kernel/linux.git/drivers/misc/ocxl, branch v4.19.39

ocxl: Fix endiannes bug in read_afu_name()

2019-01-09T16:38:43+00:00

commit 2f07229f02d4c55affccd11a61af4fd4b94dc436 upstream. The AFU Descriptor Template in the PCI config space has a Name Space field which is a 24 Byte ASCII character string of descriptive name space for the AFU. The OCXL driver read the string four characters at a time with pci_read_config_dword(). This optimization is valid on a little-endian system since this is PCI, but a big-endian system ends up with each subset of four characters in reverse order. This could be fixed by switching to read characters one by one. Another option is to swap the bytes if we're big-endian. Go for the latter with le32_to_cpu(). Cc: stable@vger.kernel.org # v4.16 Signed-off-by: Greg Kurz Acked-by: Frederic Barrat Acked-by: Andrew Donnellan Signed-off-by: Michael Ellerman Signed-off-by: Greg Kroah-Hartman

ocxl: Fix endiannes bug in ocxl_link_update_pe()

2019-01-09T16:38:43+00:00

commit e1e71e201703500f708bdeaf64660a2a178cb6a0 upstream. All fields in the PE are big-endian. Use cpu_to_be32() like everywhere else something is written to the PE. Otherwise a wrong TID will be used by the NPU. If this TID happens to point to an existing thread sharing the same mm, it could be woken up by error. This is highly improbable though. The likely outcome of this is the NPU not finding the target thread and forcing the AFU into sending an interrupt, which userspace is supposed to handle anyway. Fixes: e948e06fc63a ("ocxl: Expose the thread_id needed for wait on POWER9") Cc: stable@vger.kernel.org # v4.18 Signed-off-by: Greg Kurz Acked-by: Andrew Donnellan Signed-off-by: Michael Ellerman Signed-off-by: Greg Kroah-Hartman

ocxl: Fix access to the AFU Descriptor Data

2018-11-13T19:08:51+00:00

commit 6f8e45f7eb1bee5efdbe4a9cfe4a45627403c5fb upstream. The AFU Information DVSEC capability is a means to extract common, general information about all of the AFUs associated with a Function independent of the specific functionality that each AFU provides. Write in the AFU Index field allows to access to the descriptor data for each AFU. With the current code, we are not able to access to these specific data when the index >= 1 because we are writing to the wrong location. All requests to the data of each AFU are pointing to those of the AFU 0, which could have impacts when using a card with more than one AFU per function. This patch fixes the access to the AFU Descriptor Data indexed by the AFU Info Index field. Fixes: 5ef3166e8a32 ("ocxl: Driver code for 'generic' opencapi devices") Cc: stable # 4.16 Signed-off-by: Christophe Lombard Signed-off-by: Greg Kroah-Hartman Acked-by: Frederic Barrat Acked-by: Andrew Donnellan Signed-off-by: Michael Ellerman

Merge branch 'akpm' (patches from Andrew)

2018-08-17T23:49:31+00:00

Merge updates from Andrew Morton: - a few misc things - a few Y2038 fixes - ntfs fixes - arch/sh tweaks - ocfs2 updates - most of MM * emailed patches from Andrew Morton : (111 commits) mm/hmm.c: remove unused variables align_start and align_end fs/userfaultfd.c: remove redundant pointer uwq mm, vmacache: hash addresses based on pmd mm/list_lru: introduce list_lru_shrink_walk_irq() mm/list_lru.c: pass struct list_lru_node* as an argument to __list_lru_walk_one() mm/list_lru.c: move locking from __list_lru_walk_one() to its caller mm/list_lru.c: use list_lru_walk_one() in list_lru_walk_node() mm, swap: make CONFIG_THP_SWAP depend on CONFIG_SWAP mm/sparse: delete old sparse_init and enable new one mm/sparse: add new sparse_init_nid() and sparse_init() mm/sparse: move buffer init/fini to the common place mm/sparse: use the new sparse buffer functions in non-vmemmap mm/sparse: abstract sparse buffer allocations mm/hugetlb.c: don't zero 1GiB bootmem pages mm, page_alloc: double zone's batchsize mm/oom_kill.c: document oom_lock mm/hugetlb: remove gigantic page support for HIGHMEM mm, oom: remove sleep from under oom_lock kernel/dma: remove unsupported gfp_mask parameter from dma_alloc_from_contiguous() mm/cma: remove unsupported gfp_mask parameter from cma_alloc() ...

mm: convert return type of handle_mm_fault() caller to vm_fault_t

2018-08-17T23:20:28+00:00

Use new return type vm_fault_t for fault handler. For now, this is just documenting that the function returns a VM_FAULT value rather than an errno. Once all instances are converted, vm_fault_t will become a distinct type. Ref-> commit 1c8f422059ae ("mm: change return type to vm_fault_t") In this patch all the caller of handle_mm_fault() are changed to return vm_fault_t type. Link: http://lkml.kernel.org/r/20180617084810.GA6730@jordon-HP-15-Notebook-PC Signed-off-by: Souptick Joarder Cc: Matthew Wilcox Cc: Richard Henderson Cc: Tony Luck Cc: Matt Turner Cc: Vineet Gupta Cc: Russell King Cc: Catalin Marinas Cc: Will Deacon Cc: Richard Kuo Cc: Geert Uytterhoeven Cc: Michal Simek Cc: James Hogan Cc: Ley Foon Tan Cc: Jonas Bonn Cc: James E.J. Bottomley Cc: Benjamin Herrenschmidt Cc: Palmer Dabbelt Cc: Yoshinori Sato Cc: David S. Miller Cc: Richard Weinberger Cc: Guan Xuetao Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: "Levin, Alexander (Sasha Levin)" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

ocxl: Fix page fault handler in case of fault on dying process

2018-07-02T13:59:45+00:00

If a process exits without doing proper cleanup, there's a window where an opencapi device can try to access the memory of the dying process and may trigger a page fault. That's an expected scenario and the ocxl driver holds a reference on the mm_struct of the process until the opencapi device is notified of the process exiting. However, if mm_users is already at 0, i.e. the address space of the process has already been destroyed, the driver shouldn't try resolving the page fault, as it will fail, but it can also try accessing already freed data. It is fixed by only calling the bottom half of the page fault handler if mm_users is greater than 0 and get a reference on mm_users instead of mm_count. Otherwise, we can safely return a translation fault to the device, as its associated memory context is being removed. The opencapi device will be properly cleaned up shortly after when closing the file descriptors. Fixes: 5ef3166e8a32 ("ocxl: Driver code for 'generic' opencapi devices") Cc: stable@vger.kernel.org # v4.16+ Signed-off-by: Frederic Barrat Reviewed-By: Alastair D'Silva Acked-by: Andrew Donnellan Signed-off-by: Michael Ellerman

ocxl: Change return type for fault handler

2018-07-02T13:54:26+00:00

ocxl: Fix missing unlock on error in afu_ioctl_enable_p9_wait()

2018-06-05T11:33:57+00:00

Add the missing unlock before return from function afu_ioctl_enable_p9_wait() in the error handling case. Fixes: e948e06fc63a ("ocxl: Expose the thread_id needed for wait on POWER9") Signed-off-by: Wei Yongjun Reviewed-by: Alastair D'Silva Signed-off-by: Michael Ellerman

ocxl: Add an IOCTL so userspace knows what OCXL features are available

2018-06-03T10:40:32+00:00

In order for a userspace AFU driver to call the POWER9 specific OCXL_IOCTL_ENABLE_P9_WAIT, it needs to verify that it can actually make that call. Signed-off-by: Alastair D'Silva Acked-by: Frederic Barrat Acked-by: Andrew Donnellan Signed-off-by: Michael Ellerman

ocxl: Expose the thread_id needed for wait on POWER9

2018-06-03T10:40:32+00:00

In order to successfully issue as_notify, an AFU needs to know the TID to notify, which in turn means that this information should be available in userspace so it can be communicated to the AFU. Signed-off-by: Alastair D'Silva Acked-by: Andrew Donnellan Signed-off-by: Michael Ellerman