mirror of
https://github.com/torvalds/linux.git
synced 2024-11-17 17:41:44 +00:00
a3841f94c7
* Introduce MAP_SYNC and MAP_SHARED_VALIDATE, a mechanism to enable 'userspace flush' of persistent memory updates via filesystem-dax mappings. It arranges for any filesystem metadata updates that may be required to satisfy a write fault to also be flushed ("on disk") before the kernel returns to userspace from the fault handler. Effectively every write-fault that dirties metadata completes an fsync() before returning from the fault handler. The new MAP_SHARED_VALIDATE mapping type guarantees that the MAP_SYNC flag is validated as supported by the filesystem's ->mmap() file operation. * Add support for the standard ACPI 6.2 label access methods that replace the NVDIMM_FAMILY_INTEL (vendor specific) label methods. This enables interoperability with environments that only implement the standardized methods. * Add support for the ACPI 6.2 NVDIMM media error injection methods. * Add support for the NVDIMM_FAMILY_INTEL v1.6 DIMM commands for latch last shutdown status, firmware update, SMART error injection, and SMART alarm threshold control. * Cleanup physical address information disclosures to be root-only. * Fix revalidation of the DIMM "locked label area" status to support dynamic unlock of the label area. * Expand unit test infrastructure to mock the ACPI 6.2 Translate SPA (system-physical-address) command and error injection commands. Acknowledgements that came after the commits were pushed to -next:957ac8c421
dax: fix PMD faults on zero-length files Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>a39e596baa
xfs: support for synchronous DAX faults Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>7b565c9f96
xfs: Implement xfs_filemap_pfn_mkwrite() using __xfs_filemap_fault() Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> -----BEGIN PGP SIGNATURE----- iQIcBAABAgAGBQJaDfvcAAoJEB7SkWpmfYgCk7sP/2qJhBH+VTTdg2osDnhAdAhI co/AGEmsHFlUCMBb/Ek7UnMAmhBYiJU2q4ywPsNFBpusXpMlqNy5Iwo7k4/wQHE/ SJcIM0g4zg0ViFuUhwV+C2T0R5UzFR8JLd9EYWj/YS6aJpurtotm5l4UStaM0Hzo AhxSXJLrBDuqCpbOxbctfiGEmdRL7aRfBEAARTNRKBn/iXxJUcYHlp62rtXQS+t4 I6LC/URCWTNTTMGmzW6TRsgSD9WMfd19xKcGzN3qL6ee0KFccxN4ctFqHA/sFGOh iYLeR0XJUjJxyp+PkWGteXPVZL0Kj3bD/lSTG+Co5bm/ra8a/sh3TSFfgFyoBZD1 EqMN8Ryf80hGp3FabeH2Iw2SviYPZpHSWgjddjxLD0RA6OmpzINc+Wm8eqApjMME sbZDTOijiab4QMQ0XamF4GuDHyQtawv5Y/w2Ehhl1tmiqW+5tKhsKqxkQt+/V3Yt RTVSRe2Pkway66b+cD64IdQ6L2tyonPnmi5IzgkKOhlOEGomy+4/U2Jt2bMbhzq6 ymszKmXp2XI8P06wU8sHrIUeXO5I9qoKn/fZA73Eb8aIzgJe3tBE/5+Ab7RG6HB9 1OVfcMWoXU1gNgNktTs63X1Lsg4aW9kt/K4fPHHcqUcaliEJpJTlAbg9GLF2buoW nQ+0fTRgMRihE3ZA0Fs3 =h2vZ -----END PGP SIGNATURE----- Merge tag 'libnvdimm-for-4.15' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm Pull libnvdimm and dax updates from Dan Williams: "Save for a few late fixes, all of these commits have shipped in -next releases since before the merge window opened, and 0day has given a build success notification. The ext4 touches came from Jan, and the xfs touches have Darrick's reviewed-by. An xfstest for the MAP_SYNC feature has been through a few round of reviews and is on track to be merged. - Introduce MAP_SYNC and MAP_SHARED_VALIDATE, a mechanism to enable 'userspace flush' of persistent memory updates via filesystem-dax mappings. It arranges for any filesystem metadata updates that may be required to satisfy a write fault to also be flushed ("on disk") before the kernel returns to userspace from the fault handler. Effectively every write-fault that dirties metadata completes an fsync() before returning from the fault handler. The new MAP_SHARED_VALIDATE mapping type guarantees that the MAP_SYNC flag is validated as supported by the filesystem's ->mmap() file operation. - Add support for the standard ACPI 6.2 label access methods that replace the NVDIMM_FAMILY_INTEL (vendor specific) label methods. This enables interoperability with environments that only implement the standardized methods. - Add support for the ACPI 6.2 NVDIMM media error injection methods. - Add support for the NVDIMM_FAMILY_INTEL v1.6 DIMM commands for latch last shutdown status, firmware update, SMART error injection, and SMART alarm threshold control. - Cleanup physical address information disclosures to be root-only. - Fix revalidation of the DIMM "locked label area" status to support dynamic unlock of the label area. - Expand unit test infrastructure to mock the ACPI 6.2 Translate SPA (system-physical-address) command and error injection commands. Acknowledgements that came after the commits were pushed to -next: -957ac8c421
("dax: fix PMD faults on zero-length files"): Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com> -a39e596baa
("xfs: support for synchronous DAX faults") and7b565c9f96
("xfs: Implement xfs_filemap_pfn_mkwrite() using __xfs_filemap_fault()") Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>" * tag 'libnvdimm-for-4.15' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (49 commits) acpi, nfit: add 'Enable Latch System Shutdown Status' command support dax: fix general protection fault in dax_alloc_inode dax: fix PMD faults on zero-length files dax: stop requiring a live device for dax_flush() brd: remove dax support dax: quiet bdev_dax_supported() fs, dax: unify IOMAP_F_DIRTY read vs write handling policy in the dax core tools/testing/nvdimm: unit test clear-error commands acpi, nfit: validate commands against the device type tools/testing/nvdimm: stricter bounds checking for error injection commands xfs: support for synchronous DAX faults xfs: Implement xfs_filemap_pfn_mkwrite() using __xfs_filemap_fault() ext4: Support for synchronous DAX faults ext4: Simplify error handling in ext4_dax_huge_fault() dax: Implement dax_finish_sync_fault() dax, iomap: Add support for synchronous faults mm: Define MAP_SYNC and VM_SYNC flags dax: Allow tuning whether dax_insert_mapping_entry() dirties entry dax: Allow dax_iomap_fault() to return pfn dax: Fix comment describing dax_iomap_fault() ...
287 lines
8.3 KiB
C
287 lines
8.3 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#undef TRACE_SYSTEM
|
|
#define TRACE_SYSTEM fs_dax
|
|
|
|
#if !defined(_TRACE_FS_DAX_H) || defined(TRACE_HEADER_MULTI_READ)
|
|
#define _TRACE_FS_DAX_H
|
|
|
|
#include <linux/tracepoint.h>
|
|
|
|
DECLARE_EVENT_CLASS(dax_pmd_fault_class,
|
|
TP_PROTO(struct inode *inode, struct vm_fault *vmf,
|
|
pgoff_t max_pgoff, int result),
|
|
TP_ARGS(inode, vmf, max_pgoff, result),
|
|
TP_STRUCT__entry(
|
|
__field(unsigned long, ino)
|
|
__field(unsigned long, vm_start)
|
|
__field(unsigned long, vm_end)
|
|
__field(unsigned long, vm_flags)
|
|
__field(unsigned long, address)
|
|
__field(pgoff_t, pgoff)
|
|
__field(pgoff_t, max_pgoff)
|
|
__field(dev_t, dev)
|
|
__field(unsigned int, flags)
|
|
__field(int, result)
|
|
),
|
|
TP_fast_assign(
|
|
__entry->dev = inode->i_sb->s_dev;
|
|
__entry->ino = inode->i_ino;
|
|
__entry->vm_start = vmf->vma->vm_start;
|
|
__entry->vm_end = vmf->vma->vm_end;
|
|
__entry->vm_flags = vmf->vma->vm_flags;
|
|
__entry->address = vmf->address;
|
|
__entry->flags = vmf->flags;
|
|
__entry->pgoff = vmf->pgoff;
|
|
__entry->max_pgoff = max_pgoff;
|
|
__entry->result = result;
|
|
),
|
|
TP_printk("dev %d:%d ino %#lx %s %s address %#lx vm_start "
|
|
"%#lx vm_end %#lx pgoff %#lx max_pgoff %#lx %s",
|
|
MAJOR(__entry->dev),
|
|
MINOR(__entry->dev),
|
|
__entry->ino,
|
|
__entry->vm_flags & VM_SHARED ? "shared" : "private",
|
|
__print_flags(__entry->flags, "|", FAULT_FLAG_TRACE),
|
|
__entry->address,
|
|
__entry->vm_start,
|
|
__entry->vm_end,
|
|
__entry->pgoff,
|
|
__entry->max_pgoff,
|
|
__print_flags(__entry->result, "|", VM_FAULT_RESULT_TRACE)
|
|
)
|
|
)
|
|
|
|
#define DEFINE_PMD_FAULT_EVENT(name) \
|
|
DEFINE_EVENT(dax_pmd_fault_class, name, \
|
|
TP_PROTO(struct inode *inode, struct vm_fault *vmf, \
|
|
pgoff_t max_pgoff, int result), \
|
|
TP_ARGS(inode, vmf, max_pgoff, result))
|
|
|
|
DEFINE_PMD_FAULT_EVENT(dax_pmd_fault);
|
|
DEFINE_PMD_FAULT_EVENT(dax_pmd_fault_done);
|
|
|
|
DECLARE_EVENT_CLASS(dax_pmd_load_hole_class,
|
|
TP_PROTO(struct inode *inode, struct vm_fault *vmf,
|
|
struct page *zero_page,
|
|
void *radix_entry),
|
|
TP_ARGS(inode, vmf, zero_page, radix_entry),
|
|
TP_STRUCT__entry(
|
|
__field(unsigned long, ino)
|
|
__field(unsigned long, vm_flags)
|
|
__field(unsigned long, address)
|
|
__field(struct page *, zero_page)
|
|
__field(void *, radix_entry)
|
|
__field(dev_t, dev)
|
|
),
|
|
TP_fast_assign(
|
|
__entry->dev = inode->i_sb->s_dev;
|
|
__entry->ino = inode->i_ino;
|
|
__entry->vm_flags = vmf->vma->vm_flags;
|
|
__entry->address = vmf->address;
|
|
__entry->zero_page = zero_page;
|
|
__entry->radix_entry = radix_entry;
|
|
),
|
|
TP_printk("dev %d:%d ino %#lx %s address %#lx zero_page %p "
|
|
"radix_entry %#lx",
|
|
MAJOR(__entry->dev),
|
|
MINOR(__entry->dev),
|
|
__entry->ino,
|
|
__entry->vm_flags & VM_SHARED ? "shared" : "private",
|
|
__entry->address,
|
|
__entry->zero_page,
|
|
(unsigned long)__entry->radix_entry
|
|
)
|
|
)
|
|
|
|
#define DEFINE_PMD_LOAD_HOLE_EVENT(name) \
|
|
DEFINE_EVENT(dax_pmd_load_hole_class, name, \
|
|
TP_PROTO(struct inode *inode, struct vm_fault *vmf, \
|
|
struct page *zero_page, void *radix_entry), \
|
|
TP_ARGS(inode, vmf, zero_page, radix_entry))
|
|
|
|
DEFINE_PMD_LOAD_HOLE_EVENT(dax_pmd_load_hole);
|
|
DEFINE_PMD_LOAD_HOLE_EVENT(dax_pmd_load_hole_fallback);
|
|
|
|
DECLARE_EVENT_CLASS(dax_pmd_insert_mapping_class,
|
|
TP_PROTO(struct inode *inode, struct vm_fault *vmf,
|
|
long length, pfn_t pfn, void *radix_entry),
|
|
TP_ARGS(inode, vmf, length, pfn, radix_entry),
|
|
TP_STRUCT__entry(
|
|
__field(unsigned long, ino)
|
|
__field(unsigned long, vm_flags)
|
|
__field(unsigned long, address)
|
|
__field(long, length)
|
|
__field(u64, pfn_val)
|
|
__field(void *, radix_entry)
|
|
__field(dev_t, dev)
|
|
__field(int, write)
|
|
),
|
|
TP_fast_assign(
|
|
__entry->dev = inode->i_sb->s_dev;
|
|
__entry->ino = inode->i_ino;
|
|
__entry->vm_flags = vmf->vma->vm_flags;
|
|
__entry->address = vmf->address;
|
|
__entry->write = vmf->flags & FAULT_FLAG_WRITE;
|
|
__entry->length = length;
|
|
__entry->pfn_val = pfn.val;
|
|
__entry->radix_entry = radix_entry;
|
|
),
|
|
TP_printk("dev %d:%d ino %#lx %s %s address %#lx length %#lx "
|
|
"pfn %#llx %s radix_entry %#lx",
|
|
MAJOR(__entry->dev),
|
|
MINOR(__entry->dev),
|
|
__entry->ino,
|
|
__entry->vm_flags & VM_SHARED ? "shared" : "private",
|
|
__entry->write ? "write" : "read",
|
|
__entry->address,
|
|
__entry->length,
|
|
__entry->pfn_val & ~PFN_FLAGS_MASK,
|
|
__print_flags_u64(__entry->pfn_val & PFN_FLAGS_MASK, "|",
|
|
PFN_FLAGS_TRACE),
|
|
(unsigned long)__entry->radix_entry
|
|
)
|
|
)
|
|
|
|
#define DEFINE_PMD_INSERT_MAPPING_EVENT(name) \
|
|
DEFINE_EVENT(dax_pmd_insert_mapping_class, name, \
|
|
TP_PROTO(struct inode *inode, struct vm_fault *vmf, \
|
|
long length, pfn_t pfn, void *radix_entry), \
|
|
TP_ARGS(inode, vmf, length, pfn, radix_entry))
|
|
|
|
DEFINE_PMD_INSERT_MAPPING_EVENT(dax_pmd_insert_mapping);
|
|
|
|
DECLARE_EVENT_CLASS(dax_pte_fault_class,
|
|
TP_PROTO(struct inode *inode, struct vm_fault *vmf, int result),
|
|
TP_ARGS(inode, vmf, result),
|
|
TP_STRUCT__entry(
|
|
__field(unsigned long, ino)
|
|
__field(unsigned long, vm_flags)
|
|
__field(unsigned long, address)
|
|
__field(pgoff_t, pgoff)
|
|
__field(dev_t, dev)
|
|
__field(unsigned int, flags)
|
|
__field(int, result)
|
|
),
|
|
TP_fast_assign(
|
|
__entry->dev = inode->i_sb->s_dev;
|
|
__entry->ino = inode->i_ino;
|
|
__entry->vm_flags = vmf->vma->vm_flags;
|
|
__entry->address = vmf->address;
|
|
__entry->flags = vmf->flags;
|
|
__entry->pgoff = vmf->pgoff;
|
|
__entry->result = result;
|
|
),
|
|
TP_printk("dev %d:%d ino %#lx %s %s address %#lx pgoff %#lx %s",
|
|
MAJOR(__entry->dev),
|
|
MINOR(__entry->dev),
|
|
__entry->ino,
|
|
__entry->vm_flags & VM_SHARED ? "shared" : "private",
|
|
__print_flags(__entry->flags, "|", FAULT_FLAG_TRACE),
|
|
__entry->address,
|
|
__entry->pgoff,
|
|
__print_flags(__entry->result, "|", VM_FAULT_RESULT_TRACE)
|
|
)
|
|
)
|
|
|
|
#define DEFINE_PTE_FAULT_EVENT(name) \
|
|
DEFINE_EVENT(dax_pte_fault_class, name, \
|
|
TP_PROTO(struct inode *inode, struct vm_fault *vmf, int result), \
|
|
TP_ARGS(inode, vmf, result))
|
|
|
|
DEFINE_PTE_FAULT_EVENT(dax_pte_fault);
|
|
DEFINE_PTE_FAULT_EVENT(dax_pte_fault_done);
|
|
DEFINE_PTE_FAULT_EVENT(dax_load_hole);
|
|
DEFINE_PTE_FAULT_EVENT(dax_insert_pfn_mkwrite_no_entry);
|
|
DEFINE_PTE_FAULT_EVENT(dax_insert_pfn_mkwrite);
|
|
|
|
TRACE_EVENT(dax_insert_mapping,
|
|
TP_PROTO(struct inode *inode, struct vm_fault *vmf, void *radix_entry),
|
|
TP_ARGS(inode, vmf, radix_entry),
|
|
TP_STRUCT__entry(
|
|
__field(unsigned long, ino)
|
|
__field(unsigned long, vm_flags)
|
|
__field(unsigned long, address)
|
|
__field(void *, radix_entry)
|
|
__field(dev_t, dev)
|
|
__field(int, write)
|
|
),
|
|
TP_fast_assign(
|
|
__entry->dev = inode->i_sb->s_dev;
|
|
__entry->ino = inode->i_ino;
|
|
__entry->vm_flags = vmf->vma->vm_flags;
|
|
__entry->address = vmf->address;
|
|
__entry->write = vmf->flags & FAULT_FLAG_WRITE;
|
|
__entry->radix_entry = radix_entry;
|
|
),
|
|
TP_printk("dev %d:%d ino %#lx %s %s address %#lx radix_entry %#lx",
|
|
MAJOR(__entry->dev),
|
|
MINOR(__entry->dev),
|
|
__entry->ino,
|
|
__entry->vm_flags & VM_SHARED ? "shared" : "private",
|
|
__entry->write ? "write" : "read",
|
|
__entry->address,
|
|
(unsigned long)__entry->radix_entry
|
|
)
|
|
)
|
|
|
|
DECLARE_EVENT_CLASS(dax_writeback_range_class,
|
|
TP_PROTO(struct inode *inode, pgoff_t start_index, pgoff_t end_index),
|
|
TP_ARGS(inode, start_index, end_index),
|
|
TP_STRUCT__entry(
|
|
__field(unsigned long, ino)
|
|
__field(pgoff_t, start_index)
|
|
__field(pgoff_t, end_index)
|
|
__field(dev_t, dev)
|
|
),
|
|
TP_fast_assign(
|
|
__entry->dev = inode->i_sb->s_dev;
|
|
__entry->ino = inode->i_ino;
|
|
__entry->start_index = start_index;
|
|
__entry->end_index = end_index;
|
|
),
|
|
TP_printk("dev %d:%d ino %#lx pgoff %#lx-%#lx",
|
|
MAJOR(__entry->dev),
|
|
MINOR(__entry->dev),
|
|
__entry->ino,
|
|
__entry->start_index,
|
|
__entry->end_index
|
|
)
|
|
)
|
|
|
|
#define DEFINE_WRITEBACK_RANGE_EVENT(name) \
|
|
DEFINE_EVENT(dax_writeback_range_class, name, \
|
|
TP_PROTO(struct inode *inode, pgoff_t start_index, pgoff_t end_index),\
|
|
TP_ARGS(inode, start_index, end_index))
|
|
|
|
DEFINE_WRITEBACK_RANGE_EVENT(dax_writeback_range);
|
|
DEFINE_WRITEBACK_RANGE_EVENT(dax_writeback_range_done);
|
|
|
|
TRACE_EVENT(dax_writeback_one,
|
|
TP_PROTO(struct inode *inode, pgoff_t pgoff, pgoff_t pglen),
|
|
TP_ARGS(inode, pgoff, pglen),
|
|
TP_STRUCT__entry(
|
|
__field(unsigned long, ino)
|
|
__field(pgoff_t, pgoff)
|
|
__field(pgoff_t, pglen)
|
|
__field(dev_t, dev)
|
|
),
|
|
TP_fast_assign(
|
|
__entry->dev = inode->i_sb->s_dev;
|
|
__entry->ino = inode->i_ino;
|
|
__entry->pgoff = pgoff;
|
|
__entry->pglen = pglen;
|
|
),
|
|
TP_printk("dev %d:%d ino %#lx pgoff %#lx pglen %#lx",
|
|
MAJOR(__entry->dev),
|
|
MINOR(__entry->dev),
|
|
__entry->ino,
|
|
__entry->pgoff,
|
|
__entry->pglen
|
|
)
|
|
)
|
|
|
|
#endif /* _TRACE_FS_DAX_H */
|
|
|
|
/* This part must be outside protection */
|
|
#include <trace/define_trace.h>
|