summaryrefslogtreecommitdiffstats
path: root/drivers/dax
diff options
context:
space:
mode:
authorDan Williams <dan.j.williams@intel.com>2016-05-14 12:20:44 -0700
committerDan Williams <dan.j.williams@intel.com>2016-05-20 22:02:55 -0700
commitdee410792419aaa8bc3e3b35d2ccb6515835916d (patch)
treeb63a073ff7e6bad601ac7c45d3b0a156d906b052 /drivers/dax
parentab68f26221366f92611650e8470e6a926801c7d4 (diff)
downloadlinux-dee410792419aaa8bc3e3b35d2ccb6515835916d.tar.bz2
/dev/dax, core: file operations and dax-mmap
The "Device DAX" core enables dax mappings of performance / feature differentiated memory. An open mapping or file handle keeps the backing struct device live, but new mappings are only possible while the device is enabled. Faults are handled under rcu_read_lock to synchronize with the enabled state of the device. Similar to the filesystem-dax case the backing memory may optionally have struct page entries. However, unlike fs-dax there is no support for private mappings, or mappings that are not backed by media (see use of zero-page in fs-dax). Mappings are always guaranteed to match the alignment of the dax_region. If the dax_region is configured to have a 2MB alignment, all mappings are guaranteed to be backed by a pmd entry. Contrast this determinism with the fs-dax case where pmd mappings are opportunistic. If userspace attempts to force a misaligned mapping, the driver will fail the mmap attempt. See dax_dev_check_vma() for other scenarios that are rejected, like MAP_PRIVATE mappings. Cc: Hannes Reinecke <hare@suse.de> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Diffstat (limited to 'drivers/dax')
-rw-r--r--drivers/dax/Kconfig1
-rw-r--r--drivers/dax/dax.c322
2 files changed, 323 insertions, 0 deletions
diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
index 86ffbaa891ad..cedab7572de3 100644
--- a/drivers/dax/Kconfig
+++ b/drivers/dax/Kconfig
@@ -1,6 +1,7 @@
menuconfig DEV_DAX
tristate "DAX: direct access to differentiated memory"
default m if NVDIMM_DAX
+ depends on TRANSPARENT_HUGEPAGE
help
Support raw access to differentiated (persistence, bandwidth,
latency...) memory via an mmap(2) capable character
diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index 4c22a40f2335..b891a129b275 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -49,6 +49,7 @@ struct dax_region {
* @region - parent region
* @dev - device backing the character device
* @kref - enable this data to be tracked in filp->private_data
+ * @alive - !alive + rcu grace period == no new mappings can be established
* @id - child id in the region
* @num_resources - number of physical address extents in this device
* @res - array of physical address ranges
@@ -57,6 +58,7 @@ struct dax_dev {
struct dax_region *region;
struct device *dev;
struct kref kref;
+ bool alive;
int id;
int num_resources;
struct resource res[0];
@@ -150,6 +152,16 @@ static void unregister_dax_dev(void *_dev)
dev_dbg(dev, "%s\n", __func__);
+ /*
+ * Note, rcu is not protecting the liveness of dax_dev, rcu is
+ * ensuring that any fault handlers that might have seen
+ * dax_dev->alive == true, have completed. Any fault handlers
+ * that start after synchronize_rcu() has started will abort
+ * upon seeing dax_dev->alive == false.
+ */
+ dax_dev->alive = false;
+ synchronize_rcu();
+
get_device(dev);
device_unregister(dev);
ida_simple_remove(&dax_region->ida, dax_dev->id);
@@ -173,6 +185,7 @@ int devm_create_dax_dev(struct dax_region *dax_region, struct resource *res,
memcpy(dax_dev->res, res, sizeof(*res) * count);
dax_dev->num_resources = count;
kref_init(&dax_dev->kref);
+ dax_dev->alive = true;
dax_dev->region = dax_region;
kref_get(&dax_region->kref);
@@ -217,9 +230,318 @@ int devm_create_dax_dev(struct dax_region *dax_region, struct resource *res,
}
EXPORT_SYMBOL_GPL(devm_create_dax_dev);
+/* return an unmapped area aligned to the dax region specified alignment */
+static unsigned long dax_dev_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 dax_dev *dax_dev = filp ? filp->private_data : NULL;
+ struct dax_region *dax_region;
+
+ if (!dax_dev || addr)
+ goto out;
+
+ dax_region = dax_dev->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 int __match_devt(struct device *dev, const void *data)
+{
+ const dev_t *devt = data;
+
+ return dev->devt == *devt;
+}
+
+static struct device *dax_dev_find(dev_t dev_t)
+{
+ return class_find_device(dax_class, NULL, &dev_t, __match_devt);
+}
+
+static int dax_dev_open(struct inode *inode, struct file *filp)
+{
+ struct dax_dev *dax_dev = NULL;
+ struct device *dev;
+
+ dev = dax_dev_find(inode->i_rdev);
+ if (!dev)
+ return -ENXIO;
+
+ device_lock(dev);
+ dax_dev = dev_get_drvdata(dev);
+ if (dax_dev) {
+ dev_dbg(dev, "%s\n", __func__);
+ filp->private_data = dax_dev;
+ kref_get(&dax_dev->kref);
+ inode->i_flags = S_DAX;
+ }
+ device_unlock(dev);
+
+ if (!dax_dev) {
+ put_device(dev);
+ return -ENXIO;
+ }
+ return 0;
+}
+
+static int dax_dev_release(struct inode *inode, struct file *filp)
+{
+ struct dax_dev *dax_dev = filp->private_data;
+ struct device *dev = dax_dev->dev;
+
+ dev_dbg(dax_dev->dev, "%s\n", __func__);
+ dax_dev_put(dax_dev);
+ put_device(dev);
+
+ return 0;
+}
+
+static int check_vma(struct dax_dev *dax_dev, struct vm_area_struct *vma,
+ const char *func)
+{
+ struct dax_region *dax_region = dax_dev->region;
+ struct device *dev = dax_dev->dev;
+ unsigned long mask;
+
+ if (!dax_dev->alive)
+ return -ENXIO;
+
+ /* prevent private / writable mappings from being established */
+ if ((vma->vm_flags & (VM_NORESERVE|VM_SHARED|VM_WRITE)) == VM_WRITE) {
+ dev_info(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(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(dev, "%s: %s: fail, dax range requires MADV_DONTFORK\n",
+ current->comm, func);
+ return -EINVAL;
+ }
+
+ if (!vma_is_dax(vma)) {
+ dev_info(dev, "%s: %s: fail, vma is not DAX capable\n",
+ current->comm, func);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static phys_addr_t pgoff_to_phys(struct dax_dev *dax_dev, pgoff_t pgoff,
+ unsigned long size)
+{
+ struct resource *res;
+ phys_addr_t phys;
+ int i;
+
+ for (i = 0; i < dax_dev->num_resources; i++) {
+ res = &dax_dev->res[i];
+ phys = pgoff * PAGE_SIZE + res->start;
+ if (phys >= res->start && phys <= res->end)
+ break;
+ pgoff -= PHYS_PFN(resource_size(res));
+ }
+
+ if (i < dax_dev->num_resources) {
+ res = &dax_dev->res[i];
+ if (phys + size - 1 <= res->end)
+ return phys;
+ }
+
+ return -1;
+}
+
+static int __dax_dev_fault(struct dax_dev *dax_dev, struct vm_area_struct *vma,
+ struct vm_fault *vmf)
+{
+ unsigned long vaddr = (unsigned long) vmf->virtual_address;
+ struct device *dev = dax_dev->dev;
+ struct dax_region *dax_region;
+ int rc = VM_FAULT_SIGBUS;
+ phys_addr_t phys;
+ pfn_t pfn;
+
+ if (check_vma(dax_dev, vma, __func__))
+ return VM_FAULT_SIGBUS;
+
+ dax_region = dax_dev->region;
+ if (dax_region->align > PAGE_SIZE) {
+ dev_dbg(dev, "%s: alignment > fault size\n", __func__);
+ 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__,
+ vmf->pgoff);
+ return VM_FAULT_SIGBUS;
+ }
+
+ pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
+
+ rc = vm_insert_mixed(vma, vaddr, pfn);
+
+ if (rc == -ENOMEM)
+ return VM_FAULT_OOM;
+ if (rc < 0 && rc != -EBUSY)
+ return VM_FAULT_SIGBUS;
+
+ return VM_FAULT_NOPAGE;
+}
+
+static int dax_dev_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ int rc;
+ struct file *filp = vma->vm_file;
+ struct dax_dev *dax_dev = filp->private_data;
+
+ dev_dbg(dax_dev->dev, "%s: %s: %s (%#lx - %#lx)\n", __func__,
+ current->comm, (vmf->flags & FAULT_FLAG_WRITE)
+ ? "write" : "read", vma->vm_start, vma->vm_end);
+ rcu_read_lock();
+ rc = __dax_dev_fault(dax_dev, vma, vmf);
+ rcu_read_unlock();
+
+ return rc;
+}
+
+static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
+ struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd,
+ unsigned int flags)
+{
+ unsigned long pmd_addr = addr & PMD_MASK;
+ struct device *dev = dax_dev->dev;
+ struct dax_region *dax_region;
+ phys_addr_t phys;
+ pgoff_t pgoff;
+ pfn_t pfn;
+
+ if (check_vma(dax_dev, vma, __func__))
+ return VM_FAULT_SIGBUS;
+
+ dax_region = dax_dev->region;
+ if (dax_region->align > PMD_SIZE) {
+ dev_dbg(dev, "%s: alignment > fault size\n", __func__);
+ 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, "%s: alignment > fault size\n", __func__);
+ return VM_FAULT_SIGBUS;
+ }
+
+ pgoff = linear_page_index(vma, pmd_addr);
+ phys = pgoff_to_phys(dax_dev, pgoff, PAGE_SIZE);
+ if (phys == -1) {
+ dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__,
+ pgoff);
+ return VM_FAULT_SIGBUS;
+ }
+
+ pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
+
+ return vmf_insert_pfn_pmd(vma, addr, pmd, pfn,
+ flags & FAULT_FLAG_WRITE);
+}
+
+static int dax_dev_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
+ pmd_t *pmd, unsigned int flags)
+{
+ int rc;
+ struct file *filp = vma->vm_file;
+ struct dax_dev *dax_dev = filp->private_data;
+
+ dev_dbg(dax_dev->dev, "%s: %s: %s (%#lx - %#lx)\n", __func__,
+ current->comm, (flags & FAULT_FLAG_WRITE)
+ ? "write" : "read", vma->vm_start, vma->vm_end);
+
+ rcu_read_lock();
+ rc = __dax_dev_pmd_fault(dax_dev, vma, addr, pmd, flags);
+ rcu_read_unlock();
+
+ return rc;
+}
+
+static void dax_dev_vm_open(struct vm_area_struct *vma)
+{
+ struct file *filp = vma->vm_file;
+ struct dax_dev *dax_dev = filp->private_data;
+
+ dev_dbg(dax_dev->dev, "%s\n", __func__);
+ kref_get(&dax_dev->kref);
+}
+
+static void dax_dev_vm_close(struct vm_area_struct *vma)
+{
+ struct file *filp = vma->vm_file;
+ struct dax_dev *dax_dev = filp->private_data;
+
+ dev_dbg(dax_dev->dev, "%s\n", __func__);
+ dax_dev_put(dax_dev);
+}
+
+static const struct vm_operations_struct dax_dev_vm_ops = {
+ .fault = dax_dev_fault,
+ .pmd_fault = dax_dev_pmd_fault,
+ .open = dax_dev_vm_open,
+ .close = dax_dev_vm_close,
+};
+
+static int dax_dev_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+ struct dax_dev *dax_dev = filp->private_data;
+ int rc;
+
+ dev_dbg(dax_dev->dev, "%s\n", __func__);
+
+ rc = check_vma(dax_dev, vma, __func__);
+ if (rc)
+ return rc;
+
+ kref_get(&dax_dev->kref);
+ vma->vm_ops = &dax_dev_vm_ops;
+ vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
+ return 0;
+
+}
+
static const struct file_operations dax_fops = {
.llseek = noop_llseek,
.owner = THIS_MODULE,
+ .open = dax_dev_open,
+ .release = dax_dev_release,
+ .get_unmapped_area = dax_dev_get_unmapped_area,
+ .mmap = dax_dev_mmap,
};
static int __init dax_init(void)