From 62f0f34fbd2b2d5653d33d3b9d42fdcabb1c0101 Mon Sep 17 00:00:00 2001 From: Shuhei Takeshita Date: Sun, 9 Aug 2026 12:27:43 +0900 Subject: [PATCH] IB/hfi1: Fix the PIO_CRED credit-return mmap hfi1_file_mmap()'s PIO_CRED case must hand user space the single credit-return page that holds this context's entry. That page is the second or third page of the per-node credit-return allocation once the hardware send context index reaches 64 or 128, so the failure below is intermittent: when the entry lands on the first page the offset is zero and everything works. Two things are wrong. First, cr_page_offset is a byte offset but .va is a struct credit_return *, so adding it is pointer arithmetic and scales the offset by sizeof(struct credit_return) == 64. memvirt then lands 256 KiB or 512 KiB past a 10240-byte allocation. With an IOMMU translating, that address is inside the vmalloc range but in no vm_area, so dma_mmap_coherent() -> iommu_dma_mmap() finds no pages, vmalloc_to_pfn() returns page_to_pfn(NULL), and remap_pfn_range() installs a frame above MAXPHYADDR. The first user read then takes: psm2_ep_open_pr: Corrupted page table at address 7a14d007e000 PGD 800000013886a067 P4D 800000013886a067 PUD 13886b067 PMD 13886c067 PTE 800049168e911235 Oops: Bad pagetable: 000d [#1] SMP PTI Second, and still wrong once the arithmetic is corrected, dma_mmap_coherent() describes a whole coherent buffer and selects the page within it with vma->vm_pgoff. Offsetting cpu_addr has no effect: for a vmap'd allocation iommu_dma_mmap() uses cpu_addr only to locate the vm_area and then maps pages[vm_pgoff], which hfi1_file_mmap() has just set to 0. User space therefore always receives the first credit-return page, every credit read is for the wrong context, and send PIO stalls forever. Use the DMA API as intended: pass the base of the allocation with its full length and select the page with vm_pgoff. A separate length is needed because memlen must keep describing the VMA for the existing size check. The dma-direct path stays correct as well, since dma_direct_mmap() adds the same vm_pgoff to the base pfn. Tested on a Dell T7610 (Xeon E5-2650 v2, Intel IOMMU in DMA-FQ mode) against a Threadripper PRO 3995WX peer, both Omni-Path 100. Before this change psm2_ep_open() Oopses the kernel; with only the arithmetic corrected psm2_ep_open() succeeds but any transfer that uses send PIO hangs, PSM2_SDMA=2 (send PIO disabled) completing normally while PSM2_SDMA=0 (send PIO only) hangs every time. With this change send PIO, send DMA and the default mixed mode all work. Fixes: 1ec82317a1da ("IB/hfi1: Use dma_mmap_coherent for matching buffers") Cc: stable@vger.kernel.org Signed-off-by: Shuhei Takeshita Link: https://patch.msgid.link/20260809032743.2671579-3-jyohuku.alterego@gmail.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/hfi1/file_ops.c | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index 72c21d7455fd..1a36f995c4f6 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -326,6 +326,7 @@ static int hfi1_file_mmap(struct file *fp, struct vm_area_struct *vma) void *memvirt = NULL; dma_addr_t memdma = 0; u8 subctxt, mapio = 0, vmf = 0, type; + size_t memdmalen = 0; ssize_t memlen = 0; int ret = 0; u16 ctxt; @@ -371,7 +372,9 @@ static int hfi1_file_mmap(struct file *fp, struct vm_area_struct *vma) mapio = 1; break; case PIO_CRED: { + struct credit_return_base *cr = &dd->cr_base[uctxt->sc->node]; u64 cr_page_offset; + if (flags & VM_WRITE) { ret = -EPERM; goto done; @@ -381,11 +384,18 @@ static int hfi1_file_mmap(struct file *fp, struct vm_area_struct *vma) * second or third page allocated for credit returns (if number * of enabled contexts > 64 and 128 respectively). */ - cr_page_offset = ((u64)uctxt->sc->hw_free - - (u64)dd->cr_base[uctxt->sc->node].va) & + cr_page_offset = ((u64)uctxt->sc->hw_free - (u64)cr->va) & PAGE_MASK; - memvirt = dd->cr_base[uctxt->sc->node].va + cr_page_offset; - memdma = dd->cr_base[uctxt->sc->node].dma + cr_page_offset; + /* + * dma_mmap_coherent() describes the whole coherent buffer and + * selects the page within it with vma->vm_pgoff, so pass the + * base of the allocation and its length and let vm_pgoff pick + * the page. + */ + vma->vm_pgoff = cr_page_offset >> PAGE_SHIFT; + memvirt = cr->va; + memdma = cr->dma; + memdmalen = TXE_NUM_CONTEXTS * sizeof(struct credit_return); memlen = PAGE_SIZE; flags &= ~VM_MAYWRITE; flags |= VM_DONTCOPY | VM_DONTEXPAND; @@ -567,7 +577,8 @@ static int hfi1_file_mmap(struct file *fp, struct vm_area_struct *vma) ret = 0; } else if (memdma) { ret = dma_mmap_coherent(&dd->pcidev->dev, vma, - memvirt, memdma, memlen); + memvirt, memdma, + memdmalen ? memdmalen : memlen); } else if (mapio) { ret = io_remap_pfn_range(vma, vma->vm_start, PFN_DOWN(memaddr),