linux/drivers/dax/device.c

488 lines
12 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 2016-2018 Intel Corporation. All rights reserved. */
#include <linux/memremap.h>
#include <linux/pagemap.h>
#include <linux/module.h>
#include <linux/device.h>
#include <linux/pfn_t.h>
#include <linux/cdev.h>
#include <linux/slab.h>
#include <linux/dax.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include "dax-private.h"
#include "bus.h"
static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma,
const char *func)
{
struct dax_region *dax_region = dev_dax->region;
struct device *dev = &dev_dax->dev;
unsigned long mask;
if (!dax_alive(dev_dax->dax_dev))
return -ENXIO;
/* prevent private mappings from being established */
if ((vma->vm_flags & VM_MAYSHARE) != VM_MAYSHARE) {
dev_info_ratelimited(dev,
"%s: %s: fail, attempted private mapping\n",
current->comm, func);
return -EINVAL;
}
mask = dax_region->align - 1;
if (vma->vm_start & mask || vma->vm_end & mask) {
dev_info_ratelimited(dev,
"%s: %s: fail, unaligned vma (%#lx - %#lx, %#lx)\n",
current->comm, func, vma->vm_start, vma->vm_end,
mask);
return -EINVAL;
}
if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) == PFN_DEV
&& (vma->vm_flags & VM_DONTCOPY) == 0) {
dev_info_ratelimited(dev,
"%s: %s: fail, dax range requires MADV_DONTFORK\n",
current->comm, func);
return -EINVAL;
}
if (!vma_is_dax(vma)) {
dev_info_ratelimited(dev,
"%s: %s: fail, vma is not DAX capable\n",
current->comm, func);
return -EINVAL;
}
return 0;
}
/* see "strong" declaration in tools/testing/nvdimm/dax-dev.c */
__weak phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff,
unsigned long size)
{
struct resource *res = &dev_dax->region->res;
phys_addr_t phys;
phys = pgoff * PAGE_SIZE + res->start;
if (phys >= res->start && phys <= res->end) {
if (phys + size - 1 <= res->end)
return phys;
}
return -1;
}
static vm_fault_t __dev_dax_pte_fault(struct dev_dax *dev_dax,
struct vm_fault *vmf, pfn_t *pfn)
{
struct device *dev = &dev_dax->dev;
struct dax_region *dax_region;
phys_addr_t phys;
unsigned int fault_size = PAGE_SIZE;
if (check_vma(dev_dax, vmf->vma, __func__))
return VM_FAULT_SIGBUS;
dax_region = dev_dax->region;
if (dax_region->align > PAGE_SIZE) {
dev_dbg(dev, "alignment (%#x) > fault size (%#x)\n",
dax_region->align, fault_size);
return VM_FAULT_SIGBUS;
}
if (fault_size != dax_region->align)
return VM_FAULT_SIGBUS;
phys = dax_pgoff_to_phys(dev_dax, vmf->pgoff, PAGE_SIZE);
if (phys == -1) {
dev_dbg(dev, "pgoff_to_phys(%#lx) failed\n", vmf->pgoff);
return VM_FAULT_SIGBUS;
}
*pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
return vmf_insert_mixed(vmf->vma, vmf->address, *pfn);
}
static vm_fault_t __dev_dax_pmd_fault(struct dev_dax *dev_dax,
struct vm_fault *vmf, pfn_t *pfn)
{
unsigned long pmd_addr = vmf->address & PMD_MASK;
struct device *dev = &dev_dax->dev;
struct dax_region *dax_region;
phys_addr_t phys;
pgoff_t pgoff;
unsigned int fault_size = PMD_SIZE;
if (check_vma(dev_dax, vmf->vma, __func__))
return VM_FAULT_SIGBUS;
dax_region = dev_dax->region;
if (dax_region->align > PMD_SIZE) {
dev_dbg(dev, "alignment (%#x) > fault size (%#x)\n",
dax_region->align, fault_size);
return VM_FAULT_SIGBUS;
}
/* dax pmd mappings require pfn_t_devmap() */
if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) != (PFN_DEV|PFN_MAP)) {
dev_dbg(dev, "region lacks devmap flags\n");
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 = dax_pgoff_to_phys(dev_dax, pgoff, PMD_SIZE);
if (phys == -1) {
dev_dbg(dev, "pgoff_to_phys(%#lx) failed\n", pgoff);
return VM_FAULT_SIGBUS;
}
*pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
mm/huge_memory: fix vmf_insert_pfn_{pmd, pud}() crash, handle unaligned addresses Starting with c6f3c5ee40c1 ("mm/huge_memory.c: fix modifying of page protection by insert_pfn_pmd()") vmf_insert_pfn_pmd() internally calls pmdp_set_access_flags(). That helper enforces a pmd aligned @address argument via VM_BUG_ON() assertion. Update the implementation to take a 'struct vm_fault' argument directly and apply the address alignment fixup internally to fix crash signatures like: kernel BUG at arch/x86/mm/pgtable.c:515! invalid opcode: 0000 [#1] SMP NOPTI CPU: 51 PID: 43713 Comm: java Tainted: G OE 4.19.35 #1 [..] RIP: 0010:pmdp_set_access_flags+0x48/0x50 [..] Call Trace: vmf_insert_pfn_pmd+0x198/0x350 dax_iomap_fault+0xe82/0x1190 ext4_dax_huge_fault+0x103/0x1f0 ? __switch_to_asm+0x40/0x70 __handle_mm_fault+0x3f6/0x1370 ? __switch_to_asm+0x34/0x70 ? __switch_to_asm+0x40/0x70 handle_mm_fault+0xda/0x200 __do_page_fault+0x249/0x4f0 do_page_fault+0x32/0x110 ? page_fault+0x8/0x30 page_fault+0x1e/0x30 Link: http://lkml.kernel.org/r/155741946350.372037.11148198430068238140.stgit@dwillia2-desk3.amr.corp.intel.com Fixes: c6f3c5ee40c1 ("mm/huge_memory.c: fix modifying of page protection by insert_pfn_pmd()") Signed-off-by: Dan Williams <dan.j.williams@intel.com> Reported-by: Piotr Balcer <piotr.balcer@intel.com> Tested-by: Yan Ma <yan.ma@intel.com> Tested-by: Pankaj Gupta <pagupta@redhat.com> Reviewed-by: Matthew Wilcox <willy@infradead.org> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Cc: Chandan Rajendra <chandan@linux.ibm.com> Cc: Souptick Joarder <jrdr.linux@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 00:15:33 +00:00
return vmf_insert_pfn_pmd(vmf, *pfn, vmf->flags & FAULT_FLAG_WRITE);
}
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,
struct vm_fault *vmf, pfn_t *pfn)
{
unsigned long pud_addr = vmf->address & PUD_MASK;
struct device *dev = &dev_dax->dev;
struct dax_region *dax_region;
phys_addr_t phys;
pgoff_t pgoff;
unsigned int fault_size = PUD_SIZE;
if (check_vma(dev_dax, vmf->vma, __func__))
return VM_FAULT_SIGBUS;
dax_region = dev_dax->region;
if (dax_region->align > PUD_SIZE) {
dev_dbg(dev, "alignment (%#x) > fault size (%#x)\n",
dax_region->align, fault_size);
return VM_FAULT_SIGBUS;
}
/* dax pud mappings require pfn_t_devmap() */
if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) != (PFN_DEV|PFN_MAP)) {
dev_dbg(dev, "region lacks devmap flags\n");
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 = dax_pgoff_to_phys(dev_dax, pgoff, PUD_SIZE);
if (phys == -1) {
dev_dbg(dev, "pgoff_to_phys(%#lx) failed\n", pgoff);
return VM_FAULT_SIGBUS;
}
*pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
mm/huge_memory: fix vmf_insert_pfn_{pmd, pud}() crash, handle unaligned addresses Starting with c6f3c5ee40c1 ("mm/huge_memory.c: fix modifying of page protection by insert_pfn_pmd()") vmf_insert_pfn_pmd() internally calls pmdp_set_access_flags(). That helper enforces a pmd aligned @address argument via VM_BUG_ON() assertion. Update the implementation to take a 'struct vm_fault' argument directly and apply the address alignment fixup internally to fix crash signatures like: kernel BUG at arch/x86/mm/pgtable.c:515! invalid opcode: 0000 [#1] SMP NOPTI CPU: 51 PID: 43713 Comm: java Tainted: G OE 4.19.35 #1 [..] RIP: 0010:pmdp_set_access_flags+0x48/0x50 [..] Call Trace: vmf_insert_pfn_pmd+0x198/0x350 dax_iomap_fault+0xe82/0x1190 ext4_dax_huge_fault+0x103/0x1f0 ? __switch_to_asm+0x40/0x70 __handle_mm_fault+0x3f6/0x1370 ? __switch_to_asm+0x34/0x70 ? __switch_to_asm+0x40/0x70 handle_mm_fault+0xda/0x200 __do_page_fault+0x249/0x4f0 do_page_fault+0x32/0x110 ? page_fault+0x8/0x30 page_fault+0x1e/0x30 Link: http://lkml.kernel.org/r/155741946350.372037.11148198430068238140.stgit@dwillia2-desk3.amr.corp.intel.com Fixes: c6f3c5ee40c1 ("mm/huge_memory.c: fix modifying of page protection by insert_pfn_pmd()") Signed-off-by: Dan Williams <dan.j.williams@intel.com> Reported-by: Piotr Balcer <piotr.balcer@intel.com> Tested-by: Yan Ma <yan.ma@intel.com> Tested-by: Pankaj Gupta <pagupta@redhat.com> Reviewed-by: Matthew Wilcox <willy@infradead.org> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Cc: Chandan Rajendra <chandan@linux.ibm.com> Cc: Souptick Joarder <jrdr.linux@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 00:15:33 +00:00
return vmf_insert_pfn_pud(vmf, *pfn, vmf->flags & FAULT_FLAG_WRITE);
}
#else
static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,
struct vm_fault *vmf, pfn_t *pfn)
{
return VM_FAULT_FALLBACK;
}
#endif /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
static vm_fault_t dev_dax_huge_fault(struct vm_fault *vmf,
enum page_entry_size pe_size)
{
struct file *filp = vmf->vma->vm_file;
unsigned long fault_size;
vm_fault_t rc = VM_FAULT_SIGBUS;
int id;
pfn_t pfn;
struct dev_dax *dev_dax = filp->private_data;
dev_dbg(&dev_dax->dev, "%s: %s (%#lx - %#lx) size = %d\n", current->comm,
(vmf->flags & FAULT_FLAG_WRITE) ? "write" : "read",
vmf->vma->vm_start, vmf->vma->vm_end, pe_size);
id = dax_read_lock();
switch (pe_size) {
case PE_SIZE_PTE:
fault_size = PAGE_SIZE;
rc = __dev_dax_pte_fault(dev_dax, vmf, &pfn);
mm,fs,dax: change ->pmd_fault to ->huge_fault Patch series "1G transparent hugepage support for device dax", v2. The following series implements support for 1G trasparent hugepage on x86 for device dax. The bulk of the code was written by Mathew Wilcox a while back supporting transparent 1G hugepage for fs DAX. I have forward ported the relevant bits to 4.10-rc. The current submission has only the necessary code to support device DAX. Comments from Dan Williams: So the motivation and intended user of this functionality mirrors the motivation and users of 1GB page support in hugetlbfs. Given expected capacities of persistent memory devices an in-memory database may want to reduce tlb pressure beyond what they can already achieve with 2MB mappings of a device-dax file. We have customer feedback to that effect as Willy mentioned in his previous version of these patches [1]. [1]: https://lkml.org/lkml/2016/1/31/52 Comments from Nilesh @ Oracle: There are applications which have a process model; and if you assume 10,000 processes attempting to mmap all the 6TB memory available on a server; we are looking at the following: processes : 10,000 memory : 6TB pte @ 4k page size: 8 bytes / 4K of memory * #processes = 6TB / 4k * 8 * 10000 = 1.5GB * 80000 = 120,000GB pmd @ 2M page size: 120,000 / 512 = ~240GB pud @ 1G page size: 240GB / 512 = ~480MB As you can see with 2M pages, this system will use up an exorbitant amount of DRAM to hold the page tables; but the 1G pages finally brings it down to a reasonable level. Memory sizes will keep increasing; so this number will keep increasing. An argument can be made to convert the applications from process model to thread model, but in the real world that may not be always practical. Hopefully this helps explain the use case where this is valuable. This patch (of 3): In preparation for adding the ability to handle PUD pages, convert vm_operations_struct.pmd_fault to vm_operations_struct.huge_fault. The vm_fault structure is extended to include a union of the different page table pointers that may be needed, and three flag bits are reserved to indicate which type of pointer is in the union. [ross.zwisler@linux.intel.com: remove unused function ext4_dax_huge_fault()] Link: http://lkml.kernel.org/r/1485813172-7284-1-git-send-email-ross.zwisler@linux.intel.com [dave.jiang@intel.com: clear PMD or PUD size flags when in fall through path] Link: http://lkml.kernel.org/r/148589842696.5820.16078080610311444794.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545058784.17912.6353162518188733642.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-24 22:56:59 +00:00
break;
case PE_SIZE_PMD:
fault_size = PMD_SIZE;
rc = __dev_dax_pmd_fault(dev_dax, vmf, &pfn);
break;
case PE_SIZE_PUD:
fault_size = PUD_SIZE;
rc = __dev_dax_pud_fault(dev_dax, vmf, &pfn);
mm,fs,dax: change ->pmd_fault to ->huge_fault Patch series "1G transparent hugepage support for device dax", v2. The following series implements support for 1G trasparent hugepage on x86 for device dax. The bulk of the code was written by Mathew Wilcox a while back supporting transparent 1G hugepage for fs DAX. I have forward ported the relevant bits to 4.10-rc. The current submission has only the necessary code to support device DAX. Comments from Dan Williams: So the motivation and intended user of this functionality mirrors the motivation and users of 1GB page support in hugetlbfs. Given expected capacities of persistent memory devices an in-memory database may want to reduce tlb pressure beyond what they can already achieve with 2MB mappings of a device-dax file. We have customer feedback to that effect as Willy mentioned in his previous version of these patches [1]. [1]: https://lkml.org/lkml/2016/1/31/52 Comments from Nilesh @ Oracle: There are applications which have a process model; and if you assume 10,000 processes attempting to mmap all the 6TB memory available on a server; we are looking at the following: processes : 10,000 memory : 6TB pte @ 4k page size: 8 bytes / 4K of memory * #processes = 6TB / 4k * 8 * 10000 = 1.5GB * 80000 = 120,000GB pmd @ 2M page size: 120,000 / 512 = ~240GB pud @ 1G page size: 240GB / 512 = ~480MB As you can see with 2M pages, this system will use up an exorbitant amount of DRAM to hold the page tables; but the 1G pages finally brings it down to a reasonable level. Memory sizes will keep increasing; so this number will keep increasing. An argument can be made to convert the applications from process model to thread model, but in the real world that may not be always practical. Hopefully this helps explain the use case where this is valuable. This patch (of 3): In preparation for adding the ability to handle PUD pages, convert vm_operations_struct.pmd_fault to vm_operations_struct.huge_fault. The vm_fault structure is extended to include a union of the different page table pointers that may be needed, and three flag bits are reserved to indicate which type of pointer is in the union. [ross.zwisler@linux.intel.com: remove unused function ext4_dax_huge_fault()] Link: http://lkml.kernel.org/r/1485813172-7284-1-git-send-email-ross.zwisler@linux.intel.com [dave.jiang@intel.com: clear PMD or PUD size flags when in fall through path] Link: http://lkml.kernel.org/r/148589842696.5820.16078080610311444794.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545058784.17912.6353162518188733642.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-24 22:56:59 +00:00
break;
default:
rc = VM_FAULT_SIGBUS;
mm,fs,dax: change ->pmd_fault to ->huge_fault Patch series "1G transparent hugepage support for device dax", v2. The following series implements support for 1G trasparent hugepage on x86 for device dax. The bulk of the code was written by Mathew Wilcox a while back supporting transparent 1G hugepage for fs DAX. I have forward ported the relevant bits to 4.10-rc. The current submission has only the necessary code to support device DAX. Comments from Dan Williams: So the motivation and intended user of this functionality mirrors the motivation and users of 1GB page support in hugetlbfs. Given expected capacities of persistent memory devices an in-memory database may want to reduce tlb pressure beyond what they can already achieve with 2MB mappings of a device-dax file. We have customer feedback to that effect as Willy mentioned in his previous version of these patches [1]. [1]: https://lkml.org/lkml/2016/1/31/52 Comments from Nilesh @ Oracle: There are applications which have a process model; and if you assume 10,000 processes attempting to mmap all the 6TB memory available on a server; we are looking at the following: processes : 10,000 memory : 6TB pte @ 4k page size: 8 bytes / 4K of memory * #processes = 6TB / 4k * 8 * 10000 = 1.5GB * 80000 = 120,000GB pmd @ 2M page size: 120,000 / 512 = ~240GB pud @ 1G page size: 240GB / 512 = ~480MB As you can see with 2M pages, this system will use up an exorbitant amount of DRAM to hold the page tables; but the 1G pages finally brings it down to a reasonable level. Memory sizes will keep increasing; so this number will keep increasing. An argument can be made to convert the applications from process model to thread model, but in the real world that may not be always practical. Hopefully this helps explain the use case where this is valuable. This patch (of 3): In preparation for adding the ability to handle PUD pages, convert vm_operations_struct.pmd_fault to vm_operations_struct.huge_fault. The vm_fault structure is extended to include a union of the different page table pointers that may be needed, and three flag bits are reserved to indicate which type of pointer is in the union. [ross.zwisler@linux.intel.com: remove unused function ext4_dax_huge_fault()] Link: http://lkml.kernel.org/r/1485813172-7284-1-git-send-email-ross.zwisler@linux.intel.com [dave.jiang@intel.com: clear PMD or PUD size flags when in fall through path] Link: http://lkml.kernel.org/r/148589842696.5820.16078080610311444794.stgit@djiang5-desk3.ch.intel.com Link: http://lkml.kernel.org/r/148545058784.17912.6353162518188733642.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Jan Kara <jack@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-24 22:56:59 +00:00
}
if (rc == VM_FAULT_NOPAGE) {
unsigned long i;
pgoff_t pgoff;
/*
* In the device-dax case the only possibility for a
* VM_FAULT_NOPAGE result is when device-dax capacity is
* mapped. No need to consider the zero page, or racing
* conflicting mappings.
*/
pgoff = linear_page_index(vmf->vma, vmf->address
& ~(fault_size - 1));
for (i = 0; i < fault_size / PAGE_SIZE; i++) {
struct page *page;
page = pfn_to_page(pfn_t_to_pfn(pfn) + i);
if (page->mapping)
continue;
page->mapping = filp->f_mapping;
page->index = pgoff + i;
}
}
dax_read_unlock(id);
return rc;
}
static vm_fault_t dev_dax_fault(struct vm_fault *vmf)
{
return dev_dax_huge_fault(vmf, PE_SIZE_PTE);
}
device-dax: implement ->split() to catch invalid munmap attempts Similar to how device-dax enforces that the 'address', 'offset', and 'len' parameters to mmap() be aligned to the device's fundamental alignment, the same constraints apply to munmap(). Implement ->split() to fail munmap calls that violate the alignment constraint. Otherwise, we later fail VM_BUG_ON checks in the unmap_page_range() path with crash signatures of the form: vma ffff8800b60c8a88 start 00007f88c0000000 end 00007f88c0e00000 next (null) prev (null) mm ffff8800b61150c0 prot 8000000000000027 anon_vma (null) vm_ops ffffffffa0091240 pgoff 0 file ffff8800b638ef80 private_data (null) flags: 0x380000fb(read|write|shared|mayread|maywrite|mayexec|mayshare|softdirty|mixedmap|hugepage) ------------[ cut here ]------------ kernel BUG at mm/huge_memory.c:2014! [..] RIP: 0010:__split_huge_pud+0x12a/0x180 [..] Call Trace: unmap_page_range+0x245/0xa40 ? __vma_adjust+0x301/0x990 unmap_vmas+0x4c/0xa0 unmap_region+0xae/0x120 ? __vma_rb_erase+0x11a/0x230 do_munmap+0x276/0x410 vm_munmap+0x6a/0xa0 SyS_munmap+0x1d/0x30 Link: http://lkml.kernel.org/r/151130418681.4029.7118245855057952010.stgit@dwillia2-desk3.amr.corp.intel.com Fixes: dee410792419 ("/dev/dax, core: file operations and dax-mmap") Signed-off-by: Dan Williams <dan.j.williams@intel.com> Reported-by: Jeff Moyer <jmoyer@redhat.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-30 00:10:32 +00:00
static int dev_dax_split(struct vm_area_struct *vma, unsigned long addr)
{
struct file *filp = vma->vm_file;
struct dev_dax *dev_dax = filp->private_data;
struct dax_region *dax_region = dev_dax->region;
if (!IS_ALIGNED(addr, dax_region->align))
return -EINVAL;
return 0;
}
static unsigned long dev_dax_pagesize(struct vm_area_struct *vma)
{
struct file *filp = vma->vm_file;
struct dev_dax *dev_dax = filp->private_data;
struct dax_region *dax_region = dev_dax->region;
return dax_region->align;
}
static const struct vm_operations_struct dax_vm_ops = {
.fault = dev_dax_fault,
.huge_fault = dev_dax_huge_fault,
device-dax: implement ->split() to catch invalid munmap attempts Similar to how device-dax enforces that the 'address', 'offset', and 'len' parameters to mmap() be aligned to the device's fundamental alignment, the same constraints apply to munmap(). Implement ->split() to fail munmap calls that violate the alignment constraint. Otherwise, we later fail VM_BUG_ON checks in the unmap_page_range() path with crash signatures of the form: vma ffff8800b60c8a88 start 00007f88c0000000 end 00007f88c0e00000 next (null) prev (null) mm ffff8800b61150c0 prot 8000000000000027 anon_vma (null) vm_ops ffffffffa0091240 pgoff 0 file ffff8800b638ef80 private_data (null) flags: 0x380000fb(read|write|shared|mayread|maywrite|mayexec|mayshare|softdirty|mixedmap|hugepage) ------------[ cut here ]------------ kernel BUG at mm/huge_memory.c:2014! [..] RIP: 0010:__split_huge_pud+0x12a/0x180 [..] Call Trace: unmap_page_range+0x245/0xa40 ? __vma_adjust+0x301/0x990 unmap_vmas+0x4c/0xa0 unmap_region+0xae/0x120 ? __vma_rb_erase+0x11a/0x230 do_munmap+0x276/0x410 vm_munmap+0x6a/0xa0 SyS_munmap+0x1d/0x30 Link: http://lkml.kernel.org/r/151130418681.4029.7118245855057952010.stgit@dwillia2-desk3.amr.corp.intel.com Fixes: dee410792419 ("/dev/dax, core: file operations and dax-mmap") Signed-off-by: Dan Williams <dan.j.williams@intel.com> Reported-by: Jeff Moyer <jmoyer@redhat.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-30 00:10:32 +00:00
.split = dev_dax_split,
.pagesize = dev_dax_pagesize,
};
static int dax_mmap(struct file *filp, struct vm_area_struct *vma)
{
struct dev_dax *dev_dax = filp->private_data;
int rc, id;
dev_dbg(&dev_dax->dev, "trace\n");
/*
* We lock to check dax_dev liveness and will re-check at
* fault time.
*/
id = dax_read_lock();
rc = check_vma(dev_dax, vma, __func__);
dax_read_unlock(id);
if (rc)
return rc;
vma->vm_ops = &dax_vm_ops;
dax: remove VM_MIXEDMAP for fsdax and device dax This patch is reworked from an earlier patch that Dan has posted: https://patchwork.kernel.org/patch/10131727/ VM_MIXEDMAP is used by dax to direct mm paths like vm_normal_page() that the memory page it is dealing with is not typical memory from the linear map. The get_user_pages_fast() path, since it does not resolve the vma, is already using {pte,pmd}_devmap() as a stand-in for VM_MIXEDMAP, so we use that as a VM_MIXEDMAP replacement in some locations. In the cases where there is no pte to consult we fallback to using vma_is_dax() to detect the VM_MIXEDMAP special case. Now that we have explicit driver pfn_t-flag opt-in/opt-out for get_user_pages() support for DAX we can stop setting VM_MIXEDMAP. This also means we no longer need to worry about safely manipulating vm_flags in a future where we support dynamically changing the dax mode of a file. DAX should also now be supported with madvise_behavior(), vma_merge(), and copy_page_range(). This patch has been tested against ndctl unit test. It has also been tested against xfstests commit: 625515d using fake pmem created by memmap and no additional issues have been observed. Link: http://lkml.kernel.org/r/152847720311.55924.16999195879201817653.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Dave Jiang <dave.jiang@intel.com> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-17 22:43:40 +00:00
vma->vm_flags |= VM_HUGEPAGE;
return 0;
}
/* return an unmapped area aligned to the dax region specified alignment */
static unsigned long dax_get_unmapped_area(struct file *filp,
unsigned long addr, unsigned long len, unsigned long pgoff,
unsigned long flags)
{
unsigned long off, off_end, off_align, len_align, addr_align, align;
struct dev_dax *dev_dax = filp ? filp->private_data : NULL;
struct dax_region *dax_region;
if (!dev_dax || addr)
goto out;
dax_region = dev_dax->region;
align = dax_region->align;
off = pgoff << PAGE_SHIFT;
off_end = off + len;
off_align = round_up(off, align);
if ((off_end <= off_align) || ((off_end - off_align) < align))
goto out;
len_align = len + align;
if ((off + len_align) < off)
goto out;
addr_align = current->mm->get_unmapped_area(filp, addr, len_align,
pgoff, flags);
if (!IS_ERR_VALUE(addr_align)) {
addr_align += (off - addr_align) & (align - 1);
return addr_align;
}
out:
return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
}
static const struct address_space_operations dev_dax_aops = {
.set_page_dirty = noop_set_page_dirty,
.invalidatepage = noop_invalidatepage,
};
static int dax_open(struct inode *inode, struct file *filp)
{
struct dax_device *dax_dev = inode_dax(inode);
struct inode *__dax_inode = dax_inode(dax_dev);
struct dev_dax *dev_dax = dax_get_private(dax_dev);
dev_dbg(&dev_dax->dev, "trace\n");
inode->i_mapping = __dax_inode->i_mapping;
inode->i_mapping->host = __dax_inode;
inode->i_mapping->a_ops = &dev_dax_aops;
filp->f_mapping = inode->i_mapping;
fs: new infrastructure for writeback error handling and reporting Most filesystems currently use mapping_set_error and filemap_check_errors for setting and reporting/clearing writeback errors at the mapping level. filemap_check_errors is indirectly called from most of the filemap_fdatawait_* functions and from filemap_write_and_wait*. These functions are called from all sorts of contexts to wait on writeback to finish -- e.g. mostly in fsync, but also in truncate calls, getattr, etc. The non-fsync callers are problematic. We should be reporting writeback errors during fsync, but many places spread over the tree clear out errors before they can be properly reported, or report errors at nonsensical times. If I get -EIO on a stat() call, there is no reason for me to assume that it is because some previous writeback failed. The fact that it also clears out the error such that a subsequent fsync returns 0 is a bug, and a nasty one since that's potentially silent data corruption. This patch adds a small bit of new infrastructure for setting and reporting errors during address_space writeback. While the above was my original impetus for adding this, I think it's also the case that current fsync semantics are just problematic for userland. Most applications that call fsync do so to ensure that the data they wrote has hit the backing store. In the case where there are multiple writers to the file at the same time, this is really hard to determine. The first one to call fsync will see any stored error, and the rest get back 0. The processes with open fds may not be associated with one another in any way. They could even be in different containers, so ensuring coordination between all fsync callers is not really an option. One way to remedy this would be to track what file descriptor was used to dirty the file, but that's rather cumbersome and would likely be slow. However, there is a simpler way to improve the semantics here without incurring too much overhead. This set adds an errseq_t to struct address_space, and a corresponding one is added to struct file. Writeback errors are recorded in the mapping's errseq_t, and the one in struct file is used as the "since" value. This changes the semantics of the Linux fsync implementation such that applications can now use it to determine whether there were any writeback errors since fsync(fd) was last called (or since the file was opened in the case of fsync having never been called). Note that those writeback errors may have occurred when writing data that was dirtied via an entirely different fd, but that's the case now with the current mapping_set_error/filemap_check_error infrastructure. This will at least prevent you from getting a false report of success. The new behavior is still consistent with the POSIX spec, and is more reliable for application developers. This patch just adds some basic infrastructure for doing this, and ensures that the f_wb_err "cursor" is properly set when a file is opened. Later patches will change the existing code to use this new infrastructure for reporting errors at fsync time. Signed-off-by: Jeff Layton <jlayton@redhat.com> Reviewed-by: Jan Kara <jack@suse.cz>
2017-07-06 11:02:25 +00:00
filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
vfs: track per-sb writeback errors and report them to syncfs Patch series "vfs: have syncfs() return error when there are writeback errors", v6. Currently, syncfs does not return errors when one of the inodes fails to be written back. It will return errors based on the legacy AS_EIO and AS_ENOSPC flags when syncing out the block device fails, but that's not particularly helpful for filesystems that aren't backed by a blockdev. It's also possible for a stray sync to lose those errors. The basic idea in this set is to track writeback errors at the superblock level, so that we can quickly and easily check whether something bad happened without having to fsync each file individually. syncfs is then changed to reliably report writeback errors after they occur, much in the same fashion as fsync does now. This patch (of 2): Usually we suggest that applications call fsync when they want to ensure that all data written to the file has made it to the backing store, but that can be inefficient when there are a lot of open files. Calling syncfs on the filesystem can be more efficient in some situations, but the error reporting doesn't currently work the way most people expect. If a single inode on a filesystem reports a writeback error, syncfs won't necessarily return an error. syncfs only returns an error if __sync_blockdev fails, and on some filesystems that's a no-op. It would be better if syncfs reported an error if there were any writeback failures. Then applications could call syncfs to see if there are any errors on any open files, and could then call fsync on all of the other descriptors to figure out which one failed. This patch adds a new errseq_t to struct super_block, and has mapping_set_error also record writeback errors there. To report those errors, we also need to keep an errseq_t in struct file to act as a cursor. This patch adds a dedicated field for that purpose, which slots nicely into 4 bytes of padding at the end of struct file on x86_64. An earlier version of this patch used an O_PATH file descriptor to cue the kernel that the open file should track the superblock error and not the inode's writeback error. I think that API is just too weird though. This is simpler and should make syncfs error reporting "just work" even if someone is multiplexing fsync and syncfs on the same fds. Signed-off-by: Jeff Layton <jlayton@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Jan Kara <jack@suse.cz> Cc: Andres Freund <andres@anarazel.de> Cc: Matthew Wilcox <willy@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: David Howells <dhowells@redhat.com> Link: http://lkml.kernel.org/r/20200428135155.19223-1-jlayton@kernel.org Link: http://lkml.kernel.org/r/20200428135155.19223-2-jlayton@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-02 04:45:36 +00:00
filp->f_sb_err = file_sample_sb_err(filp);
filp->private_data = dev_dax;
inode->i_flags = S_DAX;
return 0;
}
static int dax_release(struct inode *inode, struct file *filp)
{
struct dev_dax *dev_dax = filp->private_data;
dev_dbg(&dev_dax->dev, "trace\n");
return 0;
}
static const struct file_operations dax_fops = {
.llseek = noop_llseek,
.owner = THIS_MODULE,
.open = dax_open,
.release = dax_release,
.get_unmapped_area = dax_get_unmapped_area,
.mmap = dax_mmap,
.mmap_supported_flags = MAP_SYNC,
};
static void dev_dax_cdev_del(void *cdev)
{
cdev_del(cdev);
}
static void dev_dax_kill(void *dev_dax)
{
kill_dev_dax(dev_dax);
}
int dev_dax_probe(struct device *dev)
{
struct dev_dax *dev_dax = to_dev_dax(dev);
struct dax_device *dax_dev = dev_dax->dax_dev;
struct resource *res = &dev_dax->region->res;
struct inode *inode;
struct cdev *cdev;
void *addr;
int rc;
/* 1:1 map region resource range to device-dax instance range */
if (!devm_request_mem_region(dev, res->start, resource_size(res),
dev_name(dev))) {
dev_warn(dev, "could not reserve region %pR\n", res);
return -EBUSY;
}
dev_dax->pgmap.type = MEMORY_DEVICE_DEVDAX;
addr = devm_memremap_pages(dev, &dev_dax->pgmap);
mm/devm_memremap_pages: fix final page put race Logan noticed that devm_memremap_pages_release() kills the percpu_ref drops all the page references that were acquired at init and then immediately proceeds to unplug, arch_remove_memory(), the backing pages for the pagemap. If for some reason device shutdown actually collides with a busy / elevated-ref-count page then arch_remove_memory() should be deferred until after that reference is dropped. As it stands the "wait for last page ref drop" happens *after* devm_memremap_pages_release() returns, which is obviously too late and can lead to crashes. Fix this situation by assigning the responsibility to wait for the percpu_ref to go idle to devm_memremap_pages() with a new ->cleanup() callback. Implement the new cleanup callback for all devm_memremap_pages() users: pmem, devdax, hmm, and p2pdma. Link: http://lkml.kernel.org/r/155727339156.292046.5432007428235387859.stgit@dwillia2-desk3.amr.corp.intel.com Fixes: 41e94a851304 ("add devm_memremap_pages") Signed-off-by: Dan Williams <dan.j.williams@intel.com> Reported-by: Logan Gunthorpe <logang@deltatee.com> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Reviewed-by: Logan Gunthorpe <logang@deltatee.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Rafael J. Wysocki" <rafael@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-06-13 22:56:33 +00:00
if (IS_ERR(addr))
return PTR_ERR(addr);
inode = dax_inode(dax_dev);
cdev = inode->i_cdev;
cdev_init(cdev, &dax_fops);
if (dev->class) {
/* for the CONFIG_DEV_DAX_PMEM_COMPAT case */
cdev->owner = dev->parent->driver->owner;
} else
cdev->owner = dev->driver->owner;
cdev_set_parent(cdev, &dev->kobj);
rc = cdev_add(cdev, dev->devt, 1);
if (rc)
return rc;
rc = devm_add_action_or_reset(dev, dev_dax_cdev_del, cdev);
if (rc)
return rc;
run_dax(dax_dev);
return devm_add_action_or_reset(dev, dev_dax_kill, dev_dax);
}
EXPORT_SYMBOL_GPL(dev_dax_probe);
static int dev_dax_remove(struct device *dev)
{
/* all probe actions are unwound by devm */
return 0;
}
static struct dax_device_driver device_dax_driver = {
.drv = {
.probe = dev_dax_probe,
.remove = dev_dax_remove,
},
.match_always = 1,
};
static int __init dax_init(void)
{
return dax_driver_register(&device_dax_driver);
}
static void __exit dax_exit(void)
{
dax_driver_unregister(&device_dax_driver);
}
MODULE_AUTHOR("Intel Corporation");
MODULE_LICENSE("GPL v2");
module_init(dax_init);
module_exit(dax_exit);
MODULE_ALIAS_DAX_DEVICE(0);