From 0134ed4fb9e78672ee9f7b18007114404c81e63f Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 10 Mar 2017 13:24:22 -0700 Subject: device-dax: fix pmd/pte fault fallback handling Jeff Moyer reports: With a device dax alignment of 4KB or 2MB, I get sigbus when running the attached fio job file for the current kernel (4.11.0-rc1+). If I specify an alignment of 1GB, it works. I turned on debug output, and saw that it was failing in the huge fault code. dax dax1.0: dax_open dax dax1.0: dax_mmap dax dax1.0: dax_dev_huge_fault: fio: write (0x7f08f0a00000 - dax dax1.0: __dax_dev_pud_fault: phys_to_pgoff(0xffffffffcf60 dax dax1.0: dax_release fio config for reproduce: [global] ioengine=dev-dax direct=0 filename=/dev/dax0.0 bs=2m [write] rw=write [read] stonewall rw=read The driver fails to fallback when taking a fault that is larger than the device alignment, or handling a larger fault when a smaller mapping is already established. While we could support larger mappings for a device with a smaller alignment, that change is too large for the immediate fix. The simplest change is to force fallback until the fault size matches the alignment. Fixes: dee410792419 ("/dev/dax, core: file operations and dax-mmap") Cc: Reported-by: Jeff Moyer Signed-off-by: Dave Jiang Signed-off-by: Dan Williams --- drivers/dax/dax.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c index 8d9829ff2a78..a284dc532e46 100644 --- a/drivers/dax/dax.c +++ b/drivers/dax/dax.c @@ -427,6 +427,7 @@ static int __dax_dev_pte_fault(struct dax_dev *dax_dev, struct vm_fault *vmf) int rc = VM_FAULT_SIGBUS; phys_addr_t phys; pfn_t pfn; + unsigned int fault_size = PAGE_SIZE; if (check_vma(dax_dev, vmf->vma, __func__)) return VM_FAULT_SIGBUS; @@ -437,6 +438,9 @@ static int __dax_dev_pte_fault(struct dax_dev *dax_dev, struct vm_fault *vmf) return VM_FAULT_SIGBUS; } + if (fault_size != dax_region->align) + return VM_FAULT_SIGBUS; + phys = pgoff_to_phys(dax_dev, vmf->pgoff, PAGE_SIZE); if (phys == -1) { dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__, @@ -464,6 +468,7 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev, struct vm_fault *vmf) phys_addr_t phys; pgoff_t pgoff; pfn_t pfn; + unsigned int fault_size = PMD_SIZE; if (check_vma(dax_dev, vmf->vma, __func__)) return VM_FAULT_SIGBUS; @@ -480,6 +485,16 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev, struct vm_fault *vmf) return VM_FAULT_SIGBUS; } + if (fault_size < dax_region->align) + return VM_FAULT_SIGBUS; + else if (fault_size > dax_region->align) + return VM_FAULT_FALLBACK; + + /* if we are outside of the VMA */ + if (pmd_addr < vmf->vma->vm_start || + (pmd_addr + PMD_SIZE) > vmf->vma->vm_end) + return VM_FAULT_SIGBUS; + pgoff = linear_page_index(vmf->vma, pmd_addr); phys = pgoff_to_phys(dax_dev, pgoff, PMD_SIZE); if (phys == -1) { -- cgit v1.2.3 From 70b085b06c4560a69e95607f77bb4c2b2e41943c Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 10 Mar 2017 13:24:27 -0700 Subject: device-dax: fix pud fault fallback handling Jeff Moyer reports: With a device dax alignment of 4KB or 2MB, I get sigbus when running the attached fio job file for the current kernel (4.11.0-rc1+). If I specify an alignment of 1GB, it works. I turned on debug output, and saw that it was failing in the huge fault code. dax dax1.0: dax_open dax dax1.0: dax_mmap dax dax1.0: dax_dev_huge_fault: fio: write (0x7f08f0a00000 - dax dax1.0: __dax_dev_pud_fault: phys_to_pgoff(0xffffffffcf60) dax dax1.0: dax_release fio config for reproduce: [global] ioengine=dev-dax direct=0 filename=/dev/dax0.0 bs=2m [write] rw=write [read] stonewall rw=read The driver fails to fallback when taking a fault that is larger than the device alignment, or handling a larger fault when a smaller mapping is already established. While we could support larger mappings for a device with a smaller alignment, that change is too large for the immediate fix. The simplest change is to force fallback until the fault size matches the alignment. Reported-by: Jeff Moyer Signed-off-by: Dave Jiang Signed-off-by: Dan Williams --- drivers/dax/dax.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c index a284dc532e46..523fecec7bda 100644 --- a/drivers/dax/dax.c +++ b/drivers/dax/dax.c @@ -518,6 +518,8 @@ static int __dax_dev_pud_fault(struct dax_dev *dax_dev, struct vm_fault *vmf) phys_addr_t phys; pgoff_t pgoff; pfn_t pfn; + unsigned int fault_size = PUD_SIZE; + if (check_vma(dax_dev, vmf->vma, __func__)) return VM_FAULT_SIGBUS; @@ -534,6 +536,16 @@ static int __dax_dev_pud_fault(struct dax_dev *dax_dev, struct vm_fault *vmf) return VM_FAULT_SIGBUS; } + if (fault_size < dax_region->align) + return VM_FAULT_SIGBUS; + else if (fault_size > dax_region->align) + return VM_FAULT_FALLBACK; + + /* if we are outside of the VMA */ + if (pud_addr < vmf->vma->vm_start || + (pud_addr + PUD_SIZE) > vmf->vma->vm_end) + return VM_FAULT_SIGBUS; + pgoff = linear_page_index(vmf->vma, pud_addr); phys = pgoff_to_phys(dax_dev, pgoff, PUD_SIZE); if (phys == -1) { -- cgit v1.2.3 From 52084f89b38cdd896b59627c629915ef1a7bf615 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Thu, 9 Mar 2017 16:56:01 -0700 Subject: device-dax: fix debug output typo The debug output for return the return data of pgoff_to_phys() in the fault handlers has 'phys' and 'pgoff' incorrectly swapped. Reported-by: Jeff Moyer Signed-off-by: Dave Jiang Signed-off-by: Dan Williams --- drivers/dax/dax.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c index 523fecec7bda..80c6db279ae1 100644 --- a/drivers/dax/dax.c +++ b/drivers/dax/dax.c @@ -443,7 +443,7 @@ static int __dax_dev_pte_fault(struct dax_dev *dax_dev, struct vm_fault *vmf) phys = pgoff_to_phys(dax_dev, vmf->pgoff, PAGE_SIZE); if (phys == -1) { - dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__, + dev_dbg(dev, "%s: pgoff_to_phys(%#lx) failed\n", __func__, vmf->pgoff); return VM_FAULT_SIGBUS; } @@ -498,7 +498,7 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev, struct vm_fault *vmf) pgoff = linear_page_index(vmf->vma, pmd_addr); phys = pgoff_to_phys(dax_dev, pgoff, PMD_SIZE); if (phys == -1) { - dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__, + dev_dbg(dev, "%s: pgoff_to_phys(%#lx) failed\n", __func__, pgoff); return VM_FAULT_SIGBUS; } @@ -549,7 +549,7 @@ static int __dax_dev_pud_fault(struct dax_dev *dax_dev, struct vm_fault *vmf) pgoff = linear_page_index(vmf->vma, pud_addr); phys = pgoff_to_phys(dax_dev, pgoff, PUD_SIZE); if (phys == -1) { - dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__, + dev_dbg(dev, "%s: pgoff_to_phys(%#lx) failed\n", __func__, pgoff); return VM_FAULT_SIGBUS; } -- cgit v1.2.3