diff options
285 files changed, 3738 insertions, 1532 deletions
@@ -735,6 +735,7 @@ 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> 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/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/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/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/devicetree/bindings/sound/realtek,rt5645.yaml b/Documentation/devicetree/bindings/sound/realtek,rt5645.yaml index 13f09f1bc800..0a698798c22b 100644 --- a/Documentation/devicetree/bindings/sound/realtek,rt5645.yaml +++ b/Documentation/devicetree/bindings/sound/realtek,rt5645.yaml @@ -51,7 +51,7 @@ properties: description: Power supply for AVDD, providing 1.8V. cpvdd-supply: - description: Power supply for CPVDD, providing 3.5V. + description: Power supply for CPVDD, providing 1.8V. hp-detect-gpios: description: 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/MAINTAINERS b/MAINTAINERS index b5c4e4c72618..52378f994294 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1797,7 +1797,6 @@ 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 @@ -7348,7 +7347,7 @@ 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 @@ -8925,7 +8924,7 @@ 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/ @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 13 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc5 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/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/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/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/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/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/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/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/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/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/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/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/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..45df5eeabc5e 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) @@ -2320,11 +2330,6 @@ 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/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/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/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/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/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/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/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/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_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_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/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/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/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/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/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/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/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/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/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/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/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/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/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/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/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/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/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/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-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/option.c b/drivers/usb/serial/option.c index 9ba5584061c8..64317b390d22 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -625,6 +625,8 @@ static void option_instat_callback(struct urb *urb); #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 +2404,14 @@ 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, 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) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); 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/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/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/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/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/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/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/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/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/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/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/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..959359301250 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4840,6 +4840,8 @@ smb2_writev_callback(struct mid_q_entry *mid) if (written > wdata->subreq.len) written &= 0xFFFF; + cifs_stats_bytes_written(tcon, written); + if (written < wdata->subreq.len) wdata->result = -ENOSPC; else @@ -5156,6 +5158,7 @@ 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 +6207,7 @@ 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/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/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/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/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/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_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/mlx5/driver.h b/include/linux/mlx5/driver.h index 8f5991168ccd..ea48eb879a0f 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1203,6 +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..338a76ce9083 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; } @@ -4175,6 +4185,23 @@ 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/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/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/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/trace_events.h b/include/linux/trace_events.h index 91b8ffbdfa8c..58ad4ead33fc 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -364,7 +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/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/sock.h b/include/net/sock.h index 7464e9f9f47c..c383126f691d 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) 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/io_uring/io_uring.c b/io_uring/io_uring.c index 06ff41484e29..d3403c8216db 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); } @@ -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); @@ -3214,6 +3218,7 @@ 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/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/sqpoll.c b/io_uring/sqpoll.c index 6df5e649c413..9e5bd79fd2b5 100644 --- a/io_uring/sqpoll.c +++ b/io_uring/sqpoll.c @@ -405,6 +405,7 @@ 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 +481,7 @@ __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 +492,15 @@ __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..bbe58638eca7 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; } } @@ -109,7 +109,7 @@ __cold void io_flush_timeouts(struct io_ring_ctx *ctx) u32 seq; struct io_timeout *timeout, *tmp; - 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) { @@ -134,7 +134,7 @@ __cold void io_flush_timeouts(struct io_ring_ctx *ctx) io_kill_timeout(req, 0); } ctx->cq_last_tm_flush = seq; - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); } static void io_req_tw_fail_links(struct io_kiocb *link, struct io_tw_state *ts) @@ -200,9 +200,9 @@ 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 +238,11 @@ 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 +285,9 @@ 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 +330,7 @@ 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 +345,7 @@ 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); @@ -472,12 +472,12 @@ 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 +572,7 @@ 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 +611,7 @@ 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 +620,7 @@ 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 +633,7 @@ 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); } @@ -668,7 +668,7 @@ __cold bool io_kill_timeouts(struct io_ring_ctx *ctx, struct io_uring_task *tctx * 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); @@ -676,7 +676,7 @@ __cold bool io_kill_timeouts(struct io_ring_ctx *ctx, struct io_uring_task *tctx io_kill_timeout(req, -ECANCELED)) canceled++; } - spin_unlock_irq(&ctx->timeout_lock); + raw_spin_unlock_irq(&ctx->timeout_lock); spin_unlock(&ctx->completion_lock); return canceled != 0; } 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/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/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/trace/fgraph.c b/kernel/trace/fgraph.c index ddedcb50917f..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; 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 7cc18b9bce27..f8aebcb01e62 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4206,6 +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); } @@ -5078,6 +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; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 1545cc8b49d0..770e7ed91716 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -365,6 +365,18 @@ static bool process_string(const char *fmt, int len, struct trace_event_call *ca } 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. diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 263fac44d3ca..935a886af40c 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) { 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/mm/huge_memory.c b/mm/huge_memory.c index ee335d96fc39..e53d83b3e5cf 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 @@ -3576,7 +3577,7 @@ 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 +3689,7 @@ 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 +3733,7 @@ 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 +3826,7 @@ 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 +4169,7 @@ 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..cec4b121193f 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); @@ -6643,8 +6643,7 @@ 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) { diff --git a/mm/internal.h b/mm/internal.h index cb8d8e8e3ffa..3bd08bafad04 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. 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/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/shmem.c b/mm/shmem.c index ccb9629a0f70..f6fb053ac50d 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); @@ -1969,10 +1973,8 @@ 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); @@ -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/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/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/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/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/scripts/mod/modpost.c b/scripts/mod/modpost.c index fb787a5715f5..94ee49207a45 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; @@ -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..8b72c227ebf4 100644 --- a/scripts/mod/modpost.h +++ b/scripts/mod/modpost.h @@ -95,14 +95,15 @@ 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/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/sound/core/compress_offload.c b/sound/core/compress_offload.c index 86ed2fbee0c8..840bb9cfe789 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -1025,7 +1025,7 @@ static u64 snd_compr_seqno_next(struct snd_compr_stream *stream) static int snd_compr_task_new(struct snd_compr_stream *stream, struct snd_compr_task *utask) { struct snd_compr_task_runtime *task; - int retval; + int retval, fd_i, fd_o; if (stream->runtime->total_tasks >= stream->runtime->fragments) return -EBUSY; @@ -1039,19 +1039,27 @@ static int snd_compr_task_new(struct snd_compr_stream *stream, struct snd_compr_ retval = stream->ops->task_create(stream, task); if (retval < 0) goto cleanup; - utask->input_fd = dma_buf_fd(task->input, O_WRONLY|O_CLOEXEC); - if (utask->input_fd < 0) { - retval = utask->input_fd; + /* similar functionality as in dma_buf_fd(), but ensure that both + file descriptors are allocated before fd_install() */ + if (!task->input || !task->input->file || !task->output || !task->output->file) { + retval = -EINVAL; goto cleanup; } - utask->output_fd = dma_buf_fd(task->output, O_RDONLY|O_CLOEXEC); - if (utask->output_fd < 0) { - retval = utask->output_fd; + fd_i = get_unused_fd_flags(O_WRONLY|O_CLOEXEC); + if (fd_i < 0) + goto cleanup; + fd_o = get_unused_fd_flags(O_RDONLY|O_CLOEXEC); + if (fd_o < 0) { + put_unused_fd(fd_i); goto cleanup; } /* keep dmabuf reference until freed with task free ioctl */ - dma_buf_get(utask->input_fd); - dma_buf_get(utask->output_fd); + get_dma_buf(task->input); + get_dma_buf(task->output); + fd_install(fd_i, task->input->file); + fd_install(fd_o, task->output->file); + utask->input_fd = fd_i; + utask->output_fd = fd_o; list_add_tail(&task->list, &stream->runtime->tasks); stream->runtime->total_tasks++; return 0; @@ -1069,7 +1077,7 @@ static int snd_compr_task_create(struct snd_compr_stream *stream, unsigned long return -EPERM; task = memdup_user((void __user *)arg, sizeof(*task)); if (IS_ERR(task)) - return PTR_ERR(no_free_ptr(task)); + return PTR_ERR(task); retval = snd_compr_task_new(stream, task); if (retval >= 0) if (copy_to_user((void __user *)arg, task, sizeof(*task))) @@ -1130,7 +1138,7 @@ static int snd_compr_task_start_ioctl(struct snd_compr_stream *stream, unsigned return -EPERM; task = memdup_user((void __user *)arg, sizeof(*task)); if (IS_ERR(task)) - return PTR_ERR(no_free_ptr(task)); + return PTR_ERR(task); retval = snd_compr_task_start(stream, task); if (retval >= 0) if (copy_to_user((void __user *)arg, task, sizeof(*task))) @@ -1174,18 +1182,18 @@ typedef void (*snd_compr_seq_func_t)(struct snd_compr_stream *stream, static int snd_compr_task_seq(struct snd_compr_stream *stream, unsigned long arg, snd_compr_seq_func_t fcn) { - struct snd_compr_task_runtime *task; + struct snd_compr_task_runtime *task, *temp; __u64 seqno; int retval; if (stream->runtime->state != SNDRV_PCM_STATE_SETUP) return -EPERM; - retval = get_user(seqno, (__u64 __user *)arg); - if (retval < 0) - return retval; + retval = copy_from_user(&seqno, (__u64 __user *)arg, sizeof(seqno)); + if (retval) + return -EFAULT; retval = 0; if (seqno == 0) { - list_for_each_entry_reverse(task, &stream->runtime->tasks, list) + list_for_each_entry_safe_reverse(task, temp, &stream->runtime->tasks, list) fcn(stream, task); } else { task = snd_compr_find_task(stream, seqno); @@ -1221,7 +1229,7 @@ static int snd_compr_task_status_ioctl(struct snd_compr_stream *stream, unsigned return -EPERM; status = memdup_user((void __user *)arg, sizeof(*status)); if (IS_ERR(status)) - return PTR_ERR(no_free_ptr(status)); + return PTR_ERR(status); retval = snd_compr_task_status(stream, status); if (retval >= 0) if (copy_to_user((void __user *)arg, status, sizeof(*status))) @@ -1247,6 +1255,7 @@ void snd_compr_task_finished(struct snd_compr_stream *stream, } EXPORT_SYMBOL_GPL(snd_compr_task_finished); +MODULE_IMPORT_NS("DMA_BUF"); #endif /* CONFIG_SND_COMPRESS_ACCEL */ static long snd_compr_ioctl(struct file *f, unsigned int cmd, unsigned long arg) diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c index 13b71069ae18..b3853583d2ae 100644 --- a/sound/core/memalloc.c +++ b/sound/core/memalloc.c @@ -505,7 +505,7 @@ static void *snd_dma_wc_alloc(struct snd_dma_buffer *dmab, size_t size) if (!p) return NULL; dmab->addr = dma_map_single(dmab->dev.dev, p, size, DMA_BIDIRECTIONAL); - if (dmab->addr == DMA_MAPPING_ERROR) { + if (dma_mapping_error(dmab->dev.dev, dmab->addr)) { do_free_pages(dmab->area, size, true); return NULL; } diff --git a/sound/core/seq/oss/seq_oss_synth.c b/sound/core/seq/oss/seq_oss_synth.c index e3394919daa0..51ee4c00a843 100644 --- a/sound/core/seq/oss/seq_oss_synth.c +++ b/sound/core/seq/oss/seq_oss_synth.c @@ -66,6 +66,7 @@ static struct seq_oss_synth midi_synth_dev = { }; static DEFINE_SPINLOCK(register_lock); +static DEFINE_MUTEX(sysex_mutex); /* * prototypes @@ -497,6 +498,7 @@ snd_seq_oss_synth_sysex(struct seq_oss_devinfo *dp, int dev, unsigned char *buf, if (!info) return -ENXIO; + guard(mutex)(&sysex_mutex); sysex = info->sysex; if (sysex == NULL) { sysex = kzalloc(sizeof(*sysex), GFP_KERNEL); diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 3930e2f9082f..77b6ac9b5c11 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -1275,10 +1275,16 @@ static int snd_seq_ioctl_set_client_info(struct snd_seq_client *client, if (client->type != client_info->type) return -EINVAL; - /* check validity of midi_version field */ - if (client->user_pversion >= SNDRV_PROTOCOL_VERSION(1, 0, 3) && - client_info->midi_version > SNDRV_SEQ_CLIENT_UMP_MIDI_2_0) - return -EINVAL; + if (client->user_pversion >= SNDRV_PROTOCOL_VERSION(1, 0, 3)) { + /* check validity of midi_version field */ + if (client_info->midi_version > SNDRV_SEQ_CLIENT_UMP_MIDI_2_0) + return -EINVAL; + + /* check if UMP is supported in kernel */ + if (!IS_ENABLED(CONFIG_SND_SEQ_UMP) && + client_info->midi_version > 0) + return -EINVAL; + } /* fill the info fields */ if (client_info->name[0]) diff --git a/sound/core/ump.c b/sound/core/ump.c index fe4d39ae1159..9198bff4768c 100644 --- a/sound/core/ump.c +++ b/sound/core/ump.c @@ -1244,7 +1244,7 @@ static int fill_legacy_mapping(struct snd_ump_endpoint *ump) num = 0; for (i = 0; i < SNDRV_UMP_MAX_GROUPS; i++) - if ((group_maps & (1U << i)) && ump->groups[i].valid) + if (group_maps & (1U << i)) ump->legacy_mapping[num++] = i; return num; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 61ba5dc35b8b..b74b566f675e 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -11009,6 +11009,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0xf111, 0x0001, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x0006, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x0009, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0xf111, 0x000c, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), #if 0 /* Below is a quirk table taken from the old code. diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c index 0af015806aba..0e42b87dadb8 100644 --- a/sound/pci/hda/tas2781_hda_i2c.c +++ b/sound/pci/hda/tas2781_hda_i2c.c @@ -142,6 +142,9 @@ static int tas2781_read_acpi(struct tasdevice_priv *p, const char *hid) } sub = acpi_get_subsystem_id(ACPI_HANDLE(physdev)); if (IS_ERR(sub)) { + /* No subsys id in older tas2563 projects. */ + if (!strncmp(hid, "INT8866", sizeof("INT8866"))) + goto end_2563; dev_err(p->dev, "Failed to get SUBSYS ID.\n"); ret = PTR_ERR(sub); goto err; @@ -164,6 +167,7 @@ static int tas2781_read_acpi(struct tasdevice_priv *p, const char *hid) p->speaker_id = NULL; } +end_2563: acpi_dev_free_resource_list(&resources); strscpy(p->dev_name, hid, sizeof(p->dev_name)); put_device(physdev); diff --git a/sound/sh/sh_dac_audio.c b/sound/sh/sh_dac_audio.c index a4d07438ad64..3f5422145c5e 100644 --- a/sound/sh/sh_dac_audio.c +++ b/sound/sh/sh_dac_audio.c @@ -163,7 +163,7 @@ static int snd_sh_dac_pcm_copy(struct snd_pcm_substream *substream, /* channel is not used (interleaved data) */ struct snd_sh_dac *chip = snd_pcm_substream_chip(substream); - if (copy_from_iter(chip->data_buffer + pos, src, count) != count) + if (copy_from_iter(chip->data_buffer + pos, count, src) != count) return -EFAULT; chip->buffer_end = chip->data_buffer + pos + count; diff --git a/sound/soc/amd/ps/pci-ps.c b/sound/soc/amd/ps/pci-ps.c index 823a69bf778b..4575326d0635 100644 --- a/sound/soc/amd/ps/pci-ps.c +++ b/sound/soc/amd/ps/pci-ps.c @@ -375,11 +375,18 @@ static int get_acp63_device_config(struct pci_dev *pci, struct acp63_dev_data *a { struct acpi_device *pdm_dev; const union acpi_object *obj; + acpi_handle handle; + acpi_integer dmic_status; u32 config; bool is_dmic_dev = false; bool is_sdw_dev = false; + bool wov_en, dmic_en; int ret; + /* IF WOV entry not found, enable dmic based on acp-audio-device-type entry*/ + wov_en = true; + dmic_en = false; + config = readl(acp_data->acp63_base + ACP_PIN_CONFIG); switch (config) { case ACP_CONFIG_4: @@ -412,10 +419,18 @@ static int get_acp63_device_config(struct pci_dev *pci, struct acp63_dev_data *a if (!acpi_dev_get_property(pdm_dev, "acp-audio-device-type", ACPI_TYPE_INTEGER, &obj) && obj->integer.value == ACP_DMIC_DEV) - is_dmic_dev = true; + dmic_en = true; } + + handle = ACPI_HANDLE(&pci->dev); + ret = acpi_evaluate_integer(handle, "_WOV", NULL, &dmic_status); + if (!ACPI_FAILURE(ret)) + wov_en = dmic_status; } + if (dmic_en && wov_en) + is_dmic_dev = true; + if (acp_data->is_sdw_config) { ret = acp_scan_sdw_devices(&pci->dev, ACP63_SDW_ADDR); if (!ret && acp_data->info.link_mask) diff --git a/sound/soc/codecs/rt722-sdca.c b/sound/soc/codecs/rt722-sdca.c index 908846e994df..e17a142d03b9 100644 --- a/sound/soc/codecs/rt722-sdca.c +++ b/sound/soc/codecs/rt722-sdca.c @@ -1468,13 +1468,18 @@ static void rt722_sdca_jack_preset(struct rt722_sdca_priv *rt722) 0x008d); /* check HP calibration FSM status */ for (loop_check = 0; loop_check < chk_cnt; loop_check++) { + usleep_range(10000, 11000); ret = rt722_sdca_index_read(rt722, RT722_VENDOR_CALI, RT722_DAC_DC_CALI_CTL3, &calib_status); - if (ret < 0 || loop_check == chk_cnt) + if (ret < 0) dev_dbg(&rt722->slave->dev, "calibration failed!, ret=%d\n", ret); if ((calib_status & 0x0040) == 0x0) break; } + + if (loop_check == chk_cnt) + dev_dbg(&rt722->slave->dev, "%s, calibration time-out!\n", __func__); + /* Set ADC09 power entity floating control */ rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_ADC0A_08_PDE_FLOAT_CTL, 0x2a12); diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index f3369e569abc..c9f9c9b0de9b 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -632,7 +632,7 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { .callback = sof_sdw_quirk_cb, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "233C") + DMI_MATCH(DMI_PRODUCT_NAME, "21QB") }, /* Note this quirk excludes the CODEC mic */ .driver_data = (void *)(SOC_SDW_CODEC_MIC), @@ -641,9 +641,26 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { .callback = sof_sdw_quirk_cb, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "233B") + DMI_MATCH(DMI_PRODUCT_NAME, "21QA") }, - .driver_data = (void *)(SOC_SDW_SIDECAR_AMPS), + /* Note this quirk excludes the CODEC mic */ + .driver_data = (void *)(SOC_SDW_CODEC_MIC), + }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "21Q6") + }, + .driver_data = (void *)(SOC_SDW_SIDECAR_AMPS | SOC_SDW_CODEC_MIC), + }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "21Q7") + }, + .driver_data = (void *)(SOC_SDW_SIDECAR_AMPS | SOC_SDW_CODEC_MIC), }, /* ArrowLake devices */ diff --git a/sound/soc/mediatek/common/mtk-afe-platform-driver.c b/sound/soc/mediatek/common/mtk-afe-platform-driver.c index 9b72b2a7ae91..6b6330583941 100644 --- a/sound/soc/mediatek/common/mtk-afe-platform-driver.c +++ b/sound/soc/mediatek/common/mtk-afe-platform-driver.c @@ -120,8 +120,8 @@ int mtk_afe_pcm_new(struct snd_soc_component *component, struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component); size = afe->mtk_afe_hardware->buffer_bytes_max; - snd_pcm_set_managed_buffer_all(pcm, SNDRV_DMA_TYPE_DEV, - afe->dev, size, size); + snd_pcm_set_managed_buffer_all(pcm, SNDRV_DMA_TYPE_DEV, afe->dev, 0, size); + return 0; } EXPORT_SYMBOL_GPL(mtk_afe_pcm_new); diff --git a/sound/soc/sof/intel/hda-dai.c b/sound/soc/sof/intel/hda-dai.c index c13f89b7065e..0db2a3e554fb 100644 --- a/sound/soc/sof/intel/hda-dai.c +++ b/sound/soc/sof/intel/hda-dai.c @@ -103,8 +103,10 @@ hda_dai_get_ops(struct snd_pcm_substream *substream, struct snd_soc_dai *cpu_dai return sdai->platform_private; } -int hda_link_dma_cleanup(struct snd_pcm_substream *substream, struct hdac_ext_stream *hext_stream, - struct snd_soc_dai *cpu_dai) +static int +hda_link_dma_cleanup(struct snd_pcm_substream *substream, + struct hdac_ext_stream *hext_stream, + struct snd_soc_dai *cpu_dai, bool release) { const struct hda_dai_widget_dma_ops *ops = hda_dai_get_ops(substream, cpu_dai); struct sof_intel_hda_stream *hda_stream; @@ -128,6 +130,17 @@ int hda_link_dma_cleanup(struct snd_pcm_substream *substream, struct hdac_ext_st snd_hdac_ext_bus_link_clear_stream_id(hlink, stream_tag); } + if (!release) { + /* + * Force stream reconfiguration without releasing the channel on + * subsequent stream restart (without free), including LinkDMA + * reset. + * The stream is released via hda_dai_hw_free() + */ + hext_stream->link_prepared = 0; + return 0; + } + if (ops->release_hext_stream) ops->release_hext_stream(sdev, cpu_dai, substream); @@ -211,7 +224,7 @@ static int __maybe_unused hda_dai_hw_free(struct snd_pcm_substream *substream, if (!hext_stream) return 0; - return hda_link_dma_cleanup(substream, hext_stream, cpu_dai); + return hda_link_dma_cleanup(substream, hext_stream, cpu_dai, true); } static int __maybe_unused hda_dai_hw_params_data(struct snd_pcm_substream *substream, @@ -304,7 +317,8 @@ static int __maybe_unused hda_dai_trigger(struct snd_pcm_substream *substream, i switch (cmd) { case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_SUSPEND: - ret = hda_link_dma_cleanup(substream, hext_stream, dai); + ret = hda_link_dma_cleanup(substream, hext_stream, dai, + cmd == SNDRV_PCM_TRIGGER_STOP ? false : true); if (ret < 0) { dev_err(sdev->dev, "%s: failed to clean up link DMA\n", __func__); return ret; @@ -660,8 +674,7 @@ static int hda_dai_suspend(struct hdac_bus *bus) } ret = hda_link_dma_cleanup(hext_stream->link_substream, - hext_stream, - cpu_dai); + hext_stream, cpu_dai, true); if (ret < 0) return ret; } diff --git a/sound/soc/sof/intel/hda.h b/sound/soc/sof/intel/hda.h index 22bd9c3c8216..ee4ccc1a5490 100644 --- a/sound/soc/sof/intel/hda.h +++ b/sound/soc/sof/intel/hda.h @@ -1038,8 +1038,6 @@ const struct hda_dai_widget_dma_ops * hda_select_dai_widget_ops(struct snd_sof_dev *sdev, struct snd_sof_widget *swidget); int hda_dai_config(struct snd_soc_dapm_widget *w, unsigned int flags, struct snd_sof_dai_config_data *data); -int hda_link_dma_cleanup(struct snd_pcm_substream *substream, struct hdac_ext_stream *hext_stream, - struct snd_soc_dai *cpu_dai); static inline struct snd_sof_dev *widget_to_sdev(struct snd_soc_dapm_widget *w) { diff --git a/sound/usb/mixer_us16x08.c b/sound/usb/mixer_us16x08.c index 6eb7d93b358d..20ac32635f1f 100644 --- a/sound/usb/mixer_us16x08.c +++ b/sound/usb/mixer_us16x08.c @@ -687,7 +687,7 @@ static int snd_us16x08_meter_get(struct snd_kcontrol *kcontrol, struct usb_mixer_elem_info *elem = kcontrol->private_data; struct snd_usb_audio *chip = elem->head.mixer->chip; struct snd_us16x08_meter_store *store = elem->private_data; - u8 meter_urb[64]; + u8 meter_urb[64] = {0}; switch (kcontrol->private_value) { case 0: { 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/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/testing/selftests/alsa/Makefile b/tools/testing/selftests/alsa/Makefile index 944279160fed..8dab90ad22bb 100644 --- a/tools/testing/selftests/alsa/Makefile +++ b/tools/testing/selftests/alsa/Makefile @@ -27,5 +27,5 @@ include ../lib.mk $(OUTPUT)/libatest.so: conf.c alsa-local.h $(CC) $(CFLAGS) -shared -fPIC $< $(LDLIBS) -o $@ -$(OUTPUT)/%: %.c $(TEST_GEN_PROGS_EXTENDED) alsa-local.h +$(OUTPUT)/%: %.c $(OUTPUT)/libatest.so alsa-local.h $(CC) $(CFLAGS) $< $(LDLIBS) -latest -o $@ 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/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index 95af2d78fd31..0a0b55516028 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> @@ -1557,6 +1558,11 @@ 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; @@ -1591,8 +1597,12 @@ int main(int argc, char **argv) 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/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; } |