hwe->mmio_base), - stream->oa->ctx_oactxctrl_offset[stream->hwe->class] + 1, enable ? OA_COUNTER_RESUME : 0, }, { + OAR_OACONTROL, + oacontrol, + }, + { RING_CONTEXT_CONTROL(stream->hwe->mmio_base), - regs_offset + CTX_CONTEXT_CONTROL, - _MASKED_BIT_ENABLE(CTX_CTRL_OAC_CONTEXT_ENABLE), + _MASKED_FIELD(CTX_CTRL_OAC_CONTEXT_ENABLE, + enable ? CTX_CTRL_OAC_CONTEXT_ENABLE : 0) }, }; - struct xe_oa_reg reg_lri = { OAR_OACONTROL, oacontrol }; - int err; - - /* Modify stream hwe context image with regs_context */ - err = xe_oa_modify_ctx_image(stream, stream->exec_q->lrc[0], - regs_context, ARRAY_SIZE(regs_context)); - if (err) - return err; - /* Apply reg_lri using LRI */ - return xe_oa_load_with_lri(stream, ®_lri); + return xe_oa_load_with_lri(stream, reg_lri, ARRAY_SIZE(reg_lri)); } static int xe_oa_configure_oac_context(struct xe_oa_stream *stream, bool enable) { const struct xe_oa_format *format = stream->oa_buffer.format; - struct xe_lrc *lrc = stream->exec_q->lrc[0]; - u32 regs_offset = xe_lrc_regs_offset(lrc) / sizeof(u32); u32 oacontrol = __format_to_oactrl(format, OAR_OACONTROL_COUNTER_SEL_MASK) | (enable ? OAR_OACONTROL_COUNTER_ENABLE : 0); - struct flex regs_context[] = { + struct xe_oa_reg reg_lri[] = { { OACTXCONTROL(stream->hwe->mmio_base), - stream->oa->ctx_oactxctrl_offset[stream->hwe->class] + 1, enable ? OA_COUNTER_RESUME : 0, }, { + OAC_OACONTROL, + oacontrol + }, + { RING_CONTEXT_CONTROL(stream->hwe->mmio_base), - regs_offset + CTX_CONTEXT_CONTROL, - _MASKED_BIT_ENABLE(CTX_CTRL_OAC_CONTEXT_ENABLE) | + _MASKED_FIELD(CTX_CTRL_OAC_CONTEXT_ENABLE, + enable ? CTX_CTRL_OAC_CONTEXT_ENABLE : 0) | _MASKED_FIELD(CTX_CTRL_RUN_ALONE, enable ? CTX_CTRL_RUN_ALONE : 0), }, }; - struct xe_oa_reg reg_lri = { OAC_OACONTROL, oacontrol }; - int err; /* Set ccs select to enable programming of OAC_OACONTROL */ xe_mmio_write32(&stream->gt->mmio, __oa_regs(stream)->oa_ctrl, __oa_ccs_select(stream)); - /* Modify stream hwe context image with regs_context */ - err = xe_oa_modify_ctx_image(stream, stream->exec_q->lrc[0], - regs_context, ARRAY_SIZE(regs_context)); - if (err) - return err; - - /* Apply reg_lri using LRI */ - return xe_oa_load_with_lri(stream, ®_lri); + return xe_oa_load_with_lri(stream, reg_lri, ARRAY_SIZE(reg_lri)); } static int xe_oa_configure_oa_context(struct xe_oa_stream *stream, bool enable) @@ -2066,8 +2022,8 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f if (XE_IOCTL_DBG(oa->xe, !param.exec_q)) return -ENOENT; - if (param.exec_q->width > 1) - drm_dbg(&oa->xe->drm, "exec_q->width > 1, programming only exec_q->lrc[0]\n"); + if (XE_IOCTL_DBG(oa->xe, param.exec_q->width > 1)) + return -EOPNOTSUPP; } /* diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c index 0be4f489d3e1..9f327f27c072 100644 --- a/drivers/gpu/drm/xe/xe_ring_ops.c +++ b/drivers/gpu/drm/xe/xe_ring_ops.c @@ -221,7 +221,10 @@ static int emit_pipe_imm_ggtt(u32 addr, u32 value, bool stall_only, u32 *dw, static u32 get_ppgtt_flag(struct xe_sched_job *job) { - return job->q->vm ? BIT(8) : 0; + if (job->q->vm && !job->ggtt) + return BIT(8); + + return 0; } static int emit_copy_timestamp(struct xe_lrc *lrc, u32 *dw, int i) diff --git a/drivers/gpu/drm/xe/xe_sched_job_types.h b/drivers/gpu/drm/xe/xe_sched_job_types.h index f13f333f00be..d942b20a9f29 100644 --- a/drivers/gpu/drm/xe/xe_sched_job_types.h +++ b/drivers/gpu/drm/xe/xe_sched_job_types.h @@ -56,6 +56,8 @@ struct xe_sched_job { u32 migrate_flush_flags; /** @ring_ops_flush_tlb: The ring ops need to flush TLB before payload. */ bool ring_ops_flush_tlb; + /** @ggtt: mapped in ggtt. */ + bool ggtt; /** @ptrs: per instance pointers. */ struct xe_job_ptrs ptrs[]; }; diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index c38dcdfcb914..a99112e6f0b8 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -756,7 +756,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size, * adding succeeded, it is ok to proceed even if the memory was * not onlined in time. */ - wait_for_completion_timeout(&dm_device.ol_waitevent, 5 * HZ); + wait_for_completion_timeout(&dm_device.ol_waitevent, secs_to_jiffies(5)); post_status(&dm_device); } } @@ -1373,7 +1373,8 @@ static int dm_thread_func(void *dm_dev) struct hv_dynmem_device *dm = dm_dev; while (!kthread_should_stop()) { - wait_for_completion_interruptible_timeout(&dm_device.config_event, 1 * HZ); + wait_for_completion_interruptible_timeout(&dm_device.config_event, + secs_to_jiffies(1)); /* * The host expects us to post information on the memory * pressure every second. @@ -1748,7 +1749,7 @@ static int balloon_connect_vsp(struct hv_device *dev) if (ret) goto out; - t = wait_for_completion_timeout(&dm_device.host_event, 5 * HZ); + t = wait_for_completion_timeout(&dm_device.host_event, secs_to_jiffies(5)); if (t == 0) { ret = -ETIMEDOUT; goto out; @@ -1806,7 +1807,7 @@ static int balloon_connect_vsp(struct hv_device *dev) if (ret) goto out; - t = wait_for_completion_timeout(&dm_device.host_event, 5 * HZ); + t = wait_for_completion_timeout(&dm_device.host_event, secs_to_jiffies(5)); if (t == 0) { ret = -ETIMEDOUT; goto out; diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c index d35b60c06114..7400a5a4d2bd 100644 --- a/drivers/hv/hv_kvp.c +++ b/drivers/hv/hv_kvp.c @@ -655,7 +655,7 @@ void hv_kvp_onchannelcallback(void *context) if (host_negotiatied == NEGO_NOT_STARTED) { host_negotiatied = NEGO_IN_PROGRESS; schedule_delayed_work(&kvp_host_handshake_work, - HV_UTIL_NEGO_TIMEOUT * HZ); + secs_to_jiffies(HV_UTIL_NEGO_TIMEOUT)); } return; } @@ -724,7 +724,7 @@ void hv_kvp_onchannelcallback(void *context) */ schedule_work(&kvp_sendkey_work); schedule_delayed_work(&kvp_timeout_work, - HV_UTIL_TIMEOUT * HZ); + secs_to_jiffies(HV_UTIL_TIMEOUT)); return; @@ -767,6 +767,12 @@ hv_kvp_init(struct hv_util_service *srv) */ kvp_transaction.state = HVUTIL_DEVICE_INIT; + return 0; +} + +int +hv_kvp_init_transport(void) +{ hvt = hvutil_transport_init(kvp_devname, CN_KVP_IDX, CN_KVP_VAL, kvp_on_msg, kvp_on_reset); if (!hvt) diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c index 0d2184be1691..bde637a96c37 100644 --- a/drivers/hv/hv_snapshot.c +++ b/drivers/hv/hv_snapshot.c @@ -193,7 +193,8 @@ static void vss_send_op(void) vss_transaction.state = HVUTIL_USERSPACE_REQ; schedule_delayed_work(&vss_timeout_work, op == VSS_OP_FREEZE ? - VSS_FREEZE_TIMEOUT * HZ : HV_UTIL_TIMEOUT * HZ); + secs_to_jiffies(VSS_FREEZE_TIMEOUT) : + secs_to_jiffies(HV_UTIL_TIMEOUT)); rc = hvutil_transport_send(hvt, vss_msg, sizeof(*vss_msg), NULL); if (rc) { @@ -388,6 +389,12 @@ hv_vss_init(struct hv_util_service *srv) */ vss_transaction.state = HVUTIL_DEVICE_INIT; + return 0; +} + +int +hv_vss_init_transport(void) +{ hvt = hvutil_transport_init(vss_devname, CN_VSS_IDX, CN_VSS_VAL, vss_on_msg, vss_on_reset); if (!hvt) { diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c index c4f525325790..36ee89c0358b 100644 --- a/drivers/hv/hv_util.c +++ b/drivers/hv/hv_util.c @@ -141,6 +141,7 @@ static struct hv_util_service util_heartbeat = { static struct hv_util_service util_kvp = { .util_cb = hv_kvp_onchannelcallback, .util_init = hv_kvp_init, + .util_init_transport = hv_kvp_init_transport, .util_pre_suspend = hv_kvp_pre_suspend, .util_pre_resume = hv_kvp_pre_resume, .util_deinit = hv_kvp_deinit, @@ -149,6 +150,7 @@ static struct hv_util_service util_kvp = { static struct hv_util_service util_vss = { .util_cb = hv_vss_onchannelcallback, .util_init = hv_vss_init, + .util_init_transport = hv_vss_init_transport, .util_pre_suspend = hv_vss_pre_suspend, .util_pre_resume = hv_vss_pre_resume, .util_deinit = hv_vss_deinit, @@ -590,10 +592,8 @@ static int util_probe(struct hv_device *dev, srv->channel = dev->channel; if (srv->util_init) { ret = srv->util_init(srv); - if (ret) { - ret = -ENODEV; + if (ret) goto error1; - } } /* @@ -613,6 +613,13 @@ static int util_probe(struct hv_device *dev, if (ret) goto error; + if (srv->util_init_transport) { + ret = srv->util_init_transport(); + if (ret) { + vmbus_close(dev->channel); + goto error; + } + } return 0; error: diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index d2856023d53c..52cb744b4d7f 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -370,12 +370,14 @@ void vmbus_on_event(unsigned long data); void vmbus_on_msg_dpc(unsigned long data); int hv_kvp_init(struct hv_util_service *srv); +int hv_kvp_init_transport(void); void hv_kvp_deinit(void); int hv_kvp_pre_suspend(void); int hv_kvp_pre_resume(void); void hv_kvp_onchannelcallback(void *context); int hv_vss_init(struct hv_util_service *srv); +int hv_vss_init_transport(void); void hv_vss_deinit(void); int hv_vss_pre_suspend(void); int hv_vss_pre_resume(void); diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 6d89d37b069a..2892b8da20a5 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -2507,7 +2507,7 @@ static int vmbus_bus_resume(struct device *dev) vmbus_request_offers(); if (wait_for_completion_timeout( - &vmbus_connection.ready_for_resume_event, 10 * HZ) == 0) + &vmbus_connection.ready_for_resume_event, secs_to_jiffies(10)) == 0) pr_err("Some vmbus device is missing after suspending?\n"); /* Reset the event for the next suspend. */ diff --git a/drivers/hwmon/drivetemp.c b/drivers/hwmon/drivetemp.c index 6bdd21aa005a..2a4ec55ddb47 100644 --- a/drivers/hwmon/drivetemp.c +++ b/drivers/hwmon/drivetemp.c @@ -165,6 +165,7 @@ static int drivetemp_scsi_command(struct drivetemp_data *st, { u8 scsi_cmd[MAX_COMMAND_SIZE]; enum req_op op; + int err; memset(scsi_cmd, 0, sizeof(scsi_cmd)); scsi_cmd[0] = ATA_16; @@ -192,8 +193,11 @@ static int drivetemp_scsi_command(struct drivetemp_data *st, scsi_cmd[12] = lba_high; scsi_cmd[14] = ata_command; - return scsi_execute_cmd(st->sdev, scsi_cmd, op, st->smartdata, - ATA_SECT_SIZE, HZ, 5, NULL); + err = scsi_execute_cmd(st->sdev, scsi_cmd, op, st->smartdata, + ATA_SECT_SIZE, HZ, 5, NULL); + if (err > 0) + err = -EIO; + return err; } static int drivetemp_ata_command(struct drivetemp_data *st, u8 feature, diff --git a/drivers/hwmon/tmp513.c b/drivers/hwmon/tmp513.c index 926d28cd3fab..1c2cb12071b8 100644 --- a/drivers/hwmon/tmp513.c +++ b/drivers/hwmon/tmp513.c @@ -182,7 +182,7 @@ struct tmp51x_data { struct regmap *regmap; }; -// Set the shift based on the gain 8=4, 4=3, 2=2, 1=1 +// Set the shift based on the gain: 8 -> 1, 4 -> 2, 2 -> 3, 1 -> 4 static inline u8 tmp51x_get_pga_shift(struct tmp51x_data *data) { return 5 - ffs(data->pga_gain); @@ -204,7 +204,9 @@ static int tmp51x_get_value(struct tmp51x_data *data, u8 reg, u8 pos, * 2's complement number shifted by one to four depending * on the pga gain setting. 1lsb = 10uV */ - *val = sign_extend32(regval, 17 - tmp51x_get_pga_shift(data)); + *val = sign_extend32(regval, + reg == TMP51X_SHUNT_CURRENT_RESULT ? + 16 - tmp51x_get_pga_shift(data) : 15); *val = DIV_ROUND_CLOSEST(*val * 10 * MILLI, data->shunt_uohms); break; case TMP51X_BUS_VOLTAGE_RESULT: @@ -220,7 +222,7 @@ static int tmp51x_get_value(struct tmp51x_data *data, u8 reg, u8 pos, break; case TMP51X_BUS_CURRENT_RESULT: // Current = (ShuntVoltage * CalibrationRegister) / 4096 - *val = sign_extend32(regval, 16) * data->curr_lsb_ua; + *val = sign_extend32(regval, 15) * (long)data->curr_lsb_ua; *val = DIV_ROUND_CLOSEST(*val, MILLI); break; case TMP51X_LOCAL_TEMP_RESULT: @@ -232,7 +234,7 @@ static int tmp51x_get_value(struct tmp51x_data *data, u8 reg, u8 pos, case TMP51X_REMOTE_TEMP_LIMIT_2: case TMP513_REMOTE_TEMP_LIMIT_3: // 1lsb = 0.0625 degrees centigrade - *val = sign_extend32(regval, 16) >> TMP51X_TEMP_SHIFT; + *val = sign_extend32(regval, 15) >> TMP51X_TEMP_SHIFT; *val = DIV_ROUND_CLOSEST(*val * 625, 10); break; case TMP51X_N_FACTOR_AND_HYST_1: diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index f751d231ded8..5c9a8dfbc4a0 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -335,6 +335,7 @@ static const struct of_device_id i2c_imx_dt_ids[] = { { .compatible = "fsl,imx6sll-i2c", .data = &imx6_i2c_hwdata, }, { .compatible = "fsl,imx6sx-i2c", .data = &imx6_i2c_hwdata, }, { .compatible = "fsl,imx6ul-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx7d-i2c", .data = &imx6_i2c_hwdata, }, { .compatible = "fsl,imx7s-i2c", .data = &imx6_i2c_hwdata, }, { .compatible = "fsl,imx8mm-i2c", .data = &imx6_i2c_hwdata, }, { .compatible = "fsl,imx8mn-i2c", .data = &imx6_i2c_hwdata, }, @@ -532,22 +533,20 @@ static void i2c_imx_dma_free(struct imx_i2c_struct *i2c_imx) static int i2c_imx_bus_busy(struct imx_i2c_struct *i2c_imx, int for_busy, bool atomic) { + bool multi_master = i2c_imx->multi_master; unsigned long orig_jiffies = jiffies; unsigned int temp; - if (!i2c_imx->multi_master) - return 0; - while (1) { temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2SR); /* check for arbitration lost */ - if (temp & I2SR_IAL) { + if (multi_master && (temp & I2SR_IAL)) { i2c_imx_clear_irq(i2c_imx, I2SR_IAL); return -EAGAIN; } - if (for_busy && (temp & I2SR_IBB)) { + if (for_busy && (!multi_master || (temp & I2SR_IBB))) { i2c_imx->stopped = 0; break; } diff --git a/drivers/i2c/busses/i2c-microchip-corei2c.c b/drivers/i2c/busses/i2c-microchip-corei2c.c index d1543e7d8380..5db73429125c 100644 --- a/drivers/i2c/busses/i2c-microchip-corei2c.c +++ b/drivers/i2c/busses/i2c-microchip-corei2c.c @@ -93,27 +93,35 @@ * @base: pointer to register struct * @dev: device reference * @i2c_clk: clock reference for i2c input clock + * @msg_queue: pointer to the messages requiring sending * @buf: pointer to msg buffer for easier use * @msg_complete: xfer completion object * @adapter: core i2c abstraction * @msg_err: error code for completed message * @bus_clk_rate: current i2c bus clock rate * @isr_status: cached copy of local ISR status + * @total_num: total number of messages to be sent/received + * @current_num: index of the current message being sent/received * @msg_len: number of bytes transferred in msg * @addr: address of the current slave + * @restart_needed: whether or not a repeated start is required after current message */ struct mchp_corei2c_dev { void __iomem *base; struct device *dev; struct clk *i2c_clk; + struct i2c_msg *msg_queue; u8 *buf; struct completion msg_complete; struct i2c_adapter adapter; int msg_err; + int total_num; + int current_num; u32 bus_clk_rate; u32 isr_status; u16 msg_len; u8 addr; + bool restart_needed; }; static void mchp_corei2c_core_disable(struct mchp_corei2c_dev *idev) @@ -222,6 +230,47 @@ static int mchp_corei2c_fill_tx(struct mchp_corei2c_dev *idev) return 0; } +static void mchp_corei2c_next_msg(struct mchp_corei2c_dev *idev) +{ + struct i2c_msg *this_msg; + u8 ctrl; + + if (idev->current_num >= idev->total_num) { + complete(&idev->msg_complete); + return; + } + + /* + * If there's been an error, the isr needs to return control + * to the "main" part of the driver, so as not to keep sending + * messages once it completes and clears the SI bit. + */ + if (idev->msg_err) { + complete(&idev->msg_complete); + return; + } + + this_msg = idev->msg_queue++; + + if (idev->current_num < (idev->total_num - 1)) { + struct i2c_msg *next_msg = idev->msg_queue; + + idev->restart_needed = next_msg->flags & I2C_M_RD; + } else { + idev->restart_needed = false; + } + + idev->addr = i2c_8bit_addr_from_msg(this_msg); + idev->msg_len = this_msg->len; + idev->buf = this_msg->buf; + + ctrl = readb(idev->base + CORE_I2C_CTRL); + ctrl |= CTRL_STA; + writeb(ctrl, idev->base + CORE_I2C_CTRL); + + idev->current_num++; +} + static irqreturn_t mchp_corei2c_handle_isr(struct mchp_corei2c_dev *idev) { u32 status = idev->isr_status; @@ -238,8 +287,6 @@ static irqreturn_t mchp_corei2c_handle_isr(struct mchp_corei2c_dev *idev) ctrl &= ~CTRL_STA; writeb(idev->addr, idev->base + CORE_I2C_DATA); writeb(ctrl, idev->base + CORE_I2C_CTRL); - if (idev->msg_len == 0) - finished = true; break; case STATUS_M_ARB_LOST: idev->msg_err = -EAGAIN; @@ -247,10 +294,14 @@ static irqreturn_t mchp_corei2c_handle_isr(struct mchp_corei2c_dev *idev) break; case STATUS_M_SLAW_ACK: case STATUS_M_TX_DATA_ACK: - if (idev->msg_len > 0) + if (idev->msg_len > 0) { mchp_corei2c_fill_tx(idev); - else - last_byte = true; + } else { + if (idev->restart_needed) + finished = true; + else + last_byte = true; + } break; case STATUS_M_TX_DATA_NACK: case STATUS_M_SLAR_NACK: @@ -287,7 +338,7 @@ static irqreturn_t mchp_corei2c_handle_isr(struct mchp_corei2c_dev *idev) mchp_corei2c_stop(idev); if (last_byte || finished) - complete(&idev->msg_complete); + mchp_corei2c_next_msg(idev); return IRQ_HANDLED; } @@ -311,21 +362,48 @@ static irqreturn_t mchp_corei2c_isr(int irq, void *_dev) return ret; } -static int mchp_corei2c_xfer_msg(struct mchp_corei2c_dev *idev, - struct i2c_msg *msg) +static int mchp_corei2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, + int num) { - u8 ctrl; + struct mchp_corei2c_dev *idev = i2c_get_adapdata(adap); + struct i2c_msg *this_msg = msgs; unsigned long time_left; + u8 ctrl; + + mchp_corei2c_core_enable(idev); + + /* + * The isr controls the flow of a transfer, this info needs to be saved + * to a location that it can access the queue information from. + */ + idev->restart_needed = false; + idev->msg_queue = msgs; + idev->total_num = num; + idev->current_num = 0; - idev->addr = i2c_8bit_addr_from_msg(msg); - idev->msg_len = msg->len; - idev->buf = msg->buf; + /* + * But the first entry to the isr is triggered by the start in this + * function, so the first message needs to be "dequeued". + */ + idev->addr = i2c_8bit_addr_from_msg(this_msg); + idev->msg_len = this_msg->len; + idev->buf = this_msg->buf; idev->msg_err = 0; - reinit_completion(&idev->msg_complete); + if (idev->total_num > 1) { + struct i2c_msg *next_msg = msgs + 1; - mchp_corei2c_core_enable(idev); + idev->restart_needed = next_msg->flags & I2C_M_RD; + } + idev->current_num++; + idev->msg_queue++; + + reinit_completion(&idev->msg_complete); + + /* + * Send the first start to pass control to the isr + */ ctrl = readb(idev->base + CORE_I2C_CTRL); ctrl |= CTRL_STA; writeb(ctrl, idev->base + CORE_I2C_CTRL); @@ -335,20 +413,8 @@ static int mchp_corei2c_xfer_msg(struct mchp_corei2c_dev *idev, if (!time_left) return -ETIMEDOUT; - return idev->msg_err; -} - -static int mchp_corei2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, - int num) -{ - struct mchp_corei2c_dev *idev = i2c_get_adapdata(adap); - int i, ret; - - for (i = 0; i < num; i++) { - ret = mchp_corei2c_xfer_msg(idev, msgs++); - if (ret) - return ret; - } + if (idev->msg_err) + return idev->msg_err; return num; } diff --git a/drivers/iio/adc/ad4695.c b/drivers/iio/adc/ad4695.c index 595ec4158e73..0146aed9069f 100644 --- a/drivers/iio/adc/ad4695.c +++ b/drivers/iio/adc/ad4695.c @@ -91,6 +91,7 @@ #define AD4695_T_WAKEUP_SW_MS 3 #define AD4695_T_REFBUF_MS 100 #define AD4695_T_REGCONFIG_NS 20 +#define AD4695_T_SCK_CNV_DELAY_NS 80 #define AD4695_REG_ACCESS_SCLK_HZ (10 * MEGA) /* Max number of voltage input channels. */ @@ -132,8 +133,13 @@ struct ad4695_state { unsigned int vref_mv; /* Common mode input pin voltage. */ unsigned int com_mv; - /* 1 per voltage and temperature chan plus 1 xfer to trigger 1st CNV */ - struct spi_transfer buf_read_xfer[AD4695_MAX_CHANNELS + 2]; + /* + * 2 per voltage and temperature chan plus 1 xfer to trigger 1st + * CNV. Excluding the trigger xfer, every 2nd xfer only serves + * to control CS and add a delay between the last SCLK and next + * CNV rising edges. + */ + struct spi_transfer buf_read_xfer[AD4695_MAX_CHANNELS * 2 + 3]; struct spi_message buf_read_msg; /* Raw conversion data received. */ u8 buf[ALIGN((AD4695_MAX_CHANNELS + 2) * AD4695_MAX_CHANNEL_SIZE, @@ -423,7 +429,7 @@ static int ad4695_buffer_preenable(struct iio_dev *indio_dev) u8 temp_chan_bit = st->chip_info->num_voltage_inputs; u32 bit, num_xfer, num_slots; u32 temp_en = 0; - int ret; + int ret, rx_buf_offset = 0; /* * We are using the advanced sequencer since it is the only way to read @@ -449,11 +455,9 @@ static int ad4695_buffer_preenable(struct iio_dev *indio_dev) iio_for_each_active_channel(indio_dev, bit) { xfer = &st->buf_read_xfer[num_xfer]; xfer->bits_per_word = 16; - xfer->rx_buf = &st->buf[(num_xfer - 1) * 2]; + xfer->rx_buf = &st->buf[rx_buf_offset]; xfer->len = 2; - xfer->cs_change = 1; - xfer->cs_change_delay.value = AD4695_T_CONVERT_NS; - xfer->cs_change_delay.unit = SPI_DELAY_UNIT_NSECS; + rx_buf_offset += xfer->len; if (bit == temp_chan_bit) { temp_en = 1; @@ -468,21 +472,44 @@ static int ad4695_buffer_preenable(struct iio_dev *indio_dev) } num_xfer++; + + /* + * We need to add a blank xfer in data reads, to meet the timing + * requirement of a minimum delay between the last SCLK rising + * edge and the CS deassert. + */ + xfer = &st->buf_read_xfer[num_xfer]; + xfer->delay.value = AD4695_T_SCK_CNV_DELAY_NS; + xfer->delay.unit = SPI_DELAY_UNIT_NSECS; + xfer->cs_change = 1; + xfer->cs_change_delay.value = AD4695_T_CONVERT_NS; + xfer->cs_change_delay.unit = SPI_DELAY_UNIT_NSECS; + + num_xfer++; } /* * The advanced sequencer requires that at least 2 slots are enabled. * Since slot 0 is always used for other purposes, we need only 1 - * enabled voltage channel to meet this requirement. If the temperature - * channel is the only enabled channel, we need to add one more slot - * in the sequence but not read from it. + * enabled voltage channel to meet this requirement. If the temperature + * channel is the only enabled channel, we need to add one more slot in + * the sequence but not read from it. This is because the temperature + * sensor is sampled at the end of the channel sequence in advanced + * sequencer mode (see datasheet page 38). + * + * From the iio_for_each_active_channel() block above, we now have an + * xfer with data followed by a blank xfer to allow us to meet the + * timing spec, so move both of those up before adding an extra to + * handle the temperature-only case. */ if (num_slots < 2) { - /* move last xfer so we can insert one more xfer before it */ - st->buf_read_xfer[num_xfer] = *xfer; + /* Move last two xfers */ + st->buf_read_xfer[num_xfer] = st->buf_read_xfer[num_xfer - 1]; + st->buf_read_xfer[num_xfer - 1] = st->buf_read_xfer[num_xfer - 2]; num_xfer++; - /* modify 2nd to last xfer for extra slot */ + /* Modify inserted xfer for extra slot. */ + xfer = &st->buf_read_xfer[num_xfer - 3]; memset(xfer, 0, sizeof(*xfer)); xfer->cs_change = 1; xfer->delay.value = st->chip_info->t_acq_ns; @@ -499,6 +526,12 @@ static int ad4695_buffer_preenable(struct iio_dev *indio_dev) return ret; num_slots++; + + /* + * We still want to point at the last xfer when finished, so + * update the pointer. + */ + xfer = &st->buf_read_xfer[num_xfer - 1]; } /* @@ -583,8 +616,20 @@ out: */ static int ad4695_read_one_sample(struct ad4695_state *st, unsigned int address) { - struct spi_transfer xfer[2] = { }; - int ret, i = 0; + struct spi_transfer xfers[2] = { + { + .speed_hz = AD4695_REG_ACCESS_SCLK_HZ, + .bits_per_word = 16, + .tx_buf = &st->cnv_cmd, + .len = 2, + }, + { + /* Required delay between last SCLK and CNV/CS */ + .delay.value = AD4695_T_SCK_CNV_DELAY_NS, + .delay.unit = SPI_DELAY_UNIT_NSECS, + } + }; + int ret; ret = ad4695_set_single_cycle_mode(st, address); if (ret) @@ -592,29 +637,22 @@ static int ad4695_read_one_sample(struct ad4695_state *st, unsigned int address) /* * Setting the first channel to the temperature channel isn't supported - * in single-cycle mode, so we have to do an extra xfer to read the - * temperature. + * in single-cycle mode, so we have to do an extra conversion to read + * the temperature. */ if (address == AD4695_CMD_TEMP_CHAN) { - /* We aren't reading, so we can make this a short xfer. */ - st->cnv_cmd2 = AD4695_CMD_TEMP_CHAN << 3; - xfer[0].tx_buf = &st->cnv_cmd2; - xfer[0].len = 1; - xfer[0].cs_change = 1; - xfer[0].cs_change_delay.value = AD4695_T_CONVERT_NS; - xfer[0].cs_change_delay.unit = SPI_DELAY_UNIT_NSECS; - - i = 1; + st->cnv_cmd = AD4695_CMD_TEMP_CHAN << 11; + + ret = spi_sync_transfer(st->spi, xfers, ARRAY_SIZE(xfers)); + if (ret) + return ret; } /* Then read the result and exit conversion mode. */ st->cnv_cmd = AD4695_CMD_EXIT_CNV_MODE << 11; - xfer[i].bits_per_word = 16; - xfer[i].tx_buf = &st->cnv_cmd; - xfer[i].rx_buf = &st->raw_data; - xfer[i].len = 2; + xfers[0].rx_buf = &st->raw_data; - return spi_sync_transfer(st->spi, xfer, i + 1); + return spi_sync_transfer(st->spi, xfers, ARRAY_SIZE(xfers)); } static int ad4695_read_raw(struct iio_dev *indio_dev, diff --git a/drivers/iio/adc/ad7124.c b/drivers/iio/adc/ad7124.c index 7314fb32bdec..3d678c420cbf 100644 --- a/drivers/iio/adc/ad7124.c +++ b/drivers/iio/adc/ad7124.c @@ -917,6 +917,9 @@ static int ad7124_setup(struct ad7124_state *st) * set all channels to this default value. */ ad7124_set_channel_odr(st, i, 10); + + /* Disable all channels to prevent unintended conversions. */ + ad_sd_write_reg(&st->sd, AD7124_CHANNEL(i), 2, 0); } ret = ad_sd_write_reg(&st->sd, AD7124_ADC_CONTROL, 2, st->adc_control); diff --git a/drivers/iio/adc/ad7173.c b/drivers/iio/adc/ad7173.c index 8a0c931ca83a..8b03c1e5567e 100644 --- a/drivers/iio/adc/ad7173.c +++ b/drivers/iio/adc/ad7173.c @@ -200,6 +200,7 @@ struct ad7173_channel { struct ad7173_state { struct ad_sigma_delta sd; + struct ad_sigma_delta_info sigma_delta_info; const struct ad7173_device_info *info; struct ad7173_channel *channels; struct regulator_bulk_data regulators[3]; @@ -753,7 +754,7 @@ static int ad7173_disable_one(struct ad_sigma_delta *sd, unsigned int chan) return ad_sd_write_reg(sd, AD7173_REG_CH(chan), 2, 0); } -static struct ad_sigma_delta_info ad7173_sigma_delta_info = { +static const struct ad_sigma_delta_info ad7173_sigma_delta_info = { .set_channel = ad7173_set_channel, .append_status = ad7173_append_status, .disable_all = ad7173_disable_all, @@ -1403,7 +1404,7 @@ static int ad7173_fw_parse_device_config(struct iio_dev *indio_dev) if (ret < 0) return dev_err_probe(dev, ret, "Interrupt 'rdy' is required\n"); - ad7173_sigma_delta_info.irq_line = ret; + st->sigma_delta_info.irq_line = ret; return ad7173_fw_parse_channel_config(indio_dev); } @@ -1436,8 +1437,9 @@ static int ad7173_probe(struct spi_device *spi) spi->mode = SPI_MODE_3; spi_setup(spi); - ad7173_sigma_delta_info.num_slots = st->info->num_configs; - ret = ad_sd_init(&st->sd, indio_dev, spi, &ad7173_sigma_delta_info); + st->sigma_delta_info = ad7173_sigma_delta_info; + st->sigma_delta_info.num_slots = st->info->num_configs; + ret = ad_sd_init(&st->sd, indio_dev, spi, &st->sigma_delta_info); if (ret) return ret; diff --git a/drivers/iio/adc/ad9467.c b/drivers/iio/adc/ad9467.c index d358958ab310..f30119b42ba0 100644 --- a/drivers/iio/adc/ad9467.c +++ b/drivers/iio/adc/ad9467.c @@ -895,7 +895,7 @@ static int ad9467_update_scan_mode(struct iio_dev *indio_dev, return 0; } -static struct iio_info ad9467_info = { +static const struct iio_info ad9467_info = { .read_raw = ad9467_read_raw, .write_raw = ad9467_write_raw, .update_scan_mode = ad9467_update_scan_mode, @@ -903,6 +903,14 @@ static struct iio_info ad9467_info = { .read_avail = ad9467_read_avail, }; +/* Same as above, but without .read_avail */ +static const struct iio_info ad9467_info_no_read_avail = { + .read_raw = ad9467_read_raw, + .write_raw = ad9467_write_raw, + .update_scan_mode = ad9467_update_scan_mode, + .debugfs_reg_access = ad9467_reg_access, +}; + static int ad9467_scale_fill(struct ad9467_state *st) { const struct ad9467_chip_info *info = st->info; @@ -1214,11 +1222,12 @@ static int ad9467_probe(struct spi_device *spi) } if (st->info->num_scales > 1) - ad9467_info.read_avail = ad9467_read_avail; + indio_dev->info = &ad9467_info; + else + indio_dev->info = &ad9467_info_no_read_avail; indio_dev->name = st->info->name; indio_dev->channels = st->info->channels; indio_dev->num_channels = st->info->num_channels; - indio_dev->info = &ad9467_info; ret = ad9467_iio_backend_get(st); if (ret) diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c index a3f0a2321666..5927756b749a 100644 --- a/drivers/iio/adc/at91_adc.c +++ b/drivers/iio/adc/at91_adc.c @@ -979,7 +979,7 @@ static int at91_ts_register(struct iio_dev *idev, return ret; err: - input_free_device(st->ts_input); + input_free_device(input); return ret; } diff --git a/drivers/iio/adc/rockchip_saradc.c b/drivers/iio/adc/rockchip_saradc.c index 240cfa391674..dfd47a6e1f4a 100644 --- a/drivers/iio/adc/rockchip_saradc.c +++ b/drivers/iio/adc/rockchip_saradc.c @@ -368,6 +368,8 @@ static irqreturn_t rockchip_saradc_trigger_handler(int irq, void *p) int ret; int i, j = 0; + memset(&data, 0, sizeof(data)); + mutex_lock(&info->lock); iio_for_each_active_channel(i_dev, i) { diff --git a/drivers/iio/adc/stm32-dfsdm-adc.c b/drivers/iio/adc/stm32-dfsdm-adc.c index 1f9eca2fb2bf..fe11b0d8eab3 100644 --- a/drivers/iio/adc/stm32-dfsdm-adc.c +++ b/drivers/iio/adc/stm32-dfsdm-adc.c @@ -691,11 +691,14 @@ static int stm32_dfsdm_generic_channel_parse_of(struct stm32_dfsdm *dfsdm, return -EINVAL; } - ret = fwnode_property_read_string(node, "label", &ch->datasheet_name); - if (ret < 0) { - dev_err(&indio_dev->dev, - " Error parsing 'label' for idx %d\n", ch->channel); - return ret; + if (fwnode_property_present(node, "label")) { + /* label is optional */ + ret = fwnode_property_read_string(node, "label", &ch->datasheet_name); + if (ret < 0) { + dev_err(&indio_dev->dev, + " Error parsing 'label' for idx %d\n", ch->channel); + return ret; + } } df_ch = &dfsdm->ch_list[ch->channel]; diff --git a/drivers/iio/adc/ti-ads1119.c b/drivers/iio/adc/ti-ads1119.c index e9d9d4d46d38..c268e27eec12 100644 --- a/drivers/iio/adc/ti-ads1119.c +++ b/drivers/iio/adc/ti-ads1119.c @@ -500,12 +500,14 @@ static irqreturn_t ads1119_trigger_handler(int irq, void *private) struct iio_dev *indio_dev = pf->indio_dev; struct ads1119_state *st = iio_priv(indio_dev); struct { - unsigned int sample; + s16 sample; s64 timestamp __aligned(8); } scan; unsigned int index; int ret; + memset(&scan, 0, sizeof(scan)); + if (!iio_trigger_using_own(indio_dev)) { index = find_first_bit(indio_dev->active_scan_mask, iio_get_masklength(indio_dev)); diff --git a/drivers/iio/adc/ti-ads124s08.c b/drivers/iio/adc/ti-ads124s08.c index 425b48d8986f..f452f57f11c9 100644 --- a/drivers/iio/adc/ti-ads124s08.c +++ b/drivers/iio/adc/ti-ads124s08.c @@ -183,9 +183,9 @@ static int ads124s_reset(struct iio_dev *indio_dev) struct ads124s_private *priv = iio_priv(indio_dev); if (priv->reset_gpio) { - gpiod_set_value(priv->reset_gpio, 0); + gpiod_set_value_cansleep(priv->reset_gpio, 0); udelay(200); - gpiod_set_value(priv->reset_gpio, 1); + gpiod_set_value_cansleep(priv->reset_gpio, 1); } else { return ads124s_write_cmd(indio_dev, ADS124S08_CMD_RESET); } diff --git a/drivers/iio/adc/ti-ads1298.c b/drivers/iio/adc/ti-ads1298.c index 36d43495f603..03f762415fa5 100644 --- a/drivers/iio/adc/ti-ads1298.c +++ b/drivers/iio/adc/ti-ads1298.c @@ -613,6 +613,8 @@ static int ads1298_init(struct iio_dev *indio_dev) } indio_dev->name = devm_kasprintf(dev, GFP_KERNEL, "ads129%u%s", indio_dev->num_channels, suffix); + if (!indio_dev->name) + return -ENOMEM; /* Enable internal test signal, double amplitude, double frequency */ ret = regmap_write(priv->regmap, ADS1298_REG_CONFIG2, diff --git a/drivers/iio/adc/ti-ads8688.c b/drivers/iio/adc/ti-ads8688.c index 9b1814f1965a..a31658b760a4 100644 --- a/drivers/iio/adc/ti-ads8688.c +++ b/drivers/iio/adc/ti-ads8688.c @@ -381,7 +381,7 @@ static irqreturn_t ads8688_trigger_handler(int irq, void *p) struct iio_poll_func *pf = p; struct iio_dev *indio_dev = pf->indio_dev; /* Ensure naturally aligned timestamp */ - u16 buffer[ADS8688_MAX_CHANNELS + sizeof(s64)/sizeof(u16)] __aligned(8); + u16 buffer[ADS8688_MAX_CHANNELS + sizeof(s64)/sizeof(u16)] __aligned(8) = { }; int i, j = 0; iio_for_each_active_channel(indio_dev, i) { diff --git a/drivers/iio/dummy/iio_simple_dummy_buffer.c b/drivers/iio/dummy/iio_simple_dummy_buffer.c index 4ca3f1aaff99..288880346707 100644 --- a/drivers/iio/dummy/iio_simple_dummy_buffer.c +++ b/drivers/iio/dummy/iio_simple_dummy_buffer.c @@ -48,7 +48,7 @@ static irqreturn_t iio_simple_dummy_trigger_h(int irq, void *p) int i = 0, j; u16 *data; - data = kmalloc(indio_dev->scan_bytes, GFP_KERNEL); + data = kzalloc(indio_dev->scan_bytes, GFP_KERNEL); if (!data) goto done; diff --git a/drivers/iio/gyro/fxas21002c_core.c b/drivers/iio/gyro/fxas21002c_core.c index 0391c78c2f18..754c8a564ba4 100644 --- a/drivers/iio/gyro/fxas21002c_core.c +++ b/drivers/iio/gyro/fxas21002c_core.c @@ -730,14 +730,21 @@ static irqreturn_t fxas21002c_trigger_handler(int irq, void *p) int ret; mutex_lock(&data->lock); + ret = fxas21002c_pm_get(data); + if (ret < 0) + goto out_unlock; + ret = regmap_bulk_read(data->regmap, FXAS21002C_REG_OUT_X_MSB, data->buffer, CHANNEL_SCAN_MAX * sizeof(s16)); if (ret < 0) - goto out_unlock; + goto out_pm_put; iio_push_to_buffers_with_timestamp(indio_dev, data->buffer, data->timestamp); +out_pm_put: + fxas21002c_pm_put(data); + out_unlock: mutex_unlock(&data->lock); diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600.h b/drivers/iio/imu/inv_icm42600/inv_icm42600.h index 3a07e43e4cf1..18787a43477b 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600.h +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600.h @@ -403,6 +403,7 @@ struct inv_icm42600_sensor_state { typedef int (*inv_icm42600_bus_setup)(struct inv_icm42600_state *); extern const struct regmap_config inv_icm42600_regmap_config; +extern const struct regmap_config inv_icm42600_spi_regmap_config; extern const struct dev_pm_ops inv_icm42600_pm_ops; const struct iio_mount_matrix * diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_core.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_core.c index 561d245c1d64..ef9875d3b79d 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_core.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_core.c @@ -87,6 +87,21 @@ const struct regmap_config inv_icm42600_regmap_config = { }; EXPORT_SYMBOL_NS_GPL(inv_icm42600_regmap_config, "IIO_ICM42600"); +/* define specific regmap for SPI not supporting burst write */ +const struct regmap_config inv_icm42600_spi_regmap_config = { + .name = "inv_icm42600", + .reg_bits = 8, + .val_bits = 8, + .max_register = 0x4FFF, + .ranges = inv_icm42600_regmap_ranges, + .num_ranges = ARRAY_SIZE(inv_icm42600_regmap_ranges), + .volatile_table = inv_icm42600_regmap_volatile_accesses, + .rd_noinc_table = inv_icm42600_regmap_rd_noinc_accesses, + .cache_type = REGCACHE_RBTREE, + .use_single_write = true, +}; +EXPORT_SYMBOL_NS_GPL(inv_icm42600_spi_regmap_config, "IIO_ICM42600"); + struct inv_icm42600_hw { uint8_t whoami; const char *name; @@ -814,6 +829,8 @@ out_unlock: static int inv_icm42600_resume(struct device *dev) { struct inv_icm42600_state *st = dev_get_drvdata(dev); + struct inv_icm42600_sensor_state *gyro_st = iio_priv(st->indio_gyro); + struct inv_icm42600_sensor_state *accel_st = iio_priv(st->indio_accel); int ret; mutex_lock(&st->lock); @@ -834,9 +851,12 @@ static int inv_icm42600_resume(struct device *dev) goto out_unlock; /* restore FIFO data streaming */ - if (st->fifo.on) + if (st->fifo.on) { + inv_sensors_timestamp_reset(&gyro_st->ts); + inv_sensors_timestamp_reset(&accel_st->ts); ret = regmap_write(st->map, INV_ICM42600_REG_FIFO_CONFIG, INV_ICM42600_FIFO_CONFIG_STREAM); + } out_unlock: mutex_unlock(&st->lock); diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_spi.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_spi.c index c55d8e672183..2bd2c4c8e50c 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_spi.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_spi.c @@ -59,7 +59,8 @@ static int inv_icm42600_probe(struct spi_device *spi) return -EINVAL; chip = (uintptr_t)match; - regmap = devm_regmap_init_spi(spi, &inv_icm42600_regmap_config); + /* use SPI specific regmap */ + regmap = devm_regmap_init_spi(spi, &inv_icm42600_spi_regmap_config); if (IS_ERR(regmap)) return PTR_ERR(regmap); diff --git a/drivers/iio/imu/kmx61.c b/drivers/iio/imu/kmx61.c index 324c38764656..e19c5d3137c6 100644 --- a/drivers/iio/imu/kmx61.c +++ b/drivers/iio/imu/kmx61.c @@ -1193,7 +1193,7 @@ static irqreturn_t kmx61_trigger_handler(int irq, void *p) struct kmx61_data *data = kmx61_get_data(indio_dev); int bit, ret, i = 0; u8 base; - s16 buffer[8]; + s16 buffer[8] = { }; if (indio_dev == data->acc_indio_dev) base = KMX61_ACC_XOUT_L; diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c index 136b225b6bc8..9050a59129e6 100644 --- a/drivers/iio/inkern.c +++ b/drivers/iio/inkern.c @@ -500,7 +500,7 @@ struct iio_channel *iio_channel_get_all(struct device *dev) return_ptr(chans); error_free_chans: - for (i = 0; i < nummaps; i++) + for (i = 0; i < mapind; i++) iio_device_put(chans[i].indio_dev); return ERR_PTR(ret); } diff --git a/drivers/iio/light/bh1745.c b/drivers/iio/light/bh1745.c index 56e32689bb97..63bf729df517 100644 --- a/drivers/iio/light/bh1745.c +++ b/drivers/iio/light/bh1745.c @@ -746,6 +746,8 @@ static irqreturn_t bh1745_trigger_handler(int interrupt, void *p) int i; int j = 0; + memset(&scan, 0, sizeof(scan)); + iio_for_each_active_channel(indio_dev, i) { ret = regmap_bulk_read(data->regmap, BH1745_RED_LSB + 2 * i, &value, 2); diff --git a/drivers/iio/light/vcnl4035.c b/drivers/iio/light/vcnl4035.c index 337a1332c2c6..67c94be02018 100644 --- a/drivers/iio/light/vcnl4035.c +++ b/drivers/iio/light/vcnl4035.c @@ -105,7 +105,7 @@ static irqreturn_t vcnl4035_trigger_consumer_handler(int irq, void *p) struct iio_dev *indio_dev = pf->indio_dev; struct vcnl4035_data *data = iio_priv(indio_dev); /* Ensure naturally aligned timestamp */ - u8 buffer[ALIGN(sizeof(u16), sizeof(s64)) + sizeof(s64)] __aligned(8); + u8 buffer[ALIGN(sizeof(u16), sizeof(s64)) + sizeof(s64)] __aligned(8) = { }; int ret; ret = regmap_read(data->regmap, VCNL4035_ALS_DATA, (int *)buffer); diff --git a/drivers/iio/pressure/zpa2326.c b/drivers/iio/pressure/zpa2326.c index 2adea84f5b4d..9db1c94dfc18 100644 --- a/drivers/iio/pressure/zpa2326.c +++ b/drivers/iio/pressure/zpa2326.c @@ -586,6 +586,8 @@ static int zpa2326_fill_sample_buffer(struct iio_dev *indio_dev, } sample; int err; + memset(&sample, 0, sizeof(sample)); + if (test_bit(0, indio_dev->active_scan_mask)) { /* Get current pressure from hardware FIFO. */ err = zpa2326_dequeue_pressure(indio_dev, &sample.pressure); diff --git a/drivers/iio/temperature/tmp006.c b/drivers/iio/temperature/tmp006.c index 0c844137d7aa..02b27f471baa 100644 --- a/drivers/iio/temperature/tmp006.c +++ b/drivers/iio/temperature/tmp006.c @@ -252,6 +252,8 @@ static irqreturn_t tmp006_trigger_handler(int irq, void *p) } scan; s32 ret; + memset(&scan, 0, sizeof(scan)); + ret = i2c_smbus_read_word_data(data->client, TMP006_VOBJECT); if (ret < 0) goto err; diff --git a/drivers/iio/test/Kconfig b/drivers/iio/test/Kconfig index 33cca49c8058..7a181cac3cc9 100644 --- a/drivers/iio/test/Kconfig +++ b/drivers/iio/test/Kconfig @@ -5,7 +5,7 @@ # Keep in alphabetical order config IIO_GTS_KUNIT_TEST - tristate "Test IIO formatting functions" if !KUNIT_ALL_TESTS + tristate "Test IIO gain-time-scale helpers" if !KUNIT_ALL_TESTS depends on KUNIT select IIO_GTS_HELPER select TEST_KUNIT_DEVICE_HELPERS diff --git a/drivers/iio/test/iio-test-rescale.c b/drivers/iio/test/iio-test-rescale.c index cbf13337ed1f..bbc6a2e1c2c1 100644 --- a/drivers/iio/test/iio-test-rescale.c +++ b/drivers/iio/test/iio-test-rescale.c @@ -652,6 +652,8 @@ static void iio_rescale_test_scale(struct kunit *test) int rel_ppm; int ret; + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buff); + rescale.numerator = t->numerator; rescale.denominator = t->denominator; rescale.offset = t->offset; @@ -681,6 +683,8 @@ static void iio_rescale_test_offset(struct kunit *test) int values[2]; int ret; + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buff_off); + rescale.numerator = t->numerator; rescale.denominator = t->denominator; rescale.offset = t->offset; diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 64ace0b968f0..91db10515d74 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -690,6 +690,7 @@ cma_validate_port(struct ib_device *device, u32 port, int bound_if_index = dev_addr->bound_dev_if; int dev_type = dev_addr->dev_type; struct net_device *ndev = NULL; + struct net_device *pdev = NULL; if (!rdma_dev_access_netns(device, id_priv->id.route.addr.dev_addr.net)) goto out; @@ -714,6 +715,21 @@ cma_validate_port(struct ib_device *device, u32 port, rcu_read_lock(); ndev = rcu_dereference(sgid_attr->ndev); + if (ndev->ifindex != bound_if_index) { + pdev = dev_get_by_index_rcu(dev_addr->net, bound_if_index); + if (pdev) { + if (is_vlan_dev(pdev)) { + pdev = vlan_dev_real_dev(pdev); + if (ndev->ifindex == pdev->ifindex) + bound_if_index = pdev->ifindex; + } + if (is_vlan_dev(ndev)) { + pdev = vlan_dev_real_dev(ndev); + if (bound_if_index == pdev->ifindex) + bound_if_index = ndev->ifindex; + } + } + } if (!net_eq(dev_net(ndev), dev_addr->net) || ndev->ifindex != bound_if_index) { rdma_put_gid_attr(sgid_attr); diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index ff121e59b9c0..cb987ab0177c 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -2833,8 +2833,8 @@ int rdma_nl_notify_event(struct ib_device *device, u32 port_num, enum rdma_nl_notify_event_type type) { struct sk_buff *skb; + int ret = -EMSGSIZE; struct net *net; - int ret = 0; void *nlh; net = read_pnet(&device->coredev.rdma_net); diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 66b02fbf077a..5ad14c39d48c 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -161,7 +161,7 @@ static const void __user *uverbs_request_next_ptr(struct uverbs_req_iter *iter, { const void __user *res = iter->cur; - if (iter->cur + len > iter->end) + if (len > iter->end - iter->cur) return (void __force __user *)ERR_PTR(-ENOSPC); iter->cur += len; return res; @@ -2008,11 +2008,13 @@ static int ib_uverbs_post_send(struct uverbs_attr_bundle *attrs) ret = uverbs_request_start(attrs, &iter, &cmd, sizeof(cmd)); if (ret) return ret; - wqes = uverbs_request_next_ptr(&iter, cmd.wqe_size * cmd.wr_count); + wqes = uverbs_request_next_ptr(&iter, size_mul(cmd.wqe_size, + cmd.wr_count)); if (IS_ERR(wqes)) return PTR_ERR(wqes); - sgls = uverbs_request_next_ptr( - &iter, cmd.sge_count * sizeof(struct ib_uverbs_sge)); + sgls = uverbs_request_next_ptr(&iter, + size_mul(cmd.sge_count, + sizeof(struct ib_uverbs_sge))); if (IS_ERR(sgls)) return PTR_ERR(sgls); ret = uverbs_request_finish(&iter); @@ -2198,11 +2200,11 @@ ib_uverbs_unmarshall_recv(struct uverbs_req_iter *iter, u32 wr_count, if (wqe_size < sizeof(struct ib_uverbs_recv_wr)) return ERR_PTR(-EINVAL); - wqes = uverbs_request_next_ptr(iter, wqe_size * wr_count); + wqes = uverbs_request_next_ptr(iter, size_mul(wqe_size, wr_count)); if (IS_ERR(wqes)) return ERR_CAST(wqes); - sgls = uverbs_request_next_ptr( - iter, sge_count * sizeof(struct ib_uverbs_sge)); + sgls = uverbs_request_next_ptr(iter, size_mul(sge_count, + sizeof(struct ib_uverbs_sge))); if (IS_ERR(sgls)) return ERR_CAST(sgls); ret = uverbs_request_finish(iter); diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 82023394e330..e3d26bd6de05 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -199,7 +199,7 @@ int bnxt_re_query_device(struct ib_device *ibdev, ib_attr->vendor_id = rdev->en_dev->pdev->vendor; ib_attr->vendor_part_id = rdev->en_dev->pdev->device; - ib_attr->hw_ver = rdev->en_dev->pdev->subsystem_device; + ib_attr->hw_ver = rdev->en_dev->pdev->revision; ib_attr->max_qp = dev_attr->max_qp; ib_attr->max_qp_wr = dev_attr->max_qp_wqes; ib_attr->device_cap_flags = @@ -967,13 +967,13 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp, struct ib_udata *udata) unsigned int flags; int rc; + bnxt_re_debug_rem_qpinfo(rdev, qp); + bnxt_qplib_flush_cqn_wq(&qp->qplib_qp); rc = bnxt_qplib_destroy_qp(&rdev->qplib_res, &qp->qplib_qp); - if (rc) { + if (rc) ibdev_err(&rdev->ibdev, "Failed to destroy HW QP"); - return rc; - } if (rdma_is_kernel_res(&qp->ib_qp.res)) { flags = bnxt_re_lock_cqs(qp); @@ -983,11 +983,8 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp, struct ib_udata *udata) bnxt_qplib_free_qp_res(&rdev->qplib_res, &qp->qplib_qp); - if (ib_qp->qp_type == IB_QPT_GSI && rdev->gsi_ctx.gsi_sqp) { - rc = bnxt_re_destroy_gsi_sqp(qp); - if (rc) - return rc; - } + if (ib_qp->qp_type == IB_QPT_GSI && rdev->gsi_ctx.gsi_sqp) + bnxt_re_destroy_gsi_sqp(qp); mutex_lock(&rdev->qp_lock); list_del(&qp->list); @@ -998,8 +995,6 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp, struct ib_udata *udata) else if (qp->qplib_qp.type == CMDQ_CREATE_QP_TYPE_UD) atomic_dec(&rdev->stats.res.ud_qp_count); - bnxt_re_debug_rem_qpinfo(rdev, qp); - ib_umem_release(qp->rumem); ib_umem_release(qp->sumem); @@ -2167,18 +2162,20 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr, } } - if (qp_attr_mask & IB_QP_PATH_MTU) { - qp->qplib_qp.modify_flags |= - CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU; - qp->qplib_qp.path_mtu = __from_ib_mtu(qp_attr->path_mtu); - qp->qplib_qp.mtu = ib_mtu_enum_to_int(qp_attr->path_mtu); - } else if (qp_attr->qp_state == IB_QPS_RTR) { - qp->qplib_qp.modify_flags |= - CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU; - qp->qplib_qp.path_mtu = - __from_ib_mtu(iboe_get_mtu(rdev->netdev->mtu)); - qp->qplib_qp.mtu = - ib_mtu_enum_to_int(iboe_get_mtu(rdev->netdev->mtu)); + if (qp_attr->qp_state == IB_QPS_RTR) { + enum ib_mtu qpmtu; + + qpmtu = iboe_get_mtu(rdev->netdev->mtu); + if (qp_attr_mask & IB_QP_PATH_MTU) { + if (ib_mtu_enum_to_int(qp_attr->path_mtu) > + ib_mtu_enum_to_int(qpmtu)) + return -EINVAL; + qpmtu = qp_attr->path_mtu; + } + + qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU; + qp->qplib_qp.path_mtu = __from_ib_mtu(qpmtu); + qp->qplib_qp.mtu = ib_mtu_enum_to_int(qpmtu); } if (qp_attr_mask & IB_QP_TIMEOUT) { @@ -2328,6 +2325,7 @@ int bnxt_re_query_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr, qp_attr->retry_cnt = qplib_qp->retry_cnt; qp_attr->rnr_retry = qplib_qp->rnr_retry; qp_attr->min_rnr_timer = qplib_qp->min_rnr_timer; + qp_attr->port_num = __to_ib_port_num(qplib_qp->port_id); qp_attr->rq_psn = qplib_qp->rq.psn; qp_attr->max_rd_atomic = qplib_qp->max_rd_atomic; qp_attr->sq_psn = qplib_qp->sq.psn; @@ -2824,7 +2822,8 @@ bad: wr = wr->next; } bnxt_qplib_post_send_db(&qp->qplib_qp); - bnxt_ud_qp_hw_stall_workaround(qp); + if (!bnxt_qplib_is_chip_gen_p5_p7(qp->rdev->chip_ctx)) + bnxt_ud_qp_hw_stall_workaround(qp); spin_unlock_irqrestore(&qp->sq_lock, flags); return rc; } @@ -2936,7 +2935,8 @@ bad: wr = wr->next; } bnxt_qplib_post_send_db(&qp->qplib_qp); - bnxt_ud_qp_hw_stall_workaround(qp); + if (!bnxt_qplib_is_chip_gen_p5_p7(qp->rdev->chip_ctx)) + bnxt_ud_qp_hw_stall_workaround(qp); spin_unlock_irqrestore(&qp->sq_lock, flags); return rc; diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h index ac59f1d73b15..fbb16a411d6a 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h @@ -268,6 +268,10 @@ void bnxt_re_dealloc_ucontext(struct ib_ucontext *context); int bnxt_re_mmap(struct ib_ucontext *context, struct vm_area_struct *vma); void bnxt_re_mmap_free(struct rdma_user_mmap_entry *rdma_entry); +static inline u32 __to_ib_port_num(u16 port_id) +{ + return (u32)port_id + 1; +} unsigned long bnxt_re_lock_cqs(struct bnxt_re_qp *qp); void bnxt_re_unlock_cqs(struct bnxt_re_qp *qp, unsigned long flags); diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index b7af0d5ff3b6..c143f273b759 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -1715,11 +1715,8 @@ static bool bnxt_re_is_qp1_or_shadow_qp(struct bnxt_re_dev *rdev, static void bnxt_re_dev_stop(struct bnxt_re_dev *rdev) { - int mask = IB_QP_STATE; - struct ib_qp_attr qp_attr; struct bnxt_re_qp *qp; - qp_attr.qp_state = IB_QPS_ERR; mutex_lock(&rdev->qp_lock); list_for_each_entry(qp, &rdev->qp_list, list) { /* Modify the state of all QPs except QP1/Shadow QP */ @@ -1727,12 +1724,9 @@ static void bnxt_re_dev_stop(struct bnxt_re_dev *rdev) if (qp->qplib_qp.state != CMDQ_MODIFY_QP_NEW_STATE_RESET && qp->qplib_qp.state != - CMDQ_MODIFY_QP_NEW_STATE_ERR) { + CMDQ_MODIFY_QP_NEW_STATE_ERR) bnxt_re_dispatch_event(&rdev->ibdev, &qp->ib_qp, 1, IB_EVENT_QP_FATAL); - bnxt_re_modify_qp(&qp->ib_qp, &qp_attr, mask, - NULL); - } } } mutex_unlock(&rdev->qp_lock); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index e42abf5be6c0..5336f74297f8 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -659,13 +659,6 @@ int bnxt_qplib_create_srq(struct bnxt_qplib_res *res, rc = bnxt_qplib_alloc_init_hwq(&srq->hwq, &hwq_attr); if (rc) return rc; - - srq->swq = kcalloc(srq->hwq.max_elements, sizeof(*srq->swq), - GFP_KERNEL); - if (!srq->swq) { - rc = -ENOMEM; - goto fail; - } srq->dbinfo.flags = 0; bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, CMDQ_BASE_OPCODE_CREATE_SRQ, @@ -694,9 +687,17 @@ int bnxt_qplib_create_srq(struct bnxt_qplib_res *res, spin_lock_init(&srq->lock); srq->start_idx = 0; srq->last_idx = srq->hwq.max_elements - 1; - for (idx = 0; idx < srq->hwq.max_elements; idx++) - srq->swq[idx].next_idx = idx + 1; - srq->swq[srq->last_idx].next_idx = -1; + if (!srq->hwq.is_user) { + srq->swq = kcalloc(srq->hwq.max_elements, sizeof(*srq->swq), + GFP_KERNEL); + if (!srq->swq) { + rc = -ENOMEM; + goto fail; + } + for (idx = 0; idx < srq->hwq.max_elements; idx++) + srq->swq[idx].next_idx = idx + 1; + srq->swq[srq->last_idx].next_idx = -1; + } srq->id = le32_to_cpu(resp.xid); srq->dbinfo.hwq = &srq->hwq; @@ -1000,9 +1001,7 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) u32 tbl_indx; u16 nsge; - if (res->dattr) - qp->is_host_msn_tbl = _is_host_msn_table(res->dattr->dev_cap_flags2); - + qp->is_host_msn_tbl = _is_host_msn_table(res->dattr->dev_cap_flags2); sq->dbinfo.flags = 0; bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, CMDQ_BASE_OPCODE_CREATE_QP, @@ -1034,7 +1033,12 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) : 0; /* Update msn tbl size */ if (qp->is_host_msn_tbl && psn_sz) { - hwq_attr.aux_depth = roundup_pow_of_two(bnxt_qplib_set_sq_size(sq, qp->wqe_mode)); + if (qp->wqe_mode == BNXT_QPLIB_WQE_MODE_STATIC) + hwq_attr.aux_depth = + roundup_pow_of_two(bnxt_qplib_set_sq_size(sq, qp->wqe_mode)); + else + hwq_attr.aux_depth = + roundup_pow_of_two(bnxt_qplib_set_sq_size(sq, qp->wqe_mode)) / 2; qp->msn_tbl_sz = hwq_attr.aux_depth; qp->msn = 0; } @@ -1044,13 +1048,14 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) if (rc) return rc; - rc = bnxt_qplib_alloc_init_swq(sq); - if (rc) - goto fail_sq; - - if (psn_sz) - bnxt_qplib_init_psn_ptr(qp, psn_sz); + if (!sq->hwq.is_user) { + rc = bnxt_qplib_alloc_init_swq(sq); + if (rc) + goto fail_sq; + if (psn_sz) + bnxt_qplib_init_psn_ptr(qp, psn_sz); + } req.sq_size = cpu_to_le32(bnxt_qplib_set_sq_size(sq, qp->wqe_mode)); pbl = &sq->hwq.pbl[PBL_LVL_0]; req.sq_pbl = cpu_to_le64(pbl->pg_map_arr[0]); @@ -1076,9 +1081,11 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) rc = bnxt_qplib_alloc_init_hwq(&rq->hwq, &hwq_attr); if (rc) goto sq_swq; - rc = bnxt_qplib_alloc_init_swq(rq); - if (rc) - goto fail_rq; + if (!rq->hwq.is_user) { + rc = bnxt_qplib_alloc_init_swq(rq); + if (rc) + goto fail_rq; + } req.rq_size = cpu_to_le32(rq->max_wqe); pbl = &rq->hwq.pbl[PBL_LVL_0]; @@ -1174,9 +1181,11 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) rq->dbinfo.db = qp->dpi->dbr; rq->dbinfo.max_slot = bnxt_qplib_set_rq_max_slot(rq->wqe_size); } + spin_lock_bh(&rcfw->tbl_lock); tbl_indx = map_qp_id_to_tbl_indx(qp->id, rcfw); rcfw->qp_tbl[tbl_indx].qp_id = qp->id; rcfw->qp_tbl[tbl_indx].qp_handle = (void *)qp; + spin_unlock_bh(&rcfw->tbl_lock); return 0; fail: @@ -1283,7 +1292,8 @@ static void __filter_modify_flags(struct bnxt_qplib_qp *qp) } } -static void bnxt_set_mandatory_attributes(struct bnxt_qplib_qp *qp, +static void bnxt_set_mandatory_attributes(struct bnxt_qplib_res *res, + struct bnxt_qplib_qp *qp, struct cmdq_modify_qp *req) { u32 mandatory_flags = 0; @@ -1298,6 +1308,14 @@ static void bnxt_set_mandatory_attributes(struct bnxt_qplib_qp *qp, mandatory_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_PKEY; } + if (_is_min_rnr_in_rtr_rts_mandatory(res->dattr->dev_cap_flags2) && + (qp->cur_qp_state == CMDQ_MODIFY_QP_NEW_STATE_RTR && + qp->state == CMDQ_MODIFY_QP_NEW_STATE_RTS)) { + if (qp->type == CMDQ_MODIFY_QP_QP_TYPE_RC) + mandatory_flags |= + CMDQ_MODIFY_QP_MODIFY_MASK_MIN_RNR_TIMER; + } + if (qp->type == CMDQ_MODIFY_QP_QP_TYPE_UD || qp->type == CMDQ_MODIFY_QP_QP_TYPE_GSI) mandatory_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_QKEY; @@ -1338,7 +1356,7 @@ int bnxt_qplib_modify_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) /* Set mandatory attributes for INIT -> RTR and RTR -> RTS transition */ if (_is_optimize_modify_qp_supported(res->dattr->dev_cap_flags2) && is_optimized_state_transition(qp)) - bnxt_set_mandatory_attributes(qp, &req); + bnxt_set_mandatory_attributes(res, qp, &req); } bmask = qp->modify_flags; req.modify_mask = cpu_to_le32(qp->modify_flags); @@ -1521,6 +1539,7 @@ int bnxt_qplib_query_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) qp->dest_qpn = le32_to_cpu(sb->dest_qp_id); memcpy(qp->smac, sb->src_mac, 6); qp->vlan_id = le16_to_cpu(sb->vlan_pcp_vlan_dei_vlan_id); + qp->port_id = le16_to_cpu(sb->port_id); bail: dma_free_coherent(&rcfw->pdev->dev, sbuf.size, sbuf.sb, sbuf.dma_addr); @@ -2667,10 +2686,12 @@ static int bnxt_qplib_cq_process_req(struct bnxt_qplib_cq *cq, bnxt_qplib_add_flush_qp(qp); } else { /* Before we complete, do WA 9060 */ - if (do_wa9060(qp, cq, cq_cons, sq->swq_last, - cqe_sq_cons)) { - *lib_qp = qp; - goto out; + if (!bnxt_qplib_is_chip_gen_p5_p7(qp->cctx)) { + if (do_wa9060(qp, cq, cq_cons, sq->swq_last, + cqe_sq_cons)) { + *lib_qp = qp; + goto out; + } } if (swq->flags & SQ_SEND_FLAGS_SIGNAL_COMP) { cqe->status = CQ_REQ_STATUS_OK; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.h b/drivers/infiniband/hw/bnxt_re/qplib_fp.h index ef3424c81345..0660101b5310 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h @@ -114,7 +114,6 @@ struct bnxt_qplib_sge { u32 size; }; -#define BNXT_QPLIB_QP_MAX_SGL 6 struct bnxt_qplib_swq { u64 wr_id; int next_idx; @@ -154,7 +153,7 @@ struct bnxt_qplib_swqe { #define BNXT_QPLIB_SWQE_FLAGS_UC_FENCE BIT(2) #define BNXT_QPLIB_SWQE_FLAGS_SOLICIT_EVENT BIT(3) #define BNXT_QPLIB_SWQE_FLAGS_INLINE BIT(4) - struct bnxt_qplib_sge sg_list[BNXT_QPLIB_QP_MAX_SGL]; + struct bnxt_qplib_sge sg_list[BNXT_VAR_MAX_SGE]; int num_sge; /* Max inline data is 96 bytes */ u32 inline_len; @@ -299,6 +298,7 @@ struct bnxt_qplib_qp { u32 dest_qpn; u8 smac[6]; u16 vlan_id; + u16 port_id; u8 nw_type; struct bnxt_qplib_ah ah; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index 5e90ea232de8..17e62f22683b 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -424,7 +424,8 @@ static int __send_message_basic_sanity(struct bnxt_qplib_rcfw *rcfw, /* Prevent posting if f/w is not in a state to process */ if (test_bit(ERR_DEVICE_DETACHED, &rcfw->cmdq.flags)) - return bnxt_qplib_map_rc(opcode); + return -ENXIO; + if (test_bit(FIRMWARE_STALL_DETECTED, &cmdq->flags)) return -ETIMEDOUT; @@ -493,7 +494,7 @@ static int __bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw, rc = __send_message_basic_sanity(rcfw, msg, opcode); if (rc) - return rc; + return rc == -ENXIO ? bnxt_qplib_map_rc(opcode) : rc; rc = __send_message(rcfw, msg, opcode); if (rc) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h index 21fb148713a6..cbfc49a1a56d 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h @@ -584,6 +584,11 @@ static inline bool _is_optimize_modify_qp_supported(u16 dev_cap_ext_flags2) return dev_cap_ext_flags2 & CREQ_QUERY_FUNC_RESP_SB_OPTIMIZE_MODIFY_QP_SUPPORTED; } +static inline bool _is_min_rnr_in_rtr_rts_mandatory(u16 dev_cap_ext_flags2) +{ + return !!(dev_cap_ext_flags2 & CREQ_QUERY_FUNC_RESP_SB_MIN_RNR_RTR_RTS_OPT_SUPPORTED); +} + static inline bool _is_cq_coalescing_supported(u16 dev_cap_ext_flags2) { return dev_cap_ext_flags2 & CREQ_QUERY_FUNC_RESP_SB_CQ_COALESCING_SUPPORTED; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index 7e20ae3d2c4f..9df3e3271577 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -129,12 +129,18 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw, attr->max_qp_init_rd_atom = sb->max_qp_init_rd_atom > BNXT_QPLIB_MAX_OUT_RD_ATOM ? BNXT_QPLIB_MAX_OUT_RD_ATOM : sb->max_qp_init_rd_atom; - attr->max_qp_wqes = le16_to_cpu(sb->max_qp_wr); - /* - * 128 WQEs needs to be reserved for the HW (8916). Prevent - * reporting the max number - */ - attr->max_qp_wqes -= BNXT_QPLIB_RESERVED_QP_WRS + 1; + attr->max_qp_wqes = le16_to_cpu(sb->max_qp_wr) - 1; + if (!bnxt_qplib_is_chip_gen_p5_p7(rcfw->res->cctx)) { + /* + * 128 WQEs needs to be reserved for the HW (8916). Prevent + * reporting the max number on legacy devices + */ + attr->max_qp_wqes -= BNXT_QPLIB_RESERVED_QP_WRS + 1; + } + + /* Adjust for max_qp_wqes for variable wqe */ + if (cctx->modes.wqe_mode == BNXT_QPLIB_WQE_MODE_VARIABLE) + attr->max_qp_wqes = BNXT_VAR_MAX_WQE - 1; attr->max_qp_sges = cctx->modes.wqe_mode == BNXT_QPLIB_WQE_MODE_VARIABLE ? min_t(u32, sb->max_sge_var_wqe, BNXT_VAR_MAX_SGE) : 6; diff --git a/drivers/infiniband/hw/bnxt_re/roce_hsi.h b/drivers/infiniband/hw/bnxt_re/roce_hsi.h index a98fc9c2313e..0ee60fdc18b3 100644 --- a/drivers/infiniband/hw/bnxt_re/roce_hsi.h +++ b/drivers/infiniband/hw/bnxt_re/roce_hsi.h @@ -2215,6 +2215,7 @@ struct creq_query_func_resp_sb { #define CREQ_QUERY_FUNC_RESP_SB_REQ_RETRANSMISSION_SUPPORT_IQM_MSN_TABLE (0x2UL << 4) #define CREQ_QUERY_FUNC_RESP_SB_REQ_RETRANSMISSION_SUPPORT_LAST \ CREQ_QUERY_FUNC_RESP_SB_REQ_RETRANSMISSION_SUPPORT_IQM_MSN_TABLE + #define CREQ_QUERY_FUNC_RESP_SB_MIN_RNR_RTR_RTS_OPT_SUPPORTED 0x1000UL __le16 max_xp_qp_size; __le16 create_qp_batch_size; __le16 destroy_qp_batch_size; diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.c b/drivers/infiniband/hw/hns/hns_roce_hem.c index f84521be3bea..605562122ecc 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hem.c +++ b/drivers/infiniband/hw/hns/hns_roce_hem.c @@ -931,6 +931,7 @@ struct hns_roce_hem_item { size_t count; /* max ba numbers */ int start; /* start buf offset in this hem */ int end; /* end buf offset in this hem */ + bool exist_bt; }; /* All HEM items are linked in a tree structure */ @@ -959,6 +960,7 @@ hem_list_alloc_item(struct hns_roce_dev *hr_dev, int start, int end, int count, } } + hem->exist_bt = exist_bt; hem->count = count; hem->start = start; hem->end = end; @@ -969,22 +971,22 @@ hem_list_alloc_item(struct hns_roce_dev *hr_dev, int start, int end, int count, } static void hem_list_free_item(struct hns_roce_dev *hr_dev, - struct hns_roce_hem_item *hem, bool exist_bt) + struct hns_roce_hem_item *hem) { - if (exist_bt) + if (hem->exist_bt) dma_free_coherent(hr_dev->dev, hem->count * BA_BYTE_LEN, hem->addr, hem->dma_addr); kfree(hem); } static void hem_list_free_all(struct hns_roce_dev *hr_dev, - struct list_head *head, bool exist_bt) + struct list_head *head) { struct hns_roce_hem_item *hem, *temp_hem; list_for_each_entry_safe(hem, temp_hem, head, list) { list_del(&hem->list); - hem_list_free_item(hr_dev, hem, exist_bt); + hem_list_free_item(hr_dev, hem); } } @@ -1084,6 +1086,10 @@ int hns_roce_hem_list_calc_root_ba(const struct hns_roce_buf_region *regions, for (i = 0; i < region_cnt; i++) { r = (struct hns_roce_buf_region *)®ions[i]; + /* when r->hopnum = 0, the region should not occupy root_ba. */ + if (!r->hopnum) + continue; + if (r->hopnum > 1) { step = hem_list_calc_ba_range(r->hopnum, 1, unit); if (step > 0) @@ -1177,7 +1183,7 @@ static int hem_list_alloc_mid_bt(struct hns_roce_dev *hr_dev, err_exit: for (level = 1; level < hopnum; level++) - hem_list_free_all(hr_dev, &temp_list[level], true); + hem_list_free_all(hr_dev, &temp_list[level]); return ret; } @@ -1218,16 +1224,26 @@ static int alloc_fake_root_bt(struct hns_roce_dev *hr_dev, void *cpu_base, { struct hns_roce_hem_item *hem; + /* This is on the has_mtt branch, if r->hopnum + * is 0, there is no root_ba to reuse for the + * region's fake hem, so a dma_alloc request is + * necessary here. + */ hem = hem_list_alloc_item(hr_dev, r->offset, r->offset + r->count - 1, - r->count, false); + r->count, !r->hopnum); if (!hem) return -ENOMEM; - hem_list_assign_bt(hem, cpu_base, phy_base); + /* The root_ba can be reused only when r->hopnum > 0. */ + if (r->hopnum) + hem_list_assign_bt(hem, cpu_base, phy_base); list_add(&hem->list, branch_head); list_add(&hem->sibling, leaf_head); - return r->count; + /* If r->hopnum == 0, 0 is returned, + * so that the root_bt entry is not occupied. + */ + return r->hopnum ? r->count : 0; } static int setup_middle_bt(struct hns_roce_dev *hr_dev, void *cpu_base, @@ -1271,7 +1287,7 @@ setup_root_hem(struct hns_roce_dev *hr_dev, struct hns_roce_hem_list *hem_list, return -ENOMEM; total = 0; - for (i = 0; i < region_cnt && total < max_ba_num; i++) { + for (i = 0; i < region_cnt && total <= max_ba_num; i++) { r = ®ions[i]; if (!r->count) continue; @@ -1337,9 +1353,9 @@ static int hem_list_alloc_root_bt(struct hns_roce_dev *hr_dev, region_cnt); if (ret) { for (i = 0; i < region_cnt; i++) - hem_list_free_all(hr_dev, &head.branch[i], false); + hem_list_free_all(hr_dev, &head.branch[i]); - hem_list_free_all(hr_dev, &head.root, true); + hem_list_free_all(hr_dev, &head.root); } return ret; @@ -1402,10 +1418,9 @@ void hns_roce_hem_list_release(struct hns_roce_dev *hr_dev, for (i = 0; i < HNS_ROCE_MAX_BT_REGION; i++) for (j = 0; j < HNS_ROCE_MAX_BT_LEVEL; j++) - hem_list_free_all(hr_dev, &hem_list->mid_bt[i][j], - j != 0); + hem_list_free_all(hr_dev, &hem_list->mid_bt[i][j]); - hem_list_free_all(hr_dev, &hem_list->root_bt, true); + hem_list_free_all(hr_dev, &hem_list->root_bt); INIT_LIST_HEAD(&hem_list->btm_bt); hem_list->root_ba = 0; } diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 697b17cca02e..0144e7210d05 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -468,7 +468,7 @@ static inline int set_ud_wqe(struct hns_roce_qp *qp, valid_num_sge = calc_wr_sge_num(wr, &msg_len); ret = set_ud_opcode(ud_sq_wqe, wr); - if (WARN_ON(ret)) + if (WARN_ON_ONCE(ret)) return ret; ud_sq_wqe->msg_len = cpu_to_le32(msg_len); @@ -572,7 +572,7 @@ static inline int set_rc_wqe(struct hns_roce_qp *qp, rc_sq_wqe->msg_len = cpu_to_le32(msg_len); ret = set_rc_opcode(hr_dev, rc_sq_wqe, wr); - if (WARN_ON(ret)) + if (WARN_ON_ONCE(ret)) return ret; hr_reg_write(rc_sq_wqe, RC_SEND_WQE_SO, @@ -670,6 +670,10 @@ static void write_dwqe(struct hns_roce_dev *hr_dev, struct hns_roce_qp *qp, #define HNS_ROCE_SL_SHIFT 2 struct hns_roce_v2_rc_send_wqe *rc_sq_wqe = wqe; + if (unlikely(qp->state == IB_QPS_ERR)) { + flush_cqe(hr_dev, qp); + return; + } /* All kinds of DirectWQE have the same header field layout */ hr_reg_enable(rc_sq_wqe, RC_SEND_WQE_FLAG); hr_reg_write(rc_sq_wqe, RC_SEND_WQE_DB_SL_L, qp->sl); @@ -5619,6 +5623,9 @@ static void put_dip_ctx_idx(struct hns_roce_dev *hr_dev, { struct hns_roce_dip *hr_dip = hr_qp->dip; + if (!hr_dip) + return; + xa_lock(&hr_dev->qp_table.dip_xa); hr_dip->qp_cnt--; diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c index bf30b3a65a9b..55b9283bfc6f 100644 --- a/drivers/infiniband/hw/hns/hns_roce_mr.c +++ b/drivers/infiniband/hw/hns/hns_roce_mr.c @@ -814,11 +814,6 @@ int hns_roce_mtr_map(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr, for (i = 0, mapped_cnt = 0; i < mtr->hem_cfg.region_count && mapped_cnt < page_cnt; i++) { r = &mtr->hem_cfg.region[i]; - /* if hopnum is 0, no need to map pages in this region */ - if (!r->hopnum) { - mapped_cnt += r->count; - continue; - } if (r->offset + r->count > page_cnt) { ret = -EINVAL; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index bc7930d0c564..f5b59d02f4d3 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -2839,7 +2839,7 @@ static int mlx5_ib_get_plane_num(struct mlx5_core_dev *mdev, u8 *num_plane) int err; *num_plane = 0; - if (!MLX5_CAP_GEN(mdev, ib_virt)) + if (!MLX5_CAP_GEN(mdev, ib_virt) || !MLX5_CAP_GEN_2(mdev, multiplane)) return 0; err = mlx5_query_hca_vport_context(mdev, 0, 1, 0, &vport_ctx); @@ -3639,7 +3639,8 @@ static int mlx5_ib_init_multiport_master(struct mlx5_ib_dev *dev) list_for_each_entry(mpi, &mlx5_ib_unaffiliated_port_list, list) { if (dev->sys_image_guid == mpi->sys_image_guid && - (mlx5_core_native_port_num(mpi->mdev) - 1) == i) { + (mlx5_core_native_port_num(mpi->mdev) - 1) == i && + mlx5_core_same_coredev_type(dev->mdev, mpi->mdev)) { bound = mlx5_ib_bind_slave_port(dev, mpi); } @@ -4785,7 +4786,8 @@ static int mlx5r_mp_probe(struct auxiliary_device *adev, mutex_lock(&mlx5_ib_multiport_mutex); list_for_each_entry(dev, &mlx5_ib_dev_list, ib_dev_list) { - if (dev->sys_image_guid == mpi->sys_image_guid) + if (dev->sys_image_guid == mpi->sys_image_guid && + mlx5_core_same_coredev_type(dev->mdev, mpi->mdev)) bound = mlx5_ib_bind_slave_port(dev, mpi); if (bound) { diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c index 255677bc12b2..1ba4a0c8726a 100644 --- a/drivers/infiniband/sw/rxe/rxe.c +++ b/drivers/infiniband/sw/rxe/rxe.c @@ -40,6 +40,8 @@ void rxe_dealloc(struct ib_device *ib_dev) /* initialize rxe device parameters */ static void rxe_init_device_param(struct rxe_dev *rxe) { + struct net_device *ndev; + rxe->max_inline_data = RXE_MAX_INLINE_DATA; rxe->attr.vendor_id = RXE_VENDOR_ID; @@ -71,8 +73,15 @@ static void rxe_init_device_param(struct rxe_dev *rxe) rxe->attr.max_fast_reg_page_list_len = RXE_MAX_FMR_PAGE_LIST_LEN; rxe->attr.max_pkeys = RXE_MAX_PKEYS; rxe->attr.local_ca_ack_delay = RXE_LOCAL_CA_ACK_DELAY; + + ndev = rxe_ib_device_get_netdev(&rxe->ib_dev); + if (!ndev) + return; + addrconf_addr_eui48((unsigned char *)&rxe->attr.sys_image_guid, - rxe->ndev->dev_addr); + ndev->dev_addr); + + dev_put(ndev); rxe->max_ucontext = RXE_MAX_UCONTEXT; } @@ -109,10 +118,15 @@ static void rxe_init_port_param(struct rxe_port *port) static void rxe_init_ports(struct rxe_dev *rxe) { struct rxe_port *port = &rxe->port; + struct net_device *ndev; rxe_init_port_param(port); + ndev = rxe_ib_device_get_netdev(&rxe->ib_dev); + if (!ndev) + return; addrconf_addr_eui48((unsigned char *)&port->port_guid, - rxe->ndev->dev_addr); + ndev->dev_addr); + dev_put(ndev); spin_lock_init(&port->port_lock); } @@ -167,12 +181,13 @@ void rxe_set_mtu(struct rxe_dev *rxe, unsigned int ndev_mtu) /* called by ifc layer to create new rxe device. * The caller should allocate memory for rxe by calling ib_alloc_device. */ -int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name) +int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name, + struct net_device *ndev) { rxe_init(rxe); rxe_set_mtu(rxe, mtu); - return rxe_register_device(rxe, ibdev_name); + return rxe_register_device(rxe, ibdev_name, ndev); } static int rxe_newlink(const char *ibdev_name, struct net_device *ndev) diff --git a/drivers/infiniband/sw/rxe/rxe.h b/drivers/infiniband/sw/rxe/rxe.h index d8fb2c7af30a..fe7f97066732 100644 --- a/drivers/infiniband/sw/rxe/rxe.h +++ b/drivers/infiniband/sw/rxe/rxe.h @@ -139,7 +139,8 @@ enum resp_states { void rxe_set_mtu(struct rxe_dev *rxe, unsigned int dev_mtu); -int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name); +int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name, + struct net_device *ndev); void rxe_rcv(struct sk_buff *skb); diff --git a/drivers/infiniband/sw/rxe/rxe_mcast.c b/drivers/infiniband/sw/rxe/rxe_mcast.c index 86cc2e18a7fd..07ff47bae31d 100644 --- a/drivers/infiniband/sw/rxe/rxe_mcast.c +++ b/drivers/infiniband/sw/rxe/rxe_mcast.c @@ -31,10 +31,19 @@ static int rxe_mcast_add(struct rxe_dev *rxe, union ib_gid *mgid) { unsigned char ll_addr[ETH_ALEN]; + struct net_device *ndev; + int ret; + + ndev = rxe_ib_device_get_netdev(&rxe->ib_dev); + if (!ndev) + return -ENODEV; ipv6_eth_mc_map((struct in6_addr *)mgid->raw, ll_addr); - return dev_mc_add(rxe->ndev, ll_addr); + ret = dev_mc_add(ndev, ll_addr); + dev_put(ndev); + + return ret; } /** @@ -47,10 +56,19 @@ static int rxe_mcast_add(struct rxe_dev *rxe, union ib_gid *mgid) static int rxe_mcast_del(struct rxe_dev *rxe, union ib_gid *mgid) { unsigned char ll_addr[ETH_ALEN]; + struct net_device *ndev; + int ret; + + ndev = rxe_ib_device_get_netdev(&rxe->ib_dev); + if (!ndev) + return -ENODEV; ipv6_eth_mc_map((struct in6_addr *)mgid->raw, ll_addr); - return dev_mc_del(rxe->ndev, ll_addr); + ret = dev_mc_del(ndev, ll_addr); + dev_put(ndev); + + return ret; } /** diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index 75d1407db52d..8cc64ceeb356 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -524,7 +524,16 @@ out: */ const char *rxe_parent_name(struct rxe_dev *rxe, unsigned int port_num) { - return rxe->ndev->name; + struct net_device *ndev; + char *ndev_name; + + ndev = rxe_ib_device_get_netdev(&rxe->ib_dev); + if (!ndev) + return NULL; + ndev_name = ndev->name; + dev_put(ndev); + + return ndev_name; } int rxe_net_add(const char *ibdev_name, struct net_device *ndev) @@ -536,10 +545,9 @@ int rxe_net_add(const char *ibdev_name, struct net_device *ndev) if (!rxe) return -ENOMEM; - rxe->ndev = ndev; ib_mark_name_assigned_by_user(&rxe->ib_dev); - err = rxe_add(rxe, ndev->mtu, ibdev_name); + err = rxe_add(rxe, ndev->mtu, ibdev_name, ndev); if (err) { ib_dealloc_device(&rxe->ib_dev); return err; @@ -587,10 +595,18 @@ void rxe_port_down(struct rxe_dev *rxe) void rxe_set_port_state(struct rxe_dev *rxe) { - if (netif_running(rxe->ndev) && netif_carrier_ok(rxe->ndev)) + struct net_device *ndev; + + ndev = rxe_ib_device_get_netdev(&rxe->ib_dev); + if (!ndev) + return; + + if (netif_running(ndev) && netif_carrier_ok(ndev)) rxe_port_up(rxe); else rxe_port_down(rxe); + + dev_put(ndev); } static int rxe_notify(struct notifier_block *not_blk, diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index 5c18f7e342f2..8a5fc20fd186 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -41,6 +41,7 @@ static int rxe_query_port(struct ib_device *ibdev, u32 port_num, struct ib_port_attr *attr) { struct rxe_dev *rxe = to_rdev(ibdev); + struct net_device *ndev; int err, ret; if (port_num != 1) { @@ -49,6 +50,12 @@ static int rxe_query_port(struct ib_device *ibdev, goto err_out; } + ndev = rxe_ib_device_get_netdev(ibdev); + if (!ndev) { + err = -ENODEV; + goto err_out; + } + memcpy(attr, &rxe->port.attr, sizeof(*attr)); mutex_lock(&rxe->usdev_lock); @@ -57,13 +64,14 @@ static int rxe_query_port(struct ib_device *ibdev, if (attr->state == IB_PORT_ACTIVE) attr->phys_state = IB_PORT_PHYS_STATE_LINK_UP; - else if (dev_get_flags(rxe->ndev) & IFF_UP) + else if (dev_get_flags(ndev) & IFF_UP) attr->phys_state = IB_PORT_PHYS_STATE_POLLING; else attr->phys_state = IB_PORT_PHYS_STATE_DISABLED; mutex_unlock(&rxe->usdev_lock); + dev_put(ndev); return ret; err_out: @@ -1425,9 +1433,16 @@ static const struct attribute_group rxe_attr_group = { static int rxe_enable_driver(struct ib_device *ib_dev) { struct rxe_dev *rxe = container_of(ib_dev, struct rxe_dev, ib_dev); + struct net_device *ndev; + + ndev = rxe_ib_device_get_netdev(ib_dev); + if (!ndev) + return -ENODEV; rxe_set_port_state(rxe); - dev_info(&rxe->ib_dev.dev, "added %s\n", netdev_name(rxe->ndev)); + dev_info(&rxe->ib_dev.dev, "added %s\n", netdev_name(ndev)); + + dev_put(ndev); return 0; } @@ -1495,7 +1510,8 @@ static const struct ib_device_ops rxe_dev_ops = { INIT_RDMA_OBJ_SIZE(ib_mw, rxe_mw, ibmw), }; -int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name) +int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name, + struct net_device *ndev) { int err; struct ib_device *dev = &rxe->ib_dev; @@ -1507,13 +1523,13 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name) dev->num_comp_vectors = num_possible_cpus(); dev->local_dma_lkey = 0; addrconf_addr_eui48((unsigned char *)&dev->node_guid, - rxe->ndev->dev_addr); + ndev->dev_addr); dev->uverbs_cmd_mask |= BIT_ULL(IB_USER_VERBS_CMD_POST_SEND) | BIT_ULL(IB_USER_VERBS_CMD_REQ_NOTIFY_CQ); ib_set_device_ops(dev, &rxe_dev_ops); - err = ib_device_set_netdev(&rxe->ib_dev, rxe->ndev, 1); + err = ib_device_set_netdev(&rxe->ib_dev, ndev, 1); if (err) return err; diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h index 3c1354f82283..6573ceec0ef5 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.h +++ b/drivers/infiniband/sw/rxe/rxe_verbs.h @@ -370,6 +370,7 @@ struct rxe_port { u32 qp_gsi_index; }; +#define RXE_PORT 1 struct rxe_dev { struct ib_device ib_dev; struct ib_device_attr attr; @@ -377,8 +378,6 @@ struct rxe_dev { int max_inline_data; struct mutex usdev_lock; - struct net_device *ndev; - struct rxe_pool uc_pool; struct rxe_pool pd_pool; struct rxe_pool ah_pool; @@ -406,6 +405,11 @@ struct rxe_dev { struct crypto_shash *tfm; }; +static inline struct net_device *rxe_ib_device_get_netdev(struct ib_device *dev) +{ + return ib_device_get_netdev(dev, RXE_PORT); +} + static inline void rxe_counter_inc(struct rxe_dev *rxe, enum rxe_counters index) { atomic64_inc(&rxe->stats_counters[index]); @@ -471,6 +475,7 @@ static inline struct rxe_pd *rxe_mw_pd(struct rxe_mw *mw) return to_rpd(mw->ibmw.pd); } -int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name); +int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name, + struct net_device *ndev); #endif /* RXE_VERBS_H */ diff --git a/drivers/infiniband/sw/siw/siw.h b/drivers/infiniband/sw/siw/siw.h index 86d4d6a2170e..ea5eee50dc39 100644 --- a/drivers/infiniband/sw/siw/siw.h +++ b/drivers/infiniband/sw/siw/siw.h @@ -46,6 +46,9 @@ */ #define SIW_IRQ_MAXBURST_SQ_ACTIVE 4 +/* There is always only a port 1 per siw device */ +#define SIW_PORT 1 + struct siw_dev_cap { int max_qp; int max_qp_wr; @@ -69,16 +72,12 @@ struct siw_pd { struct siw_device { struct ib_device base_dev; - struct net_device *netdev; struct siw_dev_cap attrs; u32 vendor_part_id; int numa_node; char raw_gid[ETH_ALEN]; - /* physical port state (only one port per device) */ - enum ib_port_state state; - spinlock_t lock; struct xarray qp_xa; diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c index 86323918a570..708b13993fdf 100644 --- a/drivers/infiniband/sw/siw/siw_cm.c +++ b/drivers/infiniband/sw/siw/siw_cm.c @@ -1759,6 +1759,7 @@ int siw_create_listen(struct iw_cm_id *id, int backlog) { struct socket *s; struct siw_cep *cep = NULL; + struct net_device *ndev = NULL; struct siw_device *sdev = to_siw_dev(id->device); int addr_family = id->local_addr.ss_family; int rv = 0; @@ -1779,9 +1780,15 @@ int siw_create_listen(struct iw_cm_id *id, int backlog) struct sockaddr_in *laddr = &to_sockaddr_in(id->local_addr); /* For wildcard addr, limit binding to current device only */ - if (ipv4_is_zeronet(laddr->sin_addr.s_addr)) - s->sk->sk_bound_dev_if = sdev->netdev->ifindex; - + if (ipv4_is_zeronet(laddr->sin_addr.s_addr)) { + ndev = ib_device_get_netdev(id->device, SIW_PORT); + if (ndev) { + s->sk->sk_bound_dev_if = ndev->ifindex; + } else { + rv = -ENODEV; + goto error; + } + } rv = s->ops->bind(s, (struct sockaddr *)laddr, sizeof(struct sockaddr_in)); } else { @@ -1797,9 +1804,15 @@ int siw_create_listen(struct iw_cm_id *id, int backlog) } /* For wildcard addr, limit binding to current device only */ - if (ipv6_addr_any(&laddr->sin6_addr)) - s->sk->sk_bound_dev_if = sdev->netdev->ifindex; - + if (ipv6_addr_any(&laddr->sin6_addr)) { + ndev = ib_device_get_netdev(id->device, SIW_PORT); + if (ndev) { + s->sk->sk_bound_dev_if = ndev->ifindex; + } else { + rv = -ENODEV; + goto error; + } + } rv = s->ops->bind(s, (struct sockaddr *)laddr, sizeof(struct sockaddr_in6)); } @@ -1860,6 +1873,7 @@ int siw_create_listen(struct iw_cm_id *id, int backlog) } list_add_tail(&cep->listenq, (struct list_head *)id->provider_data); cep->state = SIW_EPSTATE_LISTENING; + dev_put(ndev); siw_dbg(id->device, "Listen at laddr %pISp\n", &id->local_addr); @@ -1879,6 +1893,7 @@ error: siw_cep_set_free_and_put(cep); } sock_release(s); + dev_put(ndev); return rv; } diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c index 17abef48abcd..14d3103aee6f 100644 --- a/drivers/infiniband/sw/siw/siw_main.c +++ b/drivers/infiniband/sw/siw/siw_main.c @@ -287,7 +287,6 @@ static struct siw_device *siw_device_create(struct net_device *netdev) return NULL; base_dev = &sdev->base_dev; - sdev->netdev = netdev; if (netdev->addr_len) { memcpy(sdev->raw_gid, netdev->dev_addr, @@ -381,12 +380,10 @@ static int siw_netdev_event(struct notifier_block *nb, unsigned long event, switch (event) { case NETDEV_UP: - sdev->state = IB_PORT_ACTIVE; siw_port_event(sdev, 1, IB_EVENT_PORT_ACTIVE); break; case NETDEV_DOWN: - sdev->state = IB_PORT_DOWN; siw_port_event(sdev, 1, IB_EVENT_PORT_ERR); break; @@ -407,12 +404,8 @@ static int siw_netdev_event(struct notifier_block *nb, unsigned long event, siw_port_event(sdev, 1, IB_EVENT_LID_CHANGE); break; /* - * Todo: Below netdev events are currently not handled. + * All other events are not handled */ - case NETDEV_CHANGEMTU: - case NETDEV_CHANGE: - break; - default: break; } @@ -442,12 +435,6 @@ static int siw_newlink(const char *basedev_name, struct net_device *netdev) sdev = siw_device_create(netdev); if (sdev) { dev_dbg(&netdev->dev, "siw: new device\n"); - - if (netif_running(netdev) && netif_carrier_ok(netdev)) - sdev->state = IB_PORT_ACTIVE; - else - sdev->state = IB_PORT_DOWN; - ib_mark_name_assigned_by_user(&sdev->base_dev); rv = siw_device_register(sdev, basedev_name); if (rv) diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c index 986666c19378..7ca0297d68a4 100644 --- a/drivers/infiniband/sw/siw/siw_verbs.c +++ b/drivers/infiniband/sw/siw/siw_verbs.c @@ -171,21 +171,29 @@ int siw_query_device(struct ib_device *base_dev, struct ib_device_attr *attr, int siw_query_port(struct ib_device *base_dev, u32 port, struct ib_port_attr *attr) { - struct siw_device *sdev = to_siw_dev(base_dev); + struct net_device *ndev; int rv; memset(attr, 0, sizeof(*attr)); rv = ib_get_eth_speed(base_dev, port, &attr->active_speed, &attr->active_width); + if (rv) + return rv; + + ndev = ib_device_get_netdev(base_dev, SIW_PORT); + if (!ndev) + return -ENODEV; + attr->gid_tbl_len = 1; attr->max_msg_sz = -1; - attr->max_mtu = ib_mtu_int_to_enum(sdev->netdev->mtu); - attr->active_mtu = ib_mtu_int_to_enum(sdev->netdev->mtu); - attr->phys_state = sdev->state == IB_PORT_ACTIVE ? + attr->max_mtu = ib_mtu_int_to_enum(ndev->max_mtu); + attr->active_mtu = ib_mtu_int_to_enum(READ_ONCE(ndev->mtu)); + attr->phys_state = (netif_running(ndev) && netif_carrier_ok(ndev)) ? IB_PORT_PHYS_STATE_LINK_UP : IB_PORT_PHYS_STATE_DISABLED; + attr->state = attr->phys_state == IB_PORT_PHYS_STATE_LINK_UP ? + IB_PORT_ACTIVE : IB_PORT_DOWN; attr->port_cap_flags = IB_PORT_CM_SUP | IB_PORT_DEVICE_MGMT_SUP; - attr->state = sdev->state; /* * All zero * @@ -199,6 +207,7 @@ int siw_query_port(struct ib_device *base_dev, u32 port, * attr->subnet_timeout = 0; * attr->init_type_repy = 0; */ + dev_put(ndev); return rv; } @@ -505,21 +514,24 @@ int siw_query_qp(struct ib_qp *base_qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr) { struct siw_qp *qp; - struct siw_device *sdev; + struct net_device *ndev; - if (base_qp && qp_attr && qp_init_attr) { + if (base_qp && qp_attr && qp_init_attr) qp = to_siw_qp(base_qp); - sdev = to_siw_dev(base_qp->device); - } else { + else return -EINVAL; - } + + ndev = ib_device_get_netdev(base_qp->device, SIW_PORT); + if (!ndev) + return -ENODEV; + qp_attr->qp_state = siw_qp_state_to_ib_qp_state[qp->attrs.state]; qp_attr->cap.max_inline_data = SIW_MAX_INLINE; qp_attr->cap.max_send_wr = qp->attrs.sq_size; qp_attr->cap.max_send_sge = qp->attrs.sq_max_sges; qp_attr->cap.max_recv_wr = qp->attrs.rq_size; qp_attr->cap.max_recv_sge = qp->attrs.rq_max_sges; - qp_attr->path_mtu = ib_mtu_int_to_enum(sdev->netdev->mtu); + qp_attr->path_mtu = ib_mtu_int_to_enum(READ_ONCE(ndev->mtu)); qp_attr->max_rd_atomic = qp->attrs.irq_size; qp_attr->max_dest_rd_atomic = qp->attrs.orq_size; @@ -534,6 +546,7 @@ int siw_query_qp(struct ib_qp *base_qp, struct ib_qp_attr *qp_attr, qp_init_attr->cap = qp_attr->cap; + dev_put(ndev); return 0; } diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c index e83d95647852..ef4abdea3c2d 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c @@ -349,6 +349,7 @@ static int send_io_resp_imm(struct rtrs_srv_con *con, struct rtrs_srv_op *id, struct rtrs_srv_mr *srv_mr; bool need_inval = false; enum ib_send_flags flags; + struct ib_sge list; u32 imm; int err; @@ -401,7 +402,6 @@ static int send_io_resp_imm(struct rtrs_srv_con *con, struct rtrs_srv_op *id, imm = rtrs_to_io_rsp_imm(id->msg_id, errno, need_inval); imm_wr.wr.next = NULL; if (always_invalidate) { - struct ib_sge list; struct rtrs_msg_rkey_rsp *msg; srv_mr = &srv_path->mrs[id->msg_id]; diff --git a/drivers/interconnect/icc-clk.c b/drivers/interconnect/icc-clk.c index b956e4050f38..88f311c11020 100644 --- a/drivers/interconnect/icc-clk.c +++ b/drivers/interconnect/icc-clk.c @@ -116,6 +116,11 @@ struct icc_provider *icc_clk_register(struct device *dev, } node->name = devm_kasprintf(dev, GFP_KERNEL, "%s_master", data[i].name); + if (!node->name) { + ret = -ENOMEM; + goto err; + } + node->data = &qp->clocks[i]; icc_node_add(node, provider); /* link to the next node, slave */ @@ -129,6 +134,11 @@ struct icc_provider *icc_clk_register(struct device *dev, } node->name = devm_kasprintf(dev, GFP_KERNEL, "%s_slave", data[i].name); + if (!node->name) { + ret = -ENOMEM; + goto err; + } + /* no data for slave node */ icc_node_add(node, provider); onecell->nodes[j++] = node; diff --git a/drivers/interconnect/qcom/icc-rpm.c b/drivers/interconnect/qcom/icc-rpm.c index a8ed435f696c..ea1042d38128 100644 --- a/drivers/interconnect/qcom/icc-rpm.c +++ b/drivers/interconnect/qcom/icc-rpm.c @@ -503,6 +503,7 @@ int qnoc_probe(struct platform_device *pdev) GFP_KERNEL); if (!data) return -ENOMEM; + data->num_nodes = num_nodes; qp->num_intf_clks = cd_num; for (i = 0; i < cd_num; i++) @@ -597,7 +598,6 @@ regmap_done: data->nodes[i] = node; } - data->num_nodes = num_nodes; clk_bulk_disable_unprepare(qp->num_intf_clks, qp->intf_clks); diff --git a/drivers/macintosh/Kconfig b/drivers/macintosh/Kconfig index fb38f684444f..d00e713c1092 100644 --- a/drivers/macintosh/Kconfig +++ b/drivers/macintosh/Kconfig @@ -120,6 +120,7 @@ config PMAC_MEDIABAY config PMAC_BACKLIGHT bool "Backlight control for LCD screens" depends on PPC_PMAC && ADB_PMU && FB = y && (BROKEN || !PPC64) + depends on BACKLIGHT_CLASS_DEVICE=y select FB_BACKLIGHT help Say Y here to enable Macintosh specific extensions of the generic diff --git a/drivers/md/dm-ebs-target.c b/drivers/md/dm-ebs-target.c index ec5db1478b2f..18ae45dcbfb2 100644 --- a/drivers/md/dm-ebs-target.c +++ b/drivers/md/dm-ebs-target.c @@ -442,7 +442,7 @@ static int ebs_iterate_devices(struct dm_target *ti, static struct target_type ebs_target = { .name = "ebs", .version = {1, 0, 1}, - .features = DM_TARGET_PASSES_INTEGRITY, + .features = 0, .module = THIS_MODULE, .ctr = ebs_ctr, .dtr = ebs_dtr, diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index bf0f9dddd146..05cf4e3f2bbe 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -2332,10 +2332,9 @@ static struct thin_c *get_first_thin(struct pool *pool) struct thin_c *tc = NULL; rcu_read_lock(); - if (!list_empty(&pool->active_thins)) { - tc = list_entry_rcu(pool->active_thins.next, struct thin_c, list); + tc = list_first_or_null_rcu(&pool->active_thins, struct thin_c, list); + if (tc) thin_get(tc); - } rcu_read_unlock(); return tc; diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c index 62b1a44b8dd2..e61855da6461 100644 --- a/drivers/md/dm-verity-fec.c +++ b/drivers/md/dm-verity-fec.c @@ -40,35 +40,23 @@ static inline u64 fec_interleave(struct dm_verity *v, u64 offset) } /* - * Decode an RS block using Reed-Solomon. - */ -static int fec_decode_rs8(struct dm_verity *v, struct dm_verity_fec_io *fio, - u8 *data, u8 *fec, int neras) -{ - int i; - uint16_t par[DM_VERITY_FEC_RSM - DM_VERITY_FEC_MIN_RSN]; - - for (i = 0; i < v->fec->roots; i++) - par[i] = fec[i]; - - return decode_rs8(fio->rs, data, par, v->fec->rsn, NULL, neras, - fio->erasures, 0, NULL); -} - -/* * Read error-correcting codes for the requested RS block. Returns a pointer * to the data block. Caller is responsible for releasing buf. */ static u8 *fec_read_parity(struct dm_verity *v, u64 rsb, int index, - unsigned int *offset, struct dm_buffer **buf, - unsigned short ioprio) + unsigned int *offset, unsigned int par_buf_offset, + struct dm_buffer **buf, unsigned short ioprio) { u64 position, block, rem; u8 *res; + /* We have already part of parity bytes read, skip to the next block */ + if (par_buf_offset) + index++; + position = (index + rsb) * v->fec->roots; block = div64_u64_rem(position, v->fec->io_size, &rem); - *offset = (unsigned int)rem; + *offset = par_buf_offset ? 0 : (unsigned int)rem; res = dm_bufio_read_with_ioprio(v->fec->bufio, block, buf, ioprio); if (IS_ERR(res)) { @@ -128,11 +116,13 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_io *io, { int r, corrected = 0, res; struct dm_buffer *buf; - unsigned int n, i, offset; + unsigned int n, i, j, offset, par_buf_offset = 0; + uint16_t par_buf[DM_VERITY_FEC_RSM - DM_VERITY_FEC_MIN_RSN]; u8 *par, *block; struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size); - par = fec_read_parity(v, rsb, block_offset, &offset, &buf, bio_prio(bio)); + par = fec_read_parity(v, rsb, block_offset, &offset, + par_buf_offset, &buf, bio_prio(bio)); if (IS_ERR(par)) return PTR_ERR(par); @@ -142,7 +132,11 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_io *io, */ fec_for_each_buffer_rs_block(fio, n, i) { block = fec_buffer_rs_block(v, fio, n, i); - res = fec_decode_rs8(v, fio, block, &par[offset], neras); + for (j = 0; j < v->fec->roots - par_buf_offset; j++) + par_buf[par_buf_offset + j] = par[offset + j]; + /* Decode an RS block using Reed-Solomon */ + res = decode_rs8(fio->rs, block, par_buf, v->fec->rsn, + NULL, neras, fio->erasures, 0, NULL); if (res < 0) { r = res; goto error; @@ -155,12 +149,22 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_io *io, if (block_offset >= 1 << v->data_dev_block_bits) goto done; - /* read the next block when we run out of parity bytes */ - offset += v->fec->roots; + /* Read the next block when we run out of parity bytes */ + offset += (v->fec->roots - par_buf_offset); + /* Check if parity bytes are split between blocks */ + if (offset < v->fec->io_size && (offset + v->fec->roots) > v->fec->io_size) { + par_buf_offset = v->fec->io_size - offset; + for (j = 0; j < par_buf_offset; j++) + par_buf[j] = par[offset + j]; + offset += par_buf_offset; + } else + par_buf_offset = 0; + if (offset >= v->fec->io_size) { dm_bufio_release(buf); - par = fec_read_parity(v, rsb, block_offset, &offset, &buf, bio_prio(bio)); + par = fec_read_parity(v, rsb, block_offset, &offset, + par_buf_offset, &buf, bio_prio(bio)); if (IS_ERR(par)) return PTR_ERR(par); } @@ -724,10 +728,7 @@ int verity_fec_ctr(struct dm_verity *v) return -E2BIG; } - if ((f->roots << SECTOR_SHIFT) & ((1 << v->data_dev_block_bits) - 1)) - f->io_size = 1 << v->data_dev_block_bits; - else - f->io_size = v->fec->roots << SECTOR_SHIFT; + f->io_size = 1 << v->data_dev_block_bits; f->bufio = dm_bufio_client_create(f->dev->bdev, f->io_size, diff --git a/drivers/md/persistent-data/dm-array.c b/drivers/md/persistent-data/dm-array.c index 157c9bd2fed7..8f8792e55806 100644 --- a/drivers/md/persistent-data/dm-array.c +++ b/drivers/md/persistent-data/dm-array.c @@ -917,23 +917,27 @@ static int load_ablock(struct dm_array_cursor *c) if (c->block) unlock_ablock(c->info, c->block); - c->block = NULL; - c->ab = NULL; c->index = 0; r = dm_btree_cursor_get_value(&c->cursor, &key, &value_le); if (r) { DMERR("dm_btree_cursor_get_value failed"); - dm_btree_cursor_end(&c->cursor); + goto out; } else { r = get_ablock(c->info, le64_to_cpu(value_le), &c->block, &c->ab); if (r) { DMERR("get_ablock failed"); - dm_btree_cursor_end(&c->cursor); + goto out; } } + return 0; + +out: + dm_btree_cursor_end(&c->cursor); + c->block = NULL; + c->ab = NULL; return r; } @@ -956,10 +960,10 @@ EXPORT_SYMBOL_GPL(dm_array_cursor_begin); void dm_array_cursor_end(struct dm_array_cursor *c) { - if (c->block) { + if (c->block) unlock_ablock(c->info, c->block); - dm_btree_cursor_end(&c->cursor); - } + + dm_btree_cursor_end(&c->cursor); } EXPORT_SYMBOL_GPL(dm_array_cursor_end); @@ -999,6 +1003,7 @@ int dm_array_cursor_skip(struct dm_array_cursor *c, uint32_t count) } count -= remaining; + c->index += (remaining - 1); r = dm_array_cursor_next(c); } while (!r); diff --git a/drivers/media/dvb-frontends/dib3000mb.c b/drivers/media/dvb-frontends/dib3000mb.c index 822639f11c04..63bc7b74bc8b 100644 --- a/drivers/media/dvb-frontends/dib3000mb.c +++ b/drivers/media/dvb-frontends/dib3000mb.c @@ -51,7 +51,7 @@ MODULE_PARM_DESC(debug, "set debugging level (1=info,2=xfer,4=setfe,8=getfe (|-a static int dib3000_read_reg(struct dib3000_state *state, u16 reg) { u8 wb[] = { ((reg >> 8) | 0x80) & 0xff, reg & 0xff }; - u8 rb[2]; + u8 rb[2] = {}; struct i2c_msg msg[] = { { .addr = state->config.demod_address, .flags = 0, .buf = wb, .len = 2 }, { .addr = state->config.demod_address, .flags = I2C_M_RD, .buf = rb, .len = 2 }, diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c index eea709d93820..47c302745c1d 100644 --- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c +++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c @@ -1188,7 +1188,8 @@ err: return ret; } -static +/* clang stack usage explodes if this is inlined */ +static noinline_for_stack void vdec_vp9_slice_map_counts_eob_coef(unsigned int i, unsigned int j, unsigned int k, struct vdec_vp9_slice_frame_counts *counts, struct v4l2_vp9_frame_symbol_counts *counts_helper) diff --git a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c index e616e3ec2b42..3c1359d8d4e6 100644 --- a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c +++ b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c @@ -148,7 +148,7 @@ static int pci1xxxx_gpio_set_config(struct gpio_chip *gpio, unsigned int offset, pci1xxx_assign_bit(priv->reg_base, OPENDRAIN_OFFSET(offset), (offset % 32), true); break; default: - ret = -EOPNOTSUPP; + ret = -ENOTSUPP; break; } spin_unlock_irqrestore(&priv->lock, flags); @@ -277,7 +277,7 @@ static irqreturn_t pci1xxxx_gpio_irq_handler(int irq, void *dev_id) writel(BIT(bit), priv->reg_base + INTR_STATUS_OFFSET(gpiobank)); spin_unlock_irqrestore(&priv->lock, flags); irq = irq_find_mapping(gc->irq.domain, (bit + (gpiobank * 32))); - generic_handle_irq(irq); + handle_nested_irq(irq); } } spin_lock_irqsave(&priv->lock, flags); diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index efb0d2d5716b..af445d3f8e2a 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -3070,6 +3070,7 @@ release_clk: msdc_gate_clock(host); platform_set_drvdata(pdev, NULL); release_mem: + device_init_wakeup(&pdev->dev, false); if (host->dma.gpd) dma_free_coherent(&pdev->dev, 2 * sizeof(struct mt_gpdma_desc), @@ -3103,6 +3104,7 @@ static void msdc_drv_remove(struct platform_device *pdev) host->dma.gpd, host->dma.gpd_addr); dma_free_coherent(&pdev->dev, MAX_BD_NUM * sizeof(struct mt_bdma_desc), host->dma.bd, host->dma.bd_addr); + device_init_wakeup(&pdev->dev, false); } static void msdc_save_reg(struct msdc_host *host) diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index e00208535bd1..319f0ebbe652 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -1867,20 +1867,20 @@ static int sdhci_msm_program_key(struct cqhci_host *cq_host, struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host); union cqhci_crypto_cap_entry cap; + if (!(cfg->config_enable & CQHCI_CRYPTO_CONFIGURATION_ENABLE)) + return qcom_ice_evict_key(msm_host->ice, slot); + /* Only AES-256-XTS has been tested so far. */ cap = cq_host->crypto_cap_array[cfg->crypto_cap_idx]; if (cap.algorithm_id != CQHCI_CRYPTO_ALG_AES_XTS || cap.key_size != CQHCI_CRYPTO_KEY_SIZE_256) return -EINVAL; - if (cfg->config_enable & CQHCI_CRYPTO_CONFIGURATION_ENABLE) - return qcom_ice_program_key(msm_host->ice, - QCOM_ICE_CRYPTO_ALG_AES_XTS, - QCOM_ICE_CRYPTO_KEY_SIZE_256, - cfg->crypto_key, - cfg->data_unit_size, slot); - else - return qcom_ice_evict_key(msm_host->ice, slot); + return qcom_ice_program_key(msm_host->ice, + QCOM_ICE_CRYPTO_ALG_AES_XTS, + QCOM_ICE_CRYPTO_KEY_SIZE_256, + cfg->crypto_key, + cfg->data_unit_size, slot); } #else /* CONFIG_MMC_CRYPTO */ diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c index 4d402b601883..b2f5c3f8b839 100644 --- a/drivers/mmc/host/sdhci-tegra.c +++ b/drivers/mmc/host/sdhci-tegra.c @@ -1525,7 +1525,6 @@ static const struct sdhci_pltfm_data sdhci_tegra186_pdata = { .quirks = SDHCI_QUIRK_BROKEN_TIMEOUT_VAL | SDHCI_QUIRK_SINGLE_POWER_WRITE | SDHCI_QUIRK_NO_HISPD_BIT | - SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC | SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN, .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN | SDHCI_QUIRK2_ISSUE_CMD_DAT_RESET_TOGETHER, diff --git a/drivers/mtd/nand/raw/arasan-nand-controller.c b/drivers/mtd/nand/raw/arasan-nand-controller.c index db42aa0c7b6b..865754737f5f 100644 --- a/drivers/mtd/nand/raw/arasan-nand-controller.c +++ b/drivers/mtd/nand/raw/arasan-nand-controller.c @@ -1409,8 +1409,8 @@ static int anfc_parse_cs(struct arasan_nfc *nfc) * case, the "not" chosen CS is assigned to nfc->spare_cs and selected * whenever a GPIO CS must be asserted. */ - if (nfc->cs_array && nfc->ncs > 2) { - if (!nfc->cs_array[0] && !nfc->cs_array[1]) { + if (nfc->cs_array) { + if (nfc->ncs > 2 && !nfc->cs_array[0] && !nfc->cs_array[1]) { dev_err(nfc->dev, "Assign a single native CS when using GPIOs\n"); return -EINVAL; @@ -1478,8 +1478,15 @@ static int anfc_probe(struct platform_device *pdev) static void anfc_remove(struct platform_device *pdev) { + int i; struct arasan_nfc *nfc = platform_get_drvdata(pdev); + for (i = 0; i < nfc->ncs; i++) { + if (nfc->cs_array[i]) { + gpiod_put(nfc->cs_array[i]); + } + } + anfc_chips_cleanup(nfc); } diff --git a/drivers/mtd/nand/raw/atmel/pmecc.c b/drivers/mtd/nand/raw/atmel/pmecc.c index a22aab4ed4e8..3c7dee1be21d 100644 --- a/drivers/mtd/nand/raw/atmel/pmecc.c +++ b/drivers/mtd/nand/raw/atmel/pmecc.c @@ -380,10 +380,8 @@ atmel_pmecc_create_user(struct atmel_pmecc *pmecc, user->delta = user->dmu + req->ecc.strength + 1; gf_tables = atmel_pmecc_get_gf_tables(req); - if (IS_ERR(gf_tables)) { - kfree(user); + if (IS_ERR(gf_tables)) return ERR_CAST(gf_tables); - } user->gf_tables = gf_tables; diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c index 8db7fc424571..70d6c2250f32 100644 --- a/drivers/mtd/nand/raw/diskonchip.c +++ b/drivers/mtd/nand/raw/diskonchip.c @@ -1098,7 +1098,7 @@ static inline int __init inftl_partscan(struct mtd_info *mtd, struct mtd_partiti (i == 0) && (ip->firstUnit > 0)) { parts[0].name = " DiskOnChip IPL / Media Header partition"; parts[0].offset = 0; - parts[0].size = mtd->erasesize * ip->firstUnit; + parts[0].size = (uint64_t)mtd->erasesize * ip->firstUnit; numparts = 1; } diff --git a/drivers/mtd/nand/raw/omap2.c b/drivers/mtd/nand/raw/omap2.c index d9141f3c0dd1..b8af3a3533fc 100644 --- a/drivers/mtd/nand/raw/omap2.c +++ b/drivers/mtd/nand/raw/omap2.c @@ -254,6 +254,10 @@ static int omap_prefetch_reset(int cs, struct omap_nand_info *info) /** * omap_nand_data_in_pref - NAND data in using prefetch engine + * @chip: NAND chip + * @buf: output buffer where NAND data is placed into + * @len: length of transfer + * @force_8bit: force 8-bit transfers */ static void omap_nand_data_in_pref(struct nand_chip *chip, void *buf, unsigned int len, bool force_8bit) @@ -297,6 +301,10 @@ static void omap_nand_data_in_pref(struct nand_chip *chip, void *buf, /** * omap_nand_data_out_pref - NAND data out using Write Posting engine + * @chip: NAND chip + * @buf: input buffer that is sent to NAND + * @len: length of transfer + * @force_8bit: force 8-bit transfers */ static void omap_nand_data_out_pref(struct nand_chip *chip, const void *buf, unsigned int len, @@ -440,6 +448,10 @@ out_copy: /** * omap_nand_data_in_dma_pref - NAND data in using DMA and Prefetch + * @chip: NAND chip + * @buf: output buffer where NAND data is placed into + * @len: length of transfer + * @force_8bit: force 8-bit transfers */ static void omap_nand_data_in_dma_pref(struct nand_chip *chip, void *buf, unsigned int len, bool force_8bit) @@ -460,6 +472,10 @@ static void omap_nand_data_in_dma_pref(struct nand_chip *chip, void *buf, /** * omap_nand_data_out_dma_pref - NAND data out using DMA and write posting + * @chip: NAND chip + * @buf: input buffer that is sent to NAND + * @len: length of transfer + * @force_8bit: force 8-bit transfers */ static void omap_nand_data_out_dma_pref(struct nand_chip *chip, const void *buf, unsigned int len, diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 533bcb77c9f9..97cd8bbf2e32 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1220,20 +1220,32 @@ static void m_can_coalescing_update(struct m_can_classdev *cdev, u32 ir) static int m_can_interrupt_handler(struct m_can_classdev *cdev) { struct net_device *dev = cdev->net; - u32 ir; + u32 ir = 0, ir_read; int ret; if (pm_runtime_suspended(cdev->dev)) return IRQ_NONE; - ir = m_can_read(cdev, M_CAN_IR); + /* The m_can controller signals its interrupt status as a level, but + * depending in the integration the CPU may interpret the signal as + * edge-triggered (for example with m_can_pci). For these + * edge-triggered integrations, we must observe that IR is 0 at least + * once to be sure that the next interrupt will generate an edge. + */ + while ((ir_read = m_can_read(cdev, M_CAN_IR)) != 0) { + ir |= ir_read; + + /* ACK all irqs */ + m_can_write(cdev, M_CAN_IR, ir); + + if (!cdev->irq_edge_triggered) + break; + } + m_can_coalescing_update(cdev, ir); if (!ir) return IRQ_NONE; - /* ACK all irqs */ - m_can_write(cdev, M_CAN_IR, ir); - if (cdev->ops->clear_interrupts) cdev->ops->clear_interrupts(cdev); @@ -1695,6 +1707,14 @@ static int m_can_dev_setup(struct m_can_classdev *cdev) return -EINVAL; } + /* Write the INIT bit, in case no hardware reset has happened before + * the probe (for example, it was observed that the Intel Elkhart Lake + * SoCs do not properly reset the CAN controllers on reboot) + */ + err = m_can_cccr_update_bits(cdev, CCCR_INIT, CCCR_INIT); + if (err) + return err; + if (!cdev->is_peripheral) netif_napi_add(dev, &cdev->napi, m_can_poll); @@ -1746,11 +1766,7 @@ static int m_can_dev_setup(struct m_can_classdev *cdev) return -EINVAL; } - /* Forcing standby mode should be redundant, as the chip should be in - * standby after a reset. Write the INIT bit anyways, should the chip - * be configured by previous stage. - */ - return m_can_cccr_update_bits(cdev, CCCR_INIT, CCCR_INIT); + return 0; } static void m_can_stop(struct net_device *dev) diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h index 92b2bd8628e6..ef39e8e527ab 100644 --- a/drivers/net/can/m_can/m_can.h +++ b/drivers/net/can/m_can/m_can.h @@ -99,6 +99,7 @@ struct m_can_classdev { int pm_clock_support; int pm_wake_source; int is_peripheral; + bool irq_edge_triggered; // Cached M_CAN_IE register content u32 active_interrupts; diff --git a/drivers/net/can/m_can/m_can_pci.c b/drivers/net/can/m_can/m_can_pci.c index d72fe771dfc7..9ad7419f88f8 100644 --- a/drivers/net/can/m_can/m_can_pci.c +++ b/drivers/net/can/m_can/m_can_pci.c @@ -127,6 +127,7 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) mcan_class->pm_clock_support = 1; mcan_class->pm_wake_source = 0; mcan_class->can.clock.freq = id->driver_data; + mcan_class->irq_edge_triggered = true; mcan_class->ops = &m_can_pci_ops; pci_set_drvdata(pci, mcan_class); diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index d16817e0476f..29fe79ea74cd 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -2,7 +2,7 @@ /* * Microchip KSZ9477 switch driver main logic * - * Copyright (C) 2017-2019 Microchip Technology Inc. + * Copyright (C) 2017-2024 Microchip Technology Inc. */ #include <linux/kernel.h> @@ -983,26 +983,51 @@ void ksz9477_get_caps(struct ksz_device *dev, int port, int ksz9477_set_ageing_time(struct ksz_device *dev, unsigned int msecs) { u32 secs = msecs / 1000; - u8 value; - u8 data; + u8 data, mult, value; + u32 max_val; int ret; - value = FIELD_GET(SW_AGE_PERIOD_7_0_M, secs); +#define MAX_TIMER_VAL ((1 << 8) - 1) - ret = ksz_write8(dev, REG_SW_LUE_CTRL_3, value); - if (ret < 0) - return ret; + /* The aging timer comprises a 3-bit multiplier and an 8-bit second + * value. Either of them cannot be zero. The maximum timer is then + * 7 * 255 = 1785 seconds. + */ + if (!secs) + secs = 1; - data = FIELD_GET(SW_AGE_PERIOD_10_8_M, secs); + /* Return error if too large. */ + else if (secs > 7 * MAX_TIMER_VAL) + return -EINVAL; ret = ksz_read8(dev, REG_SW_LUE_CTRL_0, &value); if (ret < 0) return ret; - value &= ~SW_AGE_CNT_M; - value |= FIELD_PREP(SW_AGE_CNT_M, data); + /* Check whether there is need to update the multiplier. */ + mult = FIELD_GET(SW_AGE_CNT_M, value); + max_val = MAX_TIMER_VAL; + if (mult > 0) { + /* Try to use the same multiplier already in the register as + * the hardware default uses multiplier 4 and 75 seconds for + * 300 seconds. + */ + max_val = DIV_ROUND_UP(secs, mult); + if (max_val > MAX_TIMER_VAL || max_val * mult != secs) + max_val = MAX_TIMER_VAL; + } + + data = DIV_ROUND_UP(secs, max_val); + if (mult != data) { + value &= ~SW_AGE_CNT_M; + value |= FIELD_PREP(SW_AGE_CNT_M, data); + ret = ksz_write8(dev, REG_SW_LUE_CTRL_0, value); + if (ret < 0) + return ret; + } - return ksz_write8(dev, REG_SW_LUE_CTRL_0, value); + value = DIV_ROUND_UP(secs, data); + return ksz_write8(dev, REG_SW_LUE_CTRL_3, value); } void ksz9477_port_queue_split(struct ksz_device *dev, int port) diff --git a/drivers/net/dsa/microchip/ksz9477_reg.h b/drivers/net/dsa/microchip/ksz9477_reg.h index 04235c22bf40..ff579920078e 100644 --- a/drivers/net/dsa/microchip/ksz9477_reg.h +++ b/drivers/net/dsa/microchip/ksz9477_reg.h @@ -2,7 +2,7 @@ /* * Microchip KSZ9477 register definitions * - * Copyright (C) 2017-2018 Microchip Technology Inc. + * Copyright (C) 2017-2024 Microchip Technology Inc. */ #ifndef __KSZ9477_REGS_H @@ -165,8 +165,6 @@ #define SW_VLAN_ENABLE BIT(7) #define SW_DROP_INVALID_VID BIT(6) #define SW_AGE_CNT_M GENMASK(5, 3) -#define SW_AGE_CNT_S 3 -#define SW_AGE_PERIOD_10_8_M GENMASK(10, 8) #define SW_RESV_MCAST_ENABLE BIT(2) #define SW_HASH_OPTION_M 0x03 #define SW_HASH_OPTION_CRC 1 diff --git a/drivers/net/dsa/microchip/lan937x_main.c b/drivers/net/dsa/microchip/lan937x_main.c index b7652efd632e..b1ae3b9de3d1 100644 --- a/drivers/net/dsa/microchip/lan937x_main.c +++ b/drivers/net/dsa/microchip/lan937x_main.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* Microchip LAN937X switch driver main logic - * Copyright (C) 2019-2022 Microchip Technology Inc. + * Copyright (C) 2019-2024 Microchip Technology Inc. */ #include <linux/kernel.h> #include <linux/module.h> @@ -461,10 +461,66 @@ int lan937x_change_mtu(struct ksz_device *dev, int port, int new_mtu) int lan937x_set_ageing_time(struct ksz_device *dev, unsigned int msecs) { - u32 secs = msecs / 1000; - u32 value; + u8 data, mult, value8; + bool in_msec = false; + u32 max_val, value; + u32 secs = msecs; int ret; +#define MAX_TIMER_VAL ((1 << 20) - 1) + + /* The aging timer comprises a 3-bit multiplier and a 20-bit second + * value. Either of them cannot be zero. The maximum timer is then + * 7 * 1048575 = 7340025 seconds. As this value is too large for + * practical use it can be interpreted as microseconds, making the + * maximum timer 7340 seconds with finer control. This allows for + * maximum 122 minutes compared to 29 minutes in KSZ9477 switch. + */ + if (msecs % 1000) + in_msec = true; + else + secs /= 1000; + if (!secs) + secs = 1; + + /* Return error if too large. */ + else if (secs > 7 * MAX_TIMER_VAL) + return -EINVAL; + + /* Configure how to interpret the number value. */ + ret = ksz_rmw8(dev, REG_SW_LUE_CTRL_2, SW_AGE_CNT_IN_MICROSEC, + in_msec ? SW_AGE_CNT_IN_MICROSEC : 0); + if (ret < 0) + return ret; + + ret = ksz_read8(dev, REG_SW_LUE_CTRL_0, &value8); + if (ret < 0) + return ret; + + /* Check whether there is need to update the multiplier. */ + mult = FIELD_GET(SW_AGE_CNT_M, value8); + max_val = MAX_TIMER_VAL; + if (mult > 0) { + /* Try to use the same multiplier already in the register as + * the hardware default uses multiplier 4 and 75 seconds for + * 300 seconds. + */ + max_val = DIV_ROUND_UP(secs, mult); + if (max_val > MAX_TIMER_VAL || max_val * mult != secs) + max_val = MAX_TIMER_VAL; + } + + data = DIV_ROUND_UP(secs, max_val); + if (mult != data) { + value8 &= ~SW_AGE_CNT_M; + value8 |= FIELD_PREP(SW_AGE_CNT_M, data); + ret = ksz_write8(dev, REG_SW_LUE_CTRL_0, value8); + if (ret < 0) + return ret; + } + + secs = DIV_ROUND_UP(secs, data); + value = FIELD_GET(SW_AGE_PERIOD_7_0_M, secs); ret = ksz_write8(dev, REG_SW_AGE_PERIOD__1, value); diff --git a/drivers/net/dsa/microchip/lan937x_reg.h b/drivers/net/dsa/microchip/lan937x_reg.h index 4ec93e421da4..72042fd64e5b 100644 --- a/drivers/net/dsa/microchip/lan937x_reg.h +++ b/drivers/net/dsa/microchip/lan937x_reg.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Microchip LAN937X switch register definitions - * Copyright (C) 2019-2021 Microchip Technology Inc. + * Copyright (C) 2019-2024 Microchip Technology Inc. */ #ifndef __LAN937X_REG_H #define __LAN937X_REG_H @@ -56,8 +56,7 @@ #define SW_VLAN_ENABLE BIT(7) #define SW_DROP_INVALID_VID BIT(6) -#define SW_AGE_CNT_M 0x7 -#define SW_AGE_CNT_S 3 +#define SW_AGE_CNT_M GENMASK(5, 3) #define SW_RESV_MCAST_ENABLE BIT(2) #define REG_SW_LUE_CTRL_1 0x0311 @@ -70,6 +69,10 @@ #define SW_FAST_AGING BIT(1) #define SW_LINK_AUTO_AGING BIT(0) +#define REG_SW_LUE_CTRL_2 0x0312 + +#define SW_AGE_CNT_IN_MICROSEC BIT(7) + #define REG_SW_AGE_PERIOD__1 0x0313 #define SW_AGE_PERIOD_7_0_M GENMASK(7, 0) diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c index 2681889162a2..44971e71991f 100644 --- a/drivers/net/ethernet/amd/pds_core/devlink.c +++ b/drivers/net/ethernet/amd/pds_core/devlink.c @@ -118,7 +118,7 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req, if (err && err != -EIO) return err; - listlen = fw_list.num_fw_slots; + listlen = min(fw_list.num_fw_slots, ARRAY_SIZE(fw_list.fw_names)); for (i = 0; i < listlen; i++) { if (i < ARRAY_SIZE(fw_slotnames)) strscpy(buf, fw_slotnames[i], sizeof(buf)); diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 42672c63f108..bc4e1f3b3752 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1933,7 +1933,11 @@ static int bcm_sysport_open(struct net_device *dev) unsigned int i; int ret; - clk_prepare_enable(priv->clk); + ret = clk_prepare_enable(priv->clk); + if (ret) { + netdev_err(dev, "could not enable priv clock\n"); + return ret; + } /* Reset UniMAC */ umac_reset(priv); @@ -2591,7 +2595,11 @@ static int bcm_sysport_probe(struct platform_device *pdev) goto err_deregister_notifier; } - clk_prepare_enable(priv->clk); + ret = clk_prepare_enable(priv->clk); + if (ret) { + dev_err(&pdev->dev, "could not enable priv clock\n"); + goto err_deregister_netdev; + } priv->rev = topctrl_readl(priv, REV_CNTL) & REV_MASK; dev_info(&pdev->dev, @@ -2605,6 +2613,8 @@ static int bcm_sysport_probe(struct platform_device *pdev) return 0; +err_deregister_netdev: + unregister_netdev(dev); err_deregister_notifier: unregister_netdevice_notifier(&priv->netdev_notifier); err_deregister_fixed_link: @@ -2774,7 +2784,12 @@ static int __maybe_unused bcm_sysport_resume(struct device *d) if (!netif_running(dev)) return 0; - clk_prepare_enable(priv->clk); + ret = clk_prepare_enable(priv->clk); + if (ret) { + netdev_err(dev, "could not enable priv clock\n"); + return ret; + } + if (priv->wolopts) clk_disable_unprepare(priv->wol_clk); diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c index ecce23cecbea..4e266ce41180 100644 --- a/drivers/net/ethernet/broadcom/bgmac-platform.c +++ b/drivers/net/ethernet/broadcom/bgmac-platform.c @@ -171,6 +171,7 @@ static int platform_phy_connect(struct bgmac *bgmac) static int bgmac_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; + struct device_node *phy_node; struct bgmac *bgmac; struct resource *regs; int ret; @@ -236,7 +237,9 @@ static int bgmac_probe(struct platform_device *pdev) bgmac->cco_ctl_maskset = platform_bgmac_cco_ctl_maskset; bgmac->get_bus_clock = platform_bgmac_get_bus_clock; bgmac->cmn_maskset32 = platform_bgmac_cmn_maskset32; - if (of_parse_phandle(np, "phy-handle", 0)) { + phy_node = of_parse_phandle(np, "phy-handle", 0); + if (phy_node) { + of_node_put(phy_node); bgmac->phy_connect = platform_phy_connect; } else { bgmac->phy_connect = bgmac_phy_connect_direct; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index b86f980fa7ea..aeaa74f03046 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2897,6 +2897,13 @@ static int bnxt_hwrm_handler(struct bnxt *bp, struct tx_cmp *txcmp) return 0; } +static bool bnxt_vnic_is_active(struct bnxt *bp) +{ + struct bnxt_vnic_info *vnic = &bp->vnic_info[0]; + + return vnic->fw_vnic_id != INVALID_HW_RING_ID && vnic->mru > 0; +} + static irqreturn_t bnxt_msix(int irq, void *dev_instance) { struct bnxt_napi *bnapi = dev_instance; @@ -3164,7 +3171,7 @@ static int bnxt_poll(struct napi_struct *napi, int budget) break; } } - if (bp->flags & BNXT_FLAG_DIM) { + if ((bp->flags & BNXT_FLAG_DIM) && bnxt_vnic_is_active(bp)) { struct dim_sample dim_sample = {}; dim_update_sample(cpr->event_ctr, @@ -3295,7 +3302,7 @@ static int bnxt_poll_p5(struct napi_struct *napi, int budget) poll_done: cpr_rx = &cpr->cp_ring_arr[0]; if (cpr_rx->cp_ring_type == BNXT_NQ_HDL_TYPE_RX && - (bp->flags & BNXT_FLAG_DIM)) { + (bp->flags & BNXT_FLAG_DIM) && bnxt_vnic_is_active(bp)) { struct dim_sample dim_sample = {}; dim_update_sample(cpr->event_ctr, @@ -7266,6 +7273,26 @@ err_out: return rc; } +static void bnxt_cancel_dim(struct bnxt *bp) +{ + int i; + + /* DIM work is initialized in bnxt_enable_napi(). Proceed only + * if NAPI is enabled. + */ + if (!bp->bnapi || test_bit(BNXT_STATE_NAPI_DISABLED, &bp->state)) + return; + + /* Make sure NAPI sees that the VNIC is disabled */ + synchronize_net(); + for (i = 0; i < bp->rx_nr_rings; i++) { + struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; + struct bnxt_napi *bnapi = rxr->bnapi; + + cancel_work_sync(&bnapi->cp_ring.dim.work); + } +} + static int hwrm_ring_free_send_msg(struct bnxt *bp, struct bnxt_ring_struct *ring, u32 ring_type, int cmpl_ring_id) @@ -7366,6 +7393,7 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path) } } + bnxt_cancel_dim(bp); for (i = 0; i < bp->rx_nr_rings; i++) { bnxt_hwrm_rx_ring_free(bp, &bp->rx_ring[i], close_path); bnxt_hwrm_rx_agg_ring_free(bp, &bp->rx_ring[i], close_path); @@ -11309,8 +11337,6 @@ static void bnxt_disable_napi(struct bnxt *bp) if (bnapi->in_reset) cpr->sw_stats->rx.rx_resets++; napi_disable(&bnapi->napi); - if (bnapi->rx_ring) - cancel_work_sync(&cpr->dim.work); } } @@ -15572,8 +15598,10 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx) bnxt_hwrm_vnic_update(bp, vnic, VNIC_UPDATE_REQ_ENABLES_MRU_VALID); } - + /* Make sure NAPI sees that the VNIC is disabled */ + synchronize_net(); rxr = &bp->rx_ring[idx]; + cancel_work_sync(&rxr->bnapi->cp_ring.dim.work); bnxt_hwrm_rx_ring_free(bp, rxr, false); bnxt_hwrm_rx_agg_ring_free(bp, rxr, false); rxr->rx_next_cons = 0; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index b771c84cdd89..0ed26e3a28f4 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -208,7 +208,7 @@ int bnxt_send_msg(struct bnxt_en_dev *edev, rc = hwrm_req_replace(bp, req, fw_msg->msg, fw_msg->msg_len); if (rc) - return rc; + goto drop_req; hwrm_req_timeout(bp, req, fw_msg->timeout); resp = hwrm_req_hold(bp, req); @@ -220,6 +220,7 @@ int bnxt_send_msg(struct bnxt_en_dev *edev, memcpy(fw_msg->resp, resp, resp_len); } +drop_req: hwrm_req_drop(bp, req); return rc; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index bc3af0054406..604dcfd49aa4 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -1799,7 +1799,10 @@ void cxgb4_remove_tid(struct tid_info *t, unsigned int chan, unsigned int tid, struct adapter *adap = container_of(t, struct adapter, tids); struct sk_buff *skb; - WARN_ON(tid_out_of_range(&adap->tids, tid)); + if (tid_out_of_range(&adap->tids, tid)) { + dev_err(adap->pdev_dev, "tid %d out of range\n", tid); + return; + } if (t->tid_tab[tid - adap->tids.tid_base]) { t->tid_tab[tid - adap->tids.tid_base] = NULL; diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c index 96fd31d75dfd..daa1ebaef511 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c @@ -346,8 +346,9 @@ static struct sk_buff *copy_gl_to_skb_pkt(const struct pkt_gl *gl, * driver. Once driver synthesizes cpl_pass_accept_req the skb will go * through the regular cpl_pass_accept_req processing in TOM. */ - skb = alloc_skb(gl->tot_len + sizeof(struct cpl_pass_accept_req) - - pktshift, GFP_ATOMIC); + skb = alloc_skb(size_add(gl->tot_len, + sizeof(struct cpl_pass_accept_req)) - + pktshift, GFP_ATOMIC); if (unlikely(!skb)) return NULL; __skb_put(skb, gl->tot_len + sizeof(struct cpl_pass_accept_req) diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index dd92949bb214..8167cc5fb0df 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -1140,6 +1140,7 @@ int gve_xdp_xmit_one(struct gve_priv *priv, struct gve_tx_ring *tx, void gve_xdp_tx_flush(struct gve_priv *priv, u32 xdp_qid); bool gve_tx_poll(struct gve_notify_block *block, int budget); bool gve_xdp_poll(struct gve_notify_block *block, int budget); +int gve_xsk_tx_poll(struct gve_notify_block *block, int budget); int gve_tx_alloc_rings_gqi(struct gve_priv *priv, struct gve_tx_alloc_rings_cfg *cfg); void gve_tx_free_rings_gqi(struct gve_priv *priv, diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index e171ca248f9a..533e659b15b3 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -333,6 +333,14 @@ int gve_napi_poll(struct napi_struct *napi, int budget) if (block->rx) { work_done = gve_rx_poll(block, budget); + + /* Poll XSK TX as part of RX NAPI. Setup re-poll based on max of + * TX and RX work done. + */ + if (priv->xdp_prog) + work_done = max_t(int, work_done, + gve_xsk_tx_poll(block, budget)); + reschedule |= work_done == budget; } @@ -922,11 +930,13 @@ static void gve_init_sync_stats(struct gve_priv *priv) static void gve_tx_get_curr_alloc_cfg(struct gve_priv *priv, struct gve_tx_alloc_rings_cfg *cfg) { + int num_xdp_queues = priv->xdp_prog ? priv->rx_cfg.num_queues : 0; + cfg->qcfg = &priv->tx_cfg; cfg->raw_addressing = !gve_is_qpl(priv); cfg->ring_size = priv->tx_desc_cnt; cfg->start_idx = 0; - cfg->num_rings = gve_num_tx_queues(priv); + cfg->num_rings = priv->tx_cfg.num_queues + num_xdp_queues; cfg->tx = priv->tx; } @@ -1623,8 +1633,8 @@ static int gve_xsk_pool_enable(struct net_device *dev, if (err) return err; - /* If XDP prog is not installed, return */ - if (!priv->xdp_prog) + /* If XDP prog is not installed or interface is down, return. */ + if (!priv->xdp_prog || !netif_running(dev)) return 0; rx = &priv->rx[qid]; @@ -1669,21 +1679,16 @@ static int gve_xsk_pool_disable(struct net_device *dev, if (qid >= priv->rx_cfg.num_queues) return -EINVAL; - /* If XDP prog is not installed, unmap DMA and return */ - if (!priv->xdp_prog) - goto done; - - tx_qid = gve_xdp_tx_queue_id(priv, qid); - if (!netif_running(dev)) { - priv->rx[qid].xsk_pool = NULL; - xdp_rxq_info_unreg(&priv->rx[qid].xsk_rxq); - priv->tx[tx_qid].xsk_pool = NULL; + /* If XDP prog is not installed or interface is down, unmap DMA and + * return. + */ + if (!priv->xdp_prog || !netif_running(dev)) goto done; - } napi_rx = &priv->ntfy_blocks[priv->rx[qid].ntfy_id].napi; napi_disable(napi_rx); /* make sure current rx poll is done */ + tx_qid = gve_xdp_tx_queue_id(priv, qid); napi_tx = &priv->ntfy_blocks[priv->tx[tx_qid].ntfy_id].napi; napi_disable(napi_tx); /* make sure current tx poll is done */ @@ -1709,24 +1714,20 @@ done: static int gve_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) { struct gve_priv *priv = netdev_priv(dev); - int tx_queue_id = gve_xdp_tx_queue_id(priv, queue_id); + struct napi_struct *napi; + + if (!gve_get_napi_enabled(priv)) + return -ENETDOWN; if (queue_id >= priv->rx_cfg.num_queues || !priv->xdp_prog) return -EINVAL; - if (flags & XDP_WAKEUP_TX) { - struct gve_tx_ring *tx = &priv->tx[tx_queue_id]; - struct napi_struct *napi = - &priv->ntfy_blocks[tx->ntfy_id].napi; - - if (!napi_if_scheduled_mark_missed(napi)) { - /* Call local_bh_enable to trigger SoftIRQ processing */ - local_bh_disable(); - napi_schedule(napi); - local_bh_enable(); - } - - tx->xdp_xsk_wakeup++; + napi = &priv->ntfy_blocks[gve_rx_idx_to_ntfy(priv, queue_id)].napi; + if (!napi_if_scheduled_mark_missed(napi)) { + /* Call local_bh_enable to trigger SoftIRQ processing */ + local_bh_disable(); + napi_schedule(napi); + local_bh_enable(); } return 0; @@ -1837,6 +1838,7 @@ int gve_adjust_queues(struct gve_priv *priv, { struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0}; struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0}; + int num_xdp_queues; int err; gve_get_curr_alloc_cfgs(priv, &tx_alloc_cfg, &rx_alloc_cfg); @@ -1847,6 +1849,10 @@ int gve_adjust_queues(struct gve_priv *priv, rx_alloc_cfg.qcfg = &new_rx_config; tx_alloc_cfg.num_rings = new_tx_config.num_queues; + /* Add dedicated XDP TX queues if enabled. */ + num_xdp_queues = priv->xdp_prog ? new_rx_config.num_queues : 0; + tx_alloc_cfg.num_rings += num_xdp_queues; + if (netif_running(priv->dev)) { err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg); return err; @@ -1899,6 +1905,9 @@ static void gve_turndown(struct gve_priv *priv) gve_clear_napi_enabled(priv); gve_clear_report_stats(priv); + + /* Make sure that all traffic is finished processing. */ + synchronize_net(); } static void gve_turnup(struct gve_priv *priv) @@ -2232,14 +2241,18 @@ static void gve_service_task(struct work_struct *work) static void gve_set_netdev_xdp_features(struct gve_priv *priv) { + xdp_features_t xdp_features; + if (priv->queue_format == GVE_GQI_QPL_FORMAT) { - priv->dev->xdp_features = NETDEV_XDP_ACT_BASIC; - priv->dev->xdp_features |= NETDEV_XDP_ACT_REDIRECT; - priv->dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT; - priv->dev->xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY; + xdp_features = NETDEV_XDP_ACT_BASIC; + xdp_features |= NETDEV_XDP_ACT_REDIRECT; + xdp_features |= NETDEV_XDP_ACT_NDO_XMIT; + xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY; } else { - priv->dev->xdp_features = 0; + xdp_features = 0; } + + xdp_set_features_flag(priv->dev, xdp_features); } static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c index e7fb7d6d283d..4350ebd9c2bd 100644 --- a/drivers/net/ethernet/google/gve/gve_tx.c +++ b/drivers/net/ethernet/google/gve/gve_tx.c @@ -206,7 +206,10 @@ void gve_tx_stop_ring_gqi(struct gve_priv *priv, int idx) return; gve_remove_napi(priv, ntfy_idx); - gve_clean_tx_done(priv, tx, priv->tx_desc_cnt, false); + if (tx->q_num < priv->tx_cfg.num_queues) + gve_clean_tx_done(priv, tx, priv->tx_desc_cnt, false); + else + gve_clean_xdp_done(priv, tx, priv->tx_desc_cnt); netdev_tx_reset_queue(tx->netdev_txq); gve_tx_remove_from_block(priv, idx); } @@ -834,9 +837,12 @@ int gve_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, struct gve_tx_ring *tx; int i, err = 0, qid; - if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK) || !priv->xdp_prog) return -EINVAL; + if (!gve_get_napi_enabled(priv)) + return -ENETDOWN; + qid = gve_xdp_tx_queue_id(priv, smp_processor_id() % priv->num_xdp_queues); @@ -975,33 +981,41 @@ out: return sent; } +int gve_xsk_tx_poll(struct gve_notify_block *rx_block, int budget) +{ + struct gve_rx_ring *rx = rx_block->rx; + struct gve_priv *priv = rx->gve; + struct gve_tx_ring *tx; + int sent = 0; + + tx = &priv->tx[gve_xdp_tx_queue_id(priv, rx->q_num)]; + if (tx->xsk_pool) { + sent = gve_xsk_tx(priv, tx, budget); + + u64_stats_update_begin(&tx->statss); + tx->xdp_xsk_sent += sent; + u64_stats_update_end(&tx->statss); + if (xsk_uses_need_wakeup(tx->xsk_pool)) + xsk_set_tx_need_wakeup(tx->xsk_pool); + } + + return sent; +} + bool gve_xdp_poll(struct gve_notify_block *block, int budget) { struct gve_priv *priv = block->priv; struct gve_tx_ring *tx = block->tx; u32 nic_done; - bool repoll; u32 to_do; /* Find out how much work there is to be done */ nic_done = gve_tx_load_event_counter(priv, tx); to_do = min_t(u32, (nic_done - tx->done), budget); gve_clean_xdp_done(priv, tx, to_do); - repoll = nic_done != tx->done; - - if (tx->xsk_pool) { - int sent = gve_xsk_tx(priv, tx, budget); - - u64_stats_update_begin(&tx->statss); - tx->xdp_xsk_sent += sent; - u64_stats_update_end(&tx->statss); - repoll |= (sent == budget); - if (xsk_uses_need_wakeup(tx->xsk_pool)) - xsk_set_tx_need_wakeup(tx->xsk_pool); - } /* If we still have work we want to repoll */ - return repoll; + return nic_done != tx->done; } bool gve_tx_poll(struct gve_notify_block *block, int budget) diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 710a8f9f2248..12ba380eb701 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -916,9 +916,6 @@ struct hnae3_handle { u8 netdev_flags; struct dentry *hnae3_dbgfs; - /* protects concurrent contention between debugfs commands */ - struct mutex dbgfs_lock; - char **dbgfs_buf; /* Network interface message level enabled bits */ u32 msg_enable; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 807eb3bbb11c..9bbece25552b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -1260,69 +1260,55 @@ static int hns3_dbg_read_cmd(struct hns3_dbg_data *dbg_data, static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer, size_t count, loff_t *ppos) { - struct hns3_dbg_data *dbg_data = filp->private_data; + char *buf = filp->private_data; + + return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf)); +} + +static int hns3_dbg_open(struct inode *inode, struct file *filp) +{ + struct hns3_dbg_data *dbg_data = inode->i_private; struct hnae3_handle *handle = dbg_data->handle; struct hns3_nic_priv *priv = handle->priv; - ssize_t size = 0; - char **save_buf; - char *read_buf; u32 index; + char *buf; int ret; + if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) || + test_bit(HNS3_NIC_STATE_RESETTING, &priv->state)) + return -EBUSY; + ret = hns3_dbg_get_cmd_index(dbg_data, &index); if (ret) return ret; - mutex_lock(&handle->dbgfs_lock); - save_buf = &handle->dbgfs_buf[index]; - - if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) || - test_bit(HNS3_NIC_STATE_RESETTING, &priv->state)) { - ret = -EBUSY; - goto out; - } - - if (*save_buf) { - read_buf = *save_buf; - } else { - read_buf = kvzalloc(hns3_dbg_cmd[index].buf_len, GFP_KERNEL); - if (!read_buf) { - ret = -ENOMEM; - goto out; - } - - /* save the buffer addr until the last read operation */ - *save_buf = read_buf; - - /* get data ready for the first time to read */ - ret = hns3_dbg_read_cmd(dbg_data, hns3_dbg_cmd[index].cmd, - read_buf, hns3_dbg_cmd[index].buf_len); - if (ret) - goto out; - } + buf = kvzalloc(hns3_dbg_cmd[index].buf_len, GFP_KERNEL); + if (!buf) + return -ENOMEM; - size = simple_read_from_buffer(buffer, count, ppos, read_buf, - strlen(read_buf)); - if (size > 0) { - mutex_unlock(&handle->dbgfs_lock); - return size; + ret = hns3_dbg_read_cmd(dbg_data, hns3_dbg_cmd[index].cmd, + buf, hns3_dbg_cmd[index].buf_len); + if (ret) { + kvfree(buf); + return ret; } -out: - /* free the buffer for the last read operation */ - if (*save_buf) { - kvfree(*save_buf); - *save_buf = NULL; - } + filp->private_data = buf; + return 0; +} - mutex_unlock(&handle->dbgfs_lock); - return ret; +static int hns3_dbg_release(struct inode *inode, struct file *filp) +{ + kvfree(filp->private_data); + filp->private_data = NULL; + return 0; } static const struct file_operations hns3_dbg_fops = { .owner = THIS_MODULE, - .open = simple_open, + .open = hns3_dbg_open, .read = hns3_dbg_read, + .release = hns3_dbg_release, }; static int hns3_dbg_bd_file_init(struct hnae3_handle *handle, u32 cmd) @@ -1379,13 +1365,6 @@ int hns3_dbg_init(struct hnae3_handle *handle) int ret; u32 i; - handle->dbgfs_buf = devm_kcalloc(&handle->pdev->dev, - ARRAY_SIZE(hns3_dbg_cmd), - sizeof(*handle->dbgfs_buf), - GFP_KERNEL); - if (!handle->dbgfs_buf) - return -ENOMEM; - hns3_dbg_dentry[HNS3_DBG_DENTRY_COMMON].dentry = debugfs_create_dir(name, hns3_dbgfs_root); handle->hnae3_dbgfs = hns3_dbg_dentry[HNS3_DBG_DENTRY_COMMON].dentry; @@ -1395,8 +1374,6 @@ int hns3_dbg_init(struct hnae3_handle *handle) debugfs_create_dir(hns3_dbg_dentry[i].name, handle->hnae3_dbgfs); - mutex_init(&handle->dbgfs_lock); - for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++) { if ((hns3_dbg_cmd[i].cmd == HNAE3_DBG_CMD_TM_NODES && ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2) || @@ -1425,24 +1402,13 @@ int hns3_dbg_init(struct hnae3_handle *handle) out: debugfs_remove_recursive(handle->hnae3_dbgfs); handle->hnae3_dbgfs = NULL; - mutex_destroy(&handle->dbgfs_lock); return ret; } void hns3_dbg_uninit(struct hnae3_handle *handle) { - u32 i; - debugfs_remove_recursive(handle->hnae3_dbgfs); handle->hnae3_dbgfs = NULL; - - for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++) - if (handle->dbgfs_buf[i]) { - kvfree(handle->dbgfs_buf[i]); - handle->dbgfs_buf[i] = NULL; - } - - mutex_destroy(&handle->dbgfs_lock); } void hns3_dbg_register_debugfs(const char *debugfs_dir_name) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 43377a7b2426..a7e3b22f641c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -2452,7 +2452,6 @@ static int hns3_nic_set_features(struct net_device *netdev, return ret; } - netdev->features = features; return 0; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 05942fa78b11..db7845009252 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -6,6 +6,7 @@ #include <linux/etherdevice.h> #include <linux/init.h> #include <linux/interrupt.h> +#include <linux/irq.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/netdevice.h> @@ -3574,6 +3575,17 @@ static int hclge_set_vf_link_state(struct hnae3_handle *handle, int vf, return ret; } +static void hclge_set_reset_pending(struct hclge_dev *hdev, + enum hnae3_reset_type reset_type) +{ + /* When an incorrect reset type is executed, the get_reset_level + * function generates the HNAE3_NONE_RESET flag. As a result, this + * type do not need to pending. + */ + if (reset_type != HNAE3_NONE_RESET) + set_bit(reset_type, &hdev->reset_pending); +} + static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval) { u32 cmdq_src_reg, msix_src_reg, hw_err_src_reg; @@ -3594,7 +3606,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval) */ if (BIT(HCLGE_VECTOR0_IMPRESET_INT_B) & msix_src_reg) { dev_info(&hdev->pdev->dev, "IMP reset interrupt\n"); - set_bit(HNAE3_IMP_RESET, &hdev->reset_pending); + hclge_set_reset_pending(hdev, HNAE3_IMP_RESET); set_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state); *clearval = BIT(HCLGE_VECTOR0_IMPRESET_INT_B); hdev->rst_stats.imp_rst_cnt++; @@ -3604,7 +3616,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval) if (BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B) & msix_src_reg) { dev_info(&hdev->pdev->dev, "global reset interrupt\n"); set_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state); - set_bit(HNAE3_GLOBAL_RESET, &hdev->reset_pending); + hclge_set_reset_pending(hdev, HNAE3_GLOBAL_RESET); *clearval = BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B); hdev->rst_stats.global_rst_cnt++; return HCLGE_VECTOR0_EVENT_RST; @@ -3759,7 +3771,7 @@ static int hclge_misc_irq_init(struct hclge_dev *hdev) snprintf(hdev->misc_vector.name, HNAE3_INT_NAME_LEN, "%s-misc-%s", HCLGE_NAME, pci_name(hdev->pdev)); ret = request_irq(hdev->misc_vector.vector_irq, hclge_misc_irq_handle, - 0, hdev->misc_vector.name, hdev); + IRQF_NO_AUTOEN, hdev->misc_vector.name, hdev); if (ret) { hclge_free_vector(hdev, 0); dev_err(&hdev->pdev->dev, "request misc irq(%d) fail\n", @@ -4052,7 +4064,7 @@ static void hclge_do_reset(struct hclge_dev *hdev) case HNAE3_FUNC_RESET: dev_info(&pdev->dev, "PF reset requested\n"); /* schedule again to check later */ - set_bit(HNAE3_FUNC_RESET, &hdev->reset_pending); + hclge_set_reset_pending(hdev, HNAE3_FUNC_RESET); hclge_reset_task_schedule(hdev); break; default: @@ -4086,6 +4098,8 @@ static enum hnae3_reset_type hclge_get_reset_level(struct hnae3_ae_dev *ae_dev, clear_bit(HNAE3_FLR_RESET, addr); } + clear_bit(HNAE3_NONE_RESET, addr); + if (hdev->reset_type != HNAE3_NONE_RESET && rst_level < hdev->reset_type) return HNAE3_NONE_RESET; @@ -4227,7 +4241,7 @@ static bool hclge_reset_err_handle(struct hclge_dev *hdev) return false; } else if (hdev->rst_stats.reset_fail_cnt < MAX_RESET_FAIL_CNT) { hdev->rst_stats.reset_fail_cnt++; - set_bit(hdev->reset_type, &hdev->reset_pending); + hclge_set_reset_pending(hdev, hdev->reset_type); dev_info(&hdev->pdev->dev, "re-schedule reset task(%u)\n", hdev->rst_stats.reset_fail_cnt); @@ -4470,8 +4484,20 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle) static void hclge_set_def_reset_request(struct hnae3_ae_dev *ae_dev, enum hnae3_reset_type rst_type) { +#define HCLGE_SUPPORT_RESET_TYPE \ + (BIT(HNAE3_FLR_RESET) | BIT(HNAE3_FUNC_RESET) | \ + BIT(HNAE3_GLOBAL_RESET) | BIT(HNAE3_IMP_RESET)) + struct hclge_dev *hdev = ae_dev->priv; + if (!(BIT(rst_type) & HCLGE_SUPPORT_RESET_TYPE)) { + /* To prevent reset triggered by hclge_reset_event */ + set_bit(HNAE3_NONE_RESET, &hdev->default_reset_request); + dev_warn(&hdev->pdev->dev, "unsupported reset type %d\n", + rst_type); + return; + } + set_bit(rst_type, &hdev->default_reset_request); } @@ -11881,9 +11907,6 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) hclge_init_rxd_adv_layout(hdev); - /* Enable MISC vector(vector0) */ - hclge_enable_vector(&hdev->misc_vector, true); - ret = hclge_init_wol(hdev); if (ret) dev_warn(&pdev->dev, @@ -11896,6 +11919,10 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) hclge_state_init(hdev); hdev->last_reset_time = jiffies; + /* Enable MISC vector(vector0) */ + enable_irq(hdev->misc_vector.vector_irq); + hclge_enable_vector(&hdev->misc_vector, true); + dev_info(&hdev->pdev->dev, "%s driver initialization finished.\n", HCLGE_DRIVER_NAME); @@ -12301,7 +12328,7 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev) /* Disable MISC vector(vector0) */ hclge_enable_vector(&hdev->misc_vector, false); - synchronize_irq(hdev->misc_vector.vector_irq); + disable_irq(hdev->misc_vector.vector_irq); /* Disable all hw interrupts */ hclge_config_mac_tnl_int(hdev, false); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c index 5505caea88e9..bab16c2191b2 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c @@ -58,6 +58,9 @@ bool hclge_ptp_set_tx_info(struct hnae3_handle *handle, struct sk_buff *skb) struct hclge_dev *hdev = vport->back; struct hclge_ptp *ptp = hdev->ptp; + if (!ptp) + return false; + if (!test_bit(HCLGE_PTP_FLAG_TX_EN, &ptp->flags) || test_and_set_bit(HCLGE_STATE_PTP_TX_HANDLING, &hdev->state)) { ptp->tx_skipped++; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c index 43c1c18fa81f..8c057192aae6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c @@ -510,9 +510,9 @@ out: static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data, struct hnae3_knic_private_info *kinfo) { -#define HCLGE_RING_REG_OFFSET 0x200 #define HCLGE_RING_INT_REG_OFFSET 0x4 + struct hnae3_queue *tqp; int i, j, reg_num; int data_num_sum; u32 *reg = data; @@ -533,10 +533,11 @@ static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data, reg_num = ARRAY_SIZE(ring_reg_addr_list); for (j = 0; j < kinfo->num_tqps; j++) { reg += hclge_reg_get_tlv(HCLGE_REG_TAG_RING, reg_num, reg); + tqp = kinfo->tqp[j]; for (i = 0; i < reg_num; i++) - *reg++ = hclge_read_dev(&hdev->hw, - ring_reg_addr_list[i] + - HCLGE_RING_REG_OFFSET * j); + *reg++ = readl_relaxed(tqp->io_base - + HCLGE_TQP_REG_OFFSET + + ring_reg_addr_list[i]); } data_num_sum += (reg_num + HCLGE_REG_TLV_SPACE) * kinfo->num_tqps; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 2f6ffb88e700..163c6e59ea4c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1393,6 +1393,17 @@ static int hclgevf_notify_roce_client(struct hclgevf_dev *hdev, return ret; } +static void hclgevf_set_reset_pending(struct hclgevf_dev *hdev, + enum hnae3_reset_type reset_type) +{ + /* When an incorrect reset type is executed, the get_reset_level + * function generates the HNAE3_NONE_RESET flag. As a result, this + * type do not need to pending. + */ + if (reset_type != HNAE3_NONE_RESET) + set_bit(reset_type, &hdev->reset_pending); +} + static int hclgevf_reset_wait(struct hclgevf_dev *hdev) { #define HCLGEVF_RESET_WAIT_US 20000 @@ -1542,7 +1553,7 @@ static void hclgevf_reset_err_handle(struct hclgevf_dev *hdev) hdev->rst_stats.rst_fail_cnt); if (hdev->rst_stats.rst_fail_cnt < HCLGEVF_RESET_MAX_FAIL_CNT) - set_bit(hdev->reset_type, &hdev->reset_pending); + hclgevf_set_reset_pending(hdev, hdev->reset_type); if (hclgevf_is_reset_pending(hdev)) { set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state); @@ -1662,6 +1673,8 @@ static enum hnae3_reset_type hclgevf_get_reset_level(unsigned long *addr) clear_bit(HNAE3_FLR_RESET, addr); } + clear_bit(HNAE3_NONE_RESET, addr); + return rst_level; } @@ -1671,14 +1684,15 @@ static void hclgevf_reset_event(struct pci_dev *pdev, struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev); struct hclgevf_dev *hdev = ae_dev->priv; - dev_info(&hdev->pdev->dev, "received reset request from VF enet\n"); - if (hdev->default_reset_request) hdev->reset_level = hclgevf_get_reset_level(&hdev->default_reset_request); else hdev->reset_level = HNAE3_VF_FUNC_RESET; + dev_info(&hdev->pdev->dev, "received reset request from VF enet, reset level is %d\n", + hdev->reset_level); + /* reset of this VF requested */ set_bit(HCLGEVF_RESET_REQUESTED, &hdev->reset_state); hclgevf_reset_task_schedule(hdev); @@ -1689,8 +1703,20 @@ static void hclgevf_reset_event(struct pci_dev *pdev, static void hclgevf_set_def_reset_request(struct hnae3_ae_dev *ae_dev, enum hnae3_reset_type rst_type) { +#define HCLGEVF_SUPPORT_RESET_TYPE \ + (BIT(HNAE3_VF_RESET) | BIT(HNAE3_VF_FUNC_RESET) | \ + BIT(HNAE3_VF_PF_FUNC_RESET) | BIT(HNAE3_VF_FULL_RESET) | \ + BIT(HNAE3_FLR_RESET) | BIT(HNAE3_VF_EXP_RESET)) + struct hclgevf_dev *hdev = ae_dev->priv; + if (!(BIT(rst_type) & HCLGEVF_SUPPORT_RESET_TYPE)) { + /* To prevent reset triggered by hclge_reset_event */ + set_bit(HNAE3_NONE_RESET, &hdev->default_reset_request); + dev_info(&hdev->pdev->dev, "unsupported reset type %d\n", + rst_type); + return; + } set_bit(rst_type, &hdev->default_reset_request); } @@ -1847,14 +1873,14 @@ static void hclgevf_reset_service_task(struct hclgevf_dev *hdev) */ if (hdev->reset_attempts > HCLGEVF_MAX_RESET_ATTEMPTS_CNT) { /* prepare for full reset of stack + pcie interface */ - set_bit(HNAE3_VF_FULL_RESET, &hdev->reset_pending); + hclgevf_set_reset_pending(hdev, HNAE3_VF_FULL_RESET); /* "defer" schedule the reset task again */ set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state); } else { hdev->reset_attempts++; - set_bit(hdev->reset_level, &hdev->reset_pending); + hclgevf_set_reset_pending(hdev, hdev->reset_level); set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state); } hclgevf_reset_task_schedule(hdev); @@ -1977,7 +2003,7 @@ static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev, rst_ing_reg = hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING); dev_info(&hdev->pdev->dev, "receive reset interrupt 0x%x!\n", rst_ing_reg); - set_bit(HNAE3_VF_RESET, &hdev->reset_pending); + hclgevf_set_reset_pending(hdev, HNAE3_VF_RESET); set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state); set_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state); *clearval = ~(1U << HCLGEVF_VECTOR0_RST_INT_B); @@ -2287,6 +2313,8 @@ static void hclgevf_state_init(struct hclgevf_dev *hdev) clear_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state); INIT_DELAYED_WORK(&hdev->service_task, hclgevf_service_task); + /* timer needs to be initialized before misc irq */ + timer_setup(&hdev->reset_timer, hclgevf_reset_timer, 0); mutex_init(&hdev->mbx_resp.mbx_mutex); sema_init(&hdev->reset_sem, 1); @@ -2986,7 +3014,6 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev) HCLGEVF_DRIVER_NAME); hclgevf_task_schedule(hdev, round_jiffies_relative(HZ)); - timer_setup(&hdev->reset_timer, hclgevf_reset_timer, 0); return 0; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c index 6db415d8b917..7d9d9dbc7560 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c @@ -123,10 +123,10 @@ int hclgevf_get_regs_len(struct hnae3_handle *handle) void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version, void *data) { -#define HCLGEVF_RING_REG_OFFSET 0x200 #define HCLGEVF_RING_INT_REG_OFFSET 0x4 struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); + struct hnae3_queue *tqp; int i, j, reg_um; u32 *reg = data; @@ -147,10 +147,11 @@ void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version, reg_um = ARRAY_SIZE(ring_reg_addr_list); for (j = 0; j < hdev->num_tqps; j++) { reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_RING, reg_um, reg); + tqp = &hdev->htqp[j].q; for (i = 0; i < reg_um; i++) - *reg++ = hclgevf_read_dev(&hdev->hw, - ring_reg_addr_list[i] + - HCLGEVF_RING_REG_OFFSET * j); + *reg++ = readl_relaxed(tqp->io_base - + HCLGEVF_TQP_REG_OFFSET + + ring_reg_addr_list[i]); } reg_um = ARRAY_SIZE(tqp_intr_reg_addr_list); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 890f213da8d1..ae1f523d6841 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -172,6 +172,7 @@ err_init_txq: hinic_sq_dbgfs_uninit(nic_dev); devm_kfree(&netdev->dev, nic_dev->txqs); + nic_dev->txqs = NULL; return err; } @@ -268,6 +269,7 @@ err_init_rxq: hinic_rq_dbgfs_uninit(nic_dev); devm_kfree(&netdev->dev, nic_dev->rxqs); + nic_dev->rxqs = NULL; return err; } diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 1489a8ceec51..ef14cff9a333 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -2264,6 +2264,8 @@ struct ice_aqc_get_pkg_info_resp { struct ice_aqc_get_pkg_info pkg_info[]; }; +#define ICE_AQC_GET_CGU_MAX_PHASE_ADJ GENMASK(30, 0) + /* Get CGU abilities command response data structure (indirect 0x0C61) */ struct ice_aqc_get_cgu_abilities { u8 num_inputs; diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index d5ad6d84007c..38e151c7ea23 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -2065,6 +2065,18 @@ static int ice_dpll_init_worker(struct ice_pf *pf) } /** + * ice_dpll_phase_range_set - initialize phase adjust range helper + * @range: pointer to phase adjust range struct to be initialized + * @phase_adj: a value to be used as min(-)/max(+) boundary + */ +static void ice_dpll_phase_range_set(struct dpll_pin_phase_adjust_range *range, + u32 phase_adj) +{ + range->min = -phase_adj; + range->max = phase_adj; +} + +/** * ice_dpll_init_info_pins_generic - initializes generic pins info * @pf: board private structure * @input: if input pins initialized @@ -2105,8 +2117,8 @@ static int ice_dpll_init_info_pins_generic(struct ice_pf *pf, bool input) for (i = 0; i < pin_num; i++) { pins[i].idx = i; pins[i].prop.board_label = labels[i]; - pins[i].prop.phase_range.min = phase_adj_max; - pins[i].prop.phase_range.max = -phase_adj_max; + ice_dpll_phase_range_set(&pins[i].prop.phase_range, + phase_adj_max); pins[i].prop.capabilities = cap; pins[i].pf = pf; ret = ice_dpll_pin_state_update(pf, &pins[i], pin_type, NULL); @@ -2152,6 +2164,7 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf, struct ice_hw *hw = &pf->hw; struct ice_dpll_pin *pins; unsigned long caps; + u32 phase_adj_max; u8 freq_supp_num; bool input; @@ -2159,11 +2172,13 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf, case ICE_DPLL_PIN_TYPE_INPUT: pins = pf->dplls.inputs; num_pins = pf->dplls.num_inputs; + phase_adj_max = pf->dplls.input_phase_adj_max; input = true; break; case ICE_DPLL_PIN_TYPE_OUTPUT: pins = pf->dplls.outputs; num_pins = pf->dplls.num_outputs; + phase_adj_max = pf->dplls.output_phase_adj_max; input = false; break; default: @@ -2188,19 +2203,13 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf, return ret; caps |= (DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE | DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE); - pins[i].prop.phase_range.min = - pf->dplls.input_phase_adj_max; - pins[i].prop.phase_range.max = - -pf->dplls.input_phase_adj_max; } else { - pins[i].prop.phase_range.min = - pf->dplls.output_phase_adj_max; - pins[i].prop.phase_range.max = - -pf->dplls.output_phase_adj_max; ret = ice_cgu_get_output_pin_state_caps(hw, i, &caps); if (ret) return ret; } + ice_dpll_phase_range_set(&pins[i].prop.phase_range, + phase_adj_max); pins[i].prop.capabilities = caps; ret = ice_dpll_pin_state_update(pf, &pins[i], pin_type, NULL); if (ret) @@ -2308,8 +2317,10 @@ static int ice_dpll_init_info(struct ice_pf *pf, bool cgu) dp->dpll_idx = abilities.pps_dpll_idx; d->num_inputs = abilities.num_inputs; d->num_outputs = abilities.num_outputs; - d->input_phase_adj_max = le32_to_cpu(abilities.max_in_phase_adj); - d->output_phase_adj_max = le32_to_cpu(abilities.max_out_phase_adj); + d->input_phase_adj_max = le32_to_cpu(abilities.max_in_phase_adj) & + ICE_AQC_GET_CGU_MAX_PHASE_ADJ; + d->output_phase_adj_max = le32_to_cpu(abilities.max_out_phase_adj) & + ICE_AQC_GET_CGU_MAX_PHASE_ADJ; alloc_size = sizeof(*d->inputs) * d->num_inputs; d->inputs = kzalloc(alloc_size, GFP_KERNEL); diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h index 585ce200c60f..d75f0eddd631 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h @@ -761,9 +761,9 @@ const struct ice_vernier_info_e82x e822_vernier[NUM_ICE_PTP_LNK_SPD] = { /* rx_desk_rsgb_par */ 644531250, /* 644.53125 MHz Reed Solomon gearbox */ /* tx_desk_rsgb_pcs */ - 644531250, /* 644.53125 MHz Reed Solomon gearbox */ + 390625000, /* 390.625 MHz Reed Solomon gearbox */ /* rx_desk_rsgb_pcs */ - 644531250, /* 644.53125 MHz Reed Solomon gearbox */ + 390625000, /* 390.625 MHz Reed Solomon gearbox */ /* tx_fixed_delay */ 1620, /* pmd_adj_divisor */ diff --git a/drivers/net/ethernet/intel/idpf/idpf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_dev.c index 6c913a703df6..41e4bd49402a 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_dev.c +++ b/drivers/net/ethernet/intel/idpf/idpf_dev.c @@ -101,6 +101,9 @@ static int idpf_intr_reg_init(struct idpf_vport *vport) intr->dyn_ctl_itridx_s = PF_GLINT_DYN_CTL_ITR_INDX_S; intr->dyn_ctl_intrvl_s = PF_GLINT_DYN_CTL_INTERVAL_S; intr->dyn_ctl_wb_on_itr_m = PF_GLINT_DYN_CTL_WB_ON_ITR_M; + intr->dyn_ctl_swint_trig_m = PF_GLINT_DYN_CTL_SWINT_TRIG_M; + intr->dyn_ctl_sw_itridx_ena_m = + PF_GLINT_DYN_CTL_SW_ITR_INDX_ENA_M; spacing = IDPF_ITR_IDX_SPACING(reg_vals[vec_id].itrn_index_spacing, IDPF_PF_ITR_IDX_SPACING); diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 34f4118c7bc0..2fa9c36e33c9 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -3604,21 +3604,31 @@ static void idpf_vport_intr_dis_irq_all(struct idpf_vport *vport) /** * idpf_vport_intr_buildreg_itr - Enable default interrupt generation settings * @q_vector: pointer to q_vector - * @type: itr index - * @itr: itr value */ -static u32 idpf_vport_intr_buildreg_itr(struct idpf_q_vector *q_vector, - const int type, u16 itr) +static u32 idpf_vport_intr_buildreg_itr(struct idpf_q_vector *q_vector) { - u32 itr_val; + u32 itr_val = q_vector->intr_reg.dyn_ctl_intena_m; + int type = IDPF_NO_ITR_UPDATE_IDX; + u16 itr = 0; + + if (q_vector->wb_on_itr) { + /* + * Trigger a software interrupt when exiting wb_on_itr, to make + * sure we catch any pending write backs that might have been + * missed due to interrupt state transition. + */ + itr_val |= q_vector->intr_reg.dyn_ctl_swint_trig_m | + q_vector->intr_reg.dyn_ctl_sw_itridx_ena_m; + type = IDPF_SW_ITR_UPDATE_IDX; + itr = IDPF_ITR_20K; + } itr &= IDPF_ITR_MASK; /* Don't clear PBA because that can cause lost interrupts that * came in while we were cleaning/polling */ - itr_val = q_vector->intr_reg.dyn_ctl_intena_m | - (type << q_vector->intr_reg.dyn_ctl_itridx_s) | - (itr << (q_vector->intr_reg.dyn_ctl_intrvl_s - 1)); + itr_val |= (type << q_vector->intr_reg.dyn_ctl_itridx_s) | + (itr << (q_vector->intr_reg.dyn_ctl_intrvl_s - 1)); return itr_val; } @@ -3716,9 +3726,8 @@ void idpf_vport_intr_update_itr_ena_irq(struct idpf_q_vector *q_vector) /* net_dim() updates ITR out-of-band using a work item */ idpf_net_dim(q_vector); + intval = idpf_vport_intr_buildreg_itr(q_vector); q_vector->wb_on_itr = false; - intval = idpf_vport_intr_buildreg_itr(q_vector, - IDPF_NO_ITR_UPDATE_IDX, 0); writel(intval, q_vector->intr_reg.dyn_ctl); } diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h index 9c1fe84108ed..0f71a6f5557b 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h @@ -354,6 +354,8 @@ struct idpf_vec_regs { * @dyn_ctl_itridx_m: Mask for ITR index * @dyn_ctl_intrvl_s: Register bit offset for ITR interval * @dyn_ctl_wb_on_itr_m: Mask for WB on ITR feature + * @dyn_ctl_sw_itridx_ena_m: Mask for SW ITR index + * @dyn_ctl_swint_trig_m: Mask for dyn_ctl SW triggered interrupt enable * @rx_itr: RX ITR register * @tx_itr: TX ITR register * @icr_ena: Interrupt cause register offset @@ -367,6 +369,8 @@ struct idpf_intr_reg { u32 dyn_ctl_itridx_m; u32 dyn_ctl_intrvl_s; u32 dyn_ctl_wb_on_itr_m; + u32 dyn_ctl_sw_itridx_ena_m; + u32 dyn_ctl_swint_trig_m; void __iomem *rx_itr; void __iomem *tx_itr; void __iomem *icr_ena; @@ -437,7 +441,7 @@ struct idpf_q_vector { cpumask_var_t affinity_mask; __cacheline_group_end_aligned(cold); }; -libeth_cacheline_set_assert(struct idpf_q_vector, 112, +libeth_cacheline_set_assert(struct idpf_q_vector, 120, 24 + sizeof(struct napi_struct) + 2 * sizeof(struct dim), 8 + sizeof(cpumask_var_t)); @@ -471,6 +475,8 @@ struct idpf_tx_queue_stats { #define IDPF_ITR_IS_DYNAMIC(itr_mode) (itr_mode) #define IDPF_ITR_TX_DEF IDPF_ITR_20K #define IDPF_ITR_RX_DEF IDPF_ITR_20K +/* Index used for 'SW ITR' update in DYN_CTL register */ +#define IDPF_SW_ITR_UPDATE_IDX 2 /* Index used for 'No ITR' update in DYN_CTL register */ #define IDPF_NO_ITR_UPDATE_IDX 3 #define IDPF_ITR_IDX_SPACING(spacing, dflt) (spacing ? spacing : dflt) diff --git a/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c index aad62e270ae4..aba828abcb17 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c +++ b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c @@ -101,6 +101,9 @@ static int idpf_vf_intr_reg_init(struct idpf_vport *vport) intr->dyn_ctl_itridx_s = VF_INT_DYN_CTLN_ITR_INDX_S; intr->dyn_ctl_intrvl_s = VF_INT_DYN_CTLN_INTERVAL_S; intr->dyn_ctl_wb_on_itr_m = VF_INT_DYN_CTLN_WB_ON_ITR_M; + intr->dyn_ctl_swint_trig_m = VF_INT_DYN_CTLN_SWINT_TRIG_M; + intr->dyn_ctl_sw_itridx_ena_m = + VF_INT_DYN_CTLN_SW_ITR_INDX_ENA_M; spacing = IDPF_ITR_IDX_SPACING(reg_vals[vec_id].itrn_index_spacing, IDPF_VF_ITR_IDX_SPACING); diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c index 9fae8bdec2a7..1613b562d17c 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.c +++ b/drivers/net/ethernet/intel/igc/igc_base.c @@ -68,6 +68,10 @@ static s32 igc_init_nvm_params_base(struct igc_hw *hw) u32 eecd = rd32(IGC_EECD); u16 size; + /* failed to read reg and got all F's */ + if (!(~eecd)) + return -ENXIO; + size = FIELD_GET(IGC_EECD_SIZE_EX_MASK, eecd); /* Added to a constant, "size" becomes the left-shift value @@ -221,6 +225,8 @@ static s32 igc_get_invariants_base(struct igc_hw *hw) /* NVM initialization */ ret_val = igc_init_nvm_params_base(hw); + if (ret_val) + goto out; switch (hw->mac.type) { case igc_i225: ret_val = igc_init_nvm_params_i225(hw); diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index a06048719e84..67a6ff07c83d 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -2704,9 +2704,15 @@ static struct platform_device *port_platdev[3]; static void mv643xx_eth_shared_of_remove(void) { + struct mv643xx_eth_platform_data *pd; int n; for (n = 0; n < 3; n++) { + if (!port_platdev[n]) + continue; + pd = dev_get_platdata(&port_platdev[n]->dev); + if (pd) + of_node_put(pd->phy_node); platform_device_del(port_platdev[n]); port_platdev[n] = NULL; } @@ -2769,8 +2775,10 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev, } ppdev = platform_device_alloc(MV643XX_ETH_NAME, dev_num); - if (!ppdev) - return -ENOMEM; + if (!ppdev) { + ret = -ENOMEM; + goto put_err; + } ppdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); ppdev->dev.of_node = pnp; @@ -2792,6 +2800,8 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev, port_err: platform_device_put(ppdev); +put_err: + of_node_put(ppd.phy_node); return ret; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c index 232b10740c13..04e08e06f30f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c @@ -680,14 +680,17 @@ int rvu_rep_create(struct otx2_nic *priv, struct netlink_ext_ack *extack) ndev->features |= ndev->hw_features; eth_hw_addr_random(ndev); err = rvu_rep_devlink_port_register(rep); - if (err) + if (err) { + free_netdev(ndev); goto exit; + } SET_NETDEV_DEVLINK_PORT(ndev, &rep->dl_port); err = register_netdev(ndev); if (err) { NL_SET_ERR_MSG_MOD(extack, "PFVF representor registration failed"); + rvu_rep_devlink_port_unregister(rep); free_netdev(ndev); goto exit; } diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index 3914cd9210d4..988fa28cfb5f 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -130,6 +130,7 @@ static const struct pci_device_id sky2_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x436C) }, /* 88E8072 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x436D) }, /* 88E8055 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4370) }, /* 88E8075 */ + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4373) }, /* 88E8075 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4380) }, /* 88E8057 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4381) }, /* 88E8059 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4382) }, /* 88E8079 */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 6bd8a18e3af3..e733b81e18a2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1013,6 +1013,7 @@ static void cmd_work_handler(struct work_struct *work) complete(&ent->done); } up(&cmd->vars.sem); + complete(&ent->slotted); return; } } else { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index cc9bcc420032..6ab02f3fc291 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -339,9 +339,13 @@ static int mlx5e_macsec_init_sa_fs(struct macsec_context *ctx, { struct mlx5e_priv *priv = macsec_netdev_priv(ctx->netdev); struct mlx5_macsec_fs *macsec_fs = priv->mdev->macsec_fs; + const struct macsec_tx_sc *tx_sc = &ctx->secy->tx_sc; struct mlx5_macsec_rule_attrs rule_attrs; union mlx5_macsec_rule *macsec_rule; + if (is_tx && tx_sc->encoding_sa != sa->assoc_num) + return 0; + rule_attrs.macsec_obj_id = sa->macsec_obj_id; rule_attrs.sci = sa->sci; rule_attrs.assoc_num = sa->assoc_num; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index dd16d73000c3..0ec17c276bdd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -6542,8 +6542,23 @@ static void _mlx5e_remove(struct auxiliary_device *adev) mlx5_core_uplink_netdev_set(mdev, NULL); mlx5e_dcbnl_delete_app(priv); - unregister_netdev(priv->netdev); - _mlx5e_suspend(adev, false); + /* When unload driver, the netdev is in registered state + * if it's from legacy mode. If from switchdev mode, it + * is already unregistered before changing to NIC profile. + */ + if (priv->netdev->reg_state == NETREG_REGISTERED) { + unregister_netdev(priv->netdev); + _mlx5e_suspend(adev, false); + } else { + struct mlx5_core_dev *pos; + int i; + + if (test_bit(MLX5E_STATE_DESTROYING, &priv->state)) + mlx5_sd_for_each_dev(i, mdev, pos) + mlx5e_destroy_mdev_resources(pos); + else + _mlx5e_suspend(adev, true); + } /* Avoid cleanup if profile rollback failed. */ if (priv->profile) priv->profile->cleanup(priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 554f9cb5b53f..fdff9fd8a89e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1509,6 +1509,21 @@ mlx5e_vport_uplink_rep_unload(struct mlx5e_rep_priv *rpriv) priv = netdev_priv(netdev); + /* This bit is set when using devlink to change eswitch mode from + * switchdev to legacy. As need to keep uplink netdev ifindex, we + * detach uplink representor profile and attach NIC profile only. + * The netdev will be unregistered later when unload NIC auxiliary + * driver for this case. + * We explicitly block devlink eswitch mode change if any IPSec rules + * offloaded, but can't block other cases, such as driver unload + * and devlink reload. We have to unregister netdev before profile + * change for those cases. This is to avoid resource leak because + * the offloaded rules don't have the chance to be unoffloaded before + * cleanup which is triggered by detach uplink representor profile. + */ + if (!(priv->mdev->priv.flags & MLX5_PRIV_FLAGS_SWITCH_LEGACY)) + unregister_netdev(netdev); + mlx5e_netdev_attach_nic_profile(priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c index 5a0047bdcb51..ed977ae75fab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c @@ -150,11 +150,11 @@ void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev) unsigned long i; int err; - xa_for_each(&esw->offloads.vport_reps, i, rep) { - rpriv = rep->rep_data[REP_ETH].priv; - if (!rpriv || !rpriv->netdev) + mlx5_esw_for_each_rep(esw, i, rep) { + if (atomic_read(&rep->rep_data[REP_ETH].state) != REP_LOADED) continue; + rpriv = rep->rep_data[REP_ETH].priv; rhashtable_walk_enter(&rpriv->tc_ht, &iter); rhashtable_walk_start(&iter); while ((flow = rhashtable_walk_next(&iter)) != NULL) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index a83d41121db6..8573d36785f4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -714,6 +714,9 @@ void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw); MLX5_CAP_GEN_2((esw->dev), ec_vf_vport_base) +\ (last) - 1) +#define mlx5_esw_for_each_rep(esw, i, rep) \ + xa_for_each(&((esw)->offloads.vport_reps), i, rep) + struct mlx5_eswitch *__must_check mlx5_devlink_eswitch_get(struct devlink *devlink); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index d5b42b3a19fd..06076dd9ec64 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -53,9 +53,6 @@ #include "lag/lag.h" #include "en/tc/post_meter.h" -#define mlx5_esw_for_each_rep(esw, i, rep) \ - xa_for_each(&((esw)->offloads.vport_reps), i, rep) - /* There are two match-all miss flows, one for unicast dst mac and * one for multicast. */ @@ -3780,6 +3777,8 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, esw->eswitch_operation_in_progress = true; up_write(&esw->mode_lock); + if (mode == DEVLINK_ESWITCH_MODE_LEGACY) + esw->dev->priv.flags |= MLX5_PRIV_FLAGS_SWITCH_LEGACY; mlx5_eswitch_disable_locked(esw); if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) { if (mlx5_devlink_trap_get_num_active(esw->dev)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c index 6fa06ba2d346..f57c84e5128b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c @@ -1067,7 +1067,6 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, int inlen, err, eqn; void *cqc, *in; __be64 *pas; - int vector; u32 i; cq = kzalloc(sizeof(*cq), GFP_KERNEL); @@ -1096,8 +1095,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, if (!in) goto err_cqwq; - vector = raw_smp_processor_id() % mlx5_comp_vectors_max(mdev); - err = mlx5_comp_eqn_get(mdev, vector, &eqn); + err = mlx5_comp_eqn_get(mdev, 0, &eqn); if (err) { kvfree(in); goto err_cqwq; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index 4b5fd71c897d..32d2e61f2b82 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -423,8 +423,7 @@ mlxsw_sp_span_gretap4_route(const struct net_device *to_dev, parms = mlxsw_sp_ipip_netdev_parms4(to_dev); ip_tunnel_init_flow(&fl4, parms.iph.protocol, *daddrp, *saddrp, - 0, 0, dev_net(to_dev), parms.link, tun->fwmark, 0, - 0); + 0, 0, tun->net, parms.link, tun->fwmark, 0, 0); rt = ip_route_output_key(tun->net, &fl4); if (IS_ERR(rt)) diff --git a/drivers/net/ethernet/meta/fbnic/Makefile b/drivers/net/ethernet/meta/fbnic/Makefile index 239b2258ec65..ea6214ca48e7 100644 --- a/drivers/net/ethernet/meta/fbnic/Makefile +++ b/drivers/net/ethernet/meta/fbnic/Makefile @@ -13,7 +13,6 @@ fbnic-y := fbnic_csr.o \ fbnic_ethtool.o \ fbnic_fw.o \ fbnic_hw_stats.o \ - fbnic_hwmon.o \ fbnic_irq.o \ fbnic_mac.o \ fbnic_netdev.o \ diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h index 706ae6104c8e..744eb0d95449 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic.h @@ -20,7 +20,6 @@ struct fbnic_dev { struct device *dev; struct net_device *netdev; struct dentry *dbg_fbd; - struct device *hwmon; u32 __iomem *uc_addr0; u32 __iomem *uc_addr4; @@ -33,7 +32,6 @@ struct fbnic_dev { struct fbnic_fw_mbx mbx[FBNIC_IPC_MBX_INDICES]; struct fbnic_fw_cap fw_cap; - struct fbnic_fw_completion *cmpl_data; /* Lock protecting Tx Mailbox queue to prevent possible races */ spinlock_t fw_tx_lock; @@ -142,9 +140,6 @@ void fbnic_devlink_unregister(struct fbnic_dev *fbd); int fbnic_fw_enable_mbx(struct fbnic_dev *fbd); void fbnic_fw_disable_mbx(struct fbnic_dev *fbd); -void fbnic_hwmon_register(struct fbnic_dev *fbd); -void fbnic_hwmon_unregister(struct fbnic_dev *fbd); - int fbnic_pcs_irq_enable(struct fbnic_dev *fbd); void fbnic_pcs_irq_disable(struct fbnic_dev *fbd); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.c b/drivers/net/ethernet/meta/fbnic/fbnic_csr.c index 2118901b25e9..aeb9f333f4c7 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.c @@ -64,7 +64,7 @@ static void fbnic_csr_get_regs_rpc_ram(struct fbnic_dev *fbd, u32 **data_p) u32 i, j; *(data++) = start; - *(data++) = end - 1; + *(data++) = end; /* FBNIC_RPC_TCAM_ACT */ for (i = 0; i < FBNIC_RPC_TCAM_ACT_NUM_ENTRIES; i++) { diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h index 7cd8841920e4..221faf8c6756 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h @@ -44,13 +44,6 @@ struct fbnic_fw_cap { u8 link_fec; }; -struct fbnic_fw_completion { - struct { - s32 millivolts; - s32 millidegrees; - } tsene; -}; - void fbnic_mbx_init(struct fbnic_dev *fbd); void fbnic_mbx_clean(struct fbnic_dev *fbd); void fbnic_mbx_poll(struct fbnic_dev *fbd); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c b/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c deleted file mode 100644 index bcd1086e3768..000000000000 --- a/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c +++ /dev/null @@ -1,81 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright (c) Meta Platforms, Inc. and affiliates. */ - -#include <linux/hwmon.h> - -#include "fbnic.h" -#include "fbnic_mac.h" - -static int fbnic_hwmon_sensor_id(enum hwmon_sensor_types type) -{ - if (type == hwmon_temp) - return FBNIC_SENSOR_TEMP; - if (type == hwmon_in) - return FBNIC_SENSOR_VOLTAGE; - - return -EOPNOTSUPP; -} - -static umode_t fbnic_hwmon_is_visible(const void *drvdata, - enum hwmon_sensor_types type, - u32 attr, int channel) -{ - if (type == hwmon_temp && attr == hwmon_temp_input) - return 0444; - if (type == hwmon_in && attr == hwmon_in_input) - return 0444; - - return 0; -} - -static int fbnic_hwmon_read(struct device *dev, enum hwmon_sensor_types type, - u32 attr, int channel, long *val) -{ - struct fbnic_dev *fbd = dev_get_drvdata(dev); - const struct fbnic_mac *mac = fbd->mac; - int id; - - id = fbnic_hwmon_sensor_id(type); - return id < 0 ? id : mac->get_sensor(fbd, id, val); -} - -static const struct hwmon_ops fbnic_hwmon_ops = { - .is_visible = fbnic_hwmon_is_visible, - .read = fbnic_hwmon_read, -}; - -static const struct hwmon_channel_info *fbnic_hwmon_info[] = { - HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT), - HWMON_CHANNEL_INFO(in, HWMON_I_INPUT), - NULL -}; - -static const struct hwmon_chip_info fbnic_chip_info = { - .ops = &fbnic_hwmon_ops, - .info = fbnic_hwmon_info, -}; - -void fbnic_hwmon_register(struct fbnic_dev *fbd) -{ - if (!IS_REACHABLE(CONFIG_HWMON)) - return; - - fbd->hwmon = hwmon_device_register_with_info(fbd->dev, "fbnic", - fbd, &fbnic_chip_info, - NULL); - if (IS_ERR(fbd->hwmon)) { - dev_notice(fbd->dev, - "Failed to register hwmon device %pe\n", - fbd->hwmon); - fbd->hwmon = NULL; - } -} - -void fbnic_hwmon_unregister(struct fbnic_dev *fbd) -{ - if (!IS_REACHABLE(CONFIG_HWMON) || !fbd->hwmon) - return; - - hwmon_device_unregister(fbd->hwmon); - fbd->hwmon = NULL; -} diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c index 80b82ff12c4d..7b654d0a6dac 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c @@ -686,27 +686,6 @@ fbnic_mac_get_eth_mac_stats(struct fbnic_dev *fbd, bool reset, MAC_STAT_TX_BROADCAST); } -static int fbnic_mac_get_sensor_asic(struct fbnic_dev *fbd, int id, long *val) -{ - struct fbnic_fw_completion fw_cmpl; - s32 *sensor; - - switch (id) { - case FBNIC_SENSOR_TEMP: - sensor = &fw_cmpl.tsene.millidegrees; - break; - case FBNIC_SENSOR_VOLTAGE: - sensor = &fw_cmpl.tsene.millivolts; - break; - default: - return -EINVAL; - } - - *val = *sensor; - - return 0; -} - static const struct fbnic_mac fbnic_mac_asic = { .init_regs = fbnic_mac_init_regs, .pcs_enable = fbnic_pcs_enable_asic, @@ -716,7 +695,6 @@ static const struct fbnic_mac fbnic_mac_asic = { .get_eth_mac_stats = fbnic_mac_get_eth_mac_stats, .link_down = fbnic_mac_link_down_asic, .link_up = fbnic_mac_link_up_asic, - .get_sensor = fbnic_mac_get_sensor_asic, }; /** diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mac.h b/drivers/net/ethernet/meta/fbnic/fbnic_mac.h index 05a591653e09..476239a9d381 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_mac.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_mac.h @@ -47,11 +47,6 @@ enum { #define FBNIC_LINK_MODE_PAM4 (FBNIC_LINK_50R1) #define FBNIC_LINK_MODE_MASK (FBNIC_LINK_AUTO - 1) -enum fbnic_sensor_id { - FBNIC_SENSOR_TEMP, /* Temp in millidegrees Centigrade */ - FBNIC_SENSOR_VOLTAGE, /* Voltage in millivolts */ -}; - /* This structure defines the interface hooks for the MAC. The MAC hooks * will be configured as a const struct provided with a set of function * pointers. @@ -88,8 +83,6 @@ struct fbnic_mac { void (*link_down)(struct fbnic_dev *fbd); void (*link_up)(struct fbnic_dev *fbd, bool tx_pause, bool rx_pause); - - int (*get_sensor)(struct fbnic_dev *fbd, int id, long *val); }; int fbnic_mac_init(struct fbnic_dev *fbd); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c index 32702dc4a066..7ccf192f13d5 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c @@ -296,8 +296,6 @@ static int fbnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Capture snapshot of hardware stats so netdev can calculate delta */ fbnic_reset_hw_stats(fbd); - fbnic_hwmon_register(fbd); - if (!fbd->dsn) { dev_warn(&pdev->dev, "Reading serial number failed\n"); goto init_failure_mode; @@ -360,7 +358,6 @@ static void fbnic_remove(struct pci_dev *pdev) fbnic_netdev_free(fbd); } - fbnic_hwmon_unregister(fbd); fbnic_dbg_fbd_exit(fbd); fbnic_devlink_unregister(fbd); fbnic_fw_disable_mbx(fbd); diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 3d72aa7b1305..ef93df520887 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1432,7 +1432,7 @@ void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port, memset(ifh, 0, OCELOT_TAG_LEN); ocelot_ifh_set_bypass(ifh, 1); - ocelot_ifh_set_src(ifh, BIT_ULL(ocelot->num_phys_ports)); + ocelot_ifh_set_src(ifh, ocelot->num_phys_ports); ocelot_ifh_set_dest(ifh, BIT_ULL(port)); ocelot_ifh_set_qos_class(ifh, qos_class); ocelot_ifh_set_tag_type(ifh, tag_type); diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c index f9c0dcd965c2..db200e4ec284 100644 --- a/drivers/net/ethernet/oa_tc6.c +++ b/drivers/net/ethernet/oa_tc6.c @@ -113,6 +113,7 @@ struct oa_tc6 { struct mii_bus *mdiobus; struct spi_device *spi; struct mutex spi_ctrl_lock; /* Protects spi control transfer */ + spinlock_t tx_skb_lock; /* Protects tx skb handling */ void *spi_ctrl_tx_buf; void *spi_ctrl_rx_buf; void *spi_data_tx_buf; @@ -1004,8 +1005,10 @@ static u16 oa_tc6_prepare_spi_tx_buf_for_tx_skbs(struct oa_tc6 *tc6) for (used_tx_credits = 0; used_tx_credits < tc6->tx_credits; used_tx_credits++) { if (!tc6->ongoing_tx_skb) { + spin_lock_bh(&tc6->tx_skb_lock); tc6->ongoing_tx_skb = tc6->waiting_tx_skb; tc6->waiting_tx_skb = NULL; + spin_unlock_bh(&tc6->tx_skb_lock); } if (!tc6->ongoing_tx_skb) break; @@ -1111,8 +1114,9 @@ static int oa_tc6_spi_thread_handler(void *data) /* This kthread will be waken up if there is a tx skb or mac-phy * interrupt to perform spi transfer with tx chunks. */ - wait_event_interruptible(tc6->spi_wq, tc6->waiting_tx_skb || - tc6->int_flag || + wait_event_interruptible(tc6->spi_wq, tc6->int_flag || + (tc6->waiting_tx_skb && + tc6->tx_credits) || kthread_should_stop()); if (kthread_should_stop()) @@ -1209,7 +1213,9 @@ netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, struct sk_buff *skb) return NETDEV_TX_OK; } + spin_lock_bh(&tc6->tx_skb_lock); tc6->waiting_tx_skb = skb; + spin_unlock_bh(&tc6->tx_skb_lock); /* Wake spi kthread to perform spi transfer */ wake_up_interruptible(&tc6->spi_wq); @@ -1239,6 +1245,7 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev) tc6->netdev = netdev; SET_NETDEV_DEV(netdev, &spi->dev); mutex_init(&tc6->spi_ctrl_lock); + spin_lock_init(&tc6->tx_skb_lock); /* Set the SPI controller to pump at realtime priority */ tc6->spi->rt = true; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index 9e42d599840d..57edcde9e6f8 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -277,7 +277,10 @@ void ionic_dev_teardown(struct ionic *ionic) idev->phy_cmb_pages = 0; idev->cmb_npages = 0; - destroy_workqueue(ionic->wq); + if (ionic->wq) { + destroy_workqueue(ionic->wq); + ionic->wq = NULL; + } mutex_destroy(&idev->cmb_inuse_lock); } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c index dda22fa4448c..9b7f78b6cdb1 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c @@ -961,8 +961,8 @@ static int ionic_get_module_eeprom(struct net_device *netdev, len = min_t(u32, sizeof(xcvr->sprom), ee->len); do { - memcpy(data, xcvr->sprom, len); - memcpy(tbuf, xcvr->sprom, len); + memcpy(data, &xcvr->sprom[ee->offset], len); + memcpy(tbuf, &xcvr->sprom[ee->offset], len); /* Let's make sure we got a consistent copy */ if (!memcmp(data, tbuf, len)) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 40496587b2b3..3d3f936779f7 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -3869,8 +3869,8 @@ int ionic_lif_register(struct ionic_lif *lif) /* only register LIF0 for now */ err = register_netdev(lif->netdev); if (err) { - dev_err(lif->ionic->dev, "Cannot register net device, aborting\n"); - ionic_lif_unregister_phc(lif); + dev_err(lif->ionic->dev, "Cannot register net device: %d, aborting\n", err); + ionic_lif_unregister(lif); return err; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index b45efc272fdb..c7f497c36f66 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -3358,6 +3358,7 @@ int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn) p_ptt, &nvm_info.num_images); if (rc == -EOPNOTSUPP) { DP_INFO(p_hwfn, "DRV_MSG_CODE_BIST_TEST is not supported\n"); + nvm_info.num_images = 0; goto out; } else if (rc || !nvm_info.num_images) { DP_ERR(p_hwfn, "Failed getting number of images\n"); diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c index de7f11232593..c42c0516656b 100644 --- a/drivers/net/ethernet/realtek/rtase/rtase_main.c +++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c @@ -1827,7 +1827,7 @@ static int rtase_alloc_msix(struct pci_dev *pdev, struct rtase_private *tp) for (i = 0; i < tp->int_nums; i++) { irq = pci_irq_vector(pdev, i); - if (!irq) { + if (irq < 0) { pci_disable_msix(pdev); return irq; } diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c index dbbbf024e7ab..9ac6e2aad18f 100644 --- a/drivers/net/ethernet/renesas/rswitch.c +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -547,7 +547,6 @@ static int rswitch_gwca_ts_queue_alloc(struct rswitch_private *priv) desc = &gq->ts_ring[gq->ring_size]; desc->desc.die_dt = DT_LINKFIX; rswitch_desc_set_dptr(&desc->desc, gq->ring_dma); - INIT_LIST_HEAD(&priv->gwca.ts_info_list); return 0; } @@ -1003,9 +1002,10 @@ static int rswitch_gwca_request_irqs(struct rswitch_private *priv) static void rswitch_ts(struct rswitch_private *priv) { struct rswitch_gwca_queue *gq = &priv->gwca.ts_queue; - struct rswitch_gwca_ts_info *ts_info, *ts_info2; struct skb_shared_hwtstamps shhwtstamps; struct rswitch_ts_desc *desc; + struct rswitch_device *rdev; + struct sk_buff *ts_skb; struct timespec64 ts; unsigned int num; u32 tag, port; @@ -1015,23 +1015,28 @@ static void rswitch_ts(struct rswitch_private *priv) dma_rmb(); port = TS_DESC_DPN(__le32_to_cpu(desc->desc.dptrl)); - tag = TS_DESC_TSUN(__le32_to_cpu(desc->desc.dptrl)); - - list_for_each_entry_safe(ts_info, ts_info2, &priv->gwca.ts_info_list, list) { - if (!(ts_info->port == port && ts_info->tag == tag)) - continue; - - memset(&shhwtstamps, 0, sizeof(shhwtstamps)); - ts.tv_sec = __le32_to_cpu(desc->ts_sec); - ts.tv_nsec = __le32_to_cpu(desc->ts_nsec & cpu_to_le32(0x3fffffff)); - shhwtstamps.hwtstamp = timespec64_to_ktime(ts); - skb_tstamp_tx(ts_info->skb, &shhwtstamps); - dev_consume_skb_irq(ts_info->skb); - list_del(&ts_info->list); - kfree(ts_info); - break; - } + if (unlikely(port >= RSWITCH_NUM_PORTS)) + goto next; + rdev = priv->rdev[port]; + tag = TS_DESC_TSUN(__le32_to_cpu(desc->desc.dptrl)); + if (unlikely(tag >= TS_TAGS_PER_PORT)) + goto next; + ts_skb = xchg(&rdev->ts_skb[tag], NULL); + smp_mb(); /* order rdev->ts_skb[] read before bitmap update */ + clear_bit(tag, rdev->ts_skb_used); + + if (unlikely(!ts_skb)) + goto next; + + memset(&shhwtstamps, 0, sizeof(shhwtstamps)); + ts.tv_sec = __le32_to_cpu(desc->ts_sec); + ts.tv_nsec = __le32_to_cpu(desc->ts_nsec & cpu_to_le32(0x3fffffff)); + shhwtstamps.hwtstamp = timespec64_to_ktime(ts); + skb_tstamp_tx(ts_skb, &shhwtstamps); + dev_consume_skb_irq(ts_skb); + +next: gq->cur = rswitch_next_queue_index(gq, true, 1); desc = &gq->ts_ring[gq->cur]; } @@ -1576,8 +1581,9 @@ static int rswitch_open(struct net_device *ndev) static int rswitch_stop(struct net_device *ndev) { struct rswitch_device *rdev = netdev_priv(ndev); - struct rswitch_gwca_ts_info *ts_info, *ts_info2; + struct sk_buff *ts_skb; unsigned long flags; + unsigned int tag; netif_tx_stop_all_queues(ndev); @@ -1594,12 +1600,13 @@ static int rswitch_stop(struct net_device *ndev) if (bitmap_empty(rdev->priv->opened_ports, RSWITCH_NUM_PORTS)) iowrite32(GWCA_TS_IRQ_BIT, rdev->priv->addr + GWTSDID); - list_for_each_entry_safe(ts_info, ts_info2, &rdev->priv->gwca.ts_info_list, list) { - if (ts_info->port != rdev->port) - continue; - dev_kfree_skb_irq(ts_info->skb); - list_del(&ts_info->list); - kfree(ts_info); + for (tag = find_first_bit(rdev->ts_skb_used, TS_TAGS_PER_PORT); + tag < TS_TAGS_PER_PORT; + tag = find_next_bit(rdev->ts_skb_used, TS_TAGS_PER_PORT, tag + 1)) { + ts_skb = xchg(&rdev->ts_skb[tag], NULL); + clear_bit(tag, rdev->ts_skb_used); + if (ts_skb) + dev_kfree_skb(ts_skb); } return 0; @@ -1612,20 +1619,17 @@ static bool rswitch_ext_desc_set_info1(struct rswitch_device *rdev, desc->info1 = cpu_to_le64(INFO1_DV(BIT(rdev->etha->index)) | INFO1_IPV(GWCA_IPV_NUM) | INFO1_FMT); if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { - struct rswitch_gwca_ts_info *ts_info; + unsigned int tag; - ts_info = kzalloc(sizeof(*ts_info), GFP_ATOMIC); - if (!ts_info) + tag = find_first_zero_bit(rdev->ts_skb_used, TS_TAGS_PER_PORT); + if (tag == TS_TAGS_PER_PORT) return false; + smp_mb(); /* order bitmap read before rdev->ts_skb[] write */ + rdev->ts_skb[tag] = skb_get(skb); + set_bit(tag, rdev->ts_skb_used); skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; - rdev->ts_tag++; - desc->info1 |= cpu_to_le64(INFO1_TSUN(rdev->ts_tag) | INFO1_TXC); - - ts_info->skb = skb_get(skb); - ts_info->port = rdev->port; - ts_info->tag = rdev->ts_tag; - list_add_tail(&ts_info->list, &rdev->priv->gwca.ts_info_list); + desc->info1 |= cpu_to_le64(INFO1_TSUN(tag) | INFO1_TXC); skb_tx_timestamp(skb); } diff --git a/drivers/net/ethernet/renesas/rswitch.h b/drivers/net/ethernet/renesas/rswitch.h index e020800dcc57..d8d4ed7d7f8b 100644 --- a/drivers/net/ethernet/renesas/rswitch.h +++ b/drivers/net/ethernet/renesas/rswitch.h @@ -972,14 +972,6 @@ struct rswitch_gwca_queue { }; }; -struct rswitch_gwca_ts_info { - struct sk_buff *skb; - struct list_head list; - - int port; - u8 tag; -}; - #define RSWITCH_NUM_IRQ_REGS (RSWITCH_MAX_NUM_QUEUES / BITS_PER_TYPE(u32)) struct rswitch_gwca { unsigned int index; @@ -989,7 +981,6 @@ struct rswitch_gwca { struct rswitch_gwca_queue *queues; int num_queues; struct rswitch_gwca_queue ts_queue; - struct list_head ts_info_list; DECLARE_BITMAP(used, RSWITCH_MAX_NUM_QUEUES); u32 tx_irq_bits[RSWITCH_NUM_IRQ_REGS]; u32 rx_irq_bits[RSWITCH_NUM_IRQ_REGS]; @@ -997,6 +988,7 @@ struct rswitch_gwca { }; #define NUM_QUEUES_PER_NDEV 2 +#define TS_TAGS_PER_PORT 256 struct rswitch_device { struct rswitch_private *priv; struct net_device *ndev; @@ -1004,7 +996,8 @@ struct rswitch_device { void __iomem *addr; struct rswitch_gwca_queue *tx_queue; struct rswitch_gwca_queue *rx_queue; - u8 ts_tag; + struct sk_buff *ts_skb[TS_TAGS_PER_PORT]; + DECLARE_BITMAP(ts_skb_used, TS_TAGS_PER_PORT); bool disabled; int port; diff --git a/drivers/net/ethernet/sfc/tc_conntrack.c b/drivers/net/ethernet/sfc/tc_conntrack.c index d90206f27161..c0603f54cec3 100644 --- a/drivers/net/ethernet/sfc/tc_conntrack.c +++ b/drivers/net/ethernet/sfc/tc_conntrack.c @@ -16,7 +16,7 @@ static int efx_tc_flow_block(enum tc_setup_type type, void *type_data, void *cb_priv); static const struct rhashtable_params efx_tc_ct_zone_ht_params = { - .key_len = offsetof(struct efx_tc_ct_zone, linkage), + .key_len = sizeof_field(struct efx_tc_ct_zone, zone), .key_offset = 0, .head_offset = offsetof(struct efx_tc_ct_zone, linkage), }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c index 3827997d2132..dc903b846b1b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only +#include <linux/iommu.h> #include <linux/platform_device.h> #include <linux/of.h> #include <linux/module.h> @@ -19,6 +20,8 @@ struct tegra_mgbe { struct reset_control *rst_mac; struct reset_control *rst_pcs; + u32 iommu_sid; + void __iomem *hv; void __iomem *regs; void __iomem *xpcs; @@ -50,7 +53,6 @@ struct tegra_mgbe { #define MGBE_WRAP_COMMON_INTR_ENABLE 0x8704 #define MAC_SBD_INTR BIT(2) #define MGBE_WRAP_AXI_ASID0_CTRL 0x8400 -#define MGBE_SID 0x6 static int __maybe_unused tegra_mgbe_suspend(struct device *dev) { @@ -84,7 +86,7 @@ static int __maybe_unused tegra_mgbe_resume(struct device *dev) writel(MAC_SBD_INTR, mgbe->regs + MGBE_WRAP_COMMON_INTR_ENABLE); /* Program SID */ - writel(MGBE_SID, mgbe->hv + MGBE_WRAP_AXI_ASID0_CTRL); + writel(mgbe->iommu_sid, mgbe->hv + MGBE_WRAP_AXI_ASID0_CTRL); value = readl(mgbe->xpcs + XPCS_WRAP_UPHY_STATUS); if ((value & XPCS_WRAP_UPHY_STATUS_TX_P_UP) == 0) { @@ -241,6 +243,12 @@ static int tegra_mgbe_probe(struct platform_device *pdev) if (IS_ERR(mgbe->xpcs)) return PTR_ERR(mgbe->xpcs); + /* get controller's stream id from iommu property in device tree */ + if (!tegra_dev_iommu_get_stream_id(mgbe->dev, &mgbe->iommu_sid)) { + dev_err(mgbe->dev, "failed to get iommu stream id\n"); + return -EINVAL; + } + res.addr = mgbe->regs; res.irq = irq; @@ -346,7 +354,7 @@ static int tegra_mgbe_probe(struct platform_device *pdev) writel(MAC_SBD_INTR, mgbe->regs + MGBE_WRAP_COMMON_INTR_ENABLE); /* Program SID */ - writel(MGBE_SID, mgbe->hv + MGBE_WRAP_AXI_ASID0_CTRL); + writel(mgbe->iommu_sid, mgbe->hv + MGBE_WRAP_AXI_ASID0_CTRL); plat->flags |= STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 3ac32444e492..dc9884130b91 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -406,22 +406,6 @@ static int stmmac_of_get_mac_mode(struct device_node *np) } /** - * stmmac_remove_config_dt - undo the effects of stmmac_probe_config_dt() - * @pdev: platform_device structure - * @plat: driver data platform structure - * - * Release resources claimed by stmmac_probe_config_dt(). - */ -static void stmmac_remove_config_dt(struct platform_device *pdev, - struct plat_stmmacenet_data *plat) -{ - clk_disable_unprepare(plat->stmmac_clk); - clk_disable_unprepare(plat->pclk); - of_node_put(plat->phy_node); - of_node_put(plat->mdio_node); -} - -/** * stmmac_probe_config_dt - parse device-tree driver parameters * @pdev: platform_device structure * @mac: MAC address to use @@ -490,8 +474,10 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n"); rc = stmmac_mdio_setup(plat, np, &pdev->dev); - if (rc) - return ERR_PTR(rc); + if (rc) { + ret = ERR_PTR(rc); + goto error_put_phy; + } of_property_read_u32(np, "tx-fifo-depth", &plat->tx_fifo_size); @@ -581,8 +567,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*dma_cfg), GFP_KERNEL); if (!dma_cfg) { - stmmac_remove_config_dt(pdev, plat); - return ERR_PTR(-ENOMEM); + ret = ERR_PTR(-ENOMEM); + goto error_put_mdio; } plat->dma_cfg = dma_cfg; @@ -610,8 +596,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) rc = stmmac_mtl_setup(pdev, plat); if (rc) { - stmmac_remove_config_dt(pdev, plat); - return ERR_PTR(rc); + ret = ERR_PTR(rc); + goto error_put_mdio; } /* clock setup */ @@ -663,6 +649,10 @@ error_hw_init: clk_disable_unprepare(plat->pclk); error_pclk_get: clk_disable_unprepare(plat->stmmac_clk); +error_put_mdio: + of_node_put(plat->mdio_node); +error_put_phy: + of_node_put(plat->phy_node); return ret; } @@ -671,16 +661,17 @@ static void devm_stmmac_remove_config_dt(void *data) { struct plat_stmmacenet_data *plat = data; - /* Platform data argument is unused */ - stmmac_remove_config_dt(NULL, plat); + clk_disable_unprepare(plat->stmmac_clk); + clk_disable_unprepare(plat->pclk); + of_node_put(plat->mdio_node); + of_node_put(plat->phy_node); } /** * devm_stmmac_probe_config_dt * @pdev: platform_device structure * @mac: MAC address to use - * Description: Devres variant of stmmac_probe_config_dt(). Does not require - * the user to call stmmac_remove_config_dt() at driver detach. + * Description: Devres variant of stmmac_probe_config_dt(). */ struct plat_stmmacenet_data * devm_stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 14e1df721f2e..5465bf872734 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -3551,7 +3551,7 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev) init_completion(&common->tdown_complete); common->tx_ch_num = AM65_CPSW_DEFAULT_TX_CHNS; common->rx_ch_num_flows = AM65_CPSW_DEFAULT_RX_CHN_FLOWS; - common->pf_p0_rx_ptype_rrobin = false; + common->pf_p0_rx_ptype_rrobin = true; common->default_vlan = 1; common->ports = devm_kcalloc(dev, common->port_num, diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c index 5d6d1cf78e93..768578c0d958 100644 --- a/drivers/net/ethernet/ti/icssg/icss_iep.c +++ b/drivers/net/ethernet/ti/icssg/icss_iep.c @@ -215,6 +215,9 @@ static void icss_iep_enable_shadow_mode(struct icss_iep *iep) for (cmp = IEP_MIN_CMP; cmp < IEP_MAX_CMP; cmp++) { regmap_update_bits(iep->map, ICSS_IEP_CMP_STAT_REG, IEP_CMP_STATUS(cmp), IEP_CMP_STATUS(cmp)); + + regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG, + IEP_CMP_CFG_CMP_EN(cmp), 0); } /* enable reset counter on CMP0 event */ @@ -780,6 +783,11 @@ int icss_iep_exit(struct icss_iep *iep) } icss_iep_disable(iep); + if (iep->pps_enabled) + icss_iep_pps_enable(iep, false); + else if (iep->perout_enabled) + icss_iep_perout_enable(iep, NULL, false); + return 0; } EXPORT_SYMBOL_GPL(icss_iep_exit); diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c index fdebeb2f84e0..74f0f200a89d 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_common.c +++ b/drivers/net/ethernet/ti/icssg/icssg_common.c @@ -855,31 +855,6 @@ irqreturn_t prueth_rx_irq(int irq, void *dev_id) } EXPORT_SYMBOL_GPL(prueth_rx_irq); -void prueth_emac_stop(struct prueth_emac *emac) -{ - struct prueth *prueth = emac->prueth; - int slice; - - switch (emac->port_id) { - case PRUETH_PORT_MII0: - slice = ICSS_SLICE0; - break; - case PRUETH_PORT_MII1: - slice = ICSS_SLICE1; - break; - default: - netdev_err(emac->ndev, "invalid port\n"); - return; - } - - emac->fw_running = 0; - if (!emac->is_sr1) - rproc_shutdown(prueth->txpru[slice]); - rproc_shutdown(prueth->rtu[slice]); - rproc_shutdown(prueth->pru[slice]); -} -EXPORT_SYMBOL_GPL(prueth_emac_stop); - void prueth_cleanup_tx_ts(struct prueth_emac *emac) { int i; diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c index 5d2491c2943a..ddfd1c02a885 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_config.c +++ b/drivers/net/ethernet/ti/icssg/icssg_config.c @@ -397,7 +397,7 @@ static int prueth_emac_buffer_setup(struct prueth_emac *emac) return 0; } -static void icssg_init_emac_mode(struct prueth *prueth) +void icssg_init_emac_mode(struct prueth *prueth) { /* When the device is configured as a bridge and it is being brought * back to the emac mode, the host mac address has to be set as 0. @@ -406,9 +406,6 @@ static void icssg_init_emac_mode(struct prueth *prueth) int i; u8 mac[ETH_ALEN] = { 0 }; - if (prueth->emacs_initialized) - return; - /* Set VLAN TABLE address base */ regmap_update_bits(prueth->miig_rt, FDB_GEN_CFG1, SMEM_VLAN_OFFSET_MASK, addr << SMEM_VLAN_OFFSET); @@ -423,15 +420,13 @@ static void icssg_init_emac_mode(struct prueth *prueth) /* Clear host MAC address */ icssg_class_set_host_mac_addr(prueth->miig_rt, mac); } +EXPORT_SYMBOL_GPL(icssg_init_emac_mode); -static void icssg_init_fw_offload_mode(struct prueth *prueth) +void icssg_init_fw_offload_mode(struct prueth *prueth) { u32 addr = prueth->shram.pa + EMAC_ICSSG_SWITCH_DEFAULT_VLAN_TABLE_OFFSET; int i; - if (prueth->emacs_initialized) - return; - /* Set VLAN TABLE address base */ regmap_update_bits(prueth->miig_rt, FDB_GEN_CFG1, SMEM_VLAN_OFFSET_MASK, addr << SMEM_VLAN_OFFSET); @@ -448,6 +443,7 @@ static void icssg_init_fw_offload_mode(struct prueth *prueth) icssg_class_set_host_mac_addr(prueth->miig_rt, prueth->hw_bridge_dev->dev_addr); icssg_set_pvid(prueth, prueth->default_vlan, PRUETH_PORT_HOST); } +EXPORT_SYMBOL_GPL(icssg_init_fw_offload_mode); int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice) { @@ -455,11 +451,6 @@ int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice) struct icssg_flow_cfg __iomem *flow_cfg; int ret; - if (prueth->is_switch_mode || prueth->is_hsr_offload_mode) - icssg_init_fw_offload_mode(prueth); - else - icssg_init_emac_mode(prueth); - memset_io(config, 0, TAS_GATE_MASK_LIST0); icssg_miig_queues_init(prueth, slice); @@ -786,3 +777,27 @@ void icssg_set_pvid(struct prueth *prueth, u8 vid, u8 port) writel(pvid, prueth->shram.va + EMAC_ICSSG_SWITCH_PORT0_DEFAULT_VLAN_OFFSET); } EXPORT_SYMBOL_GPL(icssg_set_pvid); + +int emac_fdb_flow_id_updated(struct prueth_emac *emac) +{ + struct mgmt_cmd_rsp fdb_cmd_rsp = { 0 }; + int slice = prueth_emac_slice(emac); + struct mgmt_cmd fdb_cmd = { 0 }; + int ret; + + fdb_cmd.header = ICSSG_FW_MGMT_CMD_HEADER; + fdb_cmd.type = ICSSG_FW_MGMT_FDB_CMD_TYPE_RX_FLOW; + fdb_cmd.seqnum = ++(emac->prueth->icssg_hwcmdseq); + fdb_cmd.param = 0; + + fdb_cmd.param |= (slice << 4); + fdb_cmd.cmd_args[0] = 0; + + ret = icssg_send_fdb_msg(emac, &fdb_cmd, &fdb_cmd_rsp); + if (ret) + return ret; + + WARN_ON(fdb_cmd.seqnum != fdb_cmd_rsp.seqnum); + return fdb_cmd_rsp.status == 1 ? 0 : -EINVAL; +} +EXPORT_SYMBOL_GPL(emac_fdb_flow_id_updated); diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.h b/drivers/net/ethernet/ti/icssg/icssg_config.h index 92c2deaa3068..c884e9fa099e 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_config.h +++ b/drivers/net/ethernet/ti/icssg/icssg_config.h @@ -55,6 +55,7 @@ struct icssg_rxq_ctx { #define ICSSG_FW_MGMT_FDB_CMD_TYPE 0x03 #define ICSSG_FW_MGMT_CMD_TYPE 0x04 #define ICSSG_FW_MGMT_PKT 0x80000000 +#define ICSSG_FW_MGMT_FDB_CMD_TYPE_RX_FLOW 0x05 struct icssg_r30_cmd { u32 cmd[4]; diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index c568c84a032b..d76fe6d05e10 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -164,11 +164,26 @@ static struct icssg_firmwares icssg_emac_firmwares[] = { } }; -static int prueth_emac_start(struct prueth *prueth, struct prueth_emac *emac) +static int prueth_start(struct rproc *rproc, const char *fw_name) +{ + int ret; + + ret = rproc_set_firmware(rproc, fw_name); + if (ret) + return ret; + return rproc_boot(rproc); +} + +static void prueth_shutdown(struct rproc *rproc) +{ + rproc_shutdown(rproc); +} + +static int prueth_emac_start(struct prueth *prueth) { struct icssg_firmwares *firmwares; struct device *dev = prueth->dev; - int slice, ret; + int ret, slice; if (prueth->is_switch_mode) firmwares = icssg_switch_firmwares; @@ -177,49 +192,126 @@ static int prueth_emac_start(struct prueth *prueth, struct prueth_emac *emac) else firmwares = icssg_emac_firmwares; - slice = prueth_emac_slice(emac); - if (slice < 0) { - netdev_err(emac->ndev, "invalid port\n"); - return -EINVAL; + for (slice = 0; slice < PRUETH_NUM_MACS; slice++) { + ret = prueth_start(prueth->pru[slice], firmwares[slice].pru); + if (ret) { + dev_err(dev, "failed to boot PRU%d: %d\n", slice, ret); + goto unwind_slices; + } + + ret = prueth_start(prueth->rtu[slice], firmwares[slice].rtu); + if (ret) { + dev_err(dev, "failed to boot RTU%d: %d\n", slice, ret); + rproc_shutdown(prueth->pru[slice]); + goto unwind_slices; + } + + ret = prueth_start(prueth->txpru[slice], firmwares[slice].txpru); + if (ret) { + dev_err(dev, "failed to boot TX_PRU%d: %d\n", slice, ret); + rproc_shutdown(prueth->rtu[slice]); + rproc_shutdown(prueth->pru[slice]); + goto unwind_slices; + } } - ret = icssg_config(prueth, emac, slice); - if (ret) - return ret; + return 0; - ret = rproc_set_firmware(prueth->pru[slice], firmwares[slice].pru); - ret = rproc_boot(prueth->pru[slice]); - if (ret) { - dev_err(dev, "failed to boot PRU%d: %d\n", slice, ret); - return -EINVAL; +unwind_slices: + while (--slice >= 0) { + prueth_shutdown(prueth->txpru[slice]); + prueth_shutdown(prueth->rtu[slice]); + prueth_shutdown(prueth->pru[slice]); } - ret = rproc_set_firmware(prueth->rtu[slice], firmwares[slice].rtu); - ret = rproc_boot(prueth->rtu[slice]); - if (ret) { - dev_err(dev, "failed to boot RTU%d: %d\n", slice, ret); - goto halt_pru; + return ret; +} + +static void prueth_emac_stop(struct prueth *prueth) +{ + int slice; + + for (slice = 0; slice < PRUETH_NUM_MACS; slice++) { + prueth_shutdown(prueth->txpru[slice]); + prueth_shutdown(prueth->rtu[slice]); + prueth_shutdown(prueth->pru[slice]); } +} + +static int prueth_emac_common_start(struct prueth *prueth) +{ + struct prueth_emac *emac; + int ret = 0; + int slice; + + if (!prueth->emac[ICSS_SLICE0] && !prueth->emac[ICSS_SLICE1]) + return -EINVAL; + + /* clear SMEM and MSMC settings for all slices */ + memset_io(prueth->msmcram.va, 0, prueth->msmcram.size); + memset_io(prueth->shram.va, 0, ICSSG_CONFIG_OFFSET_SLICE1 * PRUETH_NUM_MACS); + + icssg_class_default(prueth->miig_rt, ICSS_SLICE0, 0, false); + icssg_class_default(prueth->miig_rt, ICSS_SLICE1, 0, false); + + if (prueth->is_switch_mode || prueth->is_hsr_offload_mode) + icssg_init_fw_offload_mode(prueth); + else + icssg_init_emac_mode(prueth); + + for (slice = 0; slice < PRUETH_NUM_MACS; slice++) { + emac = prueth->emac[slice]; + if (!emac) + continue; + ret = icssg_config(prueth, emac, slice); + if (ret) + goto disable_class; + } + + ret = prueth_emac_start(prueth); + if (ret) + goto disable_class; - ret = rproc_set_firmware(prueth->txpru[slice], firmwares[slice].txpru); - ret = rproc_boot(prueth->txpru[slice]); + emac = prueth->emac[ICSS_SLICE0] ? prueth->emac[ICSS_SLICE0] : + prueth->emac[ICSS_SLICE1]; + ret = icss_iep_init(emac->iep, &prueth_iep_clockops, + emac, IEP_DEFAULT_CYCLE_TIME_NS); if (ret) { - dev_err(dev, "failed to boot TX_PRU%d: %d\n", slice, ret); - goto halt_rtu; + dev_err(prueth->dev, "Failed to initialize IEP module\n"); + goto stop_pruss; } - emac->fw_running = 1; return 0; -halt_rtu: - rproc_shutdown(prueth->rtu[slice]); +stop_pruss: + prueth_emac_stop(prueth); -halt_pru: - rproc_shutdown(prueth->pru[slice]); +disable_class: + icssg_class_disable(prueth->miig_rt, ICSS_SLICE0); + icssg_class_disable(prueth->miig_rt, ICSS_SLICE1); return ret; } +static int prueth_emac_common_stop(struct prueth *prueth) +{ + struct prueth_emac *emac; + + if (!prueth->emac[ICSS_SLICE0] && !prueth->emac[ICSS_SLICE1]) + return -EINVAL; + + icssg_class_disable(prueth->miig_rt, ICSS_SLICE0); + icssg_class_disable(prueth->miig_rt, ICSS_SLICE1); + + prueth_emac_stop(prueth); + + emac = prueth->emac[ICSS_SLICE0] ? prueth->emac[ICSS_SLICE0] : + prueth->emac[ICSS_SLICE1]; + icss_iep_exit(emac->iep); + + return 0; +} + /* called back by PHY layer if there is change in link state of hw port*/ static void emac_adjust_link(struct net_device *ndev) { @@ -374,9 +466,6 @@ static void prueth_iep_settime(void *clockops_data, u64 ns) u32 cycletime; int timeout; - if (!emac->fw_running) - return; - sc_descp = emac->prueth->shram.va + TIMESYNC_FW_WC_SETCLOCK_DESC_OFFSET; cycletime = IEP_DEFAULT_CYCLE_TIME_NS; @@ -543,23 +632,17 @@ static int emac_ndo_open(struct net_device *ndev) { struct prueth_emac *emac = netdev_priv(ndev); int ret, i, num_data_chn = emac->tx_ch_num; + struct icssg_flow_cfg __iomem *flow_cfg; struct prueth *prueth = emac->prueth; int slice = prueth_emac_slice(emac); struct device *dev = prueth->dev; int max_rx_flows; int rx_flow; - /* clear SMEM and MSMC settings for all slices */ - if (!prueth->emacs_initialized) { - memset_io(prueth->msmcram.va, 0, prueth->msmcram.size); - memset_io(prueth->shram.va, 0, ICSSG_CONFIG_OFFSET_SLICE1 * PRUETH_NUM_MACS); - } - /* set h/w MAC as user might have re-configured */ ether_addr_copy(emac->mac_addr, ndev->dev_addr); icssg_class_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr); - icssg_class_default(prueth->miig_rt, slice, 0, false); icssg_ft1_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr); /* Notify the stack of the actual queue counts. */ @@ -597,18 +680,23 @@ static int emac_ndo_open(struct net_device *ndev) goto cleanup_napi; } - /* reset and start PRU firmware */ - ret = prueth_emac_start(prueth, emac); - if (ret) - goto free_rx_irq; + if (!prueth->emacs_initialized) { + ret = prueth_emac_common_start(prueth); + if (ret) + goto free_rx_irq; + } - icssg_mii_update_mtu(prueth->mii_rt, slice, ndev->max_mtu); + flow_cfg = emac->dram.va + ICSSG_CONFIG_OFFSET + PSI_L_REGULAR_FLOW_ID_BASE_OFFSET; + writew(emac->rx_flow_id_base, &flow_cfg->rx_base_flow); + ret = emac_fdb_flow_id_updated(emac); - if (!prueth->emacs_initialized) { - ret = icss_iep_init(emac->iep, &prueth_iep_clockops, - emac, IEP_DEFAULT_CYCLE_TIME_NS); + if (ret) { + netdev_err(ndev, "Failed to update Rx Flow ID %d", ret); + goto stop; } + icssg_mii_update_mtu(prueth->mii_rt, slice, ndev->max_mtu); + ret = request_threaded_irq(emac->tx_ts_irq, NULL, prueth_tx_ts_irq, IRQF_ONESHOT, dev_name(dev), emac); if (ret) @@ -653,7 +741,8 @@ reset_rx_chn: free_tx_ts_irq: free_irq(emac->tx_ts_irq, emac); stop: - prueth_emac_stop(emac); + if (!prueth->emacs_initialized) + prueth_emac_common_stop(prueth); free_rx_irq: free_irq(emac->rx_chns.irq[rx_flow], emac); cleanup_napi: @@ -689,8 +778,6 @@ static int emac_ndo_stop(struct net_device *ndev) if (ndev->phydev) phy_stop(ndev->phydev); - icssg_class_disable(prueth->miig_rt, prueth_emac_slice(emac)); - if (emac->prueth->is_hsr_offload_mode) __dev_mc_unsync(ndev, icssg_prueth_hsr_del_mcast); else @@ -728,11 +815,9 @@ static int emac_ndo_stop(struct net_device *ndev) /* Destroying the queued work in ndo_stop() */ cancel_delayed_work_sync(&emac->stats_work); - if (prueth->emacs_initialized == 1) - icss_iep_exit(emac->iep); - /* stop PRUs */ - prueth_emac_stop(emac); + if (prueth->emacs_initialized == 1) + prueth_emac_common_stop(prueth); free_irq(emac->tx_ts_irq, emac); @@ -1053,10 +1138,11 @@ static void prueth_offload_fwd_mark_update(struct prueth *prueth) } } -static void prueth_emac_restart(struct prueth *prueth) +static int prueth_emac_restart(struct prueth *prueth) { struct prueth_emac *emac0 = prueth->emac[PRUETH_MAC0]; struct prueth_emac *emac1 = prueth->emac[PRUETH_MAC1]; + int ret; /* Detach the net_device for both PRUeth ports*/ if (netif_running(emac0->ndev)) @@ -1065,36 +1151,46 @@ static void prueth_emac_restart(struct prueth *prueth) netif_device_detach(emac1->ndev); /* Disable both PRUeth ports */ - icssg_set_port_state(emac0, ICSSG_EMAC_PORT_DISABLE); - icssg_set_port_state(emac1, ICSSG_EMAC_PORT_DISABLE); + ret = icssg_set_port_state(emac0, ICSSG_EMAC_PORT_DISABLE); + ret |= icssg_set_port_state(emac1, ICSSG_EMAC_PORT_DISABLE); + if (ret) + return ret; /* Stop both pru cores for both PRUeth ports*/ - prueth_emac_stop(emac0); - prueth->emacs_initialized--; - prueth_emac_stop(emac1); - prueth->emacs_initialized--; + ret = prueth_emac_common_stop(prueth); + if (ret) { + dev_err(prueth->dev, "Failed to stop the firmwares"); + return ret; + } /* Start both pru cores for both PRUeth ports */ - prueth_emac_start(prueth, emac0); - prueth->emacs_initialized++; - prueth_emac_start(prueth, emac1); - prueth->emacs_initialized++; + ret = prueth_emac_common_start(prueth); + if (ret) { + dev_err(prueth->dev, "Failed to start the firmwares"); + return ret; + } /* Enable forwarding for both PRUeth ports */ - icssg_set_port_state(emac0, ICSSG_EMAC_PORT_FORWARD); - icssg_set_port_state(emac1, ICSSG_EMAC_PORT_FORWARD); + ret = icssg_set_port_state(emac0, ICSSG_EMAC_PORT_FORWARD); + ret |= icssg_set_port_state(emac1, ICSSG_EMAC_PORT_FORWARD); /* Attache net_device for both PRUeth ports */ netif_device_attach(emac0->ndev); netif_device_attach(emac1->ndev); + + return ret; } static void icssg_change_mode(struct prueth *prueth) { struct prueth_emac *emac; - int mac; + int mac, ret; - prueth_emac_restart(prueth); + ret = prueth_emac_restart(prueth); + if (ret) { + dev_err(prueth->dev, "Failed to restart the firmwares, aborting the process"); + return; + } for (mac = PRUETH_MAC0; mac < PRUETH_NUM_MACS; mac++) { emac = prueth->emac[mac]; @@ -1173,13 +1269,18 @@ static void prueth_netdevice_port_unlink(struct net_device *ndev) { struct prueth_emac *emac = netdev_priv(ndev); struct prueth *prueth = emac->prueth; + int ret; prueth->br_members &= ~BIT(emac->port_id); if (prueth->is_switch_mode) { prueth->is_switch_mode = false; emac->port_vlan = 0; - prueth_emac_restart(prueth); + ret = prueth_emac_restart(prueth); + if (ret) { + dev_err(prueth->dev, "Failed to restart the firmwares, aborting the process"); + return; + } } prueth_offload_fwd_mark_update(prueth); @@ -1228,6 +1329,7 @@ static void prueth_hsr_port_unlink(struct net_device *ndev) struct prueth *prueth = emac->prueth; struct prueth_emac *emac0; struct prueth_emac *emac1; + int ret; emac0 = prueth->emac[PRUETH_MAC0]; emac1 = prueth->emac[PRUETH_MAC1]; @@ -1238,7 +1340,11 @@ static void prueth_hsr_port_unlink(struct net_device *ndev) emac0->port_vlan = 0; emac1->port_vlan = 0; prueth->hsr_dev = NULL; - prueth_emac_restart(prueth); + ret = prueth_emac_restart(prueth); + if (ret) { + dev_err(prueth->dev, "Failed to restart the firmwares, aborting the process"); + return; + } netdev_dbg(ndev, "Disabling HSR Offload mode\n"); } } @@ -1413,13 +1519,10 @@ static int prueth_probe(struct platform_device *pdev) prueth->pa_stats = NULL; } - if (eth0_node) { + if (eth0_node || eth1_node) { ret = prueth_get_cores(prueth, ICSS_SLICE0, false); if (ret) goto put_cores; - } - - if (eth1_node) { ret = prueth_get_cores(prueth, ICSS_SLICE1, false); if (ret) goto put_cores; @@ -1618,14 +1721,12 @@ put_pruss: pruss_put(prueth->pruss); put_cores: - if (eth1_node) { - prueth_put_cores(prueth, ICSS_SLICE1); - of_node_put(eth1_node); - } - - if (eth0_node) { + if (eth0_node || eth1_node) { prueth_put_cores(prueth, ICSS_SLICE0); of_node_put(eth0_node); + + prueth_put_cores(prueth, ICSS_SLICE1); + of_node_put(eth1_node); } return ret; diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h index f5c1d473e9f9..5473315ea204 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h @@ -140,7 +140,6 @@ struct prueth_rx_chn { /* data for each emac port */ struct prueth_emac { bool is_sr1; - bool fw_running; struct prueth *prueth; struct net_device *ndev; u8 mac_addr[6]; @@ -361,6 +360,8 @@ int icssg_set_port_state(struct prueth_emac *emac, enum icssg_port_state_cmd state); void icssg_config_set_speed(struct prueth_emac *emac); void icssg_config_half_duplex(struct prueth_emac *emac); +void icssg_init_emac_mode(struct prueth *prueth); +void icssg_init_fw_offload_mode(struct prueth *prueth); /* Buffer queue helpers */ int icssg_queue_pop(struct prueth *prueth, u8 queue); @@ -377,6 +378,7 @@ void icssg_vtbl_modify(struct prueth_emac *emac, u8 vid, u8 port_mask, u8 untag_mask, bool add); u16 icssg_get_pvid(struct prueth_emac *emac); void icssg_set_pvid(struct prueth *prueth, u8 vid, u8 port); +int emac_fdb_flow_id_updated(struct prueth_emac *emac); #define prueth_napi_to_tx_chn(pnapi) \ container_of(pnapi, struct prueth_tx_chn, napi_tx) @@ -407,7 +409,6 @@ void emac_rx_timestamp(struct prueth_emac *emac, struct sk_buff *skb, u32 *psdata); enum netdev_tx icssg_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev); irqreturn_t prueth_rx_irq(int irq, void *dev_id); -void prueth_emac_stop(struct prueth_emac *emac); void prueth_cleanup_tx_ts(struct prueth_emac *emac); int icssg_napi_rx_poll(struct napi_struct *napi_rx, int budget); int prueth_prepare_rx_chan(struct prueth_emac *emac, diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c index 5024f0647a0d..3dc86397c367 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c @@ -440,7 +440,6 @@ static int prueth_emac_start(struct prueth *prueth, struct prueth_emac *emac) goto halt_pru; } - emac->fw_running = 1; return 0; halt_pru: @@ -449,6 +448,29 @@ halt_pru: return ret; } +static void prueth_emac_stop(struct prueth_emac *emac) +{ + struct prueth *prueth = emac->prueth; + int slice; + + switch (emac->port_id) { + case PRUETH_PORT_MII0: + slice = ICSS_SLICE0; + break; + case PRUETH_PORT_MII1: + slice = ICSS_SLICE1; + break; + default: + netdev_err(emac->ndev, "invalid port\n"); + return; + } + + if (!emac->is_sr1) + rproc_shutdown(prueth->txpru[slice]); + rproc_shutdown(prueth->rtu[slice]); + rproc_shutdown(prueth->pru[slice]); +} + /** * emac_ndo_open - EMAC device open * @ndev: network adapter device diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c index 1bf9c38e4125..deaf670c160e 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -334,27 +334,25 @@ int wx_host_interface_command(struct wx *wx, u32 *buffer, status = read_poll_timeout(rd32, hicr, hicr & WX_MNG_MBOX_CTL_FWRDY, 1000, timeout * 1000, false, wx, WX_MNG_MBOX_CTL); + buf[0] = rd32(wx, WX_MNG_MBOX); + if ((buf[0] & 0xff0000) >> 16 == 0x80) { + wx_err(wx, "Unknown FW command: 0x%x\n", buffer[0] & 0xff); + status = -EINVAL; + goto rel_out; + } + /* Check command completion */ if (status) { - wx_dbg(wx, "Command has failed with no status valid.\n"); - - buf[0] = rd32(wx, WX_MNG_MBOX); - if ((buffer[0] & 0xff) != (~buf[0] >> 24)) { - status = -EINVAL; - goto rel_out; - } - if ((buf[0] & 0xff0000) >> 16 == 0x80) { - wx_dbg(wx, "It's unknown cmd.\n"); - status = -EINVAL; - goto rel_out; - } - + wx_err(wx, "Command has failed with no status valid.\n"); wx_dbg(wx, "write value:\n"); for (i = 0; i < dword_len; i++) wx_dbg(wx, "%x ", buffer[i]); wx_dbg(wx, "read value:\n"); for (i = 0; i < dword_len; i++) wx_dbg(wx, "%x ", buf[i]); + wx_dbg(wx, "\ncheck: %x %x\n", buffer[0] & 0xff, ~buf[0] >> 24); + + goto rel_out; } if (!return_data) diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index e685a7f946f0..753215ebc67c 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -3072,7 +3072,11 @@ static int ca8210_probe(struct spi_device *spi_device) spi_set_drvdata(priv->spi, priv); if (IS_ENABLED(CONFIG_IEEE802154_CA8210_DEBUGFS)) { cascoda_api_upstream = ca8210_test_int_driver_write; - ca8210_test_interface_init(priv); + ret = ca8210_test_interface_init(priv); + if (ret) { + dev_crit(&spi_device->dev, "ca8210_test_interface_init failed\n"); + goto error; + } } else { cascoda_api_upstream = NULL; } diff --git a/drivers/net/mctp/mctp-i3c.c b/drivers/net/mctp/mctp-i3c.c index 9adad59b8676..d247fe483c58 100644 --- a/drivers/net/mctp/mctp-i3c.c +++ b/drivers/net/mctp/mctp-i3c.c @@ -125,6 +125,8 @@ static int mctp_i3c_read(struct mctp_i3c_device *mi) xfer.data.in = skb_put(skb, mi->mrl); + /* Make sure netif_rx() is read in the same order as i3c. */ + mutex_lock(&mi->lock); rc = i3c_device_do_priv_xfers(mi->i3c, &xfer, 1); if (rc < 0) goto err; @@ -166,8 +168,10 @@ static int mctp_i3c_read(struct mctp_i3c_device *mi) stats->rx_dropped++; } + mutex_unlock(&mi->lock); return 0; err: + mutex_unlock(&mi->lock); kfree_skb(skb); return rc; } diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c index b156493d7084..aea0f0357568 100644 --- a/drivers/net/mdio/fwnode_mdio.c +++ b/drivers/net/mdio/fwnode_mdio.c @@ -40,6 +40,7 @@ fwnode_find_pse_control(struct fwnode_handle *fwnode) static struct mii_timestamper * fwnode_find_mii_timestamper(struct fwnode_handle *fwnode) { + struct mii_timestamper *mii_ts; struct of_phandle_args arg; int err; @@ -53,10 +54,16 @@ fwnode_find_mii_timestamper(struct fwnode_handle *fwnode) else if (err) return ERR_PTR(err); - if (arg.args_count != 1) - return ERR_PTR(-EINVAL); + if (arg.args_count != 1) { + mii_ts = ERR_PTR(-EINVAL); + goto put_node; + } + + mii_ts = register_mii_timestamper(arg.np, arg.args[0]); - return register_mii_timestamper(arg.np, arg.args[0]); +put_node: + of_node_put(arg.np); + return mii_ts; } int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, diff --git a/drivers/net/netdevsim/health.c b/drivers/net/netdevsim/health.c index 70e8bdf34be9..688f05316b5e 100644 --- a/drivers/net/netdevsim/health.c +++ b/drivers/net/netdevsim/health.c @@ -149,6 +149,8 @@ static ssize_t nsim_dev_health_break_write(struct file *file, char *break_msg; int err; + if (count == 0 || count > PAGE_SIZE) + return -EINVAL; break_msg = memdup_user_nul(data, count); if (IS_ERR(break_msg)) return PTR_ERR(break_msg); diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index 0be47fed4efc..e068a9761c09 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -635,10 +635,10 @@ nsim_pp_hold_write(struct file *file, const char __user *data, page_pool_put_full_page(ns->page->pp, ns->page, false); ns->page = NULL; } - rtnl_unlock(); exit: - return count; + rtnl_unlock(); + return ret; } static const struct file_operations nsim_pp_hold_fops = { diff --git a/drivers/net/phy/aquantia/aquantia_leds.c b/drivers/net/phy/aquantia/aquantia_leds.c index 00ad2313fed3..951f46104eff 100644 --- a/drivers/net/phy/aquantia/aquantia_leds.c +++ b/drivers/net/phy/aquantia/aquantia_leds.c @@ -156,5 +156,5 @@ int aqr_phy_led_polarity_set(struct phy_device *phydev, int index, unsigned long if (force_active_high || force_active_low) return aqr_phy_led_active_low_set(phydev, index, force_active_low); - unreachable(); + return -EINVAL; } diff --git a/drivers/net/phy/intel-xway.c b/drivers/net/phy/intel-xway.c index b672c55a7a4e..e6ed2413e514 100644 --- a/drivers/net/phy/intel-xway.c +++ b/drivers/net/phy/intel-xway.c @@ -529,7 +529,7 @@ static int xway_gphy_led_polarity_set(struct phy_device *phydev, int index, if (force_active_high) return phy_clear_bits(phydev, XWAY_MDIO_LED, XWAY_GPHY_LED_INV(index)); - unreachable(); + return -EINVAL; } static struct phy_driver xway_gphy[] = { diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 3ef508840674..eeb33eb181ac 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -432,10 +432,12 @@ struct kszphy_ptp_priv { struct kszphy_priv { struct kszphy_ptp_priv ptp_priv; const struct kszphy_type *type; + struct clk *clk; int led_mode; u16 vct_ctrl1000; bool rmii_ref_clk_sel; bool rmii_ref_clk_sel_val; + bool clk_enable; u64 stats[ARRAY_SIZE(kszphy_hw_stats)]; }; @@ -2050,6 +2052,46 @@ static void kszphy_get_stats(struct phy_device *phydev, data[i] = kszphy_get_stat(phydev, i); } +static void kszphy_enable_clk(struct phy_device *phydev) +{ + struct kszphy_priv *priv = phydev->priv; + + if (!priv->clk_enable && priv->clk) { + clk_prepare_enable(priv->clk); + priv->clk_enable = true; + } +} + +static void kszphy_disable_clk(struct phy_device *phydev) +{ + struct kszphy_priv *priv = phydev->priv; + + if (priv->clk_enable && priv->clk) { + clk_disable_unprepare(priv->clk); + priv->clk_enable = false; + } +} + +static int kszphy_generic_resume(struct phy_device *phydev) +{ + kszphy_enable_clk(phydev); + + return genphy_resume(phydev); +} + +static int kszphy_generic_suspend(struct phy_device *phydev) +{ + int ret; + + ret = genphy_suspend(phydev); + if (ret) + return ret; + + kszphy_disable_clk(phydev); + + return 0; +} + static int kszphy_suspend(struct phy_device *phydev) { /* Disable PHY Interrupts */ @@ -2059,7 +2101,7 @@ static int kszphy_suspend(struct phy_device *phydev) phydev->drv->config_intr(phydev); } - return genphy_suspend(phydev); + return kszphy_generic_suspend(phydev); } static void kszphy_parse_led_mode(struct phy_device *phydev) @@ -2090,7 +2132,9 @@ static int kszphy_resume(struct phy_device *phydev) { int ret; - genphy_resume(phydev); + ret = kszphy_generic_resume(phydev); + if (ret) + return ret; /* After switching from power-down to normal mode, an internal global * reset is automatically generated. Wait a minimum of 1 ms before @@ -2112,6 +2156,24 @@ static int kszphy_resume(struct phy_device *phydev) return 0; } +/* Because of errata DS80000700A, receiver error following software + * power down. Suspend and resume callbacks only disable and enable + * external rmii reference clock. + */ +static int ksz8041_resume(struct phy_device *phydev) +{ + kszphy_enable_clk(phydev); + + return 0; +} + +static int ksz8041_suspend(struct phy_device *phydev) +{ + kszphy_disable_clk(phydev); + + return 0; +} + static int ksz9477_resume(struct phy_device *phydev) { int ret; @@ -2159,7 +2221,10 @@ static int ksz8061_resume(struct phy_device *phydev) if (!(ret & BMCR_PDOWN)) return 0; - genphy_resume(phydev); + ret = kszphy_generic_resume(phydev); + if (ret) + return ret; + usleep_range(1000, 2000); /* Re-program the value after chip is reset. */ @@ -2177,6 +2242,11 @@ static int ksz8061_resume(struct phy_device *phydev) return 0; } +static int ksz8061_suspend(struct phy_device *phydev) +{ + return kszphy_suspend(phydev); +} + static int kszphy_probe(struct phy_device *phydev) { const struct kszphy_type *type = phydev->drv->driver_data; @@ -2217,10 +2287,14 @@ static int kszphy_probe(struct phy_device *phydev) } else if (!clk) { /* unnamed clock from the generic ethernet-phy binding */ clk = devm_clk_get_optional_enabled(&phydev->mdio.dev, NULL); - if (IS_ERR(clk)) - return PTR_ERR(clk); } + if (IS_ERR(clk)) + return PTR_ERR(clk); + + clk_disable_unprepare(clk); + priv->clk = clk; + if (ksz8041_fiber_mode(phydev)) phydev->port = PORT_FIBRE; @@ -5290,6 +5364,21 @@ static int lan8841_probe(struct phy_device *phydev) return 0; } +static int lan8804_resume(struct phy_device *phydev) +{ + return kszphy_resume(phydev); +} + +static int lan8804_suspend(struct phy_device *phydev) +{ + return kszphy_generic_suspend(phydev); +} + +static int lan8841_resume(struct phy_device *phydev) +{ + return kszphy_generic_resume(phydev); +} + static int lan8841_suspend(struct phy_device *phydev) { struct kszphy_priv *priv = phydev->priv; @@ -5298,7 +5387,7 @@ static int lan8841_suspend(struct phy_device *phydev) if (ptp_priv->ptp_clock) ptp_cancel_worker_sync(ptp_priv->ptp_clock); - return genphy_suspend(phydev); + return kszphy_generic_suspend(phydev); } static struct phy_driver ksphy_driver[] = { @@ -5358,9 +5447,8 @@ static struct phy_driver ksphy_driver[] = { .get_sset_count = kszphy_get_sset_count, .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, - /* No suspend/resume callbacks because of errata DS80000700A, - * receiver error following software power down. - */ + .suspend = ksz8041_suspend, + .resume = ksz8041_resume, }, { .phy_id = PHY_ID_KSZ8041RNLI, .phy_id_mask = MICREL_PHY_ID_MASK, @@ -5436,7 +5524,7 @@ static struct phy_driver ksphy_driver[] = { .soft_reset = genphy_soft_reset, .config_intr = kszphy_config_intr, .handle_interrupt = kszphy_handle_interrupt, - .suspend = kszphy_suspend, + .suspend = ksz8061_suspend, .resume = ksz8061_resume, }, { .phy_id = PHY_ID_KSZ9021, @@ -5507,8 +5595,8 @@ static struct phy_driver ksphy_driver[] = { .get_sset_count = kszphy_get_sset_count, .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, - .suspend = genphy_suspend, - .resume = kszphy_resume, + .suspend = lan8804_suspend, + .resume = lan8804_resume, .config_intr = lan8804_config_intr, .handle_interrupt = lan8804_handle_interrupt, }, { @@ -5526,7 +5614,7 @@ static struct phy_driver ksphy_driver[] = { .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, .suspend = lan8841_suspend, - .resume = genphy_resume, + .resume = lan8841_resume, .cable_test_start = lan8814_cable_test_start, .cable_test_get_status = ksz886x_cable_test_get_status, }, { diff --git a/drivers/net/phy/mxl-gpy.c b/drivers/net/phy/mxl-gpy.c index db3c1f72b407..a8ccf257c109 100644 --- a/drivers/net/phy/mxl-gpy.c +++ b/drivers/net/phy/mxl-gpy.c @@ -1014,7 +1014,7 @@ static int gpy_led_polarity_set(struct phy_device *phydev, int index, if (force_active_high) return phy_clear_bits(phydev, PHY_LED, PHY_LED_POLARITY(index)); - unreachable(); + return -EINVAL; } static struct phy_driver gpy_drivers[] = { diff --git a/drivers/net/pse-pd/tps23881.c b/drivers/net/pse-pd/tps23881.c index 5c4e88be46ee..8797ca1a8a21 100644 --- a/drivers/net/pse-pd/tps23881.c +++ b/drivers/net/pse-pd/tps23881.c @@ -64,15 +64,11 @@ static int tps23881_pi_enable(struct pse_controller_dev *pcdev, int id) if (id >= TPS23881_MAX_CHANS) return -ERANGE; - ret = i2c_smbus_read_word_data(client, TPS23881_REG_PW_STATUS); - if (ret < 0) - return ret; - chan = priv->port[id].chan[0]; if (chan < 4) - val = (u16)(ret | BIT(chan)); + val = BIT(chan); else - val = (u16)(ret | BIT(chan + 4)); + val = BIT(chan + 4); if (priv->port[id].is_4p) { chan = priv->port[id].chan[1]; @@ -100,15 +96,11 @@ static int tps23881_pi_disable(struct pse_controller_dev *pcdev, int id) if (id >= TPS23881_MAX_CHANS) return -ERANGE; - ret = i2c_smbus_read_word_data(client, TPS23881_REG_PW_STATUS); - if (ret < 0) - return ret; - chan = priv->port[id].chan[0]; if (chan < 4) - val = (u16)(ret | BIT(chan + 4)); + val = BIT(chan + 4); else - val = (u16)(ret | BIT(chan + 8)); + val = BIT(chan + 8); if (priv->port[id].is_4p) { chan = priv->port[id].chan[1]; diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c index 69ea2c3c76bf..c7690adec8db 100644 --- a/drivers/net/team/team_core.c +++ b/drivers/net/team/team_core.c @@ -998,9 +998,13 @@ static void __team_compute_features(struct team *team) unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; + rcu_read_lock(); + if (list_empty(&team->port_list)) + goto done; + vlan_features = netdev_base_features(vlan_features); + enc_features = netdev_base_features(enc_features); - rcu_read_lock(); list_for_each_entry_rcu(port, &team->port_list, list) { vlan_features = netdev_increment_features(vlan_features, port->dev->vlan_features, @@ -1010,11 +1014,11 @@ static void __team_compute_features(struct team *team) port->dev->hw_enc_features, TEAM_ENC_FEATURES); - dst_release_flag &= port->dev->priv_flags; if (port->dev->hard_header_len > max_hard_header_len) max_hard_header_len = port->dev->hard_header_len; } +done: rcu_read_unlock(); team->dev->vlan_features = vlan_features; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index d7a865ef370b..e816aaba8e5f 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1481,7 +1481,7 @@ static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile, skb->truesize += skb->data_len; for (i = 1; i < it->nr_segs; i++) { - const struct iovec *iov = iter_iov(it); + const struct iovec *iov = iter_iov(it) + i; size_t fragsz = iov->iov_len; struct page *page; void *frag; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 9fe7f704a2f7..e9208a8d2bfa 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1429,6 +1429,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x2c7c, 0x0195, 4)}, /* Quectel EG95 */ {QMI_FIXED_INTF(0x2c7c, 0x0296, 4)}, /* Quectel BG96 */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x030e, 4)}, /* Quectel EM05GV2 */ + {QMI_QUIRK_SET_DTR(0x2c7c, 0x0316, 3)}, /* Quectel RG255C */ {QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)}, /* Fibocom NL678 series */ {QMI_QUIRK_SET_DTR(0x2cb7, 0x0112, 0)}, /* Fibocom FG132 */ {QMI_FIXED_INTF(0x0489, 0xe0b4, 0)}, /* Foxconn T77W968 LTE */ diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c index cd1fe8490ae5..1c43f283ac4a 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c @@ -161,6 +161,7 @@ const struct iwl_cfg_trans_params iwl_gl_trans_cfg = { const char iwl_bz_name[] = "Intel(R) TBD Bz device"; const char iwl_fm_name[] = "Intel(R) Wi-Fi 7 BE201 320MHz"; +const char iwl_wh_name[] = "Intel(R) Wi-Fi 7 BE211 320MHz"; const char iwl_gl_name[] = "Intel(R) Wi-Fi 7 BE200 320MHz"; const char iwl_mtp_name[] = "Intel(R) Wi-Fi 7 BE202 160MHz"; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h index 34c91deca57b..17721bb47e25 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h @@ -545,6 +545,7 @@ extern const char iwl_ax231_name[]; extern const char iwl_ax411_name[]; extern const char iwl_bz_name[]; extern const char iwl_fm_name[]; +extern const char iwl_wh_name[]; extern const char iwl_gl_name[]; extern const char iwl_mtp_name[]; extern const char iwl_sc_name[]; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index f85c01e04ebf..7d973546c9fb 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -2954,6 +2954,7 @@ static void iwl_mvm_query_set_freqs(struct iwl_mvm *mvm, int idx) { int i; + int n_channels = 0; if (fw_has_api(&mvm->fw->ucode_capa, IWL_UCODE_TLV_API_SCAN_OFFLOAD_CHANS)) { @@ -2962,7 +2963,7 @@ static void iwl_mvm_query_set_freqs(struct iwl_mvm *mvm, for (i = 0; i < SCAN_OFFLOAD_MATCHING_CHANNELS_LEN * 8; i++) if (matches[idx].matching_channels[i / 8] & (BIT(i % 8))) - match->channels[match->n_channels++] = + match->channels[n_channels++] = mvm->nd_channels[i]->center_freq; } else { struct iwl_scan_offload_profile_match_v1 *matches = @@ -2970,9 +2971,11 @@ static void iwl_mvm_query_set_freqs(struct iwl_mvm *mvm, for (i = 0; i < SCAN_OFFLOAD_MATCHING_CHANNELS_LEN_V1 * 8; i++) if (matches[idx].matching_channels[i / 8] & (BIT(i % 8))) - match->channels[match->n_channels++] = + match->channels[n_channels++] = mvm->nd_channels[i]->center_freq; } + /* We may have ended up with fewer channels than we allocated. */ + match->n_channels = n_channels; } /** @@ -3053,6 +3056,8 @@ static void iwl_mvm_query_netdetect_reasons(struct iwl_mvm *mvm, GFP_KERNEL); if (!net_detect || !n_matches) goto out_report_nd; + net_detect->n_matches = n_matches; + n_matches = 0; for_each_set_bit(i, &matched_profiles, mvm->n_nd_match_sets) { struct cfg80211_wowlan_nd_match *match; @@ -3066,8 +3071,9 @@ static void iwl_mvm_query_netdetect_reasons(struct iwl_mvm *mvm, GFP_KERNEL); if (!match) goto out_report_nd; + match->n_channels = n_channels; - net_detect->matches[net_detect->n_matches++] = match; + net_detect->matches[n_matches++] = match; /* We inverted the order of the SSIDs in the scan * request, so invert the index here. @@ -3082,6 +3088,8 @@ static void iwl_mvm_query_netdetect_reasons(struct iwl_mvm *mvm, iwl_mvm_query_set_freqs(mvm, d3_data->nd_results, match, i); } + /* We may have fewer matches than we allocated. */ + net_detect->n_matches = n_matches; out_report_nd: wakeup.net_detect = net_detect; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 805fb249a0c6..8fb2aa282242 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -1106,19 +1106,54 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = { iwlax210_2ax_cfg_so_jf_b0, iwl9462_name), /* Bz */ -/* FIXME: need to change the naming according to the actual CRF */ _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + iwl_cfg_bz, iwl_ax201_name), + + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + iwl_cfg_bz, iwl_ax211_name), + + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, iwl_cfg_bz, iwl_fm_name), _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + iwl_cfg_bz, iwl_wh_name), + + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + iwl_cfg_bz, iwl_ax201_name), + + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + iwl_cfg_bz, iwl_ax211_name), + + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, iwl_cfg_bz, iwl_fm_name), + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + iwl_cfg_bz, iwl_wh_name), + /* Ga (Gl) */ _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_MAC_TYPE_GL, IWL_CFG_ANY, diff --git a/drivers/net/wireless/st/cw1200/cw1200_spi.c b/drivers/net/wireless/st/cw1200/cw1200_spi.c index 862964a8cc87..52386dfb5f4a 100644 --- a/drivers/net/wireless/st/cw1200/cw1200_spi.c +++ b/drivers/net/wireless/st/cw1200/cw1200_spi.c @@ -442,8 +442,8 @@ static void cw1200_spi_disconnect(struct spi_device *func) cw1200_core_release(self->core); self->core = NULL; } + cw1200_spi_off(self, dev_get_platdata(&func->dev)); } - cw1200_spi_off(self, dev_get_platdata(&func->dev)); } static int __maybe_unused cw1200_spi_suspend(struct device *dev) diff --git a/drivers/net/wwan/iosm/iosm_ipc_mmio.c b/drivers/net/wwan/iosm/iosm_ipc_mmio.c index 63eb08c43c05..6764c13530b9 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mmio.c +++ b/drivers/net/wwan/iosm/iosm_ipc_mmio.c @@ -104,7 +104,7 @@ struct iosm_mmio *ipc_mmio_init(void __iomem *mmio, struct device *dev) break; msleep(20); - } while (retries-- > 0); + } while (--retries > 0); if (!retries) { dev_err(ipc_mmio->dev, "invalid exec stage %X", stage); diff --git a/drivers/net/wwan/t7xx/t7xx_state_monitor.c b/drivers/net/wwan/t7xx/t7xx_state_monitor.c index 3931c7a13f5a..cbdbb91e8381 100644 --- a/drivers/net/wwan/t7xx/t7xx_state_monitor.c +++ b/drivers/net/wwan/t7xx/t7xx_state_monitor.c @@ -104,14 +104,21 @@ void t7xx_fsm_broadcast_state(struct t7xx_fsm_ctl *ctl, enum md_state state) fsm_state_notify(ctl->md, state); } +static void fsm_release_command(struct kref *ref) +{ + struct t7xx_fsm_command *cmd = container_of(ref, typeof(*cmd), refcnt); + + kfree(cmd); +} + static void fsm_finish_command(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_command *cmd, int result) { if (cmd->flag & FSM_CMD_FLAG_WAIT_FOR_COMPLETION) { - *cmd->ret = result; - complete_all(cmd->done); + cmd->result = result; + complete_all(&cmd->done); } - kfree(cmd); + kref_put(&cmd->refcnt, fsm_release_command); } static void fsm_del_kf_event(struct t7xx_fsm_event *event) @@ -475,7 +482,6 @@ static int fsm_main_thread(void *data) int t7xx_fsm_append_cmd(struct t7xx_fsm_ctl *ctl, enum t7xx_fsm_cmd_state cmd_id, unsigned int flag) { - DECLARE_COMPLETION_ONSTACK(done); struct t7xx_fsm_command *cmd; unsigned long flags; int ret; @@ -487,11 +493,13 @@ int t7xx_fsm_append_cmd(struct t7xx_fsm_ctl *ctl, enum t7xx_fsm_cmd_state cmd_id INIT_LIST_HEAD(&cmd->entry); cmd->cmd_id = cmd_id; cmd->flag = flag; + kref_init(&cmd->refcnt); if (flag & FSM_CMD_FLAG_WAIT_FOR_COMPLETION) { - cmd->done = &done; - cmd->ret = &ret; + init_completion(&cmd->done); + kref_get(&cmd->refcnt); } + kref_get(&cmd->refcnt); spin_lock_irqsave(&ctl->command_lock, flags); list_add_tail(&cmd->entry, &ctl->command_queue); spin_unlock_irqrestore(&ctl->command_lock, flags); @@ -501,11 +509,11 @@ int t7xx_fsm_append_cmd(struct t7xx_fsm_ctl *ctl, enum t7xx_fsm_cmd_state cmd_id if (flag & FSM_CMD_FLAG_WAIT_FOR_COMPLETION) { unsigned long wait_ret; - wait_ret = wait_for_completion_timeout(&done, + wait_ret = wait_for_completion_timeout(&cmd->done, msecs_to_jiffies(FSM_CMD_TIMEOUT_MS)); - if (!wait_ret) - return -ETIMEDOUT; + ret = wait_ret ? cmd->result : -ETIMEDOUT; + kref_put(&cmd->refcnt, fsm_release_command); return ret; } diff --git a/drivers/net/wwan/t7xx/t7xx_state_monitor.h b/drivers/net/wwan/t7xx/t7xx_state_monitor.h index 7b0a9baf488c..6e0601bb752e 100644 --- a/drivers/net/wwan/t7xx/t7xx_state_monitor.h +++ b/drivers/net/wwan/t7xx/t7xx_state_monitor.h @@ -110,8 +110,9 @@ struct t7xx_fsm_command { struct list_head entry; enum t7xx_fsm_cmd_state cmd_id; unsigned int flag; - struct completion *done; - int *ret; + struct completion done; + int result; + struct kref refcnt; }; struct t7xx_fsm_notifier { diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 4265c1cd0ff7..63fe51d0e64d 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -867,7 +867,7 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev static int xennet_close(struct net_device *dev) { struct netfront_info *np = netdev_priv(dev); - unsigned int num_queues = dev->real_num_tx_queues; + unsigned int num_queues = np->queues ? dev->real_num_tx_queues : 0; unsigned int i; struct netfront_queue *queue; netif_tx_stop_all_queues(np->netdev); @@ -882,6 +882,9 @@ static void xennet_destroy_queues(struct netfront_info *info) { unsigned int i; + if (!info->queues) + return; + for (i = 0; i < info->netdev->real_num_tx_queues; i++) { struct netfront_queue *queue = &info->queues[i]; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index d169a30eb935..a970168a3014 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2034,7 +2034,7 @@ static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id, * or smaller than a sector size yet, so catch this early and don't * allow block I/O. */ - if (head->lba_shift > PAGE_SHIFT || head->lba_shift < SECTOR_SHIFT) { + if (blk_validate_block_size(bs)) { bs = (1 << 9); valid = false; } diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 611b02c8a8b3..c4bb8dfe1a45 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -173,6 +173,11 @@ enum nvme_quirks { * MSI (but not MSI-X) interrupts are broken and never fire. */ NVME_QUIRK_BROKEN_MSI = (1 << 21), + + /* + * Align dma pool segment size to 512 bytes + */ + NVME_QUIRK_DMAPOOL_ALIGN_512 = (1 << 22), }; /* diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 1a5ba80f1811..e2634f437f33 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2834,15 +2834,20 @@ static int nvme_disable_prepare_reset(struct nvme_dev *dev, bool shutdown) static int nvme_setup_prp_pools(struct nvme_dev *dev) { + size_t small_align = 256; + dev->prp_page_pool = dma_pool_create("prp list page", dev->dev, NVME_CTRL_PAGE_SIZE, NVME_CTRL_PAGE_SIZE, 0); if (!dev->prp_page_pool) return -ENOMEM; + if (dev->ctrl.quirks & NVME_QUIRK_DMAPOOL_ALIGN_512) + small_align = 512; + /* Optimisation for I/Os between 4k and 128k */ dev->prp_small_pool = dma_pool_create("prp list 256", dev->dev, - 256, 256, 0); + 256, small_align, 0); if (!dev->prp_small_pool) { dma_pool_destroy(dev->prp_page_pool); return -ENOMEM; @@ -3607,7 +3612,7 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_VDEVICE(REDHAT, 0x0010), /* Qemu emulated controller */ .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1217, 0x8760), /* O2 Micro 64GB Steam Deck */ - .driver_data = NVME_QUIRK_QDEPTH_ONE }, + .driver_data = NVME_QUIRK_DMAPOOL_ALIGN_512, }, { PCI_DEVICE(0x126f, 0x2262), /* Silicon Motion generic */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS | NVME_QUIRK_BOGUS_NID, }, diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 28c76a3e1bd2..b127d41dbbfe 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -2024,14 +2024,6 @@ static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl) return __nvme_tcp_alloc_io_queues(ctrl); } -static void nvme_tcp_destroy_io_queues(struct nvme_ctrl *ctrl, bool remove) -{ - nvme_tcp_stop_io_queues(ctrl); - if (remove) - nvme_remove_io_tag_set(ctrl); - nvme_tcp_free_io_queues(ctrl); -} - static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new) { int ret, nr_queues; @@ -2176,9 +2168,11 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl, nvme_sync_io_queues(ctrl); nvme_tcp_stop_io_queues(ctrl); nvme_cancel_tagset(ctrl); - if (remove) + if (remove) { nvme_unquiesce_io_queues(ctrl); - nvme_tcp_destroy_io_queues(ctrl, remove); + nvme_remove_io_tag_set(ctrl); + } + nvme_tcp_free_io_queues(ctrl); } static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl, @@ -2267,7 +2261,9 @@ destroy_io: nvme_sync_io_queues(ctrl); nvme_tcp_stop_io_queues(ctrl); nvme_cancel_tagset(ctrl); - nvme_tcp_destroy_io_queues(ctrl, new); + if (new) + nvme_remove_io_tag_set(ctrl); + nvme_tcp_free_io_queues(ctrl); } destroy_admin: nvme_stop_keep_alive(ctrl); diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 2962794ce881..fa89b0549c36 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -139,7 +139,7 @@ static u16 nvmet_get_smart_log_all(struct nvmet_req *req, unsigned long idx; ctrl = req->sq->ctrl; - xa_for_each(&ctrl->subsys->namespaces, idx, ns) { + nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) { /* we don't have the right data for file backed ns */ if (!ns->bdev) continue; @@ -331,9 +331,10 @@ static u32 nvmet_format_ana_group(struct nvmet_req *req, u32 grpid, u32 count = 0; if (!(req->cmd->get_log_page.lsp & NVME_ANA_LOG_RGO)) { - xa_for_each(&ctrl->subsys->namespaces, idx, ns) + nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) { if (ns->anagrpid == grpid) desc->nsids[count++] = cpu_to_le32(ns->nsid); + } } desc->grpid = cpu_to_le32(grpid); @@ -772,7 +773,7 @@ static void nvmet_execute_identify_endgrp_list(struct nvmet_req *req) goto out; } - xa_for_each(&ctrl->subsys->namespaces, idx, ns) { + nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) { if (ns->nsid <= min_endgid) continue; @@ -815,7 +816,7 @@ static void nvmet_execute_identify_nslist(struct nvmet_req *req, bool match_css) goto out; } - xa_for_each(&ctrl->subsys->namespaces, idx, ns) { + nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) { if (ns->nsid <= min_nsid) continue; if (match_css && req->ns->csi != req->cmd->identify.csi) diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index eeee9e9b854c..2b030f0efc38 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -810,18 +810,6 @@ static struct configfs_attribute *nvmet_ns_attrs[] = { NULL, }; -bool nvmet_subsys_nsid_exists(struct nvmet_subsys *subsys, u32 nsid) -{ - struct config_item *ns_item; - char name[12]; - - snprintf(name, sizeof(name), "%u", nsid); - mutex_lock(&subsys->namespaces_group.cg_subsys->su_mutex); - ns_item = config_group_find_item(&subsys->namespaces_group, name); - mutex_unlock(&subsys->namespaces_group.cg_subsys->su_mutex); - return ns_item != NULL; -} - static void nvmet_ns_release(struct config_item *item) { struct nvmet_ns *ns = to_nvmet_ns(item); @@ -2254,12 +2242,17 @@ static ssize_t nvmet_root_discovery_nqn_store(struct config_item *item, const char *page, size_t count) { struct list_head *entry; + char *old_nqn, *new_nqn; size_t len; len = strcspn(page, "\n"); if (!len || len > NVMF_NQN_FIELD_LEN - 1) return -EINVAL; + new_nqn = kstrndup(page, len, GFP_KERNEL); + if (!new_nqn) + return -ENOMEM; + down_write(&nvmet_config_sem); list_for_each(entry, &nvmet_subsystems_group.cg_children) { struct config_item *item = @@ -2268,13 +2261,15 @@ static ssize_t nvmet_root_discovery_nqn_store(struct config_item *item, if (!strncmp(config_item_name(item), page, len)) { pr_err("duplicate NQN %s\n", config_item_name(item)); up_write(&nvmet_config_sem); + kfree(new_nqn); return -EINVAL; } } - memset(nvmet_disc_subsys->subsysnqn, 0, NVMF_NQN_FIELD_LEN); - memcpy(nvmet_disc_subsys->subsysnqn, page, len); + old_nqn = nvmet_disc_subsys->subsysnqn; + nvmet_disc_subsys->subsysnqn = new_nqn; up_write(&nvmet_config_sem); + kfree(old_nqn); return len; } diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 1f4e9989663b..fde6c555af61 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -127,7 +127,7 @@ static u32 nvmet_max_nsid(struct nvmet_subsys *subsys) unsigned long idx; u32 nsid = 0; - xa_for_each(&subsys->namespaces, idx, cur) + nvmet_for_each_enabled_ns(&subsys->namespaces, idx, cur) nsid = cur->nsid; return nsid; @@ -441,11 +441,14 @@ u16 nvmet_req_find_ns(struct nvmet_req *req) struct nvmet_subsys *subsys = nvmet_req_subsys(req); req->ns = xa_load(&subsys->namespaces, nsid); - if (unlikely(!req->ns)) { + if (unlikely(!req->ns || !req->ns->enabled)) { req->error_loc = offsetof(struct nvme_common_command, nsid); - if (nvmet_subsys_nsid_exists(subsys, nsid)) - return NVME_SC_INTERNAL_PATH_ERROR; - return NVME_SC_INVALID_NS | NVME_STATUS_DNR; + if (!req->ns) /* ns doesn't exist! */ + return NVME_SC_INVALID_NS | NVME_STATUS_DNR; + + /* ns exists but it's disabled */ + req->ns = NULL; + return NVME_SC_INTERNAL_PATH_ERROR; } percpu_ref_get(&req->ns->ref); @@ -583,8 +586,6 @@ int nvmet_ns_enable(struct nvmet_ns *ns) goto out_unlock; ret = -EMFILE; - if (subsys->nr_namespaces == NVMET_MAX_NAMESPACES) - goto out_unlock; ret = nvmet_bdev_ns_enable(ns); if (ret == -ENOTBLK) @@ -599,38 +600,19 @@ int nvmet_ns_enable(struct nvmet_ns *ns) list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) nvmet_p2pmem_ns_add_p2p(ctrl, ns); - ret = percpu_ref_init(&ns->ref, nvmet_destroy_namespace, - 0, GFP_KERNEL); - if (ret) - goto out_dev_put; - - if (ns->nsid > subsys->max_nsid) - subsys->max_nsid = ns->nsid; - - ret = xa_insert(&subsys->namespaces, ns->nsid, ns, GFP_KERNEL); - if (ret) - goto out_restore_subsys_maxnsid; - if (ns->pr.enable) { ret = nvmet_pr_init_ns(ns); if (ret) - goto out_remove_from_subsys; + goto out_dev_put; } - subsys->nr_namespaces++; - nvmet_ns_changed(subsys, ns->nsid); ns->enabled = true; + xa_set_mark(&subsys->namespaces, ns->nsid, NVMET_NS_ENABLED); ret = 0; out_unlock: mutex_unlock(&subsys->lock); return ret; - -out_remove_from_subsys: - xa_erase(&subsys->namespaces, ns->nsid); -out_restore_subsys_maxnsid: - subsys->max_nsid = nvmet_max_nsid(subsys); - percpu_ref_exit(&ns->ref); out_dev_put: list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) pci_dev_put(radix_tree_delete(&ctrl->p2p_ns_map, ns->nsid)); @@ -649,15 +631,37 @@ void nvmet_ns_disable(struct nvmet_ns *ns) goto out_unlock; ns->enabled = false; - xa_erase(&ns->subsys->namespaces, ns->nsid); - if (ns->nsid == subsys->max_nsid) - subsys->max_nsid = nvmet_max_nsid(subsys); + xa_clear_mark(&subsys->namespaces, ns->nsid, NVMET_NS_ENABLED); list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) pci_dev_put(radix_tree_delete(&ctrl->p2p_ns_map, ns->nsid)); mutex_unlock(&subsys->lock); + if (ns->pr.enable) + nvmet_pr_exit_ns(ns); + + mutex_lock(&subsys->lock); + nvmet_ns_changed(subsys, ns->nsid); + nvmet_ns_dev_disable(ns); +out_unlock: + mutex_unlock(&subsys->lock); +} + +void nvmet_ns_free(struct nvmet_ns *ns) +{ + struct nvmet_subsys *subsys = ns->subsys; + + nvmet_ns_disable(ns); + + mutex_lock(&subsys->lock); + + xa_erase(&subsys->namespaces, ns->nsid); + if (ns->nsid == subsys->max_nsid) + subsys->max_nsid = nvmet_max_nsid(subsys); + + mutex_unlock(&subsys->lock); + /* * Now that we removed the namespaces from the lookup list, we * can kill the per_cpu ref and wait for any remaining references @@ -671,21 +675,9 @@ void nvmet_ns_disable(struct nvmet_ns *ns) wait_for_completion(&ns->disable_done); percpu_ref_exit(&ns->ref); - if (ns->pr.enable) - nvmet_pr_exit_ns(ns); - mutex_lock(&subsys->lock); - subsys->nr_namespaces--; - nvmet_ns_changed(subsys, ns->nsid); - nvmet_ns_dev_disable(ns); -out_unlock: mutex_unlock(&subsys->lock); -} - -void nvmet_ns_free(struct nvmet_ns *ns) -{ - nvmet_ns_disable(ns); down_write(&nvmet_ana_sem); nvmet_ana_group_enabled[ns->anagrpid]--; @@ -699,15 +691,33 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid) { struct nvmet_ns *ns; + mutex_lock(&subsys->lock); + + if (subsys->nr_namespaces == NVMET_MAX_NAMESPACES) + goto out_unlock; + ns = kzalloc(sizeof(*ns), GFP_KERNEL); if (!ns) - return NULL; + goto out_unlock; init_completion(&ns->disable_done); ns->nsid = nsid; ns->subsys = subsys; + if (percpu_ref_init(&ns->ref, nvmet_destroy_namespace, 0, GFP_KERNEL)) + goto out_free; + + if (ns->nsid > subsys->max_nsid) + subsys->max_nsid = nsid; + + if (xa_insert(&subsys->namespaces, ns->nsid, ns, GFP_KERNEL)) + goto out_exit; + + subsys->nr_namespaces++; + + mutex_unlock(&subsys->lock); + down_write(&nvmet_ana_sem); ns->anagrpid = NVMET_DEFAULT_ANA_GRPID; nvmet_ana_group_enabled[ns->anagrpid]++; @@ -718,6 +728,14 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid) ns->csi = NVME_CSI_NVM; return ns; +out_exit: + subsys->max_nsid = nvmet_max_nsid(subsys); + percpu_ref_exit(&ns->ref); +out_free: + kfree(ns); +out_unlock: + mutex_unlock(&subsys->lock); + return NULL; } static void nvmet_update_sq_head(struct nvmet_req *req) @@ -1394,7 +1412,7 @@ static void nvmet_setup_p2p_ns_map(struct nvmet_ctrl *ctrl, ctrl->p2p_client = get_device(req->p2p_client); - xa_for_each(&ctrl->subsys->namespaces, idx, ns) + nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) nvmet_p2pmem_ns_add_p2p(ctrl, ns); } diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index 0bda83d0fc3e..eaf31c823cbe 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -36,7 +36,7 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id) */ id->nsfeat |= 1 << 4; /* NPWG = Namespace Preferred Write Granularity. 0's based */ - id->npwg = lpp0b; + id->npwg = to0based(bdev_io_min(bdev) / bdev_logical_block_size(bdev)); /* NPWA = Namespace Preferred Write Alignment. 0's based */ id->npwa = id->npwg; /* NPDG = Namespace Preferred Deallocate Granularity. 0's based */ diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 58328b35dc96..7233549f7c8a 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -24,6 +24,7 @@ #define NVMET_DEFAULT_VS NVME_VS(2, 1, 0) +#define NVMET_NS_ENABLED XA_MARK_1 #define NVMET_ASYNC_EVENTS 4 #define NVMET_ERROR_LOG_SLOTS 128 #define NVMET_NO_ERROR_LOC ((u16)-1) @@ -33,6 +34,12 @@ #define NVMET_FR_MAX_SIZE 8 #define NVMET_PR_LOG_QUEUE_SIZE 64 +#define nvmet_for_each_ns(xa, index, entry) \ + xa_for_each(xa, index, entry) + +#define nvmet_for_each_enabled_ns(xa, index, entry) \ + xa_for_each_marked(xa, index, entry, NVMET_NS_ENABLED) + /* * Supported optional AENs: */ diff --git a/drivers/nvme/target/pr.c b/drivers/nvme/target/pr.c index 90e9f5bbe581..cd22d8333314 100644 --- a/drivers/nvme/target/pr.c +++ b/drivers/nvme/target/pr.c @@ -60,7 +60,7 @@ u16 nvmet_set_feat_resv_notif_mask(struct nvmet_req *req, u32 mask) goto success; } - xa_for_each(&ctrl->subsys->namespaces, idx, ns) { + nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) { if (ns->pr.enable) WRITE_ONCE(ns->pr.notify_mask, mask); } @@ -1056,7 +1056,7 @@ int nvmet_ctrl_init_pr(struct nvmet_ctrl *ctrl) * nvmet_pr_init_ns(), see more details in nvmet_ns_enable(). * So just check ns->pr.enable. */ - xa_for_each(&subsys->namespaces, idx, ns) { + nvmet_for_each_enabled_ns(&subsys->namespaces, idx, ns) { if (ns->pr.enable) { ret = nvmet_pr_alloc_and_insert_pc_ref(ns, ctrl->cntlid, &ctrl->hostid); @@ -1067,7 +1067,7 @@ int nvmet_ctrl_init_pr(struct nvmet_ctrl *ctrl) return 0; free_per_ctrl_refs: - xa_for_each(&subsys->namespaces, idx, ns) { + nvmet_for_each_enabled_ns(&subsys->namespaces, idx, ns) { if (ns->pr.enable) { pc_ref = xa_erase(&ns->pr_per_ctrl_refs, ctrl->cntlid); if (pc_ref) @@ -1087,7 +1087,7 @@ void nvmet_ctrl_destroy_pr(struct nvmet_ctrl *ctrl) kfifo_free(&ctrl->pr_log_mgr.log_queue); mutex_destroy(&ctrl->pr_log_mgr.lock); - xa_for_each(&ctrl->subsys->namespaces, idx, ns) { + nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) { if (ns->pr.enable) { pc_ref = xa_erase(&ns->pr_per_ctrl_refs, ctrl->cntlid); if (pc_ref) diff --git a/drivers/of/address.c b/drivers/of/address.c index c5b925ac469f..c1f1c810e810 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -459,7 +459,8 @@ static int of_translate_one(const struct device_node *parent, const struct of_bu } if (ranges == NULL || rlen == 0) { offset = of_read_number(addr, na); - memset(addr, 0, pna * 4); + /* set address to zero, pass flags through */ + memset(addr + pbus->flag_cells, 0, (pna - pbus->flag_cells) * 4); pr_debug("empty ranges; 1:1 translation\n"); goto finish; } @@ -619,7 +620,7 @@ struct device_node *__of_get_dma_parent(const struct device_node *np) if (ret < 0) return of_get_parent(np); - return of_node_get(args.np); + return args.np; } #endif diff --git a/drivers/of/base.c b/drivers/of/base.c index 7dc394255a0a..6f5abea2462a 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -88,7 +88,8 @@ static bool __of_node_is_type(const struct device_node *np, const char *type) } #define EXCLUDED_DEFAULT_CELLS_PLATFORMS ( \ - IS_ENABLED(CONFIG_SPARC) \ + IS_ENABLED(CONFIG_SPARC) || \ + of_find_compatible_node(NULL, NULL, "coreboot") \ ) int of_bus_n_addr_cells(struct device_node *np) @@ -1507,8 +1508,10 @@ int of_parse_phandle_with_args_map(const struct device_node *np, map_len--; /* Check if not found */ - if (!new) + if (!new) { + ret = -EINVAL; goto put; + } if (!of_device_is_available(new)) match = 0; @@ -1518,17 +1521,20 @@ int of_parse_phandle_with_args_map(const struct device_node *np, goto put; /* Check for malformed properties */ - if (WARN_ON(new_size > MAX_PHANDLE_ARGS)) - goto put; - if (map_len < new_size) + if (WARN_ON(new_size > MAX_PHANDLE_ARGS) || + map_len < new_size) { + ret = -EINVAL; goto put; + } /* Move forward by new node's #<list>-cells amount */ map += new_size; map_len -= new_size; } - if (!match) + if (!match) { + ret = -ENOENT; goto put; + } /* Get the <list>-map-pass-thru property (optional) */ pass = of_get_property(cur, pass_name, NULL); diff --git a/drivers/of/empty_root.dts b/drivers/of/empty_root.dts index cf9e97a60f48..cbe169ba3db5 100644 --- a/drivers/of/empty_root.dts +++ b/drivers/of/empty_root.dts @@ -2,5 +2,12 @@ /dts-v1/; / { - + /* + * #address-cells/#size-cells are required properties at root node. + * Use 2 cells for both address cells and size cells in order to fully + * support 64-bit addresses and sizes on systems using this empty root + * node. + */ + #address-cells = <0x02>; + #size-cells = <0x02>; }; diff --git a/drivers/of/irq.c b/drivers/of/irq.c index 67fc0ceaa5f5..98b1cf78ecac 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -111,6 +111,7 @@ const __be32 *of_irq_parse_imap_parent(const __be32 *imap, int len, struct of_ph else np = of_find_node_by_phandle(be32_to_cpup(imap)); imap++; + len--; /* Check if not found */ if (!np) { @@ -354,6 +355,7 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar return of_irq_parse_oldworld(device, index, out_irq); /* Get the reg property (if any) */ + addr_len = 0; addr = of_get_property(device, "reg", &addr_len); /* Prevent out-of-bounds read in case of longer interrupt parent address size */ diff --git a/drivers/of/property.c b/drivers/of/property.c index 519bf9229e61..cfc8aea002e4 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -1286,7 +1286,6 @@ DEFINE_SIMPLE_PROP(iommus, "iommus", "#iommu-cells") DEFINE_SIMPLE_PROP(mboxes, "mboxes", "#mbox-cells") DEFINE_SIMPLE_PROP(io_channels, "io-channels", "#io-channel-cells") DEFINE_SIMPLE_PROP(io_backends, "io-backends", "#io-backend-cells") -DEFINE_SIMPLE_PROP(interrupt_parent, "interrupt-parent", NULL) DEFINE_SIMPLE_PROP(dmas, "dmas", "#dma-cells") DEFINE_SIMPLE_PROP(power_domains, "power-domains", "#power-domain-cells") DEFINE_SIMPLE_PROP(hwlocks, "hwlocks", "#hwlock-cells") @@ -1432,7 +1431,6 @@ static const struct supplier_bindings of_supplier_bindings[] = { { .parse_prop = parse_mboxes, }, { .parse_prop = parse_io_channels, }, { .parse_prop = parse_io_backends, }, - { .parse_prop = parse_interrupt_parent, }, { .parse_prop = parse_dmas, .optional = true, }, { .parse_prop = parse_power_domains, }, { .parse_prop = parse_hwlocks, }, diff --git a/drivers/of/unittest-data/tests-address.dtsi b/drivers/of/unittest-data/tests-address.dtsi index 3344f15c3755..f02a181bb125 100644 --- a/drivers/of/unittest-data/tests-address.dtsi +++ b/drivers/of/unittest-data/tests-address.dtsi @@ -114,6 +114,7 @@ device_type = "pci"; ranges = <0x82000000 0 0xe8000000 0 0xe8000000 0 0x7f00000>, <0x81000000 0 0x00000000 0 0xefff0000 0 0x0010000>; + dma-ranges = <0x43000000 0x10 0x00 0x00 0x00 0x00 0x10000000>; reg = <0x00000000 0xd1070000 0x20000>; pci@0,0 { @@ -142,6 +143,7 @@ #size-cells = <0x01>; ranges = <0xa0000000 0 0 0 0x2000000>, <0xb0000000 1 0 0 0x1000000>; + dma-ranges = <0xc0000000 0x43000000 0x10 0x00 0x10000000>; dev@e0000000 { reg = <0xa0001000 0x1000>, diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index 42b411f32b1b..438fd70fa995 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -1213,6 +1213,44 @@ static void __init of_unittest_pci_dma_ranges(void) of_node_put(np); } +static void __init of_unittest_pci_empty_dma_ranges(void) +{ + struct device_node *np; + struct of_pci_range range; + struct of_pci_range_parser parser; + + if (!IS_ENABLED(CONFIG_PCI)) + return; + + np = of_find_node_by_path("/testcase-data/address-tests2/pcie@d1070000/pci@0,0/dev@0,0/local-bus@0"); + if (!np) { + pr_err("missing testcase data\n"); + return; + } + + if (of_pci_dma_range_parser_init(&parser, np)) { + pr_err("missing dma-ranges property\n"); + return; + } + + /* + * Get the dma-ranges from the device tree + */ + for_each_of_pci_range(&parser, &range) { + unittest(range.size == 0x10000000, + "for_each_of_pci_range wrong size on node %pOF size=%llx\n", + np, range.size); + unittest(range.cpu_addr == 0x00000000, + "for_each_of_pci_range wrong CPU addr (%llx) on node %pOF", + range.cpu_addr, np); + unittest(range.pci_addr == 0xc0000000, + "for_each_of_pci_range wrong DMA addr (%llx) on node %pOF", + range.pci_addr, np); + } + + of_node_put(np); +} + static void __init of_unittest_bus_ranges(void) { struct device_node *np; @@ -4272,6 +4310,7 @@ static int __init of_unittest(void) of_unittest_dma_get_max_cpu_address(); of_unittest_parse_dma_ranges(); of_unittest_pci_dma_ranges(); + of_unittest_pci_empty_dma_ranges(); of_unittest_bus_ranges(); of_unittest_bus_3cell_ranges(); of_unittest_reg(); diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index 569125726b3e..d7ba8795d60f 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -350,8 +350,11 @@ bool pci_msi_domain_supports(struct pci_dev *pdev, unsigned int feature_mask, domain = dev_get_msi_domain(&pdev->dev); - if (!domain || !irq_domain_is_hierarchy(domain)) - return mode == ALLOW_LEGACY; + if (!domain || !irq_domain_is_hierarchy(domain)) { + if (IS_ENABLED(CONFIG_PCI_MSI_ARCH_FALLBACKS)) + return mode == ALLOW_LEGACY; + return false; + } if (!irq_domain_is_msi_parent(domain)) { /* diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 3a45879d85db..2f647cac4cae 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -433,6 +433,10 @@ int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, if (WARN_ON_ONCE(dev->msi_enabled)) return -EINVAL; + /* Test for the availability of MSI support */ + if (!pci_msi_domain_supports(dev, 0, ALLOW_LEGACY)) + return -ENOTSUPP; + nvec = pci_msi_vec_count(dev); if (nvec < 0) return nvec; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 0b29ec6e8e5e..661f98c6c63a 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -6232,12 +6232,14 @@ u8 pcie_get_supported_speeds(struct pci_dev *dev) pcie_capability_read_dword(dev, PCI_EXP_LNKCAP2, &lnkcap2); speeds = lnkcap2 & PCI_EXP_LNKCAP2_SLS; + /* Ignore speeds higher than Max Link Speed */ + pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &lnkcap); + speeds &= GENMASK(lnkcap & PCI_EXP_LNKCAP_SLS, 0); + /* PCIe r3.0-compliant */ if (speeds) return speeds; - pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &lnkcap); - /* Synthesize from the Max Link Speed field */ if ((lnkcap & PCI_EXP_LNKCAP_SLS) == PCI_EXP_LNKCAP_SLS_5_0GB) speeds = PCI_EXP_LNKCAP2_SLS_5_0GB | PCI_EXP_LNKCAP2_SLS_2_5GB; diff --git a/drivers/pci/pcie/portdrv.c b/drivers/pci/pcie/portdrv.c index 5e10306b6308..02e73099bad0 100644 --- a/drivers/pci/pcie/portdrv.c +++ b/drivers/pci/pcie/portdrv.c @@ -265,12 +265,14 @@ static int get_port_device_capability(struct pci_dev *dev) (pcie_ports_dpc_native || (services & PCIE_PORT_SERVICE_AER))) services |= PCIE_PORT_SERVICE_DPC; + /* Enable bandwidth control if more than one speed is supported. */ if (pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM || pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) { u32 linkcap; pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &linkcap); - if (linkcap & PCI_EXP_LNKCAP_LBNC) + if (linkcap & PCI_EXP_LNKCAP_LBNC && + hweight8(dev->supported_speeds) > 1) services |= PCIE_PORT_SERVICE_BWCTRL; } diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 1aa303f76cc7..194c153e5d71 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -507,8 +507,7 @@ static int pmu_sbi_event_map(struct perf_event *event, u64 *econfig) { u32 type = event->attr.type; u64 config = event->attr.config; - u64 raw_config_val; - int ret; + int ret = -ENOENT; /* * Ensure we are finished checking standard hardware events for @@ -528,21 +527,23 @@ static int pmu_sbi_event_map(struct perf_event *event, u64 *econfig) case PERF_TYPE_RAW: /* * As per SBI specification, the upper 16 bits must be unused - * for a raw event. + * for a hardware raw event. * Bits 63:62 are used to distinguish between raw events * 00 - Hardware raw event * 10 - SBI firmware events * 11 - Risc-V platform specific firmware event */ - raw_config_val = config & RISCV_PMU_RAW_EVENT_MASK; + switch (config >> 62) { case 0: - ret = RISCV_PMU_RAW_EVENT_IDX; - *econfig = raw_config_val; + /* Return error any bits [48-63] is set as it is not allowed by the spec */ + if (!(config & ~RISCV_PMU_RAW_EVENT_MASK)) { + *econfig = config & RISCV_PMU_RAW_EVENT_MASK; + ret = RISCV_PMU_RAW_EVENT_IDX; + } break; case 2: - ret = (raw_config_val & 0xFFFF) | - (SBI_PMU_EVENT_TYPE_FW << 16); + ret = (config & 0xFFFF) | (SBI_PMU_EVENT_TYPE_FW << 16); break; case 3: /* @@ -551,12 +552,13 @@ static int pmu_sbi_event_map(struct perf_event *event, u64 *econfig) * Event data - raw event encoding */ ret = SBI_PMU_EVENT_TYPE_FW << 16 | RISCV_PLAT_FW_EVENT; - *econfig = raw_config_val; + *econfig = config & RISCV_PMU_PLAT_FW_EVENT_MASK; + break; + default: break; } break; default: - ret = -ENOENT; break; } diff --git a/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c b/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c index 950b7ae1d1a8..dc452610934a 100644 --- a/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c +++ b/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c @@ -325,6 +325,12 @@ static void usb_init_common_7216(struct brcm_usb_init_params *params) void __iomem *ctrl = params->regs[BRCM_REGS_CTRL]; USB_CTRL_UNSET(ctrl, USB_PM, XHC_S2_CLK_SWITCH_EN); + + /* + * The PHY might be in a bad state if it is already powered + * up. Toggle the power just in case. + */ + USB_CTRL_SET(ctrl, USB_PM, USB_PWRDN); USB_CTRL_UNSET(ctrl, USB_PM, USB_PWRDN); /* 1 millisecond - for USB clocks to settle down */ diff --git a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c index 2c8038864357..d3ccf547ba1c 100644 --- a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c +++ b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c @@ -424,8 +424,7 @@ static unsigned long fsl_samsung_hdmi_phy_find_pms(unsigned long fout, u8 *p, u1 * Fvco = (M * f_ref) / P, * where f_ref is 24MHz. */ - tmp = (u64)_m * 24 * MHZ; - do_div(tmp, _p); + tmp = div64_ul((u64)_m * 24 * MHZ, _p); if (tmp < 750 * MHZ || tmp > 3000 * MHZ) continue; diff --git a/drivers/phy/mediatek/Kconfig b/drivers/phy/mediatek/Kconfig index 60e00057e8bc..ba6461350951 100644 --- a/drivers/phy/mediatek/Kconfig +++ b/drivers/phy/mediatek/Kconfig @@ -65,6 +65,7 @@ config PHY_MTK_HDMI depends on ARCH_MEDIATEK || COMPILE_TEST depends on COMMON_CLK depends on OF + depends on REGULATOR select GENERIC_PHY help Support HDMI PHY for Mediatek SoCs. diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index f053b525ccff..413f76e2d174 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -145,8 +145,10 @@ static struct phy_provider *of_phy_provider_lookup(struct device_node *node) return phy_provider; for_each_child_of_node(phy_provider->children, child) - if (child == node) + if (child == node) { + of_node_put(child); return phy_provider; + } } return ERR_PTR(-EPROBE_DEFER); @@ -629,8 +631,10 @@ static struct phy *_of_phy_get(struct device_node *np, int index) return ERR_PTR(-ENODEV); /* This phy type handled by the usb-phy subsystem for now */ - if (of_device_is_compatible(args.np, "usb-nop-xceiv")) - return ERR_PTR(-ENODEV); + if (of_device_is_compatible(args.np, "usb-nop-xceiv")) { + phy = ERR_PTR(-ENODEV); + goto out_put_node; + } mutex_lock(&phy_provider_mutex); phy_provider = of_phy_provider_lookup(args.np); @@ -652,6 +656,7 @@ out_put_module: out_unlock: mutex_unlock(&phy_provider_mutex); +out_put_node: of_node_put(args.np); return phy; @@ -737,7 +742,7 @@ void devm_phy_put(struct device *dev, struct phy *phy) if (!phy) return; - r = devres_destroy(dev, devm_phy_release, devm_phy_match, phy); + r = devres_release(dev, devm_phy_release, devm_phy_match, phy); dev_WARN_ONCE(dev, r, "couldn't find PHY resource\n"); } EXPORT_SYMBOL_GPL(devm_phy_put); @@ -1121,7 +1126,7 @@ void devm_phy_destroy(struct device *dev, struct phy *phy) { int r; - r = devres_destroy(dev, devm_phy_consume, devm_phy_match, phy); + r = devres_release(dev, devm_phy_consume, devm_phy_match, phy); dev_WARN_ONCE(dev, r, "couldn't find PHY resource\n"); } EXPORT_SYMBOL_GPL(devm_phy_destroy); @@ -1259,12 +1264,12 @@ EXPORT_SYMBOL_GPL(of_phy_provider_unregister); * of_phy_provider_unregister to unregister the phy provider. */ void devm_of_phy_provider_unregister(struct device *dev, - struct phy_provider *phy_provider) + struct phy_provider *phy_provider) { int r; - r = devres_destroy(dev, devm_phy_provider_release, devm_phy_match, - phy_provider); + r = devres_release(dev, devm_phy_provider_release, devm_phy_match, + phy_provider); dev_WARN_ONCE(dev, r, "couldn't find PHY provider device resource\n"); } EXPORT_SYMBOL_GPL(devm_of_phy_provider_unregister); diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c index acd6075bf6d9..c9c337840715 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c @@ -1052,7 +1052,7 @@ static const struct qmp_phy_init_tbl sc8280xp_usb3_uniphy_rx_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_FASTLOCK_FO_GAIN, 0x2f), QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_FASTLOCK_COUNT_LOW, 0xff), QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_FASTLOCK_COUNT_HIGH, 0x0f), - QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_SO_GAIN, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_FO_GAIN, 0x0a), QMP_PHY_INIT_CFG(QSERDES_V5_RX_VGA_CAL_CNTRL1, 0x54), QMP_PHY_INIT_CFG(QSERDES_V5_RX_VGA_CAL_CNTRL2, 0x0f), QMP_PHY_INIT_CFG(QSERDES_V5_RX_RX_EQU_ADAPTOR_CNTRL2, 0x0f), diff --git a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c index 0a9989e41237..2eb3329ca23f 100644 --- a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c +++ b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c @@ -309,7 +309,7 @@ static int rockchip_combphy_parse_dt(struct device *dev, struct rockchip_combphy priv->ext_refclk = device_property_present(dev, "rockchip,ext-refclk"); - priv->phy_rst = devm_reset_control_array_get_exclusive(dev); + priv->phy_rst = devm_reset_control_get(dev, "phy"); if (IS_ERR(priv->phy_rst)) return dev_err_probe(dev, PTR_ERR(priv->phy_rst), "failed to get phy reset\n"); diff --git a/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c b/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c index ceab9c71d3b5..0965b9d4f9cf 100644 --- a/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c +++ b/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c @@ -1101,6 +1101,8 @@ static int rk_hdptx_phy_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(hdptx->grf), "Could not get GRF syscon\n"); + platform_set_drvdata(pdev, hdptx); + ret = devm_pm_runtime_enable(dev); if (ret) return dev_err_probe(dev, ret, "Failed to enable runtime PM\n"); @@ -1110,7 +1112,6 @@ static int rk_hdptx_phy_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(hdptx->phy), "Failed to create HDMI PHY\n"); - platform_set_drvdata(pdev, hdptx); phy_set_drvdata(hdptx->phy, hdptx); phy_set_bus_width(hdptx->phy, 8); diff --git a/drivers/phy/st/phy-stm32-combophy.c b/drivers/phy/st/phy-stm32-combophy.c index 765bb34fe358..49e9fa90a681 100644 --- a/drivers/phy/st/phy-stm32-combophy.c +++ b/drivers/phy/st/phy-stm32-combophy.c @@ -122,6 +122,7 @@ static int stm32_impedance_tune(struct stm32_combophy *combophy) u32 max_vswing = imp_lookup[imp_size - 1].vswing[vswing_size - 1]; u32 min_vswing = imp_lookup[0].vswing[0]; u32 val; + u32 regval; if (!of_property_read_u32(combophy->dev->of_node, "st,output-micro-ohms", &val)) { if (val < min_imp || val > max_imp) { @@ -129,16 +130,20 @@ static int stm32_impedance_tune(struct stm32_combophy *combophy) return -EINVAL; } - for (imp_of = 0; imp_of < ARRAY_SIZE(imp_lookup); imp_of++) - if (imp_lookup[imp_of].microohm <= val) + regval = 0; + for (imp_of = 0; imp_of < ARRAY_SIZE(imp_lookup); imp_of++) { + if (imp_lookup[imp_of].microohm <= val) { + regval = FIELD_PREP(STM32MP25_PCIEPRG_IMPCTRL_OHM, imp_of); break; + } + } dev_dbg(combophy->dev, "Set %u micro-ohms output impedance\n", imp_lookup[imp_of].microohm); regmap_update_bits(combophy->regmap, SYSCFG_PCIEPRGCR, STM32MP25_PCIEPRG_IMPCTRL_OHM, - FIELD_PREP(STM32MP25_PCIEPRG_IMPCTRL_OHM, imp_of)); + regval); } else { regmap_read(combophy->regmap, SYSCFG_PCIEPRGCR, &val); imp_of = FIELD_GET(STM32MP25_PCIEPRG_IMPCTRL_OHM, val); @@ -150,16 +155,20 @@ static int stm32_impedance_tune(struct stm32_combophy *combophy) return -EINVAL; } - for (vswing_of = 0; vswing_of < ARRAY_SIZE(imp_lookup[imp_of].vswing); vswing_of++) - if (imp_lookup[imp_of].vswing[vswing_of] >= val) + regval = 0; + for (vswing_of = 0; vswing_of < ARRAY_SIZE(imp_lookup[imp_of].vswing); vswing_of++) { + if (imp_lookup[imp_of].vswing[vswing_of] >= val) { + regval = FIELD_PREP(STM32MP25_PCIEPRG_IMPCTRL_VSWING, vswing_of); break; + } + } dev_dbg(combophy->dev, "Set %u microvolt swing\n", imp_lookup[imp_of].vswing[vswing_of]); regmap_update_bits(combophy->regmap, SYSCFG_PCIEPRGCR, STM32MP25_PCIEPRG_IMPCTRL_VSWING, - FIELD_PREP(STM32MP25_PCIEPRG_IMPCTRL_VSWING, vswing_of)); + regval); } return 0; diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c index d66c3a3e8429..b96e6368a956 100644 --- a/drivers/pinctrl/pinctrl-mcp23s08.c +++ b/drivers/pinctrl/pinctrl-mcp23s08.c @@ -86,6 +86,7 @@ const struct regmap_config mcp23x08_regmap = { .num_reg_defaults = ARRAY_SIZE(mcp23x08_defaults), .cache_type = REGCACHE_FLAT, .max_register = MCP_OLAT, + .disable_locking = true, /* mcp->lock protects the regmap */ }; EXPORT_SYMBOL_GPL(mcp23x08_regmap); @@ -132,6 +133,7 @@ const struct regmap_config mcp23x17_regmap = { .num_reg_defaults = ARRAY_SIZE(mcp23x17_defaults), .cache_type = REGCACHE_FLAT, .val_format_endian = REGMAP_ENDIAN_LITTLE, + .disable_locking = true, /* mcp->lock protects the regmap */ }; EXPORT_SYMBOL_GPL(mcp23x17_regmap); @@ -228,7 +230,9 @@ static int mcp_pinconf_get(struct pinctrl_dev *pctldev, unsigned int pin, switch (param) { case PIN_CONFIG_BIAS_PULL_UP: + mutex_lock(&mcp->lock); ret = mcp_read(mcp, MCP_GPPU, &data); + mutex_unlock(&mcp->lock); if (ret < 0) return ret; status = (data & BIT(pin)) ? 1 : 0; @@ -257,7 +261,9 @@ static int mcp_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, switch (param) { case PIN_CONFIG_BIAS_PULL_UP: + mutex_lock(&mcp->lock); ret = mcp_set_bit(mcp, MCP_GPPU, pin, arg); + mutex_unlock(&mcp->lock); break; default: dev_dbg(mcp->dev, "Invalid config param %04x\n", param); diff --git a/drivers/platform/chrome/cros_ec_lpc.c b/drivers/platform/chrome/cros_ec_lpc.c index 924bf4d3cc77..8470b7f2b135 100644 --- a/drivers/platform/chrome/cros_ec_lpc.c +++ b/drivers/platform/chrome/cros_ec_lpc.c @@ -707,7 +707,7 @@ static const struct dmi_system_id cros_ec_lpc_dmi_table[] __initconst = { /* Framework Laptop (12th Gen Intel Core) */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Framework"), - DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "12th Gen Intel Core"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Laptop (12th Gen Intel Core)"), }, .driver_data = (void *)&framework_laptop_mec_lpc_driver_data, }, @@ -715,7 +715,7 @@ static const struct dmi_system_id cros_ec_lpc_dmi_table[] __initconst = { /* Framework Laptop (13th Gen Intel Core) */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Framework"), - DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "13th Gen Intel Core"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Laptop (13th Gen Intel Core)"), }, .driver_data = (void *)&framework_laptop_mec_lpc_driver_data, }, diff --git a/drivers/platform/loongarch/Kconfig b/drivers/platform/loongarch/Kconfig index 5633e4d73991..447528797d07 100644 --- a/drivers/platform/loongarch/Kconfig +++ b/drivers/platform/loongarch/Kconfig @@ -18,7 +18,7 @@ if LOONGARCH_PLATFORM_DEVICES config LOONGSON_LAPTOP tristate "Generic Loongson-3 Laptop Driver" - depends on ACPI + depends on ACPI_EC depends on BACKLIGHT_CLASS_DEVICE depends on INPUT depends on MACH_LOONGSON64 diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c index 26b878ee5191..a254debb9256 100644 --- a/drivers/platform/x86/amd/pmc/pmc.c +++ b/drivers/platform/x86/amd/pmc/pmc.c @@ -947,6 +947,10 @@ static int amd_pmc_suspend_handler(struct device *dev) { struct amd_pmc_dev *pdev = dev_get_drvdata(dev); + /* + * Must be called only from the same set of dev_pm_ops handlers + * as i8042_pm_suspend() is called: currently just from .suspend. + */ if (pdev->disable_8042_wakeup && !disable_workarounds) { int rc = amd_pmc_wa_irq1(pdev); @@ -959,7 +963,9 @@ static int amd_pmc_suspend_handler(struct device *dev) return 0; } -static DEFINE_SIMPLE_DEV_PM_OPS(amd_pmc_pm, amd_pmc_suspend_handler, NULL); +static const struct dev_pm_ops amd_pmc_pm = { + .suspend = amd_pmc_suspend_handler, +}; static const struct pci_device_id pmc_pci_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_PS) }, diff --git a/drivers/platform/x86/dell/alienware-wmi.c b/drivers/platform/x86/dell/alienware-wmi.c index 77465ed9b449..341d01d3e3e4 100644 --- a/drivers/platform/x86/dell/alienware-wmi.c +++ b/drivers/platform/x86/dell/alienware-wmi.c @@ -190,7 +190,7 @@ static struct quirk_entry quirk_asm201 = { }; static struct quirk_entry quirk_g_series = { - .num_zones = 2, + .num_zones = 0, .hdmi_mux = 0, .amplifier = 0, .deepslp = 0, @@ -199,7 +199,7 @@ static struct quirk_entry quirk_g_series = { }; static struct quirk_entry quirk_x_series = { - .num_zones = 2, + .num_zones = 0, .hdmi_mux = 0, .amplifier = 0, .deepslp = 0, @@ -243,6 +243,15 @@ static const struct dmi_system_id alienware_quirks[] __initconst = { }, { .callback = dmi_matched, + .ident = "Alienware m16 R1 AMD", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m16 R1 AMD"), + }, + .driver_data = &quirk_x_series, + }, + { + .callback = dmi_matched, .ident = "Alienware m17 R5", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), @@ -687,6 +696,9 @@ static void alienware_zone_exit(struct platform_device *dev) { u8 zone; + if (!quirks->num_zones) + return; + sysfs_remove_group(&dev->dev.kobj, &zone_attribute_group); led_classdev_unregister(&global_led); if (zone_dev_attrs) { @@ -1229,9 +1241,11 @@ static int __init alienware_wmi_init(void) goto fail_prep_thermal_profile; } - ret = alienware_zone_init(platform_device); - if (ret) - goto fail_prep_zones; + if (quirks->num_zones > 0) { + ret = alienware_zone_init(platform_device); + if (ret) + goto fail_prep_zones; + } return 0; diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c index 81ccc96ffe40..20c55bab3b8c 100644 --- a/drivers/platform/x86/hp/hp-wmi.c +++ b/drivers/platform/x86/hp/hp-wmi.c @@ -64,7 +64,7 @@ static const char * const omen_thermal_profile_boards[] = { "874A", "8603", "8604", "8748", "886B", "886C", "878A", "878B", "878C", "88C8", "88CB", "8786", "8787", "8788", "88D1", "88D2", "88F4", "88FD", "88F5", "88F6", "88F7", "88FE", "88FF", "8900", "8901", "8902", "8912", - "8917", "8918", "8949", "894A", "89EB", "8BAD", "8A42" + "8917", "8918", "8949", "894A", "89EB", "8BAD", "8A42", "8A15" }; /* DMI Board names of Omen laptops that are specifically set to be thermal @@ -80,7 +80,7 @@ static const char * const omen_thermal_profile_force_v0_boards[] = { * "balanced" when reaching zero. */ static const char * const omen_timed_thermal_profile_boards[] = { - "8BAD", "8A42" + "8BAD", "8A42", "8A15" }; /* DMI Board names of Victus laptops */ diff --git a/drivers/platform/x86/intel/ifs/core.c b/drivers/platform/x86/intel/ifs/core.c index bc252b883210..1ae50702bdb7 100644 --- a/drivers/platform/x86/intel/ifs/core.c +++ b/drivers/platform/x86/intel/ifs/core.c @@ -20,6 +20,7 @@ static const struct x86_cpu_id ifs_cpu_ids[] __initconst = { X86_MATCH(INTEL_GRANITERAPIDS_X, ARRAY_GEN0), X86_MATCH(INTEL_GRANITERAPIDS_D, ARRAY_GEN0), X86_MATCH(INTEL_ATOM_CRESTMONT_X, ARRAY_GEN1), + X86_MATCH(INTEL_ATOM_DARKMONT_X, ARRAY_GEN1), {} }; MODULE_DEVICE_TABLE(x86cpu, ifs_cpu_ids); diff --git a/drivers/platform/x86/intel/pmc/core_ssram.c b/drivers/platform/x86/intel/pmc/core_ssram.c index 50ebfd586d3f..739569803017 100644 --- a/drivers/platform/x86/intel/pmc/core_ssram.c +++ b/drivers/platform/x86/intel/pmc/core_ssram.c @@ -269,8 +269,12 @@ pmc_core_ssram_get_pmc(struct pmc_dev *pmcdev, int pmc_idx, u32 offset) /* * The secondary PMC BARS (which are behind hidden PCI devices) * are read from fixed offsets in MMIO of the primary PMC BAR. + * If a device is not present, the value will be 0. */ ssram_base = get_base(tmp_ssram, offset); + if (!ssram_base) + return 0; + ssram = ioremap(ssram_base, SSRAM_HDR_SIZE); if (!ssram) return -ENOMEM; diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c index 1e46e30dae96..dbcd3087aaa4 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c @@ -804,6 +804,7 @@ EXPORT_SYMBOL_GPL(isst_if_cdev_unregister); static const struct x86_cpu_id isst_cpu_ids[] = { X86_MATCH_VFM(INTEL_ATOM_CRESTMONT, SST_HPM_SUPPORTED), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, SST_HPM_SUPPORTED), + X86_MATCH_VFM(INTEL_ATOM_DARKMONT_X, SST_HPM_SUPPORTED), X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, 0), X86_MATCH_VFM(INTEL_GRANITERAPIDS_D, SST_HPM_SUPPORTED), X86_MATCH_VFM(INTEL_GRANITERAPIDS_X, SST_HPM_SUPPORTED), diff --git a/drivers/platform/x86/intel/tpmi_power_domains.c b/drivers/platform/x86/intel/tpmi_power_domains.c index 603e7ded06a9..2f01cd22a6ee 100644 --- a/drivers/platform/x86/intel/tpmi_power_domains.c +++ b/drivers/platform/x86/intel/tpmi_power_domains.c @@ -81,6 +81,7 @@ static const struct x86_cpu_id tpmi_cpu_ids[] = { X86_MATCH_VFM(INTEL_GRANITERAPIDS_X, NULL), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, NULL), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT, NULL), + X86_MATCH_VFM(INTEL_ATOM_DARKMONT_X, NULL), X86_MATCH_VFM(INTEL_GRANITERAPIDS_D, NULL), X86_MATCH_VFM(INTEL_PANTHERCOVE_X, NULL), {} diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c index 4a85aad2475a..8272f1dd0fbc 100644 --- a/drivers/platform/x86/intel/vsec.c +++ b/drivers/platform/x86/intel/vsec.c @@ -423,6 +423,7 @@ static const struct intel_vsec_platform_info lnl_info = { #define PCI_DEVICE_ID_INTEL_VSEC_RPL 0xa77d #define PCI_DEVICE_ID_INTEL_VSEC_TGL 0x9a0d #define PCI_DEVICE_ID_INTEL_VSEC_LNL_M 0x647d +#define PCI_DEVICE_ID_INTEL_VSEC_PTL 0xb07d static const struct pci_device_id intel_vsec_pci_ids[] = { { PCI_DEVICE_DATA(INTEL, VSEC_ADL, &tgl_info) }, { PCI_DEVICE_DATA(INTEL, VSEC_DG1, &dg1_info) }, @@ -432,6 +433,7 @@ static const struct pci_device_id intel_vsec_pci_ids[] = { { PCI_DEVICE_DATA(INTEL, VSEC_RPL, &tgl_info) }, { PCI_DEVICE_DATA(INTEL, VSEC_TGL, &tgl_info) }, { PCI_DEVICE_DATA(INTEL, VSEC_LNL_M, &lnl_info) }, + { PCI_DEVICE_DATA(INTEL, VSEC_PTL, &mtl_info) }, { } }; MODULE_DEVICE_TABLE(pci, intel_vsec_pci_ids); diff --git a/drivers/platform/x86/mlx-platform.c b/drivers/platform/x86/mlx-platform.c index 671021cd1f59..9c7f30a47f1f 100644 --- a/drivers/platform/x86/mlx-platform.c +++ b/drivers/platform/x86/mlx-platform.c @@ -6237,6 +6237,7 @@ fail_pci_set_dma_mask: fail_pci_request_regions: pci_disable_device(pci_dev); fail_pci_enable_device: + pci_dev_put(pci_dev); return err; } @@ -6247,6 +6248,7 @@ mlxplat_pci_fpga_device_exit(struct pci_dev *pci_bridge, iounmap(pci_bridge_addr); pci_release_regions(pci_bridge); pci_disable_device(pci_bridge); + pci_dev_put(pci_bridge); } static int diff --git a/drivers/platform/x86/p2sb.c b/drivers/platform/x86/p2sb.c index d51eb0db0626..cbbb0f809704 100644 --- a/drivers/platform/x86/p2sb.c +++ b/drivers/platform/x86/p2sb.c @@ -43,6 +43,7 @@ struct p2sb_res_cache { }; static struct p2sb_res_cache p2sb_resources[NR_P2SB_RES_CACHE]; +static bool p2sb_hidden_by_bios; static void p2sb_get_devfn(unsigned int *devfn) { @@ -97,6 +98,12 @@ static void p2sb_scan_and_cache_devfn(struct pci_bus *bus, unsigned int devfn) static int p2sb_scan_and_cache(struct pci_bus *bus, unsigned int devfn) { + /* + * The BIOS prevents the P2SB device from being enumerated by the PCI + * subsystem, so we need to unhide and hide it back to lookup the BAR. + */ + pci_bus_write_config_dword(bus, devfn, P2SBC, 0); + /* Scan the P2SB device and cache its BAR0 */ p2sb_scan_and_cache_devfn(bus, devfn); @@ -104,6 +111,8 @@ static int p2sb_scan_and_cache(struct pci_bus *bus, unsigned int devfn) if (devfn == P2SB_DEVFN_GOLDMONT) p2sb_scan_and_cache_devfn(bus, SPI_DEVFN_GOLDMONT); + pci_bus_write_config_dword(bus, devfn, P2SBC, P2SBC_HIDE); + if (!p2sb_valid_resource(&p2sb_resources[PCI_FUNC(devfn)].res)) return -ENOENT; @@ -129,7 +138,7 @@ static int p2sb_cache_resources(void) u32 value = P2SBC_HIDE; struct pci_bus *bus; u16 class; - int ret; + int ret = 0; /* Get devfn for P2SB device itself */ p2sb_get_devfn(&devfn_p2sb); @@ -152,22 +161,53 @@ static int p2sb_cache_resources(void) */ pci_lock_rescan_remove(); + pci_bus_read_config_dword(bus, devfn_p2sb, P2SBC, &value); + p2sb_hidden_by_bios = value & P2SBC_HIDE; + /* - * The BIOS prevents the P2SB device from being enumerated by the PCI - * subsystem, so we need to unhide and hide it back to lookup the BAR. - * Unhide the P2SB device here, if needed. + * If the BIOS does not hide the P2SB device then its resources + * are accesilble. Cache them only if the P2SB device is hidden. */ - pci_bus_read_config_dword(bus, devfn_p2sb, P2SBC, &value); - if (value & P2SBC_HIDE) - pci_bus_write_config_dword(bus, devfn_p2sb, P2SBC, 0); + if (p2sb_hidden_by_bios) + ret = p2sb_scan_and_cache(bus, devfn_p2sb); - ret = p2sb_scan_and_cache(bus, devfn_p2sb); + pci_unlock_rescan_remove(); - /* Hide the P2SB device, if it was hidden */ - if (value & P2SBC_HIDE) - pci_bus_write_config_dword(bus, devfn_p2sb, P2SBC, P2SBC_HIDE); + return ret; +} - pci_unlock_rescan_remove(); +static int p2sb_read_from_cache(struct pci_bus *bus, unsigned int devfn, + struct resource *mem) +{ + struct p2sb_res_cache *cache = &p2sb_resources[PCI_FUNC(devfn)]; + + if (cache->bus_dev_id != bus->dev.id) + return -ENODEV; + + if (!p2sb_valid_resource(&cache->res)) + return -ENOENT; + + memcpy(mem, &cache->res, sizeof(*mem)); + + return 0; +} + +static int p2sb_read_from_dev(struct pci_bus *bus, unsigned int devfn, + struct resource *mem) +{ + struct pci_dev *pdev; + int ret = 0; + + pdev = pci_get_slot(bus, devfn); + if (!pdev) + return -ENODEV; + + if (p2sb_valid_resource(pci_resource_n(pdev, 0))) + p2sb_read_bar0(pdev, mem); + else + ret = -ENOENT; + + pci_dev_put(pdev); return ret; } @@ -188,8 +228,6 @@ static int p2sb_cache_resources(void) */ int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem) { - struct p2sb_res_cache *cache; - bus = p2sb_get_bus(bus); if (!bus) return -ENODEV; @@ -197,15 +235,10 @@ int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem) if (!devfn) p2sb_get_devfn(&devfn); - cache = &p2sb_resources[PCI_FUNC(devfn)]; - if (cache->bus_dev_id != bus->dev.id) - return -ENODEV; + if (p2sb_hidden_by_bios) + return p2sb_read_from_cache(bus, devfn, mem); - if (!p2sb_valid_resource(&cache->res)) - return -ENOENT; - - memcpy(mem, &cache->res, sizeof(*mem)); - return 0; + return p2sb_read_from_dev(bus, devfn, mem); } EXPORT_SYMBOL_GPL(p2sb_bar); diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 6371a9f765c1..2cfb2ac3f465 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -184,7 +184,8 @@ enum tpacpi_hkey_event_t { */ TP_HKEY_EV_AMT_TOGGLE = 0x131a, /* Toggle AMT on/off */ TP_HKEY_EV_DOUBLETAP_TOGGLE = 0x131c, /* Toggle trackpoint doubletap on/off */ - TP_HKEY_EV_PROFILE_TOGGLE = 0x131f, /* Toggle platform profile */ + TP_HKEY_EV_PROFILE_TOGGLE = 0x131f, /* Toggle platform profile in 2024 systems */ + TP_HKEY_EV_PROFILE_TOGGLE2 = 0x1401, /* Toggle platform profile in 2025 + systems */ /* Reasons for waking up from S3/S4 */ TP_HKEY_EV_WKUP_S3_UNDOCK = 0x2304, /* undock requested, S3 */ @@ -11200,6 +11201,7 @@ static bool tpacpi_driver_event(const unsigned int hkey_event) tp_features.trackpoint_doubletap = !tp_features.trackpoint_doubletap; return true; case TP_HKEY_EV_PROFILE_TOGGLE: + case TP_HKEY_EV_PROFILE_TOGGLE2: platform_profile_cycle(); return true; } diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 0a39f68c641d..bdc19cd8d3ed 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -855,6 +855,23 @@ static const struct ts_dmi_data rwc_nanote_next_data = { .properties = rwc_nanote_next_props, }; +static const struct property_entry sary_tab_3_props[] = { + PROPERTY_ENTRY_U32("touchscreen-size-x", 1730), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1151), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-x"), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), + PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-sary-tab-3.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + PROPERTY_ENTRY_BOOL("silead,home-button"), + { } +}; + +static const struct ts_dmi_data sary_tab_3_data = { + .acpi_name = "MSSL1680:00", + .properties = sary_tab_3_props, +}; + static const struct property_entry schneider_sct101ctm_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1715), PROPERTY_ENTRY_U32("touchscreen-size-y", 1140), @@ -1616,6 +1633,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* SARY Tab 3 */ + .driver_data = (void *)&sary_tab_3_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "SARY"), + DMI_MATCH(DMI_PRODUCT_NAME, "C210C"), + DMI_MATCH(DMI_PRODUCT_SKU, "TAB3"), + }, + }, + { /* Schneider SCT101CTM */ .driver_data = (void *)&schneider_sct101ctm_data, .matches = { diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c index bb11f467dc78..20a9efebbcb7 100644 --- a/drivers/pmdomain/core.c +++ b/drivers/pmdomain/core.c @@ -2142,6 +2142,11 @@ static int genpd_set_default_power_state(struct generic_pm_domain *genpd) return 0; } +static void genpd_provider_release(struct device *dev) +{ + /* nothing to be done here */ +} + static int genpd_alloc_data(struct generic_pm_domain *genpd) { struct genpd_governor_data *gd = NULL; @@ -2173,6 +2178,7 @@ static int genpd_alloc_data(struct generic_pm_domain *genpd) genpd->gd = gd; device_initialize(&genpd->dev); + genpd->dev.release = genpd_provider_release; if (!genpd_is_dev_name_fw(genpd)) { dev_set_name(&genpd->dev, "%s", genpd->name); diff --git a/drivers/pmdomain/imx/gpcv2.c b/drivers/pmdomain/imx/gpcv2.c index e67ecf99ef84..9bdb80fd7210 100644 --- a/drivers/pmdomain/imx/gpcv2.c +++ b/drivers/pmdomain/imx/gpcv2.c @@ -1458,12 +1458,12 @@ static int imx_gpcv2_probe(struct platform_device *pdev) .max_register = SZ_4K, }; struct device *dev = &pdev->dev; - struct device_node *pgc_np; + struct device_node *pgc_np __free(device_node) = + of_get_child_by_name(dev->of_node, "pgc"); struct regmap *regmap; void __iomem *base; int ret; - pgc_np = of_get_child_by_name(dev->of_node, "pgc"); if (!pgc_np) { dev_err(dev, "No power domains specified in DT\n"); return -EINVAL; diff --git a/drivers/power/supply/bq24190_charger.c b/drivers/power/supply/bq24190_charger.c index 2b393eb5c282..c47f32f152e6 100644 --- a/drivers/power/supply/bq24190_charger.c +++ b/drivers/power/supply/bq24190_charger.c @@ -567,6 +567,7 @@ static int bq24190_set_otg_vbus(struct bq24190_dev_info *bdi, bool enable) static int bq24296_set_otg_vbus(struct bq24190_dev_info *bdi, bool enable) { + union power_supply_propval val = { .intval = bdi->charge_type }; int ret; ret = pm_runtime_resume_and_get(bdi->dev); @@ -587,13 +588,18 @@ static int bq24296_set_otg_vbus(struct bq24190_dev_info *bdi, bool enable) ret = bq24190_write_mask(bdi, BQ24190_REG_POC, BQ24296_REG_POC_OTG_CONFIG_MASK, - BQ24296_REG_POC_CHG_CONFIG_SHIFT, + BQ24296_REG_POC_OTG_CONFIG_SHIFT, BQ24296_REG_POC_OTG_CONFIG_OTG); - } else + } else { ret = bq24190_write_mask(bdi, BQ24190_REG_POC, BQ24296_REG_POC_OTG_CONFIG_MASK, - BQ24296_REG_POC_CHG_CONFIG_SHIFT, + BQ24296_REG_POC_OTG_CONFIG_SHIFT, BQ24296_REG_POC_OTG_CONFIG_DISABLE); + if (ret < 0) + goto out; + + ret = bq24190_charger_set_charge_type(bdi, &val); + } out: pm_runtime_mark_last_busy(bdi->dev); diff --git a/drivers/power/supply/cros_charge-control.c b/drivers/power/supply/cros_charge-control.c index 17c53591ce19..9b0a7500296b 100644 --- a/drivers/power/supply/cros_charge-control.c +++ b/drivers/power/supply/cros_charge-control.c @@ -7,8 +7,10 @@ #include <acpi/battery.h> #include <linux/container_of.h> #include <linux/dmi.h> +#include <linux/lockdep.h> #include <linux/mod_devicetable.h> #include <linux/module.h> +#include <linux/mutex.h> #include <linux/platform_data/cros_ec_commands.h> #include <linux/platform_data/cros_ec_proto.h> #include <linux/platform_device.h> @@ -49,6 +51,7 @@ struct cros_chctl_priv { struct attribute *attributes[_CROS_CHCTL_ATTR_COUNT]; struct attribute_group group; + struct mutex lock; /* protects fields below and cros_ec */ enum power_supply_charge_behaviour current_behaviour; u8 current_start_threshold, current_end_threshold; }; @@ -85,6 +88,8 @@ static int cros_chctl_configure_ec(struct cros_chctl_priv *priv) { struct ec_params_charge_control req = {}; + lockdep_assert_held(&priv->lock); + req.cmd = EC_CHARGE_CONTROL_CMD_SET; switch (priv->current_behaviour) { @@ -134,11 +139,15 @@ static ssize_t cros_chctl_store_threshold(struct device *dev, struct cros_chctl_ return -EINVAL; if (is_end_threshold) { - if (val <= priv->current_start_threshold) + /* Start threshold is not exposed, use fixed value */ + if (priv->cmd_version == 2) + priv->current_start_threshold = val == 100 ? 0 : val; + + if (val < priv->current_start_threshold) return -EINVAL; priv->current_end_threshold = val; } else { - if (val >= priv->current_end_threshold) + if (val > priv->current_end_threshold) return -EINVAL; priv->current_start_threshold = val; } @@ -159,6 +168,7 @@ static ssize_t charge_control_start_threshold_show(struct device *dev, struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(&attr->attr, CROS_CHCTL_ATTR_START_THRESHOLD); + guard(mutex)(&priv->lock); return sysfs_emit(buf, "%u\n", (unsigned int)priv->current_start_threshold); } @@ -169,6 +179,7 @@ static ssize_t charge_control_start_threshold_store(struct device *dev, struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(&attr->attr, CROS_CHCTL_ATTR_START_THRESHOLD); + guard(mutex)(&priv->lock); return cros_chctl_store_threshold(dev, priv, 0, buf, count); } @@ -178,6 +189,7 @@ static ssize_t charge_control_end_threshold_show(struct device *dev, struct devi struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(&attr->attr, CROS_CHCTL_ATTR_END_THRESHOLD); + guard(mutex)(&priv->lock); return sysfs_emit(buf, "%u\n", (unsigned int)priv->current_end_threshold); } @@ -187,6 +199,7 @@ static ssize_t charge_control_end_threshold_store(struct device *dev, struct dev struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(&attr->attr, CROS_CHCTL_ATTR_END_THRESHOLD); + guard(mutex)(&priv->lock); return cros_chctl_store_threshold(dev, priv, 1, buf, count); } @@ -195,6 +208,7 @@ static ssize_t charge_behaviour_show(struct device *dev, struct device_attribute struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(&attr->attr, CROS_CHCTL_ATTR_CHARGE_BEHAVIOUR); + guard(mutex)(&priv->lock); return power_supply_charge_behaviour_show(dev, EC_CHARGE_CONTROL_BEHAVIOURS, priv->current_behaviour, buf); } @@ -210,6 +224,7 @@ static ssize_t charge_behaviour_store(struct device *dev, struct device_attribut if (ret < 0) return ret; + guard(mutex)(&priv->lock); priv->current_behaviour = ret; ret = cros_chctl_configure_ec(priv); @@ -223,12 +238,10 @@ static umode_t cros_chtl_attr_is_visible(struct kobject *kobj, struct attribute { struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(attr, n); - if (priv->cmd_version < 2) { - if (n == CROS_CHCTL_ATTR_START_THRESHOLD) - return 0; - if (n == CROS_CHCTL_ATTR_END_THRESHOLD) - return 0; - } + if (n == CROS_CHCTL_ATTR_START_THRESHOLD && priv->cmd_version < 3) + return 0; + else if (n == CROS_CHCTL_ATTR_END_THRESHOLD && priv->cmd_version < 2) + return 0; return attr->mode; } @@ -290,6 +303,10 @@ static int cros_chctl_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; + ret = devm_mutex_init(dev, &priv->lock); + if (ret) + return ret; + ret = cros_ec_get_cmd_versions(cros_ec, EC_CMD_CHARGE_CONTROL); if (ret < 0) return ret; @@ -327,7 +344,8 @@ static int cros_chctl_probe(struct platform_device *pdev) priv->current_end_threshold = 100; /* Bring EC into well-known state */ - ret = cros_chctl_configure_ec(priv); + scoped_guard(mutex, &priv->lock) + ret = cros_chctl_configure_ec(priv); if (ret < 0) return ret; diff --git a/drivers/power/supply/gpio-charger.c b/drivers/power/supply/gpio-charger.c index 68212b39785b..6139f736ecbe 100644 --- a/drivers/power/supply/gpio-charger.c +++ b/drivers/power/supply/gpio-charger.c @@ -67,6 +67,14 @@ static int set_charge_current_limit(struct gpio_charger *gpio_charger, int val) if (gpio_charger->current_limit_map[i].limit_ua <= val) break; } + + /* + * If a valid charge current limit isn't found, default to smallest + * current limitation for safety reasons. + */ + if (i >= gpio_charger->current_limit_map_size) + i = gpio_charger->current_limit_map_size - 1; + mapping = gpio_charger->current_limit_map[i]; for (i = 0; i < ndescs; i++) { diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c index b889e64522c3..17e591f61efb 100644 --- a/drivers/pwm/pwm-stm32.c +++ b/drivers/pwm/pwm-stm32.c @@ -84,7 +84,7 @@ static int stm32_pwm_round_waveform_tohw(struct pwm_chip *chip, wfhw->ccer = TIM_CCER_CCxE(ch + 1); if (priv->have_complementary_output) - wfhw->ccer = TIM_CCER_CCxNE(ch + 1); + wfhw->ccer |= TIM_CCER_CCxNE(ch + 1); rate = clk_get_rate(priv->clk); diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c index 3d85762beda6..e5b4b93c07e3 100644 --- a/drivers/regulator/of_regulator.c +++ b/drivers/regulator/of_regulator.c @@ -175,7 +175,7 @@ static int of_get_regulation_constraints(struct device *dev, if (!ret) constraints->enable_time = pval; - ret = of_property_read_u32(np, "regulator-uv-survival-time-ms", &pval); + ret = of_property_read_u32(np, "regulator-uv-less-critical-window-ms", &pval); if (!ret) constraints->uv_less_critical_window_ms = pval; else diff --git a/drivers/spi/spi-rockchip-sfc.c b/drivers/spi/spi-rockchip-sfc.c index 69d0f2175568..70bbb459caa4 100644 --- a/drivers/spi/spi-rockchip-sfc.c +++ b/drivers/spi/spi-rockchip-sfc.c @@ -182,6 +182,7 @@ struct rockchip_sfc { bool use_dma; u32 max_iosize; u16 version; + struct spi_controller *host; }; static int rockchip_sfc_reset(struct rockchip_sfc *sfc) @@ -574,6 +575,7 @@ static int rockchip_sfc_probe(struct platform_device *pdev) sfc = spi_controller_get_devdata(host); sfc->dev = dev; + sfc->host = host; sfc->regbase = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(sfc->regbase)) @@ -651,8 +653,8 @@ err_hclk: static void rockchip_sfc_remove(struct platform_device *pdev) { - struct spi_controller *host = platform_get_drvdata(pdev); struct rockchip_sfc *sfc = platform_get_drvdata(pdev); + struct spi_controller *host = sfc->host; spi_unregister_controller(host); diff --git a/drivers/staging/fbtft/Kconfig b/drivers/staging/fbtft/Kconfig index 77ab44362f16..dcf6a70455cc 100644 --- a/drivers/staging/fbtft/Kconfig +++ b/drivers/staging/fbtft/Kconfig @@ -3,6 +3,7 @@ menuconfig FB_TFT tristate "Support for small TFT LCD display modules" depends on FB && SPI depends on FB_DEVICE + depends on BACKLIGHT_CLASS_DEVICE depends on GPIOLIB || COMPILE_TEST select FB_BACKLIGHT select FB_SYSMEM_HELPERS_DEFERRED diff --git a/drivers/staging/gpib/Kconfig b/drivers/staging/gpib/Kconfig index 259f3ff33646..81510db3072e 100644 --- a/drivers/staging/gpib/Kconfig +++ b/drivers/staging/gpib/Kconfig @@ -65,6 +65,8 @@ config GPIB_NI_PCI_ISA depends on ISA_BUS || PCI || PCMCIA depends on HAS_IOPORT depends on !X86_PAE + depends on PCMCIA || !PCMCIA + depends on HAS_IOPORT_MAP select GPIB_COMMON select GPIB_NEC7210 help @@ -89,6 +91,7 @@ config GPIB_CB7210 depends on HAS_IOPORT depends on ISA_BUS || PCI || PCMCIA depends on !X86_PAE + depends on PCMCIA || !PCMCIA select GPIB_COMMON select GPIB_NEC7210 help @@ -177,6 +180,7 @@ config GPIB_HP82341 config GPIB_INES tristate "INES" depends on PCI || ISA_BUS || PCMCIA + depends on PCMCIA || !PCMCIA depends on HAS_IOPORT depends on !X86_PAE select GPIB_COMMON @@ -199,8 +203,8 @@ config GPIB_INES called cb7210. config GPIB_PCMCIA - bool "PCMCIA/Cardbus support for NI MC and Ines boards" - depends on PCCARD && (GPIB_NI_PCI_ISA || GPIB_CB7210 || GPIB_INES) + def_bool y + depends on PCMCIA && (GPIB_NI_PCI_ISA || GPIB_CB7210 || GPIB_INES) help Enable PCMCIA/CArdbus support for National Instruments, measurement computing boards and Ines boards. diff --git a/drivers/staging/gpib/agilent_82350b/Makefile b/drivers/staging/gpib/agilent_82350b/Makefile index d9236c92e04b..f24e1e713a63 100644 --- a/drivers/staging/gpib/agilent_82350b/Makefile +++ b/drivers/staging/gpib/agilent_82350b/Makefile @@ -1,2 +1,2 @@ -obj-m += agilent_82350b.o +obj-$(CONFIG_GPIB_AGILENT_82350B) += agilent_82350b.o diff --git a/drivers/staging/gpib/agilent_82350b/agilent_82350b.c b/drivers/staging/gpib/agilent_82350b/agilent_82350b.c index 53006d0cc79c..8e2334fe5c9b 100644 --- a/drivers/staging/gpib/agilent_82350b/agilent_82350b.c +++ b/drivers/staging/gpib/agilent_82350b/agilent_82350b.c @@ -700,7 +700,7 @@ static int agilent_82350b_generic_attach(gpib_board_t *board, const gpib_board_c GPIB_82350A_REGION)); dev_dbg(board->gpib_dev, "%s: gpib base address remapped to 0x%p\n", driver_name, a_priv->gpib_base); - tms_priv->iobase = a_priv->gpib_base + TMS9914_BASE_REG; + tms_priv->mmiobase = a_priv->gpib_base + TMS9914_BASE_REG; a_priv->sram_base = ioremap(pci_resource_start(a_priv->pci_device, SRAM_82350A_REGION), pci_resource_len(a_priv->pci_device, @@ -724,7 +724,7 @@ static int agilent_82350b_generic_attach(gpib_board_t *board, const gpib_board_c pci_resource_len(a_priv->pci_device, GPIB_REGION)); dev_dbg(board->gpib_dev, "%s: gpib base address remapped to 0x%p\n", driver_name, a_priv->gpib_base); - tms_priv->iobase = a_priv->gpib_base + TMS9914_BASE_REG; + tms_priv->mmiobase = a_priv->gpib_base + TMS9914_BASE_REG; a_priv->sram_base = ioremap(pci_resource_start(a_priv->pci_device, SRAM_REGION), pci_resource_len(a_priv->pci_device, SRAM_REGION)); dev_dbg(board->gpib_dev, "%s: sram base address remapped to 0x%p\n", diff --git a/drivers/staging/gpib/agilent_82357a/Makefile b/drivers/staging/gpib/agilent_82357a/Makefile index 4a1d940fce2b..81a55c257a6e 100644 --- a/drivers/staging/gpib/agilent_82357a/Makefile +++ b/drivers/staging/gpib/agilent_82357a/Makefile @@ -1,4 +1,4 @@ -obj-m += agilent_82357a.o +obj-$(CONFIG_GPIB_AGILENT_82357A) += agilent_82357a.o diff --git a/drivers/staging/gpib/cb7210/Makefile b/drivers/staging/gpib/cb7210/Makefile index 22e0214fc17d..cda0725d6487 100644 --- a/drivers/staging/gpib/cb7210/Makefile +++ b/drivers/staging/gpib/cb7210/Makefile @@ -1,4 +1,4 @@ ccflags-$(CONFIG_GPIB_PCMCIA) := -DGPIB_PCMCIA -obj-m += cb7210.o +obj-$(CONFIG_GPIB_CB7210) += cb7210.o diff --git a/drivers/staging/gpib/cb7210/cb7210.c b/drivers/staging/gpib/cb7210/cb7210.c index 63df7f3eb3f3..59e41c97f518 100644 --- a/drivers/staging/gpib/cb7210/cb7210.c +++ b/drivers/staging/gpib/cb7210/cb7210.c @@ -971,12 +971,12 @@ int cb_pci_attach(gpib_board_t *board, const gpib_board_config_t *config) switch (cb_priv->pci_chip) { case PCI_CHIP_AMCC_S5933: cb_priv->amcc_iobase = pci_resource_start(cb_priv->pci_device, 0); - nec_priv->iobase = (void *)(pci_resource_start(cb_priv->pci_device, 1)); + nec_priv->iobase = pci_resource_start(cb_priv->pci_device, 1); cb_priv->fifo_iobase = pci_resource_start(cb_priv->pci_device, 2); break; case PCI_CHIP_QUANCOM: - nec_priv->iobase = (void *)(pci_resource_start(cb_priv->pci_device, 0)); - cb_priv->fifo_iobase = (unsigned long)nec_priv->iobase; + nec_priv->iobase = pci_resource_start(cb_priv->pci_device, 0); + cb_priv->fifo_iobase = nec_priv->iobase; break; default: pr_err("cb7210: bug! unhandled pci_chip=%i\n", cb_priv->pci_chip); @@ -1040,8 +1040,8 @@ int cb_isa_attach(gpib_board_t *board, const gpib_board_config_t *config) return retval; cb_priv = board->private_data; nec_priv = &cb_priv->nec7210_priv; - if (request_region((unsigned long)config->ibbase, cb7210_iosize, "cb7210") == 0) { - pr_err("gpib: ioports starting at 0x%p are already in use\n", config->ibbase); + if (request_region(config->ibbase, cb7210_iosize, "cb7210") == 0) { + pr_err("gpib: ioports starting at 0x%u are already in use\n", config->ibbase); return -EIO; } nec_priv->iobase = config->ibbase; @@ -1471,7 +1471,7 @@ int cb_pcmcia_attach(gpib_board_t *board, const gpib_board_config_t *config) (unsigned long)curr_dev->resource[0]->start); return -EIO; } - nec_priv->iobase = (void *)(unsigned long)curr_dev->resource[0]->start; + nec_priv->iobase = curr_dev->resource[0]->start; cb_priv->fifo_iobase = curr_dev->resource[0]->start; if (request_irq(curr_dev->irq, cb7210_interrupt, IRQF_SHARED, diff --git a/drivers/staging/gpib/cb7210/cb7210.h b/drivers/staging/gpib/cb7210/cb7210.h index 4ad976de2b68..c17cb22585f7 100644 --- a/drivers/staging/gpib/cb7210/cb7210.h +++ b/drivers/staging/gpib/cb7210/cb7210.h @@ -113,9 +113,9 @@ enum hs_regs { HS_STATUS = 0x8, /* HS_STATUS register */ }; -static inline unsigned long nec7210_iobase(const struct cb7210_priv *cb_priv) +static inline u32 nec7210_iobase(const struct cb7210_priv *cb_priv) { - return (unsigned long)(cb_priv->nec7210_priv.iobase); + return cb_priv->nec7210_priv.iobase; } static inline int cb7210_page_in_bits(unsigned int page) diff --git a/drivers/staging/gpib/cec/Makefile b/drivers/staging/gpib/cec/Makefile index f4638628ff29..b7141e23d4e0 100644 --- a/drivers/staging/gpib/cec/Makefile +++ b/drivers/staging/gpib/cec/Makefile @@ -1,3 +1,3 @@ -obj-m += cec_gpib.o +obj-$(CONFIG_GPIB_CEC_PCI) += cec_gpib.o diff --git a/drivers/staging/gpib/cec/cec_gpib.c b/drivers/staging/gpib/cec/cec_gpib.c index 3dc933deb401..9c00a874468c 100644 --- a/drivers/staging/gpib/cec/cec_gpib.c +++ b/drivers/staging/gpib/cec/cec_gpib.c @@ -297,8 +297,8 @@ int cec_pci_attach(gpib_board_t *board, const gpib_board_config_t *config) cec_priv->plx_iobase = pci_resource_start(cec_priv->pci_device, 1); pr_info(" plx9050 base address 0x%lx\n", cec_priv->plx_iobase); - nec_priv->iobase = (void *)(pci_resource_start(cec_priv->pci_device, 3)); - pr_info(" nec7210 base address 0x%p\n", nec_priv->iobase); + nec_priv->iobase = pci_resource_start(cec_priv->pci_device, 3); + pr_info(" nec7210 base address 0x%x\n", nec_priv->iobase); isr_flags |= IRQF_SHARED; if (request_irq(cec_priv->pci_device->irq, cec_interrupt, isr_flags, "pci-gpib", board)) { diff --git a/drivers/staging/gpib/common/Makefile b/drivers/staging/gpib/common/Makefile index 0c4c77bea75b..460586edb574 100644 --- a/drivers/staging/gpib/common/Makefile +++ b/drivers/staging/gpib/common/Makefile @@ -1,5 +1,5 @@ -obj-m += gpib_common.o +obj-$(CONFIG_GPIB_COMMON) += gpib_common.o gpib_common-objs := gpib_os.o iblib.o diff --git a/drivers/staging/gpib/common/gpib_os.c b/drivers/staging/gpib/common/gpib_os.c index 405237d8cb47..0962729d7dfe 100644 --- a/drivers/staging/gpib/common/gpib_os.c +++ b/drivers/staging/gpib/common/gpib_os.c @@ -116,56 +116,6 @@ int io_timed_out(gpib_board_t *board) return 0; } -void writeb_wrapper(unsigned int value, void *address) -{ - writeb(value, address); -}; -EXPORT_SYMBOL(writeb_wrapper); - -void writew_wrapper(unsigned int value, void *address) -{ - writew(value, address); -}; -EXPORT_SYMBOL(writew_wrapper); - -unsigned int readb_wrapper(void *address) -{ - return readb(address); -}; -EXPORT_SYMBOL(readb_wrapper); - -unsigned int readw_wrapper(void *address) -{ - return readw(address); -}; -EXPORT_SYMBOL(readw_wrapper); - -#ifdef CONFIG_HAS_IOPORT -void outb_wrapper(unsigned int value, void *address) -{ - outb(value, (unsigned long)(address)); -}; -EXPORT_SYMBOL(outb_wrapper); - -void outw_wrapper(unsigned int value, void *address) -{ - outw(value, (unsigned long)(address)); -}; -EXPORT_SYMBOL(outw_wrapper); - -unsigned int inb_wrapper(void *address) -{ - return inb((unsigned long)(address)); -}; -EXPORT_SYMBOL(inb_wrapper); - -unsigned int inw_wrapper(void *address) -{ - return inw((unsigned long)(address)); -}; -EXPORT_SYMBOL(inw_wrapper); -#endif - /* this is a function instead of a constant because of Suse * defining HZ to be a function call to get_hz() */ @@ -536,7 +486,7 @@ int dvrsp(gpib_board_t *board, unsigned int pad, int sad, return -1; } - if (pad > MAX_GPIB_PRIMARY_ADDRESS || sad > MAX_GPIB_SECONDARY_ADDRESS) { + if (pad > MAX_GPIB_PRIMARY_ADDRESS || sad > MAX_GPIB_SECONDARY_ADDRESS || sad < -1) { pr_err("gpib: bad address for serial poll"); return -1; } @@ -1623,7 +1573,7 @@ static int iobase_ioctl(gpib_board_config_t *config, unsigned long arg) if (WARN_ON_ONCE(sizeof(void *) > sizeof(base_addr))) return -EFAULT; - config->ibbase = (void *)(unsigned long)(base_addr); + config->ibbase = base_addr; return 0; } diff --git a/drivers/staging/gpib/eastwood/Makefile b/drivers/staging/gpib/eastwood/Makefile index c74056f959d0..384825195f77 100644 --- a/drivers/staging/gpib/eastwood/Makefile +++ b/drivers/staging/gpib/eastwood/Makefile @@ -1,3 +1,3 @@ -obj-m += fluke_gpib.o +obj-$(CONFIG_GPIB_FLUKE) += fluke_gpib.o diff --git a/drivers/staging/gpib/eastwood/fluke_gpib.c b/drivers/staging/gpib/eastwood/fluke_gpib.c index 3f938ab0c84d..5e59d38beb35 100644 --- a/drivers/staging/gpib/eastwood/fluke_gpib.c +++ b/drivers/staging/gpib/eastwood/fluke_gpib.c @@ -1011,12 +1011,12 @@ static int fluke_attach_impl(gpib_board_t *board, const gpib_board_config_t *con } e_priv->gpib_iomem_res = res; - nec_priv->iobase = ioremap(e_priv->gpib_iomem_res->start, + nec_priv->mmiobase = ioremap(e_priv->gpib_iomem_res->start, resource_size(e_priv->gpib_iomem_res)); - pr_info("gpib: iobase %lx remapped to %p, length=%d\n", - (unsigned long)e_priv->gpib_iomem_res->start, - nec_priv->iobase, (int)resource_size(e_priv->gpib_iomem_res)); - if (!nec_priv->iobase) { + pr_info("gpib: mmiobase %llx remapped to %p, length=%d\n", + (u64)e_priv->gpib_iomem_res->start, + nec_priv->mmiobase, (int)resource_size(e_priv->gpib_iomem_res)); + if (!nec_priv->mmiobase) { dev_err(&fluke_gpib_pdev->dev, "Could not map I/O memory\n"); return -ENOMEM; } @@ -1107,7 +1107,7 @@ void fluke_detach(gpib_board_t *board) gpib_free_pseudo_irq(board); nec_priv = &e_priv->nec7210_priv; - if (nec_priv->iobase) { + if (nec_priv->mmiobase) { fluke_paged_write_byte(e_priv, 0, ISR0_IMR0, ISR0_IMR0_PAGE); nec7210_board_reset(nec_priv, board); } diff --git a/drivers/staging/gpib/eastwood/fluke_gpib.h b/drivers/staging/gpib/eastwood/fluke_gpib.h index fcbd42f8f9af..4e2144d45270 100644 --- a/drivers/staging/gpib/eastwood/fluke_gpib.h +++ b/drivers/staging/gpib/eastwood/fluke_gpib.h @@ -72,7 +72,7 @@ static inline uint8_t fluke_read_byte_nolock(struct nec7210_priv *nec_priv, { u8 retval; - retval = readl(nec_priv->iobase + register_num * nec_priv->offset); + retval = readl(nec_priv->mmiobase + register_num * nec_priv->offset); return retval; } @@ -80,7 +80,7 @@ static inline uint8_t fluke_read_byte_nolock(struct nec7210_priv *nec_priv, static inline void fluke_write_byte_nolock(struct nec7210_priv *nec_priv, uint8_t data, int register_num) { - writel(data, nec_priv->iobase + register_num * nec_priv->offset); + writel(data, nec_priv->mmiobase + register_num * nec_priv->offset); } static inline uint8_t fluke_paged_read_byte(struct fluke_priv *e_priv, diff --git a/drivers/staging/gpib/fmh_gpib/fmh_gpib.c b/drivers/staging/gpib/fmh_gpib/fmh_gpib.c index 62791db1c34a..0662b20a45e7 100644 --- a/drivers/staging/gpib/fmh_gpib/fmh_gpib.c +++ b/drivers/staging/gpib/fmh_gpib/fmh_gpib.c @@ -24,6 +24,8 @@ #include <linux/slab.h> MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("GPIB Driver for fmh_gpib_core"); +MODULE_AUTHOR("Frank Mori Hess <fmh6jj@gmail.com>"); static irqreturn_t fmh_gpib_interrupt(int irq, void *arg); static int fmh_gpib_attach_holdoff_all(gpib_board_t *board, const gpib_board_config_t *config); @@ -1419,15 +1421,14 @@ static int fmh_gpib_attach_impl(gpib_board_t *board, const gpib_board_config_t * } e_priv->gpib_iomem_res = res; - nec_priv->iobase = ioremap(e_priv->gpib_iomem_res->start, + nec_priv->mmiobase = ioremap(e_priv->gpib_iomem_res->start, resource_size(e_priv->gpib_iomem_res)); - if (!nec_priv->iobase) { + if (!nec_priv->mmiobase) { dev_err(board->dev, "Could not map I/O memory for gpib\n"); return -ENOMEM; } - dev_info(board->dev, "iobase 0x%lx remapped to %p, length=%ld\n", - (unsigned long)e_priv->gpib_iomem_res->start, - nec_priv->iobase, (unsigned long)resource_size(e_priv->gpib_iomem_res)); + dev_info(board->dev, "iobase %pr remapped to %p\n", + e_priv->gpib_iomem_res, nec_priv->mmiobase); res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dma_fifos"); if (!res) { @@ -1507,14 +1508,14 @@ void fmh_gpib_detach(gpib_board_t *board) free_irq(e_priv->irq, board); if (e_priv->fifo_base) fifos_write(e_priv, 0, FIFO_CONTROL_STATUS_REG); - if (nec_priv->iobase) { + if (nec_priv->mmiobase) { write_byte(nec_priv, 0, ISR0_IMR0_REG); nec7210_board_reset(nec_priv, board); } if (e_priv->fifo_base) iounmap(e_priv->fifo_base); - if (nec_priv->iobase) - iounmap(nec_priv->iobase); + if (nec_priv->mmiobase) + iounmap(nec_priv->mmiobase); if (e_priv->dma_port_res) { release_mem_region(e_priv->dma_port_res->start, resource_size(e_priv->dma_port_res)); @@ -1564,12 +1565,12 @@ static int fmh_gpib_pci_attach_impl(gpib_board_t *board, const gpib_board_config e_priv->gpib_iomem_res = &pci_device->resource[gpib_control_status_pci_resource_index]; e_priv->dma_port_res = &pci_device->resource[gpib_fifo_pci_resource_index]; - nec_priv->iobase = ioremap(pci_resource_start(pci_device, + nec_priv->mmiobase = ioremap(pci_resource_start(pci_device, gpib_control_status_pci_resource_index), pci_resource_len(pci_device, gpib_control_status_pci_resource_index)); dev_info(board->dev, "base address for gpib control/status registers remapped to 0x%p\n", - nec_priv->iobase); + nec_priv->mmiobase); if (e_priv->dma_port_res->flags & IORESOURCE_MEM) { e_priv->fifo_base = ioremap(pci_resource_start(pci_device, @@ -1632,14 +1633,14 @@ void fmh_gpib_pci_detach(gpib_board_t *board) free_irq(e_priv->irq, board); if (e_priv->fifo_base) fifos_write(e_priv, 0, FIFO_CONTROL_STATUS_REG); - if (nec_priv->iobase) { + if (nec_priv->mmiobase) { write_byte(nec_priv, 0, ISR0_IMR0_REG); nec7210_board_reset(nec_priv, board); } if (e_priv->fifo_base) iounmap(e_priv->fifo_base); - if (nec_priv->iobase) - iounmap(nec_priv->iobase); + if (nec_priv->mmiobase) + iounmap(nec_priv->mmiobase); if (e_priv->dma_port_res || e_priv->gpib_iomem_res) pci_release_regions(to_pci_dev(board->dev)); if (board->dev) diff --git a/drivers/staging/gpib/fmh_gpib/fmh_gpib.h b/drivers/staging/gpib/fmh_gpib/fmh_gpib.h index 43bfc89d2a6f..60b1bd6d3c15 100644 --- a/drivers/staging/gpib/fmh_gpib/fmh_gpib.h +++ b/drivers/staging/gpib/fmh_gpib/fmh_gpib.h @@ -127,13 +127,13 @@ static const unsigned int fifo_max_burst_length_mask = 0x00ff; static inline uint8_t gpib_cs_read_byte(struct nec7210_priv *nec_priv, unsigned int register_num) { - return readb(nec_priv->iobase + register_num * nec_priv->offset); + return readb(nec_priv->mmiobase + register_num * nec_priv->offset); } static inline void gpib_cs_write_byte(struct nec7210_priv *nec_priv, uint8_t data, unsigned int register_num) { - writeb(data, nec_priv->iobase + register_num * nec_priv->offset); + writeb(data, nec_priv->mmiobase + register_num * nec_priv->offset); } static inline uint16_t fifos_read(struct fmh_priv *fmh_priv, int register_num) diff --git a/drivers/staging/gpib/gpio/Makefile b/drivers/staging/gpib/gpio/Makefile index a31ded6e5924..00ea52abdda7 100644 --- a/drivers/staging/gpib/gpio/Makefile +++ b/drivers/staging/gpib/gpio/Makefile @@ -1,4 +1,4 @@ -obj-m += gpib_bitbang.o +obj-$(CONFIG_GPIB_GPIO) += gpib_bitbang.o diff --git a/drivers/staging/gpib/gpio/gpib_bitbang.c b/drivers/staging/gpib/gpio/gpib_bitbang.c index a2d562cbd65b..23550502e012 100644 --- a/drivers/staging/gpib/gpio/gpib_bitbang.c +++ b/drivers/staging/gpib/gpio/gpib_bitbang.c @@ -315,7 +315,7 @@ struct bb_priv { enum listener_function_state listener_state; }; -inline long usec_diff(struct timespec64 *a, struct timespec64 *b); +static inline long usec_diff(struct timespec64 *a, struct timespec64 *b); static void bb_buffer_print(unsigned char *buffer, size_t length, int cmd, int eoi); static void set_data_lines(u8 byte); static u8 get_data_lines(void); diff --git a/drivers/staging/gpib/hp_82335/Makefile b/drivers/staging/gpib/hp_82335/Makefile index 8b7a552e9355..305ce44ee48a 100644 --- a/drivers/staging/gpib/hp_82335/Makefile +++ b/drivers/staging/gpib/hp_82335/Makefile @@ -1,4 +1,4 @@ -obj-m += hp82335.o +obj-$(CONFIG_GPIB_HP82335) += hp82335.o diff --git a/drivers/staging/gpib/hp_82335/hp82335.c b/drivers/staging/gpib/hp_82335/hp82335.c index 40afe42aea47..ea78143c7ab6 100644 --- a/drivers/staging/gpib/hp_82335/hp82335.c +++ b/drivers/staging/gpib/hp_82335/hp82335.c @@ -9,6 +9,7 @@ */ #include "hp82335.h" +#include <linux/io.h> #include <linux/ioport.h> #include <linux/sched.h> #include <linux/module.h> @@ -233,7 +234,7 @@ static void hp82335_clear_interrupt(struct hp82335_priv *hp_priv) { struct tms9914_priv *tms_priv = &hp_priv->tms9914_priv; - writeb(0, tms_priv->iobase + HPREG_INTR_CLEAR); + writeb(0, tms_priv->mmiobase + HPREG_INTR_CLEAR); } int hp82335_attach(gpib_board_t *board, const gpib_board_config_t *config) @@ -241,7 +242,7 @@ int hp82335_attach(gpib_board_t *board, const gpib_board_config_t *config) struct hp82335_priv *hp_priv; struct tms9914_priv *tms_priv; int retval; - const unsigned long upper_iomem_base = (unsigned long)config->ibbase + hp82335_rom_size; + const unsigned long upper_iomem_base = config->ibbase + hp82335_rom_size; board->status = 0; @@ -253,7 +254,7 @@ int hp82335_attach(gpib_board_t *board, const gpib_board_config_t *config) tms_priv->write_byte = hp82335_write_byte; tms_priv->offset = 1; - switch ((unsigned long)(config->ibbase)) { + switch (config->ibbase) { case 0xc4000: case 0xc8000: case 0xcc000: @@ -271,7 +272,7 @@ int hp82335_attach(gpib_board_t *board, const gpib_board_config_t *config) case 0xfc000: break; default: - pr_err("hp82335: invalid base io address 0x%p\n", config->ibbase); + pr_err("hp82335: invalid base io address 0x%u\n", config->ibbase); return -EINVAL; } if (!request_mem_region(upper_iomem_base, hp82335_upper_iomem_size, "hp82335")) { @@ -280,9 +281,9 @@ int hp82335_attach(gpib_board_t *board, const gpib_board_config_t *config) return -EBUSY; } hp_priv->raw_iobase = upper_iomem_base; - tms_priv->iobase = ioremap(upper_iomem_base, hp82335_upper_iomem_size); + tms_priv->mmiobase = ioremap(upper_iomem_base, hp82335_upper_iomem_size); pr_info("hp82335: upper half of 82335 iomem region 0x%lx remapped to 0x%p\n", - hp_priv->raw_iobase, tms_priv->iobase); + hp_priv->raw_iobase, tms_priv->mmiobase); retval = request_irq(config->ibirq, hp82335_interrupt, 0, "hp82335", board); if (retval) { @@ -296,7 +297,7 @@ int hp82335_attach(gpib_board_t *board, const gpib_board_config_t *config) hp82335_clear_interrupt(hp_priv); - writeb(INTR_ENABLE, tms_priv->iobase + HPREG_CCR); + writeb(INTR_ENABLE, tms_priv->mmiobase + HPREG_CCR); tms9914_online(board, tms_priv); @@ -312,10 +313,10 @@ void hp82335_detach(gpib_board_t *board) tms_priv = &hp_priv->tms9914_priv; if (hp_priv->irq) free_irq(hp_priv->irq, board); - if (tms_priv->iobase) { - writeb(0, tms_priv->iobase + HPREG_CCR); + if (tms_priv->mmiobase) { + writeb(0, tms_priv->mmiobase + HPREG_CCR); tms9914_board_reset(tms_priv); - iounmap((void *)tms_priv->iobase); + iounmap(tms_priv->mmiobase); } if (hp_priv->raw_iobase) release_mem_region(hp_priv->raw_iobase, hp82335_upper_iomem_size); diff --git a/drivers/staging/gpib/hp_82341/Makefile b/drivers/staging/gpib/hp_82341/Makefile index 1fe7db4f8ca4..21367310a17e 100644 --- a/drivers/staging/gpib/hp_82341/Makefile +++ b/drivers/staging/gpib/hp_82341/Makefile @@ -1,2 +1,2 @@ -obj-m += hp_82341.o +obj-$(CONFIG_GPIB_HP82341) += hp_82341.o diff --git a/drivers/staging/gpib/hp_82341/hp_82341.c b/drivers/staging/gpib/hp_82341/hp_82341.c index 8ad1c885a9fb..71d481e88bd9 100644 --- a/drivers/staging/gpib/hp_82341/hp_82341.c +++ b/drivers/staging/gpib/hp_82341/hp_82341.c @@ -473,12 +473,12 @@ void hp_82341_free_private(gpib_board_t *board) static uint8_t hp_82341_read_byte(struct tms9914_priv *priv, unsigned int register_num) { - return inb((unsigned long)(priv->iobase) + register_num); + return inb(priv->iobase + register_num); } static void hp_82341_write_byte(struct tms9914_priv *priv, uint8_t data, unsigned int register_num) { - outb(data, (unsigned long)(priv->iobase) + register_num); + outb(data, priv->iobase + register_num); } static int hp_82341_find_isapnp_board(struct pnp_dev **dev) @@ -682,8 +682,8 @@ int hp_82341_attach(gpib_board_t *board, const gpib_board_config_t *config) { struct hp_82341_priv *hp_priv; struct tms9914_priv *tms_priv; - unsigned long start_addr; - void *iobase; + u32 start_addr; + u32 iobase; int irq; int i; int retval; @@ -704,7 +704,7 @@ int hp_82341_attach(gpib_board_t *board, const gpib_board_config_t *config) if (retval < 0) return retval; hp_priv->pnp_dev = dev; - iobase = (void *)(pnp_port_start(dev, 0)); + iobase = pnp_port_start(dev, 0); irq = pnp_irq(dev, 0); hp_priv->hw_version = HW_VERSION_82341D; hp_priv->io_region_offset = 0x8; @@ -714,9 +714,9 @@ int hp_82341_attach(gpib_board_t *board, const gpib_board_config_t *config) hp_priv->hw_version = HW_VERSION_82341C; hp_priv->io_region_offset = 0x400; } - pr_info("hp_82341: base io 0x%p\n", iobase); + pr_info("hp_82341: base io 0x%u\n", iobase); for (i = 0; i < hp_82341_num_io_regions; ++i) { - start_addr = (unsigned long)(iobase) + i * hp_priv->io_region_offset; + start_addr = iobase + i * hp_priv->io_region_offset; if (!request_region(start_addr, hp_82341_region_iosize, "hp_82341")) { pr_err("hp_82341: failed to allocate io ports 0x%lx-0x%lx\n", start_addr, @@ -725,7 +725,7 @@ int hp_82341_attach(gpib_board_t *board, const gpib_board_config_t *config) } hp_priv->iobase[i] = start_addr; } - tms_priv->iobase = (void *)(hp_priv->iobase[2]); + tms_priv->iobase = hp_priv->iobase[2]; if (hp_priv->hw_version == HW_VERSION_82341D) { retval = isapnp_cfg_begin(hp_priv->pnp_dev->card->number, hp_priv->pnp_dev->number); diff --git a/drivers/staging/gpib/include/gpibP.h b/drivers/staging/gpib/include/gpibP.h index 5fc42b645ab7..b97da577ba33 100644 --- a/drivers/staging/gpib/include/gpibP.h +++ b/drivers/staging/gpib/include/gpibP.h @@ -16,6 +16,7 @@ #include <linux/fs.h> #include <linux/interrupt.h> +#include <linux/io.h> void gpib_register_driver(gpib_interface_t *interface, struct module *mod); void gpib_unregister_driver(gpib_interface_t *interface); @@ -35,16 +36,5 @@ extern gpib_board_t board_array[GPIB_MAX_NUM_BOARDS]; extern struct list_head registered_drivers; -#include <linux/io.h> - -void writeb_wrapper(unsigned int value, void *address); -unsigned int readb_wrapper(void *address); -void outb_wrapper(unsigned int value, void *address); -unsigned int inb_wrapper(void *address); -void writew_wrapper(unsigned int value, void *address); -unsigned int readw_wrapper(void *address); -void outw_wrapper(unsigned int value, void *address); -unsigned int inw_wrapper(void *address); - #endif // _GPIB_P_H diff --git a/drivers/staging/gpib/include/gpib_types.h b/drivers/staging/gpib/include/gpib_types.h index ee2643da6d71..b41781a55a60 100644 --- a/drivers/staging/gpib/include/gpib_types.h +++ b/drivers/staging/gpib/include/gpib_types.h @@ -31,7 +31,8 @@ typedef struct { void *init_data; int init_data_length; /* IO base address to use for non-pnp cards (set by core, driver should make local copy) */ - void *ibbase; + u32 ibbase; + void __iomem *mmibbase; /* IRQ to use for non-pnp cards (set by core, driver should make local copy) */ unsigned int ibirq; /* dma channel to use for non-pnp cards (set by core, driver should make local copy) */ diff --git a/drivers/staging/gpib/include/nec7210.h b/drivers/staging/gpib/include/nec7210.h index c00aba4ce846..ca998c4a84bf 100644 --- a/drivers/staging/gpib/include/nec7210.h +++ b/drivers/staging/gpib/include/nec7210.h @@ -18,7 +18,10 @@ /* struct used to provide variables local to a nec7210 chip */ struct nec7210_priv { - void *iobase; +#ifdef CONFIG_HAS_IOPORT + u32 iobase; +#endif + void __iomem *mmiobase; unsigned int offset; // offset between successive nec7210 io addresses unsigned int dma_channel; u8 *dma_buffer; diff --git a/drivers/staging/gpib/include/tms9914.h b/drivers/staging/gpib/include/tms9914.h index 456b488212d2..d8c8d1c9b131 100644 --- a/drivers/staging/gpib/include/tms9914.h +++ b/drivers/staging/gpib/include/tms9914.h @@ -20,7 +20,10 @@ enum tms9914_holdoff_mode { /* struct used to provide variables local to a tms9914 chip */ struct tms9914_priv { - void *iobase; +#ifdef CONFIG_HAS_IOPORT + u32 iobase; +#endif + void __iomem *mmiobase; unsigned int offset; // offset between successive tms9914 io addresses unsigned int dma_channel; // software copy of bits written to interrupt mask registers diff --git a/drivers/staging/gpib/ines/Makefile b/drivers/staging/gpib/ines/Makefile index cdcaa59a4e39..6b6e480fd811 100644 --- a/drivers/staging/gpib/ines/Makefile +++ b/drivers/staging/gpib/ines/Makefile @@ -1,4 +1,4 @@ ccflags-$(CONFIG_GPIB_PCMCIA) := -DGPIB_PCMCIA -obj-m += ines_gpib.o +obj-$(CONFIG_GPIB_INES) += ines_gpib.o diff --git a/drivers/staging/gpib/ines/ines.h b/drivers/staging/gpib/ines/ines.h index 7e8302619998..eed038fd3f28 100644 --- a/drivers/staging/gpib/ines/ines.h +++ b/drivers/staging/gpib/ines/ines.h @@ -83,14 +83,14 @@ void ines_set_xfer_counter(struct ines_priv *priv, unsigned int count); /* inb/outb wrappers */ static inline unsigned int ines_inb(struct ines_priv *priv, unsigned int register_number) { - return inb((unsigned long)(priv->nec7210_priv.iobase) + + return inb(priv->nec7210_priv.iobase + register_number * priv->nec7210_priv.offset); } static inline void ines_outb(struct ines_priv *priv, unsigned int value, unsigned int register_number) { - outb(value, (unsigned long)(priv->nec7210_priv.iobase) + + outb(value, priv->nec7210_priv.iobase + register_number * priv->nec7210_priv.offset); } diff --git a/drivers/staging/gpib/ines/ines_gpib.c b/drivers/staging/gpib/ines/ines_gpib.c index 9d8387c3bf01..e18455ba842f 100644 --- a/drivers/staging/gpib/ines/ines_gpib.c +++ b/drivers/staging/gpib/ines/ines_gpib.c @@ -273,10 +273,10 @@ irqreturn_t ines_pci_interrupt(int irq, void *arg) struct nec7210_priv *nec_priv = &priv->nec7210_priv; if (priv->pci_chip_type == PCI_CHIP_QUANCOM) { - if ((inb((unsigned long)nec_priv->iobase + + if ((inb(nec_priv->iobase + QUANCOM_IRQ_CONTROL_STATUS_REG) & QUANCOM_IRQ_ASSERTED_BIT)) - outb(QUANCOM_IRQ_ENABLE_BIT, (unsigned long)(nec_priv->iobase) + + outb(QUANCOM_IRQ_ENABLE_BIT, nec_priv->iobase + QUANCOM_IRQ_CONTROL_STATUS_REG); } @@ -780,8 +780,8 @@ static int ines_common_pci_attach(gpib_board_t *board, const gpib_board_config_t if (pci_request_regions(ines_priv->pci_device, "ines-gpib")) return -1; - nec_priv->iobase = (void *)(pci_resource_start(ines_priv->pci_device, - found_id.gpib_region)); + nec_priv->iobase = pci_resource_start(ines_priv->pci_device, + found_id.gpib_region); ines_priv->pci_chip_type = found_id.pci_chip_type; nec_priv->offset = found_id.io_offset; @@ -840,7 +840,7 @@ static int ines_common_pci_attach(gpib_board_t *board, const gpib_board_config_t } break; case PCI_CHIP_QUANCOM: - outb(QUANCOM_IRQ_ENABLE_BIT, (unsigned long)(nec_priv->iobase) + + outb(QUANCOM_IRQ_ENABLE_BIT, nec_priv->iobase + QUANCOM_IRQ_CONTROL_STATUS_REG); break; case PCI_CHIP_QUICKLOGIC5030: @@ -899,8 +899,8 @@ int ines_isa_attach(gpib_board_t *board, const gpib_board_config_t *config) ines_priv = board->private_data; nec_priv = &ines_priv->nec7210_priv; - if (!request_region((unsigned long)config->ibbase, ines_isa_iosize, "ines_gpib")) { - pr_err("ines_gpib: ioports at 0x%p already in use\n", config->ibbase); + if (!request_region(config->ibbase, ines_isa_iosize, "ines_gpib")) { + pr_err("ines_gpib: ioports at 0x%x already in use\n", config->ibbase); return -1; } nec_priv->iobase = config->ibbase; @@ -931,7 +931,7 @@ void ines_pci_detach(gpib_board_t *board) break; case PCI_CHIP_QUANCOM: if (nec_priv->iobase) - outb(0, (unsigned long)(nec_priv->iobase) + + outb(0, nec_priv->iobase + QUANCOM_IRQ_CONTROL_STATUS_REG); break; default: @@ -960,7 +960,7 @@ void ines_isa_detach(gpib_board_t *board) free_irq(ines_priv->irq, board); if (nec_priv->iobase) { nec7210_board_reset(nec_priv, board); - release_region((unsigned long)(nec_priv->iobase), ines_isa_iosize); + release_region(nec_priv->iobase, ines_isa_iosize); } } ines_free_private(board); @@ -1355,7 +1355,7 @@ int ines_common_pcmcia_attach(gpib_board_t *board) return -1; } - nec_priv->iobase = (void *)(unsigned long)curr_dev->resource[0]->start; + nec_priv->iobase = curr_dev->resource[0]->start; nec7210_board_reset(nec_priv, board); @@ -1410,7 +1410,7 @@ void ines_pcmcia_detach(gpib_board_t *board) free_irq(ines_priv->irq, board); if (nec_priv->iobase) { nec7210_board_reset(nec_priv, board); - release_region((unsigned long)(nec_priv->iobase), ines_pcmcia_iosize); + release_region(nec_priv->iobase, ines_pcmcia_iosize); } } ines_free_private(board); diff --git a/drivers/staging/gpib/lpvo_usb_gpib/Makefile b/drivers/staging/gpib/lpvo_usb_gpib/Makefile index 137511acce63..360553488e6d 100644 --- a/drivers/staging/gpib/lpvo_usb_gpib/Makefile +++ b/drivers/staging/gpib/lpvo_usb_gpib/Makefile @@ -1,3 +1,3 @@ -obj-m += lpvo_usb_gpib.o +obj-$(CONFIG_GPIB_LPVO) += lpvo_usb_gpib.o diff --git a/drivers/staging/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c b/drivers/staging/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c index 267651a15fa0..93a05c792816 100644 --- a/drivers/staging/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c +++ b/drivers/staging/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c @@ -99,8 +99,8 @@ module_param(debug, int, 0644); #define USB_GPIB_DEBUG_ON "\nIBDE\xAA\n" #define USB_GPIB_SET_LISTEN "\nIBDT0\n" #define USB_GPIB_SET_TALK "\nIBDT1\n" -#define USB_GPIB_SET_LINES "\nIBDC\n" -#define USB_GPIB_SET_DATA "\nIBDM\n" +#define USB_GPIB_SET_LINES "\nIBDC.\n" +#define USB_GPIB_SET_DATA "\nIBDM.\n" #define USB_GPIB_READ_LINES "\nIBD?C\n" #define USB_GPIB_READ_DATA "\nIBD?M\n" #define USB_GPIB_READ_BUS "\nIBD??\n" @@ -210,7 +210,7 @@ static int skel_do_release(gpib_board_t *); * (unix time in sec and NANOsec) */ -inline int usec_diff(struct timespec64 *a, struct timespec64 *b) +static inline int usec_diff(struct timespec64 *a, struct timespec64 *b) { return ((a->tv_sec - b->tv_sec) * 1000000 + (a->tv_nsec - b->tv_nsec) / 1000); @@ -436,7 +436,7 @@ static void set_timeout(gpib_board_t *board) static int usb_gpib_attach(gpib_board_t *board, const gpib_board_config_t *config) { int retval, j; - int base = (long)config->ibbase; + u32 base = config->ibbase; char *device_path; int match; struct usb_device *udev; @@ -589,7 +589,7 @@ static int usb_gpib_command(gpib_board_t *board, size_t *bytes_written) { int i, retval; - char command[6] = "IBc\n"; + char command[6] = "IBc.\n"; DIA_LOG(1, "enter %p\n", board); @@ -608,7 +608,7 @@ static int usb_gpib_command(gpib_board_t *board, } /** - * disable_eos() - Disable END on eos byte (END on EOI only) + * usb_gpib_disable_eos() - Disable END on eos byte (END on EOI only) * * @board: the gpib_board data area for this gpib interface * @@ -624,7 +624,7 @@ static void usb_gpib_disable_eos(gpib_board_t *board) } /** - * enable_eos() - Enable END for reads when eos byte is received. + * usb_gpib_enable_eos() - Enable END for reads when eos byte is received. * * @board: the gpib_board data area for this gpib interface * @eos_byte: the 'eos' byte @@ -647,7 +647,7 @@ static int usb_gpib_enable_eos(gpib_board_t *board, } /** - * go_to_standby() - De-assert ATN + * usb_gpib_go_to_standby() - De-assert ATN * * @board: the gpib_board data area for this gpib interface */ @@ -664,7 +664,7 @@ static int usb_gpib_go_to_standby(gpib_board_t *board) } /** - * interface_clear() - Assert or de-assert IFC + * usb_gpib_interface_clear() - Assert or de-assert IFC * * @board: the gpib_board data area for this gpib interface * assert: 1: assert IFC; 0: de-assert IFC diff --git a/drivers/staging/gpib/nec7210/Makefile b/drivers/staging/gpib/nec7210/Makefile index 8d4d90f21109..64330f2e89d1 100644 --- a/drivers/staging/gpib/nec7210/Makefile +++ b/drivers/staging/gpib/nec7210/Makefile @@ -1,4 +1,4 @@ -obj-m += nec7210.o +obj-$(CONFIG_GPIB_NEC7210) += nec7210.o diff --git a/drivers/staging/gpib/nec7210/nec7210.c b/drivers/staging/gpib/nec7210/nec7210.c index 1d9951035497..c9a837fad96e 100644 --- a/drivers/staging/gpib/nec7210/nec7210.c +++ b/drivers/staging/gpib/nec7210/nec7210.c @@ -1035,7 +1035,7 @@ EXPORT_SYMBOL(nec7210_board_online); /* wrappers for io */ uint8_t nec7210_ioport_read_byte(struct nec7210_priv *priv, unsigned int register_num) { - return inb((unsigned long)(priv->iobase) + register_num * priv->offset); + return inb(priv->iobase + register_num * priv->offset); } EXPORT_SYMBOL(nec7210_ioport_read_byte); @@ -1047,7 +1047,7 @@ void nec7210_ioport_write_byte(struct nec7210_priv *priv, uint8_t data, unsigned */ nec7210_locking_ioport_write_byte(priv, data, register_num); else - outb(data, (unsigned long)(priv->iobase) + register_num * priv->offset); + outb(data, priv->iobase + register_num * priv->offset); } EXPORT_SYMBOL(nec7210_ioport_write_byte); @@ -1058,7 +1058,7 @@ uint8_t nec7210_locking_ioport_read_byte(struct nec7210_priv *priv, unsigned int unsigned long flags; spin_lock_irqsave(&priv->register_page_lock, flags); - retval = inb((unsigned long)(priv->iobase) + register_num * priv->offset); + retval = inb(priv->iobase + register_num * priv->offset); spin_unlock_irqrestore(&priv->register_page_lock, flags); return retval; } @@ -1072,7 +1072,7 @@ void nec7210_locking_ioport_write_byte(struct nec7210_priv *priv, uint8_t data, spin_lock_irqsave(&priv->register_page_lock, flags); if (register_num == AUXMR) udelay(1); - outb(data, (unsigned long)(priv->iobase) + register_num * priv->offset); + outb(data, priv->iobase + register_num * priv->offset); spin_unlock_irqrestore(&priv->register_page_lock, flags); } EXPORT_SYMBOL(nec7210_locking_ioport_write_byte); @@ -1080,7 +1080,7 @@ EXPORT_SYMBOL(nec7210_locking_ioport_write_byte); uint8_t nec7210_iomem_read_byte(struct nec7210_priv *priv, unsigned int register_num) { - return readb(priv->iobase + register_num * priv->offset); + return readb(priv->mmiobase + register_num * priv->offset); } EXPORT_SYMBOL(nec7210_iomem_read_byte); @@ -1092,7 +1092,7 @@ void nec7210_iomem_write_byte(struct nec7210_priv *priv, uint8_t data, unsigned */ nec7210_locking_iomem_write_byte(priv, data, register_num); else - writeb(data, priv->iobase + register_num * priv->offset); + writeb(data, priv->mmiobase + register_num * priv->offset); } EXPORT_SYMBOL(nec7210_iomem_write_byte); @@ -1102,7 +1102,7 @@ uint8_t nec7210_locking_iomem_read_byte(struct nec7210_priv *priv, unsigned int unsigned long flags; spin_lock_irqsave(&priv->register_page_lock, flags); - retval = readb(priv->iobase + register_num * priv->offset); + retval = readb(priv->mmiobase + register_num * priv->offset); spin_unlock_irqrestore(&priv->register_page_lock, flags); return retval; } @@ -1116,7 +1116,7 @@ void nec7210_locking_iomem_write_byte(struct nec7210_priv *priv, uint8_t data, spin_lock_irqsave(&priv->register_page_lock, flags); if (register_num == AUXMR) udelay(1); - writeb(data, priv->iobase + register_num * priv->offset); + writeb(data, priv->mmiobase + register_num * priv->offset); spin_unlock_irqrestore(&priv->register_page_lock, flags); } EXPORT_SYMBOL(nec7210_locking_iomem_write_byte); diff --git a/drivers/staging/gpib/ni_usb/Makefile b/drivers/staging/gpib/ni_usb/Makefile index e22b3b21a62c..469c5d16add3 100644 --- a/drivers/staging/gpib/ni_usb/Makefile +++ b/drivers/staging/gpib/ni_usb/Makefile @@ -1,4 +1,4 @@ -obj-m += ni_usb_gpib.o +obj-$(CONFIG_GPIB_NI_USB) += ni_usb_gpib.o diff --git a/drivers/staging/gpib/pc2/Makefile b/drivers/staging/gpib/pc2/Makefile index 8148425e0f87..481ee4296e1b 100644 --- a/drivers/staging/gpib/pc2/Makefile +++ b/drivers/staging/gpib/pc2/Makefile @@ -1,5 +1,5 @@ -obj-m += pc2_gpib.o +obj-$(CONFIG_GPIB_PC2) += pc2_gpib.o diff --git a/drivers/staging/gpib/pc2/pc2_gpib.c b/drivers/staging/gpib/pc2/pc2_gpib.c index 7b3b34f47341..d22af25125b1 100644 --- a/drivers/staging/gpib/pc2/pc2_gpib.c +++ b/drivers/staging/gpib/pc2/pc2_gpib.c @@ -426,7 +426,7 @@ int pc2_attach(gpib_board_t *board, const gpib_board_config_t *config) nec_priv = &pc2_priv->nec7210_priv; nec_priv->offset = pc2_reg_offset; - if (request_region((unsigned long)config->ibbase, pc2_iosize, "pc2") == 0) { + if (request_region(config->ibbase, pc2_iosize, "pc2") == 0) { pr_err("gpib: ioports are already in use\n"); return -1; } @@ -471,7 +471,7 @@ void pc2_detach(gpib_board_t *board) free_irq(pc2_priv->irq, board); if (nec_priv->iobase) { nec7210_board_reset(nec_priv, board); - release_region((unsigned long)(nec_priv->iobase), pc2_iosize); + release_region(nec_priv->iobase, pc2_iosize); } if (nec_priv->dma_buffer) { dma_free_coherent(board->dev, nec_priv->dma_buffer_length, @@ -498,14 +498,14 @@ static int pc2a_common_attach(gpib_board_t *board, const gpib_board_config_t *co nec_priv = &pc2_priv->nec7210_priv; nec_priv->offset = pc2a_reg_offset; - switch ((unsigned long)(config->ibbase)) { + switch (config->ibbase) { case 0x02e1: case 0x22e1: case 0x42e1: case 0x62e1: break; default: - pr_err("PCIIa base range invalid, must be one of 0x[0246]2e1, but is 0x%p\n", + pr_err("PCIIa base range invalid, must be one of 0x[0246]2e1, but is 0x%d\n", config->ibbase); return -1; } @@ -522,7 +522,7 @@ static int pc2a_common_attach(gpib_board_t *board, const gpib_board_config_t *co unsigned int err = 0; for (i = 0; i < num_registers; i++) { - if (check_region((unsigned long)config->ibbase + i * pc2a_reg_offset, 1)) + if (check_region(config->ibbase + i * pc2a_reg_offset, 1)) err++; } if (config->ibirq && check_region(pc2a_clear_intr_iobase + config->ibirq, 1)) @@ -533,11 +533,11 @@ static int pc2a_common_attach(gpib_board_t *board, const gpib_board_config_t *co } #endif for (i = 0; i < num_registers; i++) { - if (!request_region((unsigned long)config->ibbase + + if (!request_region(config->ibbase + i * pc2a_reg_offset, 1, "pc2a")) { pr_err("gpib: ioports are already in use"); for (j = 0; j < i; j++) - release_region((unsigned long)(config->ibbase) + + release_region(config->ibbase + j * pc2a_reg_offset, 1); return -1; } @@ -608,7 +608,7 @@ static void pc2a_common_detach(gpib_board_t *board, unsigned int num_registers) if (nec_priv->iobase) { nec7210_board_reset(nec_priv, board); for (i = 0; i < num_registers; i++) - release_region((unsigned long)nec_priv->iobase + + release_region(nec_priv->iobase + i * pc2a_reg_offset, 1); } if (pc2_priv->clear_intr_addr) diff --git a/drivers/staging/gpib/tms9914/Makefile b/drivers/staging/gpib/tms9914/Makefile index 81b7e3cf104c..4705ab07f413 100644 --- a/drivers/staging/gpib/tms9914/Makefile +++ b/drivers/staging/gpib/tms9914/Makefile @@ -1,5 +1,5 @@ -obj-m += tms9914.o +obj-$(CONFIG_GPIB_TMS9914) += tms9914.o diff --git a/drivers/staging/gpib/tms9914/tms9914.c b/drivers/staging/gpib/tms9914/tms9914.c index 152b243b845b..ec8e1d4d762f 100644 --- a/drivers/staging/gpib/tms9914/tms9914.c +++ b/drivers/staging/gpib/tms9914/tms9914.c @@ -866,14 +866,14 @@ EXPORT_SYMBOL_GPL(tms9914_online); // wrapper for inb uint8_t tms9914_ioport_read_byte(struct tms9914_priv *priv, unsigned int register_num) { - return inb((unsigned long)(priv->iobase) + register_num * priv->offset); + return inb(priv->iobase + register_num * priv->offset); } EXPORT_SYMBOL_GPL(tms9914_ioport_read_byte); // wrapper for outb void tms9914_ioport_write_byte(struct tms9914_priv *priv, uint8_t data, unsigned int register_num) { - outb(data, (unsigned long)(priv->iobase) + register_num * priv->offset); + outb(data, priv->iobase + register_num * priv->offset); if (register_num == AUXCR) udelay(1); } @@ -883,14 +883,14 @@ EXPORT_SYMBOL_GPL(tms9914_ioport_write_byte); // wrapper for readb uint8_t tms9914_iomem_read_byte(struct tms9914_priv *priv, unsigned int register_num) { - return readb(priv->iobase + register_num * priv->offset); + return readb(priv->mmiobase + register_num * priv->offset); } EXPORT_SYMBOL_GPL(tms9914_iomem_read_byte); // wrapper for writeb void tms9914_iomem_write_byte(struct tms9914_priv *priv, uint8_t data, unsigned int register_num) { - writeb(data, priv->iobase + register_num * priv->offset); + writeb(data, priv->mmiobase + register_num * priv->offset); if (register_num == AUXCR) udelay(1); } diff --git a/drivers/staging/gpib/tnt4882/Makefile b/drivers/staging/gpib/tnt4882/Makefile index f767c990db7a..a3c3fb96d5ed 100644 --- a/drivers/staging/gpib/tnt4882/Makefile +++ b/drivers/staging/gpib/tnt4882/Makefile @@ -1,5 +1,5 @@ ccflags-$(CONFIG_GPIB_PCMCIA) := -DGPIB_PCMCIA -obj-m += tnt4882.o +obj-$(CONFIG_GPIB_NI_PCI_ISA) += tnt4882.o tnt4882-objs := tnt4882_gpib.o mite.o diff --git a/drivers/staging/gpib/tnt4882/mite.c b/drivers/staging/gpib/tnt4882/mite.c index 0edf34d243e9..4bd352967616 100644 --- a/drivers/staging/gpib/tnt4882/mite.c +++ b/drivers/staging/gpib/tnt4882/mite.c @@ -148,72 +148,3 @@ void mite_list_devices(void) } pr_info("\n"); } - -int mite_bytes_transferred(struct mite_struct *mite, int chan) -{ - int dar, fcr; - - dar = readl(mite->mite_io_addr + MITE_DAR + CHAN_OFFSET(chan)); - fcr = readl(mite->mite_io_addr + MITE_FCR + CHAN_OFFSET(chan)) & 0x000000FF; - return dar - fcr; -} - -int mite_dma_tcr(struct mite_struct *mite) -{ - int tcr; - int lkar; - - lkar = readl(mite->mite_io_addr + CHAN_OFFSET(0) + MITE_LKAR); - tcr = readl(mite->mite_io_addr + CHAN_OFFSET(0) + MITE_TCR); - MDPRINTK("lkar=0x%08x tcr=%d\n", lkar, tcr); - - return tcr; -} - -void mite_dma_disarm(struct mite_struct *mite) -{ - int chor; - - /* disarm */ - chor = CHOR_ABORT; - writel(chor, mite->mite_io_addr + CHAN_OFFSET(0) + MITE_CHOR); -} - -void mite_dump_regs(struct mite_struct *mite) -{ - void *addr = 0; - unsigned long temp = 0; - - pr_info("mite address is =0x%p\n", mite->mite_io_addr); - - addr = mite->mite_io_addr + MITE_CHOR + CHAN_OFFSET(0); - pr_info("mite status[CHOR]at 0x%p =0x%08lx\n", addr, temp = readl(addr)); - //mite_decode(mite_CHOR_strings,temp); - addr = mite->mite_io_addr + MITE_CHCR + CHAN_OFFSET(0); - pr_info("mite status[CHCR]at 0x%p =0x%08lx\n", addr, temp = readl(addr)); - //mite_decode(mite_CHCR_strings,temp); - addr = mite->mite_io_addr + MITE_TCR + CHAN_OFFSET(0); - pr_info("mite status[TCR] at 0x%p =0x%08x\n", addr, readl(addr)); - addr = mite->mite_io_addr + MITE_MCR + CHAN_OFFSET(0); - pr_info("mite status[MCR] at 0x%p =0x%08lx\n", addr, temp = readl(addr)); - //mite_decode(mite_MCR_strings,temp); - addr = mite->mite_io_addr + MITE_MAR + CHAN_OFFSET(0); - pr_info("mite status[MAR] at 0x%p =0x%08x\n", addr, readl(addr)); - addr = mite->mite_io_addr + MITE_DCR + CHAN_OFFSET(0); - pr_info("mite status[DCR] at 0x%p =0x%08lx\n", addr, temp = readl(addr)); - //mite_decode(mite_CR_strings,temp); - addr = mite->mite_io_addr + MITE_DAR + CHAN_OFFSET(0); - pr_info("mite status[DAR] at 0x%p =0x%08x\n", addr, readl(addr)); - addr = mite->mite_io_addr + MITE_LKCR + CHAN_OFFSET(0); - pr_info("mite status[LKCR]at 0x%p =0x%08lx\n", addr, temp = readl(addr)); - //mite_decode(mite_CR_strings,temp); - addr = mite->mite_io_addr + MITE_LKAR + CHAN_OFFSET(0); - pr_info("mite status[LKAR]at 0x%p =0x%08x\n", addr, readl(addr)); - - addr = mite->mite_io_addr + MITE_CHSR + CHAN_OFFSET(0); - pr_info("mite status[CHSR]at 0x%p =0x%08lx\n", addr, temp = readl(addr)); - //mite_decode(mite_CHSR_strings,temp); - addr = mite->mite_io_addr + MITE_FCR + CHAN_OFFSET(0); - pr_info("mite status[FCR] at 0x%p =0x%08x\n\n", addr, readl(addr)); -} - diff --git a/drivers/staging/gpib/tnt4882/mite.h b/drivers/staging/gpib/tnt4882/mite.h index 6454d069b8cc..edb873435b51 100644 --- a/drivers/staging/gpib/tnt4882/mite.h +++ b/drivers/staging/gpib/tnt4882/mite.h @@ -34,9 +34,9 @@ struct mite_struct { struct pci_dev *pcidev; unsigned long mite_phys_addr; - void *mite_io_addr; + void __iomem *mite_io_addr; unsigned long daq_phys_addr; - void *daq_io_addr; + void __iomem *daq_io_addr; int DMA_CheckNearEnd; @@ -61,15 +61,6 @@ int mite_setup(struct mite_struct *mite); void mite_unsetup(struct mite_struct *mite); void mite_list_devices(void); -int mite_dma_tcr(struct mite_struct *mite); - -void mite_dma_arm(struct mite_struct *mite); -void mite_dma_disarm(struct mite_struct *mite); - -void mite_dump_regs(struct mite_struct *mite); -void mite_setregs(struct mite_struct *mite, unsigned long ll_start, int chan, int dir); -int mite_bytes_transferred(struct mite_struct *mite, int chan); - #define CHAN_OFFSET(x) (0x100 * (x)) /* DMA base for chan 0 is 0x500, chan 1 is 0x600 */ diff --git a/drivers/staging/gpib/tnt4882/tnt4882_gpib.c b/drivers/staging/gpib/tnt4882/tnt4882_gpib.c index e49a952fa0d8..ce91c3eb768c 100644 --- a/drivers/staging/gpib/tnt4882/tnt4882_gpib.c +++ b/drivers/staging/gpib/tnt4882/tnt4882_gpib.c @@ -45,10 +45,6 @@ struct tnt4882_priv { unsigned short imr0_bits; unsigned short imr3_bits; unsigned short auxg_bits; // bits written to auxiliary register G - void (*io_writeb)(unsigned int value, void *address); - void (*io_writew)(unsigned int value, void *address); - unsigned int (*io_readb)(void *address); - unsigned int (*io_readw)(void *address); }; // interface functions @@ -104,23 +100,23 @@ static const int atgpib_iosize = 32; /* paged io */ static inline unsigned int tnt_paged_readb(struct tnt4882_priv *priv, unsigned long offset) { - priv->io_writeb(AUX_PAGEIN, priv->nec7210_priv.iobase + AUXMR * priv->nec7210_priv.offset); + iowrite8(AUX_PAGEIN, priv->nec7210_priv.mmiobase + AUXMR * priv->nec7210_priv.offset); udelay(1); - return priv->io_readb(priv->nec7210_priv.iobase + offset); + return ioread8(priv->nec7210_priv.mmiobase + offset); } static inline void tnt_paged_writeb(struct tnt4882_priv *priv, unsigned int value, unsigned long offset) { - priv->io_writeb(AUX_PAGEIN, priv->nec7210_priv.iobase + AUXMR * priv->nec7210_priv.offset); + iowrite8(AUX_PAGEIN, priv->nec7210_priv.mmiobase + AUXMR * priv->nec7210_priv.offset); udelay(1); - priv->io_writeb(value, priv->nec7210_priv.iobase + offset); + iowrite8(value, priv->nec7210_priv.mmiobase + offset); } /* readb/writeb wrappers */ static inline unsigned short tnt_readb(struct tnt4882_priv *priv, unsigned long offset) { - void *address = priv->nec7210_priv.iobase + offset; + void *address = priv->nec7210_priv.mmiobase + offset; unsigned long flags; unsigned short retval; spinlock_t *register_lock = &priv->nec7210_priv.register_page_lock; @@ -134,7 +130,7 @@ static inline unsigned short tnt_readb(struct tnt4882_priv *priv, unsigned long switch (priv->nec7210_priv.type) { case TNT4882: case TNT5004: - retval = priv->io_readb(address); + retval = ioread8(address); break; case NAT4882: retval = tnt_paged_readb(priv, offset - tnt_pagein_offset); @@ -149,7 +145,7 @@ static inline unsigned short tnt_readb(struct tnt4882_priv *priv, unsigned long } break; default: - retval = priv->io_readb(address); + retval = ioread8(address); break; } spin_unlock_irqrestore(register_lock, flags); @@ -158,7 +154,7 @@ static inline unsigned short tnt_readb(struct tnt4882_priv *priv, unsigned long static inline void tnt_writeb(struct tnt4882_priv *priv, unsigned short value, unsigned long offset) { - void *address = priv->nec7210_priv.iobase + offset; + void *address = priv->nec7210_priv.mmiobase + offset; unsigned long flags; spinlock_t *register_lock = &priv->nec7210_priv.register_page_lock; @@ -170,7 +166,7 @@ static inline void tnt_writeb(struct tnt4882_priv *priv, unsigned short value, u switch (priv->nec7210_priv.type) { case TNT4882: case TNT5004: - priv->io_writeb(value, address); + iowrite8(value, address); break; case NAT4882: tnt_paged_writeb(priv, value, offset - tnt_pagein_offset); @@ -183,7 +179,7 @@ static inline void tnt_writeb(struct tnt4882_priv *priv, unsigned short value, u } break; default: - priv->io_writeb(value, address); + iowrite8(value, address); break; } spin_unlock_irqrestore(register_lock, flags); @@ -288,7 +284,7 @@ static int drain_fifo_words(struct tnt4882_priv *tnt_priv, uint8_t *buffer, int while (fifo_word_available(tnt_priv) && count + 2 <= num_bytes) { short word; - word = tnt_priv->io_readw(nec_priv->iobase + FIFOB); + word = ioread16(nec_priv->mmiobase + FIFOB); buffer[count++] = word & 0xff; buffer[count++] = (word >> 8) & 0xff; } @@ -573,7 +569,7 @@ static int generic_write(gpib_board_t *board, uint8_t *buffer, size_t length, word = buffer[count++] & 0xff; if (count < length) word |= (buffer[count++] << 8) & 0xff00; - tnt_priv->io_writew(word, nec_priv->iobase + FIFOB); + iowrite16(word, nec_priv->mmiobase + FIFOB); } // avoid unnecessary HR_NFF interrupts // tnt_priv->imr3_bits |= HR_NFF; @@ -1269,10 +1265,6 @@ int ni_pci_attach(gpib_board_t *board, const gpib_board_config_t *config) if (tnt4882_allocate_private(board)) return -ENOMEM; tnt_priv = board->private_data; - tnt_priv->io_writeb = writeb_wrapper; - tnt_priv->io_readb = readb_wrapper; - tnt_priv->io_writew = writew_wrapper; - tnt_priv->io_readw = readw_wrapper; nec_priv = &tnt_priv->nec7210_priv; nec_priv->type = TNT4882; nec_priv->read_byte = nec7210_locking_iomem_read_byte; @@ -1324,7 +1316,7 @@ int ni_pci_attach(gpib_board_t *board, const gpib_board_config_t *config) return retval; } - nec_priv->iobase = tnt_priv->mite->daq_io_addr; + nec_priv->mmiobase = tnt_priv->mite->daq_io_addr; // get irq if (request_irq(mite_irq(tnt_priv->mite), tnt4882_interrupt, isr_flags, @@ -1359,7 +1351,7 @@ void ni_pci_detach(gpib_board_t *board) if (tnt_priv) { nec_priv = &tnt_priv->nec7210_priv; - if (nec_priv->iobase) + if (nec_priv->mmiobase) tnt4882_board_reset(tnt_priv, board); if (tnt_priv->irq) free_irq(tnt_priv->irq, board); @@ -1400,7 +1392,7 @@ static int ni_isa_attach_common(gpib_board_t *board, const gpib_board_config_t * struct tnt4882_priv *tnt_priv; struct nec7210_priv *nec_priv; int isr_flags = 0; - void *iobase; + u32 iobase; int irq; board->status = 0; @@ -1408,10 +1400,6 @@ static int ni_isa_attach_common(gpib_board_t *board, const gpib_board_config_t * if (tnt4882_allocate_private(board)) return -ENOMEM; tnt_priv = board->private_data; - tnt_priv->io_writeb = outb_wrapper; - tnt_priv->io_readb = inb_wrapper; - tnt_priv->io_writew = outw_wrapper; - tnt_priv->io_readw = inw_wrapper; nec_priv = &tnt_priv->nec7210_priv; nec_priv->type = chipset; nec_priv->read_byte = nec7210_locking_ioport_read_byte; @@ -1427,18 +1415,20 @@ static int ni_isa_attach_common(gpib_board_t *board, const gpib_board_config_t * if (retval < 0) return retval; tnt_priv->pnp_dev = dev; - iobase = (void *)(pnp_port_start(dev, 0)); + iobase = pnp_port_start(dev, 0); irq = pnp_irq(dev, 0); } else { iobase = config->ibbase; irq = config->ibirq; } // allocate ioports - if (!request_region((unsigned long)(iobase), atgpib_iosize, "atgpib")) { + if (!request_region(iobase, atgpib_iosize, "atgpib")) { pr_err("tnt4882: failed to allocate ioports\n"); return -1; } - nec_priv->iobase = iobase; + nec_priv->mmiobase = ioport_map(iobase, atgpib_iosize); + if (!nec_priv->mmiobase) + return -1; // get irq if (request_irq(irq, tnt4882_interrupt, isr_flags, "atgpib", board)) { @@ -1478,8 +1468,10 @@ void ni_isa_detach(gpib_board_t *board) tnt4882_board_reset(tnt_priv, board); if (tnt_priv->irq) free_irq(tnt_priv->irq, board); + if (nec_priv->mmiobase) + ioport_unmap(nec_priv->mmiobase); if (nec_priv->iobase) - release_region((unsigned long)(nec_priv->iobase), atgpib_iosize); + release_region(nec_priv->iobase, atgpib_iosize); if (tnt_priv->pnp_dev) pnp_device_detach(tnt_priv->pnp_dev); } @@ -1817,10 +1809,6 @@ int ni_pcmcia_attach(gpib_board_t *board, const gpib_board_config_t *config) if (tnt4882_allocate_private(board)) return -ENOMEM; tnt_priv = board->private_data; - tnt_priv->io_writeb = outb_wrapper; - tnt_priv->io_readb = inb_wrapper; - tnt_priv->io_writew = outw_wrapper; - tnt_priv->io_readw = inw_wrapper; nec_priv = &tnt_priv->nec7210_priv; nec_priv->type = TNT4882; nec_priv->read_byte = nec7210_locking_ioport_read_byte; @@ -1835,7 +1823,10 @@ int ni_pcmcia_attach(gpib_board_t *board, const gpib_board_config_t *config) return -EIO; } - nec_priv->iobase = (void *)(unsigned long)curr_dev->resource[0]->start; + nec_priv->mmiobase = ioport_map(curr_dev->resource[0]->start, + resource_size(curr_dev->resource[0])); + if (!nec_priv->mmiobase) + return -1; // get irq if (request_irq(curr_dev->irq, tnt4882_interrupt, isr_flags, "tnt4882", board)) { @@ -1860,9 +1851,11 @@ void ni_pcmcia_detach(gpib_board_t *board) nec_priv = &tnt_priv->nec7210_priv; if (tnt_priv->irq) free_irq(tnt_priv->irq, board); + if (nec_priv->mmiobase) + ioport_unmap(nec_priv->mmiobase); if (nec_priv->iobase) { tnt4882_board_reset(tnt_priv, board); - release_region((unsigned long)nec_priv->iobase, pcmcia_gpib_iosize); + release_region(nec_priv->iobase, pcmcia_gpib_iosize); } } tnt4882_free_private(board); diff --git a/drivers/staging/iio/frequency/ad9832.c b/drivers/staging/iio/frequency/ad9832.c index 492612e8f8ba..140ee4f9c137 100644 --- a/drivers/staging/iio/frequency/ad9832.c +++ b/drivers/staging/iio/frequency/ad9832.c @@ -158,7 +158,7 @@ static int ad9832_write_frequency(struct ad9832_state *st, static int ad9832_write_phase(struct ad9832_state *st, unsigned long addr, unsigned long phase) { - if (phase > BIT(AD9832_PHASE_BITS)) + if (phase >= BIT(AD9832_PHASE_BITS)) return -EINVAL; st->phase_data[0] = cpu_to_be16((AD9832_CMD_PHA8BITSW << CMD_SHIFT) | diff --git a/drivers/staging/iio/frequency/ad9834.c b/drivers/staging/iio/frequency/ad9834.c index 47e7d7e6d920..6e99e008c5f4 100644 --- a/drivers/staging/iio/frequency/ad9834.c +++ b/drivers/staging/iio/frequency/ad9834.c @@ -131,7 +131,7 @@ static int ad9834_write_frequency(struct ad9834_state *st, static int ad9834_write_phase(struct ad9834_state *st, unsigned long addr, unsigned long phase) { - if (phase > BIT(AD9834_PHASE_BITS)) + if (phase >= BIT(AD9834_PHASE_BITS)) return -EINVAL; st->data = cpu_to_be16(addr | phase); diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c index fab11b98ca49..5ab4ce4daaeb 100644 --- a/drivers/thermal/thermal_of.c +++ b/drivers/thermal/thermal_of.c @@ -160,6 +160,7 @@ static struct device_node *of_thermal_zone_find(struct device_node *sensor, int return ERR_PTR(ret); } + of_node_put(sensor_specs.np); if ((sensor == sensor_specs.np) && id == (sensor_specs.args_count ? sensor_specs.args[0] : 0)) { pr_debug("sensor %pOFn id=%d belongs to %pOFn\n", sensor, id, child); diff --git a/drivers/thermal/thermal_thresholds.c b/drivers/thermal/thermal_thresholds.c index d9b2a0bb44fc..38f5fd0e8930 100644 --- a/drivers/thermal/thermal_thresholds.c +++ b/drivers/thermal/thermal_thresholds.c @@ -69,58 +69,60 @@ static struct user_threshold *__thermal_thresholds_find(const struct list_head * return NULL; } -static bool __thermal_threshold_is_crossed(struct user_threshold *threshold, int temperature, - int last_temperature, int direction, - int *low, int *high) +static bool thermal_thresholds_handle_raising(struct list_head *thresholds, int temperature, + int last_temperature) { + struct user_threshold *t; - if (temperature >= threshold->temperature) { - if (threshold->temperature > *low && - THERMAL_THRESHOLD_WAY_DOWN & threshold->direction) - *low = threshold->temperature; + list_for_each_entry(t, thresholds, list_node) { - if (last_temperature < threshold->temperature && - threshold->direction & direction) - return true; - } else { - if (threshold->temperature < *high && THERMAL_THRESHOLD_WAY_UP - & threshold->direction) - *high = threshold->temperature; + if (!(t->direction & THERMAL_THRESHOLD_WAY_UP)) + continue; - if (last_temperature >= threshold->temperature && - threshold->direction & direction) + if (temperature >= t->temperature && + last_temperature < t->temperature) return true; } return false; } -static bool thermal_thresholds_handle_raising(struct list_head *thresholds, int temperature, - int last_temperature, int *low, int *high) +static bool thermal_thresholds_handle_dropping(struct list_head *thresholds, int temperature, + int last_temperature) { struct user_threshold *t; - list_for_each_entry(t, thresholds, list_node) { - if (__thermal_threshold_is_crossed(t, temperature, last_temperature, - THERMAL_THRESHOLD_WAY_UP, low, high)) + list_for_each_entry_reverse(t, thresholds, list_node) { + + if (!(t->direction & THERMAL_THRESHOLD_WAY_DOWN)) + continue; + + if (temperature <= t->temperature && + last_temperature > t->temperature) return true; } return false; } -static bool thermal_thresholds_handle_dropping(struct list_head *thresholds, int temperature, - int last_temperature, int *low, int *high) +static void thermal_threshold_find_boundaries(struct list_head *thresholds, int temperature, + int *low, int *high) { struct user_threshold *t; - list_for_each_entry_reverse(t, thresholds, list_node) { - if (__thermal_threshold_is_crossed(t, temperature, last_temperature, - THERMAL_THRESHOLD_WAY_DOWN, low, high)) - return true; + list_for_each_entry(t, thresholds, list_node) { + if (temperature < t->temperature && + (t->direction & THERMAL_THRESHOLD_WAY_UP) && + *high > t->temperature) + *high = t->temperature; } - return false; + list_for_each_entry_reverse(t, thresholds, list_node) { + if (temperature > t->temperature && + (t->direction & THERMAL_THRESHOLD_WAY_DOWN) && + *low < t->temperature) + *low = t->temperature; + } } void thermal_thresholds_handle(struct thermal_zone_device *tz, int *low, int *high) @@ -132,6 +134,8 @@ void thermal_thresholds_handle(struct thermal_zone_device *tz, int *low, int *hi lockdep_assert_held(&tz->lock); + thermal_threshold_find_boundaries(thresholds, temperature, low, high); + /* * We need a second update in order to detect a threshold being crossed */ @@ -151,12 +155,12 @@ void thermal_thresholds_handle(struct thermal_zone_device *tz, int *low, int *hi * - decreased : thresholds are crossed the way down */ if (temperature > last_temperature) { - if (thermal_thresholds_handle_raising(thresholds, temperature, - last_temperature, low, high)) + if (thermal_thresholds_handle_raising(thresholds, + temperature, last_temperature)) thermal_notify_threshold_up(tz); } else { - if (thermal_thresholds_handle_dropping(thresholds, temperature, - last_temperature, low, high)) + if (thermal_thresholds_handle_dropping(thresholds, + temperature, last_temperature)) thermal_notify_threshold_down(tz); } } diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index 1257dd3ce7e6..f3a2264e012b 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -1520,6 +1520,14 @@ static struct pci_device_id nhi_ids[] = { .driver_data = (kernel_ulong_t)&icl_nhi_ops }, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_LNL_NHI1), .driver_data = (kernel_ulong_t)&icl_nhi_ops }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_PTL_M_NHI0), + .driver_data = (kernel_ulong_t)&icl_nhi_ops }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_PTL_M_NHI1), + .driver_data = (kernel_ulong_t)&icl_nhi_ops }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_PTL_P_NHI0), + .driver_data = (kernel_ulong_t)&icl_nhi_ops }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_PTL_P_NHI1), + .driver_data = (kernel_ulong_t)&icl_nhi_ops }, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_80G_NHI) }, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_40G_NHI) }, diff --git a/drivers/thunderbolt/nhi.h b/drivers/thunderbolt/nhi.h index 7a07c7c1a9c2..16744f25a9a0 100644 --- a/drivers/thunderbolt/nhi.h +++ b/drivers/thunderbolt/nhi.h @@ -92,6 +92,10 @@ extern const struct tb_nhi_ops icl_nhi_ops; #define PCI_DEVICE_ID_INTEL_RPL_NHI1 0xa76d #define PCI_DEVICE_ID_INTEL_LNL_NHI0 0xa833 #define PCI_DEVICE_ID_INTEL_LNL_NHI1 0xa834 +#define PCI_DEVICE_ID_INTEL_PTL_M_NHI0 0xe333 +#define PCI_DEVICE_ID_INTEL_PTL_M_NHI1 0xe334 +#define PCI_DEVICE_ID_INTEL_PTL_P_NHI0 0xe433 +#define PCI_DEVICE_ID_INTEL_PTL_P_NHI1 0xe434 #define PCI_CLASS_SERIAL_USB_USB4 0x0c0340 diff --git a/drivers/thunderbolt/retimer.c b/drivers/thunderbolt/retimer.c index 89d2919d0193..eeb64433ebbc 100644 --- a/drivers/thunderbolt/retimer.c +++ b/drivers/thunderbolt/retimer.c @@ -103,6 +103,7 @@ static int tb_retimer_nvm_add(struct tb_retimer *rt) err_nvm: dev_dbg(&rt->dev, "NVM upgrade disabled\n"); + rt->no_nvm_upgrade = true; if (!IS_ERR(nvm)) tb_nvm_free(nvm); @@ -182,8 +183,6 @@ static ssize_t nvm_authenticate_show(struct device *dev, if (!rt->nvm) ret = -EAGAIN; - else if (rt->no_nvm_upgrade) - ret = -EOPNOTSUPP; else ret = sysfs_emit(buf, "%#x\n", rt->auth_status); @@ -323,8 +322,6 @@ static ssize_t nvm_version_show(struct device *dev, if (!rt->nvm) ret = -EAGAIN; - else if (rt->no_nvm_upgrade) - ret = -EOPNOTSUPP; else ret = sysfs_emit(buf, "%x.%x\n", rt->nvm->major, rt->nvm->minor); @@ -342,6 +339,19 @@ static ssize_t vendor_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(vendor); +static umode_t retimer_is_visible(struct kobject *kobj, struct attribute *attr, + int n) +{ + struct device *dev = kobj_to_dev(kobj); + struct tb_retimer *rt = tb_to_retimer(dev); + + if (attr == &dev_attr_nvm_authenticate.attr || + attr == &dev_attr_nvm_version.attr) + return rt->no_nvm_upgrade ? 0 : attr->mode; + + return attr->mode; +} + static struct attribute *retimer_attrs[] = { &dev_attr_device.attr, &dev_attr_nvm_authenticate.attr, @@ -351,6 +361,7 @@ static struct attribute *retimer_attrs[] = { }; static const struct attribute_group retimer_group = { + .is_visible = retimer_is_visible, .attrs = retimer_attrs, }; diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index 4f777788e917..a7c6919fbf97 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -2059,6 +2059,37 @@ static void tb_exit_redrive(struct tb_port *port) } } +static void tb_switch_enter_redrive(struct tb_switch *sw) +{ + struct tb_port *port; + + tb_switch_for_each_port(sw, port) + tb_enter_redrive(port); +} + +/* + * Called during system and runtime suspend to forcefully exit redrive + * mode without querying whether the resource is available. + */ +static void tb_switch_exit_redrive(struct tb_switch *sw) +{ + struct tb_port *port; + + if (!(sw->quirks & QUIRK_KEEP_POWER_IN_DP_REDRIVE)) + return; + + tb_switch_for_each_port(sw, port) { + if (!tb_port_is_dpin(port)) + continue; + + if (port->redrive) { + port->redrive = false; + pm_runtime_put(&sw->dev); + tb_port_dbg(port, "exit redrive mode\n"); + } + } +} + static void tb_dp_resource_unavailable(struct tb *tb, struct tb_port *port) { struct tb_port *in, *out; @@ -2909,6 +2940,7 @@ static int tb_start(struct tb *tb, bool reset) tb_create_usb3_tunnels(tb->root_switch); /* Add DP IN resources for the root switch */ tb_add_dp_resources(tb->root_switch); + tb_switch_enter_redrive(tb->root_switch); /* Make the discovered switches available to the userspace */ device_for_each_child(&tb->root_switch->dev, NULL, tb_scan_finalize_switch); @@ -2924,6 +2956,7 @@ static int tb_suspend_noirq(struct tb *tb) tb_dbg(tb, "suspending...\n"); tb_disconnect_and_release_dp(tb); + tb_switch_exit_redrive(tb->root_switch); tb_switch_suspend(tb->root_switch, false); tcm->hotplug_active = false; /* signal tb_handle_hotplug to quit */ tb_dbg(tb, "suspend finished\n"); @@ -3016,6 +3049,7 @@ static int tb_resume_noirq(struct tb *tb) tb_dbg(tb, "tunnels restarted, sleeping for 100ms\n"); msleep(100); } + tb_switch_enter_redrive(tb->root_switch); /* Allow tb_handle_hotplug to progress events */ tcm->hotplug_active = true; tb_dbg(tb, "resume finished\n"); @@ -3079,6 +3113,12 @@ static int tb_runtime_suspend(struct tb *tb) struct tb_cm *tcm = tb_priv(tb); mutex_lock(&tb->lock); + /* + * The below call only releases DP resources to allow exiting and + * re-entering redrive mode. + */ + tb_disconnect_and_release_dp(tb); + tb_switch_exit_redrive(tb->root_switch); tb_switch_suspend(tb->root_switch, true); tcm->hotplug_active = false; mutex_unlock(&tb->lock); @@ -3110,6 +3150,7 @@ static int tb_runtime_resume(struct tb *tb) tb_restore_children(tb->root_switch); list_for_each_entry_safe(tunnel, n, &tcm->tunnel_list, list) tb_tunnel_restart(tunnel); + tb_switch_enter_redrive(tb->root_switch); tcm->hotplug_active = true; mutex_unlock(&tb->lock); diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index 5f9f06911795..68baf75bdadc 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -812,6 +812,9 @@ int serial8250_register_8250_port(const struct uart_8250_port *up) uart->dl_write = up->dl_write; if (uart->port.type != PORT_8250_CIR) { + if (uart_console_registered(&uart->port)) + pm_runtime_get_sync(uart->port.dev); + if (serial8250_isa_config != NULL) serial8250_isa_config(0, &uart->port, &uart->capabilities); diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index 17f70e4bee43..9c59ec128bb4 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -2692,7 +2692,7 @@ static void imx_uart_enable_wakeup(struct imx_port *sport, bool on) { u32 ucr3; - uart_port_lock(&sport->port); + uart_port_lock_irq(&sport->port); ucr3 = imx_uart_readl(sport, UCR3); if (on) { @@ -2714,7 +2714,7 @@ static void imx_uart_enable_wakeup(struct imx_port *sport, bool on) imx_uart_writel(sport, ucr1, UCR1); } - uart_port_unlock(&sport->port); + uart_port_unlock_irq(&sport->port); } static int imx_uart_suspend_noirq(struct device *dev) diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c index 7dc254546075..1ec5d8c3aef8 100644 --- a/drivers/tty/serial/stm32-usart.c +++ b/drivers/tty/serial/stm32-usart.c @@ -1051,14 +1051,14 @@ static void stm32_usart_break_ctl(struct uart_port *port, int break_state) const struct stm32_usart_offsets *ofs = &stm32_port->info->ofs; unsigned long flags; - spin_lock_irqsave(&port->lock, flags); + uart_port_lock_irqsave(port, &flags); if (break_state) stm32_usart_set_bits(port, ofs->rqr, USART_RQR_SBKRQ); else stm32_usart_clr_bits(port, ofs->rqr, USART_RQR_SBKRQ); - spin_unlock_irqrestore(&port->lock, flags); + uart_port_unlock_irqrestore(port, flags); } static int stm32_usart_startup(struct uart_port *port) diff --git a/drivers/ufs/core/ufshcd-priv.h b/drivers/ufs/core/ufshcd-priv.h index 9ffd94ddf8c7..786f20ef2238 100644 --- a/drivers/ufs/core/ufshcd-priv.h +++ b/drivers/ufs/core/ufshcd-priv.h @@ -237,12 +237,6 @@ static inline void ufshcd_vops_config_scaling_param(struct ufs_hba *hba, hba->vops->config_scaling_param(hba, p, data); } -static inline void ufshcd_vops_reinit_notify(struct ufs_hba *hba) -{ - if (hba->vops && hba->vops->reinit_notify) - hba->vops->reinit_notify(hba); -} - static inline int ufshcd_vops_mcq_config_resource(struct ufs_hba *hba) { if (hba->vops && hba->vops->mcq_config_resource) diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 8a01e4393159..9c26e8767515 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -8858,7 +8858,6 @@ static int ufshcd_probe_hba(struct ufs_hba *hba, bool init_dev_params) ufshcd_device_reset(hba); ufs_put_device_desc(hba); ufshcd_hba_stop(hba); - ufshcd_vops_reinit_notify(hba); ret = ufshcd_hba_enable(hba); if (ret) { dev_err(hba->dev, "Host controller enable failed\n"); @@ -10591,14 +10590,17 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq) } /* - * Set the default power management level for runtime and system PM. + * Set the default power management level for runtime and system PM if + * not set by the host controller drivers. * Default power saving mode is to keep UFS link in Hibern8 state * and UFS device in sleep state. */ - hba->rpm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state( + if (!hba->rpm_lvl) + hba->rpm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state( UFS_SLEEP_PWR_MODE, UIC_LINK_HIBERN8_STATE); - hba->spm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state( + if (!hba->spm_lvl) + hba->spm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state( UFS_SLEEP_PWR_MODE, UIC_LINK_HIBERN8_STATE); diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c index 68040b2ab5f8..91e94fe990b4 100644 --- a/drivers/ufs/host/ufs-qcom.c +++ b/drivers/ufs/host/ufs-qcom.c @@ -368,6 +368,11 @@ static int ufs_qcom_power_up_sequence(struct ufs_hba *hba) if (ret) return ret; + if (phy->power_count) { + phy_power_off(phy); + phy_exit(phy); + } + /* phy initialization - calibrate the phy */ ret = phy_init(phy); if (ret) { @@ -866,6 +871,7 @@ static u32 ufs_qcom_get_ufs_hci_version(struct ufs_hba *hba) */ static void ufs_qcom_advertise_quirks(struct ufs_hba *hba) { + const struct ufs_qcom_drvdata *drvdata = of_device_get_match_data(hba->dev); struct ufs_qcom_host *host = ufshcd_get_variant(hba); if (host->hw_ver.major == 0x2) @@ -874,9 +880,8 @@ static void ufs_qcom_advertise_quirks(struct ufs_hba *hba) if (host->hw_ver.major > 0x3) hba->quirks |= UFSHCD_QUIRK_REINIT_AFTER_MAX_GEAR_SWITCH; - if (of_device_is_compatible(hba->dev->of_node, "qcom,sm8550-ufshc") || - of_device_is_compatible(hba->dev->of_node, "qcom,sm8650-ufshc")) - hba->quirks |= UFSHCD_QUIRK_BROKEN_LSDBS_CAP; + if (drvdata && drvdata->quirks) + hba->quirks |= drvdata->quirks; } static void ufs_qcom_set_phy_gear(struct ufs_qcom_host *host) @@ -1064,6 +1069,7 @@ static int ufs_qcom_init(struct ufs_hba *hba) struct device *dev = hba->dev; struct ufs_qcom_host *host; struct ufs_clk_info *clki; + const struct ufs_qcom_drvdata *drvdata = of_device_get_match_data(hba->dev); host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL); if (!host) @@ -1143,6 +1149,9 @@ static int ufs_qcom_init(struct ufs_hba *hba) dev_warn(dev, "%s: failed to configure the testbus %d\n", __func__, err); + if (drvdata && drvdata->no_phy_retention) + hba->spm_lvl = UFS_PM_LVL_5; + return 0; out_variant_clear: @@ -1579,13 +1588,6 @@ static void ufs_qcom_config_scaling_param(struct ufs_hba *hba, } #endif -static void ufs_qcom_reinit_notify(struct ufs_hba *hba) -{ - struct ufs_qcom_host *host = ufshcd_get_variant(hba); - - phy_power_off(host->generic_phy); -} - /* Resources */ static const struct ufshcd_res_info ufs_res_info[RES_MAX] = { {.name = "ufs_mem",}, @@ -1825,7 +1827,6 @@ static const struct ufs_hba_variant_ops ufs_hba_qcom_vops = { .device_reset = ufs_qcom_device_reset, .config_scaling_param = ufs_qcom_config_scaling_param, .program_key = ufs_qcom_ice_program_key, - .reinit_notify = ufs_qcom_reinit_notify, .mcq_config_resource = ufs_qcom_mcq_config_resource, .get_hba_mac = ufs_qcom_get_hba_mac, .op_runtime_config = ufs_qcom_op_runtime_config, @@ -1868,9 +1869,15 @@ static void ufs_qcom_remove(struct platform_device *pdev) platform_device_msi_free_irqs_all(hba->dev); } +static const struct ufs_qcom_drvdata ufs_qcom_sm8550_drvdata = { + .quirks = UFSHCD_QUIRK_BROKEN_LSDBS_CAP, + .no_phy_retention = true, +}; + static const struct of_device_id ufs_qcom_of_match[] __maybe_unused = { { .compatible = "qcom,ufshc" }, - { .compatible = "qcom,sm8550-ufshc" }, + { .compatible = "qcom,sm8550-ufshc", .data = &ufs_qcom_sm8550_drvdata }, + { .compatible = "qcom,sm8650-ufshc", .data = &ufs_qcom_sm8550_drvdata }, {}, }; MODULE_DEVICE_TABLE(of, ufs_qcom_of_match); diff --git a/drivers/ufs/host/ufs-qcom.h b/drivers/ufs/host/ufs-qcom.h index b9de170983c9..919f53682beb 100644 --- a/drivers/ufs/host/ufs-qcom.h +++ b/drivers/ufs/host/ufs-qcom.h @@ -217,6 +217,11 @@ struct ufs_qcom_host { bool esi_enabled; }; +struct ufs_qcom_drvdata { + enum ufshcd_quirks quirks; + bool no_phy_retention; +}; + static inline u32 ufs_qcom_get_debug_reg_offset(struct ufs_qcom_host *host, u32 reg) { diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c index f2801700be8e..1a7fc638213e 100644 --- a/drivers/usb/chipidea/ci_hdrc_imx.c +++ b/drivers/usb/chipidea/ci_hdrc_imx.c @@ -370,25 +370,29 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev) data->pinctrl = devm_pinctrl_get(dev); if (PTR_ERR(data->pinctrl) == -ENODEV) data->pinctrl = NULL; - else if (IS_ERR(data->pinctrl)) - return dev_err_probe(dev, PTR_ERR(data->pinctrl), + else if (IS_ERR(data->pinctrl)) { + ret = dev_err_probe(dev, PTR_ERR(data->pinctrl), "pinctrl get failed\n"); + goto err_put; + } data->hsic_pad_regulator = devm_regulator_get_optional(dev, "hsic"); if (PTR_ERR(data->hsic_pad_regulator) == -ENODEV) { /* no pad regulator is needed */ data->hsic_pad_regulator = NULL; - } else if (IS_ERR(data->hsic_pad_regulator)) - return dev_err_probe(dev, PTR_ERR(data->hsic_pad_regulator), + } else if (IS_ERR(data->hsic_pad_regulator)) { + ret = dev_err_probe(dev, PTR_ERR(data->hsic_pad_regulator), "Get HSIC pad regulator error\n"); + goto err_put; + } if (data->hsic_pad_regulator) { ret = regulator_enable(data->hsic_pad_regulator); if (ret) { dev_err(dev, "Failed to enable HSIC pad regulator\n"); - return ret; + goto err_put; } } } @@ -402,13 +406,14 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev) dev_err(dev, "pinctrl_hsic_idle lookup failed, err=%ld\n", PTR_ERR(pinctrl_hsic_idle)); - return PTR_ERR(pinctrl_hsic_idle); + ret = PTR_ERR(pinctrl_hsic_idle); + goto err_put; } ret = pinctrl_select_state(data->pinctrl, pinctrl_hsic_idle); if (ret) { dev_err(dev, "hsic_idle select failed, err=%d\n", ret); - return ret; + goto err_put; } data->pinctrl_hsic_active = pinctrl_lookup_state(data->pinctrl, @@ -417,7 +422,8 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev) dev_err(dev, "pinctrl_hsic_active lookup failed, err=%ld\n", PTR_ERR(data->pinctrl_hsic_active)); - return PTR_ERR(data->pinctrl_hsic_active); + ret = PTR_ERR(data->pinctrl_hsic_active); + goto err_put; } } @@ -527,6 +533,8 @@ disable_hsic_regulator: if (pdata.flags & CI_HDRC_PMQOS) cpu_latency_qos_remove_request(&data->pm_qos_req); data->ci_pdev = NULL; +err_put: + put_device(data->usbmisc_data->dev); return ret; } @@ -551,6 +559,7 @@ static void ci_hdrc_imx_remove(struct platform_device *pdev) if (data->hsic_pad_regulator) regulator_disable(data->hsic_pad_regulator); } + put_device(data->usbmisc_data->dev); } static void ci_hdrc_imx_shutdown(struct platform_device *pdev) diff --git a/drivers/usb/class/usblp.c b/drivers/usb/class/usblp.c index 5a2e43331064..ff1a941fd2ed 100644 --- a/drivers/usb/class/usblp.c +++ b/drivers/usb/class/usblp.c @@ -1337,11 +1337,12 @@ static int usblp_set_protocol(struct usblp *usblp, int protocol) if (protocol < USBLP_FIRST_PROTOCOL || protocol > USBLP_LAST_PROTOCOL) return -EINVAL; + alts = usblp->protocol[protocol].alt_setting; + if (alts < 0) + return -EINVAL; + /* Don't unnecessarily set the interface if there's a single alt. */ if (usblp->intf->num_altsetting > 1) { - alts = usblp->protocol[protocol].alt_setting; - if (alts < 0) - return -EINVAL; r = usb_set_interface(usblp->dev, usblp->ifnum, alts); if (r < 0) { printk(KERN_ERR "usblp: can't set desired altsetting %d on interface %d\n", diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 4b93c0bd1d4b..21ac9b464696 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -2663,13 +2663,13 @@ int usb_new_device(struct usb_device *udev) err = sysfs_create_link(&udev->dev.kobj, &port_dev->dev.kobj, "port"); if (err) - goto fail; + goto out_del_dev; err = sysfs_create_link(&port_dev->dev.kobj, &udev->dev.kobj, "device"); if (err) { sysfs_remove_link(&udev->dev.kobj, "port"); - goto fail; + goto out_del_dev; } if (!test_and_set_bit(port1, hub->child_usage_bits)) @@ -2683,6 +2683,8 @@ int usb_new_device(struct usb_device *udev) pm_runtime_put_sync_autosuspend(&udev->dev); return err; +out_del_dev: + device_del(&udev->dev); fail: usb_set_device_state(udev, USB_STATE_NOTATTACHED); pm_runtime_disable(&udev->dev); diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c index 45d7af00f8d1..e857e532b35a 100644 --- a/drivers/usb/core/port.c +++ b/drivers/usb/core/port.c @@ -453,10 +453,11 @@ static int usb_port_runtime_suspend(struct device *dev) static void usb_port_shutdown(struct device *dev) { struct usb_port *port_dev = to_usb_port(dev); + struct usb_device *udev = port_dev->child; - if (port_dev->child) { - usb_disable_usb2_hardware_lpm(port_dev->child); - usb_unlocked_disable_lpm(port_dev->child); + if (udev && !udev->port_is_suspended) { + usb_disable_usb2_hardware_lpm(udev); + usb_unlocked_disable_lpm(udev); } } diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index ee73789326bc..f11570c8ffd0 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -464,6 +464,7 @@ #define DWC3_DCTL_TRGTULST_SS_INACT (DWC3_DCTL_TRGTULST(6)) /* These apply for core versions 1.94a and later */ +#define DWC3_DCTL_NYET_THRES_MASK (0xf << 20) #define DWC3_DCTL_NYET_THRES(n) (((n) & 0xf) << 20) #define DWC3_DCTL_KEEP_CONNECT BIT(19) diff --git a/drivers/usb/dwc3/dwc3-am62.c b/drivers/usb/dwc3/dwc3-am62.c index 5e3d1741701f..7d43da5f2897 100644 --- a/drivers/usb/dwc3/dwc3-am62.c +++ b/drivers/usb/dwc3/dwc3-am62.c @@ -309,6 +309,7 @@ static void dwc3_ti_remove(struct platform_device *pdev) pm_runtime_put_sync(dev); pm_runtime_disable(dev); + pm_runtime_dont_use_autosuspend(dev); pm_runtime_set_suspended(dev); } diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 83dc7304d701..31a654c6f15b 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -4195,8 +4195,10 @@ static void dwc3_gadget_conndone_interrupt(struct dwc3 *dwc) WARN_ONCE(DWC3_VER_IS_PRIOR(DWC3, 240A) && dwc->has_lpm_erratum, "LPM Erratum not available on dwc3 revisions < 2.40a\n"); - if (dwc->has_lpm_erratum && !DWC3_VER_IS_PRIOR(DWC3, 240A)) + if (dwc->has_lpm_erratum && !DWC3_VER_IS_PRIOR(DWC3, 240A)) { + reg &= ~DWC3_DCTL_NYET_THRES_MASK; reg |= DWC3_DCTL_NYET_THRES(dwc->lpm_nyet_threshold); + } dwc3_gadget_dctl_write_safe(dwc, reg); } else { diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig index 566ff0b1282a..76521555e3c1 100644 --- a/drivers/usb/gadget/Kconfig +++ b/drivers/usb/gadget/Kconfig @@ -211,6 +211,8 @@ config USB_F_MIDI config USB_F_MIDI2 tristate + select SND_UMP + select SND_UMP_LEGACY_RAWMIDI config USB_F_HID tristate @@ -445,8 +447,6 @@ config USB_CONFIGFS_F_MIDI2 depends on USB_CONFIGFS depends on SND select USB_LIBCOMPOSITE - select SND_UMP - select SND_UMP_LEGACY_RAWMIDI select USB_F_MIDI2 help The MIDI 2.0 function driver provides the generic emulated diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 6499a88d346c..fba2a56dae97 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -827,11 +827,15 @@ static ssize_t gadget_string_s_store(struct config_item *item, const char *page, { struct gadget_string *string = to_gadget_string(item); int size = min(sizeof(string->string), len + 1); + ssize_t cpy_len; if (len > USB_MAX_STRING_LEN) return -EINVAL; - return strscpy(string->string, page, size); + cpy_len = strscpy(string->string, page, size); + if (cpy_len > 0 && string->string[cpy_len - 1] == '\n') + string->string[cpy_len - 1] = 0; + return len; } CONFIGFS_ATTR(gadget_string_, s); diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index ad79eb0f729b..2dea9e42a0f8 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -2285,7 +2285,7 @@ static int functionfs_bind(struct ffs_data *ffs, struct usb_composite_dev *cdev) struct usb_gadget_strings **lang; int first_id; - if (WARN_ON(ffs->state != FFS_ACTIVE + if ((ffs->state != FFS_ACTIVE || test_and_set_bit(FFS_FL_BOUND, &ffs->flags))) return -EBADFD; diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c index ce5b77f89190..9b324821c93b 100644 --- a/drivers/usb/gadget/function/f_uac2.c +++ b/drivers/usb/gadget/function/f_uac2.c @@ -1185,6 +1185,7 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn) uac2->as_in_alt = 0; } + std_ac_if_desc.bNumEndpoints = 0; if (FUOUT_EN(uac2_opts) || FUIN_EN(uac2_opts)) { uac2->int_ep = usb_ep_autoconfig(gadget, &fs_ep_int_desc); if (!uac2->int_ep) { diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index 53d9fc41acc5..bc143a86c2dd 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -1420,6 +1420,10 @@ void gserial_disconnect(struct gserial *gser) /* REVISIT as above: how best to track this? */ port->port_line_coding = gser->port_line_coding; + /* disable endpoints, aborting down any active I/O */ + usb_ep_disable(gser->out); + usb_ep_disable(gser->in); + port->port_usb = NULL; gser->ioport = NULL; if (port->port.count > 0) { @@ -1431,10 +1435,6 @@ void gserial_disconnect(struct gserial *gser) spin_unlock(&port->port_lock); spin_unlock_irqrestore(&serial_port_lock, flags); - /* disable endpoints, aborting down any active I/O */ - usb_ep_disable(gser->out); - usb_ep_disable(gser->in); - /* finally, free any unused/unusable I/O buffers */ spin_lock_irqsave(&port->port_lock, flags); if (port->port.count == 0) diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 15db90c54a45..92703efda1f7 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -436,7 +436,7 @@ int xhci_ring_expansion(struct xhci_hcd *xhci, struct xhci_ring *ring, goto free_segments; } - xhci_link_rings(xhci, ring, &new_ring); + xhci_link_rings(xhci, &new_ring, ring); trace_xhci_ring_expansion(ring); xhci_dbg_trace(xhci, trace_xhci_dbg_ring_expansion, "ring expansion succeed, now has %d segments", diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index e6c9006bd568..db109b570c5c 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -290,7 +290,8 @@ int xhci_plat_probe(struct platform_device *pdev, struct device *sysdev, const s hcd->tpl_support = of_usb_host_tpl_support(sysdev->of_node); - if (priv && (priv->quirks & XHCI_SKIP_PHY_INIT)) + if ((priv && (priv->quirks & XHCI_SKIP_PHY_INIT)) || + (xhci->quirks & XHCI_SKIP_PHY_INIT)) hcd->skip_phy_initialization = 1; if (priv && (priv->quirks & XHCI_SG_TRB_CACHE_SIZE_QUIRK)) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 4cf5363875c7..09b05a62375e 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1199,8 +1199,6 @@ static void xhci_handle_cmd_stop_ep(struct xhci_hcd *xhci, int slot_id, * Keep retrying until the EP starts and stops again, on * chips where this is known to help. Wait for 100ms. */ - if (!(xhci->quirks & XHCI_NEC_HOST)) - break; if (time_is_before_jiffies(ep->stop_time + msecs_to_jiffies(100))) break; fallthrough; diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index c24101f0a07a..9960ac2b10b7 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -223,6 +223,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x19CF, 0x3000) }, /* Parrot NMEA GPS Flight Recorder */ { USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */ { USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */ + { USB_DEVICE(0x1B93, 0x1013) }, /* Phoenix Contact UPS Device */ { USB_DEVICE(0x1BA4, 0x0002) }, /* Silicon Labs 358x factory default */ { USB_DEVICE(0x1BE3, 0x07A6) }, /* WAGO 750-923 USB Service Cable */ { USB_DEVICE(0x1D6F, 0x0010) }, /* Seluxit ApS RF Dongle */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 9ba5584061c8..1e2ae0c6c41c 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -621,10 +621,12 @@ static void option_instat_callback(struct urb *urb); /* MeiG Smart Technology products */ #define MEIGSMART_VENDOR_ID 0x2dee -/* MeiG Smart SRM825L based on Qualcomm 315 */ +/* MeiG Smart SRM815/SRM825L based on Qualcomm 315 */ #define MEIGSMART_PRODUCT_SRM825L 0x4d22 /* MeiG Smart SLM320 based on UNISOC UIS8910 */ #define MEIGSMART_PRODUCT_SLM320 0x4d41 +/* MeiG Smart SLM770A based on ASR1803 */ +#define MEIGSMART_PRODUCT_SLM770A 0x4d57 /* Device flags */ @@ -1395,6 +1397,12 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10aa, 0xff), /* Telit FN920C04 (MBIM) */ .driver_info = NCTRL(3) | RSVD(4) | RSVD(5) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c0, 0xff), /* Telit FE910C04 (rmnet) */ + .driver_info = RSVD(0) | NCTRL(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c4, 0xff), /* Telit FE910C04 (rmnet) */ + .driver_info = RSVD(0) | NCTRL(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c8, 0xff), /* Telit FE910C04 (rmnet) */ + .driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM), @@ -2247,6 +2255,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(2) }, { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, 0x7127, 0xff, 0x00, 0x00), .driver_info = NCTRL(2) | NCTRL(3) | NCTRL(4) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, 0x7129, 0xff, 0x00, 0x00), /* MediaTek T7XX */ + .driver_info = NCTRL(2) | NCTRL(3) | NCTRL(4) }, { USB_DEVICE(CELLIENT_VENDOR_ID, CELLIENT_PRODUCT_MEN200) }, { USB_DEVICE(CELLIENT_VENDOR_ID, CELLIENT_PRODUCT_MPL200), .driver_info = RSVD(1) | RSVD(4) }, @@ -2375,6 +2385,18 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x0116, 0xff, 0xff, 0x30) }, /* NetPrisma LCUK54-WWD for Golbal EDU */ { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x0116, 0xff, 0x00, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x0116, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010a, 0xff, 0xff, 0x30) }, /* NetPrisma LCUK54-WRD for WWAN Ready */ + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010a, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010a, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010b, 0xff, 0xff, 0x30) }, /* NetPrisma LCUK54-WWD for WWAN Ready */ + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010b, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010b, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010c, 0xff, 0xff, 0x30) }, /* NetPrisma LCUK54-WRD for WWAN Ready */ + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010c, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010c, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010d, 0xff, 0xff, 0x30) }, /* NetPrisma LCUK54-WWD for WWAN Ready */ + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010d, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010d, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(OPPO_VENDOR_ID, OPPO_PRODUCT_R11, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x40) }, @@ -2382,9 +2404,16 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, LUAT_PRODUCT_AIR720U, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SLM320, 0xff, 0, 0) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SLM770A, 0xff, 0, 0) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x60) }, + { USB_DEVICE_INTERFACE_CLASS(0x1bbb, 0x0530, 0xff), /* TCL IK512 MBIM */ + .driver_info = NCTRL(1) }, + { USB_DEVICE_INTERFACE_CLASS(0x1bbb, 0x0640, 0xff), /* TCL IK512 ECM */ + .driver_info = NCTRL(3) }, + { USB_DEVICE_INTERFACE_CLASS(0x2949, 0x8700, 0xff) }, /* Neoway N723-EA */ { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index e5ad23d86833..54f0b1c83317 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -255,6 +255,13 @@ UNUSUAL_DEV( 0x0421, 0x06aa, 0x1110, 0x1110, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_MAX_SECTORS_64 ), +/* Added by Lubomir Rintel <lkundrak@v3.sk>, a very fine chap */ +UNUSUAL_DEV( 0x0421, 0x06c2, 0x0000, 0x0406, + "Nokia", + "Nokia 208", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_MAX_SECTORS_64 ), + #ifdef NO_SDDR09 UNUSUAL_DEV( 0x0436, 0x0005, 0x0100, 0x0100, "Microtech", diff --git a/drivers/usb/typec/tcpm/maxim_contaminant.c b/drivers/usb/typec/tcpm/maxim_contaminant.c index 22163d8f9eb0..0cdda06592fd 100644 --- a/drivers/usb/typec/tcpm/maxim_contaminant.c +++ b/drivers/usb/typec/tcpm/maxim_contaminant.c @@ -135,7 +135,7 @@ static int max_contaminant_read_resistance_kohm(struct max_tcpci_chip *chip, mv = max_contaminant_read_adc_mv(chip, channel, sleep_msec, raw, true); if (mv < 0) - return ret; + return mv; /* OVP enable */ ret = regmap_update_bits(regmap, TCPC_VENDOR_CC_CTRL2, CCOVPDIS, 0); @@ -157,7 +157,7 @@ static int max_contaminant_read_resistance_kohm(struct max_tcpci_chip *chip, mv = max_contaminant_read_adc_mv(chip, channel, sleep_msec, raw, true); if (mv < 0) - return ret; + return mv; /* Disable current source */ ret = regmap_update_bits(regmap, TCPC_VENDOR_CC_CTRL2, SBURPCTRL, 0); if (ret < 0) diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index ed32583829be..24a6a4354df8 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -700,7 +700,7 @@ static int tcpci_init(struct tcpc_dev *tcpc) tcpci->alert_mask = reg; - return tcpci_write16(tcpci, TCPC_ALERT_MASK, reg); + return 0; } irqreturn_t tcpci_irq(struct tcpci *tcpci) @@ -923,22 +923,27 @@ static int tcpci_probe(struct i2c_client *client) chip->data.set_orientation = err; + chip->tcpci = tcpci_register_port(&client->dev, &chip->data); + if (IS_ERR(chip->tcpci)) + return PTR_ERR(chip->tcpci); + err = devm_request_threaded_irq(&client->dev, client->irq, NULL, _tcpci_irq, IRQF_SHARED | IRQF_ONESHOT, dev_name(&client->dev), chip); if (err < 0) - return err; + goto unregister_port; - /* - * Disable irq while registering port. If irq is configured as an edge - * irq this allow to keep track and process the irq as soon as it is enabled. - */ - disable_irq(client->irq); - chip->tcpci = tcpci_register_port(&client->dev, &chip->data); - enable_irq(client->irq); + /* Enable chip interrupts at last */ + err = tcpci_write16(chip->tcpci, TCPC_ALERT_MASK, chip->tcpci->alert_mask); + if (err < 0) + goto unregister_port; - return PTR_ERR_OR_ZERO(chip->tcpci); + return 0; + +unregister_port: + tcpci_unregister_port(chip->tcpci); + return err; } static void tcpci_remove(struct i2c_client *client) diff --git a/drivers/usb/typec/ucsi/ucsi_ccg.c b/drivers/usb/typec/ucsi/ucsi_ccg.c index fcb8e61136cf..740171f24ef9 100644 --- a/drivers/usb/typec/ucsi/ucsi_ccg.c +++ b/drivers/usb/typec/ucsi/ucsi_ccg.c @@ -646,7 +646,7 @@ static int ucsi_ccg_sync_control(struct ucsi *ucsi, u64 command) UCSI_CMD_CONNECTOR_MASK; if (con_index == 0) { ret = -EINVAL; - goto unlock; + goto err_put; } con = &uc->ucsi->connector[con_index - 1]; ucsi_ccg_update_set_new_cam_cmd(uc, con, &command); @@ -654,8 +654,8 @@ static int ucsi_ccg_sync_control(struct ucsi *ucsi, u64 command) ret = ucsi_sync_control_common(ucsi, command); +err_put: pm_runtime_put_sync(uc->dev); -unlock: mutex_unlock(&uc->lock); return ret; diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c index 90948cd6d297..fed39d458090 100644 --- a/drivers/usb/typec/ucsi/ucsi_glink.c +++ b/drivers/usb/typec/ucsi/ucsi_glink.c @@ -185,6 +185,11 @@ static void pmic_glink_ucsi_connector_status(struct ucsi_connector *con) struct pmic_glink_ucsi *ucsi = ucsi_get_drvdata(con->ucsi); int orientation; + if (!UCSI_CONSTAT(con, CONNECTED)) { + typec_set_orientation(con->port, TYPEC_ORIENTATION_NONE); + return; + } + if (con->num > PMIC_GLINK_MAX_PORTS || !ucsi->port_orientation[con->num - 1]) return; diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 1ab58da9f38a..1a4ed5a357d3 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -1661,14 +1661,15 @@ static vm_fault_t vfio_pci_mmap_huge_fault(struct vm_fault *vmf, unsigned long pfn, pgoff = vmf->pgoff - vma->vm_pgoff; vm_fault_t ret = VM_FAULT_SIGBUS; - if (order && (vmf->address & ((PAGE_SIZE << order) - 1) || + pfn = vma_to_pfn(vma) + pgoff; + + if (order && (pfn & ((1 << order) - 1) || + vmf->address & ((PAGE_SIZE << order) - 1) || vmf->address + (PAGE_SIZE << order) > vma->vm_end)) { ret = VM_FAULT_FALLBACK; goto out; } - pfn = vma_to_pfn(vma); - down_read(&vdev->memory_lock); if (vdev->pm_runtime_engaged || !__vfio_pci_memory_enabled(vdev)) @@ -1676,18 +1677,18 @@ static vm_fault_t vfio_pci_mmap_huge_fault(struct vm_fault *vmf, switch (order) { case 0: - ret = vmf_insert_pfn(vma, vmf->address, pfn + pgoff); + ret = vmf_insert_pfn(vma, vmf->address, pfn); break; #ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP case PMD_ORDER: - ret = vmf_insert_pfn_pmd(vmf, __pfn_to_pfn_t(pfn + pgoff, - PFN_DEV), false); + ret = vmf_insert_pfn_pmd(vmf, + __pfn_to_pfn_t(pfn, PFN_DEV), false); break; #endif #ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP case PUD_ORDER: - ret = vmf_insert_pfn_pud(vmf, __pfn_to_pfn_t(pfn + pgoff, - PFN_DEV), false); + ret = vmf_insert_pfn_pud(vmf, + __pfn_to_pfn_t(pfn, PFN_DEV), false); break; #endif default: diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index de035071fedb..55c6686f091e 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -649,6 +649,7 @@ config FB_S1D13XXX config FB_ATMEL tristate "AT91 LCD Controller support" depends on FB && OF && HAVE_CLK && HAS_IOMEM + depends on BACKLIGHT_CLASS_DEVICE depends on HAVE_FB_ATMEL || COMPILE_TEST select FB_BACKLIGHT select FB_IOMEM_HELPERS @@ -660,7 +661,6 @@ config FB_ATMEL config FB_NVIDIA tristate "nVidia Framebuffer Support" depends on FB && PCI - select FB_BACKLIGHT if FB_NVIDIA_BACKLIGHT select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT @@ -700,6 +700,8 @@ config FB_NVIDIA_DEBUG config FB_NVIDIA_BACKLIGHT bool "Support for backlight control" depends on FB_NVIDIA + depends on BACKLIGHT_CLASS_DEVICE=y || BACKLIGHT_CLASS_DEVICE=FB_NVIDIA + select FB_BACKLIGHT default y help Say Y here if you want to control the backlight of your display. @@ -707,7 +709,6 @@ config FB_NVIDIA_BACKLIGHT config FB_RIVA tristate "nVidia Riva support" depends on FB && PCI - select FB_BACKLIGHT if FB_RIVA_BACKLIGHT select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT @@ -747,6 +748,8 @@ config FB_RIVA_DEBUG config FB_RIVA_BACKLIGHT bool "Support for backlight control" depends on FB_RIVA + depends on BACKLIGHT_CLASS_DEVICE=y || BACKLIGHT_CLASS_DEVICE=FB_RIVA + select FB_BACKLIGHT default y help Say Y here if you want to control the backlight of your display. @@ -934,7 +937,6 @@ config FB_MATROX_MAVEN config FB_RADEON tristate "ATI Radeon display support" depends on FB && PCI - select FB_BACKLIGHT if FB_RADEON_BACKLIGHT select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT @@ -960,6 +962,8 @@ config FB_RADEON_I2C config FB_RADEON_BACKLIGHT bool "Support for backlight control" depends on FB_RADEON + depends on BACKLIGHT_CLASS_DEVICE=y || BACKLIGHT_CLASS_DEVICE=FB_RADEON + select FB_BACKLIGHT default y help Say Y here if you want to control the backlight of your display. @@ -975,7 +979,6 @@ config FB_RADEON_DEBUG config FB_ATY128 tristate "ATI Rage128 display support" depends on FB && PCI - select FB_BACKLIGHT if FB_ATY128_BACKLIGHT select FB_IOMEM_HELPERS select FB_MACMODES if PPC_PMAC help @@ -989,6 +992,8 @@ config FB_ATY128 config FB_ATY128_BACKLIGHT bool "Support for backlight control" depends on FB_ATY128 + depends on BACKLIGHT_CLASS_DEVICE=y || BACKLIGHT_CLASS_DEVICE=FB_ATY128 + select FB_BACKLIGHT default y help Say Y here if you want to control the backlight of your display. @@ -999,7 +1004,6 @@ config FB_ATY select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT - select FB_BACKLIGHT if FB_ATY_BACKLIGHT select FB_IOMEM_FOPS select FB_MACMODES if PPC select FB_ATY_CT if SPARC64 && PCI @@ -1040,6 +1044,8 @@ config FB_ATY_GX config FB_ATY_BACKLIGHT bool "Support for backlight control" depends on FB_ATY + depends on BACKLIGHT_CLASS_DEVICE=y || BACKLIGHT_CLASS_DEVICE=FB_ATY + select FB_BACKLIGHT default y help Say Y here if you want to control the backlight of your display. @@ -1528,6 +1534,7 @@ config FB_SH_MOBILE_LCDC depends on FB && HAVE_CLK && HAS_IOMEM depends on SUPERH || COMPILE_TEST depends on FB_DEVICE + depends on BACKLIGHT_CLASS_DEVICE select FB_BACKLIGHT select FB_DEFERRED_IO select FB_DMAMEM_HELPERS @@ -1793,6 +1800,7 @@ config FB_SSD1307 tristate "Solomon SSD1307 framebuffer support" depends on FB && I2C depends on GPIOLIB || COMPILE_TEST + depends on BACKLIGHT_CLASS_DEVICE select FB_BACKLIGHT select FB_SYSMEM_HELPERS_DEFERRED help diff --git a/drivers/video/fbdev/core/Kconfig b/drivers/video/fbdev/core/Kconfig index 0ab8848ba2f1..d554d8c543d4 100644 --- a/drivers/video/fbdev/core/Kconfig +++ b/drivers/video/fbdev/core/Kconfig @@ -183,9 +183,8 @@ config FB_SYSMEM_HELPERS_DEFERRED select FB_SYSMEM_HELPERS config FB_BACKLIGHT - tristate + bool depends on FB - select BACKLIGHT_CLASS_DEVICE config FB_MODE_HELPERS bool "Enable Video Mode Handling Helpers" diff --git a/drivers/virt/coco/tdx-guest/tdx-guest.c b/drivers/virt/coco/tdx-guest/tdx-guest.c index d7db6c824e13..224e7dde9cde 100644 --- a/drivers/virt/coco/tdx-guest/tdx-guest.c +++ b/drivers/virt/coco/tdx-guest/tdx-guest.c @@ -124,10 +124,8 @@ static void *alloc_quote_buf(void) if (!addr) return NULL; - if (set_memory_decrypted((unsigned long)addr, count)) { - free_pages_exact(addr, len); + if (set_memory_decrypted((unsigned long)addr, count)) return NULL; - } return addr; } diff --git a/drivers/watchdog/stm32_iwdg.c b/drivers/watchdog/stm32_iwdg.c index d700e0d49bb9..8ad06b54c5ad 100644 --- a/drivers/watchdog/stm32_iwdg.c +++ b/drivers/watchdog/stm32_iwdg.c @@ -286,7 +286,7 @@ static int stm32_iwdg_irq_init(struct platform_device *pdev, if (!wdt->data->has_early_wakeup) return 0; - irq = platform_get_irq(pdev, 0); + irq = platform_get_irq_optional(pdev, 0); if (irq <= 0) return 0; diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 819c75233235..3bc9ce6c575e 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -57,6 +57,8 @@ static void v9fs_issue_write(struct netfs_io_subrequest *subreq) int err, len; len = p9_client_write(fid, subreq->start, &subreq->io_iter, &err); + if (len > 0) + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); netfs_write_subrequest_terminated(subreq, len ?: err, false); } @@ -80,8 +82,10 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq) if (pos + total >= i_size_read(rreq->inode)) __set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags); - if (!err) + if (!err) { subreq->transferred += total; + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + } netfs_read_subreq_terminated(subreq, err, false); } diff --git a/fs/afs/addr_prefs.c b/fs/afs/addr_prefs.c index a189ff8a5034..c0384201b8fe 100644 --- a/fs/afs/addr_prefs.c +++ b/fs/afs/addr_prefs.c @@ -413,8 +413,10 @@ int afs_proc_addr_prefs_write(struct file *file, char *buf, size_t size) do { argc = afs_split_string(&buf, argv, ARRAY_SIZE(argv)); - if (argc < 0) - return argc; + if (argc < 0) { + ret = argc; + goto done; + } if (argc < 2) goto inval; diff --git a/fs/afs/afs.h b/fs/afs/afs.h index b488072aee87..ec3db00bd081 100644 --- a/fs/afs/afs.h +++ b/fs/afs/afs.h @@ -10,7 +10,7 @@ #include <linux/in.h> -#define AFS_MAXCELLNAME 256 /* Maximum length of a cell name */ +#define AFS_MAXCELLNAME 253 /* Maximum length of a cell name (DNS limited) */ #define AFS_MAXVOLNAME 64 /* Maximum length of a volume name */ #define AFS_MAXNSERVERS 8 /* Maximum servers in a basic volume record */ #define AFS_NMAXNSERVERS 13 /* Maximum servers in a N/U-class volume record */ diff --git a/fs/afs/afs_vl.h b/fs/afs/afs_vl.h index a06296c8827d..b835e25a2c02 100644 --- a/fs/afs/afs_vl.h +++ b/fs/afs/afs_vl.h @@ -13,6 +13,7 @@ #define AFS_VL_PORT 7003 /* volume location service port */ #define VL_SERVICE 52 /* RxRPC service ID for the Volume Location service */ #define YFS_VL_SERVICE 2503 /* Service ID for AuriStor upgraded VL service */ +#define YFS_VL_MAXCELLNAME 256 /* Maximum length of a cell name in YFS protocol */ enum AFSVL_Operations { VLGETENTRYBYID = 503, /* AFS Get VLDB entry by ID */ diff --git a/fs/afs/vl_alias.c b/fs/afs/vl_alias.c index 9f36e14f1c2d..f9e76b604f31 100644 --- a/fs/afs/vl_alias.c +++ b/fs/afs/vl_alias.c @@ -253,6 +253,7 @@ static char *afs_vl_get_cell_name(struct afs_cell *cell, struct key *key) static int yfs_check_canonical_cell_name(struct afs_cell *cell, struct key *key) { struct afs_cell *master; + size_t name_len; char *cell_name; cell_name = afs_vl_get_cell_name(cell, key); @@ -264,8 +265,11 @@ static int yfs_check_canonical_cell_name(struct afs_cell *cell, struct key *key) return 0; } - master = afs_lookup_cell(cell->net, cell_name, strlen(cell_name), - NULL, false); + name_len = strlen(cell_name); + if (!name_len || name_len > AFS_MAXCELLNAME) + master = ERR_PTR(-EOPNOTSUPP); + else + master = afs_lookup_cell(cell->net, cell_name, name_len, NULL, false); kfree(cell_name); if (IS_ERR(master)) return PTR_ERR(master); diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c index cac75f89b64a..55dd0fc5aad7 100644 --- a/fs/afs/vlclient.c +++ b/fs/afs/vlclient.c @@ -697,7 +697,7 @@ static int afs_deliver_yfsvl_get_cell_name(struct afs_call *call) return ret; namesz = ntohl(call->tmp); - if (namesz > AFS_MAXCELLNAME) + if (namesz > YFS_VL_MAXCELLNAME) return afs_protocol_error(call, afs_eproto_cellname_len); paddedsz = (namesz + 3) & ~3; call->count = namesz; diff --git a/fs/afs/write.c b/fs/afs/write.c index 34107b55f834..ccb6aa8027c5 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -122,7 +122,7 @@ static void afs_issue_write_worker(struct work_struct *work) if (subreq->debug_index == 3) return netfs_write_subrequest_terminated(subreq, -ENOANO, false); - if (!test_bit(NETFS_SREQ_RETRYING, &subreq->flags)) { + if (!subreq->retry_count) { set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); return netfs_write_subrequest_terminated(subreq, -EAGAIN, false); } @@ -149,6 +149,9 @@ static void afs_issue_write_worker(struct work_struct *work) afs_wait_for_operation(op); ret = afs_put_operation(op); switch (ret) { + case 0: + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + break; case -EACCES: case -EPERM: case -ENOKEY: diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c index af3db0a7ae4d..7ea6f0b43b95 100644 --- a/fs/btrfs/bio.c +++ b/fs/btrfs/bio.c @@ -358,7 +358,7 @@ static void btrfs_simple_end_io(struct bio *bio) INIT_WORK(&bbio->end_io_work, btrfs_end_bio_work); queue_work(btrfs_end_io_wq(fs_info, bio), &bbio->end_io_work); } else { - if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status) + if (bio_is_zone_append(bio) && !bio->bi_status) btrfs_record_physical_zoned(bbio); btrfs_bio_end_io(bbio, bbio->bio.bi_status); } @@ -401,7 +401,7 @@ static void btrfs_orig_write_end_io(struct bio *bio) else bio->bi_status = BLK_STS_OK; - if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status) + if (bio_is_zone_append(bio) && !bio->bi_status) stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; btrfs_bio_end_io(bbio, bbio->bio.bi_status); @@ -415,7 +415,7 @@ static void btrfs_clone_write_end_io(struct bio *bio) if (bio->bi_status) { atomic_inc(&stripe->bioc->error); btrfs_log_dev_io_error(bio, stripe->dev); - } else if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + } else if (bio_is_zone_append(bio)) { stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; } @@ -652,8 +652,14 @@ static u64 btrfs_append_map_length(struct btrfs_bio *bbio, u64 map_length) map_length = min(map_length, bbio->fs_info->max_zone_append_size); sector_offset = bio_split_rw_at(&bbio->bio, &bbio->fs_info->limits, &nr_segs, map_length); - if (sector_offset) - return sector_offset << SECTOR_SHIFT; + if (sector_offset) { + /* + * bio_split_rw_at() could split at a size smaller than our + * sectorsize and thus cause unaligned I/Os. Fix that by + * always rounding down to the nearest boundary. + */ + return ALIGN_DOWN(sector_offset << SECTOR_SHIFT, bbio->fs_info->sectorsize); + } return map_length; } diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 693dc27ffb89..185985a337b3 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -654,6 +654,8 @@ int btrfs_force_cow_block(struct btrfs_trans_handle *trans, goto error_unlock_cow; } } + + trace_btrfs_cow_block(root, buf, cow); if (unlock_orig) btrfs_tree_unlock(buf); free_extent_buffer_stale(buf); @@ -710,7 +712,6 @@ int btrfs_cow_block(struct btrfs_trans_handle *trans, { struct btrfs_fs_info *fs_info = root->fs_info; u64 search_start; - int ret; if (unlikely(test_bit(BTRFS_ROOT_DELETING, &root->state))) { btrfs_abort_transaction(trans, -EUCLEAN); @@ -751,12 +752,8 @@ int btrfs_cow_block(struct btrfs_trans_handle *trans, * Also We don't care about the error, as it's handled internally. */ btrfs_qgroup_trace_subtree_after_cow(trans, root, buf); - ret = btrfs_force_cow_block(trans, root, buf, parent, parent_slot, - cow_ret, search_start, 0, nest); - - trace_btrfs_cow_block(root, buf, *cow_ret); - - return ret; + return btrfs_force_cow_block(trans, root, buf, parent, parent_slot, + cow_ret, search_start, 0, nest); } ALLOW_ERROR_INJECTION(btrfs_cow_block, ERRNO); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 307dedf95c70..2c341956a01c 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -371,6 +371,25 @@ static inline void btrfs_set_root_last_trans(struct btrfs_root *root, u64 transi } /* + * Return the generation this root started with. + * + * Every normal root that is created with root->root_key.offset set to it's + * originating generation. If it is a snapshot it is the generation when the + * snapshot was created. + * + * However for TREE_RELOC roots root_key.offset is the objectid of the owning + * tree root. Thankfully we copy the root item of the owning tree root, which + * has it's last_snapshot set to what we would have root_key.offset set to, so + * return that if this is a TREE_RELOC root. + */ +static inline u64 btrfs_root_origin_generation(const struct btrfs_root *root) +{ + if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) + return btrfs_root_last_snapshot(&root->root_item); + return root->root_key.offset; +} + +/* * Structure that conveys information about an extent that is going to replace * all the extents in a file range. */ diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index bd09dd3ad1a0..3c6f7fecbb9a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5285,7 +5285,7 @@ static bool visit_node_for_delete(struct btrfs_root *root, struct walk_control * * reference to it. */ generation = btrfs_node_ptr_generation(eb, slot); - if (!wc->update_ref || generation <= root->root_key.offset) + if (!wc->update_ref || generation <= btrfs_root_origin_generation(root)) return false; /* @@ -5340,7 +5340,7 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans, goto reada; if (wc->stage == UPDATE_BACKREF && - generation <= root->root_key.offset) + generation <= btrfs_root_origin_generation(root)) continue; /* We don't lock the tree block, it's OK to be racy here */ @@ -5683,7 +5683,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans, * for the subtree */ if (wc->stage == UPDATE_BACKREF && - generation <= root->root_key.offset) { + generation <= btrfs_root_origin_generation(root)) { wc->lookup_info = 1; return 1; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 488edca8333a..27b2fe7f735d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9078,9 +9078,9 @@ out: } struct btrfs_encoded_read_private { - wait_queue_head_t wait; + struct completion done; void *uring_ctx; - atomic_t pending; + refcount_t pending_refs; blk_status_t status; }; @@ -9099,14 +9099,14 @@ static void btrfs_encoded_read_endio(struct btrfs_bio *bbio) */ WRITE_ONCE(priv->status, bbio->bio.bi_status); } - if (atomic_dec_and_test(&priv->pending)) { + if (refcount_dec_and_test(&priv->pending_refs)) { int err = blk_status_to_errno(READ_ONCE(priv->status)); if (priv->uring_ctx) { btrfs_uring_read_extent_endio(priv->uring_ctx, err); kfree(priv); } else { - wake_up(&priv->wait); + complete(&priv->done); } } bio_put(&bbio->bio); @@ -9126,8 +9126,8 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, if (!priv) return -ENOMEM; - init_waitqueue_head(&priv->wait); - atomic_set(&priv->pending, 1); + init_completion(&priv->done); + refcount_set(&priv->pending_refs, 1); priv->status = 0; priv->uring_ctx = uring_ctx; @@ -9140,7 +9140,7 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, size_t bytes = min_t(u64, disk_io_size, PAGE_SIZE); if (bio_add_page(&bbio->bio, pages[i], bytes, 0) < bytes) { - atomic_inc(&priv->pending); + refcount_inc(&priv->pending_refs); btrfs_submit_bbio(bbio, 0); bbio = btrfs_bio_alloc(BIO_MAX_VECS, REQ_OP_READ, fs_info, @@ -9155,11 +9155,11 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, disk_io_size -= bytes; } while (disk_io_size); - atomic_inc(&priv->pending); + refcount_inc(&priv->pending_refs); btrfs_submit_bbio(bbio, 0); if (uring_ctx) { - if (atomic_dec_return(&priv->pending) == 0) { + if (refcount_dec_and_test(&priv->pending_refs)) { ret = blk_status_to_errno(READ_ONCE(priv->status)); btrfs_uring_read_extent_endio(uring_ctx, ret); kfree(priv); @@ -9168,8 +9168,8 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, return -EIOCBQUEUED; } else { - if (atomic_dec_return(&priv->pending) != 0) - io_wait_event(priv->wait, !atomic_read(&priv->pending)); + if (!refcount_dec_and_test(&priv->pending_refs)) + wait_for_completion_io(&priv->done); /* See btrfs_encoded_read_endio() for ordering. */ ret = blk_status_to_errno(READ_ONCE(priv->status)); kfree(priv); @@ -9799,15 +9799,25 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, struct btrfs_fs_info *fs_info = root->fs_info; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct extent_state *cached_state = NULL; - struct extent_map *em = NULL; struct btrfs_chunk_map *map = NULL; struct btrfs_device *device = NULL; struct btrfs_swap_info bsi = { .lowest_ppage = (sector_t)-1ULL, }; + struct btrfs_backref_share_check_ctx *backref_ctx = NULL; + struct btrfs_path *path = NULL; int ret = 0; u64 isize; - u64 start; + u64 prev_extent_end = 0; + + /* + * Acquire the inode's mmap lock to prevent races with memory mapped + * writes, as they could happen after we flush delalloc below and before + * we lock the extent range further below. The inode was already locked + * up in the call chain. + */ + btrfs_assert_inode_locked(BTRFS_I(inode)); + down_write(&BTRFS_I(inode)->i_mmap_lock); /* * If the swap file was just created, make sure delalloc is done. If the @@ -9816,22 +9826,32 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, */ ret = btrfs_wait_ordered_range(BTRFS_I(inode), 0, (u64)-1); if (ret) - return ret; + goto out_unlock_mmap; /* * The inode is locked, so these flags won't change after we check them. */ if (BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS) { btrfs_warn(fs_info, "swapfile must not be compressed"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW)) { btrfs_warn(fs_info, "swapfile must not be copy-on-write"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) { btrfs_warn(fs_info, "swapfile must not be checksummed"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; + } + + path = btrfs_alloc_path(); + backref_ctx = btrfs_alloc_backref_share_check_ctx(); + if (!path || !backref_ctx) { + ret = -ENOMEM; + goto out_unlock_mmap; } /* @@ -9846,7 +9866,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_SWAP_ACTIVATE)) { btrfs_warn(fs_info, "cannot activate swapfile while exclusive operation is running"); - return -EBUSY; + ret = -EBUSY; + goto out_unlock_mmap; } /* @@ -9860,7 +9881,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, btrfs_exclop_finish(fs_info); btrfs_warn(fs_info, "cannot activate swapfile because snapshot creation is in progress"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } /* * Snapshots can create extents which require COW even if NODATACOW is @@ -9881,7 +9903,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, btrfs_warn(fs_info, "cannot activate swapfile because subvolume %llu is being deleted", btrfs_root_id(root)); - return -EPERM; + ret = -EPERM; + goto out_unlock_mmap; } atomic_inc(&root->nr_swapfiles); spin_unlock(&root->root_item_lock); @@ -9889,24 +9912,39 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, isize = ALIGN_DOWN(inode->i_size, fs_info->sectorsize); lock_extent(io_tree, 0, isize - 1, &cached_state); - start = 0; - while (start < isize) { - u64 logical_block_start, physical_block_start; + while (prev_extent_end < isize) { + struct btrfs_key key; + struct extent_buffer *leaf; + struct btrfs_file_extent_item *ei; struct btrfs_block_group *bg; - u64 len = isize - start; + u64 logical_block_start; + u64 physical_block_start; + u64 extent_gen; + u64 disk_bytenr; + u64 len; - em = btrfs_get_extent(BTRFS_I(inode), NULL, start, len); - if (IS_ERR(em)) { - ret = PTR_ERR(em); + key.objectid = btrfs_ino(BTRFS_I(inode)); + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = prev_extent_end; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) goto out; - } - if (em->disk_bytenr == EXTENT_MAP_HOLE) { + /* + * If key not found it means we have an implicit hole (NO_HOLES + * is enabled). + */ + if (ret > 0) { btrfs_warn(fs_info, "swapfile must not have holes"); ret = -EINVAL; goto out; } - if (em->disk_bytenr == EXTENT_MAP_INLINE) { + + leaf = path->nodes[0]; + ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); + + if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_INLINE) { /* * It's unlikely we'll ever actually find ourselves * here, as a file small enough to fit inline won't be @@ -9918,23 +9956,45 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, ret = -EINVAL; goto out; } - if (extent_map_is_compressed(em)) { + + if (btrfs_file_extent_compression(leaf, ei) != BTRFS_COMPRESS_NONE) { btrfs_warn(fs_info, "swapfile must not be compressed"); ret = -EINVAL; goto out; } - logical_block_start = extent_map_block_start(em) + (start - em->start); - len = min(len, em->len - (start - em->start)); - free_extent_map(em); - em = NULL; + disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, ei); + if (disk_bytenr == 0) { + btrfs_warn(fs_info, "swapfile must not have holes"); + ret = -EINVAL; + goto out; + } + + logical_block_start = disk_bytenr + btrfs_file_extent_offset(leaf, ei); + extent_gen = btrfs_file_extent_generation(leaf, ei); + prev_extent_end = btrfs_file_extent_end(path); - ret = can_nocow_extent(inode, start, &len, NULL, false, true); + if (prev_extent_end > isize) + len = isize - key.offset; + else + len = btrfs_file_extent_num_bytes(leaf, ei); + + backref_ctx->curr_leaf_bytenr = leaf->start; + + /* + * Don't need the path anymore, release to avoid deadlocks when + * calling btrfs_is_data_extent_shared() because when joining a + * transaction it can block waiting for the current one's commit + * which in turn may be trying to lock the same leaf to flush + * delayed items for example. + */ + btrfs_release_path(path); + + ret = btrfs_is_data_extent_shared(BTRFS_I(inode), disk_bytenr, + extent_gen, backref_ctx); if (ret < 0) { goto out; - } else if (ret) { - ret = 0; - } else { + } else if (ret > 0) { btrfs_warn(fs_info, "swapfile must not be copy-on-write"); ret = -EINVAL; @@ -9969,7 +10029,6 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, physical_block_start = (map->stripes[0].physical + (logical_block_start - map->start)); - len = min(len, map->chunk_len - (logical_block_start - map->start)); btrfs_free_chunk_map(map); map = NULL; @@ -10010,20 +10069,23 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, if (ret) goto out; } - bsi.start = start; + bsi.start = key.offset; bsi.block_start = physical_block_start; bsi.block_len = len; } - start += len; + if (fatal_signal_pending(current)) { + ret = -EINTR; + goto out; + } + + cond_resched(); } if (bsi.block_len) ret = btrfs_add_swap_extent(sis, &bsi); out: - if (!IS_ERR_OR_NULL(em)) - free_extent_map(em); if (!IS_ERR_OR_NULL(map)) btrfs_free_chunk_map(map); @@ -10036,6 +10098,10 @@ out: btrfs_exclop_finish(fs_info); +out_unlock_mmap: + up_write(&BTRFS_I(inode)->i_mmap_lock); + btrfs_free_backref_share_ctx(backref_ctx); + btrfs_free_path(path); if (ret) return ret; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 3af8bb0c8d75..4d9305fa37a8 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4878,25 +4878,29 @@ out_fail: return ret; } +struct btrfs_uring_encoded_data { + struct btrfs_ioctl_encoded_io_args args; + struct iovec iovstack[UIO_FASTIOV]; + struct iovec *iov; + struct iov_iter iter; +}; + static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue_flags) { size_t copy_end_kernel = offsetofend(struct btrfs_ioctl_encoded_io_args, flags); size_t copy_end; - struct btrfs_ioctl_encoded_io_args args = { 0 }; int ret; u64 disk_bytenr, disk_io_size; struct file *file; struct btrfs_inode *inode; struct btrfs_fs_info *fs_info; struct extent_io_tree *io_tree; - struct iovec iovstack[UIO_FASTIOV]; - struct iovec *iov = iovstack; - struct iov_iter iter; loff_t pos; struct kiocb kiocb; struct extent_state *cached_state = NULL; u64 start, lockend; void __user *sqe_addr; + struct btrfs_uring_encoded_data *data = io_uring_cmd_get_async_data(cmd)->op_data; if (!capable(CAP_SYS_ADMIN)) { ret = -EPERM; @@ -4910,43 +4914,64 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue if (issue_flags & IO_URING_F_COMPAT) { #if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) - struct btrfs_ioctl_encoded_io_args_32 args32; - copy_end = offsetofend(struct btrfs_ioctl_encoded_io_args_32, flags); - if (copy_from_user(&args32, sqe_addr, copy_end)) { - ret = -EFAULT; - goto out_acct; - } - args.iov = compat_ptr(args32.iov); - args.iovcnt = args32.iovcnt; - args.offset = args32.offset; - args.flags = args32.flags; #else return -ENOTTY; #endif } else { copy_end = copy_end_kernel; - if (copy_from_user(&args, sqe_addr, copy_end)) { - ret = -EFAULT; + } + + if (!data) { + data = kzalloc(sizeof(*data), GFP_NOFS); + if (!data) { + ret = -ENOMEM; goto out_acct; } - } - if (args.flags != 0) - return -EINVAL; + io_uring_cmd_get_async_data(cmd)->op_data = data; - ret = import_iovec(ITER_DEST, args.iov, args.iovcnt, ARRAY_SIZE(iovstack), - &iov, &iter); - if (ret < 0) - goto out_acct; + if (issue_flags & IO_URING_F_COMPAT) { +#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) + struct btrfs_ioctl_encoded_io_args_32 args32; - if (iov_iter_count(&iter) == 0) { - ret = 0; - goto out_free; + if (copy_from_user(&args32, sqe_addr, copy_end)) { + ret = -EFAULT; + goto out_acct; + } + + data->args.iov = compat_ptr(args32.iov); + data->args.iovcnt = args32.iovcnt; + data->args.offset = args32.offset; + data->args.flags = args32.flags; +#endif + } else { + if (copy_from_user(&data->args, sqe_addr, copy_end)) { + ret = -EFAULT; + goto out_acct; + } + } + + if (data->args.flags != 0) { + ret = -EINVAL; + goto out_acct; + } + + data->iov = data->iovstack; + ret = import_iovec(ITER_DEST, data->args.iov, data->args.iovcnt, + ARRAY_SIZE(data->iovstack), &data->iov, + &data->iter); + if (ret < 0) + goto out_acct; + + if (iov_iter_count(&data->iter) == 0) { + ret = 0; + goto out_free; + } } - pos = args.offset; - ret = rw_verify_area(READ, file, &pos, args.len); + pos = data->args.offset; + ret = rw_verify_area(READ, file, &pos, data->args.len); if (ret < 0) goto out_free; @@ -4959,15 +4984,16 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue start = ALIGN_DOWN(pos, fs_info->sectorsize); lockend = start + BTRFS_MAX_UNCOMPRESSED - 1; - ret = btrfs_encoded_read(&kiocb, &iter, &args, &cached_state, + ret = btrfs_encoded_read(&kiocb, &data->iter, &data->args, &cached_state, &disk_bytenr, &disk_io_size); if (ret < 0 && ret != -EIOCBQUEUED) goto out_free; file_accessed(file); - if (copy_to_user(sqe_addr + copy_end, (const char *)&args + copy_end_kernel, - sizeof(args) - copy_end_kernel)) { + if (copy_to_user(sqe_addr + copy_end, + (const char *)&data->args + copy_end_kernel, + sizeof(data->args) - copy_end_kernel)) { if (ret == -EIOCBQUEUED) { unlock_extent(io_tree, start, lockend, &cached_state); btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); @@ -4977,40 +5003,22 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue } if (ret == -EIOCBQUEUED) { - u64 count; - - /* - * If we've optimized things by storing the iovecs on the stack, - * undo this. - */ - if (!iov) { - iov = kmalloc(sizeof(struct iovec) * args.iovcnt, GFP_NOFS); - if (!iov) { - unlock_extent(io_tree, start, lockend, &cached_state); - btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); - ret = -ENOMEM; - goto out_acct; - } - - memcpy(iov, iovstack, sizeof(struct iovec) * args.iovcnt); - } - - count = min_t(u64, iov_iter_count(&iter), disk_io_size); + u64 count = min_t(u64, iov_iter_count(&data->iter), disk_io_size); /* Match ioctl by not returning past EOF if uncompressed. */ - if (!args.compression) - count = min_t(u64, count, args.len); + if (!data->args.compression) + count = min_t(u64, count, data->args.len); - ret = btrfs_uring_read_extent(&kiocb, &iter, start, lockend, - cached_state, disk_bytenr, - disk_io_size, count, - args.compression, iov, cmd); + ret = btrfs_uring_read_extent(&kiocb, &data->iter, start, lockend, + cached_state, disk_bytenr, disk_io_size, + count, data->args.compression, + data->iov, cmd); goto out_acct; } out_free: - kfree(iov); + kfree(data->iov); out_acct: if (ret > 0) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index a6f92836c9b1..f9b214992212 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1121,6 +1121,7 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info, fs_info->qgroup_flags = BTRFS_QGROUP_STATUS_FLAG_ON; if (simple) { fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE; + btrfs_set_fs_incompat(fs_info, SIMPLE_QUOTA); btrfs_set_qgroup_status_enable_gen(leaf, ptr, trans->transid); } else { fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; @@ -1254,8 +1255,6 @@ out_add_root: spin_lock(&fs_info->qgroup_lock); fs_info->quota_root = quota_root; set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); - if (simple) - btrfs_set_fs_incompat(fs_info, SIMPLE_QUOTA); spin_unlock(&fs_info->qgroup_lock); /* Skip rescan for simple qgroups. */ diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index bf267bdfa8f8..db8b42f674b7 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2902,6 +2902,7 @@ static int relocate_one_folio(struct reloc_control *rc, const bool use_rst = btrfs_need_stripe_tree_update(fs_info, rc->block_group->flags); ASSERT(index <= last_index); +again: folio = filemap_lock_folio(inode->i_mapping, index); if (IS_ERR(folio)) { @@ -2937,6 +2938,11 @@ static int relocate_one_folio(struct reloc_control *rc, ret = -EIO; goto release_folio; } + if (folio->mapping != inode->i_mapping) { + folio_unlock(folio); + folio_put(folio); + goto again; + } } /* diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 204c928beaf9..531312efee8d 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1541,6 +1541,10 @@ static int scrub_find_fill_first_stripe(struct btrfs_block_group *bg, u64 extent_gen; int ret; + if (unlikely(!extent_root)) { + btrfs_err(fs_info, "no valid extent root for scrub"); + return -EUCLEAN; + } memset(stripe->sectors, 0, sizeof(struct scrub_sector_verification) * stripe->nr_sectors); scrub_stripe_reset_bitmaps(stripe); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 7254279c3cc9..498c84323253 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -5280,6 +5280,7 @@ static int put_file_data(struct send_ctx *sctx, u64 offset, u32 len) unsigned cur_len = min_t(unsigned, len, PAGE_SIZE - pg_offset); +again: folio = filemap_lock_folio(mapping, index); if (IS_ERR(folio)) { page_cache_sync_readahead(mapping, @@ -5312,6 +5313,11 @@ static int put_file_data(struct send_ctx *sctx, u64 offset, u32 len) ret = -EIO; break; } + if (folio->mapping != mapping) { + folio_unlock(folio); + folio_put(folio); + goto again; + } } memcpy_from_folio(sctx->send_buf + sctx->send_size, folio, diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index fdcbf650ac31..7f09b6c9cc2d 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -1118,7 +1118,7 @@ static ssize_t btrfs_nodesize_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return sysfs_emit(buf, "%u\n", fs_info->super_copy->nodesize); + return sysfs_emit(buf, "%u\n", fs_info->nodesize); } BTRFS_ATTR(, nodesize, btrfs_nodesize_show); @@ -1128,7 +1128,7 @@ static ssize_t btrfs_sectorsize_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return sysfs_emit(buf, "%u\n", fs_info->super_copy->sectorsize); + return sysfs_emit(buf, "%u\n", fs_info->sectorsize); } BTRFS_ATTR(, sectorsize, btrfs_sectorsize_show); @@ -1180,7 +1180,7 @@ static ssize_t btrfs_clone_alignment_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return sysfs_emit(buf, "%u\n", fs_info->super_copy->sectorsize); + return sysfs_emit(buf, "%u\n", fs_info->sectorsize); } BTRFS_ATTR(, clone_alignment, btrfs_clone_alignment_show); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 148d8cefa40e..dfeee033f31f 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1527,6 +1527,11 @@ static int check_extent_item(struct extent_buffer *leaf, dref_offset, fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_extent_data_ref_count(leaf, dref) == 0)) { + extent_err(leaf, slot, + "invalid data ref count, should have non-zero value"); + return -EUCLEAN; + } inline_refs += btrfs_extent_data_ref_count(leaf, dref); break; /* Contains parent bytenr and ref count */ @@ -1539,6 +1544,11 @@ static int check_extent_item(struct extent_buffer *leaf, inline_offset, fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_shared_data_ref_count(leaf, sref) == 0)) { + extent_err(leaf, slot, + "invalid shared data ref count, should have non-zero value"); + return -EUCLEAN; + } inline_refs += btrfs_shared_data_ref_count(leaf, sref); break; case BTRFS_EXTENT_OWNER_REF_KEY: @@ -1611,8 +1621,18 @@ static int check_simple_keyed_refs(struct extent_buffer *leaf, { u32 expect_item_size = 0; - if (key->type == BTRFS_SHARED_DATA_REF_KEY) + if (key->type == BTRFS_SHARED_DATA_REF_KEY) { + struct btrfs_shared_data_ref *sref; + + sref = btrfs_item_ptr(leaf, slot, struct btrfs_shared_data_ref); + if (unlikely(btrfs_shared_data_ref_count(leaf, sref) == 0)) { + extent_err(leaf, slot, + "invalid shared data backref count, should have non-zero value"); + return -EUCLEAN; + } + expect_item_size = sizeof(struct btrfs_shared_data_ref); + } if (unlikely(btrfs_item_size(leaf, slot) != expect_item_size)) { generic_err(leaf, slot, @@ -1689,6 +1709,11 @@ static int check_extent_data_ref(struct extent_buffer *leaf, offset, leaf->fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_extent_data_ref_count(leaf, dref) == 0)) { + extent_err(leaf, slot, + "invalid extent data backref count, should have non-zero value"); + return -EUCLEAN; + } } return 0; } diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index ddf0d5a448a7..c9e92c6941ec 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -174,10 +174,10 @@ int zlib_compress_folios(struct list_head *ws, struct address_space *mapping, copy_page(workspace->buf + i * PAGE_SIZE, data_in); start += PAGE_SIZE; - workspace->strm.avail_in = - (in_buf_folios << PAGE_SHIFT); } workspace->strm.next_in = workspace->buf; + workspace->strm.avail_in = min(bytes_left, + in_buf_folios << PAGE_SHIFT); } else { unsigned int pg_off; unsigned int cur_len; diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 11ed523e528e..df905ae82929 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -748,8 +748,9 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info) (u64)lim->max_segments << PAGE_SHIFT), fs_info->sectorsize); fs_info->fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_ZONED; - if (fs_info->max_zone_append_size < fs_info->max_extent_size) - fs_info->max_extent_size = fs_info->max_zone_append_size; + + fs_info->max_extent_size = min_not_zero(fs_info->max_extent_size, + fs_info->max_zone_append_size); /* * Check mount options here, because we might change fs_info->zoned diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 89b11336a836..1806bff8e59b 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -15,6 +15,7 @@ #include <linux/namei.h> #include <linux/poll.h> #include <linux/mount.h> +#include <linux/security.h> #include <linux/statfs.h> #include <linux/ctype.h> #include <linux/string.h> @@ -576,7 +577,7 @@ static int cachefiles_daemon_dir(struct cachefiles_cache *cache, char *args) */ static int cachefiles_daemon_secctx(struct cachefiles_cache *cache, char *args) { - char *secctx; + int err; _enter(",%s", args); @@ -585,16 +586,16 @@ static int cachefiles_daemon_secctx(struct cachefiles_cache *cache, char *args) return -EINVAL; } - if (cache->secctx) { + if (cache->have_secid) { pr_err("Second security context specified\n"); return -EINVAL; } - secctx = kstrdup(args, GFP_KERNEL); - if (!secctx) - return -ENOMEM; + err = security_secctx_to_secid(args, strlen(args), &cache->secid); + if (err) + return err; - cache->secctx = secctx; + cache->have_secid = true; return 0; } @@ -820,7 +821,6 @@ static void cachefiles_daemon_unbind(struct cachefiles_cache *cache) put_cred(cache->cache_cred); kfree(cache->rootdirname); - kfree(cache->secctx); kfree(cache->tag); _leave(""); diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index 7b99bd98de75..38c236e38cef 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -122,7 +122,6 @@ struct cachefiles_cache { #define CACHEFILES_STATE_CHANGED 3 /* T if state changed (poll trigger) */ #define CACHEFILES_ONDEMAND_MODE 4 /* T if in on-demand read mode */ char *rootdirname; /* name of cache root directory */ - char *secctx; /* LSM security context */ char *tag; /* cache binding tag */ refcount_t unbind_pincount;/* refcount to do daemon unbind */ struct xarray reqs; /* xarray of pending on-demand requests */ @@ -130,6 +129,8 @@ struct cachefiles_cache { struct xarray ondemand_ids; /* xarray for ondemand_id allocation */ u32 ondemand_id_next; u32 msg_id_next; + u32 secid; /* LSM security id */ + bool have_secid; /* whether "secid" was set */ }; static inline bool cachefiles_in_ondemand_mode(struct cachefiles_cache *cache) diff --git a/fs/cachefiles/security.c b/fs/cachefiles/security.c index fe777164f1d8..fc6611886b3b 100644 --- a/fs/cachefiles/security.c +++ b/fs/cachefiles/security.c @@ -18,7 +18,7 @@ int cachefiles_get_security_ID(struct cachefiles_cache *cache) struct cred *new; int ret; - _enter("{%s}", cache->secctx); + _enter("{%u}", cache->have_secid ? cache->secid : 0); new = prepare_kernel_cred(current); if (!new) { @@ -26,8 +26,8 @@ int cachefiles_get_security_ID(struct cachefiles_cache *cache) goto error; } - if (cache->secctx) { - ret = set_security_override_from_ctx(new, cache->secctx); + if (cache->have_secid) { + ret = set_security_override(new, cache->secid); if (ret < 0) { put_cred(new); pr_err("Security denies permission to nominate security context: error %d\n", diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 4b8d59ebda00..851d70200c6b 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1066,7 +1066,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, if (ceph_inode_is_shutdown(inode)) return -EIO; - if (!len) + if (!len || !i_size) return 0; /* * flush any page cache pages in this range. this @@ -1086,7 +1086,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, int num_pages; size_t page_off; bool more; - int idx; + int idx = 0; size_t left; struct ceph_osd_req_op *op; u64 read_off = off; @@ -1116,6 +1116,16 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, len = read_off + read_len - off; more = len < iov_iter_count(to); + op = &req->r_ops[0]; + if (sparse) { + extent_cnt = __ceph_sparse_read_ext_count(inode, read_len); + ret = ceph_alloc_sparse_ext_map(op, extent_cnt); + if (ret) { + ceph_osdc_put_request(req); + break; + } + } + num_pages = calc_pages_for(read_off, read_len); page_off = offset_in_page(off); pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL); @@ -1127,17 +1137,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, osd_req_op_extent_osd_data_pages(req, 0, pages, read_len, offset_in_page(read_off), - false, false); - - op = &req->r_ops[0]; - if (sparse) { - extent_cnt = __ceph_sparse_read_ext_count(inode, read_len); - ret = ceph_alloc_sparse_ext_map(op, extent_cnt); - if (ret) { - ceph_osdc_put_request(req); - break; - } - } + false, true); ceph_osdc_start_request(osdc, req); ret = ceph_osdc_wait_request(osdc, req); @@ -1160,7 +1160,14 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, else if (ret == -ENOENT) ret = 0; - if (ret > 0 && IS_ENCRYPTED(inode)) { + if (ret < 0) { + ceph_osdc_put_request(req); + if (ret == -EBLOCKLISTED) + fsc->blocklisted = true; + break; + } + + if (IS_ENCRYPTED(inode)) { int fret; fret = ceph_fscrypt_decrypt_extents(inode, pages, @@ -1186,10 +1193,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, ret = min_t(ssize_t, fret, len); } - ceph_osdc_put_request(req); - /* Short read but not EOF? Zero out the remainder. */ - if (ret >= 0 && ret < len && (off + ret < i_size)) { + if (ret < len && (off + ret < i_size)) { int zlen = min(len - ret, i_size - off - ret); int zoff = page_off + ret; @@ -1199,13 +1204,11 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, ret += zlen; } - idx = 0; - if (ret <= 0) - left = 0; - else if (off + ret > i_size) - left = i_size - off; + if (off + ret > i_size) + left = (i_size > off) ? i_size - off : 0; else left = ret; + while (left > 0) { size_t plen, copied; @@ -1221,13 +1224,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, break; } } - ceph_release_page_vector(pages, num_pages); - if (ret < 0) { - if (ret == -EBLOCKLISTED) - fsc->blocklisted = true; - break; - } + ceph_osdc_put_request(req); if (off >= i_size || !more) break; @@ -1553,6 +1551,16 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, break; } + op = &req->r_ops[0]; + if (!write && sparse) { + extent_cnt = __ceph_sparse_read_ext_count(inode, size); + ret = ceph_alloc_sparse_ext_map(op, extent_cnt); + if (ret) { + ceph_osdc_put_request(req); + break; + } + } + len = iter_get_bvecs_alloc(iter, size, &bvecs, &num_pages); if (len < 0) { ceph_osdc_put_request(req); @@ -1562,6 +1570,8 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, if (len != size) osd_req_op_extent_update(req, 0, len); + osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len); + /* * To simplify error handling, allow AIO when IO within i_size * or IO can be satisfied by single OSD request. @@ -1593,17 +1603,6 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, req->r_mtime = mtime; } - osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len); - op = &req->r_ops[0]; - if (sparse) { - extent_cnt = __ceph_sparse_read_ext_count(inode, size); - ret = ceph_alloc_sparse_ext_map(op, extent_cnt); - if (ret) { - ceph_osdc_put_request(req); - break; - } - } - if (aio_req) { aio_req->total_len += len; aio_req->num_reqs++; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 219a2cc2bf3c..785fe489ef4b 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2800,12 +2800,11 @@ retry: if (pos < 0) { /* - * A rename didn't occur, but somehow we didn't end up where - * we thought we would. Throw a warning and try again. + * The path is longer than PATH_MAX and this function + * cannot ever succeed. Creating paths that long is + * possible with Ceph, but Linux cannot use them. */ - pr_warn_client(cl, "did not end path lookup where expected (pos = %d)\n", - pos); - goto retry; + return ERR_PTR(-ENAMETOOLONG); } *pbase = base; diff --git a/fs/ceph/super.c b/fs/ceph/super.c index de03cd6eb86e..4344e1f11806 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -431,6 +431,8 @@ static int ceph_parse_mount_param(struct fs_context *fc, switch (token) { case Opt_snapdirname: + if (strlen(param->string) > NAME_MAX) + return invalfc(fc, "snapdirname too long"); kfree(fsopt->snapdir_name); fsopt->snapdir_name = param->string; param->string = NULL; diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 47dc96dfe386..16e198a26339 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -64,22 +64,13 @@ const struct file_operations *debugfs_real_fops(const struct file *filp) } EXPORT_SYMBOL_GPL(debugfs_real_fops); -/** - * debugfs_file_get - mark the beginning of file data access - * @dentry: the dentry object whose data is being accessed. - * - * Up to a matching call to debugfs_file_put(), any successive call - * into the file removing functions debugfs_remove() and - * debugfs_remove_recursive() will block. Since associated private - * file data may only get freed after a successful return of any of - * the removal functions, you may safely access it after a successful - * call to debugfs_file_get() without worrying about lifetime issues. - * - * If -%EIO is returned, the file has already been removed and thus, - * it is not safe to access any of its data. If, on the other hand, - * it is allowed to access the file data, zero is returned. - */ -int debugfs_file_get(struct dentry *dentry) +enum dbgfs_get_mode { + DBGFS_GET_ALREADY, + DBGFS_GET_REGULAR, + DBGFS_GET_SHORT, +}; + +static int __debugfs_file_get(struct dentry *dentry, enum dbgfs_get_mode mode) { struct debugfs_fsdata *fsd; void *d_fsd; @@ -96,15 +87,17 @@ int debugfs_file_get(struct dentry *dentry) if (!((unsigned long)d_fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)) { fsd = d_fsd; } else { + if (WARN_ON(mode == DBGFS_GET_ALREADY)) + return -EINVAL; + fsd = kmalloc(sizeof(*fsd), GFP_KERNEL); if (!fsd) return -ENOMEM; - if ((unsigned long)d_fsd & DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT) { + if (mode == DBGFS_GET_SHORT) { fsd->real_fops = NULL; fsd->short_fops = (void *)((unsigned long)d_fsd & - ~(DEBUGFS_FSDATA_IS_REAL_FOPS_BIT | - DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT)); + ~DEBUGFS_FSDATA_IS_REAL_FOPS_BIT); } else { fsd->real_fops = (void *)((unsigned long)d_fsd & ~DEBUGFS_FSDATA_IS_REAL_FOPS_BIT); @@ -138,6 +131,26 @@ int debugfs_file_get(struct dentry *dentry) return 0; } + +/** + * debugfs_file_get - mark the beginning of file data access + * @dentry: the dentry object whose data is being accessed. + * + * Up to a matching call to debugfs_file_put(), any successive call + * into the file removing functions debugfs_remove() and + * debugfs_remove_recursive() will block. Since associated private + * file data may only get freed after a successful return of any of + * the removal functions, you may safely access it after a successful + * call to debugfs_file_get() without worrying about lifetime issues. + * + * If -%EIO is returned, the file has already been removed and thus, + * it is not safe to access any of its data. If, on the other hand, + * it is allowed to access the file data, zero is returned. + */ +int debugfs_file_get(struct dentry *dentry) +{ + return __debugfs_file_get(dentry, DBGFS_GET_ALREADY); +} EXPORT_SYMBOL_GPL(debugfs_file_get); /** @@ -267,7 +280,7 @@ static int open_proxy_open(struct inode *inode, struct file *filp) const struct file_operations *real_fops = NULL; int r; - r = debugfs_file_get(dentry); + r = __debugfs_file_get(dentry, DBGFS_GET_REGULAR); if (r) return r == -EIO ? -ENOENT : r; @@ -424,7 +437,8 @@ static void __full_proxy_fops_init(struct file_operations *proxy_fops, proxy_fops->unlocked_ioctl = full_proxy_unlocked_ioctl; } -static int full_proxy_open(struct inode *inode, struct file *filp) +static int full_proxy_open(struct inode *inode, struct file *filp, + enum dbgfs_get_mode mode) { struct dentry *dentry = F_DENTRY(filp); const struct file_operations *real_fops; @@ -432,7 +446,7 @@ static int full_proxy_open(struct inode *inode, struct file *filp) struct debugfs_fsdata *fsd; int r; - r = debugfs_file_get(dentry); + r = __debugfs_file_get(dentry, mode); if (r) return r == -EIO ? -ENOENT : r; @@ -491,8 +505,22 @@ out: return r; } +static int full_proxy_open_regular(struct inode *inode, struct file *filp) +{ + return full_proxy_open(inode, filp, DBGFS_GET_REGULAR); +} + const struct file_operations debugfs_full_proxy_file_operations = { - .open = full_proxy_open, + .open = full_proxy_open_regular, +}; + +static int full_proxy_open_short(struct inode *inode, struct file *filp) +{ + return full_proxy_open(inode, filp, DBGFS_GET_SHORT); +} + +const struct file_operations debugfs_full_short_proxy_file_operations = { + .open = full_proxy_open_short, }; ssize_t debugfs_attr_read(struct file *file, char __user *buf, diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 38a9c7eb97e6..e752009de929 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -229,7 +229,7 @@ static void debugfs_release_dentry(struct dentry *dentry) return; /* check it wasn't a dir (no fsdata) or automount (no real_fops) */ - if (fsd && fsd->real_fops) { + if (fsd && (fsd->real_fops || fsd->short_fops)) { WARN_ON(!list_empty(&fsd->cancellations)); mutex_destroy(&fsd->cancellations_mtx); } @@ -455,8 +455,7 @@ struct dentry *debugfs_create_file_full(const char *name, umode_t mode, const struct file_operations *fops) { if (WARN_ON((unsigned long)fops & - (DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT | - DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))) + DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)) return ERR_PTR(-EINVAL); return __debugfs_create_file(name, mode, parent, data, @@ -471,15 +470,13 @@ struct dentry *debugfs_create_file_short(const char *name, umode_t mode, const struct debugfs_short_fops *fops) { if (WARN_ON((unsigned long)fops & - (DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT | - DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))) + DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)) return ERR_PTR(-EINVAL); return __debugfs_create_file(name, mode, parent, data, - fops ? &debugfs_full_proxy_file_operations : + fops ? &debugfs_full_short_proxy_file_operations : &debugfs_noop_file_operations, - (const void *)((unsigned long)fops | - DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT)); + fops); } EXPORT_SYMBOL_GPL(debugfs_create_file_short); diff --git a/fs/debugfs/internal.h b/fs/debugfs/internal.h index a3edfa4f0d8e..bbae4a228ef4 100644 --- a/fs/debugfs/internal.h +++ b/fs/debugfs/internal.h @@ -15,6 +15,7 @@ struct file_operations; extern const struct file_operations debugfs_noop_file_operations; extern const struct file_operations debugfs_open_proxy_file_operations; extern const struct file_operations debugfs_full_proxy_file_operations; +extern const struct file_operations debugfs_full_short_proxy_file_operations; struct debugfs_fsdata { const struct file_operations *real_fops; @@ -40,11 +41,6 @@ struct debugfs_fsdata { * pointer gets its lowest bit set. */ #define DEBUGFS_FSDATA_IS_REAL_FOPS_BIT BIT(0) -/* - * A dentry's ->d_fsdata, when pointing to real fops, is with - * short fops instead of full fops. - */ -#define DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT BIT(1) /* Access BITS */ #define DEBUGFS_ALLOW_API BIT(0) diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 1c49f8962021..0cd6b5c4df98 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -56,10 +56,10 @@ void erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb) buf->file = NULL; if (erofs_is_fileio_mode(sbi)) { - buf->file = sbi->fdev; /* some fs like FUSE needs it */ + buf->file = sbi->dif0.file; /* some fs like FUSE needs it */ buf->mapping = buf->file->f_mapping; } else if (erofs_is_fscache_mode(sb)) - buf->mapping = sbi->s_fscache->inode->i_mapping; + buf->mapping = sbi->dif0.fscache->inode->i_mapping; else buf->mapping = sb->s_bdev->bd_mapping; } @@ -179,19 +179,13 @@ out: } static void erofs_fill_from_devinfo(struct erofs_map_dev *map, - struct erofs_device_info *dif) + struct super_block *sb, struct erofs_device_info *dif) { + map->m_sb = sb; + map->m_dif = dif; map->m_bdev = NULL; - map->m_fp = NULL; - if (dif->file) { - if (S_ISBLK(file_inode(dif->file)->i_mode)) - map->m_bdev = file_bdev(dif->file); - else - map->m_fp = dif->file; - } - map->m_daxdev = dif->dax_dev; - map->m_dax_part_off = dif->dax_part_off; - map->m_fscache = dif->fscache; + if (dif->file && S_ISBLK(file_inode(dif->file)->i_mode)) + map->m_bdev = file_bdev(dif->file); } int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) @@ -201,12 +195,8 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) erofs_off_t startoff, length; int id; - map->m_bdev = sb->s_bdev; - map->m_daxdev = EROFS_SB(sb)->dax_dev; - map->m_dax_part_off = EROFS_SB(sb)->dax_part_off; - map->m_fscache = EROFS_SB(sb)->s_fscache; - map->m_fp = EROFS_SB(sb)->fdev; - + erofs_fill_from_devinfo(map, sb, &EROFS_SB(sb)->dif0); + map->m_bdev = sb->s_bdev; /* use s_bdev for the primary device */ if (map->m_deviceid) { down_read(&devs->rwsem); dif = idr_find(&devs->tree, map->m_deviceid - 1); @@ -219,7 +209,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) up_read(&devs->rwsem); return 0; } - erofs_fill_from_devinfo(map, dif); + erofs_fill_from_devinfo(map, sb, dif); up_read(&devs->rwsem); } else if (devs->extra_devices && !devs->flatdev) { down_read(&devs->rwsem); @@ -232,7 +222,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) if (map->m_pa >= startoff && map->m_pa < startoff + length) { map->m_pa -= startoff; - erofs_fill_from_devinfo(map, dif); + erofs_fill_from_devinfo(map, sb, dif); break; } } @@ -302,7 +292,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, iomap->offset = map.m_la; if (flags & IOMAP_DAX) - iomap->dax_dev = mdev.m_daxdev; + iomap->dax_dev = mdev.m_dif->dax_dev; else iomap->bdev = mdev.m_bdev; iomap->length = map.m_llen; @@ -331,7 +321,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, iomap->type = IOMAP_MAPPED; iomap->addr = mdev.m_pa; if (flags & IOMAP_DAX) - iomap->addr += mdev.m_dax_part_off; + iomap->addr += mdev.m_dif->dax_part_off; } return 0; } diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c index 3af96b1e2c2a..33f8539dda4a 100644 --- a/fs/erofs/fileio.c +++ b/fs/erofs/fileio.c @@ -9,6 +9,7 @@ struct erofs_fileio_rq { struct bio_vec bvecs[BIO_MAX_VECS]; struct bio bio; struct kiocb iocb; + struct super_block *sb; }; struct erofs_fileio { @@ -52,8 +53,9 @@ static void erofs_fileio_rq_submit(struct erofs_fileio_rq *rq) rq->iocb.ki_pos = rq->bio.bi_iter.bi_sector << SECTOR_SHIFT; rq->iocb.ki_ioprio = get_current_ioprio(); rq->iocb.ki_complete = erofs_fileio_ki_complete; - rq->iocb.ki_flags = (rq->iocb.ki_filp->f_mode & FMODE_CAN_ODIRECT) ? - IOCB_DIRECT : 0; + if (test_opt(&EROFS_SB(rq->sb)->opt, DIRECT_IO) && + rq->iocb.ki_filp->f_mode & FMODE_CAN_ODIRECT) + rq->iocb.ki_flags = IOCB_DIRECT; iov_iter_bvec(&iter, ITER_DEST, rq->bvecs, rq->bio.bi_vcnt, rq->bio.bi_iter.bi_size); ret = vfs_iocb_iter_read(rq->iocb.ki_filp, &rq->iocb, &iter); @@ -67,7 +69,8 @@ static struct erofs_fileio_rq *erofs_fileio_rq_alloc(struct erofs_map_dev *mdev) GFP_KERNEL | __GFP_NOFAIL); bio_init(&rq->bio, NULL, rq->bvecs, BIO_MAX_VECS, REQ_OP_READ); - rq->iocb.ki_filp = mdev->m_fp; + rq->iocb.ki_filp = mdev->m_dif->file; + rq->sb = mdev->m_sb; return rq; } diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index fda16eedafb5..ce3d8737df85 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -198,7 +198,7 @@ struct bio *erofs_fscache_bio_alloc(struct erofs_map_dev *mdev) io = kmalloc(sizeof(*io), GFP_KERNEL | __GFP_NOFAIL); bio_init(&io->bio, NULL, io->bvecs, BIO_MAX_VECS, REQ_OP_READ); - io->io.private = mdev->m_fscache->cookie; + io->io.private = mdev->m_dif->fscache->cookie; io->io.end_io = erofs_fscache_bio_endio; refcount_set(&io->io.ref, 1); return &io->bio; @@ -316,7 +316,7 @@ static int erofs_fscache_data_read_slice(struct erofs_fscache_rq *req) if (!io) return -ENOMEM; iov_iter_xarray(&io->iter, ITER_DEST, &mapping->i_pages, pos, count); - ret = erofs_fscache_read_io_async(mdev.m_fscache->cookie, + ret = erofs_fscache_read_io_async(mdev.m_dif->fscache->cookie, mdev.m_pa + (pos - map.m_la), io); erofs_fscache_req_io_put(io); @@ -657,7 +657,7 @@ int erofs_fscache_register_fs(struct super_block *sb) if (IS_ERR(fscache)) return PTR_ERR(fscache); - sbi->s_fscache = fscache; + sbi->dif0.fscache = fscache; return 0; } @@ -665,14 +665,14 @@ void erofs_fscache_unregister_fs(struct super_block *sb) { struct erofs_sb_info *sbi = EROFS_SB(sb); - erofs_fscache_unregister_cookie(sbi->s_fscache); + erofs_fscache_unregister_cookie(sbi->dif0.fscache); if (sbi->domain) erofs_fscache_domain_put(sbi->domain); else fscache_relinquish_volume(sbi->volume, NULL, false); - sbi->s_fscache = NULL; + sbi->dif0.fscache = NULL; sbi->volume = NULL; sbi->domain = NULL; } diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 1c847c30a918..686d835eb533 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -107,6 +107,7 @@ struct erofs_xattr_prefix_item { }; struct erofs_sb_info { + struct erofs_device_info dif0; struct erofs_mount_opts opt; /* options */ #ifdef CONFIG_EROFS_FS_ZIP /* list for all registered superblocks, mainly for shrinker */ @@ -124,13 +125,9 @@ struct erofs_sb_info { struct erofs_sb_lz4_info lz4; #endif /* CONFIG_EROFS_FS_ZIP */ - struct file *fdev; struct inode *packed_inode; struct erofs_dev_context *devs; - struct dax_device *dax_dev; - u64 dax_part_off; u64 total_blocks; - u32 primarydevice_blocks; u32 meta_blkaddr; #ifdef CONFIG_EROFS_FS_XATTR @@ -166,7 +163,6 @@ struct erofs_sb_info { /* fscache support */ struct fscache_volume *volume; - struct erofs_fscache *s_fscache; struct erofs_domain *domain; char *fsid; char *domain_id; @@ -180,6 +176,7 @@ struct erofs_sb_info { #define EROFS_MOUNT_POSIX_ACL 0x00000020 #define EROFS_MOUNT_DAX_ALWAYS 0x00000040 #define EROFS_MOUNT_DAX_NEVER 0x00000080 +#define EROFS_MOUNT_DIRECT_IO 0x00000100 #define clear_opt(opt, option) ((opt)->mount_opt &= ~EROFS_MOUNT_##option) #define set_opt(opt, option) ((opt)->mount_opt |= EROFS_MOUNT_##option) @@ -187,7 +184,7 @@ struct erofs_sb_info { static inline bool erofs_is_fileio_mode(struct erofs_sb_info *sbi) { - return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->fdev; + return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->dif0.file; } static inline bool erofs_is_fscache_mode(struct super_block *sb) @@ -357,11 +354,9 @@ enum { }; struct erofs_map_dev { - struct erofs_fscache *m_fscache; + struct super_block *m_sb; + struct erofs_device_info *m_dif; struct block_device *m_bdev; - struct dax_device *m_daxdev; - struct file *m_fp; - u64 m_dax_part_off; erofs_off_t m_pa; unsigned int m_deviceid; diff --git a/fs/erofs/super.c b/fs/erofs/super.c index c235a8e4315e..f5956474bfde 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -203,7 +203,7 @@ static int erofs_scan_devices(struct super_block *sb, struct erofs_device_info *dif; int id, err = 0; - sbi->total_blocks = sbi->primarydevice_blocks; + sbi->total_blocks = sbi->dif0.blocks; if (!erofs_sb_has_device_table(sbi)) ondisk_extradevs = 0; else @@ -307,7 +307,7 @@ static int erofs_read_superblock(struct super_block *sb) sbi->sb_size); goto out; } - sbi->primarydevice_blocks = le32_to_cpu(dsb->blocks); + sbi->dif0.blocks = le32_to_cpu(dsb->blocks); sbi->meta_blkaddr = le32_to_cpu(dsb->meta_blkaddr); #ifdef CONFIG_EROFS_FS_XATTR sbi->xattr_blkaddr = le32_to_cpu(dsb->xattr_blkaddr); @@ -364,14 +364,8 @@ static void erofs_default_options(struct erofs_sb_info *sbi) } enum { - Opt_user_xattr, - Opt_acl, - Opt_cache_strategy, - Opt_dax, - Opt_dax_enum, - Opt_device, - Opt_fsid, - Opt_domain_id, + Opt_user_xattr, Opt_acl, Opt_cache_strategy, Opt_dax, Opt_dax_enum, + Opt_device, Opt_fsid, Opt_domain_id, Opt_directio, Opt_err }; @@ -398,6 +392,7 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = { fsparam_string("device", Opt_device), fsparam_string("fsid", Opt_fsid), fsparam_string("domain_id", Opt_domain_id), + fsparam_flag_no("directio", Opt_directio), {} }; @@ -511,6 +506,16 @@ static int erofs_fc_parse_param(struct fs_context *fc, errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name); break; #endif + case Opt_directio: +#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE + if (result.boolean) + set_opt(&sbi->opt, DIRECT_IO); + else + clear_opt(&sbi->opt, DIRECT_IO); +#else + errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name); +#endif + break; default: return -ENOPARAM; } @@ -602,9 +607,8 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) return -EINVAL; } - sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, - &sbi->dax_part_off, - NULL, NULL); + sbi->dif0.dax_dev = fs_dax_get_by_bdev(sb->s_bdev, + &sbi->dif0.dax_part_off, NULL, NULL); } err = erofs_read_superblock(sb); @@ -627,7 +631,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) } if (test_opt(&sbi->opt, DAX_ALWAYS)) { - if (!sbi->dax_dev) { + if (!sbi->dif0.dax_dev) { errorfc(fc, "DAX unsupported by block device. Turning off DAX."); clear_opt(&sbi->opt, DAX_ALWAYS); } else if (sbi->blkszbits != PAGE_SHIFT) { @@ -703,16 +707,18 @@ static int erofs_fc_get_tree(struct fs_context *fc) GET_TREE_BDEV_QUIET_LOOKUP : 0); #ifdef CONFIG_EROFS_FS_BACKED_BY_FILE if (ret == -ENOTBLK) { + struct file *file; + if (!fc->source) return invalf(fc, "No source specified"); - sbi->fdev = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0); - if (IS_ERR(sbi->fdev)) - return PTR_ERR(sbi->fdev); + file = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0); + if (IS_ERR(file)) + return PTR_ERR(file); + sbi->dif0.file = file; - if (S_ISREG(file_inode(sbi->fdev)->i_mode) && - sbi->fdev->f_mapping->a_ops->read_folio) + if (S_ISREG(file_inode(sbi->dif0.file)->i_mode) && + sbi->dif0.file->f_mapping->a_ops->read_folio) return get_tree_nodev(fc, erofs_fc_fill_super); - fput(sbi->fdev); } #endif return ret; @@ -763,19 +769,24 @@ static void erofs_free_dev_context(struct erofs_dev_context *devs) kfree(devs); } -static void erofs_fc_free(struct fs_context *fc) +static void erofs_sb_free(struct erofs_sb_info *sbi) { - struct erofs_sb_info *sbi = fc->s_fs_info; - - if (!sbi) - return; - erofs_free_dev_context(sbi->devs); kfree(sbi->fsid); kfree(sbi->domain_id); + if (sbi->dif0.file) + fput(sbi->dif0.file); kfree(sbi); } +static void erofs_fc_free(struct fs_context *fc) +{ + struct erofs_sb_info *sbi = fc->s_fs_info; + + if (sbi) /* free here if an error occurs before transferring to sb */ + erofs_sb_free(sbi); +} + static const struct fs_context_operations erofs_context_ops = { .parse_param = erofs_fc_parse_param, .get_tree = erofs_fc_get_tree, @@ -809,19 +820,14 @@ static void erofs_kill_sb(struct super_block *sb) { struct erofs_sb_info *sbi = EROFS_SB(sb); - if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) || sbi->fdev) + if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) || + sbi->dif0.file) kill_anon_super(sb); else kill_block_super(sb); - - erofs_free_dev_context(sbi->devs); - fs_put_dax(sbi->dax_dev, NULL); + fs_put_dax(sbi->dif0.dax_dev, NULL); erofs_fscache_unregister_fs(sb); - kfree(sbi->fsid); - kfree(sbi->domain_id); - if (sbi->fdev) - fput(sbi->fdev); - kfree(sbi); + erofs_sb_free(sbi); sb->s_fs_info = NULL; } @@ -947,6 +953,8 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",dax=always"); if (test_opt(opt, DAX_NEVER)) seq_puts(seq, ",dax=never"); + if (erofs_is_fileio_mode(sbi) && test_opt(opt, DIRECT_IO)) + seq_puts(seq, ",directio"); #ifdef CONFIG_EROFS_FS_ONDEMAND if (sbi->fsid) seq_printf(seq, ",fsid=%s", sbi->fsid); diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 01f147505487..19ef4ff2a134 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1792,9 +1792,9 @@ drain_io: erofs_fscache_submit_bio(bio); else submit_bio(bio); - if (memstall) - psi_memstall_leave(&pflags); } + if (memstall) + psi_memstall_leave(&pflags); /* * although background is preferred, no one is pending for submission. diff --git a/fs/erofs/zutil.c b/fs/erofs/zutil.c index 75704f58ecfa..0dd65cefce33 100644 --- a/fs/erofs/zutil.c +++ b/fs/erofs/zutil.c @@ -230,9 +230,10 @@ void erofs_shrinker_unregister(struct super_block *sb) struct erofs_sb_info *const sbi = EROFS_SB(sb); mutex_lock(&sbi->umount_mutex); - /* clean up all remaining pclusters in memory */ - z_erofs_shrink_scan(sbi, ~0UL); - + while (!xa_empty(&sbi->managed_pslots)) { + z_erofs_shrink_scan(sbi, ~0UL); + cond_resched(); + } spin_lock(&erofs_sb_list_lock); list_del(&sbi->list); spin_unlock(&erofs_sb_list_lock); diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c index fe0a9b8a0cd0..3103b932b674 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -122,7 +122,7 @@ static int exfat_readdir(struct inode *inode, loff_t *cpos, struct exfat_dir_ent type = exfat_get_entry_type(ep); if (type == TYPE_UNUSED) { brelse(bh); - break; + goto out; } if (type != TYPE_FILE && type != TYPE_DIR) { @@ -170,6 +170,7 @@ static int exfat_readdir(struct inode *inode, loff_t *cpos, struct exfat_dir_ent } } +out: dir_entry->namebuf.lfn[0] = '\0'; *cpos = EXFAT_DEN_TO_B(dentry); return 0; diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c index 773c320d68f3..9e5492ac409b 100644 --- a/fs/exfat/fatent.c +++ b/fs/exfat/fatent.c @@ -216,6 +216,16 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain if (err) goto dec_used_clus; + + if (num_clusters >= sbi->num_clusters - EXFAT_FIRST_CLUSTER) { + /* + * The cluster chain includes a loop, scan the + * bitmap to get the number of used clusters. + */ + exfat_count_used_clusters(sb, &sbi->used_clusters); + + return 0; + } } while (clu != EXFAT_EOF_CLUSTER); } diff --git a/fs/exfat/file.c b/fs/exfat/file.c index fb38769c3e39..05b51e721783 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -545,6 +545,7 @@ static int exfat_extend_valid_size(struct file *file, loff_t new_valid_size) while (pos < new_valid_size) { u32 len; struct folio *folio; + unsigned long off; len = PAGE_SIZE - (pos & (PAGE_SIZE - 1)); if (pos + len > new_valid_size) @@ -554,6 +555,9 @@ static int exfat_extend_valid_size(struct file *file, loff_t new_valid_size) if (err) goto out; + off = offset_in_folio(folio, pos); + folio_zero_new_buffers(folio, off, off + len); + err = ops->write_end(file, mapping, pos, len, len, folio, NULL); if (err < 0) goto out; @@ -563,6 +567,8 @@ static int exfat_extend_valid_size(struct file *file, loff_t new_valid_size) cond_resched(); } + return 0; + out: return err; } diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index 97d2774760fe..099f80645072 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -330,8 +330,8 @@ static int exfat_find_empty_entry(struct inode *inode, while ((dentry = exfat_search_empty_slot(sb, &hint_femp, p_dir, num_entries, es)) < 0) { - if (dentry == -EIO) - break; + if (dentry != -ENOSPC) + return dentry; if (exfat_check_max_dentries(inode)) return -ENOSPC; diff --git a/fs/file.c b/fs/file.c index fb1011cf6b4a..25c6e53b03f8 100644 --- a/fs/file.c +++ b/fs/file.c @@ -22,6 +22,7 @@ #include <linux/close_range.h> #include <linux/file_ref.h> #include <net/sock.h> +#include <linux/init_task.h> #include "internal.h" diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 494ac372ace0..e540d05549ff 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1681,6 +1681,8 @@ static int fuse_dir_open(struct inode *inode, struct file *file) */ if (ff->open_flags & (FOPEN_STREAM | FOPEN_NONSEEKABLE)) nonseekable_open(inode, file); + if (!(ff->open_flags & FOPEN_KEEP_CACHE)) + invalidate_inode_pages2(inode->i_mapping); } return err; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 88d0946b5bc9..7d92a5479998 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1541,8 +1541,10 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii, */ struct page **pages = kzalloc(max_pages * sizeof(struct page *), GFP_KERNEL); - if (!pages) - return -ENOMEM; + if (!pages) { + ret = -ENOMEM; + goto out; + } while (nbytes < *nbytesp && nr_pages < max_pages) { unsigned nfolios, i; @@ -1557,18 +1559,22 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii, nbytes += ret; - ret += start; - /* Currently, all folios in FUSE are one page */ - nfolios = DIV_ROUND_UP(ret, PAGE_SIZE); + nfolios = DIV_ROUND_UP(ret + start, PAGE_SIZE); + + for (i = 0; i < nfolios; i++) { + struct folio *folio = page_folio(pages[i]); + unsigned int offset = start + + (folio_page_idx(folio, pages[i]) << PAGE_SHIFT); + unsigned int len = min_t(unsigned int, ret, PAGE_SIZE - start); - ap->descs[ap->num_folios].offset = start; - fuse_folio_descs_length_init(ap->descs, ap->num_folios, nfolios); - for (i = 0; i < nfolios; i++) - ap->folios[i + ap->num_folios] = page_folio(pages[i]); + ap->descs[ap->num_folios].offset = offset; + ap->descs[ap->num_folios].length = len; + ap->folios[ap->num_folios] = folio; + start = 0; + ret -= len; + ap->num_folios++; + } - ap->num_folios += nfolios; - ap->descs[ap->num_folios - 1].length -= - (PAGE_SIZE - ret) & (PAGE_SIZE - 1); nr_pages += nfolios; } kfree(pages); @@ -1584,6 +1590,7 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii, else ap->args.out_pages = true; +out: *nbytesp = nbytes; return ret < 0 ? ret : 0; diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 3bee9b5dba5e..fe09c2093a93 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -349,11 +349,13 @@ static int hfs_fill_super(struct super_block *sb, struct fs_context *fc) goto bail_no_root; res = hfs_cat_find_brec(sb, HFS_ROOT_CNID, &fd); if (!res) { - if (fd.entrylength > sizeof(rec) || fd.entrylength < 0) { + if (fd.entrylength != sizeof(rec.dir)) { res = -EIO; goto bail_hfs_find; } hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, fd.entrylength); + if (rec.type != HFS_CDR_DIR) + res = -EIO; } if (res) goto bail_hfs_find; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 90f883d6b8fd..fc1ae5132127 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -825,7 +825,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, error = PTR_ERR(folio); goto out; } - folio_zero_user(folio, ALIGN_DOWN(addr, hpage_size)); + folio_zero_user(folio, addr); __folio_mark_uptodate(folio); error = hugetlb_add_to_page_cache(folio, mapping, index); if (unlikely(error)) { diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 955f19e27e47..d303e6c8900c 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1138,7 +1138,7 @@ static void iomap_write_delalloc_scan(struct inode *inode, start_byte, end_byte, iomap, punch); /* move offset to start of next folio in range */ - start_byte = folio_next_index(folio) << PAGE_SHIFT; + start_byte = folio_pos(folio) + folio_size(folio); folio_unlock(folio); folio_put(folio); } @@ -1774,7 +1774,8 @@ static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos) */ static int iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct writeback_control *wbc, struct folio *folio, - struct inode *inode, loff_t pos, unsigned len) + struct inode *inode, loff_t pos, loff_t end_pos, + unsigned len) { struct iomap_folio_state *ifs = folio->private; size_t poff = offset_in_folio(folio, pos); @@ -1793,15 +1794,60 @@ new_ioend: if (ifs) atomic_add(len, &ifs->write_bytes_pending); + + /* + * Clamp io_offset and io_size to the incore EOF so that ondisk + * file size updates in the ioend completion are byte-accurate. + * This avoids recovering files with zeroed tail regions when + * writeback races with appending writes: + * + * Thread 1: Thread 2: + * ------------ ----------- + * write [A, A+B] + * update inode size to A+B + * submit I/O [A, A+BS] + * write [A+B, A+B+C] + * update inode size to A+B+C + * <I/O completes, updates disk size to min(A+B+C, A+BS)> + * <power failure> + * + * After reboot: + * 1) with A+B+C < A+BS, the file has zero padding in range + * [A+B, A+B+C] + * + * |< Block Size (BS) >| + * |DDDDDDDDDDDD0000000000000| + * ^ ^ ^ + * A A+B A+B+C + * (EOF) + * + * 2) with A+B+C > A+BS, the file has zero padding in range + * [A+B, A+BS] + * + * |< Block Size (BS) >|< Block Size (BS) >| + * |DDDDDDDDDDDD0000000000000|00000000000000000000000000| + * ^ ^ ^ ^ + * A A+B A+BS A+B+C + * (EOF) + * + * D = Valid Data + * 0 = Zero Padding + * + * Note that this defeats the ability to chain the ioends of + * appending writes. + */ wpc->ioend->io_size += len; + if (wpc->ioend->io_offset + wpc->ioend->io_size > end_pos) + wpc->ioend->io_size = end_pos - wpc->ioend->io_offset; + wbc_account_cgroup_owner(wbc, folio, len); return 0; } static int iomap_writepage_map_blocks(struct iomap_writepage_ctx *wpc, struct writeback_control *wbc, struct folio *folio, - struct inode *inode, u64 pos, unsigned dirty_len, - unsigned *count) + struct inode *inode, u64 pos, u64 end_pos, + unsigned dirty_len, unsigned *count) { int error; @@ -1826,7 +1872,7 @@ static int iomap_writepage_map_blocks(struct iomap_writepage_ctx *wpc, break; default: error = iomap_add_to_ioend(wpc, wbc, folio, inode, pos, - map_len); + end_pos, map_len); if (!error) (*count)++; break; @@ -1897,11 +1943,11 @@ static bool iomap_writepage_handle_eof(struct folio *folio, struct inode *inode, * remaining memory is zeroed when mapped, and writes to that * region are not written out to the file. * - * Also adjust the writeback range to skip all blocks entirely - * beyond i_size. + * Also adjust the end_pos to the end of file and skip writeback + * for all blocks entirely beyond i_size. */ folio_zero_segment(folio, poff, folio_size(folio)); - *end_pos = round_up(isize, i_blocksize(inode)); + *end_pos = isize; } return true; @@ -1914,6 +1960,7 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc, struct inode *inode = folio->mapping->host; u64 pos = folio_pos(folio); u64 end_pos = pos + folio_size(folio); + u64 end_aligned = 0; unsigned count = 0; int error = 0; u32 rlen; @@ -1955,9 +2002,10 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc, /* * Walk through the folio to find dirty areas to write back. */ - while ((rlen = iomap_find_dirty_range(folio, &pos, end_pos))) { + end_aligned = round_up(end_pos, i_blocksize(inode)); + while ((rlen = iomap_find_dirty_range(folio, &pos, end_aligned))) { error = iomap_writepage_map_blocks(wpc, wbc, folio, inode, - pos, rlen, &count); + pos, end_pos, rlen, &count); if (error) break; pos += rlen; diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 9153ff3a08e7..e8e80761ac73 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -772,9 +772,9 @@ start_journal_io: /* * If the journal is not located on the file system device, * then we must flush the file system device before we issue - * the commit record + * the commit record and update the journal tail sequence. */ - if (commit_transaction->t_need_data_flush && + if ((commit_transaction->t_need_data_flush || update_tail) && (journal->j_fs_dev != journal->j_dev) && (journal->j_flags & JBD2_BARRIER)) blkdev_issue_flush(journal->j_fs_dev); diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c index 4556e4689024..ce63d5fde9c3 100644 --- a/fs/jbd2/revoke.c +++ b/fs/jbd2/revoke.c @@ -654,7 +654,7 @@ static void flush_descriptor(journal_t *journal, set_buffer_jwrite(descriptor); BUFFER_TRACE(descriptor, "write"); set_buffer_dirty(descriptor); - write_dirty_buffer(descriptor, REQ_SYNC); + write_dirty_buffer(descriptor, JBD2_JOURNAL_REQ_FLAGS); } #endif diff --git a/fs/mount.h b/fs/mount.h index 185fc56afc13..179f690a0c72 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -38,6 +38,7 @@ struct mount { struct dentry *mnt_mountpoint; struct vfsmount mnt; union { + struct rb_node mnt_node; /* node in the ns->mounts rbtree */ struct rcu_head mnt_rcu; struct llist_node mnt_llist; }; @@ -51,10 +52,7 @@ struct mount { struct list_head mnt_child; /* and going through their mnt_child */ struct list_head mnt_instance; /* mount instance on sb->s_mounts */ const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */ - union { - struct rb_node mnt_node; /* Under ns->mounts */ - struct list_head mnt_list; - }; + struct list_head mnt_list; struct list_head mnt_expire; /* link in fs-specific expiry list */ struct list_head mnt_share; /* circular list of shared mounts */ struct list_head mnt_slave_list;/* list of slave mounts */ @@ -145,11 +143,16 @@ static inline bool is_anon_ns(struct mnt_namespace *ns) return ns->seq == 0; } +static inline bool mnt_ns_attached(const struct mount *mnt) +{ + return !RB_EMPTY_NODE(&mnt->mnt_node); +} + static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list) { - WARN_ON(!(mnt->mnt.mnt_flags & MNT_ONRB)); - mnt->mnt.mnt_flags &= ~MNT_ONRB; + WARN_ON(!mnt_ns_attached(mnt)); rb_erase(&mnt->mnt_node, &mnt->mnt_ns->mounts); + RB_CLEAR_NODE(&mnt->mnt_node); list_add_tail(&mnt->mnt_list, dt_list); } diff --git a/fs/namespace.c b/fs/namespace.c index 23e81c2a1e3f..eac057e56948 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -344,6 +344,7 @@ static struct mount *alloc_vfsmnt(const char *name) INIT_HLIST_NODE(&mnt->mnt_mp_list); INIT_LIST_HEAD(&mnt->mnt_umounting); INIT_HLIST_HEAD(&mnt->mnt_stuck_children); + RB_CLEAR_NODE(&mnt->mnt_node); mnt->mnt.mnt_idmap = &nop_mnt_idmap; } return mnt; @@ -1124,7 +1125,7 @@ static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt) struct rb_node **link = &ns->mounts.rb_node; struct rb_node *parent = NULL; - WARN_ON(mnt->mnt.mnt_flags & MNT_ONRB); + WARN_ON(mnt_ns_attached(mnt)); mnt->mnt_ns = ns; while (*link) { parent = *link; @@ -1135,7 +1136,6 @@ static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt) } rb_link_node(&mnt->mnt_node, parent, link); rb_insert_color(&mnt->mnt_node, &ns->mounts); - mnt->mnt.mnt_flags |= MNT_ONRB; } /* @@ -1305,7 +1305,7 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root, } mnt->mnt.mnt_flags = old->mnt.mnt_flags; - mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL|MNT_ONRB); + mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL); atomic_inc(&sb->s_active); mnt->mnt.mnt_idmap = mnt_idmap_get(mnt_idmap(&old->mnt)); @@ -1763,7 +1763,7 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) /* Gather the mounts to umount */ for (p = mnt; p; p = next_mnt(p, mnt)) { p->mnt.mnt_flags |= MNT_UMOUNT; - if (p->mnt.mnt_flags & MNT_ONRB) + if (mnt_ns_attached(p)) move_from_ns(p, &tmp_list); else list_move(&p->mnt_list, &tmp_list); @@ -1912,16 +1912,14 @@ static int do_umount(struct mount *mnt, int flags) event++; if (flags & MNT_DETACH) { - if (mnt->mnt.mnt_flags & MNT_ONRB || - !list_empty(&mnt->mnt_list)) + if (mnt_ns_attached(mnt) || !list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE); retval = 0; } else { shrink_submounts(mnt); retval = -EBUSY; if (!propagate_mount_busy(mnt, 2)) { - if (mnt->mnt.mnt_flags & MNT_ONRB || - !list_empty(&mnt->mnt_list)) + if (mnt_ns_attached(mnt) || !list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); retval = 0; } @@ -2055,9 +2053,15 @@ SYSCALL_DEFINE1(oldumount, char __user *, name) static bool is_mnt_ns_file(struct dentry *dentry) { + struct ns_common *ns; + /* Is this a proxy for a mount namespace? */ - return dentry->d_op == &ns_dentry_operations && - dentry->d_fsdata == &mntns_operations; + if (dentry->d_op != &ns_dentry_operations) + return false; + + ns = d_inode(dentry)->i_private; + + return ns->ops == &mntns_operations; } struct ns_common *from_mnt_ns(struct mnt_namespace *mnt) diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 7ac34550c403..4dc9b8286355 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -275,22 +275,14 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) netfs_stat(&netfs_n_rh_download); if (rreq->netfs_ops->prepare_read) { ret = rreq->netfs_ops->prepare_read(subreq); - if (ret < 0) { - atomic_dec(&rreq->nr_outstanding); - netfs_put_subrequest(subreq, false, - netfs_sreq_trace_put_cancel); - break; - } + if (ret < 0) + goto prep_failed; trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); } slice = netfs_prepare_read_iterator(subreq); - if (slice < 0) { - atomic_dec(&rreq->nr_outstanding); - netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel); - ret = slice; - break; - } + if (slice < 0) + goto prep_iter_failed; rreq->netfs_ops->issue_read(subreq); goto done; @@ -302,6 +294,8 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) trace_netfs_sreq(subreq, netfs_sreq_trace_submit); netfs_stat(&netfs_n_rh_zero); slice = netfs_prepare_read_iterator(subreq); + if (slice < 0) + goto prep_iter_failed; __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); netfs_read_subreq_terminated(subreq, 0, false); goto done; @@ -310,6 +304,8 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) if (source == NETFS_READ_FROM_CACHE) { trace_netfs_sreq(subreq, netfs_sreq_trace_submit); slice = netfs_prepare_read_iterator(subreq); + if (slice < 0) + goto prep_iter_failed; netfs_read_cache_to_pagecache(rreq, subreq); goto done; } @@ -318,6 +314,14 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) WARN_ON_ONCE(1); break; + prep_iter_failed: + ret = slice; + prep_failed: + subreq->error = ret; + atomic_dec(&rreq->nr_outstanding); + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel); + break; + done: size -= slice; start += slice; diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index 88f2adfab75e..f9421f3e6d37 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -67,7 +67,7 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * * allocate a sufficiently large bvec array and may shorten the * request. */ - if (async || user_backed_iter(iter)) { + if (user_backed_iter(iter)) { n = netfs_extract_user_iter(iter, len, &wreq->iter, 0); if (n < 0) { ret = n; @@ -77,6 +77,11 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * wreq->direct_bv_count = n; wreq->direct_bv_unpin = iov_iter_extract_will_pin(iter); } else { + /* If this is a kernel-generated async DIO request, + * assume that any resources the iterator points to + * (eg. a bio_vec array) will persist till the end of + * the op. + */ wreq->iter = *iter; } @@ -104,7 +109,6 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * trace_netfs_rreq(wreq, netfs_rreq_trace_wait_ip); wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS, TASK_UNINTERRUPTIBLE); - smp_rmb(); /* Read error/transferred after RIP flag */ ret = wreq->error; if (ret == 0) { ret = wreq->transferred; diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index 3cbb289535a8..e8624f5c7fcc 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -62,10 +62,14 @@ static void netfs_unlock_read_folio(struct netfs_io_subrequest *subreq, } else { trace_netfs_folio(folio, netfs_folio_trace_read_done); } + + folioq_clear(folioq, slot); } else { // TODO: Use of PG_private_2 is deprecated. if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) netfs_pgpriv2_mark_copy_to_cache(subreq, rreq, folioq, slot); + else + folioq_clear(folioq, slot); } if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { @@ -77,8 +81,6 @@ static void netfs_unlock_read_folio(struct netfs_io_subrequest *subreq, folio_unlock(folio); } } - - folioq_clear(folioq, slot); } /* @@ -247,16 +249,17 @@ donation_changed: /* Deal with the trickiest case: that this subreq is in the middle of a * folio, not touching either edge, but finishes first. In such a - * case, we donate to the previous subreq, if there is one, so that the - * donation is only handled when that completes - and remove this - * subreq from the list. + * case, we donate to the previous subreq, if there is one and if it is + * contiguous, so that the donation is only handled when that completes + * - and remove this subreq from the list. * * If the previous subreq finished first, we will have acquired their * donation and should be able to unlock folios and/or donate nextwards. */ if (!subreq->consumed && !prev_donated && - !list_is_first(&subreq->rreq_link, &rreq->subrequests)) { + !list_is_first(&subreq->rreq_link, &rreq->subrequests) && + subreq->start == prev->start + prev->len) { prev = list_prev_entry(subreq, rreq_link); WRITE_ONCE(prev->next_donated, prev->next_donated + subreq->len); subreq->start += subreq->len; @@ -378,8 +381,7 @@ static void netfs_rreq_assess(struct netfs_io_request *rreq) task_io_account_read(rreq->transferred); trace_netfs_rreq(rreq, netfs_rreq_trace_wake_ip); - clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags); - wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); + clear_and_wake_up_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags); trace_netfs_rreq(rreq, netfs_rreq_trace_done); netfs_clear_subrequests(rreq, false); @@ -438,7 +440,7 @@ void netfs_read_subreq_progress(struct netfs_io_subrequest *subreq, rreq->origin == NETFS_READPAGE || rreq->origin == NETFS_READ_FOR_WRITE)) { netfs_consume_read_data(subreq, was_async); - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); } } EXPORT_SYMBOL(netfs_read_subreq_progress); @@ -497,7 +499,7 @@ void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq, rreq->origin == NETFS_READPAGE || rreq->origin == NETFS_READ_FOR_WRITE)) { netfs_consume_read_data(subreq, was_async); - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); } rreq->transferred += subreq->transferred; } @@ -511,10 +513,13 @@ void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq, } else { trace_netfs_sreq(subreq, netfs_sreq_trace_short); if (subreq->transferred > subreq->consumed) { - __set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); - set_bit(NETFS_RREQ_NEED_RETRY, &rreq->flags); - } else if (!__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) { + /* If we didn't read new data, abandon retry. */ + if (subreq->retry_count && + test_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags)) { + __set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); + set_bit(NETFS_RREQ_NEED_RETRY, &rreq->flags); + } + } else if (test_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags)) { __set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); set_bit(NETFS_RREQ_NEED_RETRY, &rreq->flags); } else { diff --git a/fs/netfs/read_pgpriv2.c b/fs/netfs/read_pgpriv2.c index ba5af89d37fa..54d5004fec18 100644 --- a/fs/netfs/read_pgpriv2.c +++ b/fs/netfs/read_pgpriv2.c @@ -170,6 +170,10 @@ void netfs_pgpriv2_write_to_the_cache(struct netfs_io_request *rreq) trace_netfs_write(wreq, netfs_write_trace_copy_to_cache); netfs_stat(&netfs_n_wh_copy_to_cache); + if (!wreq->io_streams[1].avail) { + netfs_put_request(wreq, false, netfs_rreq_trace_put_return); + goto couldnt_start; + } for (;;) { error = netfs_pgpriv2_copy_folio(wreq, folio); diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c index 0350592ea804..16b676c68dcd 100644 --- a/fs/netfs/read_retry.c +++ b/fs/netfs/read_retry.c @@ -49,13 +49,15 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) * up to the first permanently failed one. */ if (!rreq->netfs_ops->prepare_read && - !test_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags)) { + !rreq->cache_resources.ops) { struct netfs_io_subrequest *subreq; list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) break; if (__test_and_clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) { + __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + subreq->retry_count++; netfs_reset_iter(subreq); netfs_reissue_read(rreq, subreq); } @@ -137,7 +139,8 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) stream0->sreq_max_len = subreq->len; __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); + __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + subreq->retry_count++; spin_lock_bh(&rreq->lock); list_add_tail(&subreq->rreq_link, &rreq->subrequests); @@ -149,7 +152,8 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) BUG_ON(!len); /* Renegotiate max_len (rsize) */ - if (rreq->netfs_ops->prepare_read(subreq) < 0) { + if (rreq->netfs_ops->prepare_read && + rreq->netfs_ops->prepare_read(subreq) < 0) { trace_netfs_sreq(subreq, netfs_sreq_trace_reprep_failed); __set_bit(NETFS_SREQ_FAILED, &subreq->flags); } @@ -213,7 +217,6 @@ abandon: subreq->error = -ENOMEM; __clear_bit(NETFS_SREQ_FAILED, &subreq->flags); __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - __clear_bit(NETFS_SREQ_RETRYING, &subreq->flags); } spin_lock_bh(&rreq->lock); list_splice_tail_init(&queue, &rreq->subrequests); diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 1d438be2e1b4..ca3a11ed9b54 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -179,7 +179,6 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, struct iov_iter source = subreq->io_iter; iov_iter_revert(&source, subreq->len - source.count); - __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); netfs_reissue_write(stream, subreq, &source); } @@ -234,7 +233,7 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, /* Renegotiate max_len (wsize) */ trace_netfs_sreq(subreq, netfs_sreq_trace_retry); __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); + subreq->retry_count++; stream->prepare_write(subreq); part = min(len, stream->sreq_max_len); @@ -279,7 +278,7 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, subreq->start = start; subreq->debug_index = atomic_inc_return(&wreq->subreq_counter); subreq->stream_nr = to->stream_nr; - __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); + subreq->retry_count = 1; trace_netfs_sreq_ref(wreq->debug_id, subreq->debug_index, refcount_read(&subreq->ref), @@ -501,8 +500,7 @@ reassess_streams: goto need_retry; if ((notes & MADE_PROGRESS) && test_bit(NETFS_RREQ_PAUSE, &wreq->flags)) { trace_netfs_rreq(wreq, netfs_rreq_trace_unpause); - clear_bit_unlock(NETFS_RREQ_PAUSE, &wreq->flags); - wake_up_bit(&wreq->flags, NETFS_RREQ_PAUSE); + clear_and_wake_up_bit(NETFS_RREQ_PAUSE, &wreq->flags); } if (notes & NEED_REASSESS) { @@ -605,8 +603,7 @@ void netfs_write_collection_worker(struct work_struct *work) _debug("finished"); trace_netfs_rreq(wreq, netfs_rreq_trace_wake_ip); - clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &wreq->flags); - wake_up_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS); + clear_and_wake_up_bit(NETFS_RREQ_IN_PROGRESS, &wreq->flags); if (wreq->iocb) { size_t written = min(wreq->transferred, wreq->len); @@ -714,8 +711,7 @@ void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error, trace_netfs_sreq(subreq, netfs_sreq_trace_terminated); - clear_bit_unlock(NETFS_SREQ_IN_PROGRESS, &subreq->flags); - wake_up_bit(&subreq->flags, NETFS_SREQ_IN_PROGRESS); + clear_and_wake_up_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); /* If we are at the head of the queue, wake up the collector, * transferring a ref to it if we were the ones to do so. diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index bf6d507578e5..ff0e82505a0b 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -244,6 +244,8 @@ void netfs_reissue_write(struct netfs_io_stream *stream, iov_iter_advance(source, size); iov_iter_truncate(&subreq->io_iter, size); + subreq->retry_count++; + __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); netfs_do_issue_write(stream, subreq); } diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 810269ee0a50..d49e4ce27999 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -263,6 +263,12 @@ int nfs_netfs_readahead(struct readahead_control *ractl) static atomic_t nfs_netfs_debug_id; static int nfs_netfs_init_request(struct netfs_io_request *rreq, struct file *file) { + if (!file) { + if (WARN_ON_ONCE(rreq->origin != NETFS_PGPRIV2_COPY_TO_CACHE)) + return -EIO; + return 0; + } + rreq->netfs_priv = get_nfs_open_context(nfs_file_open_context(file)); rreq->debug_id = atomic_inc_return(&nfs_netfs_debug_id); /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ @@ -274,7 +280,8 @@ static int nfs_netfs_init_request(struct netfs_io_request *rreq, struct file *fi static void nfs_netfs_free_request(struct netfs_io_request *rreq) { - put_nfs_open_context(rreq->netfs_priv); + if (rreq->netfs_priv) + put_nfs_open_context(rreq->netfs_priv); } static struct nfs_netfs_io_data *nfs_netfs_alloc(struct netfs_io_subrequest *sreq) diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 0d16b383a452..5f582713bf05 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1308,7 +1308,7 @@ pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo, enum pnfs_iomode *iomode) { /* Serialise LAYOUTGET/LAYOUTRETURN */ - if (atomic_read(&lo->plh_outstanding) != 0) + if (atomic_read(&lo->plh_outstanding) != 0 && lo->plh_return_seq == 0) return false; if (test_and_set_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) return false; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index ae5c5e39afa0..aeb715b4a690 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -73,6 +73,7 @@ #include "nfs.h" #include "netns.h" #include "sysfs.h" +#include "nfs4idmap.h" #define NFSDBG_FACILITY NFSDBG_VFS diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index eacafe46e3b6..aa4712362b3b 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -40,24 +40,15 @@ #define EXPKEY_HASHMAX (1 << EXPKEY_HASHBITS) #define EXPKEY_HASHMASK (EXPKEY_HASHMAX -1) -static void expkey_put_work(struct work_struct *work) +static void expkey_put(struct kref *ref) { - struct svc_expkey *key = - container_of(to_rcu_work(work), struct svc_expkey, ek_rcu_work); + struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref); if (test_bit(CACHE_VALID, &key->h.flags) && !test_bit(CACHE_NEGATIVE, &key->h.flags)) path_put(&key->ek_path); auth_domain_put(key->ek_client); - kfree(key); -} - -static void expkey_put(struct kref *ref) -{ - struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref); - - INIT_RCU_WORK(&key->ek_rcu_work, expkey_put_work); - queue_rcu_work(system_wq, &key->ek_rcu_work); + kfree_rcu(key, ek_rcu); } static int expkey_upcall(struct cache_detail *cd, struct cache_head *h) @@ -364,26 +355,16 @@ static void export_stats_destroy(struct export_stats *stats) EXP_STATS_COUNTERS_NUM); } -static void svc_export_put_work(struct work_struct *work) +static void svc_export_put(struct kref *ref) { - struct svc_export *exp = - container_of(to_rcu_work(work), struct svc_export, ex_rcu_work); - + struct svc_export *exp = container_of(ref, struct svc_export, h.ref); path_put(&exp->ex_path); auth_domain_put(exp->ex_client); nfsd4_fslocs_free(&exp->ex_fslocs); export_stats_destroy(exp->ex_stats); kfree(exp->ex_stats); kfree(exp->ex_uuid); - kfree(exp); -} - -static void svc_export_put(struct kref *ref) -{ - struct svc_export *exp = container_of(ref, struct svc_export, h.ref); - - INIT_RCU_WORK(&exp->ex_rcu_work, svc_export_put_work); - queue_rcu_work(system_wq, &exp->ex_rcu_work); + kfree_rcu(exp, ex_rcu); } static int svc_export_upcall(struct cache_detail *cd, struct cache_head *h) diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h index 6f2fbaae01fa..4d92b99c1ffd 100644 --- a/fs/nfsd/export.h +++ b/fs/nfsd/export.h @@ -75,7 +75,7 @@ struct svc_export { u32 ex_layout_types; struct nfsd4_deviceid_map *ex_devid_map; struct cache_detail *cd; - struct rcu_work ex_rcu_work; + struct rcu_head ex_rcu; unsigned long ex_xprtsec_modes; struct export_stats *ex_stats; }; @@ -92,7 +92,7 @@ struct svc_expkey { u32 ek_fsid[6]; struct path ek_path; - struct rcu_work ek_rcu_work; + struct rcu_head ek_rcu; }; #define EX_ISSYNC(exp) (!((exp)->ex_flags & NFSEXP_ASYNC)) diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 3877b53e429f..c083e539e898 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -1100,7 +1100,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c args.authflavor = clp->cl_cred.cr_flavor; clp->cl_cb_ident = conn->cb_ident; } else { - if (!conn->cb_xprt) + if (!conn->cb_xprt || !ses) return -EINVAL; clp->cl_cb_session = ses; args.bc_xprt = conn->cb_xprt; @@ -1522,8 +1522,6 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) ses = c->cn_session; } spin_unlock(&clp->cl_lock); - if (!c) - return; err = setup_callback_client(clp, &conn, ses); if (err) { diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index f8a10f90bc7a..ad44ad49274f 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1347,7 +1347,6 @@ static void nfs4_put_copy(struct nfsd4_copy *copy) { if (!refcount_dec_and_test(©->refcount)) return; - atomic_dec(©->cp_nn->pending_async_copies); kfree(copy->cp_src); kfree(copy); } @@ -1870,6 +1869,7 @@ 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); return 0; } @@ -1927,19 +1927,19 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, /* Arbitrary cap on number of pending async copy operations */ if (atomic_inc_return(&nn->pending_async_copies) > (int)rqstp->rq_pool->sp_nrthreads) - goto out_err; + goto out_dec_async_copy_err; async_copy->cp_src = kmalloc(sizeof(*async_copy->cp_src), GFP_KERNEL); if (!async_copy->cp_src) - goto out_err; + goto out_dec_async_copy_err; if (!nfs4_init_copy_state(nn, copy)) - goto out_err; + goto out_dec_async_copy_err; memcpy(&result->cb_stateid, ©->cp_stateid.cs_stid, sizeof(result->cb_stateid)); dup_copy_fields(copy, async_copy); async_copy->copy_task = kthread_create(nfsd4_do_async_copy, async_copy, "%s", "copy thread"); if (IS_ERR(async_copy->copy_task)) - goto out_err; + goto out_dec_async_copy_err; spin_lock(&async_copy->cp_clp->async_lock); list_add(&async_copy->copies, &async_copy->cp_clp->async_copies); @@ -1954,6 +1954,9 @@ out: trace_nfsd_copy_done(copy, status); release_copy_files(copy); return status; +out_dec_async_copy_err: + if (async_copy) + atomic_dec(&nn->pending_async_copies); out_err: if (nfsd4_ssc_is_inter(copy)) { /* diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index 501ad7be5174..54a3fa0cf67e 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -35,6 +35,7 @@ void nilfs_init_btnc_inode(struct inode *btnc_inode) ii->i_flags = 0; memset(&ii->i_bmap_data, 0, sizeof(struct nilfs_bmap)); mapping_set_gfp_mask(btnc_inode->i_mapping, GFP_NOFS); + btnc_inode->i_mapping->a_ops = &nilfs_buffer_cache_aops; } void nilfs_btnode_cache_clear(struct address_space *btnc) diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index ace22253fed0..2dbb15767df1 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -163,7 +163,7 @@ int nilfs_init_gcinode(struct inode *inode) inode->i_mode = S_IFREG; mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); - inode->i_mapping->a_ops = &empty_aops; + inode->i_mapping->a_ops = &nilfs_buffer_cache_aops; ii->i_flags = 0; nilfs_bmap_init_gc(ii->i_bmap); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index cf9ba481ae37..23f3a75edd50 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -276,6 +276,10 @@ const struct address_space_operations nilfs_aops = { .is_partially_uptodate = block_is_partially_uptodate, }; +const struct address_space_operations nilfs_buffer_cache_aops = { + .invalidate_folio = block_invalidate_folio, +}; + static int nilfs_insert_inode_locked(struct inode *inode, struct nilfs_root *root, unsigned long ino) @@ -544,8 +548,14 @@ struct inode *nilfs_iget(struct super_block *sb, struct nilfs_root *root, inode = nilfs_iget_locked(sb, root, ino); if (unlikely(!inode)) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + + if (!(inode->i_state & I_NEW)) { + if (!inode->i_nlink) { + iput(inode); + return ERR_PTR(-ESTALE); + } return inode; + } err = __nilfs_read_inode(sb, root, ino, inode); if (unlikely(err)) { @@ -675,6 +685,7 @@ struct inode *nilfs_iget_for_shadow(struct inode *inode) NILFS_I(s_inode)->i_flags = 0; memset(NILFS_I(s_inode)->i_bmap, 0, sizeof(struct nilfs_bmap)); mapping_set_gfp_mask(s_inode->i_mapping, GFP_NOFS); + s_inode->i_mapping->a_ops = &nilfs_buffer_cache_aops; err = nilfs_attach_btree_node_cache(s_inode); if (unlikely(err)) { diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index 9b108052d9f7..1d836a5540f3 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -67,6 +67,11 @@ nilfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) inode = NULL; } else { inode = nilfs_iget(dir->i_sb, NILFS_I(dir)->i_root, ino); + if (inode == ERR_PTR(-ESTALE)) { + nilfs_error(dir->i_sb, + "deleted inode referenced: %lu", ino); + return ERR_PTR(-EIO); + } } return d_splice_alias(inode, dentry); diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 45d03826eaf1..dff241c53fc5 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -401,6 +401,7 @@ extern const struct file_operations nilfs_dir_operations; extern const struct inode_operations nilfs_file_inode_operations; extern const struct file_operations nilfs_file_operations; extern const struct address_space_operations nilfs_aops; +extern const struct address_space_operations nilfs_buffer_cache_aops; extern const struct inode_operations nilfs_dir_inode_operations; extern const struct inode_operations nilfs_special_inode_operations; extern const struct inode_operations nilfs_symlink_inode_operations; diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c index dec553034027..e933f9c65d90 100644 --- a/fs/notify/fdinfo.c +++ b/fs/notify/fdinfo.c @@ -47,10 +47,8 @@ static void show_mark_fhandle(struct seq_file *m, struct inode *inode) size = f->handle_bytes >> 2; ret = exportfs_encode_fid(inode, (struct fid *)f->f_handle, &size); - if ((ret == FILEID_INVALID) || (ret < 0)) { - WARN_ONCE(1, "Can't encode file handler for inotify: %d\n", ret); + if ((ret == FILEID_INVALID) || (ret < 0)) return; - } f->handle_type = ret; f->handle_bytes = size * sizeof(u32); diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index 8ac42ea81a17..d1aa04a5af1b 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -971,9 +971,9 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb, start = count = 0; left = le32_to_cpu(alloc->id1.bitmap1.i_total); - while ((bit_off = ocfs2_find_next_zero_bit(bitmap, left, start)) < - left) { - if (bit_off == start) { + while (1) { + bit_off = ocfs2_find_next_zero_bit(bitmap, left, start); + if ((bit_off < left) && (bit_off == start)) { count++; start++; continue; @@ -998,29 +998,12 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb, } } + if (bit_off >= left) + break; count = 1; start = bit_off + 1; } - /* clear the contiguous bits until the end boundary */ - if (count) { - blkno = la_start_blk + - ocfs2_clusters_to_blocks(osb->sb, - start - count); - - trace_ocfs2_sync_local_to_main_free( - count, start - count, - (unsigned long long)la_start_blk, - (unsigned long long)blkno); - - status = ocfs2_release_clusters(handle, - main_bm_inode, - main_bm_bh, blkno, - count); - if (status < 0) - mlog_errno(status); - } - bail: if (status) mlog_errno(status); diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index 2b0daced98eb..3404e7a30c33 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -893,7 +893,7 @@ static int ocfs2_get_next_id(struct super_block *sb, struct kqid *qid) int status = 0; trace_ocfs2_get_next_id(from_kqid(&init_user_ns, *qid), type); - if (!sb_has_quota_loaded(sb, type)) { + if (!sb_has_quota_active(sb, type)) { status = -ESRCH; goto out; } diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 73d3367c533b..2956d888c131 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -867,6 +867,7 @@ out: brelse(oinfo->dqi_libh); brelse(oinfo->dqi_lqi_bh); kfree(oinfo); + info->dqi_priv = NULL; return status; } diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 3601ddfeddc2..0c28e5fa3407 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -415,13 +415,13 @@ int ovl_set_attr(struct ovl_fs *ofs, struct dentry *upperdentry, return err; } -struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real, +struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct inode *realinode, bool is_upper) { struct ovl_fh *fh; int fh_type, dwords; int buflen = MAX_HANDLE_SZ; - uuid_t *uuid = &real->d_sb->s_uuid; + uuid_t *uuid = &realinode->i_sb->s_uuid; int err; /* Make sure the real fid stays 32bit aligned */ @@ -438,13 +438,13 @@ struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real, * the price or reconnecting the dentry. */ dwords = buflen >> 2; - fh_type = exportfs_encode_fh(real, (void *)fh->fb.fid, &dwords, 0); + fh_type = exportfs_encode_inode_fh(realinode, (void *)fh->fb.fid, + &dwords, NULL, 0); buflen = (dwords << 2); err = -EIO; - if (WARN_ON(fh_type < 0) || - WARN_ON(buflen > MAX_HANDLE_SZ) || - WARN_ON(fh_type == FILEID_INVALID)) + if (fh_type < 0 || fh_type == FILEID_INVALID || + WARN_ON(buflen > MAX_HANDLE_SZ)) goto out_err; fh->fb.version = OVL_FH_VERSION; @@ -480,7 +480,7 @@ struct ovl_fh *ovl_get_origin_fh(struct ovl_fs *ofs, struct dentry *origin) if (!ovl_can_decode_fh(origin->d_sb)) return NULL; - return ovl_encode_real_fh(ofs, origin, false); + return ovl_encode_real_fh(ofs, d_inode(origin), false); } int ovl_set_origin_fh(struct ovl_fs *ofs, const struct ovl_fh *fh, @@ -505,7 +505,7 @@ static int ovl_set_upper_fh(struct ovl_fs *ofs, struct dentry *upper, const struct ovl_fh *fh; int err; - fh = ovl_encode_real_fh(ofs, upper, true); + fh = ovl_encode_real_fh(ofs, d_inode(upper), true); if (IS_ERR(fh)) return PTR_ERR(fh); diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index 5868cb222955..444aeeccb6da 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -176,35 +176,37 @@ static int ovl_connect_layer(struct dentry *dentry) * * Return 0 for upper file handle, > 0 for lower file handle or < 0 on error. */ -static int ovl_check_encode_origin(struct dentry *dentry) +static int ovl_check_encode_origin(struct inode *inode) { - struct ovl_fs *ofs = OVL_FS(dentry->d_sb); + struct ovl_fs *ofs = OVL_FS(inode->i_sb); bool decodable = ofs->config.nfs_export; + struct dentry *dentry; + int err; /* No upper layer? */ if (!ovl_upper_mnt(ofs)) return 1; /* Lower file handle for non-upper non-decodable */ - if (!ovl_dentry_upper(dentry) && !decodable) + if (!ovl_inode_upper(inode) && !decodable) return 1; /* Upper file handle for pure upper */ - if (!ovl_dentry_lower(dentry)) + if (!ovl_inode_lower(inode)) return 0; /* * Root is never indexed, so if there's an upper layer, encode upper for * root. */ - if (dentry == dentry->d_sb->s_root) + if (inode == d_inode(inode->i_sb->s_root)) return 0; /* * Upper decodable file handle for non-indexed upper. */ - if (ovl_dentry_upper(dentry) && decodable && - !ovl_test_flag(OVL_INDEX, d_inode(dentry))) + if (ovl_inode_upper(inode) && decodable && + !ovl_test_flag(OVL_INDEX, inode)) return 0; /* @@ -213,14 +215,23 @@ static int ovl_check_encode_origin(struct dentry *dentry) * ovl_connect_layer() will try to make origin's layer "connected" by * copying up a "connectable" ancestor. */ - if (d_is_dir(dentry) && decodable) - return ovl_connect_layer(dentry); + if (!decodable || !S_ISDIR(inode->i_mode)) + return 1; + + dentry = d_find_any_alias(inode); + if (!dentry) + return -ENOENT; + + err = ovl_connect_layer(dentry); + dput(dentry); + if (err < 0) + return err; /* Lower file handle for indexed and non-upper dir/non-dir */ return 1; } -static int ovl_dentry_to_fid(struct ovl_fs *ofs, struct dentry *dentry, +static int ovl_dentry_to_fid(struct ovl_fs *ofs, struct inode *inode, u32 *fid, int buflen) { struct ovl_fh *fh = NULL; @@ -231,13 +242,13 @@ static int ovl_dentry_to_fid(struct ovl_fs *ofs, struct dentry *dentry, * Check if we should encode a lower or upper file handle and maybe * copy up an ancestor to make lower file handle connectable. */ - err = enc_lower = ovl_check_encode_origin(dentry); + err = enc_lower = ovl_check_encode_origin(inode); if (enc_lower < 0) goto fail; /* Encode an upper or lower file handle */ - fh = ovl_encode_real_fh(ofs, enc_lower ? ovl_dentry_lower(dentry) : - ovl_dentry_upper(dentry), !enc_lower); + fh = ovl_encode_real_fh(ofs, enc_lower ? ovl_inode_lower(inode) : + ovl_inode_upper(inode), !enc_lower); if (IS_ERR(fh)) return PTR_ERR(fh); @@ -251,8 +262,8 @@ out: return err; fail: - pr_warn_ratelimited("failed to encode file handle (%pd2, err=%i)\n", - dentry, err); + pr_warn_ratelimited("failed to encode file handle (ino=%lu, err=%i)\n", + inode->i_ino, err); goto out; } @@ -260,19 +271,13 @@ static int ovl_encode_fh(struct inode *inode, u32 *fid, int *max_len, struct inode *parent) { struct ovl_fs *ofs = OVL_FS(inode->i_sb); - struct dentry *dentry; int bytes, buflen = *max_len << 2; /* TODO: encode connectable file handles */ if (parent) return FILEID_INVALID; - dentry = d_find_any_alias(inode); - if (!dentry) - return FILEID_INVALID; - - bytes = ovl_dentry_to_fid(ofs, dentry, fid, buflen); - dput(dentry); + bytes = ovl_dentry_to_fid(ofs, inode, fid, buflen); if (bytes <= 0) return FILEID_INVALID; diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index 7e27b7d4adee..cea820cb3b55 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -542,7 +542,7 @@ int ovl_verify_origin_xattr(struct ovl_fs *ofs, struct dentry *dentry, struct ovl_fh *fh; int err; - fh = ovl_encode_real_fh(ofs, real, is_upper); + fh = ovl_encode_real_fh(ofs, d_inode(real), is_upper); err = PTR_ERR(fh); if (IS_ERR(fh)) { fh = NULL; @@ -738,7 +738,7 @@ int ovl_get_index_name(struct ovl_fs *ofs, struct dentry *origin, struct ovl_fh *fh; int err; - fh = ovl_encode_real_fh(ofs, origin, false); + fh = ovl_encode_real_fh(ofs, d_inode(origin), false); if (IS_ERR(fh)) return PTR_ERR(fh); diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index b361f35762be..0021e2025020 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -865,7 +865,7 @@ int ovl_copy_up_with_data(struct dentry *dentry); int ovl_maybe_copy_up(struct dentry *dentry, int flags); int ovl_copy_xattr(struct super_block *sb, const struct path *path, struct dentry *new); int ovl_set_attr(struct ovl_fs *ofs, struct dentry *upper, struct kstat *stat); -struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real, +struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct inode *realinode, bool is_upper); struct ovl_fh *ovl_get_origin_fh(struct ovl_fs *ofs, struct dentry *origin); int ovl_set_origin_fh(struct ovl_fs *ofs, const struct ovl_fh *fh, diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 38a5a3e9cba2..f02cd362309a 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1810,7 +1810,7 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, } for (; addr != end; addr += PAGE_SIZE, idx++) { - unsigned long cur_flags = flags; + u64 cur_flags = flags; pagemap_entry_t pme; if (folio && (flags & PM_PRESENT) && diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 3d8a82cee63e..658bf199d424 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -404,6 +404,8 @@ static ssize_t __read_vmcore(struct iov_iter *iter, loff_t *fpos) if (!iov_iter_count(iter)) return acc; } + + cond_resched(); } return acc; diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index 85925ec0051a..3310d1ad4d0e 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -179,8 +179,7 @@ static int qnx6_statfs(struct dentry *dentry, struct kstatfs *buf) */ static const char *qnx6_checkroot(struct super_block *s) { - static char match_root[2][3] = {".\0\0", "..\0"}; - int i, error = 0; + int error = 0; struct qnx6_dir_entry *dir_entry; struct inode *root = d_inode(s->s_root); struct address_space *mapping = root->i_mapping; @@ -189,11 +188,9 @@ static const char *qnx6_checkroot(struct super_block *s) if (IS_ERR(folio)) return "error reading root directory"; dir_entry = kmap_local_folio(folio, 0); - for (i = 0; i < 2; i++) { - /* maximum 3 bytes - due to match_root limitation */ - if (strncmp(dir_entry[i].de_fname, match_root[i], 3)) - error = 1; - } + if (memcmp(dir_entry[0].de_fname, ".", 2) || + memcmp(dir_entry[1].de_fname, "..", 3)) + error = 1; folio_release_kmap(folio, dir_entry); if (error) return "error reading root directory."; diff --git a/fs/smb/client/Kconfig b/fs/smb/client/Kconfig index 2aff6d1395ce..9f05f94e265a 100644 --- a/fs/smb/client/Kconfig +++ b/fs/smb/client/Kconfig @@ -2,7 +2,6 @@ config CIFS tristate "SMB3 and CIFS support (advanced network filesystem)" depends on INET - select NETFS_SUPPORT select NLS select NLS_UCS2_UTILS select CRYPTO diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 9d96b833015c..b800c9f585d8 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -398,7 +398,7 @@ cifs_alloc_inode(struct super_block *sb) cifs_inode = alloc_inode_sb(sb, cifs_inode_cachep, GFP_KERNEL); if (!cifs_inode) return NULL; - cifs_inode->cifsAttrs = 0x20; /* default */ + cifs_inode->cifsAttrs = ATTR_ARCHIVE; /* default */ cifs_inode->time = 0; /* * Until the file is open and we have gotten oplock info back from the diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index 754417cb3294..d26f9bbb5382 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -614,8 +614,6 @@ int cifs_alloc_hash(const char *name, struct shash_desc **sdesc); void cifs_free_hash(struct shash_desc **sdesc); int cifs_try_adding_channels(struct cifs_ses *ses); -bool is_server_using_iface(struct TCP_Server_Info *server, - struct cifs_server_iface *iface); bool is_ses_using_iface(struct cifs_ses *ses, struct cifs_server_iface *iface); void cifs_ses_mark_for_reconnect(struct cifs_ses *ses); diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index bd42a419458e..6cb1e81993f8 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1319,14 +1319,16 @@ cifs_readv_callback(struct mid_q_entry *mid) } if (rdata->result == -ENODATA) { - __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; + __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); } else { size_t trans = rdata->subreq.transferred + rdata->got_bytes; if (trans < rdata->subreq.len && rdata->subreq.start + trans == ictx->remote_i_size) { - __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; + __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); + } else if (rdata->got_bytes > 0) { + __set_bit(NETFS_SREQ_MADE_PROGRESS, &rdata->subreq.flags); } } @@ -1670,10 +1672,13 @@ cifs_writev_callback(struct mid_q_entry *mid) if (written > wdata->subreq.len) written &= 0xFFFF; - if (written < wdata->subreq.len) + if (written < wdata->subreq.len) { result = -ENOSPC; - else + } else { result = written; + if (written > 0) + __set_bit(NETFS_SREQ_MADE_PROGRESS, &wdata->subreq.flags); + } break; case MID_REQUEST_SUBMITTED: case MID_RETRY_NEEDED: diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 2372538a1211..ddcc9e514a0e 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -987,9 +987,13 @@ clean_demultiplex_info(struct TCP_Server_Info *server) msleep(125); if (cifs_rdma_enabled(server)) smbd_destroy(server); + if (server->ssocket) { sock_release(server->ssocket); server->ssocket = NULL; + + /* Release netns reference for the socket. */ + put_net(cifs_net_ns(server)); } if (!list_empty(&server->pending_mid_q)) { @@ -1037,6 +1041,7 @@ clean_demultiplex_info(struct TCP_Server_Info *server) */ } + /* Release netns reference for this server. */ put_net(cifs_net_ns(server)); kfree(server->leaf_fullpath); kfree(server); @@ -1713,6 +1718,8 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx, tcp_ses->ops = ctx->ops; tcp_ses->vals = ctx->vals; + + /* Grab netns reference for this server. */ cifs_set_net_ns(tcp_ses, get_net(current->nsproxy->net_ns)); tcp_ses->conn_id = atomic_inc_return(&tcpSesNextId); @@ -1844,6 +1851,7 @@ smbd_connected: out_err_crypto_release: cifs_crypto_secmech_release(tcp_ses); + /* Release netns reference for this server. */ put_net(cifs_net_ns(tcp_ses)); out_err: @@ -1852,8 +1860,10 @@ out_err: cifs_put_tcp_session(tcp_ses->primary_server, false); kfree(tcp_ses->hostname); kfree(tcp_ses->leaf_fullpath); - if (tcp_ses->ssocket) + if (tcp_ses->ssocket) { sock_release(tcp_ses->ssocket); + put_net(cifs_net_ns(tcp_ses)); + } kfree(tcp_ses); } return ERR_PTR(rc); @@ -3131,20 +3141,20 @@ generic_ip_connect(struct TCP_Server_Info *server) socket = server->ssocket; } else { struct net *net = cifs_net_ns(server); - struct sock *sk; - rc = __sock_create(net, sfamily, SOCK_STREAM, - IPPROTO_TCP, &server->ssocket, 1); + rc = sock_create_kern(net, sfamily, SOCK_STREAM, IPPROTO_TCP, &server->ssocket); if (rc < 0) { cifs_server_dbg(VFS, "Error %d creating socket\n", rc); return rc; } - sk = server->ssocket->sk; - __netns_tracker_free(net, &sk->ns_tracker, false); - sk->sk_net_refcnt = 1; - get_net_track(net, &sk->ns_tracker, GFP_KERNEL); - sock_inuse_add(net, 1); + /* + * Grab netns reference for the socket. + * + * It'll be released here, on error, or in clean_demultiplex_info() upon server + * teardown. + */ + get_net(net); /* BB other socket options to set KEEPALIVE, NODELAY? */ cifs_dbg(FYI, "Socket created\n"); @@ -3158,8 +3168,10 @@ generic_ip_connect(struct TCP_Server_Info *server) } rc = bind_socket(server); - if (rc < 0) + if (rc < 0) { + put_net(cifs_net_ns(server)); return rc; + } /* * Eventually check for other socket options to change from @@ -3196,6 +3208,7 @@ generic_ip_connect(struct TCP_Server_Info *server) if (rc < 0) { cifs_dbg(FYI, "Error %d connecting to server\n", rc); trace_smb3_connect_err(server->hostname, server->conn_id, &server->dstaddr, rc); + put_net(cifs_net_ns(server)); sock_release(socket); server->ssocket = NULL; return rc; @@ -3204,6 +3217,9 @@ generic_ip_connect(struct TCP_Server_Info *server) if (sport == htons(RFC1001_PORT)) rc = ip_rfc1001_connect(server); + if (rc < 0) + put_net(cifs_net_ns(server)); + return rc; } diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index a58a3333ecc3..3b2d33291a7e 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -990,7 +990,11 @@ int cifs_open(struct inode *inode, struct file *file) } /* Get the cached handle as SMB2 close is deferred */ - rc = cifs_get_readable_path(tcon, full_path, &cfile); + if (OPEN_FMODE(file->f_flags) & FMODE_WRITE) { + rc = cifs_get_writable_path(tcon, full_path, FIND_WR_FSUID_ONLY, &cfile); + } else { + rc = cifs_get_readable_path(tcon, full_path, &cfile); + } if (rc == 0) { if (file->f_flags == cfile->f_flags) { file->private_data = cfile; diff --git a/fs/smb/client/namespace.c b/fs/smb/client/namespace.c index 0f788031b740..e3f9213131c4 100644 --- a/fs/smb/client/namespace.c +++ b/fs/smb/client/namespace.c @@ -196,11 +196,28 @@ static struct vfsmount *cifs_do_automount(struct path *path) struct smb3_fs_context tmp; char *full_path; struct vfsmount *mnt; + struct cifs_sb_info *mntpt_sb; + struct cifs_ses *ses; if (IS_ROOT(mntpt)) return ERR_PTR(-ESTALE); - cur_ctx = CIFS_SB(mntpt->d_sb)->ctx; + mntpt_sb = CIFS_SB(mntpt->d_sb); + ses = cifs_sb_master_tcon(mntpt_sb)->ses; + cur_ctx = mntpt_sb->ctx; + + /* + * At this point, the root session should be in the mntpt sb. We should + * bring the sb context passwords in sync with the root session's + * passwords. This would help prevent unnecessary retries and password + * swaps for automounts. + */ + mutex_lock(&ses->session_mutex); + rc = smb3_sync_session_ctx_passwords(mntpt_sb, ses); + mutex_unlock(&ses->session_mutex); + + if (rc) + return ERR_PTR(rc); fc = fs_context_for_submount(path->mnt->mnt_sb->s_type, mntpt); if (IS_ERR(fc)) diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index 3306fb655136..91d4d409cb1d 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -27,31 +27,6 @@ static int cifs_ses_add_channel(struct cifs_ses *ses, struct cifs_server_iface *iface); -bool -is_server_using_iface(struct TCP_Server_Info *server, - struct cifs_server_iface *iface) -{ - struct sockaddr_in *i4 = (struct sockaddr_in *)&iface->sockaddr; - struct sockaddr_in6 *i6 = (struct sockaddr_in6 *)&iface->sockaddr; - struct sockaddr_in *s4 = (struct sockaddr_in *)&server->dstaddr; - struct sockaddr_in6 *s6 = (struct sockaddr_in6 *)&server->dstaddr; - - if (server->dstaddr.ss_family != iface->sockaddr.ss_family) - return false; - if (server->dstaddr.ss_family == AF_INET) { - if (s4->sin_addr.s_addr != i4->sin_addr.s_addr) - return false; - } else if (server->dstaddr.ss_family == AF_INET6) { - if (memcmp(&s6->sin6_addr, &i6->sin6_addr, - sizeof(i6->sin6_addr)) != 0) - return false; - } else { - /* unknown family.. */ - return false; - } - return true; -} - bool is_ses_using_iface(struct cifs_ses *ses, struct cifs_server_iface *iface) { int i; diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 010eae9d6c47..0577556f0a41 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4615,6 +4615,7 @@ smb2_readv_callback(struct mid_q_entry *mid) __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; } + __set_bit(NETFS_SREQ_MADE_PROGRESS, &rdata->subreq.flags); } trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, rdata->credits.value, server->credits, server->in_flight, @@ -4840,10 +4841,14 @@ smb2_writev_callback(struct mid_q_entry *mid) if (written > wdata->subreq.len) written &= 0xFFFF; - if (written < wdata->subreq.len) + cifs_stats_bytes_written(tcon, written); + + if (written < wdata->subreq.len) { wdata->result = -ENOSPC; - else + } else if (written > 0) { wdata->subreq.len = written; + __set_bit(NETFS_SREQ_MADE_PROGRESS, &wdata->subreq.flags); + } break; case MID_REQUEST_SUBMITTED: case MID_RETRY_NEEDED: @@ -5012,7 +5017,7 @@ smb2_async_writev(struct cifs_io_subrequest *wdata) } #endif - if (test_bit(NETFS_SREQ_RETRYING, &wdata->subreq.flags)) + if (wdata->subreq.retry_count > 0) smb2_set_replay(server, &rqst); cifs_dbg(FYI, "async write at %llu %u bytes iter=%zx\n", @@ -5156,6 +5161,7 @@ replay_again: cifs_dbg(VFS, "Send error in write = %d\n", rc); } else { *nbytes = le32_to_cpu(rsp->DataLength); + cifs_stats_bytes_written(io_parms->tcon, *nbytes); trace_smb3_write_done(0, 0, xid, req->PersistentFileId, io_parms->tcon->tid, @@ -6204,7 +6210,7 @@ SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon, req->StructureSize = cpu_to_le16(36); total_len += 12; - memcpy(req->LeaseKey, lease_key, 16); + memcpy(req->LeaseKey, lease_key, SMB2_LEASE_KEY_SIZE); req->LeaseState = lease_state; flags |= CIFS_NO_RSP_BUF; diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index c14dd72e1b30..f8a40f65db6a 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -70,7 +70,6 @@ struct ksmbd_conn *ksmbd_conn_alloc(void) atomic_set(&conn->req_running, 0); atomic_set(&conn->r_count, 0); atomic_set(&conn->refcnt, 1); - atomic_set(&conn->mux_smb_requests, 0); conn->total_credits = 1; conn->outstanding_credits = 0; @@ -120,8 +119,8 @@ void ksmbd_conn_enqueue_request(struct ksmbd_work *work) if (conn->ops->get_cmd_val(work) != SMB2_CANCEL_HE) requests_queue = &conn->requests; + atomic_inc(&conn->req_running); if (requests_queue) { - atomic_inc(&conn->req_running); spin_lock(&conn->request_lock); list_add_tail(&work->request_entry, requests_queue); spin_unlock(&conn->request_lock); @@ -132,11 +131,14 @@ void ksmbd_conn_try_dequeue_request(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; + atomic_dec(&conn->req_running); + if (waitqueue_active(&conn->req_running_q)) + wake_up(&conn->req_running_q); + if (list_empty(&work->request_entry) && list_empty(&work->async_request_entry)) return; - atomic_dec(&conn->req_running); spin_lock(&conn->request_lock); list_del_init(&work->request_entry); spin_unlock(&conn->request_lock); @@ -308,7 +310,7 @@ int ksmbd_conn_handler_loop(void *p) { struct ksmbd_conn *conn = (struct ksmbd_conn *)p; struct ksmbd_transport *t = conn->transport; - unsigned int pdu_size, max_allowed_pdu_size; + unsigned int pdu_size, max_allowed_pdu_size, max_req; char hdr_buf[4] = {0,}; int size; @@ -318,6 +320,7 @@ int ksmbd_conn_handler_loop(void *p) if (t->ops->prepare && t->ops->prepare(t)) goto out; + max_req = server_conf.max_inflight_req; conn->last_active = jiffies; set_freezable(); while (ksmbd_conn_alive(conn)) { @@ -327,6 +330,13 @@ int ksmbd_conn_handler_loop(void *p) kvfree(conn->request_buf); conn->request_buf = NULL; +recheck: + if (atomic_read(&conn->req_running) + 1 > max_req) { + wait_event_interruptible(conn->req_running_q, + atomic_read(&conn->req_running) < max_req); + goto recheck; + } + size = t->ops->read(t, hdr_buf, sizeof(hdr_buf), -1); if (size != sizeof(hdr_buf)) break; diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index 8ddd5a3c7baf..b379ae4fdcdf 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -107,7 +107,6 @@ struct ksmbd_conn { __le16 signing_algorithm; bool binding; atomic_t refcnt; - atomic_t mux_smb_requests; }; struct ksmbd_conn_ops { diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index 3ba95bd8edeb..601e7fcbcf1e 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -270,7 +270,6 @@ static void handle_ksmbd_work(struct work_struct *wk) ksmbd_conn_try_dequeue_request(work); ksmbd_free_work_struct(work); - atomic_dec(&conn->mux_smb_requests); /* * Checking waitqueue to dropping pending requests on * disconnection. waitqueue_active is safe because it @@ -300,11 +299,6 @@ static int queue_ksmbd_work(struct ksmbd_conn *conn) if (err) return 0; - if (atomic_inc_return(&conn->mux_smb_requests) >= conn->vals->max_credits) { - atomic_dec_return(&conn->mux_smb_requests); - return -ENOSPC; - } - work = ksmbd_alloc_work_struct(); if (!work) { pr_err("allocation for work failed\n"); @@ -367,6 +361,7 @@ static int server_conf_init(void) server_conf.auth_mechs |= KSMBD_AUTH_KRB5 | KSMBD_AUTH_MSKRB5; #endif + server_conf.max_inflight_req = SMB2_MAX_CREDITS; return 0; } diff --git a/fs/smb/server/server.h b/fs/smb/server/server.h index 4fc529335271..94187628ff08 100644 --- a/fs/smb/server/server.h +++ b/fs/smb/server/server.h @@ -42,6 +42,7 @@ struct ksmbd_server_config { struct smb_sid domain_sid; unsigned int auth_mechs; unsigned int max_connections; + unsigned int max_inflight_req; char *conf[SERVER_CONF_WORK_GROUP + 1]; struct task_struct *dh_task; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 803b35b89513..772deec5b90f 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -695,6 +695,9 @@ void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status) struct smb2_hdr *rsp_hdr; struct ksmbd_work *in_work = ksmbd_alloc_work_struct(); + if (!in_work) + return; + if (allocate_interim_rsp_buf(in_work)) { pr_err("smb_allocate_rsp_buf failed!\n"); ksmbd_free_work_struct(in_work); @@ -1097,6 +1100,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) return rc; } + ksmbd_conn_lock(conn); smb2_buf_len = get_rfc1002_len(work->request_buf); smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects); if (smb2_neg_size > smb2_buf_len) { @@ -1247,6 +1251,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) ksmbd_conn_set_need_negotiate(conn); err_out: + ksmbd_conn_unlock(conn); if (rc) rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES; @@ -3989,6 +3994,26 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level, posix_info->DeviceId = cpu_to_le32(ksmbd_kstat->kstat->rdev); posix_info->HardLinks = cpu_to_le32(ksmbd_kstat->kstat->nlink); posix_info->Mode = cpu_to_le32(ksmbd_kstat->kstat->mode & 0777); + switch (ksmbd_kstat->kstat->mode & S_IFMT) { + case S_IFDIR: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_DIR << POSIX_FILETYPE_SHIFT); + break; + case S_IFLNK: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_SYMLINK << POSIX_FILETYPE_SHIFT); + break; + case S_IFCHR: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_CHARDEV << POSIX_FILETYPE_SHIFT); + break; + case S_IFBLK: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_BLKDEV << POSIX_FILETYPE_SHIFT); + break; + case S_IFIFO: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_FIFO << POSIX_FILETYPE_SHIFT); + break; + case S_IFSOCK: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_SOCKET << POSIX_FILETYPE_SHIFT); + } + posix_info->Inode = cpu_to_le64(ksmbd_kstat->kstat->ino); posix_info->DosAttributes = S_ISDIR(ksmbd_kstat->kstat->mode) ? @@ -5179,6 +5204,26 @@ static int find_file_posix_info(struct smb2_query_info_rsp *rsp, file_info->AllocationSize = cpu_to_le64(stat.blocks << 9); file_info->HardLinks = cpu_to_le32(stat.nlink); file_info->Mode = cpu_to_le32(stat.mode & 0777); + switch (stat.mode & S_IFMT) { + case S_IFDIR: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_DIR << POSIX_FILETYPE_SHIFT); + break; + case S_IFLNK: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_SYMLINK << POSIX_FILETYPE_SHIFT); + break; + case S_IFCHR: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_CHARDEV << POSIX_FILETYPE_SHIFT); + break; + case S_IFBLK: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_BLKDEV << POSIX_FILETYPE_SHIFT); + break; + case S_IFIFO: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_FIFO << POSIX_FILETYPE_SHIFT); + break; + case S_IFSOCK: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_SOCKET << POSIX_FILETYPE_SHIFT); + } + file_info->DeviceId = cpu_to_le32(stat.rdev); /* diff --git a/fs/smb/server/smb2pdu.h b/fs/smb/server/smb2pdu.h index 649dacf7e8c4..17a0b18a8406 100644 --- a/fs/smb/server/smb2pdu.h +++ b/fs/smb/server/smb2pdu.h @@ -502,4 +502,14 @@ static inline void *smb2_get_msg(void *buf) return buf + 4; } +#define POSIX_TYPE_FILE 0 +#define POSIX_TYPE_DIR 1 +#define POSIX_TYPE_SYMLINK 2 +#define POSIX_TYPE_CHARDEV 3 +#define POSIX_TYPE_BLKDEV 4 +#define POSIX_TYPE_FIFO 5 +#define POSIX_TYPE_SOCKET 6 + +#define POSIX_FILETYPE_SHIFT 12 + #endif /* _SMB2PDU_H */ diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index 48cda3350e5a..befaf42b84cc 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -319,8 +319,11 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req) init_smb2_max_write_size(req->smb2_max_write); if (req->smb2_max_trans) init_smb2_max_trans_size(req->smb2_max_trans); - if (req->smb2_max_credits) + if (req->smb2_max_credits) { init_smb2_max_credits(req->smb2_max_credits); + server_conf.max_inflight_req = + req->smb2_max_credits; + } if (req->smbd_max_io_size) init_smbd_max_io_size(req->smbd_max_io_size); diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index 0ef3c9f0bfeb..c3785a5434f9 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -2283,8 +2283,7 @@ out: ibdev = ib_device_get_by_netdev(netdev, RDMA_DRIVER_UNKNOWN); if (ibdev) { - if (rdma_frwr_is_supported(&ibdev->attrs)) - rdma_capable = true; + rdma_capable = rdma_frwr_is_supported(&ibdev->attrs); ib_device_put(ibdev); } } diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index 88d167a5f8b7..40f08eac519c 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -1264,6 +1264,8 @@ int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, filepath, flags, path); + if (!is_last) + next[0] = '/'; if (err) goto out2; else if (is_last) @@ -1271,7 +1273,6 @@ int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, path_put(parent_path); *parent_path = *path; - next[0] = '/'; remain_len -= filename_len + 1; } diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h index 7e7e491ff06f..2d7822644eff 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.h +++ b/fs/xfs/libxfs/xfs_rtgroup.h @@ -272,7 +272,7 @@ static inline int xfs_initialize_rtgroups(struct xfs_mount *mp, } # define xfs_rtgroup_extents(mp, rgno) (0) -# define xfs_update_last_rtgroup_size(mp, rgno) (-EOPNOTSUPP) +# define xfs_update_last_rtgroup_size(mp, rgno) (0) # define xfs_rtgroup_lock(rtg, gf) ((void)0) # define xfs_rtgroup_unlock(rtg, gf) ((void)0) # define xfs_rtgroup_trans_join(tp, rtg, gf) ((void)0) diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index f11d475898f2..201c26322ede 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -87,8 +87,9 @@ xfs_dquot_detach_buf( } spin_unlock(&qlip->qli_lock); if (bp) { + xfs_buf_lock(bp); list_del_init(&qlip->qli_item.li_bio_list); - xfs_buf_rele(bp); + xfs_buf_relse(bp); } } diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h index 6cdc873ac907..aa5233b1eba9 100644 --- a/include/clocksource/hyperv_timer.h +++ b/include/clocksource/hyperv_timer.h @@ -38,6 +38,8 @@ extern void hv_remap_tsc_clocksource(void); extern unsigned long hv_get_tsc_pfn(void); extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void); +extern void hv_adj_sched_clock_offset(u64 offset); + static __always_inline bool hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc, u64 *time) diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index e61dd7dd2286..147bd3ee4f7b 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -53,8 +53,7 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1); void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu); void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu); void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu); -void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val); -void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val); +void kvm_pmu_reprogram_counter_mask(struct kvm_vcpu *vcpu, u64 val); void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu); void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu); bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu); @@ -127,8 +126,7 @@ static inline u64 kvm_pmu_accessible_counter_mask(struct kvm_vcpu *vcpu) static inline void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) {} -static inline void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) {} -static inline void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) {} +static inline void kvm_pmu_reprogram_counter_mask(struct kvm_vcpu *vcpu, u64 val) {} static inline void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu) {} static inline bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu) diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index 7c0786bdf9af..0bbbe537c5f9 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -63,7 +63,12 @@ static inline void set_codetag_empty(union codetag_ref *ref) #else /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */ static inline bool is_codetag_empty(union codetag_ref *ref) { return false; } -static inline void set_codetag_empty(union codetag_ref *ref) {} + +static inline void set_codetag_empty(union codetag_ref *ref) +{ + if (ref) + ref->ct = NULL; +} #endif /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */ @@ -135,7 +140,7 @@ static inline struct alloc_tag_counters alloc_tag_read(struct alloc_tag *tag) #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG static inline void alloc_tag_add_check(union codetag_ref *ref, struct alloc_tag *tag) { - WARN_ONCE(ref && ref->ct, + WARN_ONCE(ref && ref->ct && !is_codetag_empty(ref), "alloc_tag was not cleared (got tag for %s:%u)\n", ref->ct->filename, ref->ct->lineno); diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index a28e2a6a13d0..74169dd0f659 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -166,9 +166,12 @@ static inline void *ffa_dev_get_drvdata(struct ffa_device *fdev) return dev_get_drvdata(&fdev->dev); } +struct ffa_partition_info; + #if IS_REACHABLE(CONFIG_ARM_FFA_TRANSPORT) -struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, - const struct ffa_ops *ops); +struct ffa_device * +ffa_device_register(const struct ffa_partition_info *part_info, + const struct ffa_ops *ops); void ffa_device_unregister(struct ffa_device *ffa_dev); int ffa_driver_register(struct ffa_driver *driver, struct module *owner, const char *mod_name); @@ -176,9 +179,9 @@ void ffa_driver_unregister(struct ffa_driver *driver); bool ffa_device_is_valid(struct ffa_device *ffa_dev); #else -static inline -struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, - const struct ffa_ops *ops) +static inline struct ffa_device * +ffa_device_register(const struct ffa_partition_info *part_info, + const struct ffa_ops *ops) { return NULL; } diff --git a/include/linux/bus/stm32_firewall_device.h b/include/linux/bus/stm32_firewall_device.h index 18e0a2fc3816..5178b72bc920 100644 --- a/include/linux/bus/stm32_firewall_device.h +++ b/include/linux/bus/stm32_firewall_device.h @@ -115,7 +115,7 @@ void stm32_firewall_release_access_by_id(struct stm32_firewall *firewall, u32 su #else /* CONFIG_STM32_FIREWALL */ int stm32_firewall_get_firewall(struct device_node *np, struct stm32_firewall *firewall, - unsigned int nb_firewall); + unsigned int nb_firewall) { return -ENODEV; } diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 108060612bb8..7ad736538649 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -155,8 +155,14 @@ static inline int get_cpu_cacheinfo_id(int cpu, int level) #ifndef CONFIG_ARCH_HAS_CPU_CACHE_ALIASING #define cpu_dcache_is_aliasing() false +#define cpu_icache_is_aliasing() cpu_dcache_is_aliasing() #else #include <asm/cachetype.h> + +#ifndef cpu_icache_is_aliasing +#define cpu_icache_is_aliasing() cpu_dcache_is_aliasing() +#endif + #endif #endif /* _LINUX_CACHEINFO_H */ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 469a64dd6495..240c632c5b95 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -216,28 +216,43 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #endif /* __KERNEL__ */ +/** + * offset_to_ptr - convert a relative memory offset to an absolute pointer + * @off: the address of the 32-bit offset value + */ +static inline void *offset_to_ptr(const int *off) +{ + return (void *)((unsigned long)off + *off); +} + +#endif /* __ASSEMBLY__ */ + +#ifdef CONFIG_64BIT +#define ARCH_SEL(a,b) a +#else +#define ARCH_SEL(a,b) b +#endif + /* * Force the compiler to emit 'sym' as a symbol, so that we can reference * it from inline assembler. Necessary in case 'sym' could be inlined * otherwise, or eliminated entirely due to lack of references that are * visible to the compiler. */ -#define ___ADDRESSABLE(sym, __attrs) \ - static void * __used __attrs \ +#define ___ADDRESSABLE(sym, __attrs) \ + static void * __used __attrs \ __UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)(uintptr_t)&sym; + #define __ADDRESSABLE(sym) \ ___ADDRESSABLE(sym, __section(".discard.addressable")) -/** - * offset_to_ptr - convert a relative memory offset to an absolute pointer - * @off: the address of the 32-bit offset value - */ -static inline void *offset_to_ptr(const int *off) -{ - return (void *)((unsigned long)off + *off); -} +#define __ADDRESSABLE_ASM(sym) \ + .pushsection .discard.addressable,"aw"; \ + .align ARCH_SEL(8,4); \ + ARCH_SEL(.quad, .long) __stringify(sym); \ + .popsection; -#endif /* __ASSEMBLY__ */ +#define __ADDRESSABLE_ASM_STR(sym) __stringify(__ADDRESSABLE_ASM(sym)) #ifdef __CHECKER__ #define __BUILD_BUG_ON_ZERO_MSG(e, msg) (0) diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index b137fdb56093..346251bf1026 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -84,7 +84,7 @@ enum dma_transfer_direction { DMA_TRANS_NONE, }; -/** +/* * Interleaved Transfer Request * ---------------------------- * A chunk is collection of contiguous bytes to be transferred. @@ -223,7 +223,7 @@ enum sum_check_bits { }; /** - * enum pq_check_flags - result of async_{xor,pq}_zero_sum operations + * enum sum_check_flags - result of async_{xor,pq}_zero_sum operations * @SUM_CHECK_P_RESULT - 1 if xor zero sum error, 0 otherwise * @SUM_CHECK_Q_RESULT - 1 if reed-solomon zero sum error, 0 otherwise */ @@ -286,7 +286,7 @@ typedef struct { DECLARE_BITMAP(bits, DMA_TX_TYPE_END); } dma_cap_mask_t; * pointer to the engine's metadata area * 4. Read out the metadata from the pointer * - * Note: the two mode is not compatible and clients must use one mode for a + * Warning: the two modes are not compatible and clients must use one mode for a * descriptor. */ enum dma_desc_metadata_mode { @@ -594,9 +594,13 @@ struct dma_descriptor_metadata_ops { * @phys: physical address of the descriptor * @chan: target channel for this operation * @tx_submit: accept the descriptor, assign ordered cookie and mark the + * @desc_free: driver's callback function to free a resusable descriptor + * after completion * descriptor pending. To be pushed on .issue_pending() call * @callback: routine to call after this operation is complete + * @callback_result: error result from a DMA transaction * @callback_param: general parameter to pass to the callback routine + * @unmap: hook for generic DMA unmap data * @desc_metadata_mode: core managed metadata mode to protect mixed use of * DESC_METADATA_CLIENT or DESC_METADATA_ENGINE. Otherwise * DESC_METADATA_NONE @@ -827,6 +831,9 @@ struct dma_filter { * @device_prep_dma_memset: prepares a memset operation * @device_prep_dma_memset_sg: prepares a memset operation over a scatter list * @device_prep_dma_interrupt: prepares an end of chain interrupt operation + * @device_prep_peripheral_dma_vec: prepares a scatter-gather DMA transfer, + * where the address and size of each segment is located in one entry of + * the dma_vec array. * @device_prep_slave_sg: prepares a slave dma operation * @device_prep_dma_cyclic: prepare a cyclic dma operation suitable for audio. * The function takes a buffer of size buf_len. The callback function will diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 0d99bf11d260..e4ce1cae03bf 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -616,6 +616,12 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, return false; } +/* + * To work around what seems to be an optimizer bug, the macro arguments + * need to have const copies or the values end up changed by the time they + * reach fortify_warn_once(). See commit 6f7630b1b5bc ("fortify: Capture + * __bos() results in const temp vars") for more details. + */ #define __fortify_memcpy_chk(p, q, size, p_size, q_size, \ p_size_field, q_size_field, op) ({ \ const size_t __fortify_size = (size_t)(size); \ @@ -623,6 +629,8 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, const size_t __q_size = (q_size); \ const size_t __p_size_field = (p_size_field); \ const size_t __q_size_field = (q_size_field); \ + /* Keep a mutable version of the size for the final copy. */ \ + size_t __copy_size = __fortify_size; \ fortify_warn_once(fortify_memcpy_chk(__fortify_size, __p_size, \ __q_size, __p_size_field, \ __q_size_field, FORTIFY_FUNC_ ##op), \ @@ -630,7 +638,11 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, __fortify_size, \ "field \"" #p "\" at " FILE_LINE, \ __p_size_field); \ - __underlying_##op(p, q, __fortify_size); \ + /* Hide only the run-time size from value range tracking to */ \ + /* silence compile-time false positive bounds warnings. */ \ + if (!__builtin_constant_p(__copy_size)) \ + OPTIMIZER_HIDE_VAR(__copy_size); \ + __underlying_##op(p, q, __copy_size); \ }) /* diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 6e452bd8e7e3..5c6bea81a90e 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -224,7 +224,13 @@ static inline struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr) { - return vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr); + struct folio *folio; + + folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr); + if (folio && user_alloc_needs_zeroing()) + clear_user_highpage(&folio->page, vaddr); + + return folio; } #endif diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 22c22fb91042..02a226bcf0ed 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1559,6 +1559,7 @@ struct hv_util_service { void *channel; void (*util_cb)(void *); int (*util_init)(struct hv_util_service *); + int (*util_init_transport)(void); void (*util_deinit)(void); int (*util_pre_suspend)(void); int (*util_pre_resume)(void); diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index c1645c86eed9..d65b5d71b93b 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -585,13 +585,16 @@ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) * vlan_get_protocol - get protocol EtherType. * @skb: skbuff to query * @type: first vlan protocol + * @mac_offset: MAC offset * @depth: buffer to store length of eth and vlan tags in bytes * * Returns the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ -static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, - int *depth) +static inline __be16 __vlan_get_protocol_offset(const struct sk_buff *skb, + __be16 type, + int mac_offset, + int *depth) { unsigned int vlan_depth = skb->mac_len, parse_depth = VLAN_MAX_DEPTH; @@ -610,7 +613,8 @@ static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, do { struct vlan_hdr vhdr, *vh; - vh = skb_header_pointer(skb, vlan_depth, sizeof(vhdr), &vhdr); + vh = skb_header_pointer(skb, mac_offset + vlan_depth, + sizeof(vhdr), &vhdr); if (unlikely(!vh || !--parse_depth)) return 0; @@ -625,6 +629,12 @@ static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, return type; } +static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, + int *depth) +{ + return __vlan_get_protocol_offset(skb, type, 0, depth); +} + /** * vlan_get_protocol - get protocol EtherType. * @skb: skbuff to query diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index e123d5e17b52..85fe4e6b275c 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -15,10 +15,8 @@ bool io_is_uring_fops(struct file *file); static inline void io_uring_files_cancel(void) { - if (current->io_uring) { - io_uring_unreg_ringfd(); + if (current->io_uring) __io_uring_cancel(false); - } } static inline void io_uring_task_cancel(void) { diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h index 0d5448c0b86c..a3ce553413de 100644 --- a/include/linux/io_uring/cmd.h +++ b/include/linux/io_uring/cmd.h @@ -18,6 +18,11 @@ struct io_uring_cmd { u8 pdu[32]; /* available inline for free use */ }; +struct io_uring_cmd_data { + struct io_uring_sqe sqes[2]; + void *op_data; +}; + static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe) { return sqe->cmd; @@ -113,4 +118,9 @@ static inline struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd return cmd_to_io_kiocb(cmd)->tctx->task; } +static inline struct io_uring_cmd_data *io_uring_cmd_get_async_data(struct io_uring_cmd *cmd) +{ + return cmd_to_io_kiocb(cmd)->async_data; +} + #endif /* _LINUX_IO_URING_CMD_H */ diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 011860ade268..fd4cdb0860a2 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -345,7 +345,7 @@ struct io_ring_ctx { /* timeouts */ struct { - spinlock_t timeout_lock; + raw_spinlock_t timeout_lock; struct list_head timeout_list; struct list_head ltimeout_list; unsigned cq_last_tm_flush; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 5675af6b740c..75bf54e76f3b 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -335,7 +335,7 @@ struct iomap_ioend { u16 io_type; u16 io_flags; /* IOMAP_F_* */ struct inode *io_inode; /* file being written to */ - size_t io_size; /* size of the extent */ + size_t io_size; /* size of data within eof */ loff_t io_offset; /* offset in the file */ sector_t io_sector; /* start sector of ioend */ struct bio io_bio; /* MUST BE LAST! */ diff --git a/include/linux/memfd.h b/include/linux/memfd.h index 3f2cf339ceaf..d437e3070850 100644 --- a/include/linux/memfd.h +++ b/include/linux/memfd.h @@ -7,6 +7,7 @@ #ifdef CONFIG_MEMFD_CREATE extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg); struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx); +unsigned int *memfd_file_seals_ptr(struct file *file); #else static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a) { @@ -16,6 +17,19 @@ static inline struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx) { return ERR_PTR(-EINVAL); } + +static inline unsigned int *memfd_file_seals_ptr(struct file *file) +{ + return NULL; +} #endif +/* Retrieve memfd seals associated with the file, if any. */ +static inline unsigned int memfd_file_seals(struct file *file) +{ + unsigned int *sealsp = memfd_file_seals_ptr(file); + + return sealsp ? *sealsp : 0; +} + #endif /* __LINUX_MEMFD_H */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index fc7e6153b73d..ea48eb879a0f 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -524,6 +524,7 @@ enum { * creation/deletion on drivers rescan. Unset during device attach. */ MLX5_PRIV_FLAGS_DETACH = 1 << 2, + MLX5_PRIV_FLAGS_SWITCH_LEGACY = 1 << 3, }; struct mlx5_adev { @@ -1202,6 +1203,12 @@ static inline bool mlx5_core_is_vf(const struct mlx5_core_dev *dev) return dev->coredev_type == MLX5_COREDEV_VF; } +static inline bool mlx5_core_same_coredev_type(const struct mlx5_core_dev *dev1, + const struct mlx5_core_dev *dev2) +{ + return dev1->coredev_type == dev2->coredev_type; +} + static inline bool mlx5_core_is_ecpf(const struct mlx5_core_dev *dev) { return dev->caps.embedded_cpu; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 4fbbcf35498b..48d47181c7cd 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2119,7 +2119,9 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 migration_in_chunks[0x1]; u8 reserved_at_d1[0x1]; u8 sf_eq_usage[0x1]; - u8 reserved_at_d3[0xd]; + u8 reserved_at_d3[0x5]; + u8 multiplane[0x1]; + u8 reserved_at_d9[0x7]; u8 cross_vhca_object_to_object_supported[0x20]; diff --git a/include/linux/mm.h b/include/linux/mm.h index c39c4945946c..b1c3db9cf355 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -31,6 +31,7 @@ #include <linux/kasan.h> #include <linux/memremap.h> #include <linux/slab.h> +#include <linux/cacheinfo.h> struct mempolicy; struct anon_vma; @@ -3010,7 +3011,15 @@ static inline void pagetable_pte_dtor(struct ptdesc *ptdesc) lruvec_stat_sub_folio(folio, NR_PAGETABLE); } -pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp); +pte_t *___pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp); +static inline pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, + pmd_t *pmdvalp) +{ + pte_t *pte; + + __cond_lock(RCU, pte = ___pte_offset_map(pmd, addr, pmdvalp)); + return pte; +} static inline pte_t *pte_offset_map(pmd_t *pmd, unsigned long addr) { return __pte_offset_map(pmd, addr, NULL); @@ -3023,7 +3032,8 @@ static inline pte_t *pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd, { pte_t *pte; - __cond_lock(*ptlp, pte = __pte_offset_map_lock(mm, pmd, addr, ptlp)); + __cond_lock(RCU, __cond_lock(*ptlp, + pte = __pte_offset_map_lock(mm, pmd, addr, ptlp))); return pte; } @@ -3115,6 +3125,7 @@ static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc) if (!pmd_ptlock_init(ptdesc)) return false; __folio_set_pgtable(folio); + ptdesc_pmd_pts_init(ptdesc); lruvec_stat_add_folio(folio, NR_PAGETABLE); return true; } @@ -4091,6 +4102,37 @@ void mem_dump_obj(void *object); static inline void mem_dump_obj(void *object) {} #endif +static inline bool is_write_sealed(int seals) +{ + return seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE); +} + +/** + * is_readonly_sealed - Checks whether write-sealed but mapped read-only, + * in which case writes should be disallowing moving + * forwards. + * @seals: the seals to check + * @vm_flags: the VMA flags to check + * + * Returns whether readonly sealed, in which case writess should be disallowed + * going forward. + */ +static inline bool is_readonly_sealed(int seals, vm_flags_t vm_flags) +{ + /* + * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as + * MAP_SHARED and read-only, take care to not allow mprotect to + * revert protections on such mappings. Do this only for shared + * mappings. For private mappings, don't need to mask + * VM_MAYWRITE as we still want them to be COW-writable. + */ + if (is_write_sealed(seals) && + ((vm_flags & (VM_SHARED | VM_WRITE)) == VM_SHARED)) + return true; + + return false; +} + /** * seal_check_write - Check for F_SEAL_WRITE or F_SEAL_FUTURE_WRITE flags and * handle them. @@ -4102,24 +4144,15 @@ static inline void mem_dump_obj(void *object) {} */ static inline int seal_check_write(int seals, struct vm_area_struct *vma) { - if (seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { - /* - * New PROT_WRITE and MAP_SHARED mmaps are not allowed when - * write seals are active. - */ - if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) - return -EPERM; - - /* - * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as - * MAP_SHARED and read-only, take care to not allow mprotect to - * revert protections on such mappings. Do this only for shared - * mappings. For private mappings, don't need to mask - * VM_MAYWRITE as we still want them to be COW-writable. - */ - if (vma->vm_flags & VM_SHARED) - vm_flags_clear(vma, VM_MAYWRITE); - } + if (!is_write_sealed(seals)) + return 0; + + /* + * New PROT_WRITE and MAP_SHARED mmaps are not allowed when + * write seals are active. + */ + if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) + return -EPERM; return 0; } @@ -4175,6 +4208,23 @@ static inline int do_mseal(unsigned long start, size_t len_in, unsigned long fla } #endif +/* + * user_alloc_needs_zeroing checks if a user folio from page allocator needs to + * be zeroed or not. + */ +static inline bool user_alloc_needs_zeroing(void) +{ + /* + * for user folios, arch with cache aliasing requires cache flush and + * arc changes folio->flags to make icache coherent with dcache, so + * always return false to make caller use + * clear_user_page()/clear_user_highpage(). + */ + return cpu_dcache_is_aliasing() || cpu_icache_is_aliasing() || + !static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, + &init_on_alloc); +} + int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status); int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status); int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7361a8f3ab68..332cee285662 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -445,6 +445,7 @@ FOLIO_MATCH(compound_head, _head_2a); * @pt_index: Used for s390 gmap. * @pt_mm: Used for x86 pgds. * @pt_frag_refcount: For fragmented page table tracking. Powerpc only. + * @pt_share_count: Used for HugeTLB PMD page table share count. * @_pt_pad_2: Padding to ensure proper alignment. * @ptl: Lock for the page table. * @__page_type: Same as page->page_type. Unused for page tables. @@ -471,6 +472,9 @@ struct ptdesc { pgoff_t pt_index; struct mm_struct *pt_mm; atomic_t pt_frag_refcount; +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING + atomic_t pt_share_count; +#endif }; union { @@ -516,6 +520,32 @@ static_assert(sizeof(struct ptdesc) <= sizeof(struct page)); const struct page *: (const struct ptdesc *)(p), \ struct page *: (struct ptdesc *)(p))) +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) +{ + atomic_set(&ptdesc->pt_share_count, 0); +} + +static inline void ptdesc_pmd_pts_inc(struct ptdesc *ptdesc) +{ + atomic_inc(&ptdesc->pt_share_count); +} + +static inline void ptdesc_pmd_pts_dec(struct ptdesc *ptdesc) +{ + atomic_dec(&ptdesc->pt_share_count); +} + +static inline int ptdesc_pmd_pts_count(struct ptdesc *ptdesc) +{ + return atomic_read(&ptdesc->pt_share_count); +} +#else +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) +{ +} +#endif + /* * Used for sizing the vmemmap region on some architectures */ diff --git a/include/linux/module.h b/include/linux/module.h index 94acbacdcdf1..b3a643435357 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -773,7 +773,8 @@ void *__module_writable_address(struct module *mod, void *loc); static inline void *module_writable_address(struct module *mod, void *loc) { - if (!IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) || !mod) + if (!IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) || !mod || + mod->state != MODULE_STATE_UNFORMED) return loc; return __module_writable_address(mod, loc); } diff --git a/include/linux/mount.h b/include/linux/mount.h index c34c18b4e8f3..04213d8ef837 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -50,7 +50,7 @@ struct path; #define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME ) #define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \ - MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED | MNT_ONRB) + MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED) #define MNT_INTERNAL 0x4000 @@ -64,7 +64,6 @@ struct path; #define MNT_SYNC_UMOUNT 0x2000000 #define MNT_MARKED 0x4000000 #define MNT_UMOUNT 0x8000000 -#define MNT_ONRB 0x10000000 struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 5eaceef41e6c..ecdd5ced16a8 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -185,6 +185,7 @@ struct netfs_io_subrequest { short error; /* 0 or error that occurred */ unsigned short debug_index; /* Index in list (for debugging output) */ unsigned int nr_segs; /* Number of segs in io_iter */ + u8 retry_count; /* The number of retries (0 on initial pass) */ enum netfs_io_source source; /* Where to read from/write to */ unsigned char stream_nr; /* I/O stream this belongs to */ unsigned char curr_folioq_slot; /* Folio currently being read */ @@ -194,14 +195,13 @@ struct netfs_io_subrequest { #define NETFS_SREQ_COPY_TO_CACHE 0 /* Set if should copy the data to the cache */ #define NETFS_SREQ_CLEAR_TAIL 1 /* Set if the rest of the read should be cleared */ #define NETFS_SREQ_SEEK_DATA_READ 3 /* Set if ->read() should SEEK_DATA first */ -#define NETFS_SREQ_NO_PROGRESS 4 /* Set if we didn't manage to read any data */ +#define NETFS_SREQ_MADE_PROGRESS 4 /* Set if we transferred at least some data */ #define NETFS_SREQ_ONDEMAND 5 /* Set if it's from on-demand read mode */ #define NETFS_SREQ_BOUNDARY 6 /* Set if ends on hard boundary (eg. ceph object) */ #define NETFS_SREQ_HIT_EOF 7 /* Set if short due to EOF */ #define NETFS_SREQ_IN_PROGRESS 8 /* Unlocked when the subrequest completes */ #define NETFS_SREQ_NEED_RETRY 9 /* Set if the filesystem requests a retry */ -#define NETFS_SREQ_RETRYING 10 /* Set if we're retrying */ -#define NETFS_SREQ_FAILED 11 /* Set if the subreq failed unretryably */ +#define NETFS_SREQ_FAILED 10 /* Set if the subreq failed unretryably */ }; enum netfs_io_origin { @@ -269,7 +269,6 @@ struct netfs_io_request { size_t prev_donated; /* Fallback for subreq->prev_donated */ refcount_t ref; unsigned long flags; -#define NETFS_RREQ_COPY_TO_CACHE 1 /* Need to write to the cache */ #define NETFS_RREQ_NO_UNLOCK_FOLIO 2 /* Don't unlock no_unlock_folio on completion */ #define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ #define NETFS_RREQ_FAILED 4 /* The request failed */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index cf46ac720802..691506bdf2c5 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -862,18 +862,10 @@ static inline void ClearPageCompound(struct page *page) ClearPageHead(page); } FOLIO_FLAG(large_rmappable, FOLIO_SECOND_PAGE) -FOLIO_TEST_FLAG(partially_mapped, FOLIO_SECOND_PAGE) -/* - * PG_partially_mapped is protected by deferred_split split_queue_lock, - * so its safe to use non-atomic set/clear. - */ -__FOLIO_SET_FLAG(partially_mapped, FOLIO_SECOND_PAGE) -__FOLIO_CLEAR_FLAG(partially_mapped, FOLIO_SECOND_PAGE) +FOLIO_FLAG(partially_mapped, FOLIO_SECOND_PAGE) #else FOLIO_FLAG_FALSE(large_rmappable) -FOLIO_TEST_FLAG_FALSE(partially_mapped) -__FOLIO_SET_FLAG_NOOP(partially_mapped) -__FOLIO_CLEAR_FLAG_NOOP(partially_mapped) +FOLIO_FLAG_FALSE(partially_mapped) #endif #define PG_head_mask ((1UL << PG_head)) diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 35842d1e3879..5b520fe86b60 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -221,10 +221,7 @@ do { \ } while (0) #define PERCPU_PTR(__p) \ -({ \ - unsigned long __pcpu_ptr = (__force unsigned long)(__p); \ - (typeof(*(__p)) __force __kernel *)(__pcpu_ptr); \ -}) + (typeof(*(__p)) __force __kernel *)((__force unsigned long)(__p)) #ifdef CONFIG_SMP diff --git a/include/linux/platform_data/amd_qdma.h b/include/linux/platform_data/amd_qdma.h index 576d952f97ed..967a6ef31cf9 100644 --- a/include/linux/platform_data/amd_qdma.h +++ b/include/linux/platform_data/amd_qdma.h @@ -26,11 +26,13 @@ struct dma_slave_map; * @max_mm_channels: Maximum number of MM DMA channels in each direction * @device_map: DMA slave map * @irq_index: The index of first IRQ + * @dma_dev: The device pointer for dma operations */ struct qdma_platdata { u32 max_mm_channels; u32 irq_index; struct dma_slave_map *device_map; + struct device *dma_dev; }; #endif /* _PLATDATA_AMD_QDMA_H */ diff --git a/include/linux/poll.h b/include/linux/poll.h index d1ea4f3714a8..12bb18e8b978 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -25,14 +25,14 @@ struct poll_table_struct; -/* +/* * structures and helpers for f_op->poll implementations */ typedef void (*poll_queue_proc)(struct file *, wait_queue_head_t *, struct poll_table_struct *); /* - * Do not touch the structure directly, use the access functions - * poll_does_not_wait() and poll_requested_events() instead. + * Do not touch the structure directly, use the access function + * poll_requested_events() instead. */ typedef struct poll_table_struct { poll_queue_proc _qproc; @@ -41,18 +41,16 @@ typedef struct poll_table_struct { static inline void poll_wait(struct file * filp, wait_queue_head_t * wait_address, poll_table *p) { - if (p && p->_qproc && wait_address) + if (p && p->_qproc) { p->_qproc(filp, wait_address, p); -} - -/* - * Return true if it is guaranteed that poll will not wait. This is the case - * if the poll() of another file descriptor in the set got an event, so there - * is no need for waiting. - */ -static inline bool poll_does_not_wait(const poll_table *p) -{ - return p == NULL || p->_qproc == NULL; + /* + * This memory barrier is paired in the wq_has_sleeper(). + * See the comment above prepare_to_wait(), we need to + * ensure that subsequent tests in this thread can't be + * reordered with __add_wait_queue() in _qproc() paths. + */ + smp_mb(); + } } /* diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 8c3c372ad735..bcba3935c6f9 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -168,29 +168,6 @@ int devm_regulator_get_enable_read_voltage(struct device *dev, const char *id); void regulator_put(struct regulator *regulator); void devm_regulator_put(struct regulator *regulator); -#if IS_ENABLED(CONFIG_OF) -struct regulator *__must_check of_regulator_get_optional(struct device *dev, - struct device_node *node, - const char *id); -struct regulator *__must_check devm_of_regulator_get_optional(struct device *dev, - struct device_node *node, - const char *id); -#else -static inline struct regulator *__must_check of_regulator_get_optional(struct device *dev, - struct device_node *node, - const char *id) -{ - return ERR_PTR(-ENODEV); -} - -static inline struct regulator *__must_check devm_of_regulator_get_optional(struct device *dev, - struct device_node *node, - const char *id) -{ - return ERR_PTR(-ENODEV); -} -#endif - int regulator_register_supply_alias(struct device *dev, const char *id, struct device *alias_dev, const char *alias_id); @@ -223,8 +200,6 @@ int regulator_disable_deferred(struct regulator *regulator, int ms); int __must_check regulator_bulk_get(struct device *dev, int num_consumers, struct regulator_bulk_data *consumers); -int __must_check of_regulator_bulk_get_all(struct device *dev, struct device_node *np, - struct regulator_bulk_data **consumers); int __must_check devm_regulator_bulk_get(struct device *dev, int num_consumers, struct regulator_bulk_data *consumers); void devm_regulator_bulk_put(struct regulator_bulk_data *consumers); @@ -373,20 +348,6 @@ devm_regulator_get_optional(struct device *dev, const char *id) return ERR_PTR(-ENODEV); } -static inline struct regulator *__must_check of_regulator_get_optional(struct device *dev, - struct device_node *node, - const char *id) -{ - return ERR_PTR(-ENODEV); -} - -static inline struct regulator *__must_check devm_of_regulator_get_optional(struct device *dev, - struct device_node *node, - const char *id) -{ - return ERR_PTR(-ENODEV); -} - static inline void regulator_put(struct regulator *regulator) { } @@ -483,12 +444,6 @@ static inline int devm_regulator_bulk_get(struct device *dev, int num_consumers, return 0; } -static inline int of_regulator_bulk_get_all(struct device *dev, struct device_node *np, - struct regulator_bulk_data **consumers) -{ - return 0; -} - static inline int devm_regulator_bulk_get_const( struct device *dev, int num_consumers, const struct regulator_bulk_data *in_consumers, @@ -700,6 +655,38 @@ regulator_is_equal(struct regulator *reg1, struct regulator *reg2) } #endif +#if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_REGULATOR) +struct regulator *__must_check of_regulator_get_optional(struct device *dev, + struct device_node *node, + const char *id); +struct regulator *__must_check devm_of_regulator_get_optional(struct device *dev, + struct device_node *node, + const char *id); +int __must_check of_regulator_bulk_get_all(struct device *dev, struct device_node *np, + struct regulator_bulk_data **consumers); +#else +static inline struct regulator *__must_check of_regulator_get_optional(struct device *dev, + struct device_node *node, + const char *id) +{ + return ERR_PTR(-ENODEV); +} + +static inline struct regulator *__must_check devm_of_regulator_get_optional(struct device *dev, + struct device_node *node, + const char *id) +{ + return ERR_PTR(-ENODEV); +} + +static inline int of_regulator_bulk_get_all(struct device *dev, struct device_node *np, + struct regulator_bulk_data **consumers) +{ + return 0; +} + +#endif + static inline int regulator_set_voltage_triplet(struct regulator *regulator, int min_uV, int target_uV, int max_uV) diff --git a/include/linux/sched.h b/include/linux/sched.h index 66b311fbd5d6..64934e0830af 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1637,8 +1637,9 @@ static inline unsigned int __task_state_index(unsigned int tsk_state, * We're lying here, but rather than expose a completely new task state * to userspace, we can make this appear as if the task has gone through * a regular rt_mutex_lock() call. + * Report frozen tasks as uninterruptible. */ - if (tsk_state & TASK_RTLOCK_WAIT) + if ((tsk_state & TASK_RTLOCK_WAIT) || (tsk_state & TASK_FROZEN)) state = TASK_UNINTERRUPTIBLE; return fls(state); diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index d9b03e0746e7..2cbe0c22a32f 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -317,17 +317,22 @@ static inline void sock_drop(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); } -static inline void sk_psock_queue_msg(struct sk_psock *psock, +static inline bool sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { + bool ret; + spin_lock_bh(&psock->ingress_lock); - if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { list_add_tail(&msg->list, &psock->ingress_msg); - else { + ret = true; + } else { sk_msg_free(psock->sk, msg); kfree(msg); + ret = false; } spin_unlock_bh(&psock->ingress_lock); + return ret; } static inline struct sk_msg *sk_psock_dequeue_msg(struct sk_psock *psock) diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 141e6b176a1b..78a77a4ae0ea 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -160,6 +160,8 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool #ifdef CONFIG_HAVE_STATIC_CALL_INLINE +extern int static_call_initialized; + extern int __init static_call_init(void); extern void static_call_force_reinit(void); @@ -225,6 +227,8 @@ extern long __static_call_return0(void); #elif defined(CONFIG_HAVE_STATIC_CALL) +#define static_call_initialized 0 + static inline int static_call_init(void) { return 0; } #define DEFINE_STATIC_CALL(name, _func) \ @@ -281,6 +285,8 @@ extern long __static_call_return0(void); #else /* Generic implementation */ +#define static_call_initialized 0 + static inline int static_call_init(void) { return 0; } static inline long __static_call_return0(void) diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 2a5df5b62cfc..58ad4ead33fc 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -273,7 +273,8 @@ struct trace_event_fields { const char *name; const int size; const int align; - const int is_signed; + const unsigned int is_signed:1; + unsigned int needs_test:1; const int filter_type; const int len; }; @@ -324,6 +325,7 @@ enum { TRACE_EVENT_FL_EPROBE_BIT, TRACE_EVENT_FL_FPROBE_BIT, TRACE_EVENT_FL_CUSTOM_BIT, + TRACE_EVENT_FL_TEST_STR_BIT, }; /* @@ -340,6 +342,7 @@ enum { * CUSTOM - Event is a custom event (to be attached to an exsiting tracepoint) * This is set when the custom event has not been attached * to a tracepoint yet, then it is cleared when it is. + * TEST_STR - The event has a "%s" that points to a string outside the event */ enum { TRACE_EVENT_FL_CAP_ANY = (1 << TRACE_EVENT_FL_CAP_ANY_BIT), @@ -352,6 +355,7 @@ enum { TRACE_EVENT_FL_EPROBE = (1 << TRACE_EVENT_FL_EPROBE_BIT), TRACE_EVENT_FL_FPROBE = (1 << TRACE_EVENT_FL_FPROBE_BIT), TRACE_EVENT_FL_CUSTOM = (1 << TRACE_EVENT_FL_CUSTOM_BIT), + TRACE_EVENT_FL_TEST_STR = (1 << TRACE_EVENT_FL_TEST_STR_BIT), }; #define TRACE_EVENT_FL_UKPROBE (TRACE_EVENT_FL_KPROBE | TRACE_EVENT_FL_UPROBE) @@ -360,7 +364,7 @@ struct trace_event_call { struct list_head list; struct trace_event_class *class; union { - char *name; + const char *name; /* Set TRACE_EVENT_FL_TRACEPOINT flag when using "tp" */ struct tracepoint *tp; }; diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index cb40f1a1d081..75342022d144 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -247,6 +247,13 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma, vma_is_shmem(vma); } +static inline bool vma_has_uffd_without_event_remap(struct vm_area_struct *vma) +{ + struct userfaultfd_ctx *uffd_ctx = vma->vm_userfaultfd_ctx.ctx; + + return uffd_ctx && (uffd_ctx->features & UFFD_FEATURE_EVENT_REMAP) == 0; +} + extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); extern void dup_userfaultfd_complete(struct list_head *); void dup_userfaultfd_fail(struct list_head *); @@ -402,6 +409,11 @@ static inline bool userfaultfd_wp_async(struct vm_area_struct *vma) return false; } +static inline bool vma_has_uffd_without_event_remap(struct vm_area_struct *vma) +{ + return false; +} + #endif /* CONFIG_USERFAULTFD */ static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma) diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h index a54046bf37e5..939ceabcaf06 100644 --- a/include/linux/vermagic.h +++ b/include/linux/vermagic.h @@ -15,10 +15,10 @@ #else #define MODULE_VERMAGIC_SMP "" #endif -#ifdef CONFIG_PREEMPT_BUILD -#define MODULE_VERMAGIC_PREEMPT "preempt " -#elif defined(CONFIG_PREEMPT_RT) +#ifdef CONFIG_PREEMPT_RT #define MODULE_VERMAGIC_PREEMPT "preempt_rt " +#elif defined(CONFIG_PREEMPT_BUILD) +#define MODULE_VERMAGIC_PREEMPT "preempt " #else #define MODULE_VERMAGIC_PREEMPT "" #endif diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index d2761bf8ff32..9f3a04345b86 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -515,7 +515,7 @@ static inline const char *node_stat_name(enum node_stat_item item) static inline const char *lru_list_name(enum lru_list lru) { - return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_" + return node_stat_name(NR_LRU_BASE + (enum node_stat_item)lru) + 3; // skip "nr_" } #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 3c82fad904d4..c7f42844c79a 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -282,7 +282,7 @@ static inline int inet_csk_reqsk_queue_len(const struct sock *sk) static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) { - return inet_csk_reqsk_queue_len(sk) >= READ_ONCE(sk->sk_max_ack_backlog); + return inet_csk_reqsk_queue_len(sk) > READ_ONCE(sk->sk_max_ack_backlog); } bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 4afa64c81304..0027beca5cd5 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -733,15 +733,18 @@ struct nft_set_ext_tmpl { /** * struct nft_set_ext - set extensions * - * @genmask: generation mask + * @genmask: generation mask, but also flags (see NFT_SET_ELEM_DEAD_BIT) * @offset: offsets of individual extension types * @data: beginning of extension data + * + * This structure must be aligned to word size, otherwise atomic bitops + * on genmask field can cause alignment failure on some archs. */ struct nft_set_ext { u8 genmask; u8 offset[NFT_SET_EXT_NUM]; char data[]; -}; +} __aligned(BITS_PER_LONG / 8); static inline void nft_set_ext_prepare(struct nft_set_ext_tmpl *tmpl) { diff --git a/include/net/sock.h b/include/net/sock.h index 7464e9f9f47c..691ca7695d1d 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1527,7 +1527,7 @@ static inline bool sk_wmem_schedule(struct sock *sk, int size) } static inline bool -sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) +__sk_rmem_schedule(struct sock *sk, int size, bool pfmemalloc) { int delta; @@ -1535,7 +1535,13 @@ sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) return true; delta = size - sk->sk_forward_alloc; return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_RECV) || - skb_pfmemalloc(skb); + pfmemalloc; +} + +static inline bool +sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) +{ + return __sk_rmem_schedule(sk, size, skb_pfmemalloc(skb)); } static inline int sk_unused_reserved_mem(const struct sock *sk) @@ -2291,7 +2297,7 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq) } /** - * sock_poll_wait - place memory barrier behind the poll_wait call. + * sock_poll_wait - wrapper for the poll_wait call. * @filp: file * @sock: socket to wait on * @p: poll_table @@ -2301,15 +2307,12 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq) static inline void sock_poll_wait(struct file *filp, struct socket *sock, poll_table *p) { - if (!poll_does_not_wait(p)) { - poll_wait(filp, &sock->wq.wait, p); - /* We need to be sure we are in sync with the - * socket flags modification. - * - * This memory barrier is paired in the wq_has_sleeper. - */ - smp_mb(); - } + /* Provides a barrier we need to be sure we are in sync + * with the socket flags modification. + * + * This memory barrier is paired in the wq_has_sleeper. + */ + poll_wait(filp, &sock->wq.wait, p); } static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk) diff --git a/include/trace/events/hugetlbfs.h b/include/trace/events/hugetlbfs.h index 8331c904a9ba..59605dfaeeb4 100644 --- a/include/trace/events/hugetlbfs.h +++ b/include/trace/events/hugetlbfs.h @@ -23,7 +23,7 @@ TRACE_EVENT(hugetlbfs_alloc_inode, TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; - __entry->dir = dir->i_ino; + __entry->dir = dir ? dir->i_ino : 0; __entry->mode = mode; ), diff --git a/include/uapi/linux/mptcp_pm.h b/include/uapi/linux/mptcp_pm.h index 50589e5dd6a3..84fa8a21dfd0 100644 --- a/include/uapi/linux/mptcp_pm.h +++ b/include/uapi/linux/mptcp_pm.h @@ -12,31 +12,33 @@ /** * enum mptcp_event_type * @MPTCP_EVENT_UNSPEC: unused event - * @MPTCP_EVENT_CREATED: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport A new MPTCP connection has been created. It is the good time - * to allocate memory and send ADD_ADDR if needed. Depending on the + * @MPTCP_EVENT_CREATED: A new MPTCP connection has been created. It is the + * good time to allocate memory and send ADD_ADDR if needed. Depending on the * traffic-patterns it can take a long time until the MPTCP_EVENT_ESTABLISHED - * is sent. - * @MPTCP_EVENT_ESTABLISHED: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport A MPTCP connection is established (can start new subflows). - * @MPTCP_EVENT_CLOSED: token A MPTCP connection has stopped. - * @MPTCP_EVENT_ANNOUNCED: token, rem_id, family, daddr4 | daddr6 [, dport] A - * new address has been announced by the peer. - * @MPTCP_EVENT_REMOVED: token, rem_id An address has been lost by the peer. - * @MPTCP_EVENT_SUB_ESTABLISHED: token, family, loc_id, rem_id, saddr4 | - * saddr6, daddr4 | daddr6, sport, dport, backup, if_idx [, error] A new - * subflow has been established. 'error' should not be set. - * @MPTCP_EVENT_SUB_CLOSED: token, family, loc_id, rem_id, saddr4 | saddr6, - * daddr4 | daddr6, sport, dport, backup, if_idx [, error] A subflow has been - * closed. An error (copy of sk_err) could be set if an error has been - * detected for this subflow. - * @MPTCP_EVENT_SUB_PRIORITY: token, family, loc_id, rem_id, saddr4 | saddr6, - * daddr4 | daddr6, sport, dport, backup, if_idx [, error] The priority of a - * subflow has changed. 'error' should not be set. - * @MPTCP_EVENT_LISTENER_CREATED: family, sport, saddr4 | saddr6 A new PM - * listener is created. - * @MPTCP_EVENT_LISTENER_CLOSED: family, sport, saddr4 | saddr6 A PM listener - * is closed. + * is sent. Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, + * sport, dport, server-side. + * @MPTCP_EVENT_ESTABLISHED: A MPTCP connection is established (can start new + * subflows). Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, + * sport, dport, server-side. + * @MPTCP_EVENT_CLOSED: A MPTCP connection has stopped. Attribute: token. + * @MPTCP_EVENT_ANNOUNCED: A new address has been announced by the peer. + * Attributes: token, rem_id, family, daddr4 | daddr6 [, dport]. + * @MPTCP_EVENT_REMOVED: An address has been lost by the peer. Attributes: + * token, rem_id. + * @MPTCP_EVENT_SUB_ESTABLISHED: A new subflow has been established. 'error' + * should not be set. Attributes: token, family, loc_id, rem_id, saddr4 | + * saddr6, daddr4 | daddr6, sport, dport, backup, if_idx [, error]. + * @MPTCP_EVENT_SUB_CLOSED: A subflow has been closed. An error (copy of + * sk_err) could be set if an error has been detected for this subflow. + * Attributes: token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | + * daddr6, sport, dport, backup, if_idx [, error]. + * @MPTCP_EVENT_SUB_PRIORITY: The priority of a subflow has changed. 'error' + * should not be set. Attributes: token, family, loc_id, rem_id, saddr4 | + * saddr6, daddr4 | daddr6, sport, dport, backup, if_idx [, error]. + * @MPTCP_EVENT_LISTENER_CREATED: A new PM listener is created. Attributes: + * family, sport, saddr4 | saddr6. + * @MPTCP_EVENT_LISTENER_CLOSED: A PM listener is closed. Attributes: family, + * sport, saddr4 | saddr6. */ enum mptcp_event_type { MPTCP_EVENT_UNSPEC, diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index 58154117d9b0..a6fce46aeb37 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -8,6 +8,13 @@ #define __always_inline inline #endif +/* Not all C++ standards support type declarations inside an anonymous union */ +#ifndef __cplusplus +#define __struct_group_tag(TAG) TAG +#else +#define __struct_group_tag(TAG) +#endif + /** * __struct_group() - Create a mirrored named and anonyomous struct * @@ -20,13 +27,13 @@ * and size: one anonymous and one named. The former's members can be used * normally without sub-struct naming, and the latter can be used to * reason about the start, end, and size of the group of struct members. - * The named struct can also be explicitly tagged for layer reuse, as well - * as both having struct attributes appended. + * The named struct can also be explicitly tagged for layer reuse (C only), + * as well as both having struct attributes appended. */ #define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \ union { \ struct { MEMBERS } ATTRS; \ - struct TAG { MEMBERS } ATTRS NAME; \ + struct __struct_group_tag(TAG) { MEMBERS } ATTRS NAME; \ } ATTRS #ifdef __cplusplus diff --git a/include/uapi/linux/thermal.h b/include/uapi/linux/thermal.h index ba8604bdf206..349718c271eb 100644 --- a/include/uapi/linux/thermal.h +++ b/include/uapi/linux/thermal.h @@ -3,8 +3,8 @@ #define _UAPI_LINUX_THERMAL_H #define THERMAL_NAME_LENGTH 20 -#define THERMAL_THRESHOLD_WAY_UP BIT(0) -#define THERMAL_THRESHOLD_WAY_DOWN BIT(1) +#define THERMAL_THRESHOLD_WAY_UP 0x1 +#define THERMAL_THRESHOLD_WAY_DOWN 0x2 enum thermal_device_mode { THERMAL_DEVICE_DISABLED = 0, diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index d650ae6b58d3..74e5b9960c54 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -329,7 +329,6 @@ struct ufs_pwr_mode_info { * @program_key: program or evict an inline encryption key * @fill_crypto_prdt: initialize crypto-related fields in the PRDT * @event_notify: called to notify important events - * @reinit_notify: called to notify reinit of UFSHCD during max gear switch * @mcq_config_resource: called to configure MCQ platform resources * @get_hba_mac: reports maximum number of outstanding commands supported by * the controller. Should be implemented for UFSHCI 4.0 or later @@ -381,7 +380,6 @@ struct ufs_hba_variant_ops { void *prdt, unsigned int num_segments); void (*event_notify)(struct ufs_hba *hba, enum ufs_event_type evt, void *data); - void (*reinit_notify)(struct ufs_hba *); int (*mcq_config_resource)(struct ufs_hba *hba); int (*get_hba_mac)(struct ufs_hba *hba); int (*op_runtime_config)(struct ufs_hba *hba); diff --git a/io_uring/eventfd.c b/io_uring/eventfd.c index fab936d31ba8..100d5da94cb9 100644 --- a/io_uring/eventfd.c +++ b/io_uring/eventfd.c @@ -33,20 +33,18 @@ static void io_eventfd_free(struct rcu_head *rcu) kfree(ev_fd); } -static void io_eventfd_do_signal(struct rcu_head *rcu) +static void io_eventfd_put(struct io_ev_fd *ev_fd) { - struct io_ev_fd *ev_fd = container_of(rcu, struct io_ev_fd, rcu); - - eventfd_signal_mask(ev_fd->cq_ev_fd, EPOLL_URING_WAKE); - if (refcount_dec_and_test(&ev_fd->refs)) - io_eventfd_free(rcu); + call_rcu(&ev_fd->rcu, io_eventfd_free); } -static void io_eventfd_put(struct io_ev_fd *ev_fd) +static void io_eventfd_do_signal(struct rcu_head *rcu) { - if (refcount_dec_and_test(&ev_fd->refs)) - call_rcu(&ev_fd->rcu, io_eventfd_free); + struct io_ev_fd *ev_fd = container_of(rcu, struct io_ev_fd, rcu); + + eventfd_signal_mask(ev_fd->cq_ev_fd, EPOLL_URING_WAKE); + io_eventfd_put(ev_fd); } static void io_eventfd_release(struct io_ev_fd *ev_fd, bool put_ref) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 06ff41484e29..4758f1ba902b 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -215,9 +215,9 @@ bool io_match_task_safe(struct io_kiocb *head, struct io_uring_task *tctx, struct io_ring_ctx *ctx = head->ctx; /* protect against races with linked timeouts */ - spin_lock_irq(&ctx->timeout_lock); + raw_spin_lock_irq(&ctx->timeout_lock); matched = io_match_linked(head); - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); } else { matched = io_match_linked(head); } @@ -320,7 +320,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) ret |= io_alloc_cache_init(&ctx->rw_cache, IO_ALLOC_CACHE_MAX, sizeof(struct io_async_rw)); ret |= io_alloc_cache_init(&ctx->uring_cache, IO_ALLOC_CACHE_MAX, - sizeof(struct uring_cache)); + sizeof(struct io_uring_cmd_data)); spin_lock_init(&ctx->msg_lock); ret |= io_alloc_cache_init(&ctx->msg_cache, IO_ALLOC_CACHE_MAX, sizeof(struct io_kiocb)); @@ -333,7 +333,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) init_waitqueue_head(&ctx->cq_wait); init_waitqueue_head(&ctx->poll_wq); spin_lock_init(&ctx->completion_lock); - spin_lock_init(&ctx->timeout_lock); + raw_spin_lock_init(&ctx->timeout_lock); INIT_WQ_LIST(&ctx->iopoll_list); INIT_LIST_HEAD(&ctx->io_buffers_comp); INIT_LIST_HEAD(&ctx->defer_list); @@ -498,10 +498,10 @@ static void io_prep_async_link(struct io_kiocb *req) if (req->flags & REQ_F_LINK_TIMEOUT) { struct io_ring_ctx *ctx = req->ctx; - spin_lock_irq(&ctx->timeout_lock); + raw_spin_lock_irq(&ctx->timeout_lock); io_for_each_link(cur, req) io_prep_async_work(cur); - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); } else { io_for_each_link(cur, req) io_prep_async_work(cur); @@ -514,7 +514,11 @@ static void io_queue_iowq(struct io_kiocb *req) struct io_uring_task *tctx = req->tctx; BUG_ON(!tctx); - BUG_ON(!tctx->io_wq); + + if ((current->flags & PF_KTHREAD) || !tctx->io_wq) { + io_req_task_queue_fail(req, -ECANCELED); + return; + } /* init ->work of the whole link before punting */ io_prep_async_link(req); @@ -1222,10 +1226,7 @@ static void io_req_normal_work_add(struct io_kiocb *req) /* SQPOLL doesn't need the task_work added, it'll run it itself */ if (ctx->flags & IORING_SETUP_SQPOLL) { - struct io_sq_data *sqd = ctx->sq_data; - - if (sqd->thread) - __set_notify_signal(sqd->thread); + __set_notify_signal(tctx->task); return; } @@ -2809,13 +2810,12 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) if (unlikely(!ctx->poll_activated)) io_activate_pollwq(ctx); - - poll_wait(file, &ctx->poll_wq, wait); /* - * synchronizes with barrier from wq_has_sleeper call in - * io_commit_cqring + * provides mb() which pairs with barrier from wq_has_sleeper + * call in io_commit_cqring */ - smp_rmb(); + poll_wait(file, &ctx->poll_wq, wait); + if (!io_sqring_full(ctx)) mask |= EPOLLOUT | EPOLLWRNORM; @@ -3214,6 +3214,7 @@ end_wait: void __io_uring_cancel(bool cancel_all) { + io_uring_unreg_ringfd(); io_uring_cancel_generic(cancel_all, NULL); } diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index 12abee607e4a..492cbbf2c23b 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -125,6 +125,9 @@ static inline void io_lockdep_assert_cq_locked(struct io_ring_ctx *ctx) #if defined(CONFIG_PROVE_LOCKING) lockdep_assert(in_task()); + if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) + lockdep_assert_held(&ctx->uring_lock); + if (ctx->flags & IORING_SETUP_IOPOLL) { lockdep_assert_held(&ctx->uring_lock); } else if (!ctx->task_complete) { @@ -136,9 +139,7 @@ static inline void io_lockdep_assert_cq_locked(struct io_ring_ctx *ctx) * Not from an SQE, as those cannot be submitted, but via * updating tagged resources. */ - if (percpu_ref_is_dying(&ctx->refs)) - lockdep_assert(current_work()); - else + if (!percpu_ref_is_dying(&ctx->refs)) lockdep_assert(current == ctx->submitter_task); } #endif diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index d407576ddfb7..eec5eb7de843 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -139,6 +139,7 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len, struct io_uring_buf_ring *br = bl->buf_ring; __u16 tail, head = bl->head; struct io_uring_buf *buf; + void __user *ret; tail = smp_load_acquire(&br->tail); if (unlikely(tail == head)) @@ -153,6 +154,7 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len, req->flags |= REQ_F_BUFFER_RING | REQ_F_BUFFERS_COMMIT; req->buf_list = bl; req->buf_index = buf->bid; + ret = u64_to_user_ptr(buf->addr); if (issue_flags & IO_URING_F_UNLOCKED || !io_file_can_poll(req)) { /* @@ -168,7 +170,7 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len, io_kbuf_commit(req, bl, *len, 1); req->buf_list = NULL; } - return u64_to_user_ptr(buf->addr); + return ret; } void __user *io_buffer_select(struct io_kiocb *req, size_t *len, diff --git a/io_uring/net.c b/io_uring/net.c index df1f7dc6f1c8..c6cd38cc5dc4 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -754,6 +754,7 @@ static int io_recvmsg_prep_setup(struct io_kiocb *req) if (req->opcode == IORING_OP_RECV) { kmsg->msg.msg_name = NULL; kmsg->msg.msg_namelen = 0; + kmsg->msg.msg_inq = 0; kmsg->msg.msg_control = NULL; kmsg->msg.msg_get_inq = 1; kmsg->msg.msg_controllen = 0; diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 3de75eca1c92..e8baef4e5146 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -7,6 +7,7 @@ #include <linux/fs.h> #include <linux/file.h> #include <linux/io_uring.h> +#include <linux/io_uring/cmd.h> #include "io_uring.h" #include "opdef.h" @@ -414,7 +415,7 @@ const struct io_issue_def io_issue_defs[] = { .plug = 1, .iopoll = 1, .iopoll_queue = 1, - .async_size = 2 * sizeof(struct io_uring_sqe), + .async_size = sizeof(struct io_uring_cmd_data), .prep = io_uring_cmd_prep, .issue = io_uring_cmd, }, diff --git a/io_uring/register.c b/io_uring/register.c index 1e99c783abdf..fdd44914c39c 100644 --- a/io_uring/register.c +++ b/io_uring/register.c @@ -414,6 +414,9 @@ static int io_register_resize_rings(struct io_ring_ctx *ctx, void __user *arg) if (ctx->flags & IORING_SETUP_SINGLE_ISSUER && current != ctx->submitter_task) return -EEXIST; + /* limited to DEFER_TASKRUN for now */ + if (!(ctx->flags & IORING_SETUP_DEFER_TASKRUN)) + return -EINVAL; if (copy_from_user(&p, arg, sizeof(p))) return -EFAULT; if (p.flags & ~RESIZE_FLAGS) diff --git a/io_uring/rw.c b/io_uring/rw.c index 0bcb83e4ce3c..29bb3010f9c0 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -983,6 +983,8 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags) io_kbuf_recycle(req, issue_flags); if (ret < 0) req_set_fail(req); + } else if (!(req->flags & REQ_F_APOLL_MULTISHOT)) { + cflags = io_put_kbuf(req, ret, issue_flags); } else { /* * Any successful return value will keep the multishot read diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c index 6df5e649c413..8961a3c1e73c 100644 --- a/io_uring/sqpoll.c +++ b/io_uring/sqpoll.c @@ -268,8 +268,12 @@ static int io_sq_thread(void *data) DEFINE_WAIT(wait); /* offload context creation failed, just exit */ - if (!current->io_uring) + if (!current->io_uring) { + mutex_lock(&sqd->lock); + sqd->thread = NULL; + mutex_unlock(&sqd->lock); goto err_out; + } snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid); set_task_comm(current, buf); @@ -405,6 +409,7 @@ void io_sqpoll_wait_sq(struct io_ring_ctx *ctx) __cold int io_sq_offload_create(struct io_ring_ctx *ctx, struct io_uring_params *p) { + struct task_struct *task_to_put = NULL; int ret; /* Retain compatibility with failing for an invalid attach attempt */ @@ -480,6 +485,7 @@ __cold int io_sq_offload_create(struct io_ring_ctx *ctx, } sqd->thread = tsk; + task_to_put = get_task_struct(tsk); ret = io_uring_alloc_task_context(tsk, ctx); wake_up_new_task(tsk); if (ret) @@ -490,11 +496,15 @@ __cold int io_sq_offload_create(struct io_ring_ctx *ctx, goto err; } + if (task_to_put) + put_task_struct(task_to_put); return 0; err_sqpoll: complete(&ctx->sq_data->exited); err: io_sq_thread_finish(ctx); + if (task_to_put) + put_task_struct(task_to_put); return ret; } diff --git a/io_uring/timeout.c b/io_uring/timeout.c index f3d502717aeb..e9cec9e4dc2f 100644 --- a/io_uring/timeout.c +++ b/io_uring/timeout.c @@ -74,10 +74,10 @@ static void io_timeout_complete(struct io_kiocb *req, struct io_tw_state *ts) if (!io_timeout_finish(timeout, data)) { if (io_req_post_cqe(req, -ETIME, IORING_CQE_F_MORE)) { /* re-arm timer */ - spin_lock_irq(&ctx->timeout_lock); + raw_spin_lock_irq(&ctx->timeout_lock); list_add(&timeout->list, ctx->timeout_list.prev); hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), data->mode); - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); return; } } @@ -85,7 +85,27 @@ static void io_timeout_complete(struct io_kiocb *req, struct io_tw_state *ts) io_req_task_complete(req, ts); } -static bool io_kill_timeout(struct io_kiocb *req, int status) +static __cold bool io_flush_killed_timeouts(struct list_head *list, int err) +{ + if (list_empty(list)) + return false; + + while (!list_empty(list)) { + struct io_timeout *timeout; + struct io_kiocb *req; + + timeout = list_first_entry(list, struct io_timeout, list); + list_del_init(&timeout->list); + req = cmd_to_io_kiocb(timeout); + if (err) + req_set_fail(req); + io_req_queue_tw_complete(req, err); + } + + return true; +} + +static void io_kill_timeout(struct io_kiocb *req, struct list_head *list) __must_hold(&req->ctx->timeout_lock) { struct io_timeout_data *io = req->async_data; @@ -93,23 +113,19 @@ static bool io_kill_timeout(struct io_kiocb *req, int status) if (hrtimer_try_to_cancel(&io->timer) != -1) { struct io_timeout *timeout = io_kiocb_to_cmd(req, struct io_timeout); - if (status) - req_set_fail(req); atomic_set(&req->ctx->cq_timeouts, atomic_read(&req->ctx->cq_timeouts) + 1); - list_del_init(&timeout->list); - io_req_queue_tw_complete(req, status); - return true; + list_move_tail(&timeout->list, list); } - return false; } __cold void io_flush_timeouts(struct io_ring_ctx *ctx) { - u32 seq; struct io_timeout *timeout, *tmp; + LIST_HEAD(list); + u32 seq; - spin_lock_irq(&ctx->timeout_lock); + raw_spin_lock_irq(&ctx->timeout_lock); seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); list_for_each_entry_safe(timeout, tmp, &ctx->timeout_list, list) { @@ -131,10 +147,11 @@ __cold void io_flush_timeouts(struct io_ring_ctx *ctx) if (events_got < events_needed) break; - io_kill_timeout(req, 0); + io_kill_timeout(req, &list); } ctx->cq_last_tm_flush = seq; - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); + io_flush_killed_timeouts(&list, 0); } static void io_req_tw_fail_links(struct io_kiocb *link, struct io_tw_state *ts) @@ -200,9 +217,9 @@ void io_disarm_next(struct io_kiocb *req) } else if (req->flags & REQ_F_LINK_TIMEOUT) { struct io_ring_ctx *ctx = req->ctx; - spin_lock_irq(&ctx->timeout_lock); + raw_spin_lock_irq(&ctx->timeout_lock); link = io_disarm_linked_timeout(req); - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); if (link) io_req_queue_tw_complete(link, -ECANCELED); } @@ -238,11 +255,11 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) struct io_ring_ctx *ctx = req->ctx; unsigned long flags; - spin_lock_irqsave(&ctx->timeout_lock, flags); + raw_spin_lock_irqsave(&ctx->timeout_lock, flags); list_del_init(&timeout->list); atomic_set(&req->ctx->cq_timeouts, atomic_read(&req->ctx->cq_timeouts) + 1); - spin_unlock_irqrestore(&ctx->timeout_lock, flags); + raw_spin_unlock_irqrestore(&ctx->timeout_lock, flags); if (!(data->flags & IORING_TIMEOUT_ETIME_SUCCESS)) req_set_fail(req); @@ -285,9 +302,9 @@ int io_timeout_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd) { struct io_kiocb *req; - spin_lock_irq(&ctx->timeout_lock); + raw_spin_lock_irq(&ctx->timeout_lock); req = io_timeout_extract(ctx, cd); - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); if (IS_ERR(req)) return PTR_ERR(req); @@ -330,7 +347,7 @@ static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) struct io_ring_ctx *ctx = req->ctx; unsigned long flags; - spin_lock_irqsave(&ctx->timeout_lock, flags); + raw_spin_lock_irqsave(&ctx->timeout_lock, flags); prev = timeout->head; timeout->head = NULL; @@ -345,7 +362,7 @@ static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) } list_del(&timeout->list); timeout->prev = prev; - spin_unlock_irqrestore(&ctx->timeout_lock, flags); + raw_spin_unlock_irqrestore(&ctx->timeout_lock, flags); req->io_task_work.func = io_req_task_link_timeout; io_req_task_work_add(req); @@ -410,10 +427,12 @@ static int io_timeout_update(struct io_ring_ctx *ctx, __u64 user_data, timeout->off = 0; /* noseq */ data = req->async_data; + data->ts = *ts; + list_add_tail(&timeout->list, &ctx->timeout_list); hrtimer_init(&data->timer, io_timeout_get_clock(data), mode); data->timer.function = io_timeout_fn; - hrtimer_start(&data->timer, timespec64_to_ktime(*ts), mode); + hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), mode); return 0; } @@ -472,12 +491,12 @@ int io_timeout_remove(struct io_kiocb *req, unsigned int issue_flags) } else { enum hrtimer_mode mode = io_translate_timeout_mode(tr->flags); - spin_lock_irq(&ctx->timeout_lock); + raw_spin_lock_irq(&ctx->timeout_lock); if (tr->ltimeout) ret = io_linked_timeout_update(ctx, tr->addr, &tr->ts, mode); else ret = io_timeout_update(ctx, tr->addr, &tr->ts, mode); - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); } if (ret < 0) @@ -572,7 +591,7 @@ int io_timeout(struct io_kiocb *req, unsigned int issue_flags) struct list_head *entry; u32 tail, off = timeout->off; - spin_lock_irq(&ctx->timeout_lock); + raw_spin_lock_irq(&ctx->timeout_lock); /* * sqe->off holds how many events that need to occur for this @@ -611,7 +630,7 @@ add: list_add(&timeout->list, entry); data->timer.function = io_timeout_fn; hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), data->mode); - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); return IOU_ISSUE_SKIP_COMPLETE; } @@ -620,7 +639,7 @@ void io_queue_linked_timeout(struct io_kiocb *req) struct io_timeout *timeout = io_kiocb_to_cmd(req, struct io_timeout); struct io_ring_ctx *ctx = req->ctx; - spin_lock_irq(&ctx->timeout_lock); + raw_spin_lock_irq(&ctx->timeout_lock); /* * If the back reference is NULL, then our linked request finished * before we got a chance to setup the timer @@ -633,7 +652,7 @@ void io_queue_linked_timeout(struct io_kiocb *req) data->mode); list_add_tail(&timeout->list, &ctx->ltimeout_list); } - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); /* drop submission reference */ io_put_req(req); } @@ -661,22 +680,22 @@ __cold bool io_kill_timeouts(struct io_ring_ctx *ctx, struct io_uring_task *tctx bool cancel_all) { struct io_timeout *timeout, *tmp; - int canceled = 0; + LIST_HEAD(list); /* * completion_lock is needed for io_match_task(). Take it before * timeout_lockfirst to keep locking ordering. */ spin_lock(&ctx->completion_lock); - spin_lock_irq(&ctx->timeout_lock); + raw_spin_lock_irq(&ctx->timeout_lock); list_for_each_entry_safe(timeout, tmp, &ctx->timeout_list, list) { struct io_kiocb *req = cmd_to_io_kiocb(timeout); - if (io_match_task(req, tctx, cancel_all) && - io_kill_timeout(req, -ECANCELED)) - canceled++; + if (io_match_task(req, tctx, cancel_all)) + io_kill_timeout(req, &list); } - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); spin_unlock(&ctx->completion_lock); - return canceled != 0; + + return io_flush_killed_timeouts(&list, -ECANCELED); } diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index af842e9b4eb9..ce7726a04883 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -16,26 +16,35 @@ #include "rsrc.h" #include "uring_cmd.h" -static struct uring_cache *io_uring_async_get(struct io_kiocb *req) +static struct io_uring_cmd_data *io_uring_async_get(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; - struct uring_cache *cache; + struct io_uring_cmd_data *cache; cache = io_alloc_cache_get(&ctx->uring_cache); if (cache) { + cache->op_data = NULL; req->flags |= REQ_F_ASYNC_DATA; req->async_data = cache; return cache; } - if (!io_alloc_async_data(req)) - return req->async_data; + if (!io_alloc_async_data(req)) { + cache = req->async_data; + cache->op_data = NULL; + return cache; + } return NULL; } static void io_req_uring_cleanup(struct io_kiocb *req, unsigned int issue_flags) { struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd); - struct uring_cache *cache = req->async_data; + struct io_uring_cmd_data *cache = req->async_data; + + if (cache->op_data) { + kfree(cache->op_data); + cache->op_data = NULL; + } if (issue_flags & IO_URING_F_UNLOCKED) return; @@ -183,7 +192,7 @@ static int io_uring_cmd_prep_setup(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd); - struct uring_cache *cache; + struct io_uring_cmd_data *cache; cache = io_uring_async_get(req); if (unlikely(!cache)) @@ -260,7 +269,7 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags) ret = file->f_op->uring_cmd(ioucmd, issue_flags); if (ret == -EAGAIN) { - struct uring_cache *cache = req->async_data; + struct io_uring_cmd_data *cache = req->async_data; if (ioucmd->sqe != (void *) cache) memcpy(cache, ioucmd->sqe, uring_sqe_size(req->ctx)); diff --git a/io_uring/uring_cmd.h b/io_uring/uring_cmd.h index 7dba0f1efc58..f6837ee0955b 100644 --- a/io_uring/uring_cmd.h +++ b/io_uring/uring_cmd.h @@ -1,9 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -struct uring_cache { - struct io_uring_sqe sqes[2]; -}; - int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags); int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f7f892a52a37..77f56674aaa9 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -21281,11 +21281,15 @@ patch_map_ops_generic: * changed in some incompatible and hard to support * way, it's fine to back out this inlining logic */ +#ifdef CONFIG_SMP insn_buf[0] = BPF_MOV32_IMM(BPF_REG_0, (u32)(unsigned long)&pcpu_hot.cpu_number); insn_buf[1] = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0); insn_buf[2] = BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0); cnt = 3; - +#else + insn_buf[0] = BPF_ALU32_REG(BPF_XOR, BPF_REG_0, BPF_REG_0); + cnt = 1; +#endif new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index f321ed515f3a..0f910c828973 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -197,10 +197,8 @@ static struct cpuset top_cpuset = { /* * There are two global locks guarding cpuset structures - cpuset_mutex and - * callback_lock. We also require taking task_lock() when dereferencing a - * task's cpuset pointer. See "The task_lock() exception", at the end of this - * comment. The cpuset code uses only cpuset_mutex. Other kernel subsystems - * can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset + * callback_lock. The cpuset code uses only cpuset_mutex. Other kernel + * subsystems can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset * structures. Note that cpuset_mutex needs to be a mutex as it is used in * paths that rely on priority inheritance (e.g. scheduler - on RT) for * correctness. @@ -229,9 +227,6 @@ static struct cpuset top_cpuset = { * The cpuset_common_seq_show() handlers only hold callback_lock across * small pieces of code, such as when reading out possibly multi-word * cpumasks and nodemasks. - * - * Accessing a task's cpuset should be done in accordance with the - * guidelines for accessing subsystem state in kernel/cgroup.c */ static DEFINE_MUTEX(cpuset_mutex); @@ -890,7 +885,15 @@ v2: */ if (cgrpv2) { for (i = 0; i < ndoms; i++) { - cpumask_copy(doms[i], csa[i]->effective_cpus); + /* + * The top cpuset may contain some boot time isolated + * CPUs that need to be excluded from the sched domain. + */ + if (csa[i] == &top_cpuset) + cpumask_and(doms[i], csa[i]->effective_cpus, + housekeeping_cpumask(HK_TYPE_DOMAIN)); + else + cpumask_copy(doms[i], csa[i]->effective_cpus); if (dattr) dattr[i] = SD_ATTR_INIT; } @@ -3121,29 +3124,6 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of, int retval = -ENODEV; buf = strstrip(buf); - - /* - * CPU or memory hotunplug may leave @cs w/o any execution - * resources, in which case the hotplug code asynchronously updates - * configuration and transfers all tasks to the nearest ancestor - * which can execute. - * - * As writes to "cpus" or "mems" may restore @cs's execution - * resources, wait for the previously scheduled operations before - * proceeding, so that we don't end up keep removing tasks added - * after execution capability is restored. - * - * cpuset_handle_hotplug may call back into cgroup core asynchronously - * via cgroup_transfer_tasks() and waiting for it from a cgroupfs - * operation like this one can lead to a deadlock through kernfs - * active_ref protection. Let's break the protection. Losing the - * protection is okay as we check whether @cs is online after - * grabbing cpuset_mutex anyway. This only happens on the legacy - * hierarchies. - */ - css_get(&cs->css); - kernfs_break_active_protection(of->kn); - cpus_read_lock(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) @@ -3176,8 +3156,6 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of, out_unlock: mutex_unlock(&cpuset_mutex); cpus_read_unlock(); - kernfs_unbreak_active_protection(of->kn); - css_put(&cs->css); flush_workqueue(cpuset_migrate_mm_wq); return retval ?: nbytes; } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index fa04b14a7d72..5d71ef85420c 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1915,6 +1915,7 @@ void uprobe_free_utask(struct task_struct *t) if (!utask) return; + t->utask = NULL; WARN_ON_ONCE(utask->active_uprobe || utask->xol_vaddr); timer_delete_sync(&utask->ri_timer); @@ -1924,7 +1925,6 @@ void uprobe_free_utask(struct task_struct *t) ri = free_ret_instance(ri, true /* cleanup_hprobe */); kfree(utask); - t->utask = NULL; } #define RI_TIMER_PERIOD (HZ / 10) /* 100 ms */ diff --git a/kernel/fork.c b/kernel/fork.c index 1450b461d196..9b301180fd41 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -639,11 +639,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, LIST_HEAD(uf); VMA_ITERATOR(vmi, mm, 0); - uprobe_start_dup_mmap(); - if (mmap_write_lock_killable(oldmm)) { - retval = -EINTR; - goto fail_uprobe_end; - } + if (mmap_write_lock_killable(oldmm)) + return -EINTR; flush_cache_dup_mm(oldmm); uprobe_dup_mmap(oldmm, mm); /* @@ -782,8 +779,6 @@ out: dup_userfaultfd_complete(&uf); else dup_userfaultfd_fail(&uf); -fail_uprobe_end: - uprobe_end_dup_mmap(); return retval; fail_nomem_anon_vma_fork: @@ -1692,9 +1687,11 @@ static struct mm_struct *dup_mm(struct task_struct *tsk, if (!mm_init(mm, tsk, mm->user_ns)) goto fail_nomem; + uprobe_start_dup_mmap(); err = dup_mmap(mm, oldmm); if (err) goto free_pt; + uprobe_end_dup_mmap(); mm->hiwater_rss = get_mm_rss(mm); mm->hiwater_vm = mm->total_vm; @@ -1709,6 +1706,8 @@ free_pt: mm->binfmt = NULL; mm_init_owner(mm, NULL); mmput(mm); + if (err) + uprobe_end_dup_mmap(); fail_nomem: return NULL; diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh index 383fd43ac612..7e1340da5aca 100755 --- a/kernel/gen_kheaders.sh +++ b/kernel/gen_kheaders.sh @@ -89,6 +89,7 @@ find $cpio_dir -type f -print0 | # Create archive and try to normalize metadata for reproducibility. tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \ + --exclude=".__afs*" --exclude=".nfs*" \ --owner=0 --group=0 --sort=name --numeric-owner --mode=u=rw,go=r,a+X \ -I $XZ -cf $tarfile -C $cpio_dir/ . > /dev/null diff --git a/kernel/kcov.c b/kernel/kcov.c index 28a6be6e64fd..187ba1b80bda 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -166,7 +166,7 @@ static void kcov_remote_area_put(struct kcov_remote_area *area, * Unlike in_serving_softirq(), this function returns false when called during * a hardirq or an NMI that happened in the softirq context. */ -static inline bool in_softirq_really(void) +static __always_inline bool in_softirq_really(void) { return in_serving_softirq() && !in_hardirq() && !in_nmi(); } diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index e858de203eb6..697a56d3d949 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1292,7 +1292,13 @@ static int __sched task_blocks_on_rt_mutex(struct rt_mutex_base *lock, */ get_task_struct(owner); + preempt_disable(); raw_spin_unlock_irq(&lock->wait_lock); + /* wake up any tasks on the wake_q before calling rt_mutex_adjust_prio_chain */ + wake_up_q(wake_q); + wake_q_init(wake_q); + preempt_enable(); + res = rt_mutex_adjust_prio_chain(owner, chwalk, lock, next_lock, waiter, task); @@ -1596,6 +1602,7 @@ static void __sched remove_waiter(struct rt_mutex_base *lock, * or TASK_UNINTERRUPTIBLE) * @timeout: the pre-initialized and started timer, or NULL for none * @waiter: the pre-initialized rt_mutex_waiter + * @wake_q: wake_q of tasks to wake when we drop the lock->wait_lock * * Must be called with lock->wait_lock held and interrupts disabled */ @@ -1603,7 +1610,8 @@ static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock, struct ww_acquire_ctx *ww_ctx, unsigned int state, struct hrtimer_sleeper *timeout, - struct rt_mutex_waiter *waiter) + struct rt_mutex_waiter *waiter, + struct wake_q_head *wake_q) __releases(&lock->wait_lock) __acquires(&lock->wait_lock) { struct rt_mutex *rtm = container_of(lock, struct rt_mutex, rtmutex); @@ -1634,7 +1642,13 @@ static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock, owner = rt_mutex_owner(lock); else owner = NULL; + preempt_disable(); raw_spin_unlock_irq(&lock->wait_lock); + if (wake_q) { + wake_up_q(wake_q); + wake_q_init(wake_q); + } + preempt_enable(); if (!owner || !rtmutex_spin_on_owner(lock, waiter, owner)) rt_mutex_schedule(); @@ -1708,7 +1722,7 @@ static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock, ret = task_blocks_on_rt_mutex(lock, waiter, current, ww_ctx, chwalk, wake_q); if (likely(!ret)) - ret = rt_mutex_slowlock_block(lock, ww_ctx, state, NULL, waiter); + ret = rt_mutex_slowlock_block(lock, ww_ctx, state, NULL, waiter, wake_q); if (likely(!ret)) { /* acquired the lock */ diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c index 33ea31d6a7b3..191e4720e546 100644 --- a/kernel/locking/rtmutex_api.c +++ b/kernel/locking/rtmutex_api.c @@ -383,7 +383,7 @@ int __sched rt_mutex_wait_proxy_lock(struct rt_mutex_base *lock, raw_spin_lock_irq(&lock->wait_lock); /* sleep on the mutex */ set_current_state(TASK_INTERRUPTIBLE); - ret = rt_mutex_slowlock_block(lock, NULL, TASK_INTERRUPTIBLE, to, waiter); + ret = rt_mutex_slowlock_block(lock, NULL, TASK_INTERRUPTIBLE, to, waiter, NULL); /* * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might * have to fix that up. diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 7fff1d045477..19813b387ef9 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -2747,6 +2747,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev) { struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx); bool prev_on_scx = prev->sched_class == &ext_sched_class; + bool prev_on_rq = prev->scx.flags & SCX_TASK_QUEUED; int nr_loops = SCX_DSP_MAX_LOOPS; lockdep_assert_rq_held(rq); @@ -2779,8 +2780,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev) * See scx_ops_disable_workfn() for the explanation on the * bypassing test. */ - if ((prev->scx.flags & SCX_TASK_QUEUED) && - prev->scx.slice && !scx_rq_bypassing(rq)) { + if (prev_on_rq && prev->scx.slice && !scx_rq_bypassing(rq)) { rq->scx.flags |= SCX_RQ_BAL_KEEP; goto has_tasks; } @@ -2813,6 +2813,10 @@ static int balance_one(struct rq *rq, struct task_struct *prev) flush_dispatch_buf(rq); + if (prev_on_rq && prev->scx.slice) { + rq->scx.flags |= SCX_RQ_BAL_KEEP; + goto has_tasks; + } if (rq->scx.local_dsq.nr) goto has_tasks; if (consume_global_dsq(rq)) @@ -2838,8 +2842,7 @@ no_tasks: * Didn't find another task to run. Keep running @prev unless * %SCX_OPS_ENQ_LAST is in effect. */ - if ((prev->scx.flags & SCX_TASK_QUEUED) && - (!static_branch_unlikely(&scx_ops_enq_last) || + if (prev_on_rq && (!static_branch_unlikely(&scx_ops_enq_last) || scx_rq_bypassing(rq))) { rq->scx.flags |= SCX_RQ_BAL_KEEP; goto has_tasks; @@ -3034,7 +3037,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p, */ if (p->scx.slice && !scx_rq_bypassing(rq)) { dispatch_enqueue(&rq->scx.local_dsq, p, SCX_ENQ_HEAD); - return; + goto switch_class; } /* @@ -3051,6 +3054,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p, } } +switch_class: if (next && next->sched_class != &ext_sched_class) switch_class(rq, next); } @@ -3586,16 +3590,8 @@ static void reset_idle_masks(void) cpumask_copy(idle_masks.smt, cpu_online_mask); } -void __scx_update_idle(struct rq *rq, bool idle) +static void update_builtin_idle(int cpu, bool idle) { - int cpu = cpu_of(rq); - - if (SCX_HAS_OP(update_idle) && !scx_rq_bypassing(rq)) { - SCX_CALL_OP(SCX_KF_REST, update_idle, cpu_of(rq), idle); - if (!static_branch_unlikely(&scx_builtin_idle_enabled)) - return; - } - if (idle) cpumask_set_cpu(cpu, idle_masks.cpu); else @@ -3622,6 +3618,57 @@ void __scx_update_idle(struct rq *rq, bool idle) #endif } +/* + * Update the idle state of a CPU to @idle. + * + * If @do_notify is true, ops.update_idle() is invoked to notify the scx + * scheduler of an actual idle state transition (idle to busy or vice + * versa). If @do_notify is false, only the idle state in the idle masks is + * refreshed without invoking ops.update_idle(). + * + * This distinction is necessary, because an idle CPU can be "reserved" and + * awakened via scx_bpf_pick_idle_cpu() + scx_bpf_kick_cpu(), marking it as + * busy even if no tasks are dispatched. In this case, the CPU may return + * to idle without a true state transition. Refreshing the idle masks + * without invoking ops.update_idle() ensures accurate idle state tracking + * while avoiding unnecessary updates and maintaining balanced state + * transitions. + */ +void __scx_update_idle(struct rq *rq, bool idle, bool do_notify) +{ + int cpu = cpu_of(rq); + + lockdep_assert_rq_held(rq); + + /* + * Trigger ops.update_idle() only when transitioning from a task to + * the idle thread and vice versa. + * + * Idle transitions are indicated by do_notify being set to true, + * managed by put_prev_task_idle()/set_next_task_idle(). + */ + if (SCX_HAS_OP(update_idle) && do_notify && !scx_rq_bypassing(rq)) + SCX_CALL_OP(SCX_KF_REST, update_idle, cpu_of(rq), idle); + + /* + * Update the idle masks: + * - for real idle transitions (do_notify == true) + * - for idle-to-idle transitions (indicated by the previous task + * being the idle thread, managed by pick_task_idle()) + * + * Skip updating idle masks if the previous task is not the idle + * thread, since set_next_task_idle() has already handled it when + * transitioning from a task to the idle thread (calling this + * function with do_notify == true). + * + * In this way we can avoid updating the idle masks twice, + * unnecessarily. + */ + if (static_branch_likely(&scx_builtin_idle_enabled)) + if (do_notify || is_idle_task(rq->curr)) + update_builtin_idle(cpu, idle); +} + static void handle_hotplug(struct rq *rq, bool online) { int cpu = cpu_of(rq); @@ -4744,10 +4791,9 @@ static void scx_ops_bypass(bool bypass) */ for_each_possible_cpu(cpu) { struct rq *rq = cpu_rq(cpu); - struct rq_flags rf; struct task_struct *p, *n; - rq_lock(rq, &rf); + raw_spin_rq_lock(rq); if (bypass) { WARN_ON_ONCE(rq->scx.flags & SCX_RQ_BYPASSING); @@ -4763,7 +4809,7 @@ static void scx_ops_bypass(bool bypass) * sees scx_rq_bypassing() before moving tasks to SCX. */ if (!scx_enabled()) { - rq_unlock_irqrestore(rq, &rf); + raw_spin_rq_unlock(rq); continue; } @@ -4783,10 +4829,11 @@ static void scx_ops_bypass(bool bypass) sched_enq_and_set_task(&ctx); } - rq_unlock(rq, &rf); - /* resched to restore ticks and idle state */ - resched_cpu(cpu); + if (cpu_online(cpu) || cpu == smp_processor_id()) + resched_curr(rq); + + raw_spin_rq_unlock(rq); } atomic_dec(&scx_ops_breather_depth); @@ -7013,7 +7060,7 @@ __bpf_kfunc int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id, return -ENOENT; INIT_LIST_HEAD(&kit->cursor.node); - kit->cursor.flags |= SCX_DSQ_LNODE_ITER_CURSOR | flags; + kit->cursor.flags = SCX_DSQ_LNODE_ITER_CURSOR | flags; kit->cursor.priv = READ_ONCE(kit->dsq->seq); return 0; diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h index b1675bb59fc4..4d022d17ac7d 100644 --- a/kernel/sched/ext.h +++ b/kernel/sched/ext.h @@ -57,15 +57,15 @@ static inline void init_sched_ext_class(void) {} #endif /* CONFIG_SCHED_CLASS_EXT */ #if defined(CONFIG_SCHED_CLASS_EXT) && defined(CONFIG_SMP) -void __scx_update_idle(struct rq *rq, bool idle); +void __scx_update_idle(struct rq *rq, bool idle, bool do_notify); -static inline void scx_update_idle(struct rq *rq, bool idle) +static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify) { if (scx_enabled()) - __scx_update_idle(rq, idle); + __scx_update_idle(rq, idle, do_notify); } #else -static inline void scx_update_idle(struct rq *rq, bool idle) {} +static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify) {} #endif #ifdef CONFIG_CGROUP_SCHED diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 621696269584..2c85c86b455f 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -452,19 +452,20 @@ static void wakeup_preempt_idle(struct rq *rq, struct task_struct *p, int flags) static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct task_struct *next) { dl_server_update_idle_time(rq, prev); - scx_update_idle(rq, false); + scx_update_idle(rq, false, true); } static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first) { update_idle_core(rq); - scx_update_idle(rq, true); + scx_update_idle(rq, true, true); schedstat_inc(rq->sched_goidle); next->se.exec_start = rq_clock_task(rq); } struct task_struct *pick_task_idle(struct rq *rq) { + scx_update_idle(rq, true, false); return rq->idle; } diff --git a/kernel/static_call_inline.c b/kernel/static_call_inline.c index 5259cda486d0..bb7d066a7c39 100644 --- a/kernel/static_call_inline.c +++ b/kernel/static_call_inline.c @@ -15,7 +15,7 @@ extern struct static_call_site __start_static_call_sites[], extern struct static_call_tramp_key __start_static_call_tramp_key[], __stop_static_call_tramp_key[]; -static int static_call_initialized; +int static_call_initialized; /* * Must be called before early_initcall() to be effective. diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 0bf78517b5d4..30e3ddc8a8a8 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -833,7 +833,7 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs #endif { for_each_set_bit(i, &bitmap, sizeof(bitmap) * BITS_PER_BYTE) { - struct fgraph_ops *gops = fgraph_array[i]; + struct fgraph_ops *gops = READ_ONCE(fgraph_array[i]); if (gops == &fgraph_stub) continue; @@ -1215,7 +1215,7 @@ void fgraph_update_pid_func(void) static int start_graph_tracing(void) { unsigned long **ret_stack_list; - int ret; + int ret, cpu; ret_stack_list = kcalloc(FTRACE_RETSTACK_ALLOC_SIZE, sizeof(*ret_stack_list), GFP_KERNEL); @@ -1223,6 +1223,12 @@ static int start_graph_tracing(void) if (!ret_stack_list) return -ENOMEM; + /* The cpu_boot init_task->ret_stack will never be freed */ + for_each_online_cpu(cpu) { + if (!idle_task(cpu)->ret_stack) + ftrace_graph_init_idle_task(idle_task(cpu), cpu); + } + do { ret = alloc_retstack_tasklist(ret_stack_list); } while (ret == -EAGAIN); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 9b17efb1a87d..2e113f8b13a2 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -902,16 +902,13 @@ static void profile_graph_return(struct ftrace_graph_ret *trace, } static struct fgraph_ops fprofiler_ops = { - .ops = { - .flags = FTRACE_OPS_FL_INITIALIZED, - INIT_OPS_HASH(fprofiler_ops.ops) - }, .entryfunc = &profile_graph_entry, .retfunc = &profile_graph_return, }; static int register_ftrace_profiler(void) { + ftrace_ops_set_global_filter(&fprofiler_ops.ops); return register_ftrace_graph(&fprofiler_ops); } @@ -922,12 +919,11 @@ static void unregister_ftrace_profiler(void) #else static struct ftrace_ops ftrace_profile_ops __read_mostly = { .func = function_profile_call, - .flags = FTRACE_OPS_FL_INITIALIZED, - INIT_OPS_HASH(ftrace_profile_ops) }; static int register_ftrace_profiler(void) { + ftrace_ops_set_global_filter(&ftrace_profile_ops); return register_ftrace_function(&ftrace_profile_ops); } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 7e257e855dd1..60210fb5b211 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -7019,7 +7019,11 @@ static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer, lockdep_assert_held(&cpu_buffer->mapping_lock); nr_subbufs = cpu_buffer->nr_pages + 1; /* + reader-subbuf */ - nr_pages = ((nr_subbufs + 1) << subbuf_order) - pgoff; /* + meta-page */ + nr_pages = ((nr_subbufs + 1) << subbuf_order); /* + meta-page */ + if (nr_pages <= pgoff) + return -EINVAL; + + nr_pages -= pgoff; nr_vma_pages = vma_pages(vma); if (!nr_vma_pages || nr_vma_pages > nr_pages) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index be62f0ea1814..f8aebcb01e62 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3611,17 +3611,12 @@ char *trace_iter_expand_format(struct trace_iterator *iter) } /* Returns true if the string is safe to dereference from an event */ -static bool trace_safe_str(struct trace_iterator *iter, const char *str, - bool star, int len) +static bool trace_safe_str(struct trace_iterator *iter, const char *str) { unsigned long addr = (unsigned long)str; struct trace_event *trace_event; struct trace_event_call *event; - /* Ignore strings with no length */ - if (star && !len) - return true; - /* OK if part of the event data */ if ((addr >= (unsigned long)iter->ent) && (addr < (unsigned long)iter->ent + iter->ent_size)) @@ -3661,181 +3656,69 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str, return false; } -static DEFINE_STATIC_KEY_FALSE(trace_no_verify); - -static int test_can_verify_check(const char *fmt, ...) -{ - char buf[16]; - va_list ap; - int ret; - - /* - * The verifier is dependent on vsnprintf() modifies the va_list - * passed to it, where it is sent as a reference. Some architectures - * (like x86_32) passes it by value, which means that vsnprintf() - * does not modify the va_list passed to it, and the verifier - * would then need to be able to understand all the values that - * vsnprintf can use. If it is passed by value, then the verifier - * is disabled. - */ - va_start(ap, fmt); - vsnprintf(buf, 16, "%d", ap); - ret = va_arg(ap, int); - va_end(ap); - - return ret; -} - -static void test_can_verify(void) -{ - if (!test_can_verify_check("%d %d", 0, 1)) { - pr_info("trace event string verifier disabled\n"); - static_branch_inc(&trace_no_verify); - } -} - /** - * trace_check_vprintf - Check dereferenced strings while writing to the seq buffer + * ignore_event - Check dereferenced fields while writing to the seq buffer * @iter: The iterator that holds the seq buffer and the event being printed - * @fmt: The format used to print the event - * @ap: The va_list holding the data to print from @fmt. * - * This writes the data into the @iter->seq buffer using the data from - * @fmt and @ap. If the format has a %s, then the source of the string - * is examined to make sure it is safe to print, otherwise it will - * warn and print "[UNSAFE MEMORY]" in place of the dereferenced string - * pointer. + * At boot up, test_event_printk() will flag any event that dereferences + * a string with "%s" that does exist in the ring buffer. It may still + * be valid, as the string may point to a static string in the kernel + * rodata that never gets freed. But if the string pointer is pointing + * to something that was allocated, there's a chance that it can be freed + * by the time the user reads the trace. This would cause a bad memory + * access by the kernel and possibly crash the system. + * + * This function will check if the event has any fields flagged as needing + * to be checked at runtime and perform those checks. + * + * If it is found that a field is unsafe, it will write into the @iter->seq + * a message stating what was found to be unsafe. + * + * @return: true if the event is unsafe and should be ignored, + * false otherwise. */ -void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, - va_list ap) +bool ignore_event(struct trace_iterator *iter) { - long text_delta = 0; - long data_delta = 0; - const char *p = fmt; - const char *str; - bool good; - int i, j; + struct ftrace_event_field *field; + struct trace_event *trace_event; + struct trace_event_call *event; + struct list_head *head; + struct trace_seq *seq; + const void *ptr; - if (WARN_ON_ONCE(!fmt)) - return; + trace_event = ftrace_find_event(iter->ent->type); - if (static_branch_unlikely(&trace_no_verify)) - goto print; + seq = &iter->seq; - /* - * When the kernel is booted with the tp_printk command line - * parameter, trace events go directly through to printk(). - * It also is checked by this function, but it does not - * have an associated trace_array (tr) for it. - */ - if (iter->tr) { - text_delta = iter->tr->text_delta; - data_delta = iter->tr->data_delta; + if (!trace_event) { + trace_seq_printf(seq, "EVENT ID %d NOT FOUND?\n", iter->ent->type); + return true; } - /* Don't bother checking when doing a ftrace_dump() */ - if (iter->fmt == static_fmt_buf) - goto print; - - while (*p) { - bool star = false; - int len = 0; - - j = 0; - - /* - * We only care about %s and variants - * as well as %p[sS] if delta is non-zero - */ - for (i = 0; p[i]; i++) { - if (i + 1 >= iter->fmt_size) { - /* - * If we can't expand the copy buffer, - * just print it. - */ - if (!trace_iter_expand_format(iter)) - goto print; - } - - if (p[i] == '\\' && p[i+1]) { - i++; - continue; - } - if (p[i] == '%') { - /* Need to test cases like %08.*s */ - for (j = 1; p[i+j]; j++) { - if (isdigit(p[i+j]) || - p[i+j] == '.') - continue; - if (p[i+j] == '*') { - star = true; - continue; - } - break; - } - if (p[i+j] == 's') - break; - - if (text_delta && p[i+1] == 'p' && - ((p[i+2] == 's' || p[i+2] == 'S'))) - break; - - star = false; - } - j = 0; - } - /* If no %s found then just print normally */ - if (!p[i]) - break; - - /* Copy up to the %s, and print that */ - strncpy(iter->fmt, p, i); - iter->fmt[i] = '\0'; - trace_seq_vprintf(&iter->seq, iter->fmt, ap); + event = container_of(trace_event, struct trace_event_call, event); + if (!(event->flags & TRACE_EVENT_FL_TEST_STR)) + return false; - /* Add delta to %pS pointers */ - if (p[i+1] == 'p') { - unsigned long addr; - char fmt[4]; + head = trace_get_fields(event); + if (!head) { + trace_seq_printf(seq, "FIELDS FOR EVENT '%s' NOT FOUND?\n", + trace_event_name(event)); + return true; + } - fmt[0] = '%'; - fmt[1] = 'p'; - fmt[2] = p[i+2]; /* Either %ps or %pS */ - fmt[3] = '\0'; + /* Offsets are from the iter->ent that points to the raw event */ + ptr = iter->ent; - addr = va_arg(ap, unsigned long); - addr += text_delta; - trace_seq_printf(&iter->seq, fmt, (void *)addr); + list_for_each_entry(field, head, link) { + const char *str; + bool good; - p += i + 3; + if (!field->needs_test) continue; - } - - /* - * If iter->seq is full, the above call no longer guarantees - * that ap is in sync with fmt processing, and further calls - * to va_arg() can return wrong positional arguments. - * - * Ensure that ap is no longer used in this case. - */ - if (iter->seq.full) { - p = ""; - break; - } - if (star) - len = va_arg(ap, int); + str = *(const char **)(ptr + field->offset); - /* The ap now points to the string data of the %s */ - str = va_arg(ap, const char *); - - good = trace_safe_str(iter, str, star, len); - - /* Could be from the last boot */ - if (data_delta && !good) { - str += data_delta; - good = trace_safe_str(iter, str, star, len); - } + good = trace_safe_str(iter, str); /* * If you hit this warning, it is likely that the @@ -3846,44 +3729,14 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, * instead. See samples/trace_events/trace-events-sample.h * for reference. */ - if (WARN_ONCE(!good, "fmt: '%s' current_buffer: '%s'", - fmt, seq_buf_str(&iter->seq.seq))) { - int ret; - - /* Try to safely read the string */ - if (star) { - if (len + 1 > iter->fmt_size) - len = iter->fmt_size - 1; - if (len < 0) - len = 0; - ret = copy_from_kernel_nofault(iter->fmt, str, len); - iter->fmt[len] = 0; - star = false; - } else { - ret = strncpy_from_kernel_nofault(iter->fmt, str, - iter->fmt_size); - } - if (ret < 0) - trace_seq_printf(&iter->seq, "(0x%px)", str); - else - trace_seq_printf(&iter->seq, "(0x%px:%s)", - str, iter->fmt); - str = "[UNSAFE-MEMORY]"; - strcpy(iter->fmt, "%s"); - } else { - strncpy(iter->fmt, p + i, j + 1); - iter->fmt[j+1] = '\0'; + if (WARN_ONCE(!good, "event '%s' has unsafe pointer field '%s'", + trace_event_name(event), field->name)) { + trace_seq_printf(seq, "EVENT %s: HAS UNSAFE POINTER FIELD '%s'\n", + trace_event_name(event), field->name); + return true; } - if (star) - trace_seq_printf(&iter->seq, iter->fmt, len, str); - else - trace_seq_printf(&iter->seq, iter->fmt, str); - - p += i + j + 1; } - print: - if (*p) - trace_seq_vprintf(&iter->seq, p, ap); + return false; } const char *trace_event_format(struct trace_iterator *iter, const char *fmt) @@ -4353,6 +4206,15 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter) if (event) { if (tr->trace_flags & TRACE_ITER_FIELDS) return print_event_fields(iter, event); + /* + * For TRACE_EVENT() events, the print_fmt is not + * safe to use if the array has delta offsets + * Force printing via the fields. + */ + if ((tr->text_delta || tr->data_delta) && + event->type > __TRACE_LAST_TYPE) + return print_event_fields(iter, event); + return event->funcs->trace(iter, sym_flags, event); } @@ -5225,6 +5087,9 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf, cpumask_var_t tracing_cpumask_new; int err; + if (count == 0 || count > KMALLOC_MAX_SIZE) + return -EINVAL; + if (!zalloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL)) return -ENOMEM; @@ -10777,8 +10642,6 @@ __init static int tracer_alloc_buffers(void) register_snapshot_cmd(); - test_can_verify(); - return 0; out_free_pipe_cpumask: diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 266740b4e121..9691b47b5f3d 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -667,9 +667,8 @@ void trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer, bool trace_is_tracepoint_string(const char *str); const char *trace_event_format(struct trace_iterator *iter, const char *fmt); -void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, - va_list ap) __printf(2, 0); char *trace_iter_expand_format(struct trace_iterator *iter); +bool ignore_event(struct trace_iterator *iter); int trace_empty(struct trace_iterator *iter); @@ -1413,7 +1412,8 @@ struct ftrace_event_field { int filter_type; int offset; int size; - int is_signed; + unsigned int is_signed:1; + unsigned int needs_test:1; int len; }; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 77e68efbd43e..770e7ed91716 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -82,7 +82,7 @@ static int system_refcount_dec(struct event_subsystem *system) } static struct ftrace_event_field * -__find_event_field(struct list_head *head, char *name) +__find_event_field(struct list_head *head, const char *name) { struct ftrace_event_field *field; @@ -114,7 +114,8 @@ trace_find_event_field(struct trace_event_call *call, char *name) static int __trace_define_field(struct list_head *head, const char *type, const char *name, int offset, int size, - int is_signed, int filter_type, int len) + int is_signed, int filter_type, int len, + int need_test) { struct ftrace_event_field *field; @@ -133,6 +134,7 @@ static int __trace_define_field(struct list_head *head, const char *type, field->offset = offset; field->size = size; field->is_signed = is_signed; + field->needs_test = need_test; field->len = len; list_add(&field->link, head); @@ -151,13 +153,13 @@ int trace_define_field(struct trace_event_call *call, const char *type, head = trace_get_fields(call); return __trace_define_field(head, type, name, offset, size, - is_signed, filter_type, 0); + is_signed, filter_type, 0, 0); } EXPORT_SYMBOL_GPL(trace_define_field); static int trace_define_field_ext(struct trace_event_call *call, const char *type, const char *name, int offset, int size, int is_signed, - int filter_type, int len) + int filter_type, int len, int need_test) { struct list_head *head; @@ -166,13 +168,13 @@ static int trace_define_field_ext(struct trace_event_call *call, const char *typ head = trace_get_fields(call); return __trace_define_field(head, type, name, offset, size, - is_signed, filter_type, len); + is_signed, filter_type, len, need_test); } #define __generic_field(type, item, filter_type) \ ret = __trace_define_field(&ftrace_generic_fields, #type, \ #item, 0, 0, is_signed_type(type), \ - filter_type, 0); \ + filter_type, 0, 0); \ if (ret) \ return ret; @@ -181,7 +183,8 @@ static int trace_define_field_ext(struct trace_event_call *call, const char *typ "common_" #item, \ offsetof(typeof(ent), item), \ sizeof(ent.item), \ - is_signed_type(type), FILTER_OTHER, 0); \ + is_signed_type(type), FILTER_OTHER, \ + 0, 0); \ if (ret) \ return ret; @@ -244,19 +247,16 @@ int trace_event_get_offsets(struct trace_event_call *call) return tail->offset + tail->size; } -/* - * Check if the referenced field is an array and return true, - * as arrays are OK to dereference. - */ -static bool test_field(const char *fmt, struct trace_event_call *call) + +static struct trace_event_fields *find_event_field(const char *fmt, + struct trace_event_call *call) { struct trace_event_fields *field = call->class->fields_array; - const char *array_descriptor; const char *p = fmt; int len; if (!(len = str_has_prefix(fmt, "REC->"))) - return false; + return NULL; fmt += len; for (p = fmt; *p; p++) { if (!isalnum(*p) && *p != '_') @@ -265,16 +265,141 @@ static bool test_field(const char *fmt, struct trace_event_call *call) len = p - fmt; for (; field->type; field++) { - if (strncmp(field->name, fmt, len) || - field->name[len]) + if (strncmp(field->name, fmt, len) || field->name[len]) continue; - array_descriptor = strchr(field->type, '['); - /* This is an array and is OK to dereference. */ - return array_descriptor != NULL; + + return field; + } + return NULL; +} + +/* + * Check if the referenced field is an array and return true, + * as arrays are OK to dereference. + */ +static bool test_field(const char *fmt, struct trace_event_call *call) +{ + struct trace_event_fields *field; + + field = find_event_field(fmt, call); + if (!field) + return false; + + /* This is an array and is OK to dereference. */ + return strchr(field->type, '[') != NULL; +} + +/* Look for a string within an argument */ +static bool find_print_string(const char *arg, const char *str, const char *end) +{ + const char *r; + + r = strstr(arg, str); + return r && r < end; +} + +/* Return true if the argument pointer is safe */ +static bool process_pointer(const char *fmt, int len, struct trace_event_call *call) +{ + const char *r, *e, *a; + + e = fmt + len; + + /* Find the REC-> in the argument */ + r = strstr(fmt, "REC->"); + if (r && r < e) { + /* + * Addresses of events on the buffer, or an array on the buffer is + * OK to dereference. There's ways to fool this, but + * this is to catch common mistakes, not malicious code. + */ + a = strchr(fmt, '&'); + if ((a && (a < r)) || test_field(r, call)) + return true; + } else if (find_print_string(fmt, "__get_dynamic_array(", e)) { + return true; + } else if (find_print_string(fmt, "__get_rel_dynamic_array(", e)) { + return true; + } else if (find_print_string(fmt, "__get_dynamic_array_len(", e)) { + return true; + } else if (find_print_string(fmt, "__get_rel_dynamic_array_len(", e)) { + return true; + } else if (find_print_string(fmt, "__get_sockaddr(", e)) { + return true; + } else if (find_print_string(fmt, "__get_rel_sockaddr(", e)) { + return true; } return false; } +/* Return true if the string is safe */ +static bool process_string(const char *fmt, int len, struct trace_event_call *call) +{ + struct trace_event_fields *field; + const char *r, *e, *s; + + e = fmt + len; + + /* + * There are several helper functions that return strings. + * If the argument contains a function, then assume its field is valid. + * It is considered that the argument has a function if it has: + * alphanumeric or '_' before a parenthesis. + */ + s = fmt; + do { + r = strstr(s, "("); + if (!r || r >= e) + break; + for (int i = 1; r - i >= s; i++) { + char ch = *(r - i); + if (isspace(ch)) + continue; + if (isalnum(ch) || ch == '_') + return true; + /* Anything else, this isn't a function */ + break; + } + /* A function could be wrapped in parethesis, try the next one */ + s = r + 1; + } while (s < e); + + /* + * Check for arrays. If the argument has: foo[REC->val] + * then it is very likely that foo is an array of strings + * that are safe to use. + */ + r = strstr(s, "["); + if (r && r < e) { + r = strstr(r, "REC->"); + if (r && r < e) + return true; + } + + /* + * If there's any strings in the argument consider this arg OK as it + * could be: REC->field ? "foo" : "bar" and we don't want to get into + * verifying that logic here. + */ + if (find_print_string(fmt, "\"", e)) + return true; + + /* Dereferenced strings are also valid like any other pointer */ + if (process_pointer(fmt, len, call)) + return true; + + /* Make sure the field is found */ + field = find_event_field(fmt, call); + if (!field) + return false; + + /* Test this field's string before printing the event */ + call->flags |= TRACE_EVENT_FL_TEST_STR; + field->needs_test = 1; + + return true; +} + /* * Examine the print fmt of the event looking for unsafe dereference * pointers using %p* that could be recorded in the trace event and @@ -284,13 +409,14 @@ static bool test_field(const char *fmt, struct trace_event_call *call) static void test_event_printk(struct trace_event_call *call) { u64 dereference_flags = 0; + u64 string_flags = 0; bool first = true; - const char *fmt, *c, *r, *a; + const char *fmt; int parens = 0; char in_quote = 0; int start_arg = 0; int arg = 0; - int i; + int i, e; fmt = call->print_fmt; @@ -374,8 +500,16 @@ static void test_event_printk(struct trace_event_call *call) star = true; continue; } - if ((fmt[i + j] == 's') && star) - arg++; + if ((fmt[i + j] == 's')) { + if (star) + arg++; + if (WARN_ONCE(arg == 63, + "Too many args for event: %s", + trace_event_name(call))) + return; + dereference_flags |= 1ULL << arg; + string_flags |= 1ULL << arg; + } break; } break; @@ -403,42 +537,47 @@ static void test_event_printk(struct trace_event_call *call) case ',': if (in_quote || parens) continue; + e = i; i++; while (isspace(fmt[i])) i++; - start_arg = i; - if (!(dereference_flags & (1ULL << arg))) - goto next_arg; - /* Find the REC-> in the argument */ - c = strchr(fmt + i, ','); - r = strstr(fmt + i, "REC->"); - if (r && (!c || r < c)) { - /* - * Addresses of events on the buffer, - * or an array on the buffer is - * OK to dereference. - * There's ways to fool this, but - * this is to catch common mistakes, - * not malicious code. - */ - a = strchr(fmt + i, '&'); - if ((a && (a < r)) || test_field(r, call)) + /* + * If start_arg is zero, then this is the start of the + * first argument. The processing of the argument happens + * when the end of the argument is found, as it needs to + * handle paranthesis and such. + */ + if (!start_arg) { + start_arg = i; + /* Balance out the i++ in the for loop */ + i--; + continue; + } + + if (dereference_flags & (1ULL << arg)) { + if (string_flags & (1ULL << arg)) { + if (process_string(fmt + start_arg, e - start_arg, call)) + dereference_flags &= ~(1ULL << arg); + } else if (process_pointer(fmt + start_arg, e - start_arg, call)) dereference_flags &= ~(1ULL << arg); - } else if ((r = strstr(fmt + i, "__get_dynamic_array(")) && - (!c || r < c)) { - dereference_flags &= ~(1ULL << arg); - } else if ((r = strstr(fmt + i, "__get_sockaddr(")) && - (!c || r < c)) { - dereference_flags &= ~(1ULL << arg); } - next_arg: - i--; + start_arg = i; arg++; + /* Balance out the i++ in the for loop */ + i--; } } + if (dereference_flags & (1ULL << arg)) { + if (string_flags & (1ULL << arg)) { + if (process_string(fmt + start_arg, i - start_arg, call)) + dereference_flags &= ~(1ULL << arg); + } else if (process_pointer(fmt + start_arg, i - start_arg, call)) + dereference_flags &= ~(1ULL << arg); + } + /* * If you triggered the below warning, the trace event reported * uses an unsafe dereference pointer %p*. As the data stored @@ -2471,7 +2610,7 @@ event_define_fields(struct trace_event_call *call) ret = trace_define_field_ext(call, field->type, field->name, offset, field->size, field->is_signed, field->filter_type, - field->len); + field->len, field->needs_test); if (WARN_ON_ONCE(ret)) { pr_err("error code is %d\n", ret); break; diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 74c353164ca1..d358c9935164 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -176,7 +176,8 @@ static void function_trace_start(struct trace_array *tr) tracing_reset_online_cpus(&tr->array_buffer); } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER +/* fregs are guaranteed not to be NULL if HAVE_DYNAMIC_FTRACE_WITH_ARGS is set */ +#if defined(CONFIG_FUNCTION_GRAPH_TRACER) && defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) static __always_inline unsigned long function_get_true_parent_ip(unsigned long parent_ip, struct ftrace_regs *fregs) { diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 263fac44d3ca..0642ea174849 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -725,7 +725,7 @@ static int trace_kprobe_module_callback(struct notifier_block *nb, static struct notifier_block trace_kprobe_module_nb = { .notifier_call = trace_kprobe_module_callback, - .priority = 1 /* Invoked after kprobe module callback */ + .priority = 2 /* Invoked after kprobe and jump_label module callback */ }; static int trace_kprobe_register_module_notifier(void) { @@ -940,8 +940,10 @@ static int __trace_kprobe_create(int argc, const char *argv[]) } /* a symbol specified */ symbol = kstrdup(argv[1], GFP_KERNEL); - if (!symbol) - return -ENOMEM; + if (!symbol) { + ret = -ENOMEM; + goto error; + } tmp = strchr(symbol, '%'); if (tmp) { diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index da748b7cbc4d..03d56f711ad1 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -317,10 +317,14 @@ EXPORT_SYMBOL(trace_raw_output_prep); void trace_event_printf(struct trace_iterator *iter, const char *fmt, ...) { + struct trace_seq *s = &iter->seq; va_list ap; + if (ignore_event(iter)) + return; + va_start(ap, fmt); - trace_check_vprintf(iter, trace_event_format(iter, fmt), ap); + trace_seq_vprintf(s, trace_event_format(iter, fmt), ap); va_end(ap); } EXPORT_SYMBOL(trace_event_printf); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 8b07576814a5..9362484a653c 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2508,6 +2508,7 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, return; } + WARN_ON_ONCE(cpu != WORK_CPU_UNBOUND && !cpu_online(cpu)); dwork->wq = wq; dwork->cpu = cpu; timer->expires = jiffies + delay; @@ -2533,6 +2534,12 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, * @dwork: work to queue * @delay: number of jiffies to wait before queueing * + * We queue the delayed_work to a specific CPU, for non-zero delays the + * caller must ensure it is online and can't go away. Callers that fail + * to ensure this, may get @dwork->timer queued to an offlined CPU and + * this will prevent queueing of @dwork->work unless the offlined CPU + * becomes online again. + * * Return: %false if @work was already on a queue, %true otherwise. If * @delay is zero and @dwork is idle, it will be scheduled for immediate * execution. @@ -3680,23 +3687,27 @@ void workqueue_softirq_dead(unsigned int cpu) * check_flush_dependency - check for flush dependency sanity * @target_wq: workqueue being flushed * @target_work: work item being flushed (NULL for workqueue flushes) + * @from_cancel: are we called from the work cancel path * * %current is trying to flush the whole @target_wq or @target_work on it. - * If @target_wq doesn't have %WQ_MEM_RECLAIM, verify that %current is not - * reclaiming memory or running on a workqueue which doesn't have - * %WQ_MEM_RECLAIM as that can break forward-progress guarantee leading to - * a deadlock. + * If this is not the cancel path (which implies work being flushed is either + * already running, or will not be at all), check if @target_wq doesn't have + * %WQ_MEM_RECLAIM and verify that %current is not reclaiming memory or running + * on a workqueue which doesn't have %WQ_MEM_RECLAIM as that can break forward- + * progress guarantee leading to a deadlock. */ static void check_flush_dependency(struct workqueue_struct *target_wq, - struct work_struct *target_work) + struct work_struct *target_work, + bool from_cancel) { - work_func_t target_func = target_work ? target_work->func : NULL; + work_func_t target_func; struct worker *worker; - if (target_wq->flags & WQ_MEM_RECLAIM) + if (from_cancel || target_wq->flags & WQ_MEM_RECLAIM) return; worker = current_wq_worker(); + target_func = target_work ? target_work->func : NULL; WARN_ONCE(current->flags & PF_MEMALLOC, "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%ps", @@ -3980,7 +3991,7 @@ void __flush_workqueue(struct workqueue_struct *wq) list_add_tail(&this_flusher.list, &wq->flusher_overflow); } - check_flush_dependency(wq, NULL); + check_flush_dependency(wq, NULL, false); mutex_unlock(&wq->mutex); @@ -4155,7 +4166,7 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, } wq = pwq->wq; - check_flush_dependency(wq, work); + check_flush_dependency(wq, work, from_cancel); insert_wq_barrier(pwq, barr, work, worker); raw_spin_unlock_irq(&pool->lock); @@ -5641,6 +5652,7 @@ static void wq_adjust_max_active(struct workqueue_struct *wq) } while (activated); } +__printf(1, 0) static struct workqueue_struct *__alloc_workqueue(const char *fmt, unsigned int flags, int max_active, va_list args) diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 35f7560a309a..7dcebf118a3e 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -209,6 +209,13 @@ void pgalloc_tag_swap(struct folio *new, struct folio *old) return; } + /* + * Clear tag references to avoid debug warning when using + * __alloc_tag_ref_set() with non-empty reference. + */ + set_codetag_empty(&ref_old); + set_codetag_empty(&ref_new); + /* swap tags */ __alloc_tag_ref_set(&ref_old, tag_new); update_page_tag_ref(handle_old, &ref_old); @@ -401,28 +408,52 @@ repeat: static int vm_module_tags_populate(void) { - unsigned long phys_size = vm_module_tags->nr_pages << PAGE_SHIFT; + unsigned long phys_end = ALIGN_DOWN(module_tags.start_addr, PAGE_SIZE) + + (vm_module_tags->nr_pages << PAGE_SHIFT); + unsigned long new_end = module_tags.start_addr + module_tags.size; - if (phys_size < module_tags.size) { + if (phys_end < new_end) { struct page **next_page = vm_module_tags->pages + vm_module_tags->nr_pages; - unsigned long addr = module_tags.start_addr + phys_size; + unsigned long old_shadow_end = ALIGN(phys_end, MODULE_ALIGN); + unsigned long new_shadow_end = ALIGN(new_end, MODULE_ALIGN); unsigned long more_pages; unsigned long nr; - more_pages = ALIGN(module_tags.size - phys_size, PAGE_SIZE) >> PAGE_SHIFT; + more_pages = ALIGN(new_end - phys_end, PAGE_SIZE) >> PAGE_SHIFT; nr = alloc_pages_bulk_array_node(GFP_KERNEL | __GFP_NOWARN, NUMA_NO_NODE, more_pages, next_page); if (nr < more_pages || - vmap_pages_range(addr, addr + (nr << PAGE_SHIFT), PAGE_KERNEL, + vmap_pages_range(phys_end, phys_end + (nr << PAGE_SHIFT), PAGE_KERNEL, next_page, PAGE_SHIFT) < 0) { /* Clean up and error out */ for (int i = 0; i < nr; i++) __free_page(next_page[i]); return -ENOMEM; } + vm_module_tags->nr_pages += nr; + + /* + * Kasan allocates 1 byte of shadow for every 8 bytes of data. + * When kasan_alloc_module_shadow allocates shadow memory, + * its unit of allocation is a page. + * Therefore, here we need to align to MODULE_ALIGN. + */ + if (old_shadow_end < new_shadow_end) + kasan_alloc_module_shadow((void *)old_shadow_end, + new_shadow_end - old_shadow_end, + GFP_KERNEL); } + /* + * Mark the pages as accessible, now that they are mapped. + * With hardware tag-based KASAN, marking is skipped for + * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc(). + */ + kasan_unpoison_vmalloc((void *)module_tags.start_addr, + new_end - module_tags.start_addr, + KASAN_VMALLOC_PROT_NORMAL); + return 0; } diff --git a/lib/maple_tree.c b/lib/maple_tree.c index d0ae808f3a14..047397136f15 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -4354,6 +4354,7 @@ int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, ret = 1; } if (ret < 0 && range_lo > min) { + mas_reset(mas); ret = mas_empty_area(mas, min, range_hi, 1); if (ret == 0) ret = 1; diff --git a/mm/damon/core.c b/mm/damon/core.c index 8b8e2933dcd4..0776452a1abb 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -868,6 +868,11 @@ static int damon_commit_schemes(struct damon_ctx *dst, struct damon_ctx *src) NUMA_NO_NODE); if (!new_scheme) return -ENOMEM; + err = damos_commit(new_scheme, src_scheme); + if (err) { + damon_destroy_scheme(new_scheme); + return err; + } damon_add_scheme(dst, new_scheme); } return 0; @@ -961,8 +966,11 @@ static int damon_commit_targets( return -ENOMEM; err = damon_commit_target(new_target, false, src_target, damon_target_has_pid(src)); - if (err) + if (err) { + damon_destroy_target(new_target); return err; + } + damon_add_target(dst, new_target); } return 0; } diff --git a/mm/filemap.c b/mm/filemap.c index f61cf51c2238..4f476411a9a2 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -124,15 +124,6 @@ * ->private_lock (zap_pte_range->block_dirty_folio) */ -static void mapping_set_update(struct xa_state *xas, - struct address_space *mapping) -{ - if (dax_mapping(mapping) || shmem_mapping(mapping)) - return; - xas_set_update(xas, workingset_update_node); - xas_set_lru(xas, &shadow_nodes); -} - static void page_cache_delete(struct address_space *mapping, struct folio *folio, void *shadow) { @@ -1532,7 +1523,7 @@ void folio_end_read(struct folio *folio, bool success) /* Must be in bottom byte for x86 to work */ BUILD_BUG_ON(PG_uptodate > 7); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); - VM_BUG_ON_FOLIO(folio_test_uptodate(folio), folio); + VM_BUG_ON_FOLIO(success && folio_test_uptodate(folio), folio); if (likely(success)) mask |= 1 << PG_uptodate; @@ -3005,7 +2996,7 @@ static inline loff_t folio_seek_hole_data(struct xa_state *xas, if (ops->is_partially_uptodate(folio, offset, bsz) == seek_data) break; - start = (start + bsz) & ~(bsz - 1); + start = (start + bsz) & ~((u64)bsz - 1); offset += bsz; } while (offset < folio_size(folio)); unlock: diff --git a/mm/huge_memory.c b/mm/huge_memory.c index ee335d96fc39..db64116a4f84 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1176,11 +1176,12 @@ static struct folio *vma_alloc_anon_folio_pmd(struct vm_area_struct *vma, folio_throttle_swaprate(folio, gfp); /* - * When a folio is not zeroed during allocation (__GFP_ZERO not used), - * folio_zero_user() is used to make sure that the page corresponding - * to the faulting address will be hot in the cache after zeroing. + * When a folio is not zeroed during allocation (__GFP_ZERO not used) + * or user folios require special handling, folio_zero_user() is used to + * make sure that the page corresponding to the faulting address will be + * hot in the cache after zeroing. */ - if (!alloc_zeroed()) + if (user_alloc_needs_zeroing()) folio_zero_user(folio, addr); /* * The memory barrier inside __folio_mark_uptodate makes sure that @@ -2205,6 +2206,16 @@ static pmd_t move_soft_dirty_pmd(pmd_t pmd) return pmd; } +static pmd_t clear_uffd_wp_pmd(pmd_t pmd) +{ + if (pmd_present(pmd)) + pmd = pmd_clear_uffd_wp(pmd); + else if (is_swap_pmd(pmd)) + pmd = pmd_swp_clear_uffd_wp(pmd); + + return pmd; +} + bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd) { @@ -2243,6 +2254,8 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, pgtable_trans_huge_deposit(mm, new_pmd, pgtable); } pmd = move_soft_dirty_pmd(pmd); + if (vma_has_uffd_without_event_remap(vma)) + pmd = clear_uffd_wp_pmd(pmd); set_pmd_at(mm, new_addr, new_pmd, pmd); if (force_flush) flush_pmd_tlb_range(vma, old_addr, old_addr + PMD_SIZE); @@ -3576,7 +3589,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, !list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; if (folio_test_partially_mapped(folio)) { - __folio_clear_partially_mapped(folio); + folio_clear_partially_mapped(folio); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); } @@ -3688,7 +3701,7 @@ bool __folio_unqueue_deferred_split(struct folio *folio) if (!list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; if (folio_test_partially_mapped(folio)) { - __folio_clear_partially_mapped(folio); + folio_clear_partially_mapped(folio); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); } @@ -3732,7 +3745,7 @@ void deferred_split_folio(struct folio *folio, bool partially_mapped) spin_lock_irqsave(&ds_queue->split_queue_lock, flags); if (partially_mapped) { if (!folio_test_partially_mapped(folio)) { - __folio_set_partially_mapped(folio); + folio_set_partially_mapped(folio); if (folio_test_pmd_mappable(folio)) count_vm_event(THP_DEFERRED_SPLIT_PAGE); count_mthp_stat(folio_order(folio), MTHP_STAT_SPLIT_DEFERRED); @@ -3825,7 +3838,7 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, } else { /* We lost race with folio_put() */ if (folio_test_partially_mapped(folio)) { - __folio_clear_partially_mapped(folio); + folio_clear_partially_mapped(folio); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); } @@ -4168,7 +4181,7 @@ static ssize_t split_huge_pages_write(struct file *file, const char __user *buf, size_t input_len = strlen(input_buf); tok = strsep(&buf, ","); - if (tok) { + if (tok && buf) { strscpy(file_path, tok); } else { ret = -EINVAL; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ea2ed8e301ef..eaaec19caa7c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5340,7 +5340,7 @@ again: break; } ret = copy_user_large_folio(new_folio, pte_folio, - ALIGN_DOWN(addr, sz), dst_vma); + addr, dst_vma); folio_put(pte_folio); if (ret) { folio_put(new_folio); @@ -5402,6 +5402,7 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte, unsigned long sz) { + bool need_clear_uffd_wp = vma_has_uffd_without_event_remap(vma); struct hstate *h = hstate_vma(vma); struct mm_struct *mm = vma->vm_mm; spinlock_t *src_ptl, *dst_ptl; @@ -5418,7 +5419,18 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); pte = huge_ptep_get_and_clear(mm, old_addr, src_pte); - set_huge_pte_at(mm, new_addr, dst_pte, pte, sz); + + if (need_clear_uffd_wp && pte_marker_uffd_wp(pte)) + huge_pte_clear(mm, new_addr, dst_pte, sz); + else { + if (need_clear_uffd_wp) { + if (pte_present(pte)) + pte = huge_pte_clear_uffd_wp(pte); + else if (is_swap_pte(pte)) + pte = pte_swp_clear_uffd_wp(pte); + } + set_huge_pte_at(mm, new_addr, dst_pte, pte, sz); + } if (src_ptl != dst_ptl) spin_unlock(src_ptl); @@ -6643,8 +6655,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, *foliop = NULL; goto out; } - ret = copy_user_large_folio(folio, *foliop, - ALIGN_DOWN(dst_addr, size), dst_vma); + ret = copy_user_large_folio(folio, *foliop, dst_addr, dst_vma); folio_put(*foliop); *foliop = NULL; if (ret) { @@ -7212,7 +7223,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, spte = hugetlb_walk(svma, saddr, vma_mmu_pagesize(svma)); if (spte) { - get_page(virt_to_page(spte)); + ptdesc_pmd_pts_inc(virt_to_ptdesc(spte)); break; } } @@ -7227,7 +7238,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, (pmd_t *)((unsigned long)spte & PAGE_MASK)); mm_inc_nr_pmds(mm); } else { - put_page(virt_to_page(spte)); + ptdesc_pmd_pts_dec(virt_to_ptdesc(spte)); } spin_unlock(&mm->page_table_lock); out: @@ -7239,10 +7250,6 @@ out: /* * unmap huge page backed by shared pte. * - * Hugetlb pte page is ref counted at the time of mapping. If pte is shared - * indicated by page_count > 1, unmap is achieved by clearing pud and - * decrementing the ref count. If count == 1, the pte page is not shared. - * * Called with page table lock held. * * returns: 1 successfully unmapped a shared pte page @@ -7251,18 +7258,20 @@ out: int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { + unsigned long sz = huge_page_size(hstate_vma(vma)); pgd_t *pgd = pgd_offset(mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); i_mmap_assert_write_locked(vma->vm_file->f_mapping); hugetlb_vma_assert_locked(vma); - BUG_ON(page_count(virt_to_page(ptep)) == 0); - if (page_count(virt_to_page(ptep)) == 1) + if (sz != PMD_SIZE) + return 0; + if (!ptdesc_pmd_pts_count(virt_to_ptdesc(ptep))) return 0; pud_clear(pud); - put_page(virt_to_page(ptep)); + ptdesc_pmd_pts_dec(virt_to_ptdesc(ptep)); mm_dec_nr_pmds(mm); return 1; } diff --git a/mm/internal.h b/mm/internal.h index cb8d8e8e3ffa..9826f7dce607 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -1285,12 +1285,6 @@ void touch_pud(struct vm_area_struct *vma, unsigned long addr, void touch_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, bool write); -static inline bool alloc_zeroed(void) -{ - return static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, - &init_on_alloc); -} - /* * Parses a string with mem suffixes into its order. Useful to parse kernel * parameters. @@ -1510,6 +1504,12 @@ static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, /* Only track the nodes of mappings with shadow entries */ void workingset_update_node(struct xa_node *node); extern struct list_lru shadow_nodes; +#define mapping_set_update(xas, mapping) do { \ + if (!dax_mapping(mapping) && !shmem_mapping(mapping)) { \ + xas_set_update(xas, workingset_update_node); \ + xas_set_lru(xas, &shadow_nodes); \ + } \ +} while (0) /* mremap.c */ unsigned long move_page_tables(struct vm_area_struct *vma, diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 6f8d46d107b4..653dbb1ff05c 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -19,6 +19,7 @@ #include <linux/rcupdate_wait.h> #include <linux/swapops.h> #include <linux/shmem_fs.h> +#include <linux/dax.h> #include <linux/ksm.h> #include <asm/tlb.h> @@ -1837,6 +1838,8 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, if (result != SCAN_SUCCEED) goto out; + mapping_set_update(&xas, mapping); + __folio_set_locked(new_folio); if (is_shmem) __folio_set_swapbacked(new_folio); diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 2a945c07ae99..820ba3b5cbfc 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -373,7 +373,7 @@ static void print_unreferenced(struct seq_file *seq, for (i = 0; i < nr_entries; i++) { void *ptr = (void *)entries[i]; - warn_or_seq_printf(seq, " [<%pK>] %pS\n", ptr, ptr); + warn_or_seq_printf(seq, " %pS\n", ptr); } } @@ -1093,7 +1093,7 @@ void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size, pr_debug("%s(0x%px, %zu)\n", __func__, ptr, size); if (kmemleak_enabled && ptr && !IS_ERR_PCPU(ptr)) - create_object_percpu((__force unsigned long)ptr, size, 0, gfp); + create_object_percpu((__force unsigned long)ptr, size, 1, gfp); } EXPORT_SYMBOL_GPL(kmemleak_alloc_percpu); diff --git a/mm/list_lru.c b/mm/list_lru.c index f93ada6a207b..7d69434c70e0 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -77,7 +77,6 @@ again: spin_lock(&l->lock); nr_items = READ_ONCE(l->nr_items); if (likely(nr_items != LONG_MIN)) { - WARN_ON(nr_items < 0); rcu_read_unlock(); return l; } @@ -450,6 +449,7 @@ static void memcg_reparent_list_lru_one(struct list_lru *lru, int nid, list_splice_init(&src->list, &dst->list); if (src->nr_items) { + WARN_ON(src->nr_items < 0); dst->nr_items += src->nr_items; set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru)); } diff --git a/mm/memfd.c b/mm/memfd.c index c17c3ea701a1..35a370d75c9a 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -170,7 +170,7 @@ static int memfd_wait_for_pins(struct address_space *mapping) return error; } -static unsigned int *memfd_file_seals_ptr(struct file *file) +unsigned int *memfd_file_seals_ptr(struct file *file) { if (shmem_file(file)) return &SHMEM_I(file_inode(file))->seals; diff --git a/mm/memory.c b/mm/memory.c index 75c2dfd04f72..398c031be9ba 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4733,12 +4733,12 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf) folio_throttle_swaprate(folio, gfp); /* * When a folio is not zeroed during allocation - * (__GFP_ZERO not used), folio_zero_user() is used - * to make sure that the page corresponding to the - * faulting address will be hot in the cache after - * zeroing. + * (__GFP_ZERO not used) or user folios require special + * handling, folio_zero_user() is used to make sure + * that the page corresponding to the faulting address + * will be hot in the cache after zeroing. */ - if (!alloc_zeroed()) + if (user_alloc_needs_zeroing()) folio_zero_user(folio, vmf->address); return folio; } @@ -6815,9 +6815,10 @@ static inline int process_huge_page( return 0; } -static void clear_gigantic_page(struct folio *folio, unsigned long addr, +static void clear_gigantic_page(struct folio *folio, unsigned long addr_hint, unsigned int nr_pages) { + unsigned long addr = ALIGN_DOWN(addr_hint, folio_size(folio)); int i; might_sleep(); @@ -6851,13 +6852,14 @@ void folio_zero_user(struct folio *folio, unsigned long addr_hint) } static int copy_user_gigantic_page(struct folio *dst, struct folio *src, - unsigned long addr, + unsigned long addr_hint, struct vm_area_struct *vma, unsigned int nr_pages) { - int i; + unsigned long addr = ALIGN_DOWN(addr_hint, folio_size(dst)); struct page *dst_page; struct page *src_page; + int i; for (i = 0; i < nr_pages; i++) { dst_page = folio_page(dst, i); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 04f35659717a..162407fbf2bc 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2268,7 +2268,8 @@ struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, page = __alloc_pages_noprof(gfp, order, nid, nodemask); - if (unlikely(pol->mode == MPOL_INTERLEAVE) && page) { + if (unlikely(pol->mode == MPOL_INTERLEAVE || + pol->mode == MPOL_WEIGHTED_INTERLEAVE) && page) { /* skip NUMA_INTERLEAVE_HIT update if numa stats is disabled */ if (static_branch_likely(&vm_numa_stat_key) && page_to_nid(page) == nid) { diff --git a/mm/mmap.c b/mm/mmap.c index d32b7e701058..aec208f90337 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -47,6 +47,7 @@ #include <linux/oom.h> #include <linux/sched/mm.h> #include <linux/ksm.h> +#include <linux/memfd.h> #include <linux/uaccess.h> #include <asm/cacheflush.h> @@ -368,6 +369,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr, if (file) { struct inode *inode = file_inode(file); + unsigned int seals = memfd_file_seals(file); unsigned long flags_mask; if (!file_mmap_ok(file, inode, pgoff, len)) @@ -408,6 +410,8 @@ unsigned long do_mmap(struct file *file, unsigned long addr, vm_flags |= VM_SHARED | VM_MAYSHARE; if (!(file->f_mode & FMODE_WRITE)) vm_flags &= ~(VM_MAYWRITE | VM_SHARED); + else if (is_readonly_sealed(seals, vm_flags)) + vm_flags &= ~VM_MAYWRITE; fallthrough; case MAP_PRIVATE: if (!(file->f_mode & FMODE_READ)) @@ -888,7 +892,7 @@ __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, if (get_area) { addr = get_area(file, addr, len, pgoff, flags); - } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) + } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && !file && !addr /* no hint */ && IS_ALIGNED(len, PMD_SIZE)) { /* Ensures that larger anonymous mappings are THP aligned. */ diff --git a/mm/mremap.c b/mm/mremap.c index 60473413836b..cff7f552f909 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -138,6 +138,7 @@ static int move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, struct vm_area_struct *new_vma, pmd_t *new_pmd, unsigned long new_addr, bool need_rmap_locks) { + bool need_clear_uffd_wp = vma_has_uffd_without_event_remap(vma); struct mm_struct *mm = vma->vm_mm; pte_t *old_pte, *new_pte, pte; pmd_t dummy_pmdval; @@ -216,7 +217,18 @@ static int move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, force_flush = true; pte = move_pte(pte, old_addr, new_addr); pte = move_soft_dirty_pte(pte); - set_pte_at(mm, new_addr, new_pte, pte); + + if (need_clear_uffd_wp && pte_marker_uffd_wp(pte)) + pte_clear(mm, new_addr, new_pte); + else { + if (need_clear_uffd_wp) { + if (pte_present(pte)) + pte = pte_clear_uffd_wp(pte); + else if (is_swap_pte(pte)) + pte = pte_swp_clear_uffd_wp(pte); + } + set_pte_at(mm, new_addr, new_pte, pte); + } } arch_leave_lazy_mmu_mode(); @@ -278,6 +290,15 @@ static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr, if (WARN_ON_ONCE(!pmd_none(*new_pmd))) return false; + /* If this pmd belongs to a uffd vma with remap events disabled, we need + * to ensure that the uffd-wp state is cleared from all pgtables. This + * means recursing into lower page tables in move_page_tables(), and we + * can reuse the existing code if we simply treat the entry as "not + * moved". + */ + if (vma_has_uffd_without_event_remap(vma)) + return false; + /* * We don't have to worry about the ordering of src and dst * ptlocks because exclusive mmap_lock prevents deadlock. @@ -333,6 +354,15 @@ static bool move_normal_pud(struct vm_area_struct *vma, unsigned long old_addr, if (WARN_ON_ONCE(!pud_none(*new_pud))) return false; + /* If this pud belongs to a uffd vma with remap events disabled, we need + * to ensure that the uffd-wp state is cleared from all pgtables. This + * means recursing into lower page tables in move_page_tables(), and we + * can reuse the existing code if we simply treat the entry as "not + * moved". + */ + if (vma_has_uffd_without_event_remap(vma)) + return false; + /* * We don't have to worry about the ordering of src and dst * ptlocks because exclusive mmap_lock prevents deadlock. diff --git a/mm/page-writeback.c b/mm/page-writeback.c index d213ead95675..d9861e42b2bd 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -692,6 +692,8 @@ static unsigned long bdi_ratio_from_pages(unsigned long pages) unsigned long ratio; global_dirty_limits(&background_thresh, &dirty_thresh); + if (!dirty_thresh) + return -EINVAL; ratio = div64_u64(pages * 100ULL * BDI_RATIO_SCALE, dirty_thresh); return ratio; @@ -790,13 +792,15 @@ int bdi_set_min_bytes(struct backing_dev_info *bdi, u64 min_bytes) { int ret; unsigned long pages = min_bytes >> PAGE_SHIFT; - unsigned long min_ratio; + long min_ratio; ret = bdi_check_pages_limit(pages); if (ret) return ret; min_ratio = bdi_ratio_from_pages(pages); + if (min_ratio < 0) + return min_ratio; return __bdi_set_min_ratio(bdi, min_ratio); } @@ -809,13 +813,15 @@ int bdi_set_max_bytes(struct backing_dev_info *bdi, u64 max_bytes) { int ret; unsigned long pages = max_bytes >> PAGE_SHIFT; - unsigned long max_ratio; + long max_ratio; ret = bdi_check_pages_limit(pages); if (ret) return ret; max_ratio = bdi_ratio_from_pages(pages); + if (max_ratio < 0) + return max_ratio; return __bdi_set_max_ratio(bdi, max_ratio); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 1cb4b8c8886d..cae7b93864c2 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1238,13 +1238,15 @@ static void split_large_buddy(struct zone *zone, struct page *page, if (order > pageblock_order) order = pageblock_order; - while (pfn != end) { + do { int mt = get_pfnblock_migratetype(page, pfn); __free_one_page(page, pfn, zone, order, mt, fpi); pfn += 1 << order; + if (pfn == end) + break; page = pfn_to_page(pfn); - } + } while (1); } static void free_one_page(struct zone *zone, struct page *page, diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 5297dcc38c37..5a882f2b10f9 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -279,7 +279,7 @@ static unsigned long pmdp_get_lockless_start(void) { return 0; } static void pmdp_get_lockless_end(unsigned long irqflags) { } #endif -pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp) +pte_t *___pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp) { unsigned long irqflags; pmd_t pmdval; diff --git a/mm/readahead.c b/mm/readahead.c index ea650b8b02fb..e151f4b13ca4 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -646,7 +646,11 @@ void page_cache_async_ra(struct readahead_control *ractl, 1UL << order); if (index == expected) { ra->start += ra->size; - ra->size = get_next_ra_size(ra, max_pages); + /* + * In the case of MADV_HUGEPAGE, the actual size might exceed + * the readahead window. + */ + ra->size = max(ra->size, get_next_ra_size(ra, max_pages)); ra->async_size = ra->size; goto readit; } diff --git a/mm/shmem.c b/mm/shmem.c index ccb9629a0f70..ac58d4fb2e6f 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -787,6 +787,14 @@ static bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index, } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +static void shmem_update_stats(struct folio *folio, int nr_pages) +{ + if (folio_test_pmd_mappable(folio)) + __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, nr_pages); + __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr_pages); + __lruvec_stat_mod_folio(folio, NR_SHMEM, nr_pages); +} + /* * Somewhat like filemap_add_folio, but error if expected item has gone. */ @@ -821,10 +829,7 @@ static int shmem_add_to_page_cache(struct folio *folio, xas_store(&xas, folio); if (xas_error(&xas)) goto unlock; - if (folio_test_pmd_mappable(folio)) - __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, nr); - __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr); - __lruvec_stat_mod_folio(folio, NR_SHMEM, nr); + shmem_update_stats(folio, nr); mapping->nrpages += nr; unlock: xas_unlock_irq(&xas); @@ -852,8 +857,7 @@ static void shmem_delete_from_page_cache(struct folio *folio, void *radswap) error = shmem_replace_entry(mapping, folio->index, folio, radswap); folio->mapping = NULL; mapping->nrpages -= nr; - __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, -nr); - __lruvec_stat_mod_folio(folio, NR_SHMEM, -nr); + shmem_update_stats(folio, -nr); xa_unlock_irq(&mapping->i_pages); folio_put_refs(folio, nr); BUG_ON(error); @@ -1531,7 +1535,7 @@ try_split: !shmem_falloc->waitq && index >= shmem_falloc->start && index < shmem_falloc->next) - shmem_falloc->nr_unswapped++; + shmem_falloc->nr_unswapped += nr_pages; else shmem_falloc = NULL; spin_unlock(&inode->i_lock); @@ -1685,6 +1689,7 @@ unsigned long shmem_allowable_huge_orders(struct inode *inode, unsigned long mask = READ_ONCE(huge_shmem_orders_always); unsigned long within_size_orders = READ_ONCE(huge_shmem_orders_within_size); unsigned long vm_flags = vma ? vma->vm_flags : 0; + pgoff_t aligned_index; bool global_huge; loff_t i_size; int order; @@ -1719,9 +1724,9 @@ unsigned long shmem_allowable_huge_orders(struct inode *inode, /* Allow mTHP that will be fully within i_size. */ order = highest_order(within_size_orders); while (within_size_orders) { - index = round_up(index + 1, order); + aligned_index = round_up(index + 1, 1 << order); i_size = round_up(i_size_read(inode), PAGE_SIZE); - if (i_size >> PAGE_SHIFT >= index) { + if (i_size >> PAGE_SHIFT >= aligned_index) { mask |= within_size_orders; break; } @@ -1969,10 +1974,8 @@ static int shmem_replace_folio(struct folio **foliop, gfp_t gfp, } if (!error) { mem_cgroup_replace_folio(old, new); - __lruvec_stat_mod_folio(new, NR_FILE_PAGES, nr_pages); - __lruvec_stat_mod_folio(new, NR_SHMEM, nr_pages); - __lruvec_stat_mod_folio(old, NR_FILE_PAGES, -nr_pages); - __lruvec_stat_mod_folio(old, NR_SHMEM, -nr_pages); + shmem_update_stats(new, nr_pages); + shmem_update_stats(old, -nr_pages); } xa_unlock_irq(&swap_mapping->i_pages); diff --git a/mm/util.c b/mm/util.c index c1c3b06ab4f9..60aa40f612b8 100644 --- a/mm/util.c +++ b/mm/util.c @@ -297,12 +297,7 @@ void *memdup_user_nul(const void __user *src, size_t len) { char *p; - /* - * Always use GFP_KERNEL, since copy_from_user() can sleep and - * cause pagefault, which makes it pointless to use GFP_NOFS - * or GFP_ATOMIC. - */ - p = kmalloc_track_caller(len + 1, GFP_KERNEL); + p = kmem_buckets_alloc_track_caller(user_buckets, len + 1, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); @@ -2460,10 +2460,13 @@ unsigned long __mmap_region(struct file *file, unsigned long addr, /* If flags changed, we might be able to merge, so try again. */ if (map.retry_merge) { + struct vm_area_struct *merged; VMG_MMAP_STATE(vmg, &map, vma); vma_iter_config(map.vmi, map.addr, map.end); - vma_merge_existing_range(&vmg); + merged = vma_merge_existing_range(&vmg); + if (merged) + vma = merged; } __mmap_complete(&map, vma); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index f009b21705c1..5c88d0e90c20 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3374,7 +3374,8 @@ void vfree(const void *addr) struct page *page = vm->pages[i]; BUG_ON(!page); - mod_memcg_page_state(page, MEMCG_VMALLOC, -1); + if (!(vm->flags & VM_MAP_PUT_PAGES)) + mod_memcg_page_state(page, MEMCG_VMALLOC, -1); /* * High-order allocs for huge vmallocs are split, so * can be freed as an array of order-0 allocations @@ -3382,7 +3383,8 @@ void vfree(const void *addr) __free_page(page); cond_resched(); } - atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages); + if (!(vm->flags & VM_MAP_PUT_PAGES)) + atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages); kvfree(vm->pages); kfree(vm); } diff --git a/mm/vmscan.c b/mm/vmscan.c index 76378bc257e3..b1ec5ece067e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -374,7 +374,14 @@ unsigned long zone_reclaimable_pages(struct zone *zone) if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL)) nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON); - + /* + * If there are no reclaimable file-backed or anonymous pages, + * ensure zones with sufficient free pages are not skipped. + * This prevents zones like DMA32 from being ignored in reclaim + * scenarios where they can still help alleviate memory pressure. + */ + if (nr == 0) + nr = zone_page_state_snapshot(zone, NR_FREE_PAGES); return nr; } @@ -4635,6 +4642,9 @@ retry: reset_batch_size(walk); } + __mod_lruvec_state(lruvec, PGDEMOTE_KSWAPD + reclaimer_offset(), + stat.nr_demoted); + item = PGSTEAL_KSWAPD + reclaimer_offset(); if (!cgroup_reclaim(sc)) __count_vm_events(item, reclaimed); diff --git a/mm/vmstat.c b/mm/vmstat.c index 4d016314a56c..16bfe1c694dd 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -2122,10 +2122,20 @@ static void __init start_shepherd_timer(void) { int cpu; - for_each_possible_cpu(cpu) + for_each_possible_cpu(cpu) { INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu), vmstat_update); + /* + * For secondary CPUs during CPU hotplug scenarios, + * vmstat_cpu_online() will enable the work. + * mm/vmstat:online enables and disables vmstat_work + * symmetrically during CPU hotplug events. + */ + if (!cpu_online(cpu)) + disable_delayed_work_sync(&per_cpu(vmstat_work, cpu)); + } + schedule_delayed_work(&shepherd, round_jiffies_relative(sysctl_stat_interval)); } @@ -2148,13 +2158,14 @@ static int vmstat_cpu_online(unsigned int cpu) if (!node_state(cpu_to_node(cpu), N_CPU)) { node_set_state(cpu_to_node(cpu), N_CPU); } + enable_delayed_work(&per_cpu(vmstat_work, cpu)); return 0; } static int vmstat_cpu_down_prep(unsigned int cpu) { - cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu)); + disable_delayed_work_sync(&per_cpu(vmstat_work, cpu)); return 0; } diff --git a/mm/zswap.c b/mm/zswap.c index f6316b66fb23..30f5a27a6862 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -251,7 +251,7 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) struct zswap_pool *pool; char name[38]; /* 'zswap' + 32 char (max) num + \0 */ gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM; - int ret; + int ret, cpu; if (!zswap_has_pool) { /* if either are unset, pool initialization failed, and we @@ -285,6 +285,9 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) goto error; } + for_each_possible_cpu(cpu) + mutex_init(&per_cpu_ptr(pool->acomp_ctx, cpu)->mutex); + ret = cpuhp_state_add_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node); if (ret) @@ -821,11 +824,12 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) struct acomp_req *req; int ret; - mutex_init(&acomp_ctx->mutex); - + mutex_lock(&acomp_ctx->mutex); acomp_ctx->buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); - if (!acomp_ctx->buffer) - return -ENOMEM; + if (!acomp_ctx->buffer) { + ret = -ENOMEM; + goto buffer_fail; + } acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu)); if (IS_ERR(acomp)) { @@ -855,12 +859,15 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &acomp_ctx->wait); + mutex_unlock(&acomp_ctx->mutex); return 0; req_fail: crypto_free_acomp(acomp_ctx->acomp); acomp_fail: kfree(acomp_ctx->buffer); +buffer_fail: + mutex_unlock(&acomp_ctx->mutex); return ret; } @@ -869,17 +876,45 @@ static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node) struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node); struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu); + mutex_lock(&acomp_ctx->mutex); if (!IS_ERR_OR_NULL(acomp_ctx)) { if (!IS_ERR_OR_NULL(acomp_ctx->req)) acomp_request_free(acomp_ctx->req); + acomp_ctx->req = NULL; if (!IS_ERR_OR_NULL(acomp_ctx->acomp)) crypto_free_acomp(acomp_ctx->acomp); kfree(acomp_ctx->buffer); } + mutex_unlock(&acomp_ctx->mutex); return 0; } +static struct crypto_acomp_ctx *acomp_ctx_get_cpu_lock(struct zswap_pool *pool) +{ + struct crypto_acomp_ctx *acomp_ctx; + + for (;;) { + acomp_ctx = raw_cpu_ptr(pool->acomp_ctx); + mutex_lock(&acomp_ctx->mutex); + if (likely(acomp_ctx->req)) + return acomp_ctx; + /* + * It is possible that we were migrated to a different CPU after + * getting the per-CPU ctx but before the mutex was acquired. If + * the old CPU got offlined, zswap_cpu_comp_dead() could have + * already freed ctx->req (among other things) and set it to + * NULL. Just try again on the new CPU that we ended up on. + */ + mutex_unlock(&acomp_ctx->mutex); + } +} + +static void acomp_ctx_put_unlock(struct crypto_acomp_ctx *acomp_ctx) +{ + mutex_unlock(&acomp_ctx->mutex); +} + static bool zswap_compress(struct page *page, struct zswap_entry *entry, struct zswap_pool *pool) { @@ -893,10 +928,7 @@ static bool zswap_compress(struct page *page, struct zswap_entry *entry, gfp_t gfp; u8 *dst; - acomp_ctx = raw_cpu_ptr(pool->acomp_ctx); - - mutex_lock(&acomp_ctx->mutex); - + acomp_ctx = acomp_ctx_get_cpu_lock(pool); dst = acomp_ctx->buffer; sg_init_table(&input, 1); sg_set_page(&input, page, PAGE_SIZE, 0); @@ -949,7 +981,7 @@ unlock: else if (alloc_ret) zswap_reject_alloc_fail++; - mutex_unlock(&acomp_ctx->mutex); + acomp_ctx_put_unlock(acomp_ctx); return comp_ret == 0 && alloc_ret == 0; } @@ -960,9 +992,7 @@ static void zswap_decompress(struct zswap_entry *entry, struct folio *folio) struct crypto_acomp_ctx *acomp_ctx; u8 *src; - acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); - mutex_lock(&acomp_ctx->mutex); - + acomp_ctx = acomp_ctx_get_cpu_lock(entry->pool); src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO); /* * If zpool_map_handle is atomic, we cannot reliably utilize its mapped buffer @@ -986,10 +1016,10 @@ static void zswap_decompress(struct zswap_entry *entry, struct folio *folio) acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, PAGE_SIZE); BUG_ON(crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait)); BUG_ON(acomp_ctx->req->dlen != PAGE_SIZE); - mutex_unlock(&acomp_ctx->mutex); if (src != acomp_ctx->buffer) zpool_unmap_handle(zpool, entry->handle); + acomp_ctx_put_unlock(acomp_ctx); } /********************************* diff --git a/net/802/psnap.c b/net/802/psnap.c index fca9d454905f..389df460c8c4 100644 --- a/net/802/psnap.c +++ b/net/802/psnap.c @@ -55,11 +55,11 @@ static int snap_rcv(struct sk_buff *skb, struct net_device *dev, goto drop; rcu_read_lock(); - proto = find_snap_client(skb_transport_header(skb)); + proto = find_snap_client(skb->data); if (proto) { /* Pass the frame on. */ - skb->transport_header += 5; skb_pull_rcsum(skb, 5); + skb_reset_transport_header(skb); rc = proto->rcvfunc(skb, dev, &snap_packet_type, orig_dev); } rcu_read_unlock(); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index c86f4e42e69c..7b2b04d6b856 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -1031,9 +1031,9 @@ static bool adv_use_rpa(struct hci_dev *hdev, uint32_t flags) static int hci_set_random_addr_sync(struct hci_dev *hdev, bdaddr_t *rpa) { - /* If we're advertising or initiating an LE connection we can't - * go ahead and change the random address at this time. This is - * because the eventual initiator address used for the + /* If a random_addr has been set we're advertising or initiating an LE + * connection we can't go ahead and change the random address at this + * time. This is because the eventual initiator address used for the * subsequently created connection will be undefined (some * controllers use the new address and others the one we had * when the operation started). @@ -1041,8 +1041,9 @@ static int hci_set_random_addr_sync(struct hci_dev *hdev, bdaddr_t *rpa) * In this kind of scenario skip the update and let the random * address be updated at the next cycle. */ - if (hci_dev_test_flag(hdev, HCI_LE_ADV) || - hci_lookup_le_connect(hdev)) { + if (bacmp(&hdev->random_addr, BDADDR_ANY) && + (hci_dev_test_flag(hdev, HCI_LE_ADV) || + hci_lookup_le_connect(hdev))) { bt_dev_dbg(hdev, "Deferring random address update"); hci_dev_set_flag(hdev, HCI_RPA_EXPIRED); return 0; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index b31192d473d0..de47ad999d7b 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -7655,6 +7655,24 @@ static void device_added(struct sock *sk, struct hci_dev *hdev, mgmt_event(MGMT_EV_DEVICE_ADDED, hdev, &ev, sizeof(ev), sk); } +static void add_device_complete(struct hci_dev *hdev, void *data, int err) +{ + struct mgmt_pending_cmd *cmd = data; + struct mgmt_cp_add_device *cp = cmd->param; + + if (!err) { + device_added(cmd->sk, hdev, &cp->addr.bdaddr, cp->addr.type, + cp->action); + device_flags_changed(NULL, hdev, &cp->addr.bdaddr, + cp->addr.type, hdev->conn_flags, + PTR_UINT(cmd->user_data)); + } + + mgmt_cmd_complete(cmd->sk, hdev->id, MGMT_OP_ADD_DEVICE, + mgmt_status(err), &cp->addr, sizeof(cp->addr)); + mgmt_pending_free(cmd); +} + static int add_device_sync(struct hci_dev *hdev, void *data) { return hci_update_passive_scan_sync(hdev); @@ -7663,6 +7681,7 @@ static int add_device_sync(struct hci_dev *hdev, void *data) static int add_device(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { + struct mgmt_pending_cmd *cmd; struct mgmt_cp_add_device *cp = data; u8 auto_conn, addr_type; struct hci_conn_params *params; @@ -7743,9 +7762,24 @@ static int add_device(struct sock *sk, struct hci_dev *hdev, current_flags = params->flags; } - err = hci_cmd_sync_queue(hdev, add_device_sync, NULL, NULL); - if (err < 0) + cmd = mgmt_pending_new(sk, MGMT_OP_ADD_DEVICE, hdev, data, len); + if (!cmd) { + err = -ENOMEM; goto unlock; + } + + cmd->user_data = UINT_PTR(current_flags); + + err = hci_cmd_sync_queue(hdev, add_device_sync, cmd, + add_device_complete); + if (err < 0) { + err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_ADD_DEVICE, + MGMT_STATUS_FAILED, &cp->addr, + sizeof(cp->addr)); + mgmt_pending_free(cmd); + } + + goto unlock; added: device_added(sk, hdev, &cp->addr.bdaddr, cp->addr.type, cp->action); diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index af80d599c337..21a5b5535ebc 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -201,14 +201,14 @@ static ssize_t address_show(struct device *tty_dev, struct device_attribute *attr, char *buf) { struct rfcomm_dev *dev = dev_get_drvdata(tty_dev); - return sprintf(buf, "%pMR\n", &dev->dst); + return sysfs_emit(buf, "%pMR\n", &dev->dst); } static ssize_t channel_show(struct device *tty_dev, struct device_attribute *attr, char *buf) { struct rfcomm_dev *dev = dev_get_drvdata(tty_dev); - return sprintf(buf, "%d\n", dev->channel); + return sysfs_emit(buf, "%d\n", dev->channel); } static DEVICE_ATTR_RO(address); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 9b1168eb77ab..b24afec24138 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1173,6 +1173,8 @@ EXPORT_SYMBOL(ceph_osdc_new_request); int __ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt) { + WARN_ON(op->op != CEPH_OSD_OP_SPARSE_READ); + op->extent.sparse_ext_cnt = cnt; op->extent.sparse_ext = kmalloc_array(cnt, sizeof(*op->extent.sparse_ext), diff --git a/net/core/dev.c b/net/core/dev.c index 45a8c3dd4a64..a9f62f5aeb84 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -753,6 +753,36 @@ int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr, } EXPORT_SYMBOL_GPL(dev_fill_forward_path); +/* must be called under rcu_read_lock(), as we dont take a reference */ +static struct napi_struct *napi_by_id(unsigned int napi_id) +{ + unsigned int hash = napi_id % HASH_SIZE(napi_hash); + struct napi_struct *napi; + + hlist_for_each_entry_rcu(napi, &napi_hash[hash], napi_hash_node) + if (napi->napi_id == napi_id) + return napi; + + return NULL; +} + +/* must be called under rcu_read_lock(), as we dont take a reference */ +struct napi_struct *netdev_napi_by_id(struct net *net, unsigned int napi_id) +{ + struct napi_struct *napi; + + napi = napi_by_id(napi_id); + if (!napi) + return NULL; + + if (WARN_ON_ONCE(!napi->dev)) + return NULL; + if (!net_eq(net, dev_net(napi->dev))) + return NULL; + + return napi; +} + /** * __dev_get_by_name - find a device by its name * @net: the applicable net namespace @@ -3642,8 +3672,10 @@ int skb_csum_hwoffload_help(struct sk_buff *skb, if (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) { if (vlan_get_protocol(skb) == htons(ETH_P_IPV6) && - skb_network_header_len(skb) != sizeof(struct ipv6hdr)) + skb_network_header_len(skb) != sizeof(struct ipv6hdr) && + !ipv6_has_hopopt_jumbo(skb)) goto sw_checksum; + switch (skb->csum_offset) { case offsetof(struct tcphdr, check): case offsetof(struct udphdr, check): @@ -6291,19 +6323,6 @@ bool napi_complete_done(struct napi_struct *n, int work_done) } EXPORT_SYMBOL(napi_complete_done); -/* must be called under rcu_read_lock(), as we dont take a reference */ -struct napi_struct *napi_by_id(unsigned int napi_id) -{ - unsigned int hash = napi_id % HASH_SIZE(napi_hash); - struct napi_struct *napi; - - hlist_for_each_entry_rcu(napi, &napi_hash[hash], napi_hash_node) - if (napi->napi_id == napi_id) - return napi; - - return NULL; -} - static void skb_defer_free_flush(struct softnet_data *sd) { struct sk_buff *skb, *next; diff --git a/net/core/dev.h b/net/core/dev.h index d043dee25a68..deb5eae5749f 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -22,6 +22,8 @@ struct sd_flow_limit { extern int netdev_flow_limit_table_len; +struct napi_struct *netdev_napi_by_id(struct net *net, unsigned int napi_id); + #ifdef CONFIG_PROC_FS int __init dev_proc_init(void); #else @@ -269,7 +271,6 @@ void xdp_do_check_flushed(struct napi_struct *napi); static inline void xdp_do_check_flushed(struct napi_struct *napi) { } #endif -struct napi_struct *napi_by_id(unsigned int napi_id); void kick_defer_list_purge(struct softnet_data *sd, unsigned int cpu); #define XMIT_RECURSION_LIMIT 8 diff --git a/net/core/filter.c b/net/core/filter.c index 21131ec25f24..834614071727 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3734,13 +3734,22 @@ static const struct bpf_func_proto bpf_skb_adjust_room_proto = { static u32 __bpf_skb_min_len(const struct sk_buff *skb) { - u32 min_len = skb_network_offset(skb); + int offset = skb_network_offset(skb); + u32 min_len = 0; - if (skb_transport_header_was_set(skb)) - min_len = skb_transport_offset(skb); - if (skb->ip_summed == CHECKSUM_PARTIAL) - min_len = skb_checksum_start_offset(skb) + - skb->csum_offset + sizeof(__sum16); + if (offset > 0) + min_len = offset; + if (skb_transport_header_was_set(skb)) { + offset = skb_transport_offset(skb); + if (offset > 0) + min_len = offset; + } + if (skb->ip_summed == CHECKSUM_PARTIAL) { + offset = skb_checksum_start_offset(skb) + + skb->csum_offset + sizeof(__sum16); + if (offset > 0) + min_len = offset; + } return min_len; } diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 1b4d39e38084..cb04ef2b9807 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -42,14 +42,18 @@ static unsigned int default_operstate(const struct net_device *dev) * first check whether lower is indeed the source of its down state. */ if (!netif_carrier_ok(dev)) { - int iflink = dev_get_iflink(dev); struct net_device *peer; + int iflink; /* If called from netdev_run_todo()/linkwatch_sync_dev(), * dev_net(dev) can be already freed, and RTNL is not held. */ - if (dev->reg_state == NETREG_UNREGISTERED || - iflink == dev->ifindex) + if (dev->reg_state <= NETREG_REGISTERED) + iflink = dev_get_iflink(dev); + else + iflink = dev->ifindex; + + if (iflink == dev->ifindex) return IF_OPER_DOWN; ASSERT_RTNL(); diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 9527dd46e4dc..a3bdaf075b6b 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -167,8 +167,6 @@ netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi, void *hdr; pid_t pid; - if (WARN_ON_ONCE(!napi->dev)) - return -EINVAL; if (!(napi->dev->flags & IFF_UP)) return 0; @@ -176,8 +174,7 @@ netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi, if (!hdr) return -EMSGSIZE; - if (napi->napi_id >= MIN_NAPI_ID && - nla_put_u32(rsp, NETDEV_A_NAPI_ID, napi->napi_id)) + if (nla_put_u32(rsp, NETDEV_A_NAPI_ID, napi->napi_id)) goto nla_put_failure; if (nla_put_u32(rsp, NETDEV_A_NAPI_IFINDEX, napi->dev->ifindex)) @@ -235,7 +232,7 @@ int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); rcu_read_lock(); - napi = napi_by_id(napi_id); + napi = netdev_napi_by_id(genl_info_net(info), napi_id); if (napi) { err = netdev_nl_napi_fill_one(rsp, napi, info); } else { @@ -246,8 +243,12 @@ int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info) rcu_read_unlock(); rtnl_unlock(); - if (err) + if (err) { goto err_free_msg; + } else if (!rsp->len) { + err = -ENOENT; + goto err_free_msg; + } return genlmsg_reply(rsp, info); @@ -268,6 +269,8 @@ netdev_nl_napi_dump_one(struct net_device *netdev, struct sk_buff *rsp, return err; list_for_each_entry(napi, &netdev->napi_list, dev_list) { + if (napi->napi_id < MIN_NAPI_ID) + continue; if (ctx->napi_id && napi->napi_id >= ctx->napi_id) continue; @@ -350,7 +353,7 @@ int netdev_nl_napi_set_doit(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); rcu_read_lock(); - napi = napi_by_id(napi_id); + napi = netdev_napi_by_id(genl_info_net(info), napi_id); if (napi) { err = netdev_nl_napi_set_config(napi, info); } else { @@ -430,10 +433,10 @@ static int netdev_nl_queue_fill(struct sk_buff *rsp, struct net_device *netdev, u32 q_idx, u32 q_type, const struct genl_info *info) { - int err = 0; + int err; if (!(netdev->flags & IFF_UP)) - return err; + return -ENOENT; err = netdev_nl_queue_validate(netdev, q_idx, q_type); if (err) @@ -488,24 +491,21 @@ netdev_nl_queue_dump_one(struct net_device *netdev, struct sk_buff *rsp, struct netdev_nl_dump_ctx *ctx) { int err = 0; - int i; if (!(netdev->flags & IFF_UP)) return err; - for (i = ctx->rxq_idx; i < netdev->real_num_rx_queues;) { - err = netdev_nl_queue_fill_one(rsp, netdev, i, + for (; ctx->rxq_idx < netdev->real_num_rx_queues; ctx->rxq_idx++) { + err = netdev_nl_queue_fill_one(rsp, netdev, ctx->rxq_idx, NETDEV_QUEUE_TYPE_RX, info); if (err) return err; - ctx->rxq_idx = i++; } - for (i = ctx->txq_idx; i < netdev->real_num_tx_queues;) { - err = netdev_nl_queue_fill_one(rsp, netdev, i, + for (; ctx->txq_idx < netdev->real_num_tx_queues; ctx->txq_idx++) { + err = netdev_nl_queue_fill_one(rsp, netdev, ctx->txq_idx, NETDEV_QUEUE_TYPE_TX, info); if (err) return err; - ctx->txq_idx = i++; } return err; @@ -671,7 +671,7 @@ netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp, i, info); if (err) return err; - ctx->rxq_idx = i++; + ctx->rxq_idx = ++i; } i = ctx->txq_idx; while (ops->get_queue_stats_tx && i < netdev->real_num_tx_queues) { @@ -679,7 +679,7 @@ netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp, i, info); if (err) return err; - ctx->txq_idx = i++; + ctx->txq_idx = ++i; } ctx->rxq_idx = 0; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index ebcfc2debf1a..d9f959c619d9 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3819,6 +3819,7 @@ out_unregister: } static struct net *rtnl_get_peer_net(const struct rtnl_link_ops *ops, + struct nlattr *tbp[], struct nlattr *data[], struct netlink_ext_ack *extack) { @@ -3826,7 +3827,7 @@ static struct net *rtnl_get_peer_net(const struct rtnl_link_ops *ops, int err; if (!data || !data[ops->peer_type]) - return NULL; + return rtnl_link_get_net_ifla(tbp); err = rtnl_nla_parse_ifinfomsg(tb, data[ops->peer_type], extack); if (err < 0) @@ -3971,7 +3972,7 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, } if (ops->peer_type) { - peer_net = rtnl_get_peer_net(ops, data, extack); + peer_net = rtnl_get_peer_net(ops, tb, data, extack); if (IS_ERR(peer_net)) { ret = PTR_ERR(peer_net); goto put_ops; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index e90fbab703b2..61f3f3d4e528 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -369,8 +369,8 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes) { int ret = -ENOSPC, i = msg->sg.curr; + u32 copy, buf_size, copied = 0; struct scatterlist *sge; - u32 copy, buf_size; void *to; do { @@ -397,6 +397,7 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, goto out; } bytes -= copy; + copied += copy; if (!bytes) break; msg->sg.copybreak = 0; @@ -404,7 +405,7 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, } while (i != msg->sg.end); out: msg->sg.curr = i; - return ret; + return (ret < 0) ? ret : copied; } EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter); @@ -445,8 +446,10 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, if (likely(!peek)) { sge->offset += copy; sge->length -= copy; - if (!msg_rx->skb) + if (!msg_rx->skb) { sk_mem_uncharge(sk, copy); + atomic_sub(copy, &sk->sk_rmem_alloc); + } msg_rx->sg.size -= copy; if (!sge->length) { @@ -772,6 +775,8 @@ static void __sk_psock_purge_ingress_msg(struct sk_psock *psock) list_for_each_entry_safe(msg, tmp, &psock->ingress_msg, list) { list_del(&msg->list); + if (!msg->skb) + atomic_sub(msg->sg.size, &psock->sk->sk_rmem_alloc); sk_msg_free(psock->sk, msg); kfree(msg); } diff --git a/net/core/sock.c b/net/core/sock.c index 74729d20cd00..be84885f9290 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1295,7 +1295,10 @@ int sk_setsockopt(struct sock *sk, int level, int optname, sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE); break; case SO_REUSEPORT: - sk->sk_reuseport = valbool; + if (valbool && !sk_is_inet(sk)) + ret = -EOPNOTSUPP; + else + sk->sk_reuseport = valbool; break; case SO_DONTROUTE: sock_valbool_flag(sk, SOCK_LOCALROUTE, valbool); diff --git a/net/dsa/tag.h b/net/dsa/tag.h index d5707870906b..5d80ddad4ff6 100644 --- a/net/dsa/tag.h +++ b/net/dsa/tag.h @@ -138,9 +138,10 @@ static inline void dsa_software_untag_vlan_unaware_bridge(struct sk_buff *skb, * dsa_software_vlan_untag: Software VLAN untagging in DSA receive path * @skb: Pointer to socket buffer (packet) * - * Receive path method for switches which cannot avoid tagging all packets - * towards the CPU port. Called when ds->untag_bridge_pvid (legacy) or - * ds->untag_vlan_aware_bridge_pvid is set to true. + * Receive path method for switches which send some packets as VLAN-tagged + * towards the CPU port (generally from VLAN-aware bridge ports) even when the + * packet was not tagged on the wire. Called when ds->untag_bridge_pvid + * (legacy) or ds->untag_vlan_aware_bridge_pvid is set to true. * * As a side effect of this method, any VLAN tag from the skb head is moved * to hwaccel. @@ -149,14 +150,19 @@ static inline struct sk_buff *dsa_software_vlan_untag(struct sk_buff *skb) { struct dsa_port *dp = dsa_user_to_port(skb->dev); struct net_device *br = dsa_port_bridge_dev_get(dp); - u16 vid; + u16 vid, proto; + int err; /* software untagging for standalone ports not yet necessary */ if (!br) return skb; + err = br_vlan_get_proto(br, &proto); + if (err) + return skb; + /* Move VLAN tag from data to hwaccel */ - if (!skb_vlan_tag_present(skb)) { + if (!skb_vlan_tag_present(skb) && skb->protocol == htons(proto)) { skb = skb_vlan_untag(skb); if (!skb) return NULL; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 25505f9b724c..09b73acf037a 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -294,7 +294,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev) ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr, iph->saddr, tunnel->parms.o_key, - iph->tos & INET_DSCP_MASK, dev_net(dev), + iph->tos & INET_DSCP_MASK, tunnel->net, tunnel->parms.link, tunnel->fwmark, 0, 0); rt = ip_route_output_key(tunnel->net, &fl4); @@ -611,7 +611,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), - tos & INET_DSCP_MASK, dev_net(dev), 0, skb->mark, + tos & INET_DSCP_MASK, tunnel->net, 0, skb->mark, skb_get_hash(skb), key->flow_flags); if (!tunnel_hlen) @@ -774,7 +774,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, tunnel->parms.o_key, tos & INET_DSCP_MASK, - dev_net(dev), READ_ONCE(tunnel->parms.link), + tunnel->net, READ_ONCE(tunnel->parms.link), tunnel->fwmark, skb_get_hash(skb), 0); if (ip_tunnel_encap(skb, &tunnel->encap, &protocol, &fl4) < 0) diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 99cef92e6290..47f65b1b70ca 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -49,13 +49,14 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, sge = sk_msg_elem(msg, i); size = (apply && apply_bytes < sge->length) ? apply_bytes : sge->length; - if (!sk_wmem_schedule(sk, size)) { + if (!__sk_rmem_schedule(sk, size, false)) { if (!copied) ret = -ENOMEM; break; } sk_mem_charge(sk, size); + atomic_add(size, &sk->sk_rmem_alloc); sk_msg_xfer(tmp, msg, i, size); copied += size; if (sge->length) @@ -74,7 +75,8 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, if (!ret) { msg->sg.start = i; - sk_psock_queue_msg(psock, tmp); + if (!sk_psock_queue_msg(psock, tmp)) + atomic_sub(copied, &sk->sk_rmem_alloc); sk_psock_data_ready(sk, psock); } else { sk_msg_free(sk, tmp); @@ -493,7 +495,7 @@ more_data: static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { struct sk_msg tmp, *msg_tx = NULL; - int copied = 0, err = 0; + int copied = 0, err = 0, ret = 0; struct sk_psock *psock; long timeo; int flags; @@ -536,14 +538,14 @@ static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) copy = msg_tx->sg.size - osize; } - err = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, msg_tx, + ret = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, msg_tx, copy); - if (err < 0) { + if (ret < 0) { sk_msg_trim(sk, msg_tx, osize); goto out_err; } - copied += copy; + copied += ret; if (psock->cork_bytes) { if (size > psock->cork_bytes) psock->cork_bytes = 0; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 5bdf13ac26ef..4811727b8a02 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -7328,6 +7328,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req, req->timeout))) { reqsk_free(req); + dst_release(dst); return 0; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a38c8b1f44db..c26f6c4b7bb4 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -896,7 +896,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, sock_net_set(ctl_sk, net); if (sk) { ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? - inet_twsk(sk)->tw_mark : sk->sk_mark; + inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark); ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_priority : READ_ONCE(sk->sk_priority); transmit_time = tcp_transmit_time(sk); diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index 7646e401c630..1d41b2ab4884 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -195,6 +195,8 @@ static const struct nf_hook_ops ila_nf_hook_ops[] = { }, }; +static DEFINE_MUTEX(ila_mutex); + static int ila_add_mapping(struct net *net, struct ila_xlat_params *xp) { struct ila_net *ilan = net_generic(net, ila_net_id); @@ -202,16 +204,20 @@ static int ila_add_mapping(struct net *net, struct ila_xlat_params *xp) spinlock_t *lock = ila_get_lock(ilan, xp->ip.locator_match); int err = 0, order; - if (!ilan->xlat.hooks_registered) { + if (!READ_ONCE(ilan->xlat.hooks_registered)) { /* We defer registering net hooks in the namespace until the * first mapping is added. */ - err = nf_register_net_hooks(net, ila_nf_hook_ops, - ARRAY_SIZE(ila_nf_hook_ops)); + mutex_lock(&ila_mutex); + if (!ilan->xlat.hooks_registered) { + err = nf_register_net_hooks(net, ila_nf_hook_ops, + ARRAY_SIZE(ila_nf_hook_ops)); + if (!err) + WRITE_ONCE(ilan->xlat.hooks_registered, true); + } + mutex_unlock(&ila_mutex); if (err) return err; - - ilan->xlat.hooks_registered = true; } ila = kzalloc(sizeof(*ila), GFP_KERNEL); diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c index 51bccfb00a9c..61b0159b2fbe 100644 --- a/net/llc/llc_input.c +++ b/net/llc/llc_input.c @@ -124,8 +124,8 @@ static inline int llc_fixup_skb(struct sk_buff *skb) if (unlikely(!pskb_may_pull(skb, llc_len))) return 0; - skb->transport_header += llc_len; skb_pull(skb, llc_len); + skb_reset_transport_header(skb); if (skb->protocol == htons(ETH_P_802_2)) { __be16 pdulen; s32 data_size; diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c index c0e2da5072be..9e4631fade90 100644 --- a/net/mac802154/iface.c +++ b/net/mac802154/iface.c @@ -684,6 +684,10 @@ void ieee802154_if_remove(struct ieee802154_sub_if_data *sdata) ASSERT_RTNL(); mutex_lock(&sdata->local->iflist_mtx); + if (list_empty(&sdata->local->interfaces)) { + mutex_unlock(&sdata->local->iflist_mtx); + return; + } list_del_rcu(&sdata->list); mutex_unlock(&sdata->local->iflist_mtx); diff --git a/net/mctp/route.c b/net/mctp/route.c index 597e9cf5aa64..3f2bd65ff5e3 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -374,8 +374,13 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) msk = NULL; rc = -EINVAL; - /* we may be receiving a locally-routed packet; drop source sk - * accounting + /* We may be receiving a locally-routed packet; drop source sk + * accounting. + * + * From here, we will either queue the skb - either to a frag_queue, or + * to a receiving socket. When that succeeds, we clear the skb pointer; + * a non-NULL skb on exit will be otherwise unowned, and hence + * kfree_skb()-ed. */ skb_orphan(skb); @@ -434,7 +439,9 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) * pending key. */ if (flags & MCTP_HDR_FLAG_EOM) { - sock_queue_rcv_skb(&msk->sk, skb); + rc = sock_queue_rcv_skb(&msk->sk, skb); + if (!rc) + skb = NULL; if (key) { /* we've hit a pending reassembly; not much we * can do but drop it @@ -443,7 +450,6 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) MCTP_TRACE_KEY_REPLIED); key = NULL; } - rc = 0; goto out_unlock; } @@ -470,8 +476,10 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) * this function. */ rc = mctp_key_add(key, msk); - if (!rc) + if (!rc) { trace_mctp_key_acquire(key); + skb = NULL; + } /* we don't need to release key->lock on exit, so * clean up here and suppress the unlock via @@ -489,6 +497,8 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) key = NULL; } else { rc = mctp_frag_queue(key, skb); + if (!rc) + skb = NULL; } } @@ -503,12 +513,19 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) else rc = mctp_frag_queue(key, skb); + if (rc) + goto out_unlock; + + /* we've queued; the queue owns the skb now */ + skb = NULL; + /* end of message? deliver to socket, and we're done with * the reassembly/response key */ - if (!rc && flags & MCTP_HDR_FLAG_EOM) { - sock_queue_rcv_skb(key->sk, key->reasm_head); - key->reasm_head = NULL; + if (flags & MCTP_HDR_FLAG_EOM) { + rc = sock_queue_rcv_skb(key->sk, key->reasm_head); + if (!rc) + key->reasm_head = NULL; __mctp_key_done_in(key, net, f, MCTP_TRACE_KEY_REPLIED); key = NULL; } @@ -527,8 +544,7 @@ out_unlock: if (any_key) mctp_key_unref(any_key); out: - if (rc) - kfree_skb(skb); + kfree_skb(skb); return rc; } diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c index 8551dab1d1e6..17165b86ce22 100644 --- a/net/mctp/test/route-test.c +++ b/net/mctp/test/route-test.c @@ -837,6 +837,90 @@ static void mctp_test_route_input_multiple_nets_key(struct kunit *test) mctp_test_route_input_multiple_nets_key_fini(test, &t2); } +/* Input route to socket, using a single-packet message, where sock delivery + * fails. Ensure we're handling the failure appropriately. + */ +static void mctp_test_route_input_sk_fail_single(struct kunit *test) +{ + const struct mctp_hdr hdr = RX_HDR(1, 10, 8, FL_S | FL_E | FL_TO); + struct mctp_test_route *rt; + struct mctp_test_dev *dev; + struct socket *sock; + struct sk_buff *skb; + int rc; + + __mctp_route_test_init(test, &dev, &rt, &sock, MCTP_NET_ANY); + + /* No rcvbuf space, so delivery should fail. __sock_set_rcvbuf will + * clamp the minimum to SOCK_MIN_RCVBUF, so we open-code this. + */ + lock_sock(sock->sk); + WRITE_ONCE(sock->sk->sk_rcvbuf, 0); + release_sock(sock->sk); + + skb = mctp_test_create_skb(&hdr, 10); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb); + skb_get(skb); + + mctp_test_skb_set_dev(skb, dev); + + /* do route input, which should fail */ + rc = mctp_route_input(&rt->rt, skb); + KUNIT_EXPECT_NE(test, rc, 0); + + /* we should hold the only reference to skb */ + KUNIT_EXPECT_EQ(test, refcount_read(&skb->users), 1); + kfree_skb(skb); + + __mctp_route_test_fini(test, dev, rt, sock); +} + +/* Input route to socket, using a fragmented message, where sock delivery fails. + */ +static void mctp_test_route_input_sk_fail_frag(struct kunit *test) +{ + const struct mctp_hdr hdrs[2] = { RX_FRAG(FL_S, 0), RX_FRAG(FL_E, 1) }; + struct mctp_test_route *rt; + struct mctp_test_dev *dev; + struct sk_buff *skbs[2]; + struct socket *sock; + unsigned int i; + int rc; + + __mctp_route_test_init(test, &dev, &rt, &sock, MCTP_NET_ANY); + + lock_sock(sock->sk); + WRITE_ONCE(sock->sk->sk_rcvbuf, 0); + release_sock(sock->sk); + + for (i = 0; i < ARRAY_SIZE(skbs); i++) { + skbs[i] = mctp_test_create_skb(&hdrs[i], 10); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skbs[i]); + skb_get(skbs[i]); + + mctp_test_skb_set_dev(skbs[i], dev); + } + + /* first route input should succeed, we're only queueing to the + * frag list + */ + rc = mctp_route_input(&rt->rt, skbs[0]); + KUNIT_EXPECT_EQ(test, rc, 0); + + /* final route input should fail to deliver to the socket */ + rc = mctp_route_input(&rt->rt, skbs[1]); + KUNIT_EXPECT_NE(test, rc, 0); + + /* we should hold the only reference to both skbs */ + KUNIT_EXPECT_EQ(test, refcount_read(&skbs[0]->users), 1); + kfree_skb(skbs[0]); + + KUNIT_EXPECT_EQ(test, refcount_read(&skbs[1]->users), 1); + kfree_skb(skbs[1]); + + __mctp_route_test_fini(test, dev, rt, sock); +} + #if IS_ENABLED(CONFIG_MCTP_FLOWS) static void mctp_test_flow_init(struct kunit *test, @@ -1053,6 +1137,8 @@ static struct kunit_case mctp_test_cases[] = { mctp_route_input_sk_reasm_gen_params), KUNIT_CASE_PARAM(mctp_test_route_input_sk_keys, mctp_route_input_sk_keys_gen_params), + KUNIT_CASE(mctp_test_route_input_sk_fail_single), + KUNIT_CASE(mctp_test_route_input_sk_fail_frag), KUNIT_CASE(mctp_test_route_input_multiple_nets_bind), KUNIT_CASE(mctp_test_route_input_multiple_nets_key), KUNIT_CASE(mctp_test_packet_flow), diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index 38d8121331d4..b0dd008e2114 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -102,16 +102,15 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) } #ifdef CONFIG_SYSCTL -static int mptcp_set_scheduler(const struct net *net, const char *name) +static int mptcp_set_scheduler(char *scheduler, const char *name) { - struct mptcp_pernet *pernet = mptcp_get_pernet(net); struct mptcp_sched_ops *sched; int ret = 0; rcu_read_lock(); sched = mptcp_sched_find(name); if (sched) - strscpy(pernet->scheduler, name, MPTCP_SCHED_NAME_MAX); + strscpy(scheduler, name, MPTCP_SCHED_NAME_MAX); else ret = -ENOENT; rcu_read_unlock(); @@ -122,7 +121,7 @@ static int mptcp_set_scheduler(const struct net *net, const char *name) static int proc_scheduler(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - const struct net *net = current->nsproxy->net_ns; + char (*scheduler)[MPTCP_SCHED_NAME_MAX] = ctl->data; char val[MPTCP_SCHED_NAME_MAX]; struct ctl_table tbl = { .data = val, @@ -130,11 +129,11 @@ static int proc_scheduler(const struct ctl_table *ctl, int write, }; int ret; - strscpy(val, mptcp_get_scheduler(net), MPTCP_SCHED_NAME_MAX); + strscpy(val, *scheduler, MPTCP_SCHED_NAME_MAX); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) - ret = mptcp_set_scheduler(net, val); + ret = mptcp_set_scheduler(*scheduler, val); return ret; } @@ -161,7 +160,9 @@ static int proc_blackhole_detect_timeout(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct mptcp_pernet *pernet = mptcp_get_pernet(current->nsproxy->net_ns); + struct mptcp_pernet *pernet = container_of(table->data, + struct mptcp_pernet, + blackhole_timeout); int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); @@ -228,7 +229,7 @@ static struct ctl_table mptcp_sysctl_table[] = { { .procname = "available_schedulers", .maxlen = MPTCP_SCHED_BUF_MAX, - .mode = 0644, + .mode = 0444, .proc_handler = proc_available_schedulers, }, { diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 1603b3702e22..a62bc874bf1e 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -667,8 +667,15 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * &echo, &drop_other_suboptions)) return false; + /* + * Later on, mptcp_write_options() will enforce mutually exclusion with + * DSS, bail out if such option is set and we can't drop it. + */ if (drop_other_suboptions) remaining += opt_size; + else if (opts->suboptions & OPTION_MPTCP_DSS) + return false; + len = mptcp_add_addr_len(opts->addr.family, echo, !!opts->addr.port); if (remaining < len) return false; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 08a72242428c..1b2e7cbb577f 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -136,6 +136,7 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, int delta; if (MPTCP_SKB_CB(from)->offset || + ((to->len + from->len) > (sk->sk_rcvbuf >> 3)) || !skb_try_coalesce(to, from, &fragstolen, &delta)) return false; @@ -528,13 +529,13 @@ static void mptcp_send_ack(struct mptcp_sock *msk) mptcp_subflow_send_ack(mptcp_subflow_tcp_sock(subflow)); } -static void mptcp_subflow_cleanup_rbuf(struct sock *ssk) +static void mptcp_subflow_cleanup_rbuf(struct sock *ssk, int copied) { bool slow; slow = lock_sock_fast(ssk); if (tcp_can_send_ack(ssk)) - tcp_cleanup_rbuf(ssk, 1); + tcp_cleanup_rbuf(ssk, copied); unlock_sock_fast(ssk, slow); } @@ -551,7 +552,7 @@ static bool mptcp_subflow_could_cleanup(const struct sock *ssk, bool rx_empty) (ICSK_ACK_PUSHED2 | ICSK_ACK_PUSHED))); } -static void mptcp_cleanup_rbuf(struct mptcp_sock *msk) +static void mptcp_cleanup_rbuf(struct mptcp_sock *msk, int copied) { int old_space = READ_ONCE(msk->old_wspace); struct mptcp_subflow_context *subflow; @@ -559,14 +560,14 @@ static void mptcp_cleanup_rbuf(struct mptcp_sock *msk) int space = __mptcp_space(sk); bool cleanup, rx_empty; - cleanup = (space > 0) && (space >= (old_space << 1)); - rx_empty = !__mptcp_rmem(sk); + cleanup = (space > 0) && (space >= (old_space << 1)) && copied; + rx_empty = !__mptcp_rmem(sk) && copied; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (cleanup || mptcp_subflow_could_cleanup(ssk, rx_empty)) - mptcp_subflow_cleanup_rbuf(ssk); + mptcp_subflow_cleanup_rbuf(ssk, copied); } } @@ -1939,6 +1940,8 @@ do_error: goto out; } +static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied); + static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, struct msghdr *msg, size_t len, int flags, @@ -1992,6 +1995,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, break; } + mptcp_rcv_space_adjust(msk, copied); return copied; } @@ -2217,9 +2221,6 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, copied += bytes_read; - /* be sure to advertise window change */ - mptcp_cleanup_rbuf(msk); - if (skb_queue_empty(&msk->receive_queue) && __mptcp_move_skbs(msk)) continue; @@ -2268,7 +2269,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, } pr_debug("block timeout %ld\n", timeo); - mptcp_rcv_space_adjust(msk, copied); + mptcp_cleanup_rbuf(msk, copied); err = sk_wait_data(sk, &timeo, NULL); if (err < 0) { err = copied ? : err; @@ -2276,7 +2277,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, } } - mptcp_rcv_space_adjust(msk, copied); + mptcp_cleanup_rbuf(msk, copied); out_err: if (cmsg_flags && copied >= 0) { diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index bfae7066936b..db794fe1300e 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -611,6 +611,8 @@ init_list_set(struct net *net, struct ip_set *set, u32 size) return true; } +static struct lock_class_key list_set_lockdep_key; + static int list_set_create(struct net *net, struct ip_set *set, struct nlattr *tb[], u32 flags) @@ -627,6 +629,7 @@ list_set_create(struct net *net, struct ip_set *set, struct nlattr *tb[], if (size < IP_SET_LIST_MIN_SIZE) size = IP_SET_LIST_MIN_SIZE; + lockdep_set_class(&set->lock, &list_set_lockdep_key); set->variant = &set_variant; set->dsize = ip_set_elem_len(set, tb, sizeof(struct set_elem), __alignof__(struct set_elem)); diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 98d7dbe3d787..c0289f83f96d 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1495,8 +1495,8 @@ int __init ip_vs_conn_init(void) max_avail -= 2; /* ~4 in hash row */ max_avail -= 1; /* IPVS up to 1/2 of mem */ max_avail -= order_base_2(sizeof(struct ip_vs_conn)); - max = clamp(max, min, max_avail); - ip_vs_conn_tab_bits = clamp_val(ip_vs_conn_tab_bits, min, max); + max = clamp(max_avail, min, max); + ip_vs_conn_tab_bits = clamp(ip_vs_conn_tab_bits, min, max); ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits; ip_vs_conn_tab_mask = ip_vs_conn_tab_size - 1; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 9db3e2b0b1c3..456446d7af20 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2517,12 +2517,15 @@ void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls) struct hlist_nulls_head *hash; unsigned int nr_slots, i; - if (*sizep > (UINT_MAX / sizeof(struct hlist_nulls_head))) + if (*sizep > (INT_MAX / sizeof(struct hlist_nulls_head))) return NULL; BUILD_BUG_ON(sizeof(struct hlist_nulls_head) != sizeof(struct hlist_head)); nr_slots = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_nulls_head)); + if (nr_slots > (INT_MAX / sizeof(struct hlist_nulls_head))) + return NULL; + hash = kvcalloc(nr_slots, sizeof(struct hlist_nulls_head), GFP_KERNEL); if (hash && nulls) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 0b9f1e8dfe49..c4af283356e7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8822,6 +8822,7 @@ static void nft_unregister_flowtable_hook(struct net *net, } static void __nft_unregister_flowtable_net_hooks(struct net *net, + struct nft_flowtable *flowtable, struct list_head *hook_list, bool release_netdev) { @@ -8829,6 +8830,8 @@ static void __nft_unregister_flowtable_net_hooks(struct net *net, list_for_each_entry_safe(hook, next, hook_list, list) { nf_unregister_net_hook(net, &hook->ops); + flowtable->data.type->setup(&flowtable->data, hook->ops.dev, + FLOW_BLOCK_UNBIND); if (release_netdev) { list_del(&hook->list); kfree_rcu(hook, rcu); @@ -8837,9 +8840,10 @@ static void __nft_unregister_flowtable_net_hooks(struct net *net, } static void nft_unregister_flowtable_net_hooks(struct net *net, + struct nft_flowtable *flowtable, struct list_head *hook_list) { - __nft_unregister_flowtable_net_hooks(net, hook_list, false); + __nft_unregister_flowtable_net_hooks(net, flowtable, hook_list, false); } static int nft_register_flowtable_net_hooks(struct net *net, @@ -9481,8 +9485,6 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) flowtable->data.type->free(&flowtable->data); list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { - flowtable->data.type->setup(&flowtable->data, hook->ops.dev, - FLOW_BLOCK_UNBIND); list_del_rcu(&hook->list); kfree_rcu(hook, rcu); } @@ -10870,6 +10872,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) &nft_trans_flowtable_hooks(trans), trans->msg_type); nft_unregister_flowtable_net_hooks(net, + nft_trans_flowtable(trans), &nft_trans_flowtable_hooks(trans)); } else { list_del_rcu(&nft_trans_flowtable(trans)->list); @@ -10878,6 +10881,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) NULL, trans->msg_type); nft_unregister_flowtable_net_hooks(net, + nft_trans_flowtable(trans), &nft_trans_flowtable(trans)->hook_list); } break; @@ -11140,11 +11144,13 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) case NFT_MSG_NEWFLOWTABLE: if (nft_trans_flowtable_update(trans)) { nft_unregister_flowtable_net_hooks(net, + nft_trans_flowtable(trans), &nft_trans_flowtable_hooks(trans)); } else { nft_use_dec_restore(&table->use); list_del_rcu(&nft_trans_flowtable(trans)->list); nft_unregister_flowtable_net_hooks(net, + nft_trans_flowtable(trans), &nft_trans_flowtable(trans)->hook_list); } break; @@ -11737,7 +11743,8 @@ static void __nft_release_hook(struct net *net, struct nft_table *table) list_for_each_entry(chain, &table->chains, list) __nf_tables_unregister_hook(net, table, chain, true); list_for_each_entry(flowtable, &table->flowtables, list) - __nft_unregister_flowtable_net_hooks(net, &flowtable->hook_list, + __nft_unregister_flowtable_net_hooks(net, flowtable, + &flowtable->hook_list, true); } diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index 2b5e246b8d9a..b94cb2ffbaf8 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -754,6 +754,12 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) int ret; struct sk_buff *skbn; + /* + * Reject malformed packets early. Check that it contains at least 2 + * addresses and 1 byte more for Time-To-Live + */ + if (skb->len < 2 * sizeof(ax25_address) + 1) + return 0; nr_src = (ax25_address *)(skb->data + 0); nr_dest = (ax25_address *)(skb->data + 7); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 886c0dd47b66..2d73769d67f4 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -538,10 +538,8 @@ static void *packet_current_frame(struct packet_sock *po, return packet_lookup_frame(po, rb, rb->head, status); } -static u16 vlan_get_tci(struct sk_buff *skb, struct net_device *dev) +static u16 vlan_get_tci(const struct sk_buff *skb, struct net_device *dev) { - u8 *skb_orig_data = skb->data; - int skb_orig_len = skb->len; struct vlan_hdr vhdr, *vh; unsigned int header_len; @@ -562,33 +560,21 @@ static u16 vlan_get_tci(struct sk_buff *skb, struct net_device *dev) else return 0; - skb_push(skb, skb->data - skb_mac_header(skb)); - vh = skb_header_pointer(skb, header_len, sizeof(vhdr), &vhdr); - if (skb_orig_data != skb->data) { - skb->data = skb_orig_data; - skb->len = skb_orig_len; - } + vh = skb_header_pointer(skb, skb_mac_offset(skb) + header_len, + sizeof(vhdr), &vhdr); if (unlikely(!vh)) return 0; return ntohs(vh->h_vlan_TCI); } -static __be16 vlan_get_protocol_dgram(struct sk_buff *skb) +static __be16 vlan_get_protocol_dgram(const struct sk_buff *skb) { __be16 proto = skb->protocol; - if (unlikely(eth_type_vlan(proto))) { - u8 *skb_orig_data = skb->data; - int skb_orig_len = skb->len; - - skb_push(skb, skb->data - skb_mac_header(skb)); - proto = __vlan_get_protocol(skb, proto, NULL); - if (skb_orig_data != skb->data) { - skb->data = skb_orig_data; - skb->len = skb_orig_len; - } - } + if (unlikely(eth_type_vlan(proto))) + proto = __vlan_get_protocol_offset(skb, proto, + skb_mac_offset(skb), NULL); return proto; } diff --git a/net/psample/psample.c b/net/psample/psample.c index a0ddae8a65f9..25f92ba0840c 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -393,7 +393,9 @@ void psample_sample_packet(struct psample_group *group, nla_total_size_64bit(sizeof(u64)) + /* timestamp */ nla_total_size(sizeof(u16)) + /* protocol */ (md->user_cookie_len ? - nla_total_size(md->user_cookie_len) : 0); /* user cookie */ + nla_total_size(md->user_cookie_len) : 0) + /* user cookie */ + (md->rate_as_probability ? + nla_total_size(0) : 0); /* rate as probability */ #ifdef CONFIG_INET tun_info = skb_tunnel_info(skb); @@ -498,8 +500,9 @@ void psample_sample_packet(struct psample_group *group, md->user_cookie)) goto error; - if (md->rate_as_probability) - nla_put_flag(nl_skb, PSAMPLE_ATTR_SAMPLE_PROBABILITY); + if (md->rate_as_probability && + nla_put_flag(nl_skb, PSAMPLE_ATTR_SAMPLE_PROBABILITY)) + goto error; genlmsg_end(nl_skb, data); genlmsg_multicast_netns(&psample_nl_family, group->net, nl_skb, 0, diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 351ac1747224..0581c53e6517 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -61,8 +61,10 @@ static atomic_t rds_tcp_unloading = ATOMIC_INIT(0); static struct kmem_cache *rds_tcp_conn_slab; -static int rds_tcp_skbuf_handler(const struct ctl_table *ctl, int write, - void *buffer, size_t *lenp, loff_t *fpos); +static int rds_tcp_sndbuf_handler(const struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *fpos); +static int rds_tcp_rcvbuf_handler(const struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *fpos); static int rds_tcp_min_sndbuf = SOCK_MIN_SNDBUF; static int rds_tcp_min_rcvbuf = SOCK_MIN_RCVBUF; @@ -74,7 +76,7 @@ static struct ctl_table rds_tcp_sysctl_table[] = { /* data is per-net pointer */ .maxlen = sizeof(int), .mode = 0644, - .proc_handler = rds_tcp_skbuf_handler, + .proc_handler = rds_tcp_sndbuf_handler, .extra1 = &rds_tcp_min_sndbuf, }, #define RDS_TCP_RCVBUF 1 @@ -83,7 +85,7 @@ static struct ctl_table rds_tcp_sysctl_table[] = { /* data is per-net pointer */ .maxlen = sizeof(int), .mode = 0644, - .proc_handler = rds_tcp_skbuf_handler, + .proc_handler = rds_tcp_rcvbuf_handler, .extra1 = &rds_tcp_min_rcvbuf, }, }; @@ -682,10 +684,10 @@ static void rds_tcp_sysctl_reset(struct net *net) spin_unlock_irq(&rds_tcp_conn_lock); } -static int rds_tcp_skbuf_handler(const struct ctl_table *ctl, int write, +static int rds_tcp_skbuf_handler(struct rds_tcp_net *rtn, + const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *fpos) { - struct net *net = current->nsproxy->net_ns; int err; err = proc_dointvec_minmax(ctl, write, buffer, lenp, fpos); @@ -694,11 +696,34 @@ static int rds_tcp_skbuf_handler(const struct ctl_table *ctl, int write, *(int *)(ctl->extra1)); return err; } - if (write) + + if (write && rtn->rds_tcp_listen_sock && rtn->rds_tcp_listen_sock->sk) { + struct net *net = sock_net(rtn->rds_tcp_listen_sock->sk); + rds_tcp_sysctl_reset(net); + } + return 0; } +static int rds_tcp_sndbuf_handler(const struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *fpos) +{ + struct rds_tcp_net *rtn = container_of(ctl->data, struct rds_tcp_net, + sndbuf_size); + + return rds_tcp_skbuf_handler(rtn, ctl, write, buffer, lenp, fpos); +} + +static int rds_tcp_rcvbuf_handler(const struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *fpos) +{ + struct rds_tcp_net *rtn = container_of(ctl->data, struct rds_tcp_net, + rcvbuf_size); + + return rds_tcp_skbuf_handler(rtn, ctl, write, buffer, lenp, fpos); +} + static void rds_tcp_exit(void) { rds_tcp_set_unloading(); diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 5502998aace7..5c2580a07530 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -356,7 +356,8 @@ static const struct nla_policy flow_policy[TCA_FLOW_MAX + 1] = { [TCA_FLOW_KEYS] = { .type = NLA_U32 }, [TCA_FLOW_MODE] = { .type = NLA_U32 }, [TCA_FLOW_BASECLASS] = { .type = NLA_U32 }, - [TCA_FLOW_RSHIFT] = { .type = NLA_U32 }, + [TCA_FLOW_RSHIFT] = NLA_POLICY_MAX(NLA_U32, + 31 /* BITS_PER_U32 - 1 */), [TCA_FLOW_ADDEND] = { .type = NLA_U32 }, [TCA_FLOW_MASK] = { .type = NLA_U32 }, [TCA_FLOW_XOR] = { .type = NLA_U32 }, diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 8d8b2db4653c..2c2e2a67f3b2 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -627,6 +627,63 @@ static bool cake_ddst(int flow_mode) return (flow_mode & CAKE_FLOW_DUAL_DST) == CAKE_FLOW_DUAL_DST; } +static void cake_dec_srchost_bulk_flow_count(struct cake_tin_data *q, + struct cake_flow *flow, + int flow_mode) +{ + if (likely(cake_dsrc(flow_mode) && + q->hosts[flow->srchost].srchost_bulk_flow_count)) + q->hosts[flow->srchost].srchost_bulk_flow_count--; +} + +static void cake_inc_srchost_bulk_flow_count(struct cake_tin_data *q, + struct cake_flow *flow, + int flow_mode) +{ + if (likely(cake_dsrc(flow_mode) && + q->hosts[flow->srchost].srchost_bulk_flow_count < CAKE_QUEUES)) + q->hosts[flow->srchost].srchost_bulk_flow_count++; +} + +static void cake_dec_dsthost_bulk_flow_count(struct cake_tin_data *q, + struct cake_flow *flow, + int flow_mode) +{ + if (likely(cake_ddst(flow_mode) && + q->hosts[flow->dsthost].dsthost_bulk_flow_count)) + q->hosts[flow->dsthost].dsthost_bulk_flow_count--; +} + +static void cake_inc_dsthost_bulk_flow_count(struct cake_tin_data *q, + struct cake_flow *flow, + int flow_mode) +{ + if (likely(cake_ddst(flow_mode) && + q->hosts[flow->dsthost].dsthost_bulk_flow_count < CAKE_QUEUES)) + q->hosts[flow->dsthost].dsthost_bulk_flow_count++; +} + +static u16 cake_get_flow_quantum(struct cake_tin_data *q, + struct cake_flow *flow, + int flow_mode) +{ + u16 host_load = 1; + + if (cake_dsrc(flow_mode)) + host_load = max(host_load, + q->hosts[flow->srchost].srchost_bulk_flow_count); + + if (cake_ddst(flow_mode)) + host_load = max(host_load, + q->hosts[flow->dsthost].dsthost_bulk_flow_count); + + /* The get_random_u16() is a way to apply dithering to avoid + * accumulating roundoff errors + */ + return (q->flow_quantum * quantum_div[host_load] + + get_random_u16()) >> 16; +} + static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb, int flow_mode, u16 flow_override, u16 host_override) { @@ -773,10 +830,8 @@ skip_hash: allocate_dst = cake_ddst(flow_mode); if (q->flows[outer_hash + k].set == CAKE_SET_BULK) { - if (allocate_src) - q->hosts[q->flows[reduced_hash].srchost].srchost_bulk_flow_count--; - if (allocate_dst) - q->hosts[q->flows[reduced_hash].dsthost].dsthost_bulk_flow_count--; + cake_dec_srchost_bulk_flow_count(q, &q->flows[outer_hash + k], flow_mode); + cake_dec_dsthost_bulk_flow_count(q, &q->flows[outer_hash + k], flow_mode); } found: /* reserve queue for future packets in same flow */ @@ -801,9 +856,10 @@ found: q->hosts[outer_hash + k].srchost_tag = srchost_hash; found_src: srchost_idx = outer_hash + k; - if (q->flows[reduced_hash].set == CAKE_SET_BULK) - q->hosts[srchost_idx].srchost_bulk_flow_count++; q->flows[reduced_hash].srchost = srchost_idx; + + if (q->flows[reduced_hash].set == CAKE_SET_BULK) + cake_inc_srchost_bulk_flow_count(q, &q->flows[reduced_hash], flow_mode); } if (allocate_dst) { @@ -824,9 +880,10 @@ found_src: q->hosts[outer_hash + k].dsthost_tag = dsthost_hash; found_dst: dsthost_idx = outer_hash + k; - if (q->flows[reduced_hash].set == CAKE_SET_BULK) - q->hosts[dsthost_idx].dsthost_bulk_flow_count++; q->flows[reduced_hash].dsthost = dsthost_idx; + + if (q->flows[reduced_hash].set == CAKE_SET_BULK) + cake_inc_dsthost_bulk_flow_count(q, &q->flows[reduced_hash], flow_mode); } } @@ -1839,10 +1896,6 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* flowchain */ if (!flow->set || flow->set == CAKE_SET_DECAYING) { - struct cake_host *srchost = &b->hosts[flow->srchost]; - struct cake_host *dsthost = &b->hosts[flow->dsthost]; - u16 host_load = 1; - if (!flow->set) { list_add_tail(&flow->flowchain, &b->new_flows); } else { @@ -1852,18 +1905,8 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, flow->set = CAKE_SET_SPARSE; b->sparse_flow_count++; - if (cake_dsrc(q->flow_mode)) - host_load = max(host_load, srchost->srchost_bulk_flow_count); - - if (cake_ddst(q->flow_mode)) - host_load = max(host_load, dsthost->dsthost_bulk_flow_count); - - flow->deficit = (b->flow_quantum * - quantum_div[host_load]) >> 16; + flow->deficit = cake_get_flow_quantum(b, flow, q->flow_mode); } else if (flow->set == CAKE_SET_SPARSE_WAIT) { - struct cake_host *srchost = &b->hosts[flow->srchost]; - struct cake_host *dsthost = &b->hosts[flow->dsthost]; - /* this flow was empty, accounted as a sparse flow, but actually * in the bulk rotation. */ @@ -1871,12 +1914,8 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, b->sparse_flow_count--; b->bulk_flow_count++; - if (cake_dsrc(q->flow_mode)) - srchost->srchost_bulk_flow_count++; - - if (cake_ddst(q->flow_mode)) - dsthost->dsthost_bulk_flow_count++; - + cake_inc_srchost_bulk_flow_count(b, flow, q->flow_mode); + cake_inc_dsthost_bulk_flow_count(b, flow, q->flow_mode); } if (q->buffer_used > q->buffer_max_used) @@ -1933,13 +1972,11 @@ static struct sk_buff *cake_dequeue(struct Qdisc *sch) { struct cake_sched_data *q = qdisc_priv(sch); struct cake_tin_data *b = &q->tins[q->cur_tin]; - struct cake_host *srchost, *dsthost; ktime_t now = ktime_get(); struct cake_flow *flow; struct list_head *head; bool first_flow = true; struct sk_buff *skb; - u16 host_load; u64 delay; u32 len; @@ -2039,11 +2076,6 @@ retry: q->cur_flow = flow - b->flows; first_flow = false; - /* triple isolation (modified DRR++) */ - srchost = &b->hosts[flow->srchost]; - dsthost = &b->hosts[flow->dsthost]; - host_load = 1; - /* flow isolation (DRR++) */ if (flow->deficit <= 0) { /* Keep all flows with deficits out of the sparse and decaying @@ -2055,11 +2087,8 @@ retry: b->sparse_flow_count--; b->bulk_flow_count++; - if (cake_dsrc(q->flow_mode)) - srchost->srchost_bulk_flow_count++; - - if (cake_ddst(q->flow_mode)) - dsthost->dsthost_bulk_flow_count++; + cake_inc_srchost_bulk_flow_count(b, flow, q->flow_mode); + cake_inc_dsthost_bulk_flow_count(b, flow, q->flow_mode); flow->set = CAKE_SET_BULK; } else { @@ -2071,19 +2100,7 @@ retry: } } - if (cake_dsrc(q->flow_mode)) - host_load = max(host_load, srchost->srchost_bulk_flow_count); - - if (cake_ddst(q->flow_mode)) - host_load = max(host_load, dsthost->dsthost_bulk_flow_count); - - WARN_ON(host_load > CAKE_QUEUES); - - /* The get_random_u16() is a way to apply dithering to avoid - * accumulating roundoff errors - */ - flow->deficit += (b->flow_quantum * quantum_div[host_load] + - get_random_u16()) >> 16; + flow->deficit += cake_get_flow_quantum(b, flow, q->flow_mode); list_move_tail(&flow->flowchain, &b->old_flows); goto retry; @@ -2107,11 +2124,8 @@ retry: if (flow->set == CAKE_SET_BULK) { b->bulk_flow_count--; - if (cake_dsrc(q->flow_mode)) - srchost->srchost_bulk_flow_count--; - - if (cake_ddst(q->flow_mode)) - dsthost->dsthost_bulk_flow_count--; + cake_dec_srchost_bulk_flow_count(b, flow, q->flow_mode); + cake_dec_dsthost_bulk_flow_count(b, flow, q->flow_mode); b->decaying_flow_count++; } else if (flow->set == CAKE_SET_SPARSE || @@ -2129,12 +2143,8 @@ retry: else if (flow->set == CAKE_SET_BULK) { b->bulk_flow_count--; - if (cake_dsrc(q->flow_mode)) - srchost->srchost_bulk_flow_count--; - - if (cake_ddst(q->flow_mode)) - dsthost->dsthost_bulk_flow_count--; - + cake_dec_srchost_bulk_flow_count(b, flow, q->flow_mode); + cake_dec_dsthost_bulk_flow_count(b, flow, q->flow_mode); } else b->decaying_flow_count--; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index c45c192b7878..0b0794f164cf 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -137,7 +137,8 @@ static struct sctp_association *sctp_association_init( = 5 * asoc->rto_max; asoc->timeouts[SCTP_EVENT_TIMEOUT_SACK] = asoc->sackdelay; - asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = sp->autoclose * HZ; + asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = + (unsigned long)sp->autoclose * HZ; /* Initializes the timers */ for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i) diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index e5a5af343c4c..8e1e97be4df7 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -387,7 +387,8 @@ static struct ctl_table sctp_net_table[] = { static int proc_sctp_do_hmac_alg(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, + sctp.sctp_hmac_alg); struct ctl_table tbl; bool changed = false; char *none = "none"; @@ -432,7 +433,7 @@ static int proc_sctp_do_hmac_alg(const struct ctl_table *ctl, int write, static int proc_sctp_do_rto_min(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, sctp.rto_min); unsigned int min = *(unsigned int *) ctl->extra1; unsigned int max = *(unsigned int *) ctl->extra2; struct ctl_table tbl; @@ -460,7 +461,7 @@ static int proc_sctp_do_rto_min(const struct ctl_table *ctl, int write, static int proc_sctp_do_rto_max(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, sctp.rto_max); unsigned int min = *(unsigned int *) ctl->extra1; unsigned int max = *(unsigned int *) ctl->extra2; struct ctl_table tbl; @@ -498,7 +499,7 @@ static int proc_sctp_do_alpha_beta(const struct ctl_table *ctl, int write, static int proc_sctp_do_auth(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, sctp.auth_enable); struct ctl_table tbl; int new_value, ret; @@ -527,7 +528,7 @@ static int proc_sctp_do_auth(const struct ctl_table *ctl, int write, static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, sctp.udp_port); unsigned int min = *(unsigned int *)ctl->extra1; unsigned int max = *(unsigned int *)ctl->extra2; struct ctl_table tbl; @@ -568,7 +569,8 @@ static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write, static int proc_sctp_do_probe_interval(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct net *net = container_of(ctl->data, struct net, + sctp.probe_interval); struct ctl_table tbl; int ret, new_value; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 9e6c69d18581..6cc7b846cff1 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2032,6 +2032,8 @@ static int smc_listen_prfx_check(struct smc_sock *new_smc, if (pclc->hdr.typev1 == SMC_TYPE_N) return 0; pclc_prfx = smc_clc_proposal_get_prefix(pclc); + if (!pclc_prfx) + return -EPROTO; if (smc_clc_prfx_match(newclcsock, pclc_prfx)) return SMC_CLC_DECL_DIFFPREFIX; @@ -2145,6 +2147,8 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, pclc_smcd = smc_get_clc_msg_smcd(pclc); smc_v2_ext = smc_get_clc_v2_ext(pclc); smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext); + if (!pclc_smcd || !smc_v2_ext || !smcd_v2_ext) + goto not_found; mutex_lock(&smcd_dev_list.mutex); if (pclc_smcd->ism.chid) { @@ -2221,7 +2225,9 @@ static void smc_find_ism_v1_device_serv(struct smc_sock *new_smc, int rc = 0; /* check if ISM V1 is available */ - if (!(ini->smcd_version & SMC_V1) || !smcd_indicated(ini->smc_type_v1)) + if (!(ini->smcd_version & SMC_V1) || + !smcd_indicated(ini->smc_type_v1) || + !pclc_smcd) goto not_found; ini->is_smcd = true; /* prepare ISM check */ ini->ism_peer_gid[0].gid = ntohll(pclc_smcd->ism.gid); @@ -2272,7 +2278,8 @@ static void smc_find_rdma_v2_device_serv(struct smc_sock *new_smc, goto not_found; smc_v2_ext = smc_get_clc_v2_ext(pclc); - if (!smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, NULL, NULL)) + if (!smc_v2_ext || + !smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, NULL, NULL)) goto not_found; /* prepare RDMA check */ @@ -2881,6 +2888,13 @@ __poll_t smc_poll(struct file *file, struct socket *sock, } else { sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + + if (sk->sk_state != SMC_INIT) { + /* Race breaker the same way as tcp_poll(). */ + smp_mb__after_atomic(); + if (atomic_read(&smc->conn.sndbuf_space)) + mask |= EPOLLOUT | EPOLLWRNORM; + } } if (atomic_read(&smc->conn.bytes_to_rcv)) mask |= EPOLLIN | EPOLLRDNORM; diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 33fa787c28eb..521f5df80e10 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -352,8 +352,11 @@ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc) struct smc_clc_msg_hdr *hdr = &pclc->hdr; struct smc_clc_v2_extension *v2_ext; - v2_ext = smc_get_clc_v2_ext(pclc); pclc_prfx = smc_clc_proposal_get_prefix(pclc); + if (!pclc_prfx || + pclc_prfx->ipv6_prefixes_cnt > SMC_CLC_MAX_V6_PREFIX) + return false; + if (hdr->version == SMC_V1) { if (hdr->typev1 == SMC_TYPE_N) return false; @@ -365,6 +368,13 @@ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc) sizeof(struct smc_clc_msg_trail)) return false; } else { + v2_ext = smc_get_clc_v2_ext(pclc); + if ((hdr->typev2 != SMC_TYPE_N && + (!v2_ext || v2_ext->hdr.eid_cnt > SMC_CLC_MAX_UEID)) || + (smcd_indicated(hdr->typev2) && + v2_ext->hdr.ism_gid_cnt > SMCD_CLC_MAX_V2_GID_ENTRIES)) + return false; + if (ntohs(hdr->length) != sizeof(*pclc) + sizeof(struct smc_clc_msg_smcd) + @@ -764,6 +774,11 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, SMC_CLC_RECV_BUF_LEN : datlen; iov_iter_kvec(&msg.msg_iter, ITER_DEST, &vec, 1, recvlen); len = sock_recvmsg(smc->clcsock, &msg, krflags); + if (len < recvlen) { + smc->sk.sk_err = EPROTO; + reason_code = -EPROTO; + goto out; + } datlen -= len; } if (clcm->type == SMC_CLC_DECLINE) { diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 5fd6f5b8ef03..767289925410 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -336,8 +336,12 @@ struct smc_clc_msg_decline_v2 { /* clc decline message */ static inline struct smc_clc_msg_proposal_prefix * smc_clc_proposal_get_prefix(struct smc_clc_msg_proposal *pclc) { + u16 offset = ntohs(pclc->iparea_offset); + + if (offset > sizeof(struct smc_clc_msg_smcd)) + return NULL; return (struct smc_clc_msg_proposal_prefix *) - ((u8 *)pclc + sizeof(*pclc) + ntohs(pclc->iparea_offset)); + ((u8 *)pclc + sizeof(*pclc) + offset); } static inline bool smcr_indicated(int smc_type) @@ -376,8 +380,14 @@ static inline struct smc_clc_v2_extension * smc_get_clc_v2_ext(struct smc_clc_msg_proposal *prop) { struct smc_clc_msg_smcd *prop_smcd = smc_get_clc_msg_smcd(prop); + u16 max_offset; - if (!prop_smcd || !ntohs(prop_smcd->v2_ext_offset)) + max_offset = offsetof(struct smc_clc_msg_proposal_area, pclc_v2_ext) - + offsetof(struct smc_clc_msg_proposal_area, pclc_smcd) - + offsetofend(struct smc_clc_msg_smcd, v2_ext_offset); + + if (!prop_smcd || !ntohs(prop_smcd->v2_ext_offset) || + ntohs(prop_smcd->v2_ext_offset) > max_offset) return NULL; return (struct smc_clc_v2_extension *) @@ -390,9 +400,15 @@ smc_get_clc_v2_ext(struct smc_clc_msg_proposal *prop) static inline struct smc_clc_smcd_v2_extension * smc_get_clc_smcd_v2_ext(struct smc_clc_v2_extension *prop_v2ext) { + u16 max_offset = offsetof(struct smc_clc_msg_proposal_area, pclc_smcd_v2_ext) - + offsetof(struct smc_clc_msg_proposal_area, pclc_v2_ext) - + offsetof(struct smc_clc_v2_extension, hdr) - + offsetofend(struct smc_clnt_opts_area_hdr, smcd_v2_ext_offset); + if (!prop_v2ext) return NULL; - if (!ntohs(prop_v2ext->hdr.smcd_v2_ext_offset)) + if (!ntohs(prop_v2ext->hdr.smcd_v2_ext_offset) || + ntohs(prop_v2ext->hdr.smcd_v2_ext_offset) > max_offset) return NULL; return (struct smc_clc_smcd_v2_extension *) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 500952c2e67b..3b125d348b4a 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1818,7 +1818,9 @@ void smcr_link_down_cond_sched(struct smc_link *lnk) { if (smc_link_downing(&lnk->state)) { trace_smcr_link_down(lnk, __builtin_return_address(0)); - schedule_work(&lnk->link_down_wrk); + smcr_link_hold(lnk); /* smcr_link_put in link_down_wrk */ + if (!schedule_work(&lnk->link_down_wrk)) + smcr_link_put(lnk); } } @@ -1850,11 +1852,14 @@ static void smc_link_down_work(struct work_struct *work) struct smc_link_group *lgr = link->lgr; if (list_empty(&lgr->list)) - return; + goto out; wake_up_all(&lgr->llc_msg_waiter); down_write(&lgr->llc_conf_mutex); smcr_link_down(link); up_write(&lgr->llc_conf_mutex); + +out: + smcr_link_put(link); /* smcr_link_hold by schedulers of link_down_work */ } static int smc_vlan_by_tcpsk_walk(struct net_device *lower_dev, diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index bbf26cc4f6ee..7bcc9b4408a2 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -458,7 +458,7 @@ int tls_tx_records(struct sock *sk, int flags) tx_err: if (rc < 0 && rc != -EAGAIN) - tls_err_abort(sk, -EBADMSG); + tls_err_abort(sk, rc); return rc; } diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs index b89c681d97c0..2fbfb6a94c11 100644 --- a/rust/kernel/net/phy.rs +++ b/rust/kernel/net/phy.rs @@ -860,7 +860,7 @@ impl DeviceMask { /// ]; /// #[cfg(MODULE)] /// #[no_mangle] -/// static __mod_mdio__phydev_device_table: [::kernel::bindings::mdio_device_id; 2] = _DEVICE_TABLE; +/// static __mod_device_table__mdio__phydev: [::kernel::bindings::mdio_device_id; 2] = _DEVICE_TABLE; /// ``` #[macro_export] macro_rules! module_phy_driver { @@ -883,7 +883,7 @@ macro_rules! module_phy_driver { #[cfg(MODULE)] #[no_mangle] - static __mod_mdio__phydev_device_table: [$crate::bindings::mdio_device_id; + static __mod_device_table__mdio__phydev: [$crate::bindings::mdio_device_id; $crate::module_phy_driver!(@count_devices $($dev),+) + 1] = _DEVICE_TABLE; }; diff --git a/rust/kernel/workqueue.rs b/rust/kernel/workqueue.rs index 4d1d2062f6eb..fd3e97192ed8 100644 --- a/rust/kernel/workqueue.rs +++ b/rust/kernel/workqueue.rs @@ -519,7 +519,15 @@ impl_has_work! { impl{T} HasWork<Self> for ClosureWork<T> { self.work } } -// SAFETY: TODO. +// SAFETY: The `__enqueue` implementation in RawWorkItem uses a `work_struct` initialized with the +// `run` method of this trait as the function pointer because: +// - `__enqueue` gets the `work_struct` from the `Work` field, using `T::raw_get_work`. +// - The only safe way to create a `Work` object is through `Work::new`. +// - `Work::new` makes sure that `T::Pointer::run` is passed to `init_work_with_key`. +// - Finally `Work` and `RawWorkItem` guarantee that the correct `Work` field +// will be used because of the ID const generic bound. This makes sure that `T::raw_get_work` +// uses the correct offset for the `Work` field, and `Work::new` picks the correct +// implementation of `WorkItemPointer` for `Arc<T>`. unsafe impl<T, const ID: u64> WorkItemPointer<ID> for Arc<T> where T: WorkItem<ID, Pointer = Self>, @@ -537,7 +545,13 @@ where } } -// SAFETY: TODO. +// SAFETY: The `work_struct` raw pointer is guaranteed to be valid for the duration of the call to +// the closure because we get it from an `Arc`, which means that the ref count will be at least 1, +// and we don't drop the `Arc` ourselves. If `queue_work_on` returns true, it is further guaranteed +// to be valid until a call to the function pointer in `work_struct` because we leak the memory it +// points to, and only reclaim it if the closure returns false, or in `WorkItemPointer::run`, which +// is what the function pointer in the `work_struct` must be pointing to, according to the safety +// requirements of `WorkItemPointer`. unsafe impl<T, const ID: u64> RawWorkItem<ID> for Arc<T> where T: WorkItem<ID, Pointer = Self>, diff --git a/scripts/decode_stacktrace.sh b/scripts/decode_stacktrace.sh index 46fa18b80fc1..17abc4e7a985 100755 --- a/scripts/decode_stacktrace.sh +++ b/scripts/decode_stacktrace.sh @@ -286,6 +286,18 @@ handle_line() { last=$(( $last - 1 )) fi + # Extract info after the symbol if present. E.g.: + # func_name+0x54/0x80 (P) + # ^^^ + # The regex assumes only uppercase letters will be used. To be + # extended if needed. + local info_str="" + if [[ ${words[$last]} =~ \([A-Z]*\) ]]; then + info_str=${words[$last]} + unset words[$last] + last=$(( $last - 1 )) + fi + if [[ ${words[$last]} =~ \[([^]]+)\] ]]; then module=${words[$last]} # some traces format is "(%pS)", which like "(foo+0x0/0x1 [bar])" @@ -313,9 +325,9 @@ handle_line() { # Add up the line number to the symbol if [[ -z ${module} ]] then - echo "${words[@]}" "$symbol" + echo "${words[@]}" "$symbol ${info_str}" else - echo "${words[@]}" "$symbol $module" + echo "${words[@]}" "$symbol $module ${info_str}" fi } diff --git a/scripts/mksysmap b/scripts/mksysmap index c12723a04655..3accbdb269ac 100755 --- a/scripts/mksysmap +++ b/scripts/mksysmap @@ -26,7 +26,7 @@ # (do not forget a space before each pattern) # local symbols for ARM, MIPS, etc. -/ \\$/d +/ \$/d # local labels, .LBB, .Ltmpxxx, .L__unnamed_xx, .LASANPC, etc. / \.L/d @@ -39,7 +39,7 @@ / __pi_\.L/d # arm64 local symbols in non-VHE KVM namespace -/ __kvm_nvhe_\\$/d +/ __kvm_nvhe_\$/d / __kvm_nvhe_\.L/d # lld arm/aarch64/mips thunks diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 5b5745f00eb3..19ec72a69e90 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -132,7 +132,8 @@ struct devtable { * based at address m. */ #define DEF_FIELD(m, devid, f) \ - typeof(((struct devid *)0)->f) f = TO_NATIVE(*(typeof(f) *)((m) + OFF_##devid##_##f)) + typeof(((struct devid *)0)->f) f = \ + get_unaligned_native((typeof(f) *)((m) + OFF_##devid##_##f)) /* Define a variable f that holds the address of field f of struct devid * based at address m. Due to the way typeof works, for a field of type @@ -600,7 +601,7 @@ static void do_pnp_card_entry(struct module *mod, void *symval) static void do_pcmcia_entry(struct module *mod, void *symval) { char alias[256] = {}; - unsigned int i; + DEF_FIELD(symval, pcmcia_device_id, match_flags); DEF_FIELD(symval, pcmcia_device_id, manf_id); DEF_FIELD(symval, pcmcia_device_id, card_id); @@ -609,10 +610,6 @@ static void do_pcmcia_entry(struct module *mod, void *symval) DEF_FIELD(symval, pcmcia_device_id, device_no); DEF_FIELD_ADDR(symval, pcmcia_device_id, prod_id_hash); - for (i=0; i<4; i++) { - (*prod_id_hash)[i] = TO_NATIVE((*prod_id_hash)[i]); - } - ADD(alias, "m", match_flags & PCMCIA_DEV_ID_MATCH_MANF_ID, manf_id); ADD(alias, "c", match_flags & PCMCIA_DEV_ID_MATCH_CARD_ID, @@ -623,10 +620,14 @@ static void do_pcmcia_entry(struct module *mod, void *symval) function); ADD(alias, "pfn", match_flags & PCMCIA_DEV_ID_MATCH_DEVICE_NO, device_no); - ADD(alias, "pa", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID1, (*prod_id_hash)[0]); - ADD(alias, "pb", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID2, (*prod_id_hash)[1]); - ADD(alias, "pc", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID3, (*prod_id_hash)[2]); - ADD(alias, "pd", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID4, (*prod_id_hash)[3]); + ADD(alias, "pa", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID1, + get_unaligned_native(*prod_id_hash + 0)); + ADD(alias, "pb", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID2, + get_unaligned_native(*prod_id_hash + 1)); + ADD(alias, "pc", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID3, + get_unaligned_native(*prod_id_hash + 2)); + ADD(alias, "pd", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID4, + get_unaligned_native(*prod_id_hash + 3)); module_alias_printf(mod, true, "pcmcia:%s", alias); } @@ -654,10 +655,9 @@ static void do_input(char *alias, { unsigned int i; - for (i = min / BITS_PER_LONG; i < max / BITS_PER_LONG + 1; i++) - arr[i] = TO_NATIVE(arr[i]); - for (i = min; i < max; i++) - if (arr[i / BITS_PER_LONG] & (1ULL << (i%BITS_PER_LONG))) + for (i = min; i <= max; i++) + if (get_unaligned_native(arr + i / BITS_PER_LONG) & + (1ULL << (i % BITS_PER_LONG))) sprintf(alias + strlen(alias), "%X,*", i); } @@ -812,15 +812,13 @@ static void do_virtio_entry(struct module *mod, void *symval) * Each byte of the guid will be represented by two hex characters * in the name. */ - static void do_vmbus_entry(struct module *mod, void *symval) { - int i; DEF_FIELD_ADDR(symval, hv_vmbus_device_id, guid); - char guid_name[(sizeof(*guid) + 1) * 2]; + char guid_name[sizeof(*guid) * 2 + 1]; - for (i = 0; i < (sizeof(*guid) * 2); i += 2) - sprintf(&guid_name[i], "%02x", TO_NATIVE((guid->b)[i/2])); + for (int i = 0; i < sizeof(*guid); i++) + sprintf(&guid_name[i * 2], "%02x", guid->b[i]); module_alias_printf(mod, false, "vmbus:%s", guid_name); } diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index fb787a5715f5..7ea59dc4926b 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -155,12 +155,13 @@ char *get_line(char **stringp) /* A list of all modules we processed */ LIST_HEAD(modules); -static struct module *find_module(const char *modname) +static struct module *find_module(const char *filename, const char *modname) { struct module *mod; list_for_each_entry(mod, &modules, list) { - if (strcmp(mod->name, modname) == 0) + if (!strcmp(mod->dump_file, filename) && + !strcmp(mod->name, modname)) return mod; } return NULL; @@ -1137,9 +1138,9 @@ static Elf_Addr addend_386_rel(uint32_t *location, unsigned int r_type) { switch (r_type) { case R_386_32: - return TO_NATIVE(*location); + return get_unaligned_native(location); case R_386_PC32: - return TO_NATIVE(*location) + 4; + return get_unaligned_native(location) + 4; } return (Elf_Addr)(-1); @@ -1160,24 +1161,24 @@ static Elf_Addr addend_arm_rel(void *loc, Elf_Sym *sym, unsigned int r_type) switch (r_type) { case R_ARM_ABS32: case R_ARM_REL32: - inst = TO_NATIVE(*(uint32_t *)loc); + inst = get_unaligned_native((uint32_t *)loc); return inst + sym->st_value; case R_ARM_MOVW_ABS_NC: case R_ARM_MOVT_ABS: - inst = TO_NATIVE(*(uint32_t *)loc); + inst = get_unaligned_native((uint32_t *)loc); offset = sign_extend32(((inst & 0xf0000) >> 4) | (inst & 0xfff), 15); return offset + sym->st_value; case R_ARM_PC24: case R_ARM_CALL: case R_ARM_JUMP24: - inst = TO_NATIVE(*(uint32_t *)loc); + inst = get_unaligned_native((uint32_t *)loc); offset = sign_extend32((inst & 0x00ffffff) << 2, 25); return offset + sym->st_value + 8; case R_ARM_THM_MOVW_ABS_NC: case R_ARM_THM_MOVT_ABS: - upper = TO_NATIVE(*(uint16_t *)loc); - lower = TO_NATIVE(*((uint16_t *)loc + 1)); + upper = get_unaligned_native((uint16_t *)loc); + lower = get_unaligned_native((uint16_t *)loc + 1); offset = sign_extend32(((upper & 0x000f) << 12) | ((upper & 0x0400) << 1) | ((lower & 0x7000) >> 4) | @@ -1194,8 +1195,8 @@ static Elf_Addr addend_arm_rel(void *loc, Elf_Sym *sym, unsigned int r_type) * imm11 = lower[10:0] * imm32 = SignExtend(S:J2:J1:imm6:imm11:'0') */ - upper = TO_NATIVE(*(uint16_t *)loc); - lower = TO_NATIVE(*((uint16_t *)loc + 1)); + upper = get_unaligned_native((uint16_t *)loc); + lower = get_unaligned_native((uint16_t *)loc + 1); sign = (upper >> 10) & 1; j1 = (lower >> 13) & 1; @@ -1218,8 +1219,8 @@ static Elf_Addr addend_arm_rel(void *loc, Elf_Sym *sym, unsigned int r_type) * I2 = NOT(J2 XOR S) * imm32 = SignExtend(S:I1:I2:imm10:imm11:'0') */ - upper = TO_NATIVE(*(uint16_t *)loc); - lower = TO_NATIVE(*((uint16_t *)loc + 1)); + upper = get_unaligned_native((uint16_t *)loc); + lower = get_unaligned_native((uint16_t *)loc + 1); sign = (upper >> 10) & 1; j1 = (lower >> 13) & 1; @@ -1240,7 +1241,7 @@ static Elf_Addr addend_mips_rel(uint32_t *location, unsigned int r_type) { uint32_t inst; - inst = TO_NATIVE(*location); + inst = get_unaligned_native(location); switch (r_type) { case R_MIPS_LO16: return inst & 0xffff; @@ -2030,10 +2031,10 @@ static void read_dump(const char *fname) continue; } - mod = find_module(modname); + mod = find_module(fname, modname); if (!mod) { mod = new_module(modname, strlen(modname)); - mod->from_dump = true; + mod->dump_file = fname; } s = sym_add_exported(symname, mod, gpl_only, namespace); sym_set_crc(s, crc); @@ -2052,7 +2053,7 @@ static void write_dump(const char *fname) struct symbol *sym; list_for_each_entry(mod, &modules, list) { - if (mod->from_dump) + if (mod->dump_file) continue; list_for_each_entry(sym, &mod->exported_symbols, list) { if (trim_unused_exports && !sym->used) @@ -2076,7 +2077,7 @@ static void write_namespace_deps_files(const char *fname) list_for_each_entry(mod, &modules, list) { - if (mod->from_dump || list_empty(&mod->missing_namespaces)) + if (mod->dump_file || list_empty(&mod->missing_namespaces)) continue; buf_printf(&ns_deps_buf, "%s.ko:", mod->name); @@ -2194,7 +2195,7 @@ int main(int argc, char **argv) read_symbols_from_files(files_source); list_for_each_entry(mod, &modules, list) { - if (mod->from_dump || mod->is_vmlinux) + if (mod->dump_file || mod->is_vmlinux) continue; check_modname_len(mod); @@ -2205,7 +2206,7 @@ int main(int argc, char **argv) handle_white_list_exports(unused_exports_white_list); list_for_each_entry(mod, &modules, list) { - if (mod->from_dump) + if (mod->dump_file) continue; if (mod->is_vmlinux) diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h index 49848fcbe2a1..ffd0a52a606e 100644 --- a/scripts/mod/modpost.h +++ b/scripts/mod/modpost.h @@ -65,6 +65,20 @@ #define TO_NATIVE(x) \ (target_is_big_endian == host_is_big_endian ? x : bswap(x)) +#define __get_unaligned_t(type, ptr) ({ \ + const struct { type x; } __attribute__((__packed__)) *__pptr = \ + (typeof(__pptr))(ptr); \ + __pptr->x; \ +}) + +#define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr)) + +#define get_unaligned_native(ptr) \ +({ \ + typeof(*(ptr)) _val = get_unaligned(ptr); \ + TO_NATIVE(_val); \ +}) + #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) #define strstarts(str, prefix) (strncmp(str, prefix, strlen(prefix)) == 0) @@ -95,14 +109,15 @@ struct module_alias { /** * struct module - represent a module (vmlinux or *.ko) * + * @dump_file: path to the .symvers file if loaded from a file * @aliases: list head for module_aliases */ struct module { struct list_head list; struct list_head exported_symbols; struct list_head unresolved_symbols; + const char *dump_file; bool is_gpl_compatible; - bool from_dump; /* true if module was loaded from *.symvers */ bool is_vmlinux; bool seen; bool has_init; diff --git a/scripts/package/PKGBUILD b/scripts/package/PKGBUILD index f83493838cf9..dca706617adc 100644 --- a/scripts/package/PKGBUILD +++ b/scripts/package/PKGBUILD @@ -103,7 +103,7 @@ _package-headers() { _package-api-headers() { pkgdesc="Kernel headers sanitized for use in userspace" - provides=(linux-api-headers) + provides=(linux-api-headers="${pkgver}") conflicts=(linux-api-headers) _prologue diff --git a/scripts/package/builddeb b/scripts/package/builddeb index fb686fd3266f..ad7aba0f268e 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -63,6 +63,12 @@ install_linux_image () { esac cp "$(${MAKE} -s -f ${srctree}/Makefile image_name)" "${pdir}/${installed_image_path}" + if [ "${ARCH}" != um ]; then + install_maint_scripts "${pdir}" + fi +} + +install_maint_scripts () { # Install the maintainer scripts # Note: hook scripts under /etc/kernel are also executed by official Debian # kernel packages, as well as kernel packages built using make-kpkg. diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian index 4ffcc70f8e31..b038a1380b8a 100755 --- a/scripts/package/mkdebian +++ b/scripts/package/mkdebian @@ -70,6 +70,13 @@ set_debarch() { debarch=sh4$(if_enabled_echo CONFIG_CPU_BIG_ENDIAN eb) fi ;; + um) + if is_enabled CONFIG_64BIT; then + debarch=amd64 + else + debarch=i386 + fi + ;; esac if [ -z "$debarch" ]; then debarch=$(dpkg-architecture -qDEB_HOST_ARCH) diff --git a/scripts/sorttable.h b/scripts/sorttable.h index 7bd0184380d3..a7c5445baf00 100644 --- a/scripts/sorttable.h +++ b/scripts/sorttable.h @@ -110,7 +110,7 @@ static inline unsigned long orc_ip(const int *ip) static int orc_sort_cmp(const void *_a, const void *_b) { - struct orc_entry *orc_a; + struct orc_entry *orc_a, *orc_b; const int *a = g_orc_ip_table + *(int *)_a; const int *b = g_orc_ip_table + *(int *)_b; unsigned long a_val = orc_ip(a); @@ -128,6 +128,9 @@ static int orc_sort_cmp(const void *_a, const void *_b) * whitelisted .o files which didn't get objtool generation. */ orc_a = g_orc_table + (a - g_orc_ip_table); + orc_b = g_orc_table + (b - g_orc_ip_table); + if (orc_a->type == ORC_TYPE_UNDEFINED && orc_b->type == ORC_TYPE_UNDEFINED) + return 0; return orc_a->type == ORC_TYPE_UNDEFINED ? -1 : 1; } diff --git a/security/selinux/avc.c b/security/selinux/avc.c index cc0b0af20296..1f2680bcc43a 100644 --- a/security/selinux/avc.c +++ b/security/selinux/avc.c @@ -174,13 +174,15 @@ int avc_get_hash_stats(char *page) * using a linked list for extended_perms_decision lookup because the list is * always small. i.e. less than 5, typically 1 */ -static struct extended_perms_decision *avc_xperms_decision_lookup(u8 driver, - struct avc_xperms_node *xp_node) +static struct extended_perms_decision * +avc_xperms_decision_lookup(u8 driver, u8 base_perm, + struct avc_xperms_node *xp_node) { struct avc_xperms_decision_node *xpd_node; list_for_each_entry(xpd_node, &xp_node->xpd_head, xpd_list) { - if (xpd_node->xpd.driver == driver) + if (xpd_node->xpd.driver == driver && + xpd_node->xpd.base_perm == base_perm) return &xpd_node->xpd; } return NULL; @@ -205,11 +207,12 @@ avc_xperms_has_perm(struct extended_perms_decision *xpd, } static void avc_xperms_allow_perm(struct avc_xperms_node *xp_node, - u8 driver, u8 perm) + u8 driver, u8 base_perm, u8 perm) { struct extended_perms_decision *xpd; security_xperm_set(xp_node->xp.drivers.p, driver); - xpd = avc_xperms_decision_lookup(driver, xp_node); + xp_node->xp.base_perms |= base_perm; + xpd = avc_xperms_decision_lookup(driver, base_perm, xp_node); if (xpd && xpd->allowed) security_xperm_set(xpd->allowed->p, perm); } @@ -245,6 +248,7 @@ static void avc_xperms_free(struct avc_xperms_node *xp_node) static void avc_copy_xperms_decision(struct extended_perms_decision *dest, struct extended_perms_decision *src) { + dest->base_perm = src->base_perm; dest->driver = src->driver; dest->used = src->used; if (dest->used & XPERMS_ALLOWED) @@ -272,6 +276,7 @@ static inline void avc_quick_copy_xperms_decision(u8 perm, */ u8 i = perm >> 5; + dest->base_perm = src->base_perm; dest->used = src->used; if (dest->used & XPERMS_ALLOWED) dest->allowed->p[i] = src->allowed->p[i]; @@ -357,6 +362,7 @@ static int avc_xperms_populate(struct avc_node *node, memcpy(dest->xp.drivers.p, src->xp.drivers.p, sizeof(dest->xp.drivers.p)); dest->xp.len = src->xp.len; + dest->xp.base_perms = src->xp.base_perms; /* for each source xpd allocate a destination xpd and copy */ list_for_each_entry(src_xpd, &src->xpd_head, xpd_list) { @@ -807,6 +813,7 @@ out: * @event : Updating event * @perms : Permission mask bits * @driver: xperm driver information + * @base_perm: the base permission associated with the extended permission * @xperm: xperm permissions * @ssid: AVC entry source sid * @tsid: AVC entry target sid @@ -820,10 +827,9 @@ out: * otherwise, this function updates the AVC entry. The original AVC-entry object * will release later by RCU. */ -static int avc_update_node(u32 event, u32 perms, u8 driver, u8 xperm, u32 ssid, - u32 tsid, u16 tclass, u32 seqno, - struct extended_perms_decision *xpd, - u32 flags) +static int avc_update_node(u32 event, u32 perms, u8 driver, u8 base_perm, + u8 xperm, u32 ssid, u32 tsid, u16 tclass, u32 seqno, + struct extended_perms_decision *xpd, u32 flags) { u32 hvalue; int rc = 0; @@ -880,7 +886,7 @@ static int avc_update_node(u32 event, u32 perms, u8 driver, u8 xperm, u32 ssid, case AVC_CALLBACK_GRANT: node->ae.avd.allowed |= perms; if (node->ae.xp_node && (flags & AVC_EXTENDED_PERMS)) - avc_xperms_allow_perm(node->ae.xp_node, driver, xperm); + avc_xperms_allow_perm(node->ae.xp_node, driver, base_perm, xperm); break; case AVC_CALLBACK_TRY_REVOKE: case AVC_CALLBACK_REVOKE: @@ -987,10 +993,9 @@ static noinline void avc_compute_av(u32 ssid, u32 tsid, u16 tclass, avc_insert(ssid, tsid, tclass, avd, xp_node); } -static noinline int avc_denied(u32 ssid, u32 tsid, - u16 tclass, u32 requested, - u8 driver, u8 xperm, unsigned int flags, - struct av_decision *avd) +static noinline int avc_denied(u32 ssid, u32 tsid, u16 tclass, u32 requested, + u8 driver, u8 base_perm, u8 xperm, + unsigned int flags, struct av_decision *avd) { if (flags & AVC_STRICT) return -EACCES; @@ -999,7 +1004,7 @@ static noinline int avc_denied(u32 ssid, u32 tsid, !(avd->flags & AVD_FLAGS_PERMISSIVE)) return -EACCES; - avc_update_node(AVC_CALLBACK_GRANT, requested, driver, + avc_update_node(AVC_CALLBACK_GRANT, requested, driver, base_perm, xperm, ssid, tsid, tclass, avd->seqno, NULL, flags); return 0; } @@ -1012,7 +1017,8 @@ static noinline int avc_denied(u32 ssid, u32 tsid, * driver field is used to specify which set contains the permission. */ int avc_has_extended_perms(u32 ssid, u32 tsid, u16 tclass, u32 requested, - u8 driver, u8 xperm, struct common_audit_data *ad) + u8 driver, u8 base_perm, u8 xperm, + struct common_audit_data *ad) { struct avc_node *node; struct av_decision avd; @@ -1047,22 +1053,23 @@ int avc_has_extended_perms(u32 ssid, u32 tsid, u16 tclass, u32 requested, local_xpd.auditallow = &auditallow; local_xpd.dontaudit = &dontaudit; - xpd = avc_xperms_decision_lookup(driver, xp_node); + xpd = avc_xperms_decision_lookup(driver, base_perm, xp_node); if (unlikely(!xpd)) { /* * Compute the extended_perms_decision only if the driver - * is flagged + * is flagged and the base permission is known. */ - if (!security_xperm_test(xp_node->xp.drivers.p, driver)) { + if (!security_xperm_test(xp_node->xp.drivers.p, driver) || + !(xp_node->xp.base_perms & base_perm)) { avd.allowed &= ~requested; goto decision; } rcu_read_unlock(); - security_compute_xperms_decision(ssid, tsid, tclass, - driver, &local_xpd); + security_compute_xperms_decision(ssid, tsid, tclass, driver, + base_perm, &local_xpd); rcu_read_lock(); - avc_update_node(AVC_CALLBACK_ADD_XPERMS, requested, - driver, xperm, ssid, tsid, tclass, avd.seqno, + avc_update_node(AVC_CALLBACK_ADD_XPERMS, requested, driver, + base_perm, xperm, ssid, tsid, tclass, avd.seqno, &local_xpd, 0); } else { avc_quick_copy_xperms_decision(xperm, &local_xpd, xpd); @@ -1075,8 +1082,8 @@ int avc_has_extended_perms(u32 ssid, u32 tsid, u16 tclass, u32 requested, decision: denied = requested & ~(avd.allowed); if (unlikely(denied)) - rc = avc_denied(ssid, tsid, tclass, requested, - driver, xperm, AVC_EXTENDED_PERMS, &avd); + rc = avc_denied(ssid, tsid, tclass, requested, driver, + base_perm, xperm, AVC_EXTENDED_PERMS, &avd); rcu_read_unlock(); @@ -1110,7 +1117,7 @@ static noinline int avc_perm_nonode(u32 ssid, u32 tsid, u16 tclass, avc_compute_av(ssid, tsid, tclass, avd, &xp_node); denied = requested & ~(avd->allowed); if (unlikely(denied)) - return avc_denied(ssid, tsid, tclass, requested, 0, 0, + return avc_denied(ssid, tsid, tclass, requested, 0, 0, 0, flags, avd); return 0; } @@ -1158,7 +1165,7 @@ inline int avc_has_perm_noaudit(u32 ssid, u32 tsid, rcu_read_unlock(); if (unlikely(denied)) - return avc_denied(ssid, tsid, tclass, requested, 0, 0, + return avc_denied(ssid, tsid, tclass, requested, 0, 0, 0, flags, avd); return 0; } diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 366c87a40bd1..171dd7fceac5 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3688,8 +3688,8 @@ static int ioctl_has_perm(const struct cred *cred, struct file *file, return 0; isec = inode_security(inode); - rc = avc_has_extended_perms(ssid, isec->sid, isec->sclass, - requested, driver, xperm, &ad); + rc = avc_has_extended_perms(ssid, isec->sid, isec->sclass, requested, + driver, AVC_EXT_IOCTL, xperm, &ad); out: return rc; } @@ -5952,7 +5952,7 @@ static int nlmsg_sock_has_extended_perms(struct sock *sk, u32 perms, u16 nlmsg_t xperm = nlmsg_type & 0xff; return avc_has_extended_perms(current_sid(), sksec->sid, sksec->sclass, - perms, driver, xperm, &ad); + perms, driver, AVC_EXT_NLMSG, xperm, &ad); } static int selinux_netlink_send(struct sock *sk, struct sk_buff *skb) diff --git a/security/selinux/include/avc.h b/security/selinux/include/avc.h index 96a614d47df8..281f40103663 100644 --- a/security/selinux/include/avc.h +++ b/security/selinux/include/avc.h @@ -136,8 +136,11 @@ int avc_has_perm_noaudit(u32 ssid, u32 tsid, u16 tclass, u32 requested, int avc_has_perm(u32 ssid, u32 tsid, u16 tclass, u32 requested, struct common_audit_data *auditdata); +#define AVC_EXT_IOCTL (1 << 0) /* Cache entry for an ioctl extended permission */ +#define AVC_EXT_NLMSG (1 << 1) /* Cache entry for an nlmsg extended permission */ int avc_has_extended_perms(u32 ssid, u32 tsid, u16 tclass, u32 requested, - u8 driver, u8 perm, struct common_audit_data *ad); + u8 driver, u8 base_perm, u8 perm, + struct common_audit_data *ad); u32 avc_policy_seqno(void); diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h index c7f2731abd03..700bd6c8bb38 100644 --- a/security/selinux/include/security.h +++ b/security/selinux/include/security.h @@ -239,6 +239,7 @@ struct extended_perms_data { struct extended_perms_decision { u8 used; u8 driver; + u8 base_perm; struct extended_perms_data *allowed; struct extended_perms_data *auditallow; struct extended_perms_data *dontaudit; @@ -246,6 +247,7 @@ struct extended_perms_decision { struct extended_perms { u16 len; /* length associated decision chain */ + u8 base_perms; /* which base permissions are covered */ struct extended_perms_data drivers; /* flag drivers that are used */ }; @@ -257,6 +259,7 @@ void security_compute_av(u32 ssid, u32 tsid, u16 tclass, struct extended_perms *xperms); void security_compute_xperms_decision(u32 ssid, u32 tsid, u16 tclass, u8 driver, + u8 base_perm, struct extended_perms_decision *xpermd); void security_compute_av_user(u32 ssid, u32 tsid, u16 tclass, diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index 971c45d576ba..d9f58b5d0f49 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -582,7 +582,7 @@ static void type_attribute_bounds_av(struct policydb *policydb, } /* - * Flag which drivers have permissions. + * Flag which drivers have permissions and which base permissions are covered. */ void services_compute_xperms_drivers( struct extended_perms *xperms, @@ -592,12 +592,19 @@ void services_compute_xperms_drivers( switch (node->datum.u.xperms->specified) { case AVTAB_XPERMS_IOCTLDRIVER: + xperms->base_perms |= AVC_EXT_IOCTL; /* if one or more driver has all permissions allowed */ for (i = 0; i < ARRAY_SIZE(xperms->drivers.p); i++) xperms->drivers.p[i] |= node->datum.u.xperms->perms.p[i]; break; case AVTAB_XPERMS_IOCTLFUNCTION: + xperms->base_perms |= AVC_EXT_IOCTL; + /* if allowing permissions within a driver */ + security_xperm_set(xperms->drivers.p, + node->datum.u.xperms->driver); + break; case AVTAB_XPERMS_NLMSG: + xperms->base_perms |= AVC_EXT_NLMSG; /* if allowing permissions within a driver */ security_xperm_set(xperms->drivers.p, node->datum.u.xperms->driver); @@ -631,8 +638,7 @@ static void context_struct_compute_av(struct policydb *policydb, avd->auditallow = 0; avd->auditdeny = 0xffffffff; if (xperms) { - memset(&xperms->drivers, 0, sizeof(xperms->drivers)); - xperms->len = 0; + memset(xperms, 0, sizeof(*xperms)); } if (unlikely(!tclass || tclass > policydb->p_classes.nprim)) { @@ -969,17 +975,26 @@ void services_compute_xperms_decision(struct extended_perms_decision *xpermd, { switch (node->datum.u.xperms->specified) { case AVTAB_XPERMS_IOCTLFUNCTION: - case AVTAB_XPERMS_NLMSG: - if (xpermd->driver != node->datum.u.xperms->driver) + if (xpermd->base_perm != AVC_EXT_IOCTL || + xpermd->driver != node->datum.u.xperms->driver) return; break; case AVTAB_XPERMS_IOCTLDRIVER: - if (!security_xperm_test(node->datum.u.xperms->perms.p, - xpermd->driver)) + if (xpermd->base_perm != AVC_EXT_IOCTL || + !security_xperm_test(node->datum.u.xperms->perms.p, + xpermd->driver)) + return; + break; + case AVTAB_XPERMS_NLMSG: + if (xpermd->base_perm != AVC_EXT_NLMSG || + xpermd->driver != node->datum.u.xperms->driver) return; break; default: - BUG(); + pr_warn_once( + "SELinux: unknown extended permission (%u) will be ignored\n", + node->datum.u.xperms->specified); + return; } if (node->key.specified == AVTAB_XPERMS_ALLOWED) { @@ -998,7 +1013,8 @@ void services_compute_xperms_decision(struct extended_perms_decision *xpermd, &node->datum.u.xperms->perms, xpermd->dontaudit); } else { - BUG(); + pr_warn_once("SELinux: unknown specified key (%u)\n", + node->key.specified); } } @@ -1006,6 +1022,7 @@ void security_compute_xperms_decision(u32 ssid, u32 tsid, u16 orig_tclass, u8 driver, + u8 base_perm, struct extended_perms_decision *xpermd) { struct selinux_policy *policy; @@ -1019,6 +1036,7 @@ void security_compute_xperms_decision(u32 ssid, struct ebitmap_node *snode, *tnode; unsigned int i, j; + xpermd->base_perm = base_perm; xpermd->driver = driver; xpermd->used = 0; memset(xpermd->allowed->p, 0, sizeof(xpermd->allowed->p)); diff --git a/sound/soc/fsl/Kconfig b/sound/soc/fsl/Kconfig index 8e88830e8e57..678540b78280 100644 --- a/sound/soc/fsl/Kconfig +++ b/sound/soc/fsl/Kconfig @@ -29,8 +29,8 @@ config SND_SOC_FSL_SAI config SND_SOC_FSL_MQS tristate "Medium Quality Sound (MQS) module support" depends on SND_SOC_FSL_SAI + depends on IMX_SCMI_MISC_DRV || !IMX_SCMI_MISC_DRV select REGMAP_MMIO - select IMX_SCMI_MISC_DRV if IMX_SCMI_MISC_EXT !=n help Say Y if you want to add Medium Quality Sound (MQS) support for the Freescale CPUs. diff --git a/tools/hv/.gitignore b/tools/hv/.gitignore new file mode 100644 index 000000000000..0c5bc15d602f --- /dev/null +++ b/tools/hv/.gitignore @@ -0,0 +1,3 @@ +hv_fcopy_uio_daemon +hv_kvp_daemon +hv_vss_daemon diff --git a/tools/hv/hv_fcopy_uio_daemon.c b/tools/hv/hv_fcopy_uio_daemon.c index 7a00f3066a98..0198321d14a2 100644 --- a/tools/hv/hv_fcopy_uio_daemon.c +++ b/tools/hv/hv_fcopy_uio_daemon.c @@ -35,8 +35,6 @@ #define WIN8_SRV_MINOR 1 #define WIN8_SRV_VERSION (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR) -#define MAX_FOLDER_NAME 15 -#define MAX_PATH_LEN 15 #define FCOPY_UIO "/sys/bus/vmbus/devices/eb765408-105f-49b6-b4aa-c123b64d17d4/uio" #define FCOPY_VER_COUNT 1 @@ -51,7 +49,7 @@ static const int fw_versions[] = { #define HV_RING_SIZE 0x4000 /* 16KB ring buffer size */ -unsigned char desc[HV_RING_SIZE]; +static unsigned char desc[HV_RING_SIZE]; static int target_fd; static char target_fname[PATH_MAX]; @@ -409,8 +407,8 @@ int main(int argc, char *argv[]) struct vmbus_br txbr, rxbr; void *ring; uint32_t len = HV_RING_SIZE; - char uio_name[MAX_FOLDER_NAME] = {0}; - char uio_dev_path[MAX_PATH_LEN] = {0}; + char uio_name[NAME_MAX] = {0}; + char uio_dev_path[PATH_MAX] = {0}; static struct option long_options[] = { {"help", no_argument, 0, 'h' }, @@ -468,8 +466,10 @@ int main(int argc, char *argv[]) */ ret = pread(fcopy_fd, &tmp, sizeof(int), 0); if (ret < 0) { + if (errno == EINTR || errno == EAGAIN) + continue; syslog(LOG_ERR, "pread failed: %s", strerror(errno)); - continue; + goto close; } len = HV_RING_SIZE; diff --git a/tools/hv/hv_get_dns_info.sh b/tools/hv/hv_get_dns_info.sh index 058c17b46ffc..268521234d4b 100755 --- a/tools/hv/hv_get_dns_info.sh +++ b/tools/hv/hv_get_dns_info.sh @@ -1,4 +1,4 @@ -#!/bin/bash +#!/bin/sh # This example script parses /etc/resolv.conf to retrive DNS information. # In the interest of keeping the KVP daemon code free of distro specific @@ -10,4 +10,4 @@ # this script can be based on the Network Manager APIs for retrieving DNS # entries. -cat /etc/resolv.conf 2>/dev/null | awk '/^nameserver/ { print $2 }' +exec awk '/^nameserver/ { print $2 }' /etc/resolv.conf 2>/dev/null diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index ae57bf69ad4a..04ba035d67e9 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -725,7 +725,7 @@ static void kvp_get_ipconfig_info(char *if_name, * . */ - sprintf(cmd, KVP_SCRIPTS_PATH "%s", "hv_get_dns_info"); + sprintf(cmd, "exec %s %s", KVP_SCRIPTS_PATH "hv_get_dns_info", if_name); /* * Execute the command to gather DNS info. @@ -742,7 +742,7 @@ static void kvp_get_ipconfig_info(char *if_name, * Enabled: DHCP enabled. */ - sprintf(cmd, KVP_SCRIPTS_PATH "%s %s", "hv_get_dhcp_info", if_name); + sprintf(cmd, "exec %s %s", KVP_SCRIPTS_PATH "hv_get_dhcp_info", if_name); file = popen(cmd, "r"); if (file == NULL) @@ -1606,8 +1606,9 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) * invoke the external script to do its magic. */ - str_len = snprintf(cmd, sizeof(cmd), KVP_SCRIPTS_PATH "%s %s %s", - "hv_set_ifconfig", if_filename, nm_filename); + str_len = snprintf(cmd, sizeof(cmd), "exec %s %s %s", + KVP_SCRIPTS_PATH "hv_set_ifconfig", + if_filename, nm_filename); /* * This is a little overcautious, but it's necessary to suppress some * false warnings from gcc 8.0.1. diff --git a/tools/hv/hv_set_ifconfig.sh b/tools/hv/hv_set_ifconfig.sh index 440a91b35823..2f8baed2b8f7 100755 --- a/tools/hv/hv_set_ifconfig.sh +++ b/tools/hv/hv_set_ifconfig.sh @@ -81,7 +81,7 @@ echo "ONBOOT=yes" >> $1 cp $1 /etc/sysconfig/network-scripts/ -chmod 600 $2 +umask 0177 interface=$(echo $2 | awk -F - '{ print $2 }') filename="${2##*/}" diff --git a/tools/include/uapi/linux/stddef.h b/tools/include/uapi/linux/stddef.h index bb6ea517efb5..c53cde425406 100644 --- a/tools/include/uapi/linux/stddef.h +++ b/tools/include/uapi/linux/stddef.h @@ -8,6 +8,13 @@ #define __always_inline __inline__ #endif +/* Not all C++ standards support type declarations inside an anonymous union */ +#ifndef __cplusplus +#define __struct_group_tag(TAG) TAG +#else +#define __struct_group_tag(TAG) +#endif + /** * __struct_group() - Create a mirrored named and anonyomous struct * @@ -20,14 +27,14 @@ * and size: one anonymous and one named. The former's members can be used * normally without sub-struct naming, and the latter can be used to * reason about the start, end, and size of the group of struct members. - * The named struct can also be explicitly tagged for layer reuse, as well - * as both having struct attributes appended. + * The named struct can also be explicitly tagged for layer reuse (C only), + * as well as both having struct attributes appended. */ #define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \ union { \ struct { MEMBERS } ATTRS; \ - struct TAG { MEMBERS } ATTRS NAME; \ - } + struct __struct_group_tag(TAG) { MEMBERS } ATTRS NAME; \ + } ATTRS /** * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index 01ec01a90e76..eea29359a899 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -556,10 +556,10 @@ class YnlFamily(SpecFamily): if attr["type"] == 'nest': nl_type |= Netlink.NLA_F_NESTED attr_payload = b'' - sub_attrs = SpaceAttrs(self.attr_sets[space], value, search_attrs) + sub_space = attr['nested-attributes'] + sub_attrs = SpaceAttrs(self.attr_sets[sub_space], value, search_attrs) for subname, subvalue in value.items(): - attr_payload += self._add_attr(attr['nested-attributes'], - subname, subvalue, sub_attrs) + attr_payload += self._add_attr(sub_space, subname, subvalue, sub_attrs) elif attr["type"] == 'flag': if not value: # If value is absent or false then skip attribute creation. diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 4ce176ad411f..76060da755b5 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -3820,9 +3820,12 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, break; case INSN_CONTEXT_SWITCH: - if (func && (!next_insn || !next_insn->hint)) { - WARN_INSN(insn, "unsupported instruction in callable function"); - return 1; + if (func) { + if (!next_insn || !next_insn->hint) { + WARN_INSN(insn, "unsupported instruction in callable function"); + return 1; + } + break; } return 0; diff --git a/tools/objtool/noreturns.h b/tools/objtool/noreturns.h index f37614cc2c1b..b2174894f9f7 100644 --- a/tools/objtool/noreturns.h +++ b/tools/objtool/noreturns.h @@ -19,6 +19,7 @@ NORETURN(__x64_sys_exit_group) NORETURN(arch_cpu_idle_dead) NORETURN(bch2_trans_in_restart_error) NORETURN(bch2_trans_restart_error) +NORETURN(bch2_trans_unlocked_error) NORETURN(cpu_bringup_and_idle) NORETURN(cpu_startup_entry) NORETURN(do_exit) diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h index 2f36b7b6418d..625f5b046776 100644 --- a/tools/sched_ext/include/scx/common.bpf.h +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -40,9 +40,9 @@ void scx_bpf_dsq_insert(struct task_struct *p, u64 dsq_id, u64 slice, u64 enq_fl void scx_bpf_dsq_insert_vtime(struct task_struct *p, u64 dsq_id, u64 slice, u64 vtime, u64 enq_flags) __ksym __weak; u32 scx_bpf_dispatch_nr_slots(void) __ksym; void scx_bpf_dispatch_cancel(void) __ksym; -bool scx_bpf_dsq_move_to_local(u64 dsq_id) __ksym; -void scx_bpf_dsq_move_set_slice(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym; -void scx_bpf_dsq_move_set_vtime(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym; +bool scx_bpf_dsq_move_to_local(u64 dsq_id) __ksym __weak; +void scx_bpf_dsq_move_set_slice(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym __weak; +void scx_bpf_dsq_move_set_vtime(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym __weak; bool scx_bpf_dsq_move(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak; bool scx_bpf_dsq_move_vtime(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak; u32 scx_bpf_reenqueue_local(void) __ksym; diff --git a/tools/sched_ext/scx_central.c b/tools/sched_ext/scx_central.c index 21deea320bd7..e938156ed0a0 100644 --- a/tools/sched_ext/scx_central.c +++ b/tools/sched_ext/scx_central.c @@ -97,7 +97,7 @@ restart: SCX_BUG_ON(!cpuset, "Failed to allocate cpuset"); CPU_ZERO(cpuset); CPU_SET(skel->rodata->central_cpu, cpuset); - SCX_BUG_ON(sched_setaffinity(0, sizeof(cpuset), cpuset), + SCX_BUG_ON(sched_setaffinity(0, sizeof(*cpuset), cpuset), "Failed to affinitize to central CPU %d (max %d)", skel->rodata->central_cpu, skel->rodata->nr_cpu_ids - 1); CPU_FREE(cpuset); diff --git a/tools/testing/selftests/bpf/prog_tests/socket_helpers.h b/tools/testing/selftests/bpf/prog_tests/socket_helpers.h new file mode 100644 index 000000000000..1bdfb79ef009 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/socket_helpers.h @@ -0,0 +1,394 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __SOCKET_HELPERS__ +#define __SOCKET_HELPERS__ + +#include <linux/vm_sockets.h> + +/* include/linux/net.h */ +#define SOCK_TYPE_MASK 0xf + +#define IO_TIMEOUT_SEC 30 +#define MAX_STRERR_LEN 256 + +/* workaround for older vm_sockets.h */ +#ifndef VMADDR_CID_LOCAL +#define VMADDR_CID_LOCAL 1 +#endif + +/* include/linux/cleanup.h */ +#define __get_and_null(p, nullvalue) \ + ({ \ + __auto_type __ptr = &(p); \ + __auto_type __val = *__ptr; \ + *__ptr = nullvalue; \ + __val; \ + }) + +#define take_fd(fd) __get_and_null(fd, -EBADF) + +/* Wrappers that fail the test on error and report it. */ + +#define _FAIL(errnum, fmt...) \ + ({ \ + error_at_line(0, (errnum), __func__, __LINE__, fmt); \ + CHECK_FAIL(true); \ + }) +#define FAIL(fmt...) _FAIL(0, fmt) +#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt) +#define FAIL_LIBBPF(err, msg) \ + ({ \ + char __buf[MAX_STRERR_LEN]; \ + libbpf_strerror((err), __buf, sizeof(__buf)); \ + FAIL("%s: %s", (msg), __buf); \ + }) + + +#define xaccept_nonblock(fd, addr, len) \ + ({ \ + int __ret = \ + accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC); \ + if (__ret == -1) \ + FAIL_ERRNO("accept"); \ + __ret; \ + }) + +#define xbind(fd, addr, len) \ + ({ \ + int __ret = bind((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("bind"); \ + __ret; \ + }) + +#define xclose(fd) \ + ({ \ + int __ret = close((fd)); \ + if (__ret == -1) \ + FAIL_ERRNO("close"); \ + __ret; \ + }) + +#define xconnect(fd, addr, len) \ + ({ \ + int __ret = connect((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("connect"); \ + __ret; \ + }) + +#define xgetsockname(fd, addr, len) \ + ({ \ + int __ret = getsockname((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("getsockname"); \ + __ret; \ + }) + +#define xgetsockopt(fd, level, name, val, len) \ + ({ \ + int __ret = getsockopt((fd), (level), (name), (val), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("getsockopt(" #name ")"); \ + __ret; \ + }) + +#define xlisten(fd, backlog) \ + ({ \ + int __ret = listen((fd), (backlog)); \ + if (__ret == -1) \ + FAIL_ERRNO("listen"); \ + __ret; \ + }) + +#define xsetsockopt(fd, level, name, val, len) \ + ({ \ + int __ret = setsockopt((fd), (level), (name), (val), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("setsockopt(" #name ")"); \ + __ret; \ + }) + +#define xsend(fd, buf, len, flags) \ + ({ \ + ssize_t __ret = send((fd), (buf), (len), (flags)); \ + if (__ret == -1) \ + FAIL_ERRNO("send"); \ + __ret; \ + }) + +#define xrecv_nonblock(fd, buf, len, flags) \ + ({ \ + ssize_t __ret = recv_timeout((fd), (buf), (len), (flags), \ + IO_TIMEOUT_SEC); \ + if (__ret == -1) \ + FAIL_ERRNO("recv"); \ + __ret; \ + }) + +#define xsocket(family, sotype, flags) \ + ({ \ + int __ret = socket(family, sotype, flags); \ + if (__ret == -1) \ + FAIL_ERRNO("socket"); \ + __ret; \ + }) + +static inline void close_fd(int *fd) +{ + if (*fd >= 0) + xclose(*fd); +} + +#define __close_fd __attribute__((cleanup(close_fd))) + +static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss) +{ + return (struct sockaddr *)ss; +} + +static inline void init_addr_loopback4(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss)); + + addr4->sin_family = AF_INET; + addr4->sin_port = 0; + addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); + *len = sizeof(*addr4); +} + +static inline void init_addr_loopback6(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss)); + + addr6->sin6_family = AF_INET6; + addr6->sin6_port = 0; + addr6->sin6_addr = in6addr_loopback; + *len = sizeof(*addr6); +} + +static inline void init_addr_loopback_vsock(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss)); + + addr->svm_family = AF_VSOCK; + addr->svm_port = VMADDR_PORT_ANY; + addr->svm_cid = VMADDR_CID_LOCAL; + *len = sizeof(*addr); +} + +static inline void init_addr_loopback(int family, struct sockaddr_storage *ss, + socklen_t *len) +{ + switch (family) { + case AF_INET: + init_addr_loopback4(ss, len); + return; + case AF_INET6: + init_addr_loopback6(ss, len); + return; + case AF_VSOCK: + init_addr_loopback_vsock(ss, len); + return; + default: + FAIL("unsupported address family %d", family); + } +} + +static inline int enable_reuseport(int s, int progfd) +{ + int err, one = 1; + + err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); + if (err) + return -1; + err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd, + sizeof(progfd)); + if (err) + return -1; + + return 0; +} + +static inline int socket_loopback_reuseport(int family, int sotype, int progfd) +{ + struct sockaddr_storage addr; + socklen_t len = 0; + int err, s; + + init_addr_loopback(family, &addr, &len); + + s = xsocket(family, sotype, 0); + if (s == -1) + return -1; + + if (progfd >= 0) + enable_reuseport(s, progfd); + + err = xbind(s, sockaddr(&addr), len); + if (err) + goto close; + + if (sotype & SOCK_DGRAM) + return s; + + err = xlisten(s, SOMAXCONN); + if (err) + goto close; + + return s; +close: + xclose(s); + return -1; +} + +static inline int socket_loopback(int family, int sotype) +{ + return socket_loopback_reuseport(family, sotype, -1); +} + +static inline int poll_connect(int fd, unsigned int timeout_sec) +{ + struct timeval timeout = { .tv_sec = timeout_sec }; + fd_set wfds; + int r, eval; + socklen_t esize = sizeof(eval); + + FD_ZERO(&wfds); + FD_SET(fd, &wfds); + + r = select(fd + 1, NULL, &wfds, NULL, &timeout); + if (r == 0) + errno = ETIME; + if (r != 1) + return -1; + + if (getsockopt(fd, SOL_SOCKET, SO_ERROR, &eval, &esize) < 0) + return -1; + if (eval != 0) { + errno = eval; + return -1; + } + + return 0; +} + +static inline int poll_read(int fd, unsigned int timeout_sec) +{ + struct timeval timeout = { .tv_sec = timeout_sec }; + fd_set rfds; + int r; + + FD_ZERO(&rfds); + FD_SET(fd, &rfds); + + r = select(fd + 1, &rfds, NULL, NULL, &timeout); + if (r == 0) + errno = ETIME; + + return r == 1 ? 0 : -1; +} + +static inline int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len, + unsigned int timeout_sec) +{ + if (poll_read(fd, timeout_sec)) + return -1; + + return accept(fd, addr, len); +} + +static inline int recv_timeout(int fd, void *buf, size_t len, int flags, + unsigned int timeout_sec) +{ + if (poll_read(fd, timeout_sec)) + return -1; + + return recv(fd, buf, len, flags); +} + + +static inline int create_pair(int family, int sotype, int *p0, int *p1) +{ + __close_fd int s, c = -1, p = -1; + struct sockaddr_storage addr; + socklen_t len = sizeof(addr); + int err; + + s = socket_loopback(family, sotype); + if (s < 0) + return s; + + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + return err; + + c = xsocket(family, sotype, 0); + if (c < 0) + return c; + + err = connect(c, sockaddr(&addr), len); + if (err) { + if (errno != EINPROGRESS) { + FAIL_ERRNO("connect"); + return err; + } + + err = poll_connect(c, IO_TIMEOUT_SEC); + if (err) { + FAIL_ERRNO("poll_connect"); + return err; + } + } + + switch (sotype & SOCK_TYPE_MASK) { + case SOCK_DGRAM: + err = xgetsockname(c, sockaddr(&addr), &len); + if (err) + return err; + + err = xconnect(s, sockaddr(&addr), len); + if (err) + return err; + + *p0 = take_fd(s); + break; + case SOCK_STREAM: + case SOCK_SEQPACKET: + p = xaccept_nonblock(s, NULL, NULL); + if (p < 0) + return p; + + *p0 = take_fd(p); + break; + default: + FAIL("Unsupported socket type %#x", sotype); + return -EOPNOTSUPP; + } + + *p1 = take_fd(c); + return 0; +} + +static inline int create_socket_pairs(int family, int sotype, int *c0, int *c1, + int *p0, int *p1) +{ + int err; + + err = create_pair(family, sotype, c0, p0); + if (err) + return err; + + err = create_pair(family, sotype, c1, p1); + if (err) { + close(*c0); + close(*p0); + } + + return err; +} + +#endif // __SOCKET_HELPERS__ diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 248754296d97..884ad87783d5 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -12,6 +12,7 @@ #include "test_sockmap_progs_query.skel.h" #include "test_sockmap_pass_prog.skel.h" #include "test_sockmap_drop_prog.skel.h" +#include "test_sockmap_change_tail.skel.h" #include "bpf_iter_sockmap.skel.h" #include "sockmap_helpers.h" @@ -643,6 +644,54 @@ out: test_sockmap_drop_prog__destroy(drop); } +static void test_sockmap_skb_verdict_change_tail(void) +{ + struct test_sockmap_change_tail *skel; + int err, map, verdict; + int c1, p1, sent, recvd; + int zero = 0; + char buf[2]; + + skel = test_sockmap_change_tail__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + verdict = bpf_program__fd(skel->progs.prog_skb_verdict); + map = bpf_map__fd(skel->maps.sock_map_rx); + + err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach")) + goto out; + err = create_pair(AF_INET, SOCK_STREAM, &c1, &p1); + if (!ASSERT_OK(err, "create_pair()")) + goto out; + err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(c1)")) + goto out_close; + sent = xsend(p1, "Tr", 2, 0); + ASSERT_EQ(sent, 2, "xsend(p1)"); + recvd = recv(c1, buf, 2, 0); + ASSERT_EQ(recvd, 1, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret"); + + sent = xsend(p1, "G", 1, 0); + ASSERT_EQ(sent, 1, "xsend(p1)"); + recvd = recv(c1, buf, 2, 0); + ASSERT_EQ(recvd, 2, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret"); + + sent = xsend(p1, "E", 1, 0); + ASSERT_EQ(sent, 1, "xsend(p1)"); + recvd = recv(c1, buf, 1, 0); + ASSERT_EQ(recvd, 1, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret"); + +out_close: + close(c1); + close(p1); +out: + test_sockmap_change_tail__destroy(skel); +} + static void test_sockmap_skb_verdict_peek_helper(int map) { int err, c1, p1, zero = 0, sent, recvd, avail; @@ -1058,6 +1107,8 @@ void test_sockmap_basic(void) test_sockmap_skb_verdict_fionread(true); if (test__start_subtest("sockmap skb_verdict fionread on drop")) test_sockmap_skb_verdict_fionread(false); + if (test__start_subtest("sockmap skb_verdict change tail")) + test_sockmap_skb_verdict_change_tail(); if (test__start_subtest("sockmap skb_verdict msg_f_peek")) test_sockmap_skb_verdict_peek(); if (test__start_subtest("sockmap skb_verdict msg_f_peek with link")) diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h index 38e35c72bdaa..3e5571dd578d 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h @@ -1,139 +1,12 @@ #ifndef __SOCKMAP_HELPERS__ #define __SOCKMAP_HELPERS__ -#include <linux/vm_sockets.h> +#include "socket_helpers.h" -/* include/linux/net.h */ -#define SOCK_TYPE_MASK 0xf - -#define IO_TIMEOUT_SEC 30 -#define MAX_STRERR_LEN 256 #define MAX_TEST_NAME 80 -/* workaround for older vm_sockets.h */ -#ifndef VMADDR_CID_LOCAL -#define VMADDR_CID_LOCAL 1 -#endif - #define __always_unused __attribute__((__unused__)) -/* include/linux/cleanup.h */ -#define __get_and_null(p, nullvalue) \ - ({ \ - __auto_type __ptr = &(p); \ - __auto_type __val = *__ptr; \ - *__ptr = nullvalue; \ - __val; \ - }) - -#define take_fd(fd) __get_and_null(fd, -EBADF) - -#define _FAIL(errnum, fmt...) \ - ({ \ - error_at_line(0, (errnum), __func__, __LINE__, fmt); \ - CHECK_FAIL(true); \ - }) -#define FAIL(fmt...) _FAIL(0, fmt) -#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt) -#define FAIL_LIBBPF(err, msg) \ - ({ \ - char __buf[MAX_STRERR_LEN]; \ - libbpf_strerror((err), __buf, sizeof(__buf)); \ - FAIL("%s: %s", (msg), __buf); \ - }) - -/* Wrappers that fail the test on error and report it. */ - -#define xaccept_nonblock(fd, addr, len) \ - ({ \ - int __ret = \ - accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC); \ - if (__ret == -1) \ - FAIL_ERRNO("accept"); \ - __ret; \ - }) - -#define xbind(fd, addr, len) \ - ({ \ - int __ret = bind((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("bind"); \ - __ret; \ - }) - -#define xclose(fd) \ - ({ \ - int __ret = close((fd)); \ - if (__ret == -1) \ - FAIL_ERRNO("close"); \ - __ret; \ - }) - -#define xconnect(fd, addr, len) \ - ({ \ - int __ret = connect((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("connect"); \ - __ret; \ - }) - -#define xgetsockname(fd, addr, len) \ - ({ \ - int __ret = getsockname((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("getsockname"); \ - __ret; \ - }) - -#define xgetsockopt(fd, level, name, val, len) \ - ({ \ - int __ret = getsockopt((fd), (level), (name), (val), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("getsockopt(" #name ")"); \ - __ret; \ - }) - -#define xlisten(fd, backlog) \ - ({ \ - int __ret = listen((fd), (backlog)); \ - if (__ret == -1) \ - FAIL_ERRNO("listen"); \ - __ret; \ - }) - -#define xsetsockopt(fd, level, name, val, len) \ - ({ \ - int __ret = setsockopt((fd), (level), (name), (val), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("setsockopt(" #name ")"); \ - __ret; \ - }) - -#define xsend(fd, buf, len, flags) \ - ({ \ - ssize_t __ret = send((fd), (buf), (len), (flags)); \ - if (__ret == -1) \ - FAIL_ERRNO("send"); \ - __ret; \ - }) - -#define xrecv_nonblock(fd, buf, len, flags) \ - ({ \ - ssize_t __ret = recv_timeout((fd), (buf), (len), (flags), \ - IO_TIMEOUT_SEC); \ - if (__ret == -1) \ - FAIL_ERRNO("recv"); \ - __ret; \ - }) - -#define xsocket(family, sotype, flags) \ - ({ \ - int __ret = socket(family, sotype, flags); \ - if (__ret == -1) \ - FAIL_ERRNO("socket"); \ - __ret; \ - }) - #define xbpf_map_delete_elem(fd, key) \ ({ \ int __ret = bpf_map_delete_elem((fd), (key)); \ @@ -193,130 +66,6 @@ __ret; \ }) -static inline void close_fd(int *fd) -{ - if (*fd >= 0) - xclose(*fd); -} - -#define __close_fd __attribute__((cleanup(close_fd))) - -static inline int poll_connect(int fd, unsigned int timeout_sec) -{ - struct timeval timeout = { .tv_sec = timeout_sec }; - fd_set wfds; - int r, eval; - socklen_t esize = sizeof(eval); - - FD_ZERO(&wfds); - FD_SET(fd, &wfds); - - r = select(fd + 1, NULL, &wfds, NULL, &timeout); - if (r == 0) - errno = ETIME; - if (r != 1) - return -1; - - if (getsockopt(fd, SOL_SOCKET, SO_ERROR, &eval, &esize) < 0) - return -1; - if (eval != 0) { - errno = eval; - return -1; - } - - return 0; -} - -static inline int poll_read(int fd, unsigned int timeout_sec) -{ - struct timeval timeout = { .tv_sec = timeout_sec }; - fd_set rfds; - int r; - - FD_ZERO(&rfds); - FD_SET(fd, &rfds); - - r = select(fd + 1, &rfds, NULL, NULL, &timeout); - if (r == 0) - errno = ETIME; - - return r == 1 ? 0 : -1; -} - -static inline int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len, - unsigned int timeout_sec) -{ - if (poll_read(fd, timeout_sec)) - return -1; - - return accept(fd, addr, len); -} - -static inline int recv_timeout(int fd, void *buf, size_t len, int flags, - unsigned int timeout_sec) -{ - if (poll_read(fd, timeout_sec)) - return -1; - - return recv(fd, buf, len, flags); -} - -static inline void init_addr_loopback4(struct sockaddr_storage *ss, - socklen_t *len) -{ - struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss)); - - addr4->sin_family = AF_INET; - addr4->sin_port = 0; - addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); - *len = sizeof(*addr4); -} - -static inline void init_addr_loopback6(struct sockaddr_storage *ss, - socklen_t *len) -{ - struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss)); - - addr6->sin6_family = AF_INET6; - addr6->sin6_port = 0; - addr6->sin6_addr = in6addr_loopback; - *len = sizeof(*addr6); -} - -static inline void init_addr_loopback_vsock(struct sockaddr_storage *ss, - socklen_t *len) -{ - struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss)); - - addr->svm_family = AF_VSOCK; - addr->svm_port = VMADDR_PORT_ANY; - addr->svm_cid = VMADDR_CID_LOCAL; - *len = sizeof(*addr); -} - -static inline void init_addr_loopback(int family, struct sockaddr_storage *ss, - socklen_t *len) -{ - switch (family) { - case AF_INET: - init_addr_loopback4(ss, len); - return; - case AF_INET6: - init_addr_loopback6(ss, len); - return; - case AF_VSOCK: - init_addr_loopback_vsock(ss, len); - return; - default: - FAIL("unsupported address family %d", family); - } -} - -static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss) -{ - return (struct sockaddr *)ss; -} - static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2) { u64 value; @@ -334,136 +83,4 @@ static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2) return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); } -static inline int enable_reuseport(int s, int progfd) -{ - int err, one = 1; - - err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); - if (err) - return -1; - err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd, - sizeof(progfd)); - if (err) - return -1; - - return 0; -} - -static inline int socket_loopback_reuseport(int family, int sotype, int progfd) -{ - struct sockaddr_storage addr; - socklen_t len = 0; - int err, s; - - init_addr_loopback(family, &addr, &len); - - s = xsocket(family, sotype, 0); - if (s == -1) - return -1; - - if (progfd >= 0) - enable_reuseport(s, progfd); - - err = xbind(s, sockaddr(&addr), len); - if (err) - goto close; - - if (sotype & SOCK_DGRAM) - return s; - - err = xlisten(s, SOMAXCONN); - if (err) - goto close; - - return s; -close: - xclose(s); - return -1; -} - -static inline int socket_loopback(int family, int sotype) -{ - return socket_loopback_reuseport(family, sotype, -1); -} - -static inline int create_pair(int family, int sotype, int *p0, int *p1) -{ - __close_fd int s, c = -1, p = -1; - struct sockaddr_storage addr; - socklen_t len = sizeof(addr); - int err; - - s = socket_loopback(family, sotype); - if (s < 0) - return s; - - err = xgetsockname(s, sockaddr(&addr), &len); - if (err) - return err; - - c = xsocket(family, sotype, 0); - if (c < 0) - return c; - - err = connect(c, sockaddr(&addr), len); - if (err) { - if (errno != EINPROGRESS) { - FAIL_ERRNO("connect"); - return err; - } - - err = poll_connect(c, IO_TIMEOUT_SEC); - if (err) { - FAIL_ERRNO("poll_connect"); - return err; - } - } - - switch (sotype & SOCK_TYPE_MASK) { - case SOCK_DGRAM: - err = xgetsockname(c, sockaddr(&addr), &len); - if (err) - return err; - - err = xconnect(s, sockaddr(&addr), len); - if (err) - return err; - - *p0 = take_fd(s); - break; - case SOCK_STREAM: - case SOCK_SEQPACKET: - p = xaccept_nonblock(s, NULL, NULL); - if (p < 0) - return p; - - *p0 = take_fd(p); - break; - default: - FAIL("Unsupported socket type %#x", sotype); - return -EOPNOTSUPP; - } - - *p1 = take_fd(c); - return 0; -} - -static inline int create_socket_pairs(int family, int sotype, int *c0, int *c1, - int *p0, int *p1) -{ - int err; - - err = create_pair(family, sotype, c0, p0); - if (err) - return err; - - err = create_pair(family, sotype, c1, p1); - if (err) { - close(*c0); - close(*p0); - } - - return err; -} - #endif // __SOCKMAP_HELPERS__ diff --git a/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c b/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c new file mode 100644 index 000000000000..74752233e779 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <error.h> +#include <test_progs.h> +#include <linux/pkt_cls.h> + +#include "test_tc_change_tail.skel.h" +#include "socket_helpers.h" + +#define LO_IFINDEX 1 + +void test_tc_change_tail(void) +{ + LIBBPF_OPTS(bpf_tcx_opts, tcx_opts); + struct test_tc_change_tail *skel = NULL; + struct bpf_link *link; + int c1, p1; + char buf[2]; + int ret; + + skel = test_tc_change_tail__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_tc_change_tail__open_and_load")) + return; + + link = bpf_program__attach_tcx(skel->progs.change_tail, LO_IFINDEX, + &tcx_opts); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_tcx")) + goto destroy; + + skel->links.change_tail = link; + ret = create_pair(AF_INET, SOCK_DGRAM, &c1, &p1); + if (!ASSERT_OK(ret, "create_pair")) + goto destroy; + + ret = xsend(p1, "Tr", 2, 0); + ASSERT_EQ(ret, 2, "xsend(p1)"); + ret = recv(c1, buf, 2, 0); + ASSERT_EQ(ret, 2, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret"); + + ret = xsend(p1, "G", 1, 0); + ASSERT_EQ(ret, 1, "xsend(p1)"); + ret = recv(c1, buf, 2, 0); + ASSERT_EQ(ret, 1, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret"); + + ret = xsend(p1, "E", 1, 0); + ASSERT_EQ(ret, 1, "xsend(p1)"); + ret = recv(c1, buf, 1, 0); + ASSERT_EQ(ret, 1, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret"); + + ret = xsend(p1, "Z", 1, 0); + ASSERT_EQ(ret, 1, "xsend(p1)"); + ret = recv(c1, buf, 1, 0); + ASSERT_EQ(ret, 1, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret"); + + close(c1); + close(p1); +destroy: + test_tc_change_tail__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c b/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c new file mode 100644 index 000000000000..2796dd8545eb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 ByteDance */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} sock_map_rx SEC(".maps"); + +long change_tail_ret = 1; + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + char *data, *data_end; + + bpf_skb_pull_data(skb, 1); + data = (char *)(unsigned long)skb->data; + data_end = (char *)(unsigned long)skb->data_end; + + if (data + 1 > data_end) + return SK_PASS; + + if (data[0] == 'T') { /* Trim the packet */ + change_tail_ret = bpf_skb_change_tail(skb, skb->len - 1, 0); + return SK_PASS; + } else if (data[0] == 'G') { /* Grow the packet */ + change_tail_ret = bpf_skb_change_tail(skb, skb->len + 1, 0); + return SK_PASS; + } else if (data[0] == 'E') { /* Error */ + change_tail_ret = bpf_skb_change_tail(skb, 65535, 0); + return SK_PASS; + } + return SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_change_tail.c b/tools/testing/selftests/bpf/progs/test_tc_change_tail.c new file mode 100644 index 000000000000..28edafe803f0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tc_change_tail.c @@ -0,0 +1,106 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/udp.h> +#include <linux/pkt_cls.h> + +long change_tail_ret = 1; + +static __always_inline struct iphdr *parse_ip_header(struct __sk_buff *skb, int *ip_proto) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + struct ethhdr *eth = data; + struct iphdr *iph; + + /* Verify Ethernet header */ + if ((void *)(data + sizeof(*eth)) > data_end) + return NULL; + + /* Skip Ethernet header to get to IP header */ + iph = (void *)(data + sizeof(struct ethhdr)); + + /* Verify IP header */ + if ((void *)(data + sizeof(struct ethhdr) + sizeof(*iph)) > data_end) + return NULL; + + /* Basic IP header validation */ + if (iph->version != 4) /* Only support IPv4 */ + return NULL; + + if (iph->ihl < 5) /* Minimum IP header length */ + return NULL; + + *ip_proto = iph->protocol; + return iph; +} + +static __always_inline struct udphdr *parse_udp_header(struct __sk_buff *skb, struct iphdr *iph) +{ + void *data_end = (void *)(long)skb->data_end; + void *hdr = (void *)iph; + struct udphdr *udp; + + /* Calculate UDP header position */ + udp = hdr + (iph->ihl * 4); + hdr = (void *)udp; + + /* Verify UDP header bounds */ + if ((void *)(hdr + sizeof(*udp)) > data_end) + return NULL; + + return udp; +} + +SEC("tc/ingress") +int change_tail(struct __sk_buff *skb) +{ + int len = skb->len; + struct udphdr *udp; + struct iphdr *iph; + void *data_end; + char *payload; + int ip_proto; + + bpf_skb_pull_data(skb, len); + + data_end = (void *)(long)skb->data_end; + iph = parse_ip_header(skb, &ip_proto); + if (!iph) + return TCX_PASS; + + if (ip_proto != IPPROTO_UDP) + return TCX_PASS; + + udp = parse_udp_header(skb, iph); + if (!udp) + return TCX_PASS; + + payload = (char *)udp + (sizeof(struct udphdr)); + if (payload + 1 > (char *)data_end) + return TCX_PASS; + + if (payload[0] == 'T') { /* Trim the packet */ + change_tail_ret = bpf_skb_change_tail(skb, len - 1, 0); + if (!change_tail_ret) + bpf_skb_change_tail(skb, len, 0); + return TCX_PASS; + } else if (payload[0] == 'G') { /* Grow the packet */ + change_tail_ret = bpf_skb_change_tail(skb, len + 1, 0); + if (!change_tail_ret) + bpf_skb_change_tail(skb, len, 0); + return TCX_PASS; + } else if (payload[0] == 'E') { /* Error */ + change_tail_ret = bpf_skb_change_tail(skb, 65535, 0); + return TCX_PASS; + } else if (payload[0] == 'Z') { /* Zero */ + change_tail_ret = bpf_skb_change_tail(skb, 0, 0); + return TCX_PASS; + } + return TCX_DROP; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/sdt.h b/tools/testing/selftests/bpf/sdt.h index ca0162b4dc57..1fcfa5160231 100644 --- a/tools/testing/selftests/bpf/sdt.h +++ b/tools/testing/selftests/bpf/sdt.h @@ -102,6 +102,8 @@ # define STAP_SDT_ARG_CONSTRAINT nZr # elif defined __arm__ # define STAP_SDT_ARG_CONSTRAINT g +# elif defined __loongarch__ +# define STAP_SDT_ARG_CONSTRAINT nmr # else # define STAP_SDT_ARG_CONSTRAINT nor # endif diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index 2d742fdac6b9..81943c6254e6 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -293,6 +293,10 @@ static int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *st return 0; } #else +# ifndef PROCMAP_QUERY_VMA_EXECUTABLE +# define PROCMAP_QUERY_VMA_EXECUTABLE 0x04 +# endif + static int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, size_t *offset, int *flags) { return -EOPNOTSUPP; diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index 03c1bdaed2c3..400a696a0d21 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -86,15 +86,15 @@ echo "" > test/cpuset.cpus # # If isolated CPUs have been reserved at boot time (as shown in -# cpuset.cpus.isolated), these isolated CPUs should be outside of CPUs 0-7 +# cpuset.cpus.isolated), these isolated CPUs should be outside of CPUs 0-8 # that will be used by this script for testing purpose. If not, some of -# the tests may fail incorrectly. These isolated CPUs will also be removed -# before being compared with the expected results. +# the tests may fail incorrectly. These pre-isolated CPUs should stay in +# an isolated state throughout the testing process for now. # BOOT_ISOLCPUS=$(cat $CGROUP2/cpuset.cpus.isolated) if [[ -n "$BOOT_ISOLCPUS" ]] then - [[ $(echo $BOOT_ISOLCPUS | sed -e "s/[,-].*//") -le 7 ]] && + [[ $(echo $BOOT_ISOLCPUS | sed -e "s/[,-].*//") -le 8 ]] && skip_test "Pre-isolated CPUs ($BOOT_ISOLCPUS) overlap CPUs to be tested" echo "Pre-isolated CPUs: $BOOT_ISOLCPUS" fi @@ -684,14 +684,18 @@ check_isolcpus() fi # + # Appending pre-isolated CPUs + # Even though CPU #8 isn't used for testing, it can't be pre-isolated + # to make appending those CPUs easier. + # + [[ -n "$BOOT_ISOLCPUS" ]] && { + EXPECT_VAL=${EXPECT_VAL:+${EXPECT_VAL},}${BOOT_ISOLCPUS} + EXPECT_VAL2=${EXPECT_VAL2:+${EXPECT_VAL2},}${BOOT_ISOLCPUS} + } + + # # Check cpuset.cpus.isolated cpumask # - if [[ -z "$BOOT_ISOLCPUS" ]] - then - ISOLCPUS=$(cat $ISCPUS) - else - ISOLCPUS=$(cat $ISCPUS | sed -e "s/,*$BOOT_ISOLCPUS//") - fi [[ "$EXPECT_VAL2" != "$ISOLCPUS" ]] && { # Take a 50ms pause and try again pause 0.05 @@ -731,8 +735,6 @@ check_isolcpus() fi done [[ "$ISOLCPUS" = *- ]] && ISOLCPUS=${ISOLCPUS}$LASTISOLCPU - [[ -n "BOOT_ISOLCPUS" ]] && - ISOLCPUS=$(echo $ISOLCPUS | sed -e "s/,*$BOOT_ISOLCPUS//") [[ "$EXPECT_VAL" = "$ISOLCPUS" ]] } @@ -836,8 +838,11 @@ run_state_test() # if available [[ -n "$ICPUS" ]] && { check_isolcpus $ICPUS - [[ $? -ne 0 ]] && test_fail $I "isolated CPU" \ - "Expect $ICPUS, get $ISOLCPUS instead" + [[ $? -ne 0 ]] && { + [[ -n "$BOOT_ISOLCPUS" ]] && ICPUS=${ICPUS},${BOOT_ISOLCPUS} + test_fail $I "isolated CPU" \ + "Expect $ICPUS, get $ISOLCPUS instead" + } } reset_cgroup_states # diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py index 30f29096e27c..38303da957ee 100755 --- a/tools/testing/selftests/drivers/net/queues.py +++ b/tools/testing/selftests/drivers/net/queues.py @@ -1,32 +1,37 @@ #!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 -from lib.py import ksft_run, ksft_exit, ksft_eq, KsftSkipEx -from lib.py import EthtoolFamily, NetdevFamily +from lib.py import ksft_disruptive, ksft_exit, ksft_run +from lib.py import ksft_eq, ksft_raises, KsftSkipEx +from lib.py import EthtoolFamily, NetdevFamily, NlError from lib.py import NetDrvEnv -from lib.py import cmd +from lib.py import cmd, defer, ip +import errno import glob -def sys_get_queues(ifname) -> int: - folders = glob.glob(f'/sys/class/net/{ifname}/queues/rx-*') +def sys_get_queues(ifname, qtype='rx') -> int: + folders = glob.glob(f'/sys/class/net/{ifname}/queues/{qtype}-*') return len(folders) -def nl_get_queues(cfg, nl): +def nl_get_queues(cfg, nl, qtype='rx'): queues = nl.queue_get({'ifindex': cfg.ifindex}, dump=True) if queues: - return len([q for q in queues if q['type'] == 'rx']) + return len([q for q in queues if q['type'] == qtype]) return None def get_queues(cfg, nl) -> None: - queues = nl_get_queues(cfg, nl) - if not queues: - raise KsftSkipEx('queue-get not supported by device') + snl = NetdevFamily(recv_size=4096) - expected = sys_get_queues(cfg.dev['ifname']) - ksft_eq(queues, expected) + for qtype in ['rx', 'tx']: + queues = nl_get_queues(cfg, snl, qtype) + if not queues: + raise KsftSkipEx('queue-get not supported by device') + + expected = sys_get_queues(cfg.dev['ifname'], qtype) + ksft_eq(queues, expected) def addremove_queues(cfg, nl) -> None: @@ -56,9 +61,27 @@ def addremove_queues(cfg, nl) -> None: ksft_eq(queues, expected) +@ksft_disruptive +def check_down(cfg, nl) -> None: + # Check the NAPI IDs before interface goes down and hides them + napis = nl.napi_get({'ifindex': cfg.ifindex}, dump=True) + + ip(f"link set dev {cfg.dev['ifname']} down") + defer(ip, f"link set dev {cfg.dev['ifname']} up") + + with ksft_raises(NlError) as cm: + nl.queue_get({'ifindex': cfg.ifindex, 'id': 0, 'type': 'rx'}) + ksft_eq(cm.exception.nl_msg.error, -errno.ENOENT) + + if napis: + with ksft_raises(NlError) as cm: + nl.napi_get({'id': napis[0]['id']}) + ksft_eq(cm.exception.nl_msg.error, -errno.ENOENT) + + def main() -> None: - with NetDrvEnv(__file__, queue_count=3) as cfg: - ksft_run([get_queues, addremove_queues], args=(cfg, NetdevFamily())) + with NetDrvEnv(__file__, queue_count=100) as cfg: + ksft_run([get_queues, addremove_queues, check_down], args=(cfg, NetdevFamily())) ksft_exit() diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py index 63e3c045a3b2..031ac9def6c0 100755 --- a/tools/testing/selftests/drivers/net/stats.py +++ b/tools/testing/selftests/drivers/net/stats.py @@ -110,6 +110,23 @@ def qstat_by_ifindex(cfg) -> None: ksft_ge(triple[1][key], triple[0][key], comment="bad key: " + key) ksft_ge(triple[2][key], triple[1][key], comment="bad key: " + key) + # Sanity check the dumps + queues = NetdevFamily(recv_size=4096).qstats_get({"scope": "queue"}, dump=True) + # Reformat the output into {ifindex: {rx: [id, id, ...], tx: [id, id, ...]}} + parsed = {} + for entry in queues: + ifindex = entry["ifindex"] + if ifindex not in parsed: + parsed[ifindex] = {"rx":[], "tx": []} + parsed[ifindex][entry["queue-type"]].append(entry['queue-id']) + # Now, validate + for ifindex, queues in parsed.items(): + for qtype in ['rx', 'tx']: + ksft_eq(len(queues[qtype]), len(set(queues[qtype])), + comment="repeated queue keys") + ksft_eq(len(queues[qtype]), max(queues[qtype]) + 1, + comment="missing queue keys") + # Test invalid dumps # 0 is invalid with ksft_raises(NlError) as cm: @@ -158,7 +175,7 @@ def check_down(cfg) -> None: def main() -> None: - with NetDrvEnv(__file__) as cfg: + with NetDrvEnv(__file__, queue_count=100) as cfg: ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex, check_down], args=(cfg, )) diff --git a/tools/testing/selftests/kvm/aarch64/set_id_regs.c b/tools/testing/selftests/kvm/aarch64/set_id_regs.c index a79b7f18452d..3a97c160b5fe 100644 --- a/tools/testing/selftests/kvm/aarch64/set_id_regs.c +++ b/tools/testing/selftests/kvm/aarch64/set_id_regs.c @@ -152,7 +152,6 @@ static const struct reg_ftr_bits ftr_id_aa64mmfr0_el1[] = { REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, BIGENDEL0, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, SNSMEM, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, BIGEND, 0), - REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, ASIDBITS, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, PARANGE, 0), REG_FTR_END, }; diff --git a/tools/testing/selftests/kvm/s390x/ucontrol_test.c b/tools/testing/selftests/kvm/s390x/ucontrol_test.c index 0c112319dab1..135ee22856cf 100644 --- a/tools/testing/selftests/kvm/s390x/ucontrol_test.c +++ b/tools/testing/selftests/kvm/s390x/ucontrol_test.c @@ -210,10 +210,13 @@ TEST_F(uc_kvm, uc_attr_mem_limit) struct kvm_device_attr attr = { .group = KVM_S390_VM_MEM_CTRL, .attr = KVM_S390_VM_MEM_LIMIT_SIZE, - .addr = (unsigned long)&limit, + .addr = (u64)&limit, }; int rc; + rc = ioctl(self->vm_fd, KVM_HAS_DEVICE_ATTR, &attr); + EXPECT_EQ(0, rc); + rc = ioctl(self->vm_fd, KVM_GET_DEVICE_ATTR, &attr); EXPECT_EQ(0, rc); EXPECT_EQ(~0UL, limit); @@ -635,4 +638,171 @@ TEST_F(uc_kvm, uc_skey) uc_assert_diag44(self); } +static char uc_flic_b[PAGE_SIZE]; +static struct kvm_s390_io_adapter uc_flic_ioa = { .id = 0 }; +static struct kvm_s390_io_adapter_req uc_flic_ioam = { .id = 0 }; +static struct kvm_s390_ais_req uc_flic_asim = { .isc = 0 }; +static struct kvm_s390_ais_all uc_flic_asima = { .simm = 0 }; +static struct uc_flic_attr_test { + char *name; + struct kvm_device_attr a; + int hasrc; + int geterrno; + int seterrno; +} uc_flic_attr_tests[] = { + { + .name = "KVM_DEV_FLIC_GET_ALL_IRQS", + .seterrno = EINVAL, + .a = { + .group = KVM_DEV_FLIC_GET_ALL_IRQS, + .addr = (u64)&uc_flic_b, + .attr = PAGE_SIZE, + }, + }, + { + .name = "KVM_DEV_FLIC_ENQUEUE", + .geterrno = EINVAL, + .a = { .group = KVM_DEV_FLIC_ENQUEUE, }, + }, + { + .name = "KVM_DEV_FLIC_CLEAR_IRQS", + .geterrno = EINVAL, + .a = { .group = KVM_DEV_FLIC_CLEAR_IRQS, }, + }, + { + .name = "KVM_DEV_FLIC_ADAPTER_REGISTER", + .geterrno = EINVAL, + .a = { + .group = KVM_DEV_FLIC_ADAPTER_REGISTER, + .addr = (u64)&uc_flic_ioa, + }, + }, + { + .name = "KVM_DEV_FLIC_ADAPTER_MODIFY", + .geterrno = EINVAL, + .seterrno = EINVAL, + .a = { + .group = KVM_DEV_FLIC_ADAPTER_MODIFY, + .addr = (u64)&uc_flic_ioam, + .attr = sizeof(uc_flic_ioam), + }, + }, + { + .name = "KVM_DEV_FLIC_CLEAR_IO_IRQ", + .geterrno = EINVAL, + .seterrno = EINVAL, + .a = { + .group = KVM_DEV_FLIC_CLEAR_IO_IRQ, + .attr = 32, + }, + }, + { + .name = "KVM_DEV_FLIC_AISM", + .geterrno = EINVAL, + .seterrno = ENOTSUP, + .a = { + .group = KVM_DEV_FLIC_AISM, + .addr = (u64)&uc_flic_asim, + }, + }, + { + .name = "KVM_DEV_FLIC_AIRQ_INJECT", + .geterrno = EINVAL, + .a = { .group = KVM_DEV_FLIC_AIRQ_INJECT, }, + }, + { + .name = "KVM_DEV_FLIC_AISM_ALL", + .geterrno = ENOTSUP, + .seterrno = ENOTSUP, + .a = { + .group = KVM_DEV_FLIC_AISM_ALL, + .addr = (u64)&uc_flic_asima, + .attr = sizeof(uc_flic_asima), + }, + }, + { + .name = "KVM_DEV_FLIC_APF_ENABLE", + .geterrno = EINVAL, + .seterrno = EINVAL, + .a = { .group = KVM_DEV_FLIC_APF_ENABLE, }, + }, + { + .name = "KVM_DEV_FLIC_APF_DISABLE_WAIT", + .geterrno = EINVAL, + .seterrno = EINVAL, + .a = { .group = KVM_DEV_FLIC_APF_DISABLE_WAIT, }, + }, +}; + +TEST_F(uc_kvm, uc_flic_attrs) +{ + struct kvm_create_device cd = { .type = KVM_DEV_TYPE_FLIC }; + struct kvm_device_attr attr; + u64 value; + int rc, i; + + rc = ioctl(self->vm_fd, KVM_CREATE_DEVICE, &cd); + ASSERT_EQ(0, rc) TH_LOG("create device failed with err %s (%i)", + strerror(errno), errno); + + for (i = 0; i < ARRAY_SIZE(uc_flic_attr_tests); i++) { + TH_LOG("test %s", uc_flic_attr_tests[i].name); + attr = (struct kvm_device_attr) { + .group = uc_flic_attr_tests[i].a.group, + .attr = uc_flic_attr_tests[i].a.attr, + .addr = uc_flic_attr_tests[i].a.addr, + }; + if (attr.addr == 0) + attr.addr = (u64)&value; + + rc = ioctl(cd.fd, KVM_HAS_DEVICE_ATTR, &attr); + EXPECT_EQ(uc_flic_attr_tests[i].hasrc, !!rc) + TH_LOG("expected dev attr missing %s", + uc_flic_attr_tests[i].name); + + rc = ioctl(cd.fd, KVM_GET_DEVICE_ATTR, &attr); + EXPECT_EQ(!!uc_flic_attr_tests[i].geterrno, !!rc) + TH_LOG("get dev attr rc not expected on %s %s (%i)", + uc_flic_attr_tests[i].name, + strerror(errno), errno); + if (uc_flic_attr_tests[i].geterrno) + EXPECT_EQ(uc_flic_attr_tests[i].geterrno, errno) + TH_LOG("get dev attr errno not expected on %s %s (%i)", + uc_flic_attr_tests[i].name, + strerror(errno), errno); + + rc = ioctl(cd.fd, KVM_SET_DEVICE_ATTR, &attr); + EXPECT_EQ(!!uc_flic_attr_tests[i].seterrno, !!rc) + TH_LOG("set sev attr rc not expected on %s %s (%i)", + uc_flic_attr_tests[i].name, + strerror(errno), errno); + if (uc_flic_attr_tests[i].seterrno) + EXPECT_EQ(uc_flic_attr_tests[i].seterrno, errno) + TH_LOG("set dev attr errno not expected on %s %s (%i)", + uc_flic_attr_tests[i].name, + strerror(errno), errno); + } + + close(cd.fd); +} + +TEST_F(uc_kvm, uc_set_gsi_routing) +{ + struct kvm_irq_routing *routing = kvm_gsi_routing_create(); + struct kvm_irq_routing_entry ue = { + .type = KVM_IRQ_ROUTING_S390_ADAPTER, + .gsi = 1, + .u.adapter = (struct kvm_irq_routing_s390_adapter) { + .ind_addr = 0, + }, + }; + int rc; + + routing->entries[0] = ue; + routing->nr = 1; + rc = ioctl(self->vm_fd, KVM_SET_GSI_ROUTING, routing); + ASSERT_EQ(-1, rc) TH_LOG("err %s (%i)", strerror(errno), errno); + ASSERT_EQ(EINVAL, errno) TH_LOG("err %s (%i)", strerror(errno), errno); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index 95af2d78fd31..c0c53451a16d 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -9,6 +9,7 @@ #include <fcntl.h> #include <linux/memfd.h> #include <sched.h> +#include <stdbool.h> #include <stdio.h> #include <stdlib.h> #include <signal.h> @@ -281,6 +282,24 @@ static void *mfd_assert_mmap_shared(int fd) return p; } +static void *mfd_assert_mmap_read_shared(int fd) +{ + void *p; + + p = mmap(NULL, + mfd_def_size, + PROT_READ, + MAP_SHARED, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + + return p; +} + static void *mfd_assert_mmap_private(int fd) { void *p; @@ -979,6 +998,30 @@ static void test_seal_future_write(void) close(fd); } +static void test_seal_write_map_read_shared(void) +{ + int fd; + void *p; + + printf("%s SEAL-WRITE-MAP-READ\n", memfd_str); + + fd = mfd_assert_new("kern_memfd_seal_write_map_read", + mfd_def_size, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + + mfd_assert_add_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_WRITE); + + p = mfd_assert_mmap_read_shared(fd); + + mfd_assert_read(fd); + mfd_assert_read_shared(fd); + mfd_fail_write(fd); + + munmap(p, mfd_def_size); + close(fd); +} + /* * Test SEAL_SHRINK * Test whether SEAL_SHRINK actually prevents shrinking @@ -1557,6 +1600,11 @@ static void test_share_fork(char *banner, char *b_suffix) close(fd); } +static bool pid_ns_supported(void) +{ + return access("/proc/self/ns/pid", F_OK) == 0; +} + int main(int argc, char **argv) { pid_t pid; @@ -1587,12 +1635,17 @@ int main(int argc, char **argv) test_seal_write(); test_seal_future_write(); + test_seal_write_map_read_shared(); test_seal_shrink(); test_seal_grow(); test_seal_resize(); - test_sysctl_simple(); - test_sysctl_nested(); + if (pid_ns_supported()) { + test_sysctl_simple(); + test_sysctl_nested(); + } else { + printf("PID namespaces are not supported; skipping sysctl tests\n"); + } test_share_dup("SHARE-DUP", ""); test_share_mmap("SHARE-MMAP", ""); diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index 32c6ccc2a6be..1238e1c5aae1 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -758,7 +758,7 @@ static void do_run_with_base_page(test_fn fn, bool swapout) } /* Populate a base page. */ - memset(mem, 0, pagesize); + memset(mem, 1, pagesize); if (swapout) { madvise(mem, pagesize, MADV_PAGEOUT); @@ -824,12 +824,12 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run, size_t thpsize) * Try to populate a THP. Touch the first sub-page and test if * we get the last sub-page populated automatically. */ - mem[0] = 0; + mem[0] = 1; if (!pagemap_is_populated(pagemap_fd, mem + thpsize - pagesize)) { ksft_test_result_skip("Did not get a THP populated\n"); goto munmap; } - memset(mem, 0, thpsize); + memset(mem, 1, thpsize); size = thpsize; switch (thp_run) { @@ -1012,7 +1012,7 @@ static void run_with_hugetlb(test_fn fn, const char *desc, size_t hugetlbsize) } /* Populate an huge page. */ - memset(mem, 0, hugetlbsize); + memset(mem, 1, hugetlbsize); /* * We need a total of two hugetlb pages to handle COW/unsharing diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index c35548767756..ecd34f364125 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -7,7 +7,6 @@ ALL_TESTS="standalone vlan_unaware_bridge vlan_aware_bridge test_vlan \ NUM_NETIFS=2 PING_COUNT=1 REQUIRE_MTOOLS=yes -REQUIRE_MZ=no source lib.sh diff --git a/tools/testing/selftests/net/lib/py/ynl.py b/tools/testing/selftests/net/lib/py/ynl.py index a0d689d58c57..076a7e8dc3eb 100644 --- a/tools/testing/selftests/net/lib/py/ynl.py +++ b/tools/testing/selftests/net/lib/py/ynl.py @@ -32,23 +32,23 @@ except ModuleNotFoundError as e: # Set schema='' to avoid jsonschema validation, it's slow # class EthtoolFamily(YnlFamily): - def __init__(self): + def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('ethtool.yaml')).as_posix(), - schema='') + schema='', recv_size=recv_size) class RtnlFamily(YnlFamily): - def __init__(self): + def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('rt_link.yaml')).as_posix(), - schema='') + schema='', recv_size=recv_size) class NetdevFamily(YnlFamily): - def __init__(self): + def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('netdev.yaml')).as_posix(), - schema='') + schema='', recv_size=recv_size) class NetshaperFamily(YnlFamily): - def __init__(self): + def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('net_shaper.yaml')).as_posix(), - schema='') + schema='', recv_size=recv_size) diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index cc0bfae2bafa..960e1ab4dd04 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -171,8 +171,10 @@ ovs_add_netns_and_veths () { ovs_add_if "$1" "$2" "$4" -u || return 1 fi - [ $TRACING -eq 1 ] && ovs_netns_spawn_daemon "$1" "$ns" \ - tcpdump -i any -s 65535 + if [ $TRACING -eq 1 ]; then + ovs_netns_spawn_daemon "$1" "$3" tcpdump -l -i any -s 6553 + ovs_wait grep -q "listening on any" ${ovs_dir}/stderr + fi return 0 } diff --git a/tools/testing/selftests/riscv/abi/pointer_masking.c b/tools/testing/selftests/riscv/abi/pointer_masking.c index dee41b7ee3e3..059d2e87eb1f 100644 --- a/tools/testing/selftests/riscv/abi/pointer_masking.c +++ b/tools/testing/selftests/riscv/abi/pointer_masking.c @@ -185,8 +185,20 @@ static void test_fork_exec(void) } } +static bool pwrite_wrapper(int fd, void *buf, size_t count, const char *msg) +{ + int ret = pwrite(fd, buf, count, 0); + + if (ret != count) { + ksft_perror(msg); + return false; + } + return true; +} + static void test_tagged_addr_abi_sysctl(void) { + char *err_pwrite_msg = "failed to write to /proc/sys/abi/tagged_addr_disabled\n"; char value; int fd; @@ -200,14 +212,18 @@ static void test_tagged_addr_abi_sysctl(void) } value = '1'; - pwrite(fd, &value, 1, 0); - ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == -EINVAL, - "sysctl disabled\n"); + if (!pwrite_wrapper(fd, &value, 1, "write '1'")) + ksft_test_result_fail(err_pwrite_msg); + else + ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == -EINVAL, + "sysctl disabled\n"); value = '0'; - pwrite(fd, &value, 1, 0); - ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == 0, - "sysctl enabled\n"); + if (!pwrite_wrapper(fd, &value, 1, "write '0'")) + ksft_test_result_fail(err_pwrite_msg); + else + ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == 0, + "sysctl enabled\n"); set_tagged_addr_ctrl(0, false); diff --git a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c b/tools/testing/selftests/riscv/vector/v_initval_nolibc.c index 1dd94197da30..6174ffe016dc 100644 --- a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c +++ b/tools/testing/selftests/riscv/vector/v_initval_nolibc.c @@ -25,6 +25,8 @@ int main(void) unsigned long vl; char *datap, *tmp; + ksft_set_plan(1); + datap = malloc(MAX_VSIZE); if (!datap) { ksft_test_result_fail("fail to allocate memory for size = %d\n", MAX_VSIZE); @@ -63,6 +65,8 @@ int main(void) } free(datap); + + ksft_test_result_pass("tests for v_initval_nolibc pass\n"); ksft_exit_pass(); return 0; } diff --git a/tools/testing/selftests/riscv/vector/vstate_prctl.c b/tools/testing/selftests/riscv/vector/vstate_prctl.c index 895177f6bf4c..40b3bffcbb40 100644 --- a/tools/testing/selftests/riscv/vector/vstate_prctl.c +++ b/tools/testing/selftests/riscv/vector/vstate_prctl.c @@ -76,6 +76,8 @@ int main(void) long flag, expected; long rc; + ksft_set_plan(1); + pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0; rc = riscv_hwprobe(&pair, 1, 0, NULL, 0); if (rc < 0) { diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c index 37d9bf6fb745..6f4c3f5a1c5d 100644 --- a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c +++ b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c @@ -20,7 +20,7 @@ s32 BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_select_cpu, struct task_struct *p, * If we dispatch to a bogus DSQ that will fall back to the * builtin global DSQ, we fail gracefully. */ - scx_bpf_dispatch_vtime(p, 0xcafef00d, SCX_SLICE_DFL, + scx_bpf_dsq_insert_vtime(p, 0xcafef00d, SCX_SLICE_DFL, p->scx.dsq_vtime, 0); return cpu; } diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c index dffc97d9cdf1..e4a55027778f 100644 --- a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c +++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c @@ -17,8 +17,8 @@ s32 BPF_STRUCT_OPS(ddsp_vtimelocal_fail_select_cpu, struct task_struct *p, if (cpu >= 0) { /* Shouldn't be allowed to vtime dispatch to a builtin DSQ. */ - scx_bpf_dispatch_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, - p->scx.dsq_vtime, 0); + scx_bpf_dsq_insert_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, + p->scx.dsq_vtime, 0); return cpu; } diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c index 6a7db1502c29..fbda6bf54671 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c @@ -43,9 +43,12 @@ void BPF_STRUCT_OPS(dsp_local_on_dispatch, s32 cpu, struct task_struct *prev) if (!p) return; - target = bpf_get_prandom_u32() % nr_cpus; + if (p->nr_cpus_allowed == nr_cpus) + target = bpf_get_prandom_u32() % nr_cpus; + else + target = scx_bpf_task_cpu(p); - scx_bpf_dispatch(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0); bpf_task_release(p); } diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.c b/tools/testing/selftests/sched_ext/dsp_local_on.c index 472851b56854..0ff27e57fe43 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.c @@ -34,9 +34,10 @@ static enum scx_test_status run(void *ctx) /* Just sleeping is fine, plenty of scheduling events happening */ sleep(1); - SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_ERROR)); bpf_link__destroy(link); + SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_UNREG)); + return SCX_TEST_PASS; } @@ -50,7 +51,7 @@ static void cleanup(void *ctx) struct scx_test dsp_local_on = { .name = "dsp_local_on", .description = "Verify we can directly dispatch tasks to a local DSQs " - "from osp.dispatch()", + "from ops.dispatch()", .setup = setup, .run = run, .cleanup = cleanup, diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c index 1efb50d61040..a7cf868d5e31 100644 --- a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c +++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c @@ -31,7 +31,7 @@ void BPF_STRUCT_OPS(enq_select_cpu_fails_enqueue, struct task_struct *p, /* Can only call from ops.select_cpu() */ scx_bpf_select_cpu_dfl(p, 0, 0, &found); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); } SEC(".struct_ops.link") diff --git a/tools/testing/selftests/sched_ext/exit.bpf.c b/tools/testing/selftests/sched_ext/exit.bpf.c index d75d4faf07f6..4bc36182d3ff 100644 --- a/tools/testing/selftests/sched_ext/exit.bpf.c +++ b/tools/testing/selftests/sched_ext/exit.bpf.c @@ -33,7 +33,7 @@ void BPF_STRUCT_OPS(exit_enqueue, struct task_struct *p, u64 enq_flags) if (exit_point == EXIT_ENQUEUE) EXIT_CLEANLY(); - scx_bpf_dispatch(p, DSQ_ID, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags); } void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p) @@ -41,7 +41,7 @@ void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p) if (exit_point == EXIT_DISPATCH) EXIT_CLEANLY(); - scx_bpf_consume(DSQ_ID); + scx_bpf_dsq_move_to_local(DSQ_ID); } void BPF_STRUCT_OPS(exit_enable, struct task_struct *p) diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c index 4d4cd8d966db..430f5e13bf55 100644 --- a/tools/testing/selftests/sched_ext/maximal.bpf.c +++ b/tools/testing/selftests/sched_ext/maximal.bpf.c @@ -12,6 +12,8 @@ char _license[] SEC("license") = "GPL"; +#define DSQ_ID 0 + s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags) { @@ -20,7 +22,7 @@ s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu, void BPF_STRUCT_OPS(maximal_enqueue, struct task_struct *p, u64 enq_flags) { - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags); } void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags) @@ -28,7 +30,7 @@ void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags) void BPF_STRUCT_OPS(maximal_dispatch, s32 cpu, struct task_struct *prev) { - scx_bpf_consume(SCX_DSQ_GLOBAL); + scx_bpf_dsq_move_to_local(DSQ_ID); } void BPF_STRUCT_OPS(maximal_runnable, struct task_struct *p, u64 enq_flags) @@ -123,7 +125,7 @@ void BPF_STRUCT_OPS(maximal_cgroup_set_weight, struct cgroup *cgrp, u32 weight) s32 BPF_STRUCT_OPS_SLEEPABLE(maximal_init) { - return 0; + return scx_bpf_create_dsq(DSQ_ID, -1); } void BPF_STRUCT_OPS(maximal_exit, struct scx_exit_info *info) diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c index f171ac470970..13d0f5be788d 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c @@ -30,7 +30,7 @@ void BPF_STRUCT_OPS(select_cpu_dfl_enqueue, struct task_struct *p, } scx_bpf_put_idle_cpumask(idle_mask); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); } SEC(".struct_ops.link") diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c index 9efdbb7da928..815f1d5d61ac 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c @@ -67,7 +67,7 @@ void BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_enqueue, struct task_struct *p, saw_local = true; } - scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, enq_flags); } s32 BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_init_task, diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c index 59bfc4f36167..4bb99699e920 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c @@ -29,7 +29,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_select_cpu, struct task_struct *p, cpu = prev_cpu; dispatch: - scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, 0); return cpu; } diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c index 3bbd5fcdfb18..2a75de11b2cf 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c @@ -18,7 +18,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_bad_dsq_select_cpu, struct task_struct *p s32 prev_cpu, u64 wake_flags) { /* Dispatching to a random DSQ should fail. */ - scx_bpf_dispatch(p, 0xcafef00d, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, 0xcafef00d, SCX_SLICE_DFL, 0); return prev_cpu; } diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c index 0fda57fe0ecf..99d075695c97 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c @@ -18,8 +18,8 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_dbl_dsp_select_cpu, struct task_struct *p s32 prev_cpu, u64 wake_flags) { /* Dispatching twice in a row is disallowed. */ - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); return prev_cpu; } diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c index e6c67bcf5e6e..bfcb96cd4954 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c @@ -2,8 +2,8 @@ /* * A scheduler that validates that enqueue flags are properly stored and * applied at dispatch time when a task is directly dispatched from - * ops.select_cpu(). We validate this by using scx_bpf_dispatch_vtime(), and - * making the test a very basic vtime scheduler. + * ops.select_cpu(). We validate this by using scx_bpf_dsq_insert_vtime(), + * and making the test a very basic vtime scheduler. * * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. * Copyright (c) 2024 David Vernet <dvernet@meta.com> @@ -47,13 +47,13 @@ s32 BPF_STRUCT_OPS(select_cpu_vtime_select_cpu, struct task_struct *p, cpu = prev_cpu; scx_bpf_test_and_clear_cpu_idle(cpu); ddsp: - scx_bpf_dispatch_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0); + scx_bpf_dsq_insert_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0); return cpu; } void BPF_STRUCT_OPS(select_cpu_vtime_dispatch, s32 cpu, struct task_struct *p) { - if (scx_bpf_consume(VTIME_DSQ)) + if (scx_bpf_dsq_move_to_local(VTIME_DSQ)) consumed = true; } diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json index 996448afe31b..91d120548bf5 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json @@ -78,10 +78,10 @@ "setup": [ "$TC qdisc add dev $DEV1 ingress" ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 protocol ip flow map key dst rshift 0xff", + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 protocol ip flow map key dst rshift 0x1f", "expExitCode": "0", "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 protocol ip prio 1 flow", - "matchPattern": "filter parent ffff: protocol ip pref 1 flow chain [0-9]+ handle 0x1 map keys dst rshift 255 baseclass", + "matchPattern": "filter parent ffff: protocol ip pref 1 flow chain [0-9]+ handle 0x1 map keys dst rshift 31 baseclass", "matchCount": "1", "teardown": [ "$TC qdisc del dev $DEV1 ingress" diff --git a/tools/testing/shared/linux/maple_tree.h b/tools/testing/shared/linux/maple_tree.h index 06c89bdcc515..f67d47d32857 100644 --- a/tools/testing/shared/linux/maple_tree.h +++ b/tools/testing/shared/linux/maple_tree.h @@ -2,6 +2,6 @@ #define atomic_t int32_t #define atomic_inc(x) uatomic_inc(x) #define atomic_read(x) uatomic_read(x) -#define atomic_set(x, y) do {} while (0) +#define atomic_set(x, y) uatomic_set(x, y) #define U8_MAX UCHAR_MAX #include "../../../../include/linux/maple_tree.h" diff --git a/tools/testing/vma/linux/atomic.h b/tools/testing/vma/linux/atomic.h index e01f66f98982..3e1b6adc027b 100644 --- a/tools/testing/vma/linux/atomic.h +++ b/tools/testing/vma/linux/atomic.h @@ -6,7 +6,7 @@ #define atomic_t int32_t #define atomic_inc(x) uatomic_inc(x) #define atomic_read(x) uatomic_read(x) -#define atomic_set(x, y) do {} while (0) +#define atomic_set(x, y) uatomic_set(x, y) #define U8_MAX UCHAR_MAX #endif /* _LINUX_ATOMIC_H */ diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c index 8b66387e5f35..4403cc4eba30 100644 --- a/tools/tracing/rtla/src/timerlat_hist.c +++ b/tools/tracing/rtla/src/timerlat_hist.c @@ -282,6 +282,21 @@ static void timerlat_hist_header(struct osnoise_tool *tool) } /* + * format_summary_value - format a line of summary value (min, max or avg) + * of hist data + */ +static void format_summary_value(struct trace_seq *seq, + int count, + unsigned long long val, + bool avg) +{ + if (count) + trace_seq_printf(seq, "%9llu ", avg ? val / count : val); + else + trace_seq_printf(seq, "%9c ", '-'); +} + +/* * timerlat_print_summary - print the summary of the hist data to the output */ static void @@ -328,29 +343,23 @@ timerlat_print_summary(struct timerlat_hist_params *params, if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count) continue; - if (!params->no_irq) { - if (data->hist[cpu].irq_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].min_irq); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_irq) + format_summary_value(trace->seq, + data->hist[cpu].irq_count, + data->hist[cpu].min_irq, + false); - if (!params->no_thread) { - if (data->hist[cpu].thread_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].min_thread); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_thread) + format_summary_value(trace->seq, + data->hist[cpu].thread_count, + data->hist[cpu].min_thread, + false); - if (params->user_hist) { - if (data->hist[cpu].user_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].min_user); - else - trace_seq_printf(trace->seq, " - "); - } + if (params->user_hist) + format_summary_value(trace->seq, + data->hist[cpu].user_count, + data->hist[cpu].min_user, + false); } trace_seq_printf(trace->seq, "\n"); @@ -364,29 +373,23 @@ timerlat_print_summary(struct timerlat_hist_params *params, if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count) continue; - if (!params->no_irq) { - if (data->hist[cpu].irq_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].sum_irq / data->hist[cpu].irq_count); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_irq) + format_summary_value(trace->seq, + data->hist[cpu].irq_count, + data->hist[cpu].sum_irq, + true); - if (!params->no_thread) { - if (data->hist[cpu].thread_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].sum_thread / data->hist[cpu].thread_count); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_thread) + format_summary_value(trace->seq, + data->hist[cpu].thread_count, + data->hist[cpu].sum_thread, + true); - if (params->user_hist) { - if (data->hist[cpu].user_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].sum_user / data->hist[cpu].user_count); - else - trace_seq_printf(trace->seq, " - "); - } + if (params->user_hist) + format_summary_value(trace->seq, + data->hist[cpu].user_count, + data->hist[cpu].sum_user, + true); } trace_seq_printf(trace->seq, "\n"); @@ -400,29 +403,23 @@ timerlat_print_summary(struct timerlat_hist_params *params, if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count) continue; - if (!params->no_irq) { - if (data->hist[cpu].irq_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].max_irq); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_irq) + format_summary_value(trace->seq, + data->hist[cpu].irq_count, + data->hist[cpu].max_irq, + false); - if (!params->no_thread) { - if (data->hist[cpu].thread_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].max_thread); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_thread) + format_summary_value(trace->seq, + data->hist[cpu].thread_count, + data->hist[cpu].max_thread, + false); - if (params->user_hist) { - if (data->hist[cpu].user_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].max_user); - else - trace_seq_printf(trace->seq, " - "); - } + if (params->user_hist) + format_summary_value(trace->seq, + data->hist[cpu].user_count, + data->hist[cpu].max_user, + false); } trace_seq_printf(trace->seq, "\n"); trace_seq_do_printf(trace->seq); @@ -506,16 +503,22 @@ timerlat_print_stats_all(struct timerlat_hist_params *params, trace_seq_printf(trace->seq, "min: "); if (!params->no_irq) - trace_seq_printf(trace->seq, "%9llu ", - sum.min_irq); + format_summary_value(trace->seq, + sum.irq_count, + sum.min_irq, + false); if (!params->no_thread) - trace_seq_printf(trace->seq, "%9llu ", - sum.min_thread); + format_summary_value(trace->seq, + sum.thread_count, + sum.min_thread, + false); if (params->user_hist) - trace_seq_printf(trace->seq, "%9llu ", - sum.min_user); + format_summary_value(trace->seq, + sum.user_count, + sum.min_user, + false); trace_seq_printf(trace->seq, "\n"); @@ -523,16 +526,22 @@ timerlat_print_stats_all(struct timerlat_hist_params *params, trace_seq_printf(trace->seq, "avg: "); if (!params->no_irq) - trace_seq_printf(trace->seq, "%9llu ", - sum.sum_irq / sum.irq_count); + format_summary_value(trace->seq, + sum.irq_count, + sum.sum_irq, + true); if (!params->no_thread) - trace_seq_printf(trace->seq, "%9llu ", - sum.sum_thread / sum.thread_count); + format_summary_value(trace->seq, + sum.thread_count, + sum.sum_thread, + true); if (params->user_hist) - trace_seq_printf(trace->seq, "%9llu ", - sum.sum_user / sum.user_count); + format_summary_value(trace->seq, + sum.user_count, + sum.sum_user, + true); trace_seq_printf(trace->seq, "\n"); @@ -540,16 +549,22 @@ timerlat_print_stats_all(struct timerlat_hist_params *params, trace_seq_printf(trace->seq, "max: "); if (!params->no_irq) - trace_seq_printf(trace->seq, "%9llu ", - sum.max_irq); + format_summary_value(trace->seq, + sum.irq_count, + sum.max_irq, + false); if (!params->no_thread) - trace_seq_printf(trace->seq, "%9llu ", - sum.max_thread); + format_summary_value(trace->seq, + sum.thread_count, + sum.max_thread, + false); if (params->user_hist) - trace_seq_printf(trace->seq, "%9llu ", - sum.max_user); + format_summary_value(trace->seq, + sum.user_count, + sum.max_user, + false); trace_seq_printf(trace->seq, "\n"); trace_seq_do_printf(trace->seq); diff --git a/usr/include/Makefile b/usr/include/Makefile index 771e32872b2a..6c6de1b1622b 100644 --- a/usr/include/Makefile +++ b/usr/include/Makefile @@ -78,7 +78,7 @@ quiet_cmd_hdrtest = HDRTEST $< cmd_hdrtest = \ $(CC) $(c_flags) -fsyntax-only -x c /dev/null \ $(if $(filter-out $(no-header-test), $*.h), -include $< -include $<); \ - $(PERL) $(src)/headers_check.pl $(obj) $(SRCARCH) $<; \ + $(PERL) $(src)/headers_check.pl $(obj) $<; \ touch $@ $(obj)/%.hdrtest: $(obj)/%.h FORCE diff --git a/usr/include/headers_check.pl b/usr/include/headers_check.pl index b6aec5e4365f..2b70bfa5558e 100755 --- a/usr/include/headers_check.pl +++ b/usr/include/headers_check.pl @@ -3,9 +3,8 @@ # # headers_check.pl execute a number of trivial consistency checks # -# Usage: headers_check.pl dir arch [files...] +# Usage: headers_check.pl dir [files...] # dir: dir to look for included files -# arch: architecture # files: list of files to check # # The script reads the supplied files line by line and: @@ -23,7 +22,7 @@ use warnings; use strict; use File::Basename; -my ($dir, $arch, @files) = @ARGV; +my ($dir, @files) = @ARGV; my $ret = 0; my $line; @@ -55,10 +54,6 @@ sub check_include my $found; $found = stat($dir . "/" . $inc); if (!$found) { - $inc =~ s#asm/#asm-$arch/#; - $found = stat($dir . "/" . $inc); - } - if (!$found) { printf STDERR "$filename:$lineno: included file '$inc' is not exported\n"; $ret = 1; } |