diff options
307 files changed, 4054 insertions, 1666 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/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/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/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 baf0eeb9a355..910305c11e8a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7347,7 +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 @@ -8453,7 +8453,7 @@ F: include/video/s1d13xxxfb.h EROFS FILE SYSTEM M: Gao Xiang <xiang@kernel.org> M: Chao Yu <chao@kernel.org> -R: Yue Hu <huyue2@coolpad.com> +R: Yue Hu <zbestahu@gmail.com> R: Jeffle Xu <jefflexu@linux.alibaba.com> R: Sandeep Dhavale <dhavale@google.com> L: linux-erofs@lists.ozlabs.org @@ -8924,7 +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 = -rc4 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/arm64/boot/dts/arm/fvp-base-revc.dts b/arch/arm64/boot/dts/arm/fvp-base-revc.dts index 19973ab4ea6b..9e10d7a6b5a2 100644 --- a/arch/arm64/boot/dts/arm/fvp-base-revc.dts +++ b/arch/arm64/boot/dts/arm/fvp-base-revc.dts @@ -233,7 +233,7 @@ #interrupt-cells = <0x1>; compatible = "pci-host-ecam-generic"; device_type = "pci"; - bus-range = <0x0 0x1>; + bus-range = <0x0 0xff>; reg = <0x0 0x40000000 0x0 0x10000000>; ranges = <0x2000000 0x0 0x50000000 0x0 0x50000000 0x0 0x10000000>; interrupt-map = <0 0 0 1 &gic 0 0 GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi index 6e5a984c1d4e..26a29e5e5078 100644 --- a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi +++ b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi @@ -67,7 +67,7 @@ l2_cache_l0: l2-cache-l0 { compatible = "cache"; cache-size = <0x80000>; - cache-line-size = <128>; + cache-line-size = <64>; cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set cache-level = <2>; cache-unified; @@ -91,7 +91,7 @@ l2_cache_l1: l2-cache-l1 { compatible = "cache"; cache-size = <0x80000>; - cache-line-size = <128>; + cache-line-size = <64>; cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set cache-level = <2>; cache-unified; @@ -115,7 +115,7 @@ l2_cache_l2: l2-cache-l2 { compatible = "cache"; cache-size = <0x80000>; - cache-line-size = <128>; + cache-line-size = <64>; cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set cache-level = <2>; cache-unified; @@ -139,7 +139,7 @@ l2_cache_l3: l2-cache-l3 { compatible = "cache"; cache-size = <0x80000>; - cache-line-size = <128>; + cache-line-size = <64>; cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set cache-level = <2>; cache-unified; diff --git a/arch/arm64/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/hexagon/Makefile b/arch/hexagon/Makefile index 92d005958dfb..ff172cbe5881 100644 --- a/arch/hexagon/Makefile +++ b/arch/hexagon/Makefile @@ -32,3 +32,9 @@ KBUILD_LDFLAGS += $(ldflags-y) TIR_NAME := r19 KBUILD_CFLAGS += -ffixed-$(TIR_NAME) -DTHREADINFO_REG=$(TIR_NAME) -D__linux__ KBUILD_AFLAGS += -DTHREADINFO_REG=$(TIR_NAME) + +# Disable HexagonConstExtenders pass for LLVM versions prior to 19.1.0 +# https://github.com/llvm/llvm-project/issues/99714 +ifneq ($(call clang-min-version, 190100),y) +KBUILD_CFLAGS += -mllvm -hexagon-cext=false +endif diff --git a/arch/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/s390/boot/startup.c b/arch/s390/boot/startup.c index abe6e6c0ab98..6087d38c7235 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -234,6 +234,8 @@ static unsigned long get_vmem_size(unsigned long identity_size, vsize = round_up(SZ_2G + max_mappable, rte_size) + round_up(vmemmap_size, rte_size) + FIXMAP_SIZE + MODULES_LEN + KASLR_LEN; + if (IS_ENABLED(CONFIG_KMSAN)) + vsize += MODULES_LEN * 2; return size_add(vsize, vmalloc_size); } diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index 145035f84a0e..3fa28db2fe59 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -306,7 +306,7 @@ static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long e pages++; } } - if (mode == POPULATE_DIRECT) + if (mode == POPULATE_IDENTITY) update_page_count(PG_DIRECT_MAP_4K, pages); } @@ -339,7 +339,7 @@ static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long e } pgtable_pte_populate(pmd, addr, next, mode); } - if (mode == POPULATE_DIRECT) + if (mode == POPULATE_IDENTITY) update_page_count(PG_DIRECT_MAP_1M, pages); } @@ -372,7 +372,7 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e } pgtable_pmd_populate(pud, addr, next, mode); } - if (mode == POPULATE_DIRECT) + if (mode == POPULATE_IDENTITY) update_page_count(PG_DIRECT_MAP_2G, pages); } diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index edbb52ce3f1e..7d12a1305fc9 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -270,7 +270,7 @@ static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj, \ if (len >= sizeof(_value)) \ return -E2BIG; \ len = strscpy(_value, buf, sizeof(_value)); \ - if (len < 0) \ + if ((ssize_t)len < 0) \ return len; \ strim(_value); \ return len; \ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 17b6590748c0..645aa360628d 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -452,6 +452,7 @@ #define X86_FEATURE_SME_COHERENT (19*32+10) /* AMD hardware-enforced cache coherency */ #define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" AMD SEV-ES full debug state swap support */ #define X86_FEATURE_SVSM (19*32+28) /* "svsm" SVSM present */ +#define X86_FEATURE_HV_INUSE_WR_ALLOWED (19*32+30) /* Allow Write to in-use hypervisor-owned pages */ /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */ #define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* No Nested Data Breakpoints */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index c0975815980c..20e6009381ed 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -230,6 +230,8 @@ static inline unsigned long long l1tf_pfn_limit(void) return BIT_ULL(boot_cpu_data.x86_cache_bits - 1 - PAGE_SHIFT); } +void init_cpu_devs(void); +void get_cpu_vendor(struct cpuinfo_x86 *c); extern void early_cpu_init(void); extern void identify_secondary_cpu(struct cpuinfo_x86 *); extern void print_cpu_info(struct cpuinfo_x86 *); diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index 125c407e2abe..41502bd2afd6 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -65,4 +65,19 @@ extern bool __static_call_fixup(void *tramp, u8 op, void *dest); +extern void __static_call_update_early(void *tramp, void *func); + +#define static_call_update_early(name, _func) \ +({ \ + typeof(&STATIC_CALL_TRAMP(name)) __F = (_func); \ + if (static_call_initialized) { \ + __static_call_update(&STATIC_CALL_KEY(name), \ + STATIC_CALL_TRAMP_ADDR(name), __F);\ + } else { \ + WRITE_ONCE(STATIC_CALL_KEY(name).func, _func); \ + __static_call_update_early(STATIC_CALL_TRAMP_ADDR(name),\ + __F); \ + } \ +}) + #endif /* _ASM_STATIC_CALL_H */ diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h index ab7382f92aff..96bda43538ee 100644 --- a/arch/x86/include/asm/sync_core.h +++ b/arch/x86/include/asm/sync_core.h @@ -8,7 +8,7 @@ #include <asm/special_insns.h> #ifdef CONFIG_X86_32 -static inline void iret_to_self(void) +static __always_inline void iret_to_self(void) { asm volatile ( "pushfl\n\t" @@ -19,7 +19,7 @@ static inline void iret_to_self(void) : ASM_CALL_CONSTRAINT : : "memory"); } #else -static inline void iret_to_self(void) +static __always_inline void iret_to_self(void) { unsigned int tmp; @@ -55,7 +55,7 @@ static inline void iret_to_self(void) * Like all of Linux's memory ordering operations, this is a * compiler barrier as well. */ -static inline void sync_core(void) +static __always_inline void sync_core(void) { /* * The SERIALIZE instruction is the most straightforward way to diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index a2dd24947eb8..97771b9d33af 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -39,9 +39,11 @@ #include <linux/string.h> #include <linux/types.h> #include <linux/pgtable.h> +#include <linux/instrumentation.h> #include <trace/events/xen.h> +#include <asm/alternative.h> #include <asm/page.h> #include <asm/smap.h> #include <asm/nospec-branch.h> @@ -86,11 +88,20 @@ struct xen_dm_op_buf; * there aren't more than 5 arguments...) */ -extern struct { char _entry[32]; } hypercall_page[]; +void xen_hypercall_func(void); +DECLARE_STATIC_CALL(xen_hypercall, xen_hypercall_func); -#define __HYPERCALL "call hypercall_page+%c[offset]" -#define __HYPERCALL_ENTRY(x) \ - [offset] "i" (__HYPERVISOR_##x * sizeof(hypercall_page[0])) +#ifdef MODULE +#define __ADDRESSABLE_xen_hypercall +#else +#define __ADDRESSABLE_xen_hypercall __ADDRESSABLE_ASM_STR(__SCK__xen_hypercall) +#endif + +#define __HYPERCALL \ + __ADDRESSABLE_xen_hypercall \ + "call __SCT__xen_hypercall" + +#define __HYPERCALL_ENTRY(x) "a" (x) #ifdef CONFIG_X86_32 #define __HYPERCALL_RETREG "eax" @@ -148,7 +159,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_0ARG(); \ asm volatile (__HYPERCALL \ : __HYPERCALL_0PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER0); \ (type)__res; \ }) @@ -159,7 +170,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_1ARG(a1); \ asm volatile (__HYPERCALL \ : __HYPERCALL_1PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER1); \ (type)__res; \ }) @@ -170,7 +181,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_2ARG(a1, a2); \ asm volatile (__HYPERCALL \ : __HYPERCALL_2PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER2); \ (type)__res; \ }) @@ -181,7 +192,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_3ARG(a1, a2, a3); \ asm volatile (__HYPERCALL \ : __HYPERCALL_3PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER3); \ (type)__res; \ }) @@ -192,7 +203,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_4ARG(a1, a2, a3, a4); \ asm volatile (__HYPERCALL \ : __HYPERCALL_4PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER4); \ (type)__res; \ }) @@ -206,12 +217,9 @@ xen_single_call(unsigned int call, __HYPERCALL_DECLS; __HYPERCALL_5ARG(a1, a2, a3, a4, a5); - if (call >= PAGE_SIZE / sizeof(hypercall_page[0])) - return -EINVAL; - - asm volatile(CALL_NOSPEC + asm volatile(__HYPERCALL : __HYPERCALL_5PARAM - : [thunk_target] "a" (&hypercall_page[call]) + : __HYPERCALL_ENTRY(call) : __HYPERCALL_CLOBBER5); return (long)__res; diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index 465647456753..f17d16607882 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -143,11 +143,6 @@ static bool skip_addr(void *dest) dest < (void*)relocate_kernel + KEXEC_CONTROL_CODE_MAX_SIZE) return true; #endif -#ifdef CONFIG_XEN - if (dest >= (void *)hypercall_page && - dest < (void*)hypercall_page + PAGE_SIZE) - return true; -#endif return false; } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index a5c28975c608..3e9037690814 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -867,7 +867,7 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c) tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]); } -static void get_cpu_vendor(struct cpuinfo_x86 *c) +void get_cpu_vendor(struct cpuinfo_x86 *c) { char *v = c->x86_vendor_id; int i; @@ -1649,15 +1649,11 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) detect_nopl(); } -void __init early_cpu_init(void) +void __init init_cpu_devs(void) { const struct cpu_dev *const *cdev; int count = 0; -#ifdef CONFIG_PROCESSOR_SELECT - pr_info("KERNEL supported cpus:\n"); -#endif - for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) { const struct cpu_dev *cpudev = *cdev; @@ -1665,20 +1661,30 @@ void __init early_cpu_init(void) break; cpu_devs[count] = cpudev; count++; + } +} +void __init early_cpu_init(void) +{ #ifdef CONFIG_PROCESSOR_SELECT - { - unsigned int j; - - for (j = 0; j < 2; j++) { - if (!cpudev->c_ident[j]) - continue; - pr_info(" %s %s\n", cpudev->c_vendor, - cpudev->c_ident[j]); - } - } + unsigned int i, j; + + pr_info("KERNEL supported cpus:\n"); #endif + + init_cpu_devs(); + +#ifdef CONFIG_PROCESSOR_SELECT + for (i = 0; i < X86_VENDOR_NUM && cpu_devs[i]; i++) { + for (j = 0; j < 2; j++) { + if (!cpu_devs[i]->c_ident[j]) + continue; + pr_info(" %s %s\n", cpu_devs[i]->c_vendor, + cpu_devs[i]->c_ident[j]); + } } +#endif + early_identify_cpu(&boot_cpu_data); } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index d18078834ded..dc12fe5ef3ca 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -223,6 +223,63 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs) hyperv_cleanup(); } #endif /* CONFIG_CRASH_DUMP */ + +static u64 hv_ref_counter_at_suspend; +static void (*old_save_sched_clock_state)(void); +static void (*old_restore_sched_clock_state)(void); + +/* + * Hyper-V clock counter resets during hibernation. Save and restore clock + * offset during suspend/resume, while also considering the time passed + * before suspend. This is to make sure that sched_clock using hv tsc page + * based clocksource, proceeds from where it left off during suspend and + * it shows correct time for the timestamps of kernel messages after resume. + */ +static void save_hv_clock_tsc_state(void) +{ + hv_ref_counter_at_suspend = hv_read_reference_counter(); +} + +static void restore_hv_clock_tsc_state(void) +{ + /* + * Adjust the offsets used by hv tsc clocksource to + * account for the time spent before hibernation. + * adjusted value = reference counter (time) at suspend + * - reference counter (time) now. + */ + hv_adj_sched_clock_offset(hv_ref_counter_at_suspend - hv_read_reference_counter()); +} + +/* + * Functions to override save_sched_clock_state and restore_sched_clock_state + * functions of x86_platform. The Hyper-V clock counter is reset during + * suspend-resume and the offset used to measure time needs to be + * corrected, post resume. + */ +static void hv_save_sched_clock_state(void) +{ + old_save_sched_clock_state(); + save_hv_clock_tsc_state(); +} + +static void hv_restore_sched_clock_state(void) +{ + restore_hv_clock_tsc_state(); + old_restore_sched_clock_state(); +} + +static void __init x86_setup_ops_for_tsc_pg_clock(void) +{ + if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) + return; + + old_save_sched_clock_state = x86_platform.save_sched_clock_state; + x86_platform.save_sched_clock_state = hv_save_sched_clock_state; + + old_restore_sched_clock_state = x86_platform.restore_sched_clock_state; + x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state; +} #endif /* CONFIG_HYPERV */ static uint32_t __init ms_hyperv_platform(void) @@ -579,6 +636,7 @@ static void __init ms_hyperv_init_platform(void) /* Register Hyper-V specific clocksource */ hv_init_clocksource(); + x86_setup_ops_for_tsc_pg_clock(); hv_vtl_init_platform(); #endif /* diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 4eefaac64c6c..9eed0c144dad 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -172,6 +172,15 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail) } EXPORT_SYMBOL_GPL(arch_static_call_transform); +noinstr void __static_call_update_early(void *tramp, void *func) +{ + BUG_ON(system_state != SYSTEM_BOOTING); + BUG_ON(!early_boot_irqs_disabled); + BUG_ON(static_call_initialized); + __text_gen_insn(tramp, JMP32_INSN_OPCODE, tramp, func, JMP32_INSN_SIZE); + sync_core(); +} + #ifdef CONFIG_MITIGATION_RETHUNK /* * This is called by apply_returns() to fix up static call trampolines, diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index fab3ac9a4574..6a17396c8174 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -519,14 +519,10 @@ INIT_PER_CPU(irq_stack_backing_store); * linker will never mark as relocatable. (Using just ABSOLUTE() is not * sufficient for that). */ -#ifdef CONFIG_XEN #ifdef CONFIG_XEN_PV xen_elfnote_entry_value = ABSOLUTE(xen_elfnote_entry) + ABSOLUTE(startup_xen); #endif -xen_elfnote_hypercall_page_value = - ABSOLUTE(xen_elfnote_hypercall_page) + ABSOLUTE(hypercall_page); -#endif #ifdef CONFIG_PVH xen_elfnote_phys32_entry_value = ABSOLUTE(xen_elfnote_phys32_entry) + ABSOLUTE(pvh_start_xen - LOAD_OFFSET); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 22e7ad235123..2401606db260 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3364,18 +3364,6 @@ static bool fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, return true; } -static bool is_access_allowed(struct kvm_page_fault *fault, u64 spte) -{ - if (fault->exec) - return is_executable_pte(spte); - - if (fault->write) - return is_writable_pte(spte); - - /* Fault was on Read access */ - return spte & PT_PRESENT_MASK; -} - /* * Returns the last level spte pointer of the shadow page walk for the given * gpa, and sets *spte to the spte value. This spte may be non-preset. If no diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index f332b33bc817..af10bc0380a3 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -462,6 +462,23 @@ static inline bool is_mmu_writable_spte(u64 spte) } /* + * Returns true if the access indicated by @fault is allowed by the existing + * SPTE protections. Note, the caller is responsible for checking that the + * SPTE is a shadow-present, leaf SPTE (either before or after). + */ +static inline bool is_access_allowed(struct kvm_page_fault *fault, u64 spte) +{ + if (fault->exec) + return is_executable_pte(spte); + + if (fault->write) + return is_writable_pte(spte); + + /* Fault was on Read access */ + return spte & PT_PRESENT_MASK; +} + +/* * If the MMU-writable flag is cleared, i.e. the SPTE is write-protected for * write-tracking, remote TLBs must be flushed, even if the SPTE was read-only, * as KVM allows stale Writable TLB entries to exist. When dirty logging, KVM diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 4508d868f1cd..2f15e0e33903 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -985,6 +985,11 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, if (fault->prefetch && is_shadow_present_pte(iter->old_spte)) return RET_PF_SPURIOUS; + if (is_shadow_present_pte(iter->old_spte) && + is_access_allowed(fault, iter->old_spte) && + is_last_spte(iter->old_spte, iter->level)) + return RET_PF_SPURIOUS; + if (unlikely(!fault->slot)) new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL); else diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 4b74ea91f4e6..65fd245a9953 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -1199,6 +1199,12 @@ bool avic_hardware_setup(void) return false; } + if (cc_platform_has(CC_ATTR_HOST_SEV_SNP) && + !boot_cpu_has(X86_FEATURE_HV_INUSE_WR_ALLOWED)) { + pr_warn("AVIC disabled: missing HvInUseWrAllowed on SNP-enabled system\n"); + return false; + } + if (boot_cpu_has(X86_FEATURE_AVIC)) { pr_info("AVIC enabled\n"); } else if (force_avic) { diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index dd15cc635655..21dacd312779 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3201,15 +3201,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) if (data & ~supported_de_cfg) return 1; - /* - * Don't let the guest change the host-programmed value. The - * MSR is very model specific, i.e. contains multiple bits that - * are completely unknown to KVM, and the one bit known to KVM - * is simply a reflection of hardware capabilities. - */ - if (!msr->host_initiated && data != svm->msr_decfg) - return 1; - svm->msr_decfg = data; break; } diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h index 1715d2ab07be..ad9116a99bcc 100644 --- a/arch/x86/kvm/vmx/posted_intr.h +++ b/arch/x86/kvm/vmx/posted_intr.h @@ -2,7 +2,7 @@ #ifndef __KVM_X86_VMX_POSTED_INTR_H #define __KVM_X86_VMX_POSTED_INTR_H -#include <linux/find.h> +#include <linux/bitmap.h> #include <asm/posted_intr.h> void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c8160baf3838..c79a8cc57ba4 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9976,7 +9976,7 @@ static int complete_hypercall_exit(struct kvm_vcpu *vcpu) { u64 ret = vcpu->run->hypercall.ret; - if (!is_64_bit_mode(vcpu)) + if (!is_64_bit_hypercall(vcpu)) ret = (u32)ret; kvm_rax_write(vcpu, ret); ++vcpu->stat.hypercalls; @@ -12724,6 +12724,13 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_hv_init_vm(kvm); kvm_xen_init_vm(kvm); + if (ignore_msrs && !report_ignored_msrs) { + pr_warn_once("Running KVM with ignore_msrs=1 and report_ignored_msrs=0 is not a\n" + "a supported configuration. Lying to the guest about the existence of MSRs\n" + "may cause the guest operating system to hang or produce errors. If a guest\n" + "does not run without ignore_msrs=1, please report it to kvm@vger.kernel.org.\n"); + } + return 0; out_uninit_mmu: diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 84e5adbd0925..43dcd8c7badc 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -2,6 +2,7 @@ #include <linux/console.h> #include <linux/cpu.h> +#include <linux/instrumentation.h> #include <linux/kexec.h> #include <linux/memblock.h> #include <linux/slab.h> @@ -21,7 +22,8 @@ #include "xen-ops.h" -EXPORT_SYMBOL_GPL(hypercall_page); +DEFINE_STATIC_CALL(xen_hypercall, xen_hypercall_hvm); +EXPORT_STATIC_CALL_TRAMP(xen_hypercall); /* * Pointer to the xen_vcpu_info structure or @@ -68,6 +70,67 @@ EXPORT_SYMBOL(xen_start_flags); */ struct shared_info *HYPERVISOR_shared_info = &xen_dummy_shared_info; +static __ref void xen_get_vendor(void) +{ + init_cpu_devs(); + cpu_detect(&boot_cpu_data); + get_cpu_vendor(&boot_cpu_data); +} + +void xen_hypercall_setfunc(void) +{ + if (static_call_query(xen_hypercall) != xen_hypercall_hvm) + return; + + if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) + static_call_update(xen_hypercall, xen_hypercall_amd); + else + static_call_update(xen_hypercall, xen_hypercall_intel); +} + +/* + * Evaluate processor vendor in order to select the correct hypercall + * function for HVM/PVH guests. + * Might be called very early in boot before vendor has been set by + * early_cpu_init(). + */ +noinstr void *__xen_hypercall_setfunc(void) +{ + void (*func)(void); + + /* + * Xen is supported only on CPUs with CPUID, so testing for + * X86_FEATURE_CPUID is a test for early_cpu_init() having been + * run. + * + * Note that __xen_hypercall_setfunc() is noinstr only due to a nasty + * dependency chain: it is being called via the xen_hypercall static + * call when running as a PVH or HVM guest. Hypercalls need to be + * noinstr due to PV guests using hypercalls in noinstr code. So we + * can safely tag the function body as "instrumentation ok", since + * the PV guest requirement is not of interest here (xen_get_vendor() + * calls noinstr functions, and static_call_update_early() might do + * so, too). + */ + instrumentation_begin(); + + if (!boot_cpu_has(X86_FEATURE_CPUID)) + xen_get_vendor(); + + if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) + func = xen_hypercall_amd; + else + func = xen_hypercall_intel; + + static_call_update_early(xen_hypercall, func); + + instrumentation_end(); + + return func; +} + static int xen_cpu_up_online(unsigned int cpu) { xen_init_lock_cpu(cpu); diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 24d2957a4726..fe57ff85d004 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -106,15 +106,8 @@ static void __init init_hvm_pv_info(void) /* PVH set up hypercall page in xen_prepare_pvh(). */ if (xen_pvh_domain()) pv_info.name = "Xen PVH"; - else { - u64 pfn; - uint32_t msr; - + else pv_info.name = "Xen HVM"; - msr = cpuid_ebx(base + 2); - pfn = __pa(hypercall_page); - wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); - } xen_setup_features(); @@ -300,6 +293,10 @@ static uint32_t __init xen_platform_hvm(void) if (xen_pv_domain()) return 0; + /* Set correct hypercall function. */ + if (xen_domain) + xen_hypercall_setfunc(); + if (xen_pvh_domain() && nopv) { /* Guest booting via the Xen-PVH boot entry goes here */ pr_info("\"nopv\" parameter is ignored in PVH guest\n"); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index d6818c6cafda..a8eb7e0c473c 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1341,6 +1341,9 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si) xen_domain_type = XEN_PV_DOMAIN; xen_start_flags = xen_start_info->flags; + /* Interrupts are guaranteed to be off initially. */ + early_boot_irqs_disabled = true; + static_call_update_early(xen_hypercall, xen_hypercall_pv); xen_setup_features(); @@ -1431,7 +1434,6 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si) WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_pv, xen_cpu_dead_pv)); local_irq_disable(); - early_boot_irqs_disabled = true; xen_raw_console_write("mapping kernel into physical memory\n"); xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base, diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index bf68c329fc01..0e3d930bcb89 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -129,17 +129,10 @@ static void __init pvh_arch_setup(void) void __init xen_pvh_init(struct boot_params *boot_params) { - u32 msr; - u64 pfn; - xen_pvh = 1; xen_domain_type = XEN_HVM_DOMAIN; xen_start_flags = pvh_start_info.flags; - msr = cpuid_ebx(xen_cpuid_base() + 2); - pfn = __pa(hypercall_page); - wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); - x86_init.oem.arch_setup = pvh_arch_setup; x86_init.oem.banner = xen_banner; diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 83189cf5cdce..b518f36d1ca2 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -20,10 +20,33 @@ #include <linux/init.h> #include <linux/linkage.h> +#include <linux/objtool.h> #include <../entry/calling.h> .pushsection .noinstr.text, "ax" /* + * PV hypercall interface to the hypervisor. + * + * Called via inline asm(), so better preserve %rcx and %r11. + * + * Input: + * %eax: hypercall number + * %rdi, %rsi, %rdx, %r10, %r8: args 1..5 for the hypercall + * Output: %rax + */ +SYM_FUNC_START(xen_hypercall_pv) + ANNOTATE_NOENDBR + push %rcx + push %r11 + UNWIND_HINT_SAVE + syscall + UNWIND_HINT_RESTORE + pop %r11 + pop %rcx + RET +SYM_FUNC_END(xen_hypercall_pv) + +/* * Disabling events is simply a matter of making the event mask * non-zero. */ @@ -176,7 +199,6 @@ SYM_CODE_START(xen_early_idt_handler_array) SYM_CODE_END(xen_early_idt_handler_array) __FINIT -hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 /* * Xen64 iret frame: * @@ -186,17 +208,28 @@ hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 * cs * rip <-- standard iret frame * - * flags + * flags <-- xen_iret must push from here on * - * rcx } - * r11 }<-- pushed by hypercall page - * rsp->rax } + * rcx + * r11 + * rsp->rax */ +.macro xen_hypercall_iret + pushq $0 /* Flags */ + push %rcx + push %r11 + push %rax + mov $__HYPERVISOR_iret, %eax + syscall /* Do the IRET. */ +#ifdef CONFIG_MITIGATION_SLS + int3 +#endif +.endm + SYM_CODE_START(xen_iret) UNWIND_HINT_UNDEFINED ANNOTATE_NOENDBR - pushq $0 - jmp hypercall_iret + xen_hypercall_iret SYM_CODE_END(xen_iret) /* @@ -301,8 +334,7 @@ SYM_CODE_START(xen_entry_SYSENTER_compat) ENDBR lea 16(%rsp), %rsp /* strip %rcx, %r11 */ mov $-ENOSYS, %rax - pushq $0 - jmp hypercall_iret + xen_hypercall_iret SYM_CODE_END(xen_entry_SYSENTER_compat) SYM_CODE_END(xen_entry_SYSCALL_compat) diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 7f6c69dbb816..9252652afe59 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -6,9 +6,11 @@ #include <linux/elfnote.h> #include <linux/init.h> +#include <linux/instrumentation.h> #include <asm/boot.h> #include <asm/asm.h> +#include <asm/frame.h> #include <asm/msr.h> #include <asm/page_types.h> #include <asm/percpu.h> @@ -20,28 +22,6 @@ #include <xen/interface/xen-mca.h> #include <asm/xen/interface.h> -.pushsection .noinstr.text, "ax" - .balign PAGE_SIZE -SYM_CODE_START(hypercall_page) - .rept (PAGE_SIZE / 32) - UNWIND_HINT_FUNC - ANNOTATE_NOENDBR - ANNOTATE_UNRET_SAFE - ret - /* - * Xen will write the hypercall page, and sort out ENDBR. - */ - .skip 31, 0xcc - .endr - -#define HYPERCALL(n) \ - .equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \ - .type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32 -#include <asm/xen-hypercalls.h> -#undef HYPERCALL -SYM_CODE_END(hypercall_page) -.popsection - #ifdef CONFIG_XEN_PV __INIT SYM_CODE_START(startup_xen) @@ -87,6 +67,87 @@ SYM_CODE_END(xen_cpu_bringup_again) #endif #endif + .pushsection .noinstr.text, "ax" +/* + * Xen hypercall interface to the hypervisor. + * + * Input: + * %eax: hypercall number + * 32-bit: + * %ebx, %ecx, %edx, %esi, %edi: args 1..5 for the hypercall + * 64-bit: + * %rdi, %rsi, %rdx, %r10, %r8: args 1..5 for the hypercall + * Output: %[er]ax + */ +SYM_FUNC_START(xen_hypercall_hvm) + ENDBR + FRAME_BEGIN + /* Save all relevant registers (caller save and arguments). */ +#ifdef CONFIG_X86_32 + push %eax + push %ebx + push %ecx + push %edx + push %esi + push %edi +#else + push %rax + push %rcx + push %rdx + push %rdi + push %rsi + push %r11 + push %r10 + push %r9 + push %r8 +#ifdef CONFIG_FRAME_POINTER + pushq $0 /* Dummy push for stack alignment. */ +#endif +#endif + /* Set the vendor specific function. */ + call __xen_hypercall_setfunc + /* Set ZF = 1 if AMD, Restore saved registers. */ +#ifdef CONFIG_X86_32 + lea xen_hypercall_amd, %ebx + cmp %eax, %ebx + pop %edi + pop %esi + pop %edx + pop %ecx + pop %ebx + pop %eax +#else + lea xen_hypercall_amd(%rip), %rbx + cmp %rax, %rbx +#ifdef CONFIG_FRAME_POINTER + pop %rax /* Dummy pop. */ +#endif + pop %r8 + pop %r9 + pop %r10 + pop %r11 + pop %rsi + pop %rdi + pop %rdx + pop %rcx + pop %rax +#endif + /* Use correct hypercall function. */ + jz xen_hypercall_amd + jmp xen_hypercall_intel +SYM_FUNC_END(xen_hypercall_hvm) + +SYM_FUNC_START(xen_hypercall_amd) + vmmcall + RET +SYM_FUNC_END(xen_hypercall_amd) + +SYM_FUNC_START(xen_hypercall_intel) + vmcall + RET +SYM_FUNC_END(xen_hypercall_intel) + .popsection + ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux") ELFNOTE(Xen, XEN_ELFNOTE_GUEST_VERSION, .asciz "2.6") ELFNOTE(Xen, XEN_ELFNOTE_XEN_VERSION, .asciz "xen-3.0") @@ -116,8 +177,6 @@ SYM_CODE_END(xen_cpu_bringup_again) #else # define FEATURES_DOM0 0 #endif - ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, .globl xen_elfnote_hypercall_page; - xen_elfnote_hypercall_page: _ASM_PTR xen_elfnote_hypercall_page_value - .) ELFNOTE(Xen, XEN_ELFNOTE_SUPPORTED_FEATURES, .long FEATURES_PV | FEATURES_PVH | FEATURES_DOM0) ELFNOTE(Xen, XEN_ELFNOTE_LOADER, .asciz "generic") diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index e1b782e823e6..63c13a2ccf55 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -326,4 +326,13 @@ static inline void xen_smp_intr_free_pv(unsigned int cpu) {} static inline void xen_smp_count_cpus(void) { } #endif /* CONFIG_SMP */ +#ifdef CONFIG_XEN_PV +void xen_hypercall_pv(void); +#endif +void xen_hypercall_hvm(void); +void xen_hypercall_amd(void); +void xen_hypercall_intel(void); +void xen_hypercall_setfunc(void); +void *__xen_hypercall_setfunc(void); + #endif /* XEN_OPS_H */ diff --git a/block/bdev.c b/block/bdev.c index 738e3c8457e7..9d73a8fbf7f9 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -155,8 +155,7 @@ int set_blocksize(struct file *file, int size) struct inode *inode = file->f_mapping->host; struct block_device *bdev = I_BDEV(inode); - /* Size must be a power of two, and between 512 and PAGE_SIZE */ - if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size)) + if (blk_validate_block_size(size)) return -EINVAL; /* Size cannot be smaller than the size supported by the device */ diff --git a/block/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/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/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index 99177835cade..b39dee7b93af 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -27,7 +27,8 @@ #include <asm/mshyperv.h> static struct clock_event_device __percpu *hv_clock_event; -static u64 hv_sched_clock_offset __ro_after_init; +/* Note: offset can hold negative values after hibernation. */ +static u64 hv_sched_clock_offset __read_mostly; /* * If false, we're using the old mechanism for stimer0 interrupts @@ -470,6 +471,17 @@ static void resume_hv_clock_tsc(struct clocksource *arg) hv_set_msr(HV_MSR_REFERENCE_TSC, tsc_msr.as_uint64); } +/* + * Called during resume from hibernation, from overridden + * x86_platform.restore_sched_clock_state routine. This is to adjust offsets + * used to calculate time for hv tsc page based sched_clock, to account for + * time spent before hibernation. + */ +void hv_adj_sched_clock_offset(u64 offset) +{ + hv_sched_clock_offset -= offset; +} + #ifdef HAVE_VDSO_CLOCKMODE_HVCLOCK static int hv_cs_enable(struct clocksource *cs) { diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index d7630bab2516..66e5dfc711c0 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -374,15 +374,19 @@ static inline int amd_pstate_cppc_enable(bool enable) static int msr_init_perf(struct amd_cpudata *cpudata) { - u64 cap1; + u64 cap1, numerator; int ret = rdmsrl_safe_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1, &cap1); if (ret) return ret; - WRITE_ONCE(cpudata->highest_perf, AMD_CPPC_HIGHEST_PERF(cap1)); - WRITE_ONCE(cpudata->max_limit_perf, AMD_CPPC_HIGHEST_PERF(cap1)); + ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator); + if (ret) + return ret; + + WRITE_ONCE(cpudata->highest_perf, numerator); + WRITE_ONCE(cpudata->max_limit_perf, numerator); WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1)); WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1)); WRITE_ONCE(cpudata->lowest_perf, AMD_CPPC_LOWEST_PERF(cap1)); @@ -394,13 +398,18 @@ static int msr_init_perf(struct amd_cpudata *cpudata) static int shmem_init_perf(struct amd_cpudata *cpudata) { struct cppc_perf_caps cppc_perf; + u64 numerator; int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); if (ret) return ret; - WRITE_ONCE(cpudata->highest_perf, cppc_perf.highest_perf); - WRITE_ONCE(cpudata->max_limit_perf, cppc_perf.highest_perf); + ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator); + if (ret) + return ret; + + WRITE_ONCE(cpudata->highest_perf, numerator); + WRITE_ONCE(cpudata->max_limit_perf, numerator); WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf); WRITE_ONCE(cpudata->lowest_nonlinear_perf, cppc_perf.lowest_nonlinear_perf); @@ -561,16 +570,13 @@ static int amd_pstate_verify(struct cpufreq_policy_data *policy_data) static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy) { - u32 max_limit_perf, min_limit_perf, lowest_perf, max_perf; + u32 max_limit_perf, min_limit_perf, lowest_perf, max_perf, max_freq; struct amd_cpudata *cpudata = policy->driver_data; - if (cpudata->boost_supported && !policy->boost_enabled) - max_perf = READ_ONCE(cpudata->nominal_perf); - else - max_perf = READ_ONCE(cpudata->highest_perf); - - max_limit_perf = div_u64(policy->max * max_perf, policy->cpuinfo.max_freq); - min_limit_perf = div_u64(policy->min * max_perf, policy->cpuinfo.max_freq); + max_perf = READ_ONCE(cpudata->highest_perf); + max_freq = READ_ONCE(cpudata->max_freq); + max_limit_perf = div_u64(policy->max * max_perf, max_freq); + min_limit_perf = div_u64(policy->min * max_perf, max_freq); lowest_perf = READ_ONCE(cpudata->lowest_perf); if (min_limit_perf < lowest_perf) @@ -889,7 +895,6 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata) { int ret; u32 min_freq, max_freq; - u64 numerator; u32 nominal_perf, nominal_freq; u32 lowest_nonlinear_perf, lowest_nonlinear_freq; u32 boost_ratio, lowest_nonlinear_ratio; @@ -911,10 +916,7 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata) nominal_perf = READ_ONCE(cpudata->nominal_perf); - ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator); - if (ret) - return ret; - boost_ratio = div_u64(numerator << SCHED_CAPACITY_SHIFT, nominal_perf); + boost_ratio = div_u64(cpudata->highest_perf << SCHED_CAPACITY_SHIFT, nominal_perf); max_freq = (nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT) * 1000; lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf); @@ -1869,18 +1871,18 @@ static int __init amd_pstate_init(void) static_call_update(amd_pstate_update_perf, shmem_update_perf); } - ret = amd_pstate_register_driver(cppc_state); - if (ret) { - pr_err("failed to register with return %d\n", ret); - return ret; - } - if (amd_pstate_prefcore) { ret = amd_detect_prefcore(&amd_pstate_prefcore); if (ret) return ret; } + ret = amd_pstate_register_driver(cppc_state); + if (ret) { + pr_err("failed to register with return %d\n", ret); + return ret; + } + dev_root = bus_get_dev_root(&cpu_subsys); if (dev_root) { ret = sysfs_create_group(&dev_root->kobj, &amd_pstate_global_attr_group); diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index d77899650798..b98b1ccffd1c 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -1295,6 +1295,7 @@ static int cxl_port_setup_targets(struct cxl_port *port, struct cxl_region_params *p = &cxlr->params; struct cxl_decoder *cxld = cxl_rr->decoder; struct cxl_switch_decoder *cxlsd; + struct cxl_port *iter = port; u16 eig, peig; u8 eiw, peiw; @@ -1311,16 +1312,26 @@ static int cxl_port_setup_targets(struct cxl_port *port, cxlsd = to_cxl_switch_decoder(&cxld->dev); if (cxl_rr->nr_targets_set) { - int i, distance; + int i, distance = 1; + struct cxl_region_ref *cxl_rr_iter; /* - * Passthrough decoders impose no distance requirements between - * peers + * The "distance" between peer downstream ports represents which + * endpoint positions in the region interleave a given port can + * host. + * + * For example, at the root of a hierarchy the distance is + * always 1 as every index targets a different host-bridge. At + * each subsequent switch level those ports map every Nth region + * position where N is the width of the switch == distance. */ - if (cxl_rr->nr_targets == 1) - distance = 0; - else - distance = p->nr_targets / cxl_rr->nr_targets; + do { + cxl_rr_iter = cxl_rr_load(iter, cxlr); + distance *= cxl_rr_iter->nr_targets; + iter = to_cxl_port(iter->dev.parent); + } while (!is_cxl_root(iter)); + distance *= cxlrd->cxlsd.cxld.interleave_ways; + for (i = 0; i < cxl_rr->nr_targets_set; i++) if (ep->dport == cxlsd->target[i]) { rc = check_last_peer(cxled, ep, cxl_rr, diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 0241d1d7133a..6d94ff4a4f1a 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -836,6 +836,9 @@ static ssize_t rcd_pcie_cap_emit(struct device *dev, u16 offset, char *buf, size if (!root_dev) return -ENXIO; + if (!dport->regs.rcd_pcie_cap) + return -ENXIO; + guard(device)(root_dev); if (!root_dev->driver) return -ENXIO; @@ -1032,8 +1035,7 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (rc) return rc; - rc = cxl_pci_ras_unmask(pdev); - if (rc) + if (cxl_pci_ras_unmask(pdev)) dev_dbg(&pdev->dev, "No RAS reporting unmasked\n"); pci_save_state(pdev); diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 7eeee3a38202..5baa83b85515 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -60,7 +60,7 @@ static void __dma_buf_debugfs_list_add(struct dma_buf *dmabuf) { } -static void __dma_buf_debugfs_list_del(struct file *file) +static void __dma_buf_debugfs_list_del(struct dma_buf *dmabuf) { } #endif diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c index 8ce1f074c2d3..cc7398cc17d6 100644 --- a/drivers/dma-buf/udmabuf.c +++ b/drivers/dma-buf/udmabuf.c @@ -297,7 +297,7 @@ static const struct dma_buf_ops udmabuf_ops = { }; #define SEALS_WANTED (F_SEAL_SHRINK) -#define SEALS_DENIED (F_SEAL_WRITE) +#define SEALS_DENIED (F_SEAL_WRITE|F_SEAL_FUTURE_WRITE) static int check_memfd_seals(struct file *memfd) { @@ -317,12 +317,10 @@ static int check_memfd_seals(struct file *memfd) return 0; } -static int export_udmabuf(struct udmabuf *ubuf, - struct miscdevice *device, - u32 flags) +static struct dma_buf *export_udmabuf(struct udmabuf *ubuf, + struct miscdevice *device) { DEFINE_DMA_BUF_EXPORT_INFO(exp_info); - struct dma_buf *buf; ubuf->device = device; exp_info.ops = &udmabuf_ops; @@ -330,11 +328,7 @@ static int export_udmabuf(struct udmabuf *ubuf, exp_info.priv = ubuf; exp_info.flags = O_RDWR; - buf = dma_buf_export(&exp_info); - if (IS_ERR(buf)) - return PTR_ERR(buf); - - return dma_buf_fd(buf, flags); + return dma_buf_export(&exp_info); } static long udmabuf_pin_folios(struct udmabuf *ubuf, struct file *memfd, @@ -391,6 +385,7 @@ static long udmabuf_create(struct miscdevice *device, struct folio **folios = NULL; pgoff_t pgcnt = 0, pglimit; struct udmabuf *ubuf; + struct dma_buf *dmabuf; long ret = -EINVAL; u32 i, flags; @@ -436,23 +431,39 @@ static long udmabuf_create(struct miscdevice *device, goto err; } + /* + * Take the inode lock to protect against concurrent + * memfd_add_seals(), which takes this lock in write mode. + */ + inode_lock_shared(file_inode(memfd)); ret = check_memfd_seals(memfd); - if (ret < 0) { - fput(memfd); - goto err; - } + if (ret) + goto out_unlock; ret = udmabuf_pin_folios(ubuf, memfd, list[i].offset, list[i].size, folios); +out_unlock: + inode_unlock_shared(file_inode(memfd)); fput(memfd); if (ret) goto err; } flags = head->flags & UDMABUF_FLAGS_CLOEXEC ? O_CLOEXEC : 0; - ret = export_udmabuf(ubuf, device, flags); - if (ret < 0) + dmabuf = export_udmabuf(ubuf, device); + if (IS_ERR(dmabuf)) { + ret = PTR_ERR(dmabuf); goto err; + } + /* + * Ownership of ubuf is held by the dmabuf from here. + * If the following dma_buf_fd() fails, dma_buf_put() cleans up both the + * dmabuf and the ubuf (through udmabuf_ops.release). + */ + + ret = dma_buf_fd(dmabuf, flags); + if (ret < 0) + dma_buf_put(dmabuf); kvfree(folios); return ret; diff --git a/drivers/dma/amd/qdma/qdma.c b/drivers/dma/amd/qdma/qdma.c index 6d9079458fe9..66f00ad67351 100644 --- a/drivers/dma/amd/qdma/qdma.c +++ b/drivers/dma/amd/qdma/qdma.c @@ -7,9 +7,9 @@ #include <linux/bitfield.h> #include <linux/bitops.h> #include <linux/dmaengine.h> +#include <linux/dma-mapping.h> #include <linux/module.h> #include <linux/mod_devicetable.h> -#include <linux/dma-map-ops.h> #include <linux/platform_device.h> #include <linux/platform_data/amd_qdma.h> #include <linux/regmap.h> @@ -492,18 +492,9 @@ static int qdma_device_verify(struct qdma_device *qdev) static int qdma_device_setup(struct qdma_device *qdev) { - struct device *dev = &qdev->pdev->dev; u32 ring_sz = QDMA_DEFAULT_RING_SIZE; int ret = 0; - while (dev && get_dma_ops(dev)) - dev = dev->parent; - if (!dev) { - qdma_err(qdev, "dma device not found"); - return -EINVAL; - } - set_dma_ops(&qdev->pdev->dev, get_dma_ops(dev)); - ret = qdma_setup_fmap_context(qdev); if (ret) { qdma_err(qdev, "Failed setup fmap context"); @@ -548,11 +539,12 @@ static void qdma_free_queue_resources(struct dma_chan *chan) { struct qdma_queue *queue = to_qdma_queue(chan); struct qdma_device *qdev = queue->qdev; - struct device *dev = qdev->dma_dev.dev; + struct qdma_platdata *pdata; qdma_clear_queue_context(queue); vchan_free_chan_resources(&queue->vchan); - dma_free_coherent(dev, queue->ring_size * QDMA_MM_DESC_SIZE, + pdata = dev_get_platdata(&qdev->pdev->dev); + dma_free_coherent(pdata->dma_dev, queue->ring_size * QDMA_MM_DESC_SIZE, queue->desc_base, queue->dma_desc_base); } @@ -565,6 +557,7 @@ static int qdma_alloc_queue_resources(struct dma_chan *chan) struct qdma_queue *queue = to_qdma_queue(chan); struct qdma_device *qdev = queue->qdev; struct qdma_ctxt_sw_desc desc; + struct qdma_platdata *pdata; size_t size; int ret; @@ -572,8 +565,9 @@ static int qdma_alloc_queue_resources(struct dma_chan *chan) if (ret) return ret; + pdata = dev_get_platdata(&qdev->pdev->dev); size = queue->ring_size * QDMA_MM_DESC_SIZE; - queue->desc_base = dma_alloc_coherent(qdev->dma_dev.dev, size, + queue->desc_base = dma_alloc_coherent(pdata->dma_dev, size, &queue->dma_desc_base, GFP_KERNEL); if (!queue->desc_base) { @@ -588,7 +582,7 @@ static int qdma_alloc_queue_resources(struct dma_chan *chan) if (ret) { qdma_err(qdev, "Failed to setup SW desc ctxt for %s", chan->name); - dma_free_coherent(qdev->dma_dev.dev, size, queue->desc_base, + dma_free_coherent(pdata->dma_dev, size, queue->desc_base, queue->dma_desc_base); return ret; } @@ -948,8 +942,9 @@ static int qdma_init_error_irq(struct qdma_device *qdev) static int qdmam_alloc_qintr_rings(struct qdma_device *qdev) { - u32 ctxt[QDMA_CTXT_REGMAP_LEN]; + struct qdma_platdata *pdata = dev_get_platdata(&qdev->pdev->dev); struct device *dev = &qdev->pdev->dev; + u32 ctxt[QDMA_CTXT_REGMAP_LEN]; struct qdma_intr_ring *ring; struct qdma_ctxt_intr intr_ctxt; u32 vector; @@ -969,7 +964,8 @@ static int qdmam_alloc_qintr_rings(struct qdma_device *qdev) ring->msix_id = qdev->err_irq_idx + i + 1; ring->ridx = i; ring->color = 1; - ring->base = dmam_alloc_coherent(dev, QDMA_INTR_RING_SIZE, + ring->base = dmam_alloc_coherent(pdata->dma_dev, + QDMA_INTR_RING_SIZE, &ring->dev_base, GFP_KERNEL); if (!ring->base) { qdma_err(qdev, "Failed to alloc intr ring %d", i); diff --git a/drivers/dma/apple-admac.c b/drivers/dma/apple-admac.c index c499173d80b2..bd49f0374291 100644 --- a/drivers/dma/apple-admac.c +++ b/drivers/dma/apple-admac.c @@ -153,6 +153,8 @@ static int admac_alloc_sram_carveout(struct admac_data *ad, { struct admac_sram *sram; int i, ret = 0, nblocks; + ad->txcache.size = readl_relaxed(ad->base + REG_TX_SRAM_SIZE); + ad->rxcache.size = readl_relaxed(ad->base + REG_RX_SRAM_SIZE); if (dir == DMA_MEM_TO_DEV) sram = &ad->txcache; @@ -912,12 +914,7 @@ static int admac_probe(struct platform_device *pdev) goto free_irq; } - ad->txcache.size = readl_relaxed(ad->base + REG_TX_SRAM_SIZE); - ad->rxcache.size = readl_relaxed(ad->base + REG_RX_SRAM_SIZE); - dev_info(&pdev->dev, "Audio DMA Controller\n"); - dev_info(&pdev->dev, "imprint %x TX cache %u RX cache %u\n", - readl_relaxed(ad->base + REG_IMPRINT), ad->txcache.size, ad->rxcache.size); return 0; diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 9c7b40220004..ba25c23164e7 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -1363,6 +1363,8 @@ at_xdmac_prep_dma_memset(struct dma_chan *chan, dma_addr_t dest, int value, return NULL; desc = at_xdmac_memset_create_desc(chan, atchan, dest, len, value); + if (!desc) + return NULL; list_add_tail(&desc->desc_node, &desc->descs_list); desc->tx_dma_desc.cookie = -EBUSY; diff --git a/drivers/dma/dw/acpi.c b/drivers/dma/dw/acpi.c index c510c109d2c3..b6452fffa657 100644 --- a/drivers/dma/dw/acpi.c +++ b/drivers/dma/dw/acpi.c @@ -8,13 +8,15 @@ static bool dw_dma_acpi_filter(struct dma_chan *chan, void *param) { + struct dw_dma *dw = to_dw_dma(chan->device); + struct dw_dma_chip_pdata *data = dev_get_drvdata(dw->dma.dev); struct acpi_dma_spec *dma_spec = param; struct dw_dma_slave slave = { .dma_dev = dma_spec->dev, .src_id = dma_spec->slave_id, .dst_id = dma_spec->slave_id, - .m_master = 0, - .p_master = 1, + .m_master = data->m_master, + .p_master = data->p_master, }; return dw_dma_filter(chan, &slave); diff --git a/drivers/dma/dw/internal.h b/drivers/dma/dw/internal.h index 563ce73488db..f1bd06a20cd6 100644 --- a/drivers/dma/dw/internal.h +++ b/drivers/dma/dw/internal.h @@ -51,11 +51,15 @@ struct dw_dma_chip_pdata { int (*probe)(struct dw_dma_chip *chip); int (*remove)(struct dw_dma_chip *chip); struct dw_dma_chip *chip; + u8 m_master; + u8 p_master; }; static __maybe_unused const struct dw_dma_chip_pdata dw_dma_chip_pdata = { .probe = dw_dma_probe, .remove = dw_dma_remove, + .m_master = 0, + .p_master = 1, }; static const struct dw_dma_platform_data idma32_pdata = { @@ -72,6 +76,8 @@ static __maybe_unused const struct dw_dma_chip_pdata idma32_chip_pdata = { .pdata = &idma32_pdata, .probe = idma32_dma_probe, .remove = idma32_dma_remove, + .m_master = 0, + .p_master = 0, }; static const struct dw_dma_platform_data xbar_pdata = { @@ -88,6 +94,8 @@ static __maybe_unused const struct dw_dma_chip_pdata xbar_chip_pdata = { .pdata = &xbar_pdata, .probe = idma32_dma_probe, .remove = idma32_dma_remove, + .m_master = 0, + .p_master = 0, }; #endif /* _DMA_DW_INTERNAL_H */ diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c index ad2d4d012cf7..e8a0eb81726a 100644 --- a/drivers/dma/dw/pci.c +++ b/drivers/dma/dw/pci.c @@ -56,10 +56,10 @@ static int dw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *pid) if (ret) return ret; - dw_dma_acpi_controller_register(chip->dw); - pci_set_drvdata(pdev, data); + dw_dma_acpi_controller_register(chip->dw); + return 0; } diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h index ce37e1ee9c46..fe8f103d4a63 100644 --- a/drivers/dma/fsl-edma-common.h +++ b/drivers/dma/fsl-edma-common.h @@ -166,6 +166,7 @@ struct fsl_edma_chan { struct work_struct issue_worker; struct platform_device *pdev; struct device *pd_dev; + struct device_link *pd_dev_link; u32 srcid; struct clk *clk; int priority; diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c index 60de1003193a..1a613236b3e4 100644 --- a/drivers/dma/fsl-edma-main.c +++ b/drivers/dma/fsl-edma-main.c @@ -417,10 +417,33 @@ static const struct of_device_id fsl_edma_dt_ids[] = { }; MODULE_DEVICE_TABLE(of, fsl_edma_dt_ids); +static void fsl_edma3_detach_pd(struct fsl_edma_engine *fsl_edma) +{ + struct fsl_edma_chan *fsl_chan; + int i; + + for (i = 0; i < fsl_edma->n_chans; i++) { + if (fsl_edma->chan_masked & BIT(i)) + continue; + fsl_chan = &fsl_edma->chans[i]; + if (fsl_chan->pd_dev_link) + device_link_del(fsl_chan->pd_dev_link); + if (fsl_chan->pd_dev) { + dev_pm_domain_detach(fsl_chan->pd_dev, false); + pm_runtime_dont_use_autosuspend(fsl_chan->pd_dev); + pm_runtime_set_suspended(fsl_chan->pd_dev); + } + } +} + +static void devm_fsl_edma3_detach_pd(void *data) +{ + fsl_edma3_detach_pd(data); +} + static int fsl_edma3_attach_pd(struct platform_device *pdev, struct fsl_edma_engine *fsl_edma) { struct fsl_edma_chan *fsl_chan; - struct device_link *link; struct device *pd_chan; struct device *dev; int i; @@ -436,15 +459,16 @@ static int fsl_edma3_attach_pd(struct platform_device *pdev, struct fsl_edma_eng pd_chan = dev_pm_domain_attach_by_id(dev, i); if (IS_ERR_OR_NULL(pd_chan)) { dev_err(dev, "Failed attach pd %d\n", i); - return -EINVAL; + goto detach; } - link = device_link_add(dev, pd_chan, DL_FLAG_STATELESS | + fsl_chan->pd_dev_link = device_link_add(dev, pd_chan, DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE); - if (!link) { + if (!fsl_chan->pd_dev_link) { dev_err(dev, "Failed to add device_link to %d\n", i); - return -EINVAL; + dev_pm_domain_detach(pd_chan, false); + goto detach; } fsl_chan->pd_dev = pd_chan; @@ -455,6 +479,10 @@ static int fsl_edma3_attach_pd(struct platform_device *pdev, struct fsl_edma_eng } return 0; + +detach: + fsl_edma3_detach_pd(fsl_edma); + return -EINVAL; } static int fsl_edma_probe(struct platform_device *pdev) @@ -544,6 +572,9 @@ static int fsl_edma_probe(struct platform_device *pdev) ret = fsl_edma3_attach_pd(pdev, fsl_edma); if (ret) return ret; + ret = devm_add_action_or_reset(&pdev->dev, devm_fsl_edma3_detach_pd, fsl_edma); + if (ret) + return ret; } if (drvdata->flags & FSL_EDMA_DRV_TCD64) diff --git a/drivers/dma/loongson2-apb-dma.c b/drivers/dma/loongson2-apb-dma.c index 367ed34ce4da..c528f02b9f84 100644 --- a/drivers/dma/loongson2-apb-dma.c +++ b/drivers/dma/loongson2-apb-dma.c @@ -31,7 +31,7 @@ #define LDMA_ASK_VALID BIT(2) #define LDMA_START BIT(3) /* DMA start operation */ #define LDMA_STOP BIT(4) /* DMA stop operation */ -#define LDMA_CONFIG_MASK GENMASK(4, 0) /* DMA controller config bits mask */ +#define LDMA_CONFIG_MASK GENMASK_ULL(4, 0) /* DMA controller config bits mask */ /* Bitfields in ndesc_addr field of HW descriptor */ #define LDMA_DESC_EN BIT(0) /*1: The next descriptor is valid */ diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c index 43efce77bb57..40b76b40bc30 100644 --- a/drivers/dma/mv_xor.c +++ b/drivers/dma/mv_xor.c @@ -1388,6 +1388,7 @@ static int mv_xor_probe(struct platform_device *pdev) irq = irq_of_parse_and_map(np, 0); if (!irq) { ret = -ENODEV; + of_node_put(np); goto err_channel_add; } @@ -1396,6 +1397,7 @@ static int mv_xor_probe(struct platform_device *pdev) if (IS_ERR(chan)) { ret = PTR_ERR(chan); irq_dispose_mapping(irq); + of_node_put(np); goto err_channel_add; } diff --git a/drivers/dma/tegra186-gpc-dma.c b/drivers/dma/tegra186-gpc-dma.c index cacf3757adc2..4d6fe0efa76e 100644 --- a/drivers/dma/tegra186-gpc-dma.c +++ b/drivers/dma/tegra186-gpc-dma.c @@ -231,6 +231,7 @@ struct tegra_dma_channel { bool config_init; char name[30]; enum dma_transfer_direction sid_dir; + enum dma_status status; int id; int irq; int slave_id; @@ -393,6 +394,8 @@ static int tegra_dma_pause(struct tegra_dma_channel *tdc) tegra_dma_dump_chan_regs(tdc); } + tdc->status = DMA_PAUSED; + return ret; } @@ -419,6 +422,8 @@ static void tegra_dma_resume(struct tegra_dma_channel *tdc) val = tdc_read(tdc, TEGRA_GPCDMA_CHAN_CSRE); val &= ~TEGRA_GPCDMA_CHAN_CSRE_PAUSE; tdc_write(tdc, TEGRA_GPCDMA_CHAN_CSRE, val); + + tdc->status = DMA_IN_PROGRESS; } static int tegra_dma_device_resume(struct dma_chan *dc) @@ -544,6 +549,7 @@ static void tegra_dma_xfer_complete(struct tegra_dma_channel *tdc) tegra_dma_sid_free(tdc); tdc->dma_desc = NULL; + tdc->status = DMA_COMPLETE; } static void tegra_dma_chan_decode_error(struct tegra_dma_channel *tdc, @@ -716,6 +722,7 @@ static int tegra_dma_terminate_all(struct dma_chan *dc) tdc->dma_desc = NULL; } + tdc->status = DMA_COMPLETE; tegra_dma_sid_free(tdc); vchan_get_all_descriptors(&tdc->vc, &head); spin_unlock_irqrestore(&tdc->vc.lock, flags); @@ -769,6 +776,9 @@ static enum dma_status tegra_dma_tx_status(struct dma_chan *dc, if (ret == DMA_COMPLETE) return ret; + if (tdc->status == DMA_PAUSED) + ret = DMA_PAUSED; + spin_lock_irqsave(&tdc->vc.lock, flags); vd = vchan_find_desc(&tdc->vc, cookie); if (vd) { diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c index eb17d03b66fe..dfda5ffc14db 100644 --- a/drivers/firmware/arm_ffa/bus.c +++ b/drivers/firmware/arm_ffa/bus.c @@ -187,13 +187,18 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev) return valid; } -struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, - const struct ffa_ops *ops) +struct ffa_device * +ffa_device_register(const struct ffa_partition_info *part_info, + const struct ffa_ops *ops) { int id, ret; + uuid_t uuid; struct device *dev; struct ffa_device *ffa_dev; + if (!part_info) + return NULL; + id = ida_alloc_min(&ffa_bus_id, 1, GFP_KERNEL); if (id < 0) return NULL; @@ -210,9 +215,11 @@ struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, dev_set_name(&ffa_dev->dev, "arm-ffa-%d", id); ffa_dev->id = id; - ffa_dev->vm_id = vm_id; + ffa_dev->vm_id = part_info->id; + ffa_dev->properties = part_info->properties; ffa_dev->ops = ops; - uuid_copy(&ffa_dev->uuid, uuid); + import_uuid(&uuid, (u8 *)part_info->uuid); + uuid_copy(&ffa_dev->uuid, &uuid); ret = device_register(&ffa_dev->dev); if (ret) { diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index b14cbdae94e8..2c2ec3c35f15 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -1387,7 +1387,6 @@ static struct notifier_block ffa_bus_nb = { static int ffa_setup_partitions(void) { int count, idx, ret; - uuid_t uuid; struct ffa_device *ffa_dev; struct ffa_dev_part_info *info; struct ffa_partition_info *pbuf, *tpbuf; @@ -1406,23 +1405,19 @@ static int ffa_setup_partitions(void) xa_init(&drv_info->partition_info); for (idx = 0, tpbuf = pbuf; idx < count; idx++, tpbuf++) { - import_uuid(&uuid, (u8 *)tpbuf->uuid); - /* Note that if the UUID will be uuid_null, that will require * ffa_bus_notifier() to find the UUID of this partition id * with help of ffa_device_match_uuid(). FF-A v1.1 and above * provides UUID here for each partition as part of the * discovery API and the same is passed. */ - ffa_dev = ffa_device_register(&uuid, tpbuf->id, &ffa_drv_ops); + ffa_dev = ffa_device_register(tpbuf, &ffa_drv_ops); if (!ffa_dev) { pr_err("%s: failed to register partition ID 0x%x\n", __func__, tpbuf->id); continue; } - ffa_dev->properties = tpbuf->properties; - if (drv_info->version > FFA_VERSION_1_0 && !(tpbuf->properties & FFA_PARTITION_AARCH64_EXEC)) ffa_mode_32bit_set(ffa_dev); diff --git a/drivers/firmware/arm_scmi/vendors/imx/Kconfig b/drivers/firmware/arm_scmi/vendors/imx/Kconfig index 2883ed24a84d..a01bf5e47301 100644 --- a/drivers/firmware/arm_scmi/vendors/imx/Kconfig +++ b/drivers/firmware/arm_scmi/vendors/imx/Kconfig @@ -15,6 +15,7 @@ config IMX_SCMI_BBM_EXT config IMX_SCMI_MISC_EXT tristate "i.MX SCMI MISC EXTENSION" depends on ARM_SCMI_PROTOCOL || (COMPILE_TEST && OF) + depends on IMX_SCMI_MISC_DRV default y if ARCH_MXC help This enables i.MX System MISC control logic such as gpio expander diff --git a/drivers/firmware/imx/Kconfig b/drivers/firmware/imx/Kconfig index 477d3f32d99a..907cd149c40a 100644 --- a/drivers/firmware/imx/Kconfig +++ b/drivers/firmware/imx/Kconfig @@ -25,7 +25,6 @@ config IMX_SCU config IMX_SCMI_MISC_DRV tristate "IMX SCMI MISC Protocol driver" - depends on IMX_SCMI_MISC_EXT || COMPILE_TEST default y if ARCH_MXC help The System Controller Management Interface firmware (SCMI FW) is diff --git a/drivers/firmware/microchip/mpfs-auto-update.c b/drivers/firmware/microchip/mpfs-auto-update.c index 38a03698cec9..e194f7acb2a9 100644 --- a/drivers/firmware/microchip/mpfs-auto-update.c +++ b/drivers/firmware/microchip/mpfs-auto-update.c @@ -402,10 +402,10 @@ static int mpfs_auto_update_available(struct mpfs_auto_update_priv *priv) return -EIO; /* - * Bit 5 of byte 1 is "UL_Auto Update" & if it is set, Auto Update is + * Bit 5 of byte 1 is "UL_IAP" & if it is set, Auto Update is * not possible. */ - if (response_msg[1] & AUTO_UPDATE_FEATURE_ENABLED) + if ((((u8 *)response_msg)[1] & AUTO_UPDATE_FEATURE_ENABLED)) return -EPERM; return 0; diff --git a/drivers/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/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/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/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/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index c38dcdfcb914..a99112e6f0b8 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -756,7 +756,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size, * adding succeeded, it is ok to proceed even if the memory was * not onlined in time. */ - wait_for_completion_timeout(&dm_device.ol_waitevent, 5 * HZ); + wait_for_completion_timeout(&dm_device.ol_waitevent, secs_to_jiffies(5)); post_status(&dm_device); } } @@ -1373,7 +1373,8 @@ static int dm_thread_func(void *dm_dev) struct hv_dynmem_device *dm = dm_dev; while (!kthread_should_stop()) { - wait_for_completion_interruptible_timeout(&dm_device.config_event, 1 * HZ); + wait_for_completion_interruptible_timeout(&dm_device.config_event, + secs_to_jiffies(1)); /* * The host expects us to post information on the memory * pressure every second. @@ -1748,7 +1749,7 @@ static int balloon_connect_vsp(struct hv_device *dev) if (ret) goto out; - t = wait_for_completion_timeout(&dm_device.host_event, 5 * HZ); + t = wait_for_completion_timeout(&dm_device.host_event, secs_to_jiffies(5)); if (t == 0) { ret = -ETIMEDOUT; goto out; @@ -1806,7 +1807,7 @@ static int balloon_connect_vsp(struct hv_device *dev) if (ret) goto out; - t = wait_for_completion_timeout(&dm_device.host_event, 5 * HZ); + t = wait_for_completion_timeout(&dm_device.host_event, secs_to_jiffies(5)); if (t == 0) { ret = -ETIMEDOUT; goto out; diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c index d35b60c06114..7400a5a4d2bd 100644 --- a/drivers/hv/hv_kvp.c +++ b/drivers/hv/hv_kvp.c @@ -655,7 +655,7 @@ void hv_kvp_onchannelcallback(void *context) if (host_negotiatied == NEGO_NOT_STARTED) { host_negotiatied = NEGO_IN_PROGRESS; schedule_delayed_work(&kvp_host_handshake_work, - HV_UTIL_NEGO_TIMEOUT * HZ); + secs_to_jiffies(HV_UTIL_NEGO_TIMEOUT)); } return; } @@ -724,7 +724,7 @@ void hv_kvp_onchannelcallback(void *context) */ schedule_work(&kvp_sendkey_work); schedule_delayed_work(&kvp_timeout_work, - HV_UTIL_TIMEOUT * HZ); + secs_to_jiffies(HV_UTIL_TIMEOUT)); return; @@ -767,6 +767,12 @@ hv_kvp_init(struct hv_util_service *srv) */ kvp_transaction.state = HVUTIL_DEVICE_INIT; + return 0; +} + +int +hv_kvp_init_transport(void) +{ hvt = hvutil_transport_init(kvp_devname, CN_KVP_IDX, CN_KVP_VAL, kvp_on_msg, kvp_on_reset); if (!hvt) diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c index 0d2184be1691..bde637a96c37 100644 --- a/drivers/hv/hv_snapshot.c +++ b/drivers/hv/hv_snapshot.c @@ -193,7 +193,8 @@ static void vss_send_op(void) vss_transaction.state = HVUTIL_USERSPACE_REQ; schedule_delayed_work(&vss_timeout_work, op == VSS_OP_FREEZE ? - VSS_FREEZE_TIMEOUT * HZ : HV_UTIL_TIMEOUT * HZ); + secs_to_jiffies(VSS_FREEZE_TIMEOUT) : + secs_to_jiffies(HV_UTIL_TIMEOUT)); rc = hvutil_transport_send(hvt, vss_msg, sizeof(*vss_msg), NULL); if (rc) { @@ -388,6 +389,12 @@ hv_vss_init(struct hv_util_service *srv) */ vss_transaction.state = HVUTIL_DEVICE_INIT; + return 0; +} + +int +hv_vss_init_transport(void) +{ hvt = hvutil_transport_init(vss_devname, CN_VSS_IDX, CN_VSS_VAL, vss_on_msg, vss_on_reset); if (!hvt) { diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c index c4f525325790..36ee89c0358b 100644 --- a/drivers/hv/hv_util.c +++ b/drivers/hv/hv_util.c @@ -141,6 +141,7 @@ static struct hv_util_service util_heartbeat = { static struct hv_util_service util_kvp = { .util_cb = hv_kvp_onchannelcallback, .util_init = hv_kvp_init, + .util_init_transport = hv_kvp_init_transport, .util_pre_suspend = hv_kvp_pre_suspend, .util_pre_resume = hv_kvp_pre_resume, .util_deinit = hv_kvp_deinit, @@ -149,6 +150,7 @@ static struct hv_util_service util_kvp = { static struct hv_util_service util_vss = { .util_cb = hv_vss_onchannelcallback, .util_init = hv_vss_init, + .util_init_transport = hv_vss_init_transport, .util_pre_suspend = hv_vss_pre_suspend, .util_pre_resume = hv_vss_pre_resume, .util_deinit = hv_vss_deinit, @@ -590,10 +592,8 @@ static int util_probe(struct hv_device *dev, srv->channel = dev->channel; if (srv->util_init) { ret = srv->util_init(srv); - if (ret) { - ret = -ENODEV; + if (ret) goto error1; - } } /* @@ -613,6 +613,13 @@ static int util_probe(struct hv_device *dev, if (ret) goto error; + if (srv->util_init_transport) { + ret = srv->util_init_transport(); + if (ret) { + vmbus_close(dev->channel); + goto error; + } + } return 0; error: diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index d2856023d53c..52cb744b4d7f 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -370,12 +370,14 @@ void vmbus_on_event(unsigned long data); void vmbus_on_msg_dpc(unsigned long data); int hv_kvp_init(struct hv_util_service *srv); +int hv_kvp_init_transport(void); void hv_kvp_deinit(void); int hv_kvp_pre_suspend(void); int hv_kvp_pre_resume(void); void hv_kvp_onchannelcallback(void *context); int hv_vss_init(struct hv_util_service *srv); +int hv_vss_init_transport(void); void hv_vss_deinit(void); int hv_vss_pre_suspend(void); int hv_vss_pre_resume(void); diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 6d89d37b069a..2892b8da20a5 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -2507,7 +2507,7 @@ static int vmbus_bus_resume(struct device *dev) vmbus_request_offers(); if (wait_for_completion_timeout( - &vmbus_connection.ready_for_resume_event, 10 * HZ) == 0) + &vmbus_connection.ready_for_resume_event, secs_to_jiffies(10)) == 0) pr_err("Some vmbus device is missing after suspending?\n"); /* Reset the event for the next suspend. */ diff --git a/drivers/hwmon/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/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/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index efb0d2d5716b..af445d3f8e2a 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -3070,6 +3070,7 @@ release_clk: msdc_gate_clock(host); platform_set_drvdata(pdev, NULL); release_mem: + device_init_wakeup(&pdev->dev, false); if (host->dma.gpd) dma_free_coherent(&pdev->dev, 2 * sizeof(struct mt_gpdma_desc), @@ -3103,6 +3104,7 @@ static void msdc_drv_remove(struct platform_device *pdev) host->dma.gpd, host->dma.gpd_addr); dma_free_coherent(&pdev->dev, MAX_BD_NUM * sizeof(struct mt_bdma_desc), host->dma.bd, host->dma.bd_addr); + device_init_wakeup(&pdev->dev, false); } static void msdc_save_reg(struct msdc_host *host) diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c index 4d402b601883..b2f5c3f8b839 100644 --- a/drivers/mmc/host/sdhci-tegra.c +++ b/drivers/mmc/host/sdhci-tegra.c @@ -1525,7 +1525,6 @@ static const struct sdhci_pltfm_data sdhci_tegra186_pdata = { .quirks = SDHCI_QUIRK_BROKEN_TIMEOUT_VAL | SDHCI_QUIRK_SINGLE_POWER_WRITE | SDHCI_QUIRK_NO_HISPD_BIT | - SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC | SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN, .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN | SDHCI_QUIRK2_ISSUE_CMD_DAT_RESET_TOGETHER, diff --git a/drivers/mtd/nand/raw/arasan-nand-controller.c b/drivers/mtd/nand/raw/arasan-nand-controller.c index db42aa0c7b6b..865754737f5f 100644 --- a/drivers/mtd/nand/raw/arasan-nand-controller.c +++ b/drivers/mtd/nand/raw/arasan-nand-controller.c @@ -1409,8 +1409,8 @@ static int anfc_parse_cs(struct arasan_nfc *nfc) * case, the "not" chosen CS is assigned to nfc->spare_cs and selected * whenever a GPIO CS must be asserted. */ - if (nfc->cs_array && nfc->ncs > 2) { - if (!nfc->cs_array[0] && !nfc->cs_array[1]) { + if (nfc->cs_array) { + if (nfc->ncs > 2 && !nfc->cs_array[0] && !nfc->cs_array[1]) { dev_err(nfc->dev, "Assign a single native CS when using GPIOs\n"); return -EINVAL; @@ -1478,8 +1478,15 @@ static int anfc_probe(struct platform_device *pdev) static void anfc_remove(struct platform_device *pdev) { + int i; struct arasan_nfc *nfc = platform_get_drvdata(pdev); + for (i = 0; i < nfc->ncs; i++) { + if (nfc->cs_array[i]) { + gpiod_put(nfc->cs_array[i]); + } + } + anfc_chips_cleanup(nfc); } diff --git a/drivers/mtd/nand/raw/atmel/pmecc.c b/drivers/mtd/nand/raw/atmel/pmecc.c index a22aab4ed4e8..3c7dee1be21d 100644 --- a/drivers/mtd/nand/raw/atmel/pmecc.c +++ b/drivers/mtd/nand/raw/atmel/pmecc.c @@ -380,10 +380,8 @@ atmel_pmecc_create_user(struct atmel_pmecc *pmecc, user->delta = user->dmu + req->ecc.strength + 1; gf_tables = atmel_pmecc_get_gf_tables(req); - if (IS_ERR(gf_tables)) { - kfree(user); + if (IS_ERR(gf_tables)) return ERR_CAST(gf_tables); - } user->gf_tables = gf_tables; diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c index 8db7fc424571..70d6c2250f32 100644 --- a/drivers/mtd/nand/raw/diskonchip.c +++ b/drivers/mtd/nand/raw/diskonchip.c @@ -1098,7 +1098,7 @@ static inline int __init inftl_partscan(struct mtd_info *mtd, struct mtd_partiti (i == 0) && (ip->firstUnit > 0)) { parts[0].name = " DiskOnChip IPL / Media Header partition"; parts[0].offset = 0; - parts[0].size = mtd->erasesize * ip->firstUnit; + parts[0].size = (uint64_t)mtd->erasesize * ip->firstUnit; numparts = 1; } diff --git a/drivers/mtd/nand/raw/omap2.c b/drivers/mtd/nand/raw/omap2.c index d9141f3c0dd1..b8af3a3533fc 100644 --- a/drivers/mtd/nand/raw/omap2.c +++ b/drivers/mtd/nand/raw/omap2.c @@ -254,6 +254,10 @@ static int omap_prefetch_reset(int cs, struct omap_nand_info *info) /** * omap_nand_data_in_pref - NAND data in using prefetch engine + * @chip: NAND chip + * @buf: output buffer where NAND data is placed into + * @len: length of transfer + * @force_8bit: force 8-bit transfers */ static void omap_nand_data_in_pref(struct nand_chip *chip, void *buf, unsigned int len, bool force_8bit) @@ -297,6 +301,10 @@ static void omap_nand_data_in_pref(struct nand_chip *chip, void *buf, /** * omap_nand_data_out_pref - NAND data out using Write Posting engine + * @chip: NAND chip + * @buf: input buffer that is sent to NAND + * @len: length of transfer + * @force_8bit: force 8-bit transfers */ static void omap_nand_data_out_pref(struct nand_chip *chip, const void *buf, unsigned int len, @@ -440,6 +448,10 @@ out_copy: /** * omap_nand_data_in_dma_pref - NAND data in using DMA and Prefetch + * @chip: NAND chip + * @buf: output buffer where NAND data is placed into + * @len: length of transfer + * @force_8bit: force 8-bit transfers */ static void omap_nand_data_in_dma_pref(struct nand_chip *chip, void *buf, unsigned int len, bool force_8bit) @@ -460,6 +472,10 @@ static void omap_nand_data_in_dma_pref(struct nand_chip *chip, void *buf, /** * omap_nand_data_out_dma_pref - NAND data out using DMA and write posting + * @chip: NAND chip + * @buf: input buffer that is sent to NAND + * @len: length of transfer + * @force_8bit: force 8-bit transfers */ static void omap_nand_data_out_dma_pref(struct nand_chip *chip, const void *buf, unsigned int len, diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 533bcb77c9f9..97cd8bbf2e32 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1220,20 +1220,32 @@ static void m_can_coalescing_update(struct m_can_classdev *cdev, u32 ir) static int m_can_interrupt_handler(struct m_can_classdev *cdev) { struct net_device *dev = cdev->net; - u32 ir; + u32 ir = 0, ir_read; int ret; if (pm_runtime_suspended(cdev->dev)) return IRQ_NONE; - ir = m_can_read(cdev, M_CAN_IR); + /* The m_can controller signals its interrupt status as a level, but + * depending in the integration the CPU may interpret the signal as + * edge-triggered (for example with m_can_pci). For these + * edge-triggered integrations, we must observe that IR is 0 at least + * once to be sure that the next interrupt will generate an edge. + */ + while ((ir_read = m_can_read(cdev, M_CAN_IR)) != 0) { + ir |= ir_read; + + /* ACK all irqs */ + m_can_write(cdev, M_CAN_IR, ir); + + if (!cdev->irq_edge_triggered) + break; + } + m_can_coalescing_update(cdev, ir); if (!ir) return IRQ_NONE; - /* ACK all irqs */ - m_can_write(cdev, M_CAN_IR, ir); - if (cdev->ops->clear_interrupts) cdev->ops->clear_interrupts(cdev); @@ -1695,6 +1707,14 @@ static int m_can_dev_setup(struct m_can_classdev *cdev) return -EINVAL; } + /* Write the INIT bit, in case no hardware reset has happened before + * the probe (for example, it was observed that the Intel Elkhart Lake + * SoCs do not properly reset the CAN controllers on reboot) + */ + err = m_can_cccr_update_bits(cdev, CCCR_INIT, CCCR_INIT); + if (err) + return err; + if (!cdev->is_peripheral) netif_napi_add(dev, &cdev->napi, m_can_poll); @@ -1746,11 +1766,7 @@ static int m_can_dev_setup(struct m_can_classdev *cdev) return -EINVAL; } - /* Forcing standby mode should be redundant, as the chip should be in - * standby after a reset. Write the INIT bit anyways, should the chip - * be configured by previous stage. - */ - return m_can_cccr_update_bits(cdev, CCCR_INIT, CCCR_INIT); + return 0; } static void m_can_stop(struct net_device *dev) diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h index 92b2bd8628e6..ef39e8e527ab 100644 --- a/drivers/net/can/m_can/m_can.h +++ b/drivers/net/can/m_can/m_can.h @@ -99,6 +99,7 @@ struct m_can_classdev { int pm_clock_support; int pm_wake_source; int is_peripheral; + bool irq_edge_triggered; // Cached M_CAN_IE register content u32 active_interrupts; diff --git a/drivers/net/can/m_can/m_can_pci.c b/drivers/net/can/m_can/m_can_pci.c index d72fe771dfc7..9ad7419f88f8 100644 --- a/drivers/net/can/m_can/m_can_pci.c +++ b/drivers/net/can/m_can/m_can_pci.c @@ -127,6 +127,7 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) mcan_class->pm_clock_support = 1; mcan_class->pm_wake_source = 0; mcan_class->can.clock.freq = id->driver_data; + mcan_class->irq_edge_triggered = true; mcan_class->ops = &m_can_pci_ops; pci_set_drvdata(pci, mcan_class); diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c index ecce23cecbea..4e266ce41180 100644 --- a/drivers/net/ethernet/broadcom/bgmac-platform.c +++ b/drivers/net/ethernet/broadcom/bgmac-platform.c @@ -171,6 +171,7 @@ static int platform_phy_connect(struct bgmac *bgmac) static int bgmac_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; + struct device_node *phy_node; struct bgmac *bgmac; struct resource *regs; int ret; @@ -236,7 +237,9 @@ static int bgmac_probe(struct platform_device *pdev) bgmac->cco_ctl_maskset = platform_bgmac_cco_ctl_maskset; bgmac->get_bus_clock = platform_bgmac_get_bus_clock; bgmac->cmn_maskset32 = platform_bgmac_cmn_maskset32; - if (of_parse_phandle(np, "phy-handle", 0)) { + phy_node = of_parse_phandle(np, "phy-handle", 0); + if (phy_node) { + of_node_put(phy_node); bgmac->phy_connect = platform_phy_connect; } else { bgmac->phy_connect = bgmac_phy_connect_direct; diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c index 96fd31d75dfd..daa1ebaef511 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c @@ -346,8 +346,9 @@ static struct sk_buff *copy_gl_to_skb_pkt(const struct pkt_gl *gl, * driver. Once driver synthesizes cpl_pass_accept_req the skb will go * through the regular cpl_pass_accept_req processing in TOM. */ - skb = alloc_skb(gl->tot_len + sizeof(struct cpl_pass_accept_req) - - pktshift, GFP_ATOMIC); + skb = alloc_skb(size_add(gl->tot_len, + sizeof(struct cpl_pass_accept_req)) - + pktshift, GFP_ATOMIC); if (unlikely(!skb)) return NULL; __skb_put(skb, gl->tot_len + sizeof(struct cpl_pass_accept_req) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 890f213da8d1..ae1f523d6841 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -172,6 +172,7 @@ err_init_txq: hinic_sq_dbgfs_uninit(nic_dev); devm_kfree(&netdev->dev, nic_dev->txqs); + nic_dev->txqs = NULL; return err; } @@ -268,6 +269,7 @@ err_init_rxq: hinic_rq_dbgfs_uninit(nic_dev); devm_kfree(&netdev->dev, nic_dev->rxqs); + nic_dev->rxqs = NULL; return err; } diff --git a/drivers/net/ethernet/intel/idpf/idpf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_dev.c index 6c913a703df6..41e4bd49402a 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_dev.c +++ b/drivers/net/ethernet/intel/idpf/idpf_dev.c @@ -101,6 +101,9 @@ static int idpf_intr_reg_init(struct idpf_vport *vport) intr->dyn_ctl_itridx_s = PF_GLINT_DYN_CTL_ITR_INDX_S; intr->dyn_ctl_intrvl_s = PF_GLINT_DYN_CTL_INTERVAL_S; intr->dyn_ctl_wb_on_itr_m = PF_GLINT_DYN_CTL_WB_ON_ITR_M; + intr->dyn_ctl_swint_trig_m = PF_GLINT_DYN_CTL_SWINT_TRIG_M; + intr->dyn_ctl_sw_itridx_ena_m = + PF_GLINT_DYN_CTL_SW_ITR_INDX_ENA_M; spacing = IDPF_ITR_IDX_SPACING(reg_vals[vec_id].itrn_index_spacing, IDPF_PF_ITR_IDX_SPACING); diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 34f4118c7bc0..2fa9c36e33c9 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -3604,21 +3604,31 @@ static void idpf_vport_intr_dis_irq_all(struct idpf_vport *vport) /** * idpf_vport_intr_buildreg_itr - Enable default interrupt generation settings * @q_vector: pointer to q_vector - * @type: itr index - * @itr: itr value */ -static u32 idpf_vport_intr_buildreg_itr(struct idpf_q_vector *q_vector, - const int type, u16 itr) +static u32 idpf_vport_intr_buildreg_itr(struct idpf_q_vector *q_vector) { - u32 itr_val; + u32 itr_val = q_vector->intr_reg.dyn_ctl_intena_m; + int type = IDPF_NO_ITR_UPDATE_IDX; + u16 itr = 0; + + if (q_vector->wb_on_itr) { + /* + * Trigger a software interrupt when exiting wb_on_itr, to make + * sure we catch any pending write backs that might have been + * missed due to interrupt state transition. + */ + itr_val |= q_vector->intr_reg.dyn_ctl_swint_trig_m | + q_vector->intr_reg.dyn_ctl_sw_itridx_ena_m; + type = IDPF_SW_ITR_UPDATE_IDX; + itr = IDPF_ITR_20K; + } itr &= IDPF_ITR_MASK; /* Don't clear PBA because that can cause lost interrupts that * came in while we were cleaning/polling */ - itr_val = q_vector->intr_reg.dyn_ctl_intena_m | - (type << q_vector->intr_reg.dyn_ctl_itridx_s) | - (itr << (q_vector->intr_reg.dyn_ctl_intrvl_s - 1)); + itr_val |= (type << q_vector->intr_reg.dyn_ctl_itridx_s) | + (itr << (q_vector->intr_reg.dyn_ctl_intrvl_s - 1)); return itr_val; } @@ -3716,9 +3726,8 @@ void idpf_vport_intr_update_itr_ena_irq(struct idpf_q_vector *q_vector) /* net_dim() updates ITR out-of-band using a work item */ idpf_net_dim(q_vector); + intval = idpf_vport_intr_buildreg_itr(q_vector); q_vector->wb_on_itr = false; - intval = idpf_vport_intr_buildreg_itr(q_vector, - IDPF_NO_ITR_UPDATE_IDX, 0); writel(intval, q_vector->intr_reg.dyn_ctl); } diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h index 9c1fe84108ed..0f71a6f5557b 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h @@ -354,6 +354,8 @@ struct idpf_vec_regs { * @dyn_ctl_itridx_m: Mask for ITR index * @dyn_ctl_intrvl_s: Register bit offset for ITR interval * @dyn_ctl_wb_on_itr_m: Mask for WB on ITR feature + * @dyn_ctl_sw_itridx_ena_m: Mask for SW ITR index + * @dyn_ctl_swint_trig_m: Mask for dyn_ctl SW triggered interrupt enable * @rx_itr: RX ITR register * @tx_itr: TX ITR register * @icr_ena: Interrupt cause register offset @@ -367,6 +369,8 @@ struct idpf_intr_reg { u32 dyn_ctl_itridx_m; u32 dyn_ctl_intrvl_s; u32 dyn_ctl_wb_on_itr_m; + u32 dyn_ctl_sw_itridx_ena_m; + u32 dyn_ctl_swint_trig_m; void __iomem *rx_itr; void __iomem *tx_itr; void __iomem *icr_ena; @@ -437,7 +441,7 @@ struct idpf_q_vector { cpumask_var_t affinity_mask; __cacheline_group_end_aligned(cold); }; -libeth_cacheline_set_assert(struct idpf_q_vector, 112, +libeth_cacheline_set_assert(struct idpf_q_vector, 120, 24 + sizeof(struct napi_struct) + 2 * sizeof(struct dim), 8 + sizeof(cpumask_var_t)); @@ -471,6 +475,8 @@ struct idpf_tx_queue_stats { #define IDPF_ITR_IS_DYNAMIC(itr_mode) (itr_mode) #define IDPF_ITR_TX_DEF IDPF_ITR_20K #define IDPF_ITR_RX_DEF IDPF_ITR_20K +/* Index used for 'SW ITR' update in DYN_CTL register */ +#define IDPF_SW_ITR_UPDATE_IDX 2 /* Index used for 'No ITR' update in DYN_CTL register */ #define IDPF_NO_ITR_UPDATE_IDX 3 #define IDPF_ITR_IDX_SPACING(spacing, dflt) (spacing ? spacing : dflt) diff --git a/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c index aad62e270ae4..aba828abcb17 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c +++ b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c @@ -101,6 +101,9 @@ static int idpf_vf_intr_reg_init(struct idpf_vport *vport) intr->dyn_ctl_itridx_s = VF_INT_DYN_CTLN_ITR_INDX_S; intr->dyn_ctl_intrvl_s = VF_INT_DYN_CTLN_INTERVAL_S; intr->dyn_ctl_wb_on_itr_m = VF_INT_DYN_CTLN_WB_ON_ITR_M; + intr->dyn_ctl_swint_trig_m = VF_INT_DYN_CTLN_SWINT_TRIG_M; + intr->dyn_ctl_sw_itridx_ena_m = + VF_INT_DYN_CTLN_SW_ITR_INDX_ENA_M; spacing = IDPF_ITR_IDX_SPACING(reg_vals[vec_id].itrn_index_spacing, IDPF_VF_ITR_IDX_SPACING); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c index 232b10740c13..04e08e06f30f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c @@ -680,14 +680,17 @@ int rvu_rep_create(struct otx2_nic *priv, struct netlink_ext_ack *extack) ndev->features |= ndev->hw_features; eth_hw_addr_random(ndev); err = rvu_rep_devlink_port_register(rep); - if (err) + if (err) { + free_netdev(ndev); goto exit; + } SET_NETDEV_DEVLINK_PORT(ndev, &rep->dl_port); err = register_netdev(ndev); if (err) { NL_SET_ERR_MSG_MOD(extack, "PFVF representor registration failed"); + rvu_rep_devlink_port_unregister(rep); free_netdev(ndev); goto exit; } diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 3d72aa7b1305..ef93df520887 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1432,7 +1432,7 @@ void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port, memset(ifh, 0, OCELOT_TAG_LEN); ocelot_ifh_set_bypass(ifh, 1); - ocelot_ifh_set_src(ifh, BIT_ULL(ocelot->num_phys_ports)); + ocelot_ifh_set_src(ifh, ocelot->num_phys_ports); ocelot_ifh_set_dest(ifh, BIT_ULL(port)); ocelot_ifh_set_qos_class(ifh, qos_class); ocelot_ifh_set_tag_type(ifh, tag_type); diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c index f9c0dcd965c2..db200e4ec284 100644 --- a/drivers/net/ethernet/oa_tc6.c +++ b/drivers/net/ethernet/oa_tc6.c @@ -113,6 +113,7 @@ struct oa_tc6 { struct mii_bus *mdiobus; struct spi_device *spi; struct mutex spi_ctrl_lock; /* Protects spi control transfer */ + spinlock_t tx_skb_lock; /* Protects tx skb handling */ void *spi_ctrl_tx_buf; void *spi_ctrl_rx_buf; void *spi_data_tx_buf; @@ -1004,8 +1005,10 @@ static u16 oa_tc6_prepare_spi_tx_buf_for_tx_skbs(struct oa_tc6 *tc6) for (used_tx_credits = 0; used_tx_credits < tc6->tx_credits; used_tx_credits++) { if (!tc6->ongoing_tx_skb) { + spin_lock_bh(&tc6->tx_skb_lock); tc6->ongoing_tx_skb = tc6->waiting_tx_skb; tc6->waiting_tx_skb = NULL; + spin_unlock_bh(&tc6->tx_skb_lock); } if (!tc6->ongoing_tx_skb) break; @@ -1111,8 +1114,9 @@ static int oa_tc6_spi_thread_handler(void *data) /* This kthread will be waken up if there is a tx skb or mac-phy * interrupt to perform spi transfer with tx chunks. */ - wait_event_interruptible(tc6->spi_wq, tc6->waiting_tx_skb || - tc6->int_flag || + wait_event_interruptible(tc6->spi_wq, tc6->int_flag || + (tc6->waiting_tx_skb && + tc6->tx_credits) || kthread_should_stop()); if (kthread_should_stop()) @@ -1209,7 +1213,9 @@ netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, struct sk_buff *skb) return NETDEV_TX_OK; } + spin_lock_bh(&tc6->tx_skb_lock); tc6->waiting_tx_skb = skb; + spin_unlock_bh(&tc6->tx_skb_lock); /* Wake spi kthread to perform spi transfer */ wake_up_interruptible(&tc6->spi_wq); @@ -1239,6 +1245,7 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev) tc6->netdev = netdev; SET_NETDEV_DEV(netdev, &spi->dev); mutex_init(&tc6->spi_ctrl_lock); + spin_lock_init(&tc6->tx_skb_lock); /* Set the SPI controller to pump at realtime priority */ tc6->spi->rt = true; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index 9e42d599840d..57edcde9e6f8 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -277,7 +277,10 @@ void ionic_dev_teardown(struct ionic *ionic) idev->phy_cmb_pages = 0; idev->cmb_npages = 0; - destroy_workqueue(ionic->wq); + if (ionic->wq) { + destroy_workqueue(ionic->wq); + ionic->wq = NULL; + } mutex_destroy(&idev->cmb_inuse_lock); } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c index dda22fa4448c..9b7f78b6cdb1 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c @@ -961,8 +961,8 @@ static int ionic_get_module_eeprom(struct net_device *netdev, len = min_t(u32, sizeof(xcvr->sprom), ee->len); do { - memcpy(data, xcvr->sprom, len); - memcpy(tbuf, xcvr->sprom, len); + memcpy(data, &xcvr->sprom[ee->offset], len); + memcpy(tbuf, &xcvr->sprom[ee->offset], len); /* Let's make sure we got a consistent copy */ if (!memcmp(data, tbuf, len)) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 40496587b2b3..3d3f936779f7 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -3869,8 +3869,8 @@ int ionic_lif_register(struct ionic_lif *lif) /* only register LIF0 for now */ err = register_netdev(lif->netdev); if (err) { - dev_err(lif->ionic->dev, "Cannot register net device, aborting\n"); - ionic_lif_unregister_phc(lif); + dev_err(lif->ionic->dev, "Cannot register net device: %d, aborting\n", err); + ionic_lif_unregister(lif); return err; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index b45efc272fdb..c7f497c36f66 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -3358,6 +3358,7 @@ int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn) p_ptt, &nvm_info.num_images); if (rc == -EOPNOTSUPP) { DP_INFO(p_hwfn, "DRV_MSG_CODE_BIST_TEST is not supported\n"); + nvm_info.num_images = 0; goto out; } else if (rc || !nvm_info.num_images) { DP_ERR(p_hwfn, "Failed getting number of images\n"); diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c index dbbbf024e7ab..9ac6e2aad18f 100644 --- a/drivers/net/ethernet/renesas/rswitch.c +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -547,7 +547,6 @@ static int rswitch_gwca_ts_queue_alloc(struct rswitch_private *priv) desc = &gq->ts_ring[gq->ring_size]; desc->desc.die_dt = DT_LINKFIX; rswitch_desc_set_dptr(&desc->desc, gq->ring_dma); - INIT_LIST_HEAD(&priv->gwca.ts_info_list); return 0; } @@ -1003,9 +1002,10 @@ static int rswitch_gwca_request_irqs(struct rswitch_private *priv) static void rswitch_ts(struct rswitch_private *priv) { struct rswitch_gwca_queue *gq = &priv->gwca.ts_queue; - struct rswitch_gwca_ts_info *ts_info, *ts_info2; struct skb_shared_hwtstamps shhwtstamps; struct rswitch_ts_desc *desc; + struct rswitch_device *rdev; + struct sk_buff *ts_skb; struct timespec64 ts; unsigned int num; u32 tag, port; @@ -1015,23 +1015,28 @@ static void rswitch_ts(struct rswitch_private *priv) dma_rmb(); port = TS_DESC_DPN(__le32_to_cpu(desc->desc.dptrl)); - tag = TS_DESC_TSUN(__le32_to_cpu(desc->desc.dptrl)); - - list_for_each_entry_safe(ts_info, ts_info2, &priv->gwca.ts_info_list, list) { - if (!(ts_info->port == port && ts_info->tag == tag)) - continue; - - memset(&shhwtstamps, 0, sizeof(shhwtstamps)); - ts.tv_sec = __le32_to_cpu(desc->ts_sec); - ts.tv_nsec = __le32_to_cpu(desc->ts_nsec & cpu_to_le32(0x3fffffff)); - shhwtstamps.hwtstamp = timespec64_to_ktime(ts); - skb_tstamp_tx(ts_info->skb, &shhwtstamps); - dev_consume_skb_irq(ts_info->skb); - list_del(&ts_info->list); - kfree(ts_info); - break; - } + if (unlikely(port >= RSWITCH_NUM_PORTS)) + goto next; + rdev = priv->rdev[port]; + tag = TS_DESC_TSUN(__le32_to_cpu(desc->desc.dptrl)); + if (unlikely(tag >= TS_TAGS_PER_PORT)) + goto next; + ts_skb = xchg(&rdev->ts_skb[tag], NULL); + smp_mb(); /* order rdev->ts_skb[] read before bitmap update */ + clear_bit(tag, rdev->ts_skb_used); + + if (unlikely(!ts_skb)) + goto next; + + memset(&shhwtstamps, 0, sizeof(shhwtstamps)); + ts.tv_sec = __le32_to_cpu(desc->ts_sec); + ts.tv_nsec = __le32_to_cpu(desc->ts_nsec & cpu_to_le32(0x3fffffff)); + shhwtstamps.hwtstamp = timespec64_to_ktime(ts); + skb_tstamp_tx(ts_skb, &shhwtstamps); + dev_consume_skb_irq(ts_skb); + +next: gq->cur = rswitch_next_queue_index(gq, true, 1); desc = &gq->ts_ring[gq->cur]; } @@ -1576,8 +1581,9 @@ static int rswitch_open(struct net_device *ndev) static int rswitch_stop(struct net_device *ndev) { struct rswitch_device *rdev = netdev_priv(ndev); - struct rswitch_gwca_ts_info *ts_info, *ts_info2; + struct sk_buff *ts_skb; unsigned long flags; + unsigned int tag; netif_tx_stop_all_queues(ndev); @@ -1594,12 +1600,13 @@ static int rswitch_stop(struct net_device *ndev) if (bitmap_empty(rdev->priv->opened_ports, RSWITCH_NUM_PORTS)) iowrite32(GWCA_TS_IRQ_BIT, rdev->priv->addr + GWTSDID); - list_for_each_entry_safe(ts_info, ts_info2, &rdev->priv->gwca.ts_info_list, list) { - if (ts_info->port != rdev->port) - continue; - dev_kfree_skb_irq(ts_info->skb); - list_del(&ts_info->list); - kfree(ts_info); + for (tag = find_first_bit(rdev->ts_skb_used, TS_TAGS_PER_PORT); + tag < TS_TAGS_PER_PORT; + tag = find_next_bit(rdev->ts_skb_used, TS_TAGS_PER_PORT, tag + 1)) { + ts_skb = xchg(&rdev->ts_skb[tag], NULL); + clear_bit(tag, rdev->ts_skb_used); + if (ts_skb) + dev_kfree_skb(ts_skb); } return 0; @@ -1612,20 +1619,17 @@ static bool rswitch_ext_desc_set_info1(struct rswitch_device *rdev, desc->info1 = cpu_to_le64(INFO1_DV(BIT(rdev->etha->index)) | INFO1_IPV(GWCA_IPV_NUM) | INFO1_FMT); if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { - struct rswitch_gwca_ts_info *ts_info; + unsigned int tag; - ts_info = kzalloc(sizeof(*ts_info), GFP_ATOMIC); - if (!ts_info) + tag = find_first_zero_bit(rdev->ts_skb_used, TS_TAGS_PER_PORT); + if (tag == TS_TAGS_PER_PORT) return false; + smp_mb(); /* order bitmap read before rdev->ts_skb[] write */ + rdev->ts_skb[tag] = skb_get(skb); + set_bit(tag, rdev->ts_skb_used); skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; - rdev->ts_tag++; - desc->info1 |= cpu_to_le64(INFO1_TSUN(rdev->ts_tag) | INFO1_TXC); - - ts_info->skb = skb_get(skb); - ts_info->port = rdev->port; - ts_info->tag = rdev->ts_tag; - list_add_tail(&ts_info->list, &rdev->priv->gwca.ts_info_list); + desc->info1 |= cpu_to_le64(INFO1_TSUN(tag) | INFO1_TXC); skb_tx_timestamp(skb); } diff --git a/drivers/net/ethernet/renesas/rswitch.h b/drivers/net/ethernet/renesas/rswitch.h index e020800dcc57..d8d4ed7d7f8b 100644 --- a/drivers/net/ethernet/renesas/rswitch.h +++ b/drivers/net/ethernet/renesas/rswitch.h @@ -972,14 +972,6 @@ struct rswitch_gwca_queue { }; }; -struct rswitch_gwca_ts_info { - struct sk_buff *skb; - struct list_head list; - - int port; - u8 tag; -}; - #define RSWITCH_NUM_IRQ_REGS (RSWITCH_MAX_NUM_QUEUES / BITS_PER_TYPE(u32)) struct rswitch_gwca { unsigned int index; @@ -989,7 +981,6 @@ struct rswitch_gwca { struct rswitch_gwca_queue *queues; int num_queues; struct rswitch_gwca_queue ts_queue; - struct list_head ts_info_list; DECLARE_BITMAP(used, RSWITCH_MAX_NUM_QUEUES); u32 tx_irq_bits[RSWITCH_NUM_IRQ_REGS]; u32 rx_irq_bits[RSWITCH_NUM_IRQ_REGS]; @@ -997,6 +988,7 @@ struct rswitch_gwca { }; #define NUM_QUEUES_PER_NDEV 2 +#define TS_TAGS_PER_PORT 256 struct rswitch_device { struct rswitch_private *priv; struct net_device *ndev; @@ -1004,7 +996,8 @@ struct rswitch_device { void __iomem *addr; struct rswitch_gwca_queue *tx_queue; struct rswitch_gwca_queue *rx_queue; - u8 ts_tag; + struct sk_buff *ts_skb[TS_TAGS_PER_PORT]; + DECLARE_BITMAP(ts_skb_used, TS_TAGS_PER_PORT); bool disabled; int port; diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c index b156493d7084..aea0f0357568 100644 --- a/drivers/net/mdio/fwnode_mdio.c +++ b/drivers/net/mdio/fwnode_mdio.c @@ -40,6 +40,7 @@ fwnode_find_pse_control(struct fwnode_handle *fwnode) static struct mii_timestamper * fwnode_find_mii_timestamper(struct fwnode_handle *fwnode) { + struct mii_timestamper *mii_ts; struct of_phandle_args arg; int err; @@ -53,10 +54,16 @@ fwnode_find_mii_timestamper(struct fwnode_handle *fwnode) else if (err) return ERR_PTR(err); - if (arg.args_count != 1) - return ERR_PTR(-EINVAL); + if (arg.args_count != 1) { + mii_ts = ERR_PTR(-EINVAL); + goto put_node; + } + + mii_ts = register_mii_timestamper(arg.np, arg.args[0]); - return register_mii_timestamper(arg.np, arg.args[0]); +put_node: + of_node_put(arg.np); + return mii_ts; } int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, diff --git a/drivers/net/netdevsim/health.c b/drivers/net/netdevsim/health.c index 70e8bdf34be9..688f05316b5e 100644 --- a/drivers/net/netdevsim/health.c +++ b/drivers/net/netdevsim/health.c @@ -149,6 +149,8 @@ static ssize_t nsim_dev_health_break_write(struct file *file, char *break_msg; int err; + if (count == 0 || count > PAGE_SIZE) + return -EINVAL; break_msg = memdup_user_nul(data, count); if (IS_ERR(break_msg)) return PTR_ERR(break_msg); diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index 0be47fed4efc..e068a9761c09 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -635,10 +635,10 @@ nsim_pp_hold_write(struct file *file, const char __user *data, page_pool_put_full_page(ns->page->pp, ns->page, false); ns->page = NULL; } - rtnl_unlock(); exit: - return count; + rtnl_unlock(); + return ret; } static const struct file_operations nsim_pp_hold_fops = { diff --git a/drivers/net/phy/aquantia/aquantia_leds.c b/drivers/net/phy/aquantia/aquantia_leds.c index 00ad2313fed3..951f46104eff 100644 --- a/drivers/net/phy/aquantia/aquantia_leds.c +++ b/drivers/net/phy/aquantia/aquantia_leds.c @@ -156,5 +156,5 @@ int aqr_phy_led_polarity_set(struct phy_device *phydev, int index, unsigned long if (force_active_high || force_active_low) return aqr_phy_led_active_low_set(phydev, index, force_active_low); - unreachable(); + return -EINVAL; } diff --git a/drivers/net/phy/intel-xway.c b/drivers/net/phy/intel-xway.c index b672c55a7a4e..e6ed2413e514 100644 --- a/drivers/net/phy/intel-xway.c +++ b/drivers/net/phy/intel-xway.c @@ -529,7 +529,7 @@ static int xway_gphy_led_polarity_set(struct phy_device *phydev, int index, if (force_active_high) return phy_clear_bits(phydev, XWAY_MDIO_LED, XWAY_GPHY_LED_INV(index)); - unreachable(); + return -EINVAL; } static struct phy_driver xway_gphy[] = { diff --git a/drivers/net/phy/mxl-gpy.c b/drivers/net/phy/mxl-gpy.c index db3c1f72b407..a8ccf257c109 100644 --- a/drivers/net/phy/mxl-gpy.c +++ b/drivers/net/phy/mxl-gpy.c @@ -1014,7 +1014,7 @@ static int gpy_led_polarity_set(struct phy_device *phydev, int index, if (force_active_high) return phy_clear_bits(phydev, PHY_LED, PHY_LED_POLARITY(index)); - unreachable(); + return -EINVAL; } static struct phy_driver gpy_drivers[] = { diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c index 69ea2c3c76bf..c7690adec8db 100644 --- a/drivers/net/team/team_core.c +++ b/drivers/net/team/team_core.c @@ -998,9 +998,13 @@ static void __team_compute_features(struct team *team) unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; + rcu_read_lock(); + if (list_empty(&team->port_list)) + goto done; + vlan_features = netdev_base_features(vlan_features); + enc_features = netdev_base_features(enc_features); - rcu_read_lock(); list_for_each_entry_rcu(port, &team->port_list, list) { vlan_features = netdev_increment_features(vlan_features, port->dev->vlan_features, @@ -1010,11 +1014,11 @@ static void __team_compute_features(struct team *team) port->dev->hw_enc_features, TEAM_ENC_FEATURES); - dst_release_flag &= port->dev->priv_flags; if (port->dev->hard_header_len > max_hard_header_len) max_hard_header_len = port->dev->hard_header_len; } +done: rcu_read_unlock(); team->dev->vlan_features = vlan_features; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index d7a865ef370b..e816aaba8e5f 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1481,7 +1481,7 @@ static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile, skb->truesize += skb->data_len; for (i = 1; i < it->nr_segs; i++) { - const struct iovec *iov = iter_iov(it); + const struct iovec *iov = iter_iov(it) + i; size_t fragsz = iov->iov_len; struct page *page; void *frag; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 9fe7f704a2f7..e9208a8d2bfa 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1429,6 +1429,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x2c7c, 0x0195, 4)}, /* Quectel EG95 */ {QMI_FIXED_INTF(0x2c7c, 0x0296, 4)}, /* Quectel BG96 */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x030e, 4)}, /* Quectel EM05GV2 */ + {QMI_QUIRK_SET_DTR(0x2c7c, 0x0316, 3)}, /* Quectel RG255C */ {QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)}, /* Fibocom NL678 series */ {QMI_QUIRK_SET_DTR(0x2cb7, 0x0112, 0)}, /* Fibocom FG132 */ {QMI_FIXED_INTF(0x0489, 0xe0b4, 0)}, /* Foxconn T77W968 LTE */ diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 4265c1cd0ff7..63fe51d0e64d 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -867,7 +867,7 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev static int xennet_close(struct net_device *dev) { struct netfront_info *np = netdev_priv(dev); - unsigned int num_queues = dev->real_num_tx_queues; + unsigned int num_queues = np->queues ? dev->real_num_tx_queues : 0; unsigned int i; struct netfront_queue *queue; netif_tx_stop_all_queues(np->netdev); @@ -882,6 +882,9 @@ static void xennet_destroy_queues(struct netfront_info *info) { unsigned int i; + if (!info->queues) + return; + for (i = 0; i < info->netdev->real_num_tx_queues; i++) { struct netfront_queue *queue = &info->queues[i]; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index d169a30eb935..a970168a3014 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2034,7 +2034,7 @@ static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id, * or smaller than a sector size yet, so catch this early and don't * allow block I/O. */ - if (head->lba_shift > PAGE_SHIFT || head->lba_shift < SECTOR_SHIFT) { + if (blk_validate_block_size(bs)) { bs = (1 << 9); valid = false; } diff --git a/drivers/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/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/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/dell/alienware-wmi.c b/drivers/platform/x86/dell/alienware-wmi.c index 77465ed9b449..341d01d3e3e4 100644 --- a/drivers/platform/x86/dell/alienware-wmi.c +++ b/drivers/platform/x86/dell/alienware-wmi.c @@ -190,7 +190,7 @@ static struct quirk_entry quirk_asm201 = { }; static struct quirk_entry quirk_g_series = { - .num_zones = 2, + .num_zones = 0, .hdmi_mux = 0, .amplifier = 0, .deepslp = 0, @@ -199,7 +199,7 @@ static struct quirk_entry quirk_g_series = { }; static struct quirk_entry quirk_x_series = { - .num_zones = 2, + .num_zones = 0, .hdmi_mux = 0, .amplifier = 0, .deepslp = 0, @@ -243,6 +243,15 @@ static const struct dmi_system_id alienware_quirks[] __initconst = { }, { .callback = dmi_matched, + .ident = "Alienware m16 R1 AMD", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m16 R1 AMD"), + }, + .driver_data = &quirk_x_series, + }, + { + .callback = dmi_matched, .ident = "Alienware m17 R5", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), @@ -687,6 +696,9 @@ static void alienware_zone_exit(struct platform_device *dev) { u8 zone; + if (!quirks->num_zones) + return; + sysfs_remove_group(&dev->dev.kobj, &zone_attribute_group); led_classdev_unregister(&global_led); if (zone_dev_attrs) { @@ -1229,9 +1241,11 @@ static int __init alienware_wmi_init(void) goto fail_prep_thermal_profile; } - ret = alienware_zone_init(platform_device); - if (ret) - goto fail_prep_zones; + if (quirks->num_zones > 0) { + ret = alienware_zone_init(platform_device); + if (ret) + goto fail_prep_zones; + } return 0; diff --git a/drivers/platform/x86/intel/ifs/core.c b/drivers/platform/x86/intel/ifs/core.c index bc252b883210..1ae50702bdb7 100644 --- a/drivers/platform/x86/intel/ifs/core.c +++ b/drivers/platform/x86/intel/ifs/core.c @@ -20,6 +20,7 @@ static const struct x86_cpu_id ifs_cpu_ids[] __initconst = { X86_MATCH(INTEL_GRANITERAPIDS_X, ARRAY_GEN0), X86_MATCH(INTEL_GRANITERAPIDS_D, ARRAY_GEN0), X86_MATCH(INTEL_ATOM_CRESTMONT_X, ARRAY_GEN1), + X86_MATCH(INTEL_ATOM_DARKMONT_X, ARRAY_GEN1), {} }; MODULE_DEVICE_TABLE(x86cpu, ifs_cpu_ids); diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c index 4a85aad2475a..8272f1dd0fbc 100644 --- a/drivers/platform/x86/intel/vsec.c +++ b/drivers/platform/x86/intel/vsec.c @@ -423,6 +423,7 @@ static const struct intel_vsec_platform_info lnl_info = { #define PCI_DEVICE_ID_INTEL_VSEC_RPL 0xa77d #define PCI_DEVICE_ID_INTEL_VSEC_TGL 0x9a0d #define PCI_DEVICE_ID_INTEL_VSEC_LNL_M 0x647d +#define PCI_DEVICE_ID_INTEL_VSEC_PTL 0xb07d static const struct pci_device_id intel_vsec_pci_ids[] = { { PCI_DEVICE_DATA(INTEL, VSEC_ADL, &tgl_info) }, { PCI_DEVICE_DATA(INTEL, VSEC_DG1, &dg1_info) }, @@ -432,6 +433,7 @@ static const struct pci_device_id intel_vsec_pci_ids[] = { { PCI_DEVICE_DATA(INTEL, VSEC_RPL, &tgl_info) }, { PCI_DEVICE_DATA(INTEL, VSEC_TGL, &tgl_info) }, { PCI_DEVICE_DATA(INTEL, VSEC_LNL_M, &lnl_info) }, + { PCI_DEVICE_DATA(INTEL, VSEC_PTL, &mtl_info) }, { } }; MODULE_DEVICE_TABLE(pci, intel_vsec_pci_ids); diff --git a/drivers/platform/x86/p2sb.c b/drivers/platform/x86/p2sb.c index d51eb0db0626..cbbb0f809704 100644 --- a/drivers/platform/x86/p2sb.c +++ b/drivers/platform/x86/p2sb.c @@ -43,6 +43,7 @@ struct p2sb_res_cache { }; static struct p2sb_res_cache p2sb_resources[NR_P2SB_RES_CACHE]; +static bool p2sb_hidden_by_bios; static void p2sb_get_devfn(unsigned int *devfn) { @@ -97,6 +98,12 @@ static void p2sb_scan_and_cache_devfn(struct pci_bus *bus, unsigned int devfn) static int p2sb_scan_and_cache(struct pci_bus *bus, unsigned int devfn) { + /* + * The BIOS prevents the P2SB device from being enumerated by the PCI + * subsystem, so we need to unhide and hide it back to lookup the BAR. + */ + pci_bus_write_config_dword(bus, devfn, P2SBC, 0); + /* Scan the P2SB device and cache its BAR0 */ p2sb_scan_and_cache_devfn(bus, devfn); @@ -104,6 +111,8 @@ static int p2sb_scan_and_cache(struct pci_bus *bus, unsigned int devfn) if (devfn == P2SB_DEVFN_GOLDMONT) p2sb_scan_and_cache_devfn(bus, SPI_DEVFN_GOLDMONT); + pci_bus_write_config_dword(bus, devfn, P2SBC, P2SBC_HIDE); + if (!p2sb_valid_resource(&p2sb_resources[PCI_FUNC(devfn)].res)) return -ENOENT; @@ -129,7 +138,7 @@ static int p2sb_cache_resources(void) u32 value = P2SBC_HIDE; struct pci_bus *bus; u16 class; - int ret; + int ret = 0; /* Get devfn for P2SB device itself */ p2sb_get_devfn(&devfn_p2sb); @@ -152,22 +161,53 @@ static int p2sb_cache_resources(void) */ pci_lock_rescan_remove(); + pci_bus_read_config_dword(bus, devfn_p2sb, P2SBC, &value); + p2sb_hidden_by_bios = value & P2SBC_HIDE; + /* - * The BIOS prevents the P2SB device from being enumerated by the PCI - * subsystem, so we need to unhide and hide it back to lookup the BAR. - * Unhide the P2SB device here, if needed. + * If the BIOS does not hide the P2SB device then its resources + * are accesilble. Cache them only if the P2SB device is hidden. */ - pci_bus_read_config_dword(bus, devfn_p2sb, P2SBC, &value); - if (value & P2SBC_HIDE) - pci_bus_write_config_dword(bus, devfn_p2sb, P2SBC, 0); + if (p2sb_hidden_by_bios) + ret = p2sb_scan_and_cache(bus, devfn_p2sb); - ret = p2sb_scan_and_cache(bus, devfn_p2sb); + pci_unlock_rescan_remove(); - /* Hide the P2SB device, if it was hidden */ - if (value & P2SBC_HIDE) - pci_bus_write_config_dword(bus, devfn_p2sb, P2SBC, P2SBC_HIDE); + return ret; +} - pci_unlock_rescan_remove(); +static int p2sb_read_from_cache(struct pci_bus *bus, unsigned int devfn, + struct resource *mem) +{ + struct p2sb_res_cache *cache = &p2sb_resources[PCI_FUNC(devfn)]; + + if (cache->bus_dev_id != bus->dev.id) + return -ENODEV; + + if (!p2sb_valid_resource(&cache->res)) + return -ENOENT; + + memcpy(mem, &cache->res, sizeof(*mem)); + + return 0; +} + +static int p2sb_read_from_dev(struct pci_bus *bus, unsigned int devfn, + struct resource *mem) +{ + struct pci_dev *pdev; + int ret = 0; + + pdev = pci_get_slot(bus, devfn); + if (!pdev) + return -ENODEV; + + if (p2sb_valid_resource(pci_resource_n(pdev, 0))) + p2sb_read_bar0(pdev, mem); + else + ret = -ENOENT; + + pci_dev_put(pdev); return ret; } @@ -188,8 +228,6 @@ static int p2sb_cache_resources(void) */ int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem) { - struct p2sb_res_cache *cache; - bus = p2sb_get_bus(bus); if (!bus) return -ENODEV; @@ -197,15 +235,10 @@ int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem) if (!devfn) p2sb_get_devfn(&devfn); - cache = &p2sb_resources[PCI_FUNC(devfn)]; - if (cache->bus_dev_id != bus->dev.id) - return -ENODEV; + if (p2sb_hidden_by_bios) + return p2sb_read_from_cache(bus, devfn, mem); - if (!p2sb_valid_resource(&cache->res)) - return -ENOENT; - - memcpy(mem, &cache->res, sizeof(*mem)); - return 0; + return p2sb_read_from_dev(bus, devfn, mem); } EXPORT_SYMBOL_GPL(p2sb_bar); diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 0a39f68c641d..bdc19cd8d3ed 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -855,6 +855,23 @@ static const struct ts_dmi_data rwc_nanote_next_data = { .properties = rwc_nanote_next_props, }; +static const struct property_entry sary_tab_3_props[] = { + PROPERTY_ENTRY_U32("touchscreen-size-x", 1730), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1151), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-x"), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), + PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-sary-tab-3.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + PROPERTY_ENTRY_BOOL("silead,home-button"), + { } +}; + +static const struct ts_dmi_data sary_tab_3_data = { + .acpi_name = "MSSL1680:00", + .properties = sary_tab_3_props, +}; + static const struct property_entry schneider_sct101ctm_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1715), PROPERTY_ENTRY_U32("touchscreen-size-y", 1140), @@ -1616,6 +1633,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* SARY Tab 3 */ + .driver_data = (void *)&sary_tab_3_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "SARY"), + DMI_MATCH(DMI_PRODUCT_NAME, "C210C"), + DMI_MATCH(DMI_PRODUCT_SKU, "TAB3"), + }, + }, + { /* Schneider SCT101CTM */ .driver_data = (void *)&schneider_sct101ctm_data, .matches = { diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c index b889e64522c3..17e591f61efb 100644 --- a/drivers/pwm/pwm-stm32.c +++ b/drivers/pwm/pwm-stm32.c @@ -84,7 +84,7 @@ static int stm32_pwm_round_waveform_tohw(struct pwm_chip *chip, wfhw->ccer = TIM_CCER_CCxE(ch + 1); if (priv->have_complementary_output) - wfhw->ccer = TIM_CCER_CCxNE(ch + 1); + wfhw->ccer |= TIM_CCER_CCxNE(ch + 1); rate = clk_get_rate(priv->clk); diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c index 3d85762beda6..e5b4b93c07e3 100644 --- a/drivers/regulator/of_regulator.c +++ b/drivers/regulator/of_regulator.c @@ -175,7 +175,7 @@ static int of_get_regulation_constraints(struct device *dev, if (!ret) constraints->enable_time = pval; - ret = of_property_read_u32(np, "regulator-uv-survival-time-ms", &pval); + ret = of_property_read_u32(np, "regulator-uv-less-critical-window-ms", &pval); if (!ret) constraints->uv_less_critical_window_ms = pval; else diff --git a/drivers/spi/spi-rockchip-sfc.c b/drivers/spi/spi-rockchip-sfc.c index 69d0f2175568..70bbb459caa4 100644 --- a/drivers/spi/spi-rockchip-sfc.c +++ b/drivers/spi/spi-rockchip-sfc.c @@ -182,6 +182,7 @@ struct rockchip_sfc { bool use_dma; u32 max_iosize; u16 version; + struct spi_controller *host; }; static int rockchip_sfc_reset(struct rockchip_sfc *sfc) @@ -574,6 +575,7 @@ static int rockchip_sfc_probe(struct platform_device *pdev) sfc = spi_controller_get_devdata(host); sfc->dev = dev; + sfc->host = host; sfc->regbase = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(sfc->regbase)) @@ -651,8 +653,8 @@ err_hclk: static void rockchip_sfc_remove(struct platform_device *pdev) { - struct spi_controller *host = platform_get_drvdata(pdev); struct rockchip_sfc *sfc = platform_get_drvdata(pdev); + struct spi_controller *host = sfc->host; spi_unregister_controller(host); diff --git a/drivers/staging/fbtft/Kconfig b/drivers/staging/fbtft/Kconfig index 77ab44362f16..dcf6a70455cc 100644 --- a/drivers/staging/fbtft/Kconfig +++ b/drivers/staging/fbtft/Kconfig @@ -3,6 +3,7 @@ menuconfig FB_TFT tristate "Support for small TFT LCD display modules" depends on FB && SPI depends on FB_DEVICE + depends on BACKLIGHT_CLASS_DEVICE depends on GPIOLIB || COMPILE_TEST select FB_BACKLIGHT select FB_SYSMEM_HELPERS_DEFERRED diff --git a/drivers/staging/gpib/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/fs/btrfs/bio.c b/fs/btrfs/bio.c index af3db0a7ae4d..7ea6f0b43b95 100644 --- a/fs/btrfs/bio.c +++ b/fs/btrfs/bio.c @@ -358,7 +358,7 @@ static void btrfs_simple_end_io(struct bio *bio) INIT_WORK(&bbio->end_io_work, btrfs_end_bio_work); queue_work(btrfs_end_io_wq(fs_info, bio), &bbio->end_io_work); } else { - if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status) + if (bio_is_zone_append(bio) && !bio->bi_status) btrfs_record_physical_zoned(bbio); btrfs_bio_end_io(bbio, bbio->bio.bi_status); } @@ -401,7 +401,7 @@ static void btrfs_orig_write_end_io(struct bio *bio) else bio->bi_status = BLK_STS_OK; - if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status) + if (bio_is_zone_append(bio) && !bio->bi_status) stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; btrfs_bio_end_io(bbio, bbio->bio.bi_status); @@ -415,7 +415,7 @@ static void btrfs_clone_write_end_io(struct bio *bio) if (bio->bi_status) { atomic_inc(&stripe->bioc->error); btrfs_log_dev_io_error(bio, stripe->dev); - } else if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + } else if (bio_is_zone_append(bio)) { stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; } @@ -652,8 +652,14 @@ static u64 btrfs_append_map_length(struct btrfs_bio *bbio, u64 map_length) map_length = min(map_length, bbio->fs_info->max_zone_append_size); sector_offset = bio_split_rw_at(&bbio->bio, &bbio->fs_info->limits, &nr_segs, map_length); - if (sector_offset) - return sector_offset << SECTOR_SHIFT; + if (sector_offset) { + /* + * bio_split_rw_at() could split at a size smaller than our + * sectorsize and thus cause unaligned I/Os. Fix that by + * always rounding down to the nearest boundary. + */ + return ALIGN_DOWN(sector_offset << SECTOR_SHIFT, bbio->fs_info->sectorsize); + } return map_length; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 307dedf95c70..2c341956a01c 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -371,6 +371,25 @@ static inline void btrfs_set_root_last_trans(struct btrfs_root *root, u64 transi } /* + * Return the generation this root started with. + * + * Every normal root that is created with root->root_key.offset set to it's + * originating generation. If it is a snapshot it is the generation when the + * snapshot was created. + * + * However for TREE_RELOC roots root_key.offset is the objectid of the owning + * tree root. Thankfully we copy the root item of the owning tree root, which + * has it's last_snapshot set to what we would have root_key.offset set to, so + * return that if this is a TREE_RELOC root. + */ +static inline u64 btrfs_root_origin_generation(const struct btrfs_root *root) +{ + if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) + return btrfs_root_last_snapshot(&root->root_item); + return root->root_key.offset; +} + +/* * Structure that conveys information about an extent that is going to replace * all the extents in a file range. */ diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index bd09dd3ad1a0..3c6f7fecbb9a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5285,7 +5285,7 @@ static bool visit_node_for_delete(struct btrfs_root *root, struct walk_control * * reference to it. */ generation = btrfs_node_ptr_generation(eb, slot); - if (!wc->update_ref || generation <= root->root_key.offset) + if (!wc->update_ref || generation <= btrfs_root_origin_generation(root)) return false; /* @@ -5340,7 +5340,7 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans, goto reada; if (wc->stage == UPDATE_BACKREF && - generation <= root->root_key.offset) + generation <= btrfs_root_origin_generation(root)) continue; /* We don't lock the tree block, it's OK to be racy here */ @@ -5683,7 +5683,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans, * for the subtree */ if (wc->stage == UPDATE_BACKREF && - generation <= root->root_key.offset) { + generation <= btrfs_root_origin_generation(root)) { wc->lookup_info = 1; return 1; } diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 148d8cefa40e..dfeee033f31f 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1527,6 +1527,11 @@ static int check_extent_item(struct extent_buffer *leaf, dref_offset, fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_extent_data_ref_count(leaf, dref) == 0)) { + extent_err(leaf, slot, + "invalid data ref count, should have non-zero value"); + return -EUCLEAN; + } inline_refs += btrfs_extent_data_ref_count(leaf, dref); break; /* Contains parent bytenr and ref count */ @@ -1539,6 +1544,11 @@ static int check_extent_item(struct extent_buffer *leaf, inline_offset, fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_shared_data_ref_count(leaf, sref) == 0)) { + extent_err(leaf, slot, + "invalid shared data ref count, should have non-zero value"); + return -EUCLEAN; + } inline_refs += btrfs_shared_data_ref_count(leaf, sref); break; case BTRFS_EXTENT_OWNER_REF_KEY: @@ -1611,8 +1621,18 @@ static int check_simple_keyed_refs(struct extent_buffer *leaf, { u32 expect_item_size = 0; - if (key->type == BTRFS_SHARED_DATA_REF_KEY) + if (key->type == BTRFS_SHARED_DATA_REF_KEY) { + struct btrfs_shared_data_ref *sref; + + sref = btrfs_item_ptr(leaf, slot, struct btrfs_shared_data_ref); + if (unlikely(btrfs_shared_data_ref_count(leaf, sref) == 0)) { + extent_err(leaf, slot, + "invalid shared data backref count, should have non-zero value"); + return -EUCLEAN; + } + expect_item_size = sizeof(struct btrfs_shared_data_ref); + } if (unlikely(btrfs_item_size(leaf, slot) != expect_item_size)) { generic_err(leaf, slot, @@ -1689,6 +1709,11 @@ static int check_extent_data_ref(struct extent_buffer *leaf, offset, leaf->fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_extent_data_ref_count(leaf, dref) == 0)) { + extent_err(leaf, slot, + "invalid extent data backref count, should have non-zero value"); + return -EUCLEAN; + } } return 0; } diff --git a/fs/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/erofs/data.c b/fs/erofs/data.c index 1c49f8962021..0cd6b5c4df98 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -56,10 +56,10 @@ void erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb) buf->file = NULL; if (erofs_is_fileio_mode(sbi)) { - buf->file = sbi->fdev; /* some fs like FUSE needs it */ + buf->file = sbi->dif0.file; /* some fs like FUSE needs it */ buf->mapping = buf->file->f_mapping; } else if (erofs_is_fscache_mode(sb)) - buf->mapping = sbi->s_fscache->inode->i_mapping; + buf->mapping = sbi->dif0.fscache->inode->i_mapping; else buf->mapping = sb->s_bdev->bd_mapping; } @@ -179,19 +179,13 @@ out: } static void erofs_fill_from_devinfo(struct erofs_map_dev *map, - struct erofs_device_info *dif) + struct super_block *sb, struct erofs_device_info *dif) { + map->m_sb = sb; + map->m_dif = dif; map->m_bdev = NULL; - map->m_fp = NULL; - if (dif->file) { - if (S_ISBLK(file_inode(dif->file)->i_mode)) - map->m_bdev = file_bdev(dif->file); - else - map->m_fp = dif->file; - } - map->m_daxdev = dif->dax_dev; - map->m_dax_part_off = dif->dax_part_off; - map->m_fscache = dif->fscache; + if (dif->file && S_ISBLK(file_inode(dif->file)->i_mode)) + map->m_bdev = file_bdev(dif->file); } int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) @@ -201,12 +195,8 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) erofs_off_t startoff, length; int id; - map->m_bdev = sb->s_bdev; - map->m_daxdev = EROFS_SB(sb)->dax_dev; - map->m_dax_part_off = EROFS_SB(sb)->dax_part_off; - map->m_fscache = EROFS_SB(sb)->s_fscache; - map->m_fp = EROFS_SB(sb)->fdev; - + erofs_fill_from_devinfo(map, sb, &EROFS_SB(sb)->dif0); + map->m_bdev = sb->s_bdev; /* use s_bdev for the primary device */ if (map->m_deviceid) { down_read(&devs->rwsem); dif = idr_find(&devs->tree, map->m_deviceid - 1); @@ -219,7 +209,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) up_read(&devs->rwsem); return 0; } - erofs_fill_from_devinfo(map, dif); + erofs_fill_from_devinfo(map, sb, dif); up_read(&devs->rwsem); } else if (devs->extra_devices && !devs->flatdev) { down_read(&devs->rwsem); @@ -232,7 +222,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) if (map->m_pa >= startoff && map->m_pa < startoff + length) { map->m_pa -= startoff; - erofs_fill_from_devinfo(map, dif); + erofs_fill_from_devinfo(map, sb, dif); break; } } @@ -302,7 +292,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, iomap->offset = map.m_la; if (flags & IOMAP_DAX) - iomap->dax_dev = mdev.m_daxdev; + iomap->dax_dev = mdev.m_dif->dax_dev; else iomap->bdev = mdev.m_bdev; iomap->length = map.m_llen; @@ -331,7 +321,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, iomap->type = IOMAP_MAPPED; iomap->addr = mdev.m_pa; if (flags & IOMAP_DAX) - iomap->addr += mdev.m_dax_part_off; + iomap->addr += mdev.m_dif->dax_part_off; } return 0; } diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c index 3af96b1e2c2a..33f8539dda4a 100644 --- a/fs/erofs/fileio.c +++ b/fs/erofs/fileio.c @@ -9,6 +9,7 @@ struct erofs_fileio_rq { struct bio_vec bvecs[BIO_MAX_VECS]; struct bio bio; struct kiocb iocb; + struct super_block *sb; }; struct erofs_fileio { @@ -52,8 +53,9 @@ static void erofs_fileio_rq_submit(struct erofs_fileio_rq *rq) rq->iocb.ki_pos = rq->bio.bi_iter.bi_sector << SECTOR_SHIFT; rq->iocb.ki_ioprio = get_current_ioprio(); rq->iocb.ki_complete = erofs_fileio_ki_complete; - rq->iocb.ki_flags = (rq->iocb.ki_filp->f_mode & FMODE_CAN_ODIRECT) ? - IOCB_DIRECT : 0; + if (test_opt(&EROFS_SB(rq->sb)->opt, DIRECT_IO) && + rq->iocb.ki_filp->f_mode & FMODE_CAN_ODIRECT) + rq->iocb.ki_flags = IOCB_DIRECT; iov_iter_bvec(&iter, ITER_DEST, rq->bvecs, rq->bio.bi_vcnt, rq->bio.bi_iter.bi_size); ret = vfs_iocb_iter_read(rq->iocb.ki_filp, &rq->iocb, &iter); @@ -67,7 +69,8 @@ static struct erofs_fileio_rq *erofs_fileio_rq_alloc(struct erofs_map_dev *mdev) GFP_KERNEL | __GFP_NOFAIL); bio_init(&rq->bio, NULL, rq->bvecs, BIO_MAX_VECS, REQ_OP_READ); - rq->iocb.ki_filp = mdev->m_fp; + rq->iocb.ki_filp = mdev->m_dif->file; + rq->sb = mdev->m_sb; return rq; } diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index fda16eedafb5..ce3d8737df85 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -198,7 +198,7 @@ struct bio *erofs_fscache_bio_alloc(struct erofs_map_dev *mdev) io = kmalloc(sizeof(*io), GFP_KERNEL | __GFP_NOFAIL); bio_init(&io->bio, NULL, io->bvecs, BIO_MAX_VECS, REQ_OP_READ); - io->io.private = mdev->m_fscache->cookie; + io->io.private = mdev->m_dif->fscache->cookie; io->io.end_io = erofs_fscache_bio_endio; refcount_set(&io->io.ref, 1); return &io->bio; @@ -316,7 +316,7 @@ static int erofs_fscache_data_read_slice(struct erofs_fscache_rq *req) if (!io) return -ENOMEM; iov_iter_xarray(&io->iter, ITER_DEST, &mapping->i_pages, pos, count); - ret = erofs_fscache_read_io_async(mdev.m_fscache->cookie, + ret = erofs_fscache_read_io_async(mdev.m_dif->fscache->cookie, mdev.m_pa + (pos - map.m_la), io); erofs_fscache_req_io_put(io); @@ -657,7 +657,7 @@ int erofs_fscache_register_fs(struct super_block *sb) if (IS_ERR(fscache)) return PTR_ERR(fscache); - sbi->s_fscache = fscache; + sbi->dif0.fscache = fscache; return 0; } @@ -665,14 +665,14 @@ void erofs_fscache_unregister_fs(struct super_block *sb) { struct erofs_sb_info *sbi = EROFS_SB(sb); - erofs_fscache_unregister_cookie(sbi->s_fscache); + erofs_fscache_unregister_cookie(sbi->dif0.fscache); if (sbi->domain) erofs_fscache_domain_put(sbi->domain); else fscache_relinquish_volume(sbi->volume, NULL, false); - sbi->s_fscache = NULL; + sbi->dif0.fscache = NULL; sbi->volume = NULL; sbi->domain = NULL; } diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 1c847c30a918..686d835eb533 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -107,6 +107,7 @@ struct erofs_xattr_prefix_item { }; struct erofs_sb_info { + struct erofs_device_info dif0; struct erofs_mount_opts opt; /* options */ #ifdef CONFIG_EROFS_FS_ZIP /* list for all registered superblocks, mainly for shrinker */ @@ -124,13 +125,9 @@ struct erofs_sb_info { struct erofs_sb_lz4_info lz4; #endif /* CONFIG_EROFS_FS_ZIP */ - struct file *fdev; struct inode *packed_inode; struct erofs_dev_context *devs; - struct dax_device *dax_dev; - u64 dax_part_off; u64 total_blocks; - u32 primarydevice_blocks; u32 meta_blkaddr; #ifdef CONFIG_EROFS_FS_XATTR @@ -166,7 +163,6 @@ struct erofs_sb_info { /* fscache support */ struct fscache_volume *volume; - struct erofs_fscache *s_fscache; struct erofs_domain *domain; char *fsid; char *domain_id; @@ -180,6 +176,7 @@ struct erofs_sb_info { #define EROFS_MOUNT_POSIX_ACL 0x00000020 #define EROFS_MOUNT_DAX_ALWAYS 0x00000040 #define EROFS_MOUNT_DAX_NEVER 0x00000080 +#define EROFS_MOUNT_DIRECT_IO 0x00000100 #define clear_opt(opt, option) ((opt)->mount_opt &= ~EROFS_MOUNT_##option) #define set_opt(opt, option) ((opt)->mount_opt |= EROFS_MOUNT_##option) @@ -187,7 +184,7 @@ struct erofs_sb_info { static inline bool erofs_is_fileio_mode(struct erofs_sb_info *sbi) { - return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->fdev; + return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->dif0.file; } static inline bool erofs_is_fscache_mode(struct super_block *sb) @@ -357,11 +354,9 @@ enum { }; struct erofs_map_dev { - struct erofs_fscache *m_fscache; + struct super_block *m_sb; + struct erofs_device_info *m_dif; struct block_device *m_bdev; - struct dax_device *m_daxdev; - struct file *m_fp; - u64 m_dax_part_off; erofs_off_t m_pa; unsigned int m_deviceid; diff --git a/fs/erofs/super.c b/fs/erofs/super.c index c235a8e4315e..f5956474bfde 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -203,7 +203,7 @@ static int erofs_scan_devices(struct super_block *sb, struct erofs_device_info *dif; int id, err = 0; - sbi->total_blocks = sbi->primarydevice_blocks; + sbi->total_blocks = sbi->dif0.blocks; if (!erofs_sb_has_device_table(sbi)) ondisk_extradevs = 0; else @@ -307,7 +307,7 @@ static int erofs_read_superblock(struct super_block *sb) sbi->sb_size); goto out; } - sbi->primarydevice_blocks = le32_to_cpu(dsb->blocks); + sbi->dif0.blocks = le32_to_cpu(dsb->blocks); sbi->meta_blkaddr = le32_to_cpu(dsb->meta_blkaddr); #ifdef CONFIG_EROFS_FS_XATTR sbi->xattr_blkaddr = le32_to_cpu(dsb->xattr_blkaddr); @@ -364,14 +364,8 @@ static void erofs_default_options(struct erofs_sb_info *sbi) } enum { - Opt_user_xattr, - Opt_acl, - Opt_cache_strategy, - Opt_dax, - Opt_dax_enum, - Opt_device, - Opt_fsid, - Opt_domain_id, + Opt_user_xattr, Opt_acl, Opt_cache_strategy, Opt_dax, Opt_dax_enum, + Opt_device, Opt_fsid, Opt_domain_id, Opt_directio, Opt_err }; @@ -398,6 +392,7 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = { fsparam_string("device", Opt_device), fsparam_string("fsid", Opt_fsid), fsparam_string("domain_id", Opt_domain_id), + fsparam_flag_no("directio", Opt_directio), {} }; @@ -511,6 +506,16 @@ static int erofs_fc_parse_param(struct fs_context *fc, errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name); break; #endif + case Opt_directio: +#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE + if (result.boolean) + set_opt(&sbi->opt, DIRECT_IO); + else + clear_opt(&sbi->opt, DIRECT_IO); +#else + errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name); +#endif + break; default: return -ENOPARAM; } @@ -602,9 +607,8 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) return -EINVAL; } - sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, - &sbi->dax_part_off, - NULL, NULL); + sbi->dif0.dax_dev = fs_dax_get_by_bdev(sb->s_bdev, + &sbi->dif0.dax_part_off, NULL, NULL); } err = erofs_read_superblock(sb); @@ -627,7 +631,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) } if (test_opt(&sbi->opt, DAX_ALWAYS)) { - if (!sbi->dax_dev) { + if (!sbi->dif0.dax_dev) { errorfc(fc, "DAX unsupported by block device. Turning off DAX."); clear_opt(&sbi->opt, DAX_ALWAYS); } else if (sbi->blkszbits != PAGE_SHIFT) { @@ -703,16 +707,18 @@ static int erofs_fc_get_tree(struct fs_context *fc) GET_TREE_BDEV_QUIET_LOOKUP : 0); #ifdef CONFIG_EROFS_FS_BACKED_BY_FILE if (ret == -ENOTBLK) { + struct file *file; + if (!fc->source) return invalf(fc, "No source specified"); - sbi->fdev = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0); - if (IS_ERR(sbi->fdev)) - return PTR_ERR(sbi->fdev); + file = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0); + if (IS_ERR(file)) + return PTR_ERR(file); + sbi->dif0.file = file; - if (S_ISREG(file_inode(sbi->fdev)->i_mode) && - sbi->fdev->f_mapping->a_ops->read_folio) + if (S_ISREG(file_inode(sbi->dif0.file)->i_mode) && + sbi->dif0.file->f_mapping->a_ops->read_folio) return get_tree_nodev(fc, erofs_fc_fill_super); - fput(sbi->fdev); } #endif return ret; @@ -763,19 +769,24 @@ static void erofs_free_dev_context(struct erofs_dev_context *devs) kfree(devs); } -static void erofs_fc_free(struct fs_context *fc) +static void erofs_sb_free(struct erofs_sb_info *sbi) { - struct erofs_sb_info *sbi = fc->s_fs_info; - - if (!sbi) - return; - erofs_free_dev_context(sbi->devs); kfree(sbi->fsid); kfree(sbi->domain_id); + if (sbi->dif0.file) + fput(sbi->dif0.file); kfree(sbi); } +static void erofs_fc_free(struct fs_context *fc) +{ + struct erofs_sb_info *sbi = fc->s_fs_info; + + if (sbi) /* free here if an error occurs before transferring to sb */ + erofs_sb_free(sbi); +} + static const struct fs_context_operations erofs_context_ops = { .parse_param = erofs_fc_parse_param, .get_tree = erofs_fc_get_tree, @@ -809,19 +820,14 @@ static void erofs_kill_sb(struct super_block *sb) { struct erofs_sb_info *sbi = EROFS_SB(sb); - if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) || sbi->fdev) + if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) || + sbi->dif0.file) kill_anon_super(sb); else kill_block_super(sb); - - erofs_free_dev_context(sbi->devs); - fs_put_dax(sbi->dax_dev, NULL); + fs_put_dax(sbi->dif0.dax_dev, NULL); erofs_fscache_unregister_fs(sb); - kfree(sbi->fsid); - kfree(sbi->domain_id); - if (sbi->fdev) - fput(sbi->fdev); - kfree(sbi); + erofs_sb_free(sbi); sb->s_fs_info = NULL; } @@ -947,6 +953,8 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",dax=always"); if (test_opt(opt, DAX_NEVER)) seq_puts(seq, ",dax=never"); + if (erofs_is_fileio_mode(sbi) && test_opt(opt, DIRECT_IO)) + seq_puts(seq, ",directio"); #ifdef CONFIG_EROFS_FS_ONDEMAND if (sbi->fsid) seq_printf(seq, ",fsid=%s", sbi->fsid); diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 01f147505487..19ef4ff2a134 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1792,9 +1792,9 @@ drain_io: erofs_fscache_submit_bio(bio); else submit_bio(bio); - if (memstall) - psi_memstall_leave(&pflags); } + if (memstall) + psi_memstall_leave(&pflags); /* * although background is preferred, no one is pending for submission. diff --git a/fs/erofs/zutil.c b/fs/erofs/zutil.c index 75704f58ecfa..0dd65cefce33 100644 --- a/fs/erofs/zutil.c +++ b/fs/erofs/zutil.c @@ -230,9 +230,10 @@ void erofs_shrinker_unregister(struct super_block *sb) struct erofs_sb_info *const sbi = EROFS_SB(sb); mutex_lock(&sbi->umount_mutex); - /* clean up all remaining pclusters in memory */ - z_erofs_shrink_scan(sbi, ~0UL); - + while (!xa_empty(&sbi->managed_pslots)) { + z_erofs_shrink_scan(sbi, ~0UL); + cond_resched(); + } spin_lock(&erofs_sb_list_lock); list_del(&sbi->list); spin_unlock(&erofs_sb_list_lock); diff --git a/fs/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/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/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/fs/smb/server/connection.c b/fs/smb/server/connection.c index c14dd72e1b30..f8a40f65db6a 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -70,7 +70,6 @@ struct ksmbd_conn *ksmbd_conn_alloc(void) atomic_set(&conn->req_running, 0); atomic_set(&conn->r_count, 0); atomic_set(&conn->refcnt, 1); - atomic_set(&conn->mux_smb_requests, 0); conn->total_credits = 1; conn->outstanding_credits = 0; @@ -120,8 +119,8 @@ void ksmbd_conn_enqueue_request(struct ksmbd_work *work) if (conn->ops->get_cmd_val(work) != SMB2_CANCEL_HE) requests_queue = &conn->requests; + atomic_inc(&conn->req_running); if (requests_queue) { - atomic_inc(&conn->req_running); spin_lock(&conn->request_lock); list_add_tail(&work->request_entry, requests_queue); spin_unlock(&conn->request_lock); @@ -132,11 +131,14 @@ void ksmbd_conn_try_dequeue_request(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; + atomic_dec(&conn->req_running); + if (waitqueue_active(&conn->req_running_q)) + wake_up(&conn->req_running_q); + if (list_empty(&work->request_entry) && list_empty(&work->async_request_entry)) return; - atomic_dec(&conn->req_running); spin_lock(&conn->request_lock); list_del_init(&work->request_entry); spin_unlock(&conn->request_lock); @@ -308,7 +310,7 @@ int ksmbd_conn_handler_loop(void *p) { struct ksmbd_conn *conn = (struct ksmbd_conn *)p; struct ksmbd_transport *t = conn->transport; - unsigned int pdu_size, max_allowed_pdu_size; + unsigned int pdu_size, max_allowed_pdu_size, max_req; char hdr_buf[4] = {0,}; int size; @@ -318,6 +320,7 @@ int ksmbd_conn_handler_loop(void *p) if (t->ops->prepare && t->ops->prepare(t)) goto out; + max_req = server_conf.max_inflight_req; conn->last_active = jiffies; set_freezable(); while (ksmbd_conn_alive(conn)) { @@ -327,6 +330,13 @@ int ksmbd_conn_handler_loop(void *p) kvfree(conn->request_buf); conn->request_buf = NULL; +recheck: + if (atomic_read(&conn->req_running) + 1 > max_req) { + wait_event_interruptible(conn->req_running_q, + atomic_read(&conn->req_running) < max_req); + goto recheck; + } + size = t->ops->read(t, hdr_buf, sizeof(hdr_buf), -1); if (size != sizeof(hdr_buf)) break; diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index 8ddd5a3c7baf..b379ae4fdcdf 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -107,7 +107,6 @@ struct ksmbd_conn { __le16 signing_algorithm; bool binding; atomic_t refcnt; - atomic_t mux_smb_requests; }; struct ksmbd_conn_ops { diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index 3ba95bd8edeb..601e7fcbcf1e 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -270,7 +270,6 @@ static void handle_ksmbd_work(struct work_struct *wk) ksmbd_conn_try_dequeue_request(work); ksmbd_free_work_struct(work); - atomic_dec(&conn->mux_smb_requests); /* * Checking waitqueue to dropping pending requests on * disconnection. waitqueue_active is safe because it @@ -300,11 +299,6 @@ static int queue_ksmbd_work(struct ksmbd_conn *conn) if (err) return 0; - if (atomic_inc_return(&conn->mux_smb_requests) >= conn->vals->max_credits) { - atomic_dec_return(&conn->mux_smb_requests); - return -ENOSPC; - } - work = ksmbd_alloc_work_struct(); if (!work) { pr_err("allocation for work failed\n"); @@ -367,6 +361,7 @@ static int server_conf_init(void) server_conf.auth_mechs |= KSMBD_AUTH_KRB5 | KSMBD_AUTH_MSKRB5; #endif + server_conf.max_inflight_req = SMB2_MAX_CREDITS; return 0; } diff --git a/fs/smb/server/server.h b/fs/smb/server/server.h index 4fc529335271..94187628ff08 100644 --- a/fs/smb/server/server.h +++ b/fs/smb/server/server.h @@ -42,6 +42,7 @@ struct ksmbd_server_config { struct smb_sid domain_sid; unsigned int auth_mechs; unsigned int max_connections; + unsigned int max_inflight_req; char *conf[SERVER_CONF_WORK_GROUP + 1]; struct task_struct *dh_task; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 803b35b89513..23e21845f928 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -1097,6 +1097,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) return rc; } + ksmbd_conn_lock(conn); smb2_buf_len = get_rfc1002_len(work->request_buf); smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects); if (smb2_neg_size > smb2_buf_len) { @@ -1247,6 +1248,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) ksmbd_conn_set_need_negotiate(conn); err_out: + ksmbd_conn_unlock(conn); if (rc) rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES; diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index 48cda3350e5a..befaf42b84cc 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -319,8 +319,11 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req) init_smb2_max_write_size(req->smb2_max_write); if (req->smb2_max_trans) init_smb2_max_trans_size(req->smb2_max_trans); - if (req->smb2_max_credits) + if (req->smb2_max_credits) { init_smb2_max_credits(req->smb2_max_credits); + server_conf.max_inflight_req = + req->smb2_max_credits; + } if (req->smbd_max_io_size) init_smbd_max_io_size(req->smbd_max_io_size); diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h index 6cdc873ac907..aa5233b1eba9 100644 --- a/include/clocksource/hyperv_timer.h +++ b/include/clocksource/hyperv_timer.h @@ -38,6 +38,8 @@ extern void hv_remap_tsc_clocksource(void); extern unsigned long hv_get_tsc_pfn(void); extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void); +extern void hv_adj_sched_clock_offset(u64 offset); + static __always_inline bool hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc, u64 *time) diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index 7c0786bdf9af..0bbbe537c5f9 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -63,7 +63,12 @@ static inline void set_codetag_empty(union codetag_ref *ref) #else /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */ static inline bool is_codetag_empty(union codetag_ref *ref) { return false; } -static inline void set_codetag_empty(union codetag_ref *ref) {} + +static inline void set_codetag_empty(union codetag_ref *ref) +{ + if (ref) + ref->ct = NULL; +} #endif /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */ @@ -135,7 +140,7 @@ static inline struct alloc_tag_counters alloc_tag_read(struct alloc_tag *tag) #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG static inline void alloc_tag_add_check(union codetag_ref *ref, struct alloc_tag *tag) { - WARN_ONCE(ref && ref->ct, + WARN_ONCE(ref && ref->ct && !is_codetag_empty(ref), "alloc_tag was not cleared (got tag for %s:%u)\n", ref->ct->filename, ref->ct->lineno); diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index a28e2a6a13d0..74169dd0f659 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -166,9 +166,12 @@ static inline void *ffa_dev_get_drvdata(struct ffa_device *fdev) return dev_get_drvdata(&fdev->dev); } +struct ffa_partition_info; + #if IS_REACHABLE(CONFIG_ARM_FFA_TRANSPORT) -struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, - const struct ffa_ops *ops); +struct ffa_device * +ffa_device_register(const struct ffa_partition_info *part_info, + const struct ffa_ops *ops); void ffa_device_unregister(struct ffa_device *ffa_dev); int ffa_driver_register(struct ffa_driver *driver, struct module *owner, const char *mod_name); @@ -176,9 +179,9 @@ void ffa_driver_unregister(struct ffa_driver *driver); bool ffa_device_is_valid(struct ffa_device *ffa_dev); #else -static inline -struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, - const struct ffa_ops *ops) +static inline struct ffa_device * +ffa_device_register(const struct ffa_partition_info *part_info, + const struct ffa_ops *ops) { return NULL; } diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 108060612bb8..7ad736538649 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -155,8 +155,14 @@ static inline int get_cpu_cacheinfo_id(int cpu, int level) #ifndef CONFIG_ARCH_HAS_CPU_CACHE_ALIASING #define cpu_dcache_is_aliasing() false +#define cpu_icache_is_aliasing() cpu_dcache_is_aliasing() #else #include <asm/cachetype.h> + +#ifndef cpu_icache_is_aliasing +#define cpu_icache_is_aliasing() cpu_dcache_is_aliasing() +#endif + #endif #endif /* _LINUX_CACHEINFO_H */ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 469a64dd6495..240c632c5b95 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -216,28 +216,43 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #endif /* __KERNEL__ */ +/** + * offset_to_ptr - convert a relative memory offset to an absolute pointer + * @off: the address of the 32-bit offset value + */ +static inline void *offset_to_ptr(const int *off) +{ + return (void *)((unsigned long)off + *off); +} + +#endif /* __ASSEMBLY__ */ + +#ifdef CONFIG_64BIT +#define ARCH_SEL(a,b) a +#else +#define ARCH_SEL(a,b) b +#endif + /* * Force the compiler to emit 'sym' as a symbol, so that we can reference * it from inline assembler. Necessary in case 'sym' could be inlined * otherwise, or eliminated entirely due to lack of references that are * visible to the compiler. */ -#define ___ADDRESSABLE(sym, __attrs) \ - static void * __used __attrs \ +#define ___ADDRESSABLE(sym, __attrs) \ + static void * __used __attrs \ __UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)(uintptr_t)&sym; + #define __ADDRESSABLE(sym) \ ___ADDRESSABLE(sym, __section(".discard.addressable")) -/** - * offset_to_ptr - convert a relative memory offset to an absolute pointer - * @off: the address of the 32-bit offset value - */ -static inline void *offset_to_ptr(const int *off) -{ - return (void *)((unsigned long)off + *off); -} +#define __ADDRESSABLE_ASM(sym) \ + .pushsection .discard.addressable,"aw"; \ + .align ARCH_SEL(8,4); \ + ARCH_SEL(.quad, .long) __stringify(sym); \ + .popsection; -#endif /* __ASSEMBLY__ */ +#define __ADDRESSABLE_ASM_STR(sym) __stringify(__ADDRESSABLE_ASM(sym)) #ifdef __CHECKER__ #define __BUILD_BUG_ON_ZERO_MSG(e, msg) (0) diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index b137fdb56093..346251bf1026 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -84,7 +84,7 @@ enum dma_transfer_direction { DMA_TRANS_NONE, }; -/** +/* * Interleaved Transfer Request * ---------------------------- * A chunk is collection of contiguous bytes to be transferred. @@ -223,7 +223,7 @@ enum sum_check_bits { }; /** - * enum pq_check_flags - result of async_{xor,pq}_zero_sum operations + * enum sum_check_flags - result of async_{xor,pq}_zero_sum operations * @SUM_CHECK_P_RESULT - 1 if xor zero sum error, 0 otherwise * @SUM_CHECK_Q_RESULT - 1 if reed-solomon zero sum error, 0 otherwise */ @@ -286,7 +286,7 @@ typedef struct { DECLARE_BITMAP(bits, DMA_TX_TYPE_END); } dma_cap_mask_t; * pointer to the engine's metadata area * 4. Read out the metadata from the pointer * - * Note: the two mode is not compatible and clients must use one mode for a + * Warning: the two modes are not compatible and clients must use one mode for a * descriptor. */ enum dma_desc_metadata_mode { @@ -594,9 +594,13 @@ struct dma_descriptor_metadata_ops { * @phys: physical address of the descriptor * @chan: target channel for this operation * @tx_submit: accept the descriptor, assign ordered cookie and mark the + * @desc_free: driver's callback function to free a resusable descriptor + * after completion * descriptor pending. To be pushed on .issue_pending() call * @callback: routine to call after this operation is complete + * @callback_result: error result from a DMA transaction * @callback_param: general parameter to pass to the callback routine + * @unmap: hook for generic DMA unmap data * @desc_metadata_mode: core managed metadata mode to protect mixed use of * DESC_METADATA_CLIENT or DESC_METADATA_ENGINE. Otherwise * DESC_METADATA_NONE @@ -827,6 +831,9 @@ struct dma_filter { * @device_prep_dma_memset: prepares a memset operation * @device_prep_dma_memset_sg: prepares a memset operation over a scatter list * @device_prep_dma_interrupt: prepares an end of chain interrupt operation + * @device_prep_peripheral_dma_vec: prepares a scatter-gather DMA transfer, + * where the address and size of each segment is located in one entry of + * the dma_vec array. * @device_prep_slave_sg: prepares a slave dma operation * @device_prep_dma_cyclic: prepare a cyclic dma operation suitable for audio. * The function takes a buffer of size buf_len. The callback function will diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 0d99bf11d260..e4ce1cae03bf 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -616,6 +616,12 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, return false; } +/* + * To work around what seems to be an optimizer bug, the macro arguments + * need to have const copies or the values end up changed by the time they + * reach fortify_warn_once(). See commit 6f7630b1b5bc ("fortify: Capture + * __bos() results in const temp vars") for more details. + */ #define __fortify_memcpy_chk(p, q, size, p_size, q_size, \ p_size_field, q_size_field, op) ({ \ const size_t __fortify_size = (size_t)(size); \ @@ -623,6 +629,8 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, const size_t __q_size = (q_size); \ const size_t __p_size_field = (p_size_field); \ const size_t __q_size_field = (q_size_field); \ + /* Keep a mutable version of the size for the final copy. */ \ + size_t __copy_size = __fortify_size; \ fortify_warn_once(fortify_memcpy_chk(__fortify_size, __p_size, \ __q_size, __p_size_field, \ __q_size_field, FORTIFY_FUNC_ ##op), \ @@ -630,7 +638,11 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, __fortify_size, \ "field \"" #p "\" at " FILE_LINE, \ __p_size_field); \ - __underlying_##op(p, q, __fortify_size); \ + /* Hide only the run-time size from value range tracking to */ \ + /* silence compile-time false positive bounds warnings. */ \ + if (!__builtin_constant_p(__copy_size)) \ + OPTIMIZER_HIDE_VAR(__copy_size); \ + __underlying_##op(p, q, __copy_size); \ }) /* diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 6e452bd8e7e3..5c6bea81a90e 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -224,7 +224,13 @@ static inline struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr) { - return vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr); + struct folio *folio; + + folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr); + if (folio && user_alloc_needs_zeroing()) + clear_user_highpage(&folio->page, vaddr); + + return folio; } #endif diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 22c22fb91042..02a226bcf0ed 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1559,6 +1559,7 @@ struct hv_util_service { void *channel; void (*util_cb)(void *); int (*util_init)(struct hv_util_service *); + int (*util_init_transport)(void); void (*util_deinit)(void); int (*util_pre_suspend)(void); int (*util_pre_resume)(void); diff --git a/include/linux/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/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/skmsg.h b/include/linux/skmsg.h index d9b03e0746e7..2cbe0c22a32f 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -317,17 +317,22 @@ static inline void sock_drop(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); } -static inline void sk_psock_queue_msg(struct sk_psock *psock, +static inline bool sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { + bool ret; + spin_lock_bh(&psock->ingress_lock); - if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { list_add_tail(&msg->list, &psock->ingress_msg); - else { + ret = true; + } else { sk_msg_free(psock->sk, msg); kfree(msg); + ret = false; } spin_unlock_bh(&psock->ingress_lock); + return ret; } static inline struct sk_msg *sk_psock_dequeue_msg(struct sk_psock *psock) diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 141e6b176a1b..78a77a4ae0ea 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -160,6 +160,8 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool #ifdef CONFIG_HAVE_STATIC_CALL_INLINE +extern int static_call_initialized; + extern int __init static_call_init(void); extern void static_call_force_reinit(void); @@ -225,6 +227,8 @@ extern long __static_call_return0(void); #elif defined(CONFIG_HAVE_STATIC_CALL) +#define static_call_initialized 0 + static inline int static_call_init(void) { return 0; } #define DEFINE_STATIC_CALL(name, _func) \ @@ -281,6 +285,8 @@ extern long __static_call_return0(void); #else /* Generic implementation */ +#define static_call_initialized 0 + static inline int static_call_init(void) { return 0; } static inline long __static_call_return0(void) diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 2a5df5b62cfc..91b8ffbdfa8c 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -273,7 +273,8 @@ struct trace_event_fields { const char *name; const int size; const int align; - const int is_signed; + const unsigned int is_signed:1; + unsigned int needs_test:1; const int filter_type; const int len; }; @@ -324,6 +325,7 @@ enum { TRACE_EVENT_FL_EPROBE_BIT, TRACE_EVENT_FL_FPROBE_BIT, TRACE_EVENT_FL_CUSTOM_BIT, + TRACE_EVENT_FL_TEST_STR_BIT, }; /* @@ -340,6 +342,7 @@ enum { * CUSTOM - Event is a custom event (to be attached to an exsiting tracepoint) * This is set when the custom event has not been attached * to a tracepoint yet, then it is cleared when it is. + * TEST_STR - The event has a "%s" that points to a string outside the event */ enum { TRACE_EVENT_FL_CAP_ANY = (1 << TRACE_EVENT_FL_CAP_ANY_BIT), @@ -352,6 +355,7 @@ enum { TRACE_EVENT_FL_EPROBE = (1 << TRACE_EVENT_FL_EPROBE_BIT), TRACE_EVENT_FL_FPROBE = (1 << TRACE_EVENT_FL_FPROBE_BIT), TRACE_EVENT_FL_CUSTOM = (1 << TRACE_EVENT_FL_CUSTOM_BIT), + TRACE_EVENT_FL_TEST_STR = (1 << TRACE_EVENT_FL_TEST_STR_BIT), }; #define TRACE_EVENT_FL_UKPROBE (TRACE_EVENT_FL_KPROBE | TRACE_EVENT_FL_UPROBE) 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/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/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/static_call_inline.c b/kernel/static_call_inline.c index 5259cda486d0..bb7d066a7c39 100644 --- a/kernel/static_call_inline.c +++ b/kernel/static_call_inline.c @@ -15,7 +15,7 @@ extern struct static_call_site __start_static_call_sites[], extern struct static_call_tramp_key __start_static_call_tramp_key[], __stop_static_call_tramp_key[]; -static int static_call_initialized; +int static_call_initialized; /* * Must be called before early_initcall() to be effective. diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 0bf78517b5d4..ddedcb50917f 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -1215,7 +1215,7 @@ void fgraph_update_pid_func(void) static int start_graph_tracing(void) { unsigned long **ret_stack_list; - int ret; + int ret, cpu; ret_stack_list = kcalloc(FTRACE_RETSTACK_ALLOC_SIZE, sizeof(*ret_stack_list), GFP_KERNEL); @@ -1223,6 +1223,12 @@ static int start_graph_tracing(void) if (!ret_stack_list) return -ENOMEM; + /* The cpu_boot init_task->ret_stack will never be freed */ + for_each_online_cpu(cpu) { + if (!idle_task(cpu)->ret_stack) + ftrace_graph_init_idle_task(idle_task(cpu), cpu); + } + do { ret = alloc_retstack_tasklist(ret_stack_list); } while (ret == -EAGAIN); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 7e257e855dd1..60210fb5b211 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -7019,7 +7019,11 @@ static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer, lockdep_assert_held(&cpu_buffer->mapping_lock); nr_subbufs = cpu_buffer->nr_pages + 1; /* + reader-subbuf */ - nr_pages = ((nr_subbufs + 1) << subbuf_order) - pgoff; /* + meta-page */ + nr_pages = ((nr_subbufs + 1) << subbuf_order); /* + meta-page */ + if (nr_pages <= pgoff) + return -EINVAL; + + nr_pages -= pgoff; nr_vma_pages = vma_pages(vma); if (!nr_vma_pages || nr_vma_pages > nr_pages) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index be62f0ea1814..957f941a08e7 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3611,17 +3611,12 @@ char *trace_iter_expand_format(struct trace_iterator *iter) } /* Returns true if the string is safe to dereference from an event */ -static bool trace_safe_str(struct trace_iterator *iter, const char *str, - bool star, int len) +static bool trace_safe_str(struct trace_iterator *iter, const char *str) { unsigned long addr = (unsigned long)str; struct trace_event *trace_event; struct trace_event_call *event; - /* Ignore strings with no length */ - if (star && !len) - return true; - /* OK if part of the event data */ if ((addr >= (unsigned long)iter->ent) && (addr < (unsigned long)iter->ent + iter->ent_size)) @@ -3661,181 +3656,69 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str, return false; } -static DEFINE_STATIC_KEY_FALSE(trace_no_verify); - -static int test_can_verify_check(const char *fmt, ...) -{ - char buf[16]; - va_list ap; - int ret; - - /* - * The verifier is dependent on vsnprintf() modifies the va_list - * passed to it, where it is sent as a reference. Some architectures - * (like x86_32) passes it by value, which means that vsnprintf() - * does not modify the va_list passed to it, and the verifier - * would then need to be able to understand all the values that - * vsnprintf can use. If it is passed by value, then the verifier - * is disabled. - */ - va_start(ap, fmt); - vsnprintf(buf, 16, "%d", ap); - ret = va_arg(ap, int); - va_end(ap); - - return ret; -} - -static void test_can_verify(void) -{ - if (!test_can_verify_check("%d %d", 0, 1)) { - pr_info("trace event string verifier disabled\n"); - static_branch_inc(&trace_no_verify); - } -} - /** - * trace_check_vprintf - Check dereferenced strings while writing to the seq buffer + * ignore_event - Check dereferenced fields while writing to the seq buffer * @iter: The iterator that holds the seq buffer and the event being printed - * @fmt: The format used to print the event - * @ap: The va_list holding the data to print from @fmt. * - * This writes the data into the @iter->seq buffer using the data from - * @fmt and @ap. If the format has a %s, then the source of the string - * is examined to make sure it is safe to print, otherwise it will - * warn and print "[UNSAFE MEMORY]" in place of the dereferenced string - * pointer. + * At boot up, test_event_printk() will flag any event that dereferences + * a string with "%s" that does exist in the ring buffer. It may still + * be valid, as the string may point to a static string in the kernel + * rodata that never gets freed. But if the string pointer is pointing + * to something that was allocated, there's a chance that it can be freed + * by the time the user reads the trace. This would cause a bad memory + * access by the kernel and possibly crash the system. + * + * This function will check if the event has any fields flagged as needing + * to be checked at runtime and perform those checks. + * + * If it is found that a field is unsafe, it will write into the @iter->seq + * a message stating what was found to be unsafe. + * + * @return: true if the event is unsafe and should be ignored, + * false otherwise. */ -void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, - va_list ap) +bool ignore_event(struct trace_iterator *iter) { - long text_delta = 0; - long data_delta = 0; - const char *p = fmt; - const char *str; - bool good; - int i, j; + struct ftrace_event_field *field; + struct trace_event *trace_event; + struct trace_event_call *event; + struct list_head *head; + struct trace_seq *seq; + const void *ptr; - if (WARN_ON_ONCE(!fmt)) - return; + trace_event = ftrace_find_event(iter->ent->type); - if (static_branch_unlikely(&trace_no_verify)) - goto print; + seq = &iter->seq; - /* - * When the kernel is booted with the tp_printk command line - * parameter, trace events go directly through to printk(). - * It also is checked by this function, but it does not - * have an associated trace_array (tr) for it. - */ - if (iter->tr) { - text_delta = iter->tr->text_delta; - data_delta = iter->tr->data_delta; + if (!trace_event) { + trace_seq_printf(seq, "EVENT ID %d NOT FOUND?\n", iter->ent->type); + return true; } - /* Don't bother checking when doing a ftrace_dump() */ - if (iter->fmt == static_fmt_buf) - goto print; - - while (*p) { - bool star = false; - int len = 0; - - j = 0; - - /* - * We only care about %s and variants - * as well as %p[sS] if delta is non-zero - */ - for (i = 0; p[i]; i++) { - if (i + 1 >= iter->fmt_size) { - /* - * If we can't expand the copy buffer, - * just print it. - */ - if (!trace_iter_expand_format(iter)) - goto print; - } - - if (p[i] == '\\' && p[i+1]) { - i++; - continue; - } - if (p[i] == '%') { - /* Need to test cases like %08.*s */ - for (j = 1; p[i+j]; j++) { - if (isdigit(p[i+j]) || - p[i+j] == '.') - continue; - if (p[i+j] == '*') { - star = true; - continue; - } - break; - } - if (p[i+j] == 's') - break; - - if (text_delta && p[i+1] == 'p' && - ((p[i+2] == 's' || p[i+2] == 'S'))) - break; - - star = false; - } - j = 0; - } - /* If no %s found then just print normally */ - if (!p[i]) - break; - - /* Copy up to the %s, and print that */ - strncpy(iter->fmt, p, i); - iter->fmt[i] = '\0'; - trace_seq_vprintf(&iter->seq, iter->fmt, ap); + event = container_of(trace_event, struct trace_event_call, event); + if (!(event->flags & TRACE_EVENT_FL_TEST_STR)) + return false; - /* Add delta to %pS pointers */ - if (p[i+1] == 'p') { - unsigned long addr; - char fmt[4]; + head = trace_get_fields(event); + if (!head) { + trace_seq_printf(seq, "FIELDS FOR EVENT '%s' NOT FOUND?\n", + trace_event_name(event)); + return true; + } - fmt[0] = '%'; - fmt[1] = 'p'; - fmt[2] = p[i+2]; /* Either %ps or %pS */ - fmt[3] = '\0'; + /* Offsets are from the iter->ent that points to the raw event */ + ptr = iter->ent; - addr = va_arg(ap, unsigned long); - addr += text_delta; - trace_seq_printf(&iter->seq, fmt, (void *)addr); + list_for_each_entry(field, head, link) { + const char *str; + bool good; - p += i + 3; + if (!field->needs_test) continue; - } - /* - * If iter->seq is full, the above call no longer guarantees - * that ap is in sync with fmt processing, and further calls - * to va_arg() can return wrong positional arguments. - * - * Ensure that ap is no longer used in this case. - */ - if (iter->seq.full) { - p = ""; - break; - } + str = *(const char **)(ptr + field->offset); - if (star) - len = va_arg(ap, int); - - /* The ap now points to the string data of the %s */ - str = va_arg(ap, const char *); - - good = trace_safe_str(iter, str, star, len); - - /* Could be from the last boot */ - if (data_delta && !good) { - str += data_delta; - good = trace_safe_str(iter, str, star, len); - } + good = trace_safe_str(iter, str); /* * If you hit this warning, it is likely that the @@ -3846,44 +3729,14 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, * instead. See samples/trace_events/trace-events-sample.h * for reference. */ - if (WARN_ONCE(!good, "fmt: '%s' current_buffer: '%s'", - fmt, seq_buf_str(&iter->seq.seq))) { - int ret; - - /* Try to safely read the string */ - if (star) { - if (len + 1 > iter->fmt_size) - len = iter->fmt_size - 1; - if (len < 0) - len = 0; - ret = copy_from_kernel_nofault(iter->fmt, str, len); - iter->fmt[len] = 0; - star = false; - } else { - ret = strncpy_from_kernel_nofault(iter->fmt, str, - iter->fmt_size); - } - if (ret < 0) - trace_seq_printf(&iter->seq, "(0x%px)", str); - else - trace_seq_printf(&iter->seq, "(0x%px:%s)", - str, iter->fmt); - str = "[UNSAFE-MEMORY]"; - strcpy(iter->fmt, "%s"); - } else { - strncpy(iter->fmt, p + i, j + 1); - iter->fmt[j+1] = '\0'; + if (WARN_ONCE(!good, "event '%s' has unsafe pointer field '%s'", + trace_event_name(event), field->name)) { + trace_seq_printf(seq, "EVENT %s: HAS UNSAFE POINTER FIELD '%s'\n", + trace_event_name(event), field->name); + return true; } - if (star) - trace_seq_printf(&iter->seq, iter->fmt, len, str); - else - trace_seq_printf(&iter->seq, iter->fmt, str); - - p += i + j + 1; } - print: - if (*p) - trace_seq_vprintf(&iter->seq, p, ap); + return false; } const char *trace_event_format(struct trace_iterator *iter, const char *fmt) @@ -4353,6 +4206,15 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter) if (event) { if (tr->trace_flags & TRACE_ITER_FIELDS) return print_event_fields(iter, event); + /* + * For TRACE_EVENT() events, the print_fmt is not + * safe to use if the array has delta offsets + * Force printing via the fields. + */ + if ((tr->text_delta || tr->data_delta) && + event->type > __TRACE_LAST_TYPE) + return print_event_fields(iter, event); + return event->funcs->trace(iter, sym_flags, event); } @@ -10777,8 +10639,6 @@ __init static int tracer_alloc_buffers(void) register_snapshot_cmd(); - test_can_verify(); - return 0; out_free_pipe_cpumask: diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 266740b4e121..9691b47b5f3d 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -667,9 +667,8 @@ void trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer, bool trace_is_tracepoint_string(const char *str); const char *trace_event_format(struct trace_iterator *iter, const char *fmt); -void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, - va_list ap) __printf(2, 0); char *trace_iter_expand_format(struct trace_iterator *iter); +bool ignore_event(struct trace_iterator *iter); int trace_empty(struct trace_iterator *iter); @@ -1413,7 +1412,8 @@ struct ftrace_event_field { int filter_type; int offset; int size; - int is_signed; + unsigned int is_signed:1; + unsigned int needs_test:1; int len; }; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 77e68efbd43e..1545cc8b49d0 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -82,7 +82,7 @@ static int system_refcount_dec(struct event_subsystem *system) } static struct ftrace_event_field * -__find_event_field(struct list_head *head, char *name) +__find_event_field(struct list_head *head, const char *name) { struct ftrace_event_field *field; @@ -114,7 +114,8 @@ trace_find_event_field(struct trace_event_call *call, char *name) static int __trace_define_field(struct list_head *head, const char *type, const char *name, int offset, int size, - int is_signed, int filter_type, int len) + int is_signed, int filter_type, int len, + int need_test) { struct ftrace_event_field *field; @@ -133,6 +134,7 @@ static int __trace_define_field(struct list_head *head, const char *type, field->offset = offset; field->size = size; field->is_signed = is_signed; + field->needs_test = need_test; field->len = len; list_add(&field->link, head); @@ -151,13 +153,13 @@ int trace_define_field(struct trace_event_call *call, const char *type, head = trace_get_fields(call); return __trace_define_field(head, type, name, offset, size, - is_signed, filter_type, 0); + is_signed, filter_type, 0, 0); } EXPORT_SYMBOL_GPL(trace_define_field); static int trace_define_field_ext(struct trace_event_call *call, const char *type, const char *name, int offset, int size, int is_signed, - int filter_type, int len) + int filter_type, int len, int need_test) { struct list_head *head; @@ -166,13 +168,13 @@ static int trace_define_field_ext(struct trace_event_call *call, const char *typ head = trace_get_fields(call); return __trace_define_field(head, type, name, offset, size, - is_signed, filter_type, len); + is_signed, filter_type, len, need_test); } #define __generic_field(type, item, filter_type) \ ret = __trace_define_field(&ftrace_generic_fields, #type, \ #item, 0, 0, is_signed_type(type), \ - filter_type, 0); \ + filter_type, 0, 0); \ if (ret) \ return ret; @@ -181,7 +183,8 @@ static int trace_define_field_ext(struct trace_event_call *call, const char *typ "common_" #item, \ offsetof(typeof(ent), item), \ sizeof(ent.item), \ - is_signed_type(type), FILTER_OTHER, 0); \ + is_signed_type(type), FILTER_OTHER, \ + 0, 0); \ if (ret) \ return ret; @@ -244,19 +247,16 @@ int trace_event_get_offsets(struct trace_event_call *call) return tail->offset + tail->size; } -/* - * Check if the referenced field is an array and return true, - * as arrays are OK to dereference. - */ -static bool test_field(const char *fmt, struct trace_event_call *call) + +static struct trace_event_fields *find_event_field(const char *fmt, + struct trace_event_call *call) { struct trace_event_fields *field = call->class->fields_array; - const char *array_descriptor; const char *p = fmt; int len; if (!(len = str_has_prefix(fmt, "REC->"))) - return false; + return NULL; fmt += len; for (p = fmt; *p; p++) { if (!isalnum(*p) && *p != '_') @@ -265,16 +265,129 @@ static bool test_field(const char *fmt, struct trace_event_call *call) len = p - fmt; for (; field->type; field++) { - if (strncmp(field->name, fmt, len) || - field->name[len]) + if (strncmp(field->name, fmt, len) || field->name[len]) continue; - array_descriptor = strchr(field->type, '['); - /* This is an array and is OK to dereference. */ - return array_descriptor != NULL; + + return field; + } + return NULL; +} + +/* + * Check if the referenced field is an array and return true, + * as arrays are OK to dereference. + */ +static bool test_field(const char *fmt, struct trace_event_call *call) +{ + struct trace_event_fields *field; + + field = find_event_field(fmt, call); + if (!field) + return false; + + /* This is an array and is OK to dereference. */ + return strchr(field->type, '[') != NULL; +} + +/* Look for a string within an argument */ +static bool find_print_string(const char *arg, const char *str, const char *end) +{ + const char *r; + + r = strstr(arg, str); + return r && r < end; +} + +/* Return true if the argument pointer is safe */ +static bool process_pointer(const char *fmt, int len, struct trace_event_call *call) +{ + const char *r, *e, *a; + + e = fmt + len; + + /* Find the REC-> in the argument */ + r = strstr(fmt, "REC->"); + if (r && r < e) { + /* + * Addresses of events on the buffer, or an array on the buffer is + * OK to dereference. There's ways to fool this, but + * this is to catch common mistakes, not malicious code. + */ + a = strchr(fmt, '&'); + if ((a && (a < r)) || test_field(r, call)) + return true; + } else if (find_print_string(fmt, "__get_dynamic_array(", e)) { + return true; + } else if (find_print_string(fmt, "__get_rel_dynamic_array(", e)) { + return true; + } else if (find_print_string(fmt, "__get_dynamic_array_len(", e)) { + return true; + } else if (find_print_string(fmt, "__get_rel_dynamic_array_len(", e)) { + return true; + } else if (find_print_string(fmt, "__get_sockaddr(", e)) { + return true; + } else if (find_print_string(fmt, "__get_rel_sockaddr(", e)) { + return true; } return false; } +/* Return true if the string is safe */ +static bool process_string(const char *fmt, int len, struct trace_event_call *call) +{ + struct trace_event_fields *field; + const char *r, *e, *s; + + e = fmt + len; + + /* + * There are several helper functions that return strings. + * If the argument contains a function, then assume its field is valid. + * It is considered that the argument has a function if it has: + * alphanumeric or '_' before a parenthesis. + */ + s = fmt; + do { + r = strstr(s, "("); + if (!r || r >= e) + break; + for (int i = 1; r - i >= s; i++) { + char ch = *(r - i); + if (isspace(ch)) + continue; + if (isalnum(ch) || ch == '_') + return true; + /* Anything else, this isn't a function */ + break; + } + /* A function could be wrapped in parethesis, try the next one */ + s = r + 1; + } while (s < e); + + /* + * If there's any strings in the argument consider this arg OK as it + * could be: REC->field ? "foo" : "bar" and we don't want to get into + * verifying that logic here. + */ + if (find_print_string(fmt, "\"", e)) + return true; + + /* Dereferenced strings are also valid like any other pointer */ + if (process_pointer(fmt, len, call)) + return true; + + /* Make sure the field is found */ + field = find_event_field(fmt, call); + if (!field) + return false; + + /* Test this field's string before printing the event */ + call->flags |= TRACE_EVENT_FL_TEST_STR; + field->needs_test = 1; + + return true; +} + /* * Examine the print fmt of the event looking for unsafe dereference * pointers using %p* that could be recorded in the trace event and @@ -284,13 +397,14 @@ static bool test_field(const char *fmt, struct trace_event_call *call) static void test_event_printk(struct trace_event_call *call) { u64 dereference_flags = 0; + u64 string_flags = 0; bool first = true; - const char *fmt, *c, *r, *a; + const char *fmt; int parens = 0; char in_quote = 0; int start_arg = 0; int arg = 0; - int i; + int i, e; fmt = call->print_fmt; @@ -374,8 +488,16 @@ static void test_event_printk(struct trace_event_call *call) star = true; continue; } - if ((fmt[i + j] == 's') && star) - arg++; + if ((fmt[i + j] == 's')) { + if (star) + arg++; + if (WARN_ONCE(arg == 63, + "Too many args for event: %s", + trace_event_name(call))) + return; + dereference_flags |= 1ULL << arg; + string_flags |= 1ULL << arg; + } break; } break; @@ -403,42 +525,47 @@ static void test_event_printk(struct trace_event_call *call) case ',': if (in_quote || parens) continue; + e = i; i++; while (isspace(fmt[i])) i++; - start_arg = i; - if (!(dereference_flags & (1ULL << arg))) - goto next_arg; - /* Find the REC-> in the argument */ - c = strchr(fmt + i, ','); - r = strstr(fmt + i, "REC->"); - if (r && (!c || r < c)) { - /* - * Addresses of events on the buffer, - * or an array on the buffer is - * OK to dereference. - * There's ways to fool this, but - * this is to catch common mistakes, - * not malicious code. - */ - a = strchr(fmt + i, '&'); - if ((a && (a < r)) || test_field(r, call)) + /* + * If start_arg is zero, then this is the start of the + * first argument. The processing of the argument happens + * when the end of the argument is found, as it needs to + * handle paranthesis and such. + */ + if (!start_arg) { + start_arg = i; + /* Balance out the i++ in the for loop */ + i--; + continue; + } + + if (dereference_flags & (1ULL << arg)) { + if (string_flags & (1ULL << arg)) { + if (process_string(fmt + start_arg, e - start_arg, call)) + dereference_flags &= ~(1ULL << arg); + } else if (process_pointer(fmt + start_arg, e - start_arg, call)) dereference_flags &= ~(1ULL << arg); - } else if ((r = strstr(fmt + i, "__get_dynamic_array(")) && - (!c || r < c)) { - dereference_flags &= ~(1ULL << arg); - } else if ((r = strstr(fmt + i, "__get_sockaddr(")) && - (!c || r < c)) { - dereference_flags &= ~(1ULL << arg); } - next_arg: - i--; + start_arg = i; arg++; + /* Balance out the i++ in the for loop */ + i--; } } + if (dereference_flags & (1ULL << arg)) { + if (string_flags & (1ULL << arg)) { + if (process_string(fmt + start_arg, i - start_arg, call)) + dereference_flags &= ~(1ULL << arg); + } else if (process_pointer(fmt + start_arg, i - start_arg, call)) + dereference_flags &= ~(1ULL << arg); + } + /* * If you triggered the below warning, the trace event reported * uses an unsafe dereference pointer %p*. As the data stored @@ -2471,7 +2598,7 @@ event_define_fields(struct trace_event_call *call) ret = trace_define_field_ext(call, field->type, field->name, offset, field->size, field->is_signed, field->filter_type, - field->len); + field->len, field->needs_test); if (WARN_ON_ONCE(ret)) { pr_err("error code is %d\n", ret); break; diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 74c353164ca1..d358c9935164 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -176,7 +176,8 @@ static void function_trace_start(struct trace_array *tr) tracing_reset_online_cpus(&tr->array_buffer); } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER +/* fregs are guaranteed not to be NULL if HAVE_DYNAMIC_FTRACE_WITH_ARGS is set */ +#if defined(CONFIG_FUNCTION_GRAPH_TRACER) && defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) static __always_inline unsigned long function_get_true_parent_ip(unsigned long parent_ip, struct ftrace_regs *fregs) { diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index da748b7cbc4d..03d56f711ad1 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -317,10 +317,14 @@ EXPORT_SYMBOL(trace_raw_output_prep); void trace_event_printf(struct trace_iterator *iter, const char *fmt, ...) { + struct trace_seq *s = &iter->seq; va_list ap; + if (ignore_event(iter)) + return; + va_start(ap, fmt); - trace_check_vprintf(iter, trace_event_format(iter, fmt), ap); + trace_seq_vprintf(s, trace_event_format(iter, fmt), ap); va_end(ap); } EXPORT_SYMBOL(trace_event_printf); diff --git a/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/netdev-genl.c b/net/core/netdev-genl.c index 9527dd46e4dc..2d3ae0cd3ad2 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -430,10 +430,10 @@ static int netdev_nl_queue_fill(struct sk_buff *rsp, struct net_device *netdev, u32 q_idx, u32 q_type, const struct genl_info *info) { - int err = 0; + int err; if (!(netdev->flags & IFF_UP)) - return err; + return -ENOENT; err = netdev_nl_queue_validate(netdev, q_idx, q_type); if (err) @@ -488,24 +488,21 @@ netdev_nl_queue_dump_one(struct net_device *netdev, struct sk_buff *rsp, struct netdev_nl_dump_ctx *ctx) { int err = 0; - int i; if (!(netdev->flags & IFF_UP)) return err; - for (i = ctx->rxq_idx; i < netdev->real_num_rx_queues;) { - err = netdev_nl_queue_fill_one(rsp, netdev, i, + for (; ctx->rxq_idx < netdev->real_num_rx_queues; ctx->rxq_idx++) { + err = netdev_nl_queue_fill_one(rsp, netdev, ctx->rxq_idx, NETDEV_QUEUE_TYPE_RX, info); if (err) return err; - ctx->rxq_idx = i++; } - for (i = ctx->txq_idx; i < netdev->real_num_tx_queues;) { - err = netdev_nl_queue_fill_one(rsp, netdev, i, + for (; ctx->txq_idx < netdev->real_num_tx_queues; ctx->txq_idx++) { + err = netdev_nl_queue_fill_one(rsp, netdev, ctx->txq_idx, NETDEV_QUEUE_TYPE_TX, info); if (err) return err; - ctx->txq_idx = i++; } return err; @@ -671,7 +668,7 @@ netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp, i, info); if (err) return err; - ctx->rxq_idx = i++; + ctx->rxq_idx = ++i; } i = ctx->txq_idx; while (ops->get_queue_stats_tx && i < netdev->real_num_tx_queues) { @@ -679,7 +676,7 @@ netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp, i, info); if (err) return err; - ctx->txq_idx = i++; + ctx->txq_idx = ++i; } ctx->rxq_idx = 0; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index ebcfc2debf1a..d9f959c619d9 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3819,6 +3819,7 @@ out_unregister: } static struct net *rtnl_get_peer_net(const struct rtnl_link_ops *ops, + struct nlattr *tbp[], struct nlattr *data[], struct netlink_ext_ack *extack) { @@ -3826,7 +3827,7 @@ static struct net *rtnl_get_peer_net(const struct rtnl_link_ops *ops, int err; if (!data || !data[ops->peer_type]) - return NULL; + return rtnl_link_get_net_ifla(tbp); err = rtnl_nla_parse_ifinfomsg(tb, data[ops->peer_type], extack); if (err < 0) @@ -3971,7 +3972,7 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, } if (ops->peer_type) { - peer_net = rtnl_get_peer_net(ops, data, extack); + peer_net = rtnl_get_peer_net(ops, tb, data, extack); if (IS_ERR(peer_net)) { ret = PTR_ERR(peer_net); goto put_ops; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index e90fbab703b2..61f3f3d4e528 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -369,8 +369,8 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes) { int ret = -ENOSPC, i = msg->sg.curr; + u32 copy, buf_size, copied = 0; struct scatterlist *sge; - u32 copy, buf_size; void *to; do { @@ -397,6 +397,7 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, goto out; } bytes -= copy; + copied += copy; if (!bytes) break; msg->sg.copybreak = 0; @@ -404,7 +405,7 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, } while (i != msg->sg.end); out: msg->sg.curr = i; - return ret; + return (ret < 0) ? ret : copied; } EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter); @@ -445,8 +446,10 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, if (likely(!peek)) { sge->offset += copy; sge->length -= copy; - if (!msg_rx->skb) + if (!msg_rx->skb) { sk_mem_uncharge(sk, copy); + atomic_sub(copy, &sk->sk_rmem_alloc); + } msg_rx->sg.size -= copy; if (!sge->length) { @@ -772,6 +775,8 @@ static void __sk_psock_purge_ingress_msg(struct sk_psock *psock) list_for_each_entry_safe(msg, tmp, &psock->ingress_msg, list) { list_del(&msg->list); + if (!msg->skb) + atomic_sub(msg->sg.size, &psock->sk->sk_rmem_alloc); sk_msg_free(psock->sk, msg); kfree(msg); } diff --git a/net/dsa/tag.h b/net/dsa/tag.h index d5707870906b..5d80ddad4ff6 100644 --- a/net/dsa/tag.h +++ b/net/dsa/tag.h @@ -138,9 +138,10 @@ static inline void dsa_software_untag_vlan_unaware_bridge(struct sk_buff *skb, * dsa_software_vlan_untag: Software VLAN untagging in DSA receive path * @skb: Pointer to socket buffer (packet) * - * Receive path method for switches which cannot avoid tagging all packets - * towards the CPU port. Called when ds->untag_bridge_pvid (legacy) or - * ds->untag_vlan_aware_bridge_pvid is set to true. + * Receive path method for switches which send some packets as VLAN-tagged + * towards the CPU port (generally from VLAN-aware bridge ports) even when the + * packet was not tagged on the wire. Called when ds->untag_bridge_pvid + * (legacy) or ds->untag_vlan_aware_bridge_pvid is set to true. * * As a side effect of this method, any VLAN tag from the skb head is moved * to hwaccel. @@ -149,14 +150,19 @@ static inline struct sk_buff *dsa_software_vlan_untag(struct sk_buff *skb) { struct dsa_port *dp = dsa_user_to_port(skb->dev); struct net_device *br = dsa_port_bridge_dev_get(dp); - u16 vid; + u16 vid, proto; + int err; /* software untagging for standalone ports not yet necessary */ if (!br) return skb; + err = br_vlan_get_proto(br, &proto); + if (err) + return skb; + /* Move VLAN tag from data to hwaccel */ - if (!skb_vlan_tag_present(skb)) { + if (!skb_vlan_tag_present(skb) && skb->protocol == htons(proto)) { skb = skb_vlan_untag(skb); if (!skb) return NULL; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 99cef92e6290..47f65b1b70ca 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -49,13 +49,14 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, sge = sk_msg_elem(msg, i); size = (apply && apply_bytes < sge->length) ? apply_bytes : sge->length; - if (!sk_wmem_schedule(sk, size)) { + if (!__sk_rmem_schedule(sk, size, false)) { if (!copied) ret = -ENOMEM; break; } sk_mem_charge(sk, size); + atomic_add(size, &sk->sk_rmem_alloc); sk_msg_xfer(tmp, msg, i, size); copied += size; if (sge->length) @@ -74,7 +75,8 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, if (!ret) { msg->sg.start = i; - sk_psock_queue_msg(psock, tmp); + if (!sk_psock_queue_msg(psock, tmp)) + atomic_sub(copied, &sk->sk_rmem_alloc); sk_psock_data_ready(sk, psock); } else { sk_msg_free(sk, tmp); @@ -493,7 +495,7 @@ more_data: static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { struct sk_msg tmp, *msg_tx = NULL; - int copied = 0, err = 0; + int copied = 0, err = 0, ret = 0; struct sk_psock *psock; long timeo; int flags; @@ -536,14 +538,14 @@ static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) copy = msg_tx->sg.size - osize; } - err = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, msg_tx, + ret = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, msg_tx, copy); - if (err < 0) { + if (ret < 0) { sk_msg_trim(sk, msg_tx, osize); goto out_err; } - copied += copy; + copied += ret; if (psock->cork_bytes) { if (size > psock->cork_bytes) psock->cork_bytes = 0; diff --git a/net/mctp/route.c b/net/mctp/route.c index 597e9cf5aa64..3f2bd65ff5e3 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -374,8 +374,13 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) msk = NULL; rc = -EINVAL; - /* we may be receiving a locally-routed packet; drop source sk - * accounting + /* We may be receiving a locally-routed packet; drop source sk + * accounting. + * + * From here, we will either queue the skb - either to a frag_queue, or + * to a receiving socket. When that succeeds, we clear the skb pointer; + * a non-NULL skb on exit will be otherwise unowned, and hence + * kfree_skb()-ed. */ skb_orphan(skb); @@ -434,7 +439,9 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) * pending key. */ if (flags & MCTP_HDR_FLAG_EOM) { - sock_queue_rcv_skb(&msk->sk, skb); + rc = sock_queue_rcv_skb(&msk->sk, skb); + if (!rc) + skb = NULL; if (key) { /* we've hit a pending reassembly; not much we * can do but drop it @@ -443,7 +450,6 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) MCTP_TRACE_KEY_REPLIED); key = NULL; } - rc = 0; goto out_unlock; } @@ -470,8 +476,10 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) * this function. */ rc = mctp_key_add(key, msk); - if (!rc) + if (!rc) { trace_mctp_key_acquire(key); + skb = NULL; + } /* we don't need to release key->lock on exit, so * clean up here and suppress the unlock via @@ -489,6 +497,8 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) key = NULL; } else { rc = mctp_frag_queue(key, skb); + if (!rc) + skb = NULL; } } @@ -503,12 +513,19 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) else rc = mctp_frag_queue(key, skb); + if (rc) + goto out_unlock; + + /* we've queued; the queue owns the skb now */ + skb = NULL; + /* end of message? deliver to socket, and we're done with * the reassembly/response key */ - if (!rc && flags & MCTP_HDR_FLAG_EOM) { - sock_queue_rcv_skb(key->sk, key->reasm_head); - key->reasm_head = NULL; + if (flags & MCTP_HDR_FLAG_EOM) { + rc = sock_queue_rcv_skb(key->sk, key->reasm_head); + if (!rc) + key->reasm_head = NULL; __mctp_key_done_in(key, net, f, MCTP_TRACE_KEY_REPLIED); key = NULL; } @@ -527,8 +544,7 @@ out_unlock: if (any_key) mctp_key_unref(any_key); out: - if (rc) - kfree_skb(skb); + kfree_skb(skb); return rc; } diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c index 8551dab1d1e6..17165b86ce22 100644 --- a/net/mctp/test/route-test.c +++ b/net/mctp/test/route-test.c @@ -837,6 +837,90 @@ static void mctp_test_route_input_multiple_nets_key(struct kunit *test) mctp_test_route_input_multiple_nets_key_fini(test, &t2); } +/* Input route to socket, using a single-packet message, where sock delivery + * fails. Ensure we're handling the failure appropriately. + */ +static void mctp_test_route_input_sk_fail_single(struct kunit *test) +{ + const struct mctp_hdr hdr = RX_HDR(1, 10, 8, FL_S | FL_E | FL_TO); + struct mctp_test_route *rt; + struct mctp_test_dev *dev; + struct socket *sock; + struct sk_buff *skb; + int rc; + + __mctp_route_test_init(test, &dev, &rt, &sock, MCTP_NET_ANY); + + /* No rcvbuf space, so delivery should fail. __sock_set_rcvbuf will + * clamp the minimum to SOCK_MIN_RCVBUF, so we open-code this. + */ + lock_sock(sock->sk); + WRITE_ONCE(sock->sk->sk_rcvbuf, 0); + release_sock(sock->sk); + + skb = mctp_test_create_skb(&hdr, 10); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb); + skb_get(skb); + + mctp_test_skb_set_dev(skb, dev); + + /* do route input, which should fail */ + rc = mctp_route_input(&rt->rt, skb); + KUNIT_EXPECT_NE(test, rc, 0); + + /* we should hold the only reference to skb */ + KUNIT_EXPECT_EQ(test, refcount_read(&skb->users), 1); + kfree_skb(skb); + + __mctp_route_test_fini(test, dev, rt, sock); +} + +/* Input route to socket, using a fragmented message, where sock delivery fails. + */ +static void mctp_test_route_input_sk_fail_frag(struct kunit *test) +{ + const struct mctp_hdr hdrs[2] = { RX_FRAG(FL_S, 0), RX_FRAG(FL_E, 1) }; + struct mctp_test_route *rt; + struct mctp_test_dev *dev; + struct sk_buff *skbs[2]; + struct socket *sock; + unsigned int i; + int rc; + + __mctp_route_test_init(test, &dev, &rt, &sock, MCTP_NET_ANY); + + lock_sock(sock->sk); + WRITE_ONCE(sock->sk->sk_rcvbuf, 0); + release_sock(sock->sk); + + for (i = 0; i < ARRAY_SIZE(skbs); i++) { + skbs[i] = mctp_test_create_skb(&hdrs[i], 10); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skbs[i]); + skb_get(skbs[i]); + + mctp_test_skb_set_dev(skbs[i], dev); + } + + /* first route input should succeed, we're only queueing to the + * frag list + */ + rc = mctp_route_input(&rt->rt, skbs[0]); + KUNIT_EXPECT_EQ(test, rc, 0); + + /* final route input should fail to deliver to the socket */ + rc = mctp_route_input(&rt->rt, skbs[1]); + KUNIT_EXPECT_NE(test, rc, 0); + + /* we should hold the only reference to both skbs */ + KUNIT_EXPECT_EQ(test, refcount_read(&skbs[0]->users), 1); + kfree_skb(skbs[0]); + + KUNIT_EXPECT_EQ(test, refcount_read(&skbs[1]->users), 1); + kfree_skb(skbs[1]); + + __mctp_route_test_fini(test, dev, rt, sock); +} + #if IS_ENABLED(CONFIG_MCTP_FLOWS) static void mctp_test_flow_init(struct kunit *test, @@ -1053,6 +1137,8 @@ static struct kunit_case mctp_test_cases[] = { mctp_route_input_sk_reasm_gen_params), KUNIT_CASE_PARAM(mctp_test_route_input_sk_keys, mctp_route_input_sk_keys_gen_params), + KUNIT_CASE(mctp_test_route_input_sk_fail_single), + KUNIT_CASE(mctp_test_route_input_sk_fail_frag), KUNIT_CASE(mctp_test_route_input_multiple_nets_bind), KUNIT_CASE(mctp_test_route_input_multiple_nets_key), KUNIT_CASE(mctp_test_packet_flow), diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index bfae7066936b..db794fe1300e 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -611,6 +611,8 @@ init_list_set(struct net *net, struct ip_set *set, u32 size) return true; } +static struct lock_class_key list_set_lockdep_key; + static int list_set_create(struct net *net, struct ip_set *set, struct nlattr *tb[], u32 flags) @@ -627,6 +629,7 @@ list_set_create(struct net *net, struct ip_set *set, struct nlattr *tb[], if (size < IP_SET_LIST_MIN_SIZE) size = IP_SET_LIST_MIN_SIZE; + lockdep_set_class(&set->lock, &list_set_lockdep_key); set->variant = &set_variant; set->dsize = ip_set_elem_len(set, tb, sizeof(struct set_elem), __alignof__(struct set_elem)); diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 98d7dbe3d787..c0289f83f96d 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1495,8 +1495,8 @@ int __init ip_vs_conn_init(void) max_avail -= 2; /* ~4 in hash row */ max_avail -= 1; /* IPVS up to 1/2 of mem */ max_avail -= order_base_2(sizeof(struct ip_vs_conn)); - max = clamp(max, min, max_avail); - ip_vs_conn_tab_bits = clamp_val(ip_vs_conn_tab_bits, min, max); + max = clamp(max_avail, min, max); + ip_vs_conn_tab_bits = clamp(ip_vs_conn_tab_bits, min, max); ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits; ip_vs_conn_tab_mask = ip_vs_conn_tab_size - 1; diff --git a/net/psample/psample.c b/net/psample/psample.c index a0ddae8a65f9..25f92ba0840c 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -393,7 +393,9 @@ void psample_sample_packet(struct psample_group *group, nla_total_size_64bit(sizeof(u64)) + /* timestamp */ nla_total_size(sizeof(u16)) + /* protocol */ (md->user_cookie_len ? - nla_total_size(md->user_cookie_len) : 0); /* user cookie */ + nla_total_size(md->user_cookie_len) : 0) + /* user cookie */ + (md->rate_as_probability ? + nla_total_size(0) : 0); /* rate as probability */ #ifdef CONFIG_INET tun_info = skb_tunnel_info(skb); @@ -498,8 +500,9 @@ void psample_sample_packet(struct psample_group *group, md->user_cookie)) goto error; - if (md->rate_as_probability) - nla_put_flag(nl_skb, PSAMPLE_ATTR_SAMPLE_PROBABILITY); + if (md->rate_as_probability && + nla_put_flag(nl_skb, PSAMPLE_ATTR_SAMPLE_PROBABILITY)) + goto error; genlmsg_end(nl_skb, data); genlmsg_multicast_netns(&psample_nl_family, group->net, nl_skb, 0, diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 9e6c69d18581..6cc7b846cff1 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2032,6 +2032,8 @@ static int smc_listen_prfx_check(struct smc_sock *new_smc, if (pclc->hdr.typev1 == SMC_TYPE_N) return 0; pclc_prfx = smc_clc_proposal_get_prefix(pclc); + if (!pclc_prfx) + return -EPROTO; if (smc_clc_prfx_match(newclcsock, pclc_prfx)) return SMC_CLC_DECL_DIFFPREFIX; @@ -2145,6 +2147,8 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, pclc_smcd = smc_get_clc_msg_smcd(pclc); smc_v2_ext = smc_get_clc_v2_ext(pclc); smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext); + if (!pclc_smcd || !smc_v2_ext || !smcd_v2_ext) + goto not_found; mutex_lock(&smcd_dev_list.mutex); if (pclc_smcd->ism.chid) { @@ -2221,7 +2225,9 @@ static void smc_find_ism_v1_device_serv(struct smc_sock *new_smc, int rc = 0; /* check if ISM V1 is available */ - if (!(ini->smcd_version & SMC_V1) || !smcd_indicated(ini->smc_type_v1)) + if (!(ini->smcd_version & SMC_V1) || + !smcd_indicated(ini->smc_type_v1) || + !pclc_smcd) goto not_found; ini->is_smcd = true; /* prepare ISM check */ ini->ism_peer_gid[0].gid = ntohll(pclc_smcd->ism.gid); @@ -2272,7 +2278,8 @@ static void smc_find_rdma_v2_device_serv(struct smc_sock *new_smc, goto not_found; smc_v2_ext = smc_get_clc_v2_ext(pclc); - if (!smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, NULL, NULL)) + if (!smc_v2_ext || + !smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, NULL, NULL)) goto not_found; /* prepare RDMA check */ @@ -2881,6 +2888,13 @@ __poll_t smc_poll(struct file *file, struct socket *sock, } else { sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + + if (sk->sk_state != SMC_INIT) { + /* Race breaker the same way as tcp_poll(). */ + smp_mb__after_atomic(); + if (atomic_read(&smc->conn.sndbuf_space)) + mask |= EPOLLOUT | EPOLLWRNORM; + } } if (atomic_read(&smc->conn.bytes_to_rcv)) mask |= EPOLLIN | EPOLLRDNORM; diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 33fa787c28eb..521f5df80e10 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -352,8 +352,11 @@ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc) struct smc_clc_msg_hdr *hdr = &pclc->hdr; struct smc_clc_v2_extension *v2_ext; - v2_ext = smc_get_clc_v2_ext(pclc); pclc_prfx = smc_clc_proposal_get_prefix(pclc); + if (!pclc_prfx || + pclc_prfx->ipv6_prefixes_cnt > SMC_CLC_MAX_V6_PREFIX) + return false; + if (hdr->version == SMC_V1) { if (hdr->typev1 == SMC_TYPE_N) return false; @@ -365,6 +368,13 @@ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc) sizeof(struct smc_clc_msg_trail)) return false; } else { + v2_ext = smc_get_clc_v2_ext(pclc); + if ((hdr->typev2 != SMC_TYPE_N && + (!v2_ext || v2_ext->hdr.eid_cnt > SMC_CLC_MAX_UEID)) || + (smcd_indicated(hdr->typev2) && + v2_ext->hdr.ism_gid_cnt > SMCD_CLC_MAX_V2_GID_ENTRIES)) + return false; + if (ntohs(hdr->length) != sizeof(*pclc) + sizeof(struct smc_clc_msg_smcd) + @@ -764,6 +774,11 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, SMC_CLC_RECV_BUF_LEN : datlen; iov_iter_kvec(&msg.msg_iter, ITER_DEST, &vec, 1, recvlen); len = sock_recvmsg(smc->clcsock, &msg, krflags); + if (len < recvlen) { + smc->sk.sk_err = EPROTO; + reason_code = -EPROTO; + goto out; + } datlen -= len; } if (clcm->type == SMC_CLC_DECLINE) { diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 5fd6f5b8ef03..767289925410 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -336,8 +336,12 @@ struct smc_clc_msg_decline_v2 { /* clc decline message */ static inline struct smc_clc_msg_proposal_prefix * smc_clc_proposal_get_prefix(struct smc_clc_msg_proposal *pclc) { + u16 offset = ntohs(pclc->iparea_offset); + + if (offset > sizeof(struct smc_clc_msg_smcd)) + return NULL; return (struct smc_clc_msg_proposal_prefix *) - ((u8 *)pclc + sizeof(*pclc) + ntohs(pclc->iparea_offset)); + ((u8 *)pclc + sizeof(*pclc) + offset); } static inline bool smcr_indicated(int smc_type) @@ -376,8 +380,14 @@ static inline struct smc_clc_v2_extension * smc_get_clc_v2_ext(struct smc_clc_msg_proposal *prop) { struct smc_clc_msg_smcd *prop_smcd = smc_get_clc_msg_smcd(prop); + u16 max_offset; - if (!prop_smcd || !ntohs(prop_smcd->v2_ext_offset)) + max_offset = offsetof(struct smc_clc_msg_proposal_area, pclc_v2_ext) - + offsetof(struct smc_clc_msg_proposal_area, pclc_smcd) - + offsetofend(struct smc_clc_msg_smcd, v2_ext_offset); + + if (!prop_smcd || !ntohs(prop_smcd->v2_ext_offset) || + ntohs(prop_smcd->v2_ext_offset) > max_offset) return NULL; return (struct smc_clc_v2_extension *) @@ -390,9 +400,15 @@ smc_get_clc_v2_ext(struct smc_clc_msg_proposal *prop) static inline struct smc_clc_smcd_v2_extension * smc_get_clc_smcd_v2_ext(struct smc_clc_v2_extension *prop_v2ext) { + u16 max_offset = offsetof(struct smc_clc_msg_proposal_area, pclc_smcd_v2_ext) - + offsetof(struct smc_clc_msg_proposal_area, pclc_v2_ext) - + offsetof(struct smc_clc_v2_extension, hdr) - + offsetofend(struct smc_clnt_opts_area_hdr, smcd_v2_ext_offset); + if (!prop_v2ext) return NULL; - if (!ntohs(prop_v2ext->hdr.smcd_v2_ext_offset)) + if (!ntohs(prop_v2ext->hdr.smcd_v2_ext_offset) || + ntohs(prop_v2ext->hdr.smcd_v2_ext_offset) > max_offset) return NULL; return (struct smc_clc_smcd_v2_extension *) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 500952c2e67b..3b125d348b4a 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1818,7 +1818,9 @@ void smcr_link_down_cond_sched(struct smc_link *lnk) { if (smc_link_downing(&lnk->state)) { trace_smcr_link_down(lnk, __builtin_return_address(0)); - schedule_work(&lnk->link_down_wrk); + smcr_link_hold(lnk); /* smcr_link_put in link_down_wrk */ + if (!schedule_work(&lnk->link_down_wrk)) + smcr_link_put(lnk); } } @@ -1850,11 +1852,14 @@ static void smc_link_down_work(struct work_struct *work) struct smc_link_group *lgr = link->lgr; if (list_empty(&lgr->list)) - return; + goto out; wake_up_all(&lgr->llc_msg_waiter); down_write(&lgr->llc_conf_mutex); smcr_link_down(link); up_write(&lgr->llc_conf_mutex); + +out: + smcr_link_put(link); /* smcr_link_hold by schedulers of link_down_work */ } static int smc_vlan_by_tcpsk_walk(struct net_device *lower_dev, diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs index b89c681d97c0..2fbfb6a94c11 100644 --- a/rust/kernel/net/phy.rs +++ b/rust/kernel/net/phy.rs @@ -860,7 +860,7 @@ impl DeviceMask { /// ]; /// #[cfg(MODULE)] /// #[no_mangle] -/// static __mod_mdio__phydev_device_table: [::kernel::bindings::mdio_device_id; 2] = _DEVICE_TABLE; +/// static __mod_device_table__mdio__phydev: [::kernel::bindings::mdio_device_id; 2] = _DEVICE_TABLE; /// ``` #[macro_export] macro_rules! module_phy_driver { @@ -883,7 +883,7 @@ macro_rules! module_phy_driver { #[cfg(MODULE)] #[no_mangle] - static __mod_mdio__phydev_device_table: [$crate::bindings::mdio_device_id; + static __mod_device_table__mdio__phydev: [$crate::bindings::mdio_device_id; $crate::module_phy_driver!(@count_devices $($dev),+) + 1] = _DEVICE_TABLE; }; diff --git a/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/security/selinux/ss/services.c b/security/selinux/ss/services.c index 971c45d576ba..3d5c563cfc4c 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -979,7 +979,10 @@ void services_compute_xperms_decision(struct extended_perms_decision *xpermd, return; break; default: - BUG(); + pr_warn_once( + "SELinux: unknown extended permission (%u) will be ignored\n", + node->datum.u.xperms->specified); + return; } if (node->key.specified == AVTAB_XPERMS_ALLOWED) { @@ -998,7 +1001,8 @@ void services_compute_xperms_decision(struct extended_perms_decision *xpermd, &node->datum.u.xperms->perms, xpermd->dontaudit); } else { - BUG(); + pr_warn_once("SELinux: unknown specified key (%u)\n", + node->key.specified); } } diff --git a/sound/soc/fsl/Kconfig b/sound/soc/fsl/Kconfig index 8e88830e8e57..678540b78280 100644 --- a/sound/soc/fsl/Kconfig +++ b/sound/soc/fsl/Kconfig @@ -29,8 +29,8 @@ config SND_SOC_FSL_SAI config SND_SOC_FSL_MQS tristate "Medium Quality Sound (MQS) module support" depends on SND_SOC_FSL_SAI + depends on IMX_SCMI_MISC_DRV || !IMX_SCMI_MISC_DRV select REGMAP_MMIO - select IMX_SCMI_MISC_DRV if IMX_SCMI_MISC_EXT !=n help Say Y if you want to add Medium Quality Sound (MQS) support for the Freescale CPUs. diff --git a/tools/hv/.gitignore b/tools/hv/.gitignore new file mode 100644 index 000000000000..0c5bc15d602f --- /dev/null +++ b/tools/hv/.gitignore @@ -0,0 +1,3 @@ +hv_fcopy_uio_daemon +hv_kvp_daemon +hv_vss_daemon diff --git a/tools/hv/hv_fcopy_uio_daemon.c b/tools/hv/hv_fcopy_uio_daemon.c index 7a00f3066a98..0198321d14a2 100644 --- a/tools/hv/hv_fcopy_uio_daemon.c +++ b/tools/hv/hv_fcopy_uio_daemon.c @@ -35,8 +35,6 @@ #define WIN8_SRV_MINOR 1 #define WIN8_SRV_VERSION (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR) -#define MAX_FOLDER_NAME 15 -#define MAX_PATH_LEN 15 #define FCOPY_UIO "/sys/bus/vmbus/devices/eb765408-105f-49b6-b4aa-c123b64d17d4/uio" #define FCOPY_VER_COUNT 1 @@ -51,7 +49,7 @@ static const int fw_versions[] = { #define HV_RING_SIZE 0x4000 /* 16KB ring buffer size */ -unsigned char desc[HV_RING_SIZE]; +static unsigned char desc[HV_RING_SIZE]; static int target_fd; static char target_fname[PATH_MAX]; @@ -409,8 +407,8 @@ int main(int argc, char *argv[]) struct vmbus_br txbr, rxbr; void *ring; uint32_t len = HV_RING_SIZE; - char uio_name[MAX_FOLDER_NAME] = {0}; - char uio_dev_path[MAX_PATH_LEN] = {0}; + char uio_name[NAME_MAX] = {0}; + char uio_dev_path[PATH_MAX] = {0}; static struct option long_options[] = { {"help", no_argument, 0, 'h' }, @@ -468,8 +466,10 @@ int main(int argc, char *argv[]) */ ret = pread(fcopy_fd, &tmp, sizeof(int), 0); if (ret < 0) { + if (errno == EINTR || errno == EAGAIN) + continue; syslog(LOG_ERR, "pread failed: %s", strerror(errno)); - continue; + goto close; } len = HV_RING_SIZE; diff --git a/tools/hv/hv_get_dns_info.sh b/tools/hv/hv_get_dns_info.sh index 058c17b46ffc..268521234d4b 100755 --- a/tools/hv/hv_get_dns_info.sh +++ b/tools/hv/hv_get_dns_info.sh @@ -1,4 +1,4 @@ -#!/bin/bash +#!/bin/sh # This example script parses /etc/resolv.conf to retrive DNS information. # In the interest of keeping the KVP daemon code free of distro specific @@ -10,4 +10,4 @@ # this script can be based on the Network Manager APIs for retrieving DNS # entries. -cat /etc/resolv.conf 2>/dev/null | awk '/^nameserver/ { print $2 }' +exec awk '/^nameserver/ { print $2 }' /etc/resolv.conf 2>/dev/null diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index ae57bf69ad4a..04ba035d67e9 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -725,7 +725,7 @@ static void kvp_get_ipconfig_info(char *if_name, * . */ - sprintf(cmd, KVP_SCRIPTS_PATH "%s", "hv_get_dns_info"); + sprintf(cmd, "exec %s %s", KVP_SCRIPTS_PATH "hv_get_dns_info", if_name); /* * Execute the command to gather DNS info. @@ -742,7 +742,7 @@ static void kvp_get_ipconfig_info(char *if_name, * Enabled: DHCP enabled. */ - sprintf(cmd, KVP_SCRIPTS_PATH "%s %s", "hv_get_dhcp_info", if_name); + sprintf(cmd, "exec %s %s", KVP_SCRIPTS_PATH "hv_get_dhcp_info", if_name); file = popen(cmd, "r"); if (file == NULL) @@ -1606,8 +1606,9 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) * invoke the external script to do its magic. */ - str_len = snprintf(cmd, sizeof(cmd), KVP_SCRIPTS_PATH "%s %s %s", - "hv_set_ifconfig", if_filename, nm_filename); + str_len = snprintf(cmd, sizeof(cmd), "exec %s %s %s", + KVP_SCRIPTS_PATH "hv_set_ifconfig", + if_filename, nm_filename); /* * This is a little overcautious, but it's necessary to suppress some * false warnings from gcc 8.0.1. diff --git a/tools/hv/hv_set_ifconfig.sh b/tools/hv/hv_set_ifconfig.sh index 440a91b35823..2f8baed2b8f7 100755 --- a/tools/hv/hv_set_ifconfig.sh +++ b/tools/hv/hv_set_ifconfig.sh @@ -81,7 +81,7 @@ echo "ONBOOT=yes" >> $1 cp $1 /etc/sysconfig/network-scripts/ -chmod 600 $2 +umask 0177 interface=$(echo $2 | awk -F - '{ print $2 }') filename="${2##*/}" diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index 01ec01a90e76..eea29359a899 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -556,10 +556,10 @@ class YnlFamily(SpecFamily): if attr["type"] == 'nest': nl_type |= Netlink.NLA_F_NESTED attr_payload = b'' - sub_attrs = SpaceAttrs(self.attr_sets[space], value, search_attrs) + sub_space = attr['nested-attributes'] + sub_attrs = SpaceAttrs(self.attr_sets[sub_space], value, search_attrs) for subname, subvalue in value.items(): - attr_payload += self._add_attr(attr['nested-attributes'], - subname, subvalue, sub_attrs) + attr_payload += self._add_attr(sub_space, subname, subvalue, sub_attrs) elif attr["type"] == 'flag': if not value: # If value is absent or false then skip attribute creation. diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 4ce176ad411f..76060da755b5 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -3820,9 +3820,12 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, break; case INSN_CONTEXT_SWITCH: - if (func && (!next_insn || !next_insn->hint)) { - WARN_INSN(insn, "unsupported instruction in callable function"); - return 1; + if (func) { + if (!next_insn || !next_insn->hint) { + WARN_INSN(insn, "unsupported instruction in callable function"); + return 1; + } + break; } return 0; diff --git a/tools/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/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py index 30f29096e27c..9c5473abbd78 100755 --- a/tools/testing/selftests/drivers/net/queues.py +++ b/tools/testing/selftests/drivers/net/queues.py @@ -8,25 +8,28 @@ from lib.py import cmd import glob -def sys_get_queues(ifname) -> int: - folders = glob.glob(f'/sys/class/net/{ifname}/queues/rx-*') +def sys_get_queues(ifname, qtype='rx') -> int: + folders = glob.glob(f'/sys/class/net/{ifname}/queues/{qtype}-*') return len(folders) -def nl_get_queues(cfg, nl): +def nl_get_queues(cfg, nl, qtype='rx'): queues = nl.queue_get({'ifindex': cfg.ifindex}, dump=True) if queues: - return len([q for q in queues if q['type'] == 'rx']) + return len([q for q in queues if q['type'] == qtype]) return None def get_queues(cfg, nl) -> None: - queues = nl_get_queues(cfg, nl) - if not queues: - raise KsftSkipEx('queue-get not supported by device') + snl = NetdevFamily(recv_size=4096) - expected = sys_get_queues(cfg.dev['ifname']) - ksft_eq(queues, expected) + for qtype in ['rx', 'tx']: + queues = nl_get_queues(cfg, snl, qtype) + if not queues: + raise KsftSkipEx('queue-get not supported by device') + + expected = sys_get_queues(cfg.dev['ifname'], qtype) + ksft_eq(queues, expected) def addremove_queues(cfg, nl) -> None: @@ -57,7 +60,7 @@ def addremove_queues(cfg, nl) -> None: def main() -> None: - with NetDrvEnv(__file__, queue_count=3) as cfg: + with NetDrvEnv(__file__, queue_count=100) as cfg: ksft_run([get_queues, addremove_queues], args=(cfg, NetdevFamily())) ksft_exit() diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py index 63e3c045a3b2..031ac9def6c0 100755 --- a/tools/testing/selftests/drivers/net/stats.py +++ b/tools/testing/selftests/drivers/net/stats.py @@ -110,6 +110,23 @@ def qstat_by_ifindex(cfg) -> None: ksft_ge(triple[1][key], triple[0][key], comment="bad key: " + key) ksft_ge(triple[2][key], triple[1][key], comment="bad key: " + key) + # Sanity check the dumps + queues = NetdevFamily(recv_size=4096).qstats_get({"scope": "queue"}, dump=True) + # Reformat the output into {ifindex: {rx: [id, id, ...], tx: [id, id, ...]}} + parsed = {} + for entry in queues: + ifindex = entry["ifindex"] + if ifindex not in parsed: + parsed[ifindex] = {"rx":[], "tx": []} + parsed[ifindex][entry["queue-type"]].append(entry['queue-id']) + # Now, validate + for ifindex, queues in parsed.items(): + for qtype in ['rx', 'tx']: + ksft_eq(len(queues[qtype]), len(set(queues[qtype])), + comment="repeated queue keys") + ksft_eq(len(queues[qtype]), max(queues[qtype]) + 1, + comment="missing queue keys") + # Test invalid dumps # 0 is invalid with ksft_raises(NlError) as cm: @@ -158,7 +175,7 @@ def check_down(cfg) -> None: def main() -> None: - with NetDrvEnv(__file__) as cfg: + with NetDrvEnv(__file__, queue_count=100) as cfg: ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex, check_down], args=(cfg, )) diff --git a/tools/testing/selftests/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/testing/selftests/net/lib/py/ynl.py b/tools/testing/selftests/net/lib/py/ynl.py index a0d689d58c57..076a7e8dc3eb 100644 --- a/tools/testing/selftests/net/lib/py/ynl.py +++ b/tools/testing/selftests/net/lib/py/ynl.py @@ -32,23 +32,23 @@ except ModuleNotFoundError as e: # Set schema='' to avoid jsonschema validation, it's slow # class EthtoolFamily(YnlFamily): - def __init__(self): + def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('ethtool.yaml')).as_posix(), - schema='') + schema='', recv_size=recv_size) class RtnlFamily(YnlFamily): - def __init__(self): + def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('rt_link.yaml')).as_posix(), - schema='') + schema='', recv_size=recv_size) class NetdevFamily(YnlFamily): - def __init__(self): + def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('netdev.yaml')).as_posix(), - schema='') + schema='', recv_size=recv_size) class NetshaperFamily(YnlFamily): - def __init__(self): + def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('net_shaper.yaml')).as_posix(), - schema='') + schema='', recv_size=recv_size) diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index cc0bfae2bafa..960e1ab4dd04 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -171,8 +171,10 @@ ovs_add_netns_and_veths () { ovs_add_if "$1" "$2" "$4" -u || return 1 fi - [ $TRACING -eq 1 ] && ovs_netns_spawn_daemon "$1" "$ns" \ - tcpdump -i any -s 65535 + if [ $TRACING -eq 1 ]; then + ovs_netns_spawn_daemon "$1" "$3" tcpdump -l -i any -s 6553 + ovs_wait grep -q "listening on any" ${ovs_dir}/stderr + fi return 0 } diff --git a/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; } |