1
0
Files
Greg Kroah-Hartman 8cd45b17eb Merge 4.9.187 into android-4.9
Changes in 4.9.187
	MIPS: ath79: fix ar933x uart parity mode
	MIPS: fix build on non-linux hosts
	arm64/efi: Mark __efistub_stext_offset as an absolute symbol explicitly
	dmaengine: imx-sdma: fix use-after-free on probe error path
	ath10k: Do not send probe response template for mesh
	ath9k: Check for errors when reading SREV register
	ath6kl: add some bounds checking
	ath: DFS JP domain W56 fixed pulse type 3 RADAR detection
	batman-adv: fix for leaked TVLV handler.
	media: dvb: usb: fix use after free in dvb_usb_device_exit
	crypto: talitos - fix skcipher failure due to wrong output IV
	media: marvell-ccic: fix DMA s/g desc number calculation
	media: vpss: fix a potential NULL pointer dereference
	media: media_device_enum_links32: clean a reserved field
	net: stmmac: dwmac1000: Clear unused address entries
	net: stmmac: dwmac4/5: Clear unused address entries
	signal/pid_namespace: Fix reboot_pid_ns to use send_sig not force_sig
	af_key: fix leaks in key_pol_get_resp and dump_sp.
	xfrm: Fix xfrm sel prefix length validation
	media: mc-device.c: don't memset __user pointer contents
	media: staging: media: davinci_vpfe: - Fix for memory leak if decoder initialization fails.
	net: phy: Check against net_device being NULL
	crypto: talitos - properly handle split ICV.
	crypto: talitos - Align SEC1 accesses to 32 bits boundaries.
	tua6100: Avoid build warnings.
	locking/lockdep: Fix merging of hlocks with non-zero references
	media: wl128x: Fix some error handling in fm_v4l2_init_video_device()
	cpupower : frequency-set -r option misses the last cpu in related cpu list
	net: fec: Do not use netdev messages too early
	net: axienet: Fix race condition causing TX hang
	s390/qdio: handle PENDING state for QEBSM devices
	perf cs-etm: Properly set the value of 'old' and 'head' in snapshot mode
	perf test 6: Fix missing kvm module load for s390
	gpio: omap: fix lack of irqstatus_raw0 for OMAP4
	gpio: omap: ensure irq is enabled before wakeup
	regmap: fix bulk writes on paged registers
	bpf: silence warning messages in core
	rcu: Force inlining of rcu_read_lock()
	blkcg, writeback: dead memcgs shouldn't contribute to writeback ownership arbitration
	xfrm: fix sa selector validation
	perf evsel: Make perf_evsel__name() accept a NULL argument
	vhost_net: disable zerocopy by default
	ipoib: correcly show a VF hardware address
	EDAC/sysfs: Fix memory leak when creating a csrow object
	ipsec: select crypto ciphers for xfrm_algo
	media: i2c: fix warning same module names
	ntp: Limit TAI-UTC offset
	timer_list: Guard procfs specific code
	acpi/arm64: ignore 5.1 FADTs that are reported as 5.0
	media: coda: fix mpeg2 sequence number handling
	media: coda: increment sequence offset for the last returned frame
	mt7601u: do not schedule rx_tasklet when the device has been disconnected
	x86/build: Add 'set -e' to mkcapflags.sh to delete broken capflags.c
	mt7601u: fix possible memory leak when the device is disconnected
	ath10k: fix PCIE device wake up failed
	perf tools: Increase MAX_NR_CPUS and MAX_CACHES
	libata: don't request sense data on !ZAC ATA devices
	clocksource/drivers/exynos_mct: Increase priority over ARM arch timer
	rslib: Fix decoding of shortened codes
	rslib: Fix handling of of caller provided syndrome
	ixgbe: Check DDM existence in transceiver before access
	crypto: asymmetric_keys - select CRYPTO_HASH where needed
	EDAC: Fix global-out-of-bounds write when setting edac_mc_poll_msec
	bcache: check c->gc_thread by IS_ERR_OR_NULL in cache_set_flush()
	iwlwifi: mvm: Drop large non sta frames
	net: usb: asix: init MAC address buffers
	gpiolib: Fix references to gpiod_[gs]et_*value_cansleep() variants
	Bluetooth: hci_bcsp: Fix memory leak in rx_skb
	Bluetooth: 6lowpan: search for destination address in all peers
	Bluetooth: Check state in l2cap_disconnect_rsp
	Bluetooth: validate BLE connection interval updates
	gtp: fix Illegal context switch in RCU read-side critical section.
	gtp: fix use-after-free in gtp_newlink()
	xen: let alloc_xenballooned_pages() fail if not enough memory free
	scsi: NCR5380: Reduce goto statements in NCR5380_select()
	scsi: NCR5380: Always re-enable reselection interrupt
	scsi: mac_scsi: Increase PIO/PDMA transfer length threshold
	crypto: ghash - fix unaligned memory access in ghash_setkey()
	crypto: arm64/sha1-ce - correct digest for empty data in finup
	crypto: arm64/sha2-ce - correct digest for empty data in finup
	crypto: chacha20poly1305 - fix atomic sleep when using async algorithm
	crypto: crypto4xx - fix a potential double free in ppc4xx_trng_probe
	Input: gtco - bounds check collection indent level
	regulator: s2mps11: Fix buck7 and buck8 wrong voltages
	arm64: tegra: Update Jetson TX1 GPU regulator timings
	iwlwifi: pcie: don't service an interrupt that was masked
	tracing/snapshot: Resize spare buffer if size changed
	NFSv4: Handle the special Linux file open access mode
	lib/scatterlist: Fix mapping iterator when sg->offset is greater than PAGE_SIZE
	ALSA: seq: Break too long mutex context in the write loop
	ALSA: hda/realtek: apply ALC891 headset fixup to one Dell machine
	media: v4l2: Test type instead of cfg->type in v4l2_ctrl_new_custom()
	media: coda: Remove unbalanced and unneeded mutex unlock
	KVM: x86/vPMU: refine kvm_pmu err msg when event creation failed
	arm64: tegra: Fix AGIC register range
	fs/proc/proc_sysctl.c: fix the default values of i_uid/i_gid on /proc/sys inodes.
	drm/nouveau/i2c: Enable i2c pads & busses during preinit
	padata: use smp_mb in padata_reorder to avoid orphaned padata jobs
	9p/virtio: Add cleanup path in p9_virtio_init
	PCI: Do not poll for PME if the device is in D3cold
	Btrfs: add missing inode version, ctime and mtime updates when punching hole
	libnvdimm/pfn: fix fsdax-mode namespace info-block zero-fields
	take floppy compat ioctls to sodding floppy.c
	floppy: fix div-by-zero in setup_format_params
	floppy: fix out-of-bounds read in next_valid_format
	floppy: fix invalid pointer dereference in drive_name
	floppy: fix out-of-bounds read in copy_buffer
	coda: pass the host file in vma->vm_file on mmap
	gpu: ipu-v3: ipu-ic: Fix saturation bit offset in TPMEM
	crypto: ccp - Validate the the error value used to index error messages
	PCI: hv: Delete the device earlier from hbus->children for hot-remove
	PCI: hv: Fix a use-after-free bug in hv_eject_device_work()
	crypto: caam - limit output IV to CBC to work around CTR mode DMA issue
	um: Allow building and running on older hosts
	um: Fix FP register size for XSTATE/XSAVE
	parisc: Ensure userspace privilege for ptraced processes in regset functions
	parisc: Fix kernel panic due invalid values in IAOQ0 or IAOQ1
	powerpc/32s: fix suspend/resume when IBATs 4-7 are used
	powerpc/watchpoint: Restore NV GPRs while returning from exception
	eCryptfs: fix a couple type promotion bugs
	intel_th: msu: Fix single mode with disabled IOMMU
	Bluetooth: Add SMP workaround Microsoft Surface Precision Mouse bug
	usb: Handle USB3 remote wakeup for LPM enabled devices correctly
	dm bufio: fix deadlock with loop device
	compiler.h, kasan: Avoid duplicating __read_once_size_nocheck()
	compiler.h: Add read_word_at_a_time() function.
	lib/strscpy: Shut up KASAN false-positives in strscpy()
	ext4: allow directory holes
	bnx2x: Prevent load reordering in tx completion processing
	bnx2x: Prevent ptp_task to be rescheduled indefinitely
	caif-hsi: fix possible deadlock in cfhsi_exit_module()
	igmp: fix memory leak in igmpv3_del_delrec()
	ipv4: don't set IPv6 only flags to IPv4 addresses
	net: bcmgenet: use promisc for unsupported filters
	net: dsa: mv88e6xxx: wait after reset deactivation
	net: neigh: fix multiple neigh timer scheduling
	net: openvswitch: fix csum updates for MPLS actions
	nfc: fix potential illegal memory access
	rxrpc: Fix send on a connected, but unbound socket
	sky2: Disable MSI on ASUS P6T
	vrf: make sure skb->data contains ip header to make routing
	macsec: fix use-after-free of skb during RX
	macsec: fix checksumming after decryption
	netrom: fix a memory leak in nr_rx_frame()
	netrom: hold sock when setting skb->destructor
	bonding: validate ip header before check IPPROTO_IGMP
	tcp: Reset bytes_acked and bytes_received when disconnecting
	net: bridge: mcast: fix stale nsrcs pointer in igmp3/mld2 report handling
	net: bridge: mcast: fix stale ipv6 hdr pointer when handling v6 query
	net: bridge: stp: don't cache eth dest pointer before skb pull
	perf/x86/amd/uncore: Rename 'L2' to 'LLC'
	perf/x86/amd/uncore: Get correct number of cores sharing last level cache
	perf/events/amd/uncore: Fix amd_uncore_llc ID to use pre-defined cpu_llc_id
	NFSv4: Fix open create exclusive when the server reboots
	nfsd: increase DRC cache limit
	nfsd: give out fewer session slots as limit approaches
	nfsd: fix performance-limiting session calculation
	nfsd: Fix overflow causing non-working mounts on 1 TB machines
	drm/panel: simple: Fix panel_simple_dsi_probe
	usb: core: hub: Disable hub-initiated U1/U2
	tty: max310x: Fix invalid baudrate divisors calculator
	pinctrl: rockchip: fix leaked of_node references
	tty: serial: cpm_uart - fix init when SMC is relocated
	drm/bridge: tc358767: read display_props in get_modes()
	drm/bridge: sii902x: pixel clock unit is 10kHz instead of 1kHz
	memstick: Fix error cleanup path of memstick_init
	tty/serial: digicolor: Fix digicolor-usart already registered warning
	tty: serial: msm_serial: avoid system lockup condition
	serial: 8250: Fix TX interrupt handling condition
	drm/virtio: Add memory barriers for capset cache.
	phy: renesas: rcar-gen2: Fix memory leak at error paths
	drm/rockchip: Properly adjust to a true clock in adjusted_mode
	tty: serial_core: Set port active bit in uart_port_activate
	usb: gadget: Zero ffs_io_data
	powerpc/pci/of: Fix OF flags parsing for 64bit BARs
	PCI: sysfs: Ignore lockdep for remove attribute
	kbuild: Add -Werror=unknown-warning-option to CLANG_FLAGS
	PCI: xilinx-nwl: Fix Multi MSI data programming
	iio: iio-utils: Fix possible incorrect mask calculation
	recordmcount: Fix spurious mcount entries on powerpc
	mfd: core: Set fwnode for created devices
	mfd: arizona: Fix undefined behavior
	mfd: hi655x-pmic: Fix missing return value check for devm_regmap_init_mmio_clk
	um: Silence lockdep complaint about mmap_sem
	powerpc/4xx/uic: clear pending interrupt after irq type/pol change
	RDMA/i40iw: Set queue pair state when being queried
	serial: sh-sci: Terminate TX DMA during buffer flushing
	serial: sh-sci: Fix TX DMA buffer flushing and workqueue races
	kallsyms: exclude kasan local symbols on s390
	perf test mmap-thread-lookup: Initialize variable to suppress memory sanitizer warning
	RDMA/rxe: Fill in wc byte_len with IB_WC_RECV_RDMA_WITH_IMM
	powerpc/boot: add {get, put}_unaligned_be32 to xz_config.h
	f2fs: avoid out-of-range memory access
	mailbox: handle failed named mailbox channel request
	powerpc/eeh: Handle hugepages in ioremap space
	sh: prevent warnings when using iounmap
	mm/kmemleak.c: fix check for softirq context
	9p: pass the correct prototype to read_cache_page
	mm/mmu_notifier: use hlist_add_head_rcu()
	locking/lockdep: Fix lock used or unused stats error
	locking/lockdep: Hide unused 'class' variable
	usb: wusbcore: fix unbalanced get/put cluster_id
	usb: pci-quirks: Correct AMD PLL quirk detection
	x86/sysfb_efi: Add quirks for some devices with swapped width and height
	x86/speculation/mds: Apply more accurate check on hypervisor platform
	hpet: Fix division by zero in hpet_time_div()
	ALSA: line6: Fix wrong altsetting for LINE6_PODHD500_1
	ALSA: hda - Add a conexant codec entry to let mute led work
	powerpc/tm: Fix oops on sigreturn on systems without TM
	access: avoid the RCU grace period for the temporary subjective credentials
	ipv6: check sk sk_type and protocol early in ip_mroute_set/getsockopt
	tcp: reset sk_send_head in tcp_write_queue_purge
	arm64: dts: marvell: Fix A37xx UART0 register size
	i2c: qup: fixed releasing dma without flush operation completion
	arm64: compat: Provide definition for COMPAT_SIGMINSTKSZ
	ISDN: hfcsusb: checking idx of ep configuration
	media: au0828: fix null dereference in error path
	media: cpia2_usb: first wake up, then free in disconnect
	media: radio-raremono: change devm_k*alloc to k*alloc
	Bluetooth: hci_uart: check for missing tty operations
	sched/fair: Don't free p->numa_faults with concurrent readers
	drivers/pps/pps.c: clear offset flags in PPS_SETPARAMS ioctl
	ceph: hold i_ceph_lock when removing caps for freeing inode
	Linux 4.9.187

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
2019-08-05 20:19:31 +03:00

718 lines
18 KiB
C

/*
* Copyright(c) 2013-2016 Intel Corporation. All rights reserved.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*/
#include <linux/memremap.h>
#include <linux/blkdev.h>
#include <linux/device.h>
#include <linux/genhd.h>
#include <linux/sizes.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include "nd-core.h"
#include "pfn.h"
#include "nd.h"
static void nd_pfn_release(struct device *dev)
{
struct nd_region *nd_region = to_nd_region(dev->parent);
struct nd_pfn *nd_pfn = to_nd_pfn(dev);
dev_dbg(dev, "%s\n", __func__);
nd_detach_ndns(&nd_pfn->dev, &nd_pfn->ndns);
ida_simple_remove(&nd_region->pfn_ida, nd_pfn->id);
kfree(nd_pfn->uuid);
kfree(nd_pfn);
}
static struct device_type nd_pfn_device_type = {
.name = "nd_pfn",
.release = nd_pfn_release,
};
bool is_nd_pfn(struct device *dev)
{
return dev ? dev->type == &nd_pfn_device_type : false;
}
EXPORT_SYMBOL(is_nd_pfn);
struct nd_pfn *to_nd_pfn(struct device *dev)
{
struct nd_pfn *nd_pfn = container_of(dev, struct nd_pfn, dev);
WARN_ON(!is_nd_pfn(dev));
return nd_pfn;
}
EXPORT_SYMBOL(to_nd_pfn);
static ssize_t mode_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
switch (nd_pfn->mode) {
case PFN_MODE_RAM:
return sprintf(buf, "ram\n");
case PFN_MODE_PMEM:
return sprintf(buf, "pmem\n");
default:
return sprintf(buf, "none\n");
}
}
static ssize_t mode_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc = 0;
device_lock(dev);
nvdimm_bus_lock(dev);
if (dev->driver)
rc = -EBUSY;
else {
size_t n = len - 1;
if (strncmp(buf, "pmem\n", n) == 0
|| strncmp(buf, "pmem", n) == 0) {
nd_pfn->mode = PFN_MODE_PMEM;
} else if (strncmp(buf, "ram\n", n) == 0
|| strncmp(buf, "ram", n) == 0)
nd_pfn->mode = PFN_MODE_RAM;
else if (strncmp(buf, "none\n", n) == 0
|| strncmp(buf, "none", n) == 0)
nd_pfn->mode = PFN_MODE_NONE;
else
rc = -EINVAL;
}
dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__,
rc, buf, buf[len - 1] == '\n' ? "" : "\n");
nvdimm_bus_unlock(dev);
device_unlock(dev);
return rc ? rc : len;
}
static DEVICE_ATTR_RW(mode);
static ssize_t align_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
return sprintf(buf, "%ld\n", nd_pfn->align);
}
static ssize_t __align_store(struct nd_pfn *nd_pfn, const char *buf)
{
unsigned long val;
int rc;
rc = kstrtoul(buf, 0, &val);
if (rc)
return rc;
if (!is_power_of_2(val) || val < PAGE_SIZE || val > SZ_1G)
return -EINVAL;
if (nd_pfn->dev.driver)
return -EBUSY;
else
nd_pfn->align = val;
return 0;
}
static ssize_t align_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc;
device_lock(dev);
nvdimm_bus_lock(dev);
rc = __align_store(nd_pfn, buf);
dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__,
rc, buf, buf[len - 1] == '\n' ? "" : "\n");
nvdimm_bus_unlock(dev);
device_unlock(dev);
return rc ? rc : len;
}
static DEVICE_ATTR_RW(align);
static ssize_t uuid_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
if (nd_pfn->uuid)
return sprintf(buf, "%pUb\n", nd_pfn->uuid);
return sprintf(buf, "\n");
}
static ssize_t uuid_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc;
device_lock(dev);
rc = nd_uuid_store(dev, &nd_pfn->uuid, buf, len);
dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__,
rc, buf, buf[len - 1] == '\n' ? "" : "\n");
device_unlock(dev);
return rc ? rc : len;
}
static DEVICE_ATTR_RW(uuid);
static ssize_t namespace_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc;
nvdimm_bus_lock(dev);
rc = sprintf(buf, "%s\n", nd_pfn->ndns
? dev_name(&nd_pfn->ndns->dev) : "");
nvdimm_bus_unlock(dev);
return rc;
}
static ssize_t namespace_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc;
device_lock(dev);
nvdimm_bus_lock(dev);
rc = nd_namespace_store(dev, &nd_pfn->ndns, buf, len);
dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__,
rc, buf, buf[len - 1] == '\n' ? "" : "\n");
nvdimm_bus_unlock(dev);
device_unlock(dev);
return rc;
}
static DEVICE_ATTR_RW(namespace);
static ssize_t resource_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc;
device_lock(dev);
if (dev->driver) {
struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
u64 offset = __le64_to_cpu(pfn_sb->dataoff);
struct nd_namespace_common *ndns = nd_pfn->ndns;
u32 start_pad = __le32_to_cpu(pfn_sb->start_pad);
struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
rc = sprintf(buf, "%#llx\n", (unsigned long long) nsio->res.start
+ start_pad + offset);
} else {
/* no address to convey if the pfn instance is disabled */
rc = -ENXIO;
}
device_unlock(dev);
return rc;
}
static DEVICE_ATTR_RO(resource);
static ssize_t size_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc;
device_lock(dev);
if (dev->driver) {
struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
u64 offset = __le64_to_cpu(pfn_sb->dataoff);
struct nd_namespace_common *ndns = nd_pfn->ndns;
u32 start_pad = __le32_to_cpu(pfn_sb->start_pad);
u32 end_trunc = __le32_to_cpu(pfn_sb->end_trunc);
struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
rc = sprintf(buf, "%llu\n", (unsigned long long)
resource_size(&nsio->res) - start_pad
- end_trunc - offset);
} else {
/* no size to convey if the pfn instance is disabled */
rc = -ENXIO;
}
device_unlock(dev);
return rc;
}
static DEVICE_ATTR_RO(size);
static struct attribute *nd_pfn_attributes[] = {
&dev_attr_mode.attr,
&dev_attr_namespace.attr,
&dev_attr_uuid.attr,
&dev_attr_align.attr,
&dev_attr_resource.attr,
&dev_attr_size.attr,
NULL,
};
static umode_t pfn_visible(struct kobject *kobj, struct attribute *a, int n)
{
if (a == &dev_attr_resource.attr)
return 0400;
return a->mode;
}
struct attribute_group nd_pfn_attribute_group = {
.attrs = nd_pfn_attributes,
.is_visible = pfn_visible,
};
static const struct attribute_group *nd_pfn_attribute_groups[] = {
&nd_pfn_attribute_group,
&nd_device_attribute_group,
&nd_numa_attribute_group,
NULL,
};
struct device *nd_pfn_devinit(struct nd_pfn *nd_pfn,
struct nd_namespace_common *ndns)
{
struct device *dev = &nd_pfn->dev;
if (!nd_pfn)
return NULL;
nd_pfn->mode = PFN_MODE_NONE;
nd_pfn->align = HPAGE_SIZE;
dev = &nd_pfn->dev;
device_initialize(&nd_pfn->dev);
if (ndns && !__nd_attach_ndns(&nd_pfn->dev, ndns, &nd_pfn->ndns)) {
dev_dbg(&ndns->dev, "%s failed, already claimed by %s\n",
__func__, dev_name(ndns->claim));
put_device(dev);
return NULL;
}
return dev;
}
static struct nd_pfn *nd_pfn_alloc(struct nd_region *nd_region)
{
struct nd_pfn *nd_pfn;
struct device *dev;
nd_pfn = kzalloc(sizeof(*nd_pfn), GFP_KERNEL);
if (!nd_pfn)
return NULL;
nd_pfn->id = ida_simple_get(&nd_region->pfn_ida, 0, 0, GFP_KERNEL);
if (nd_pfn->id < 0) {
kfree(nd_pfn);
return NULL;
}
dev = &nd_pfn->dev;
dev_set_name(dev, "pfn%d.%d", nd_region->id, nd_pfn->id);
dev->groups = nd_pfn_attribute_groups;
dev->type = &nd_pfn_device_type;
dev->parent = &nd_region->dev;
return nd_pfn;
}
struct device *nd_pfn_create(struct nd_region *nd_region)
{
struct nd_pfn *nd_pfn;
struct device *dev;
if (!is_nd_pmem(&nd_region->dev))
return NULL;
nd_pfn = nd_pfn_alloc(nd_region);
dev = nd_pfn_devinit(nd_pfn, NULL);
__nd_device_register(dev);
return dev;
}
/**
* nd_pfn_validate - read and validate info-block
* @nd_pfn: fsdax namespace runtime state / properties
* @sig: 'devdax' or 'fsdax' signature
*
* Upon return the info-block buffer contents (->pfn_sb) are
* indeterminate when validation fails, and a coherent info-block
* otherwise.
*/
int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
{
u64 checksum, offset;
enum nd_pfn_mode mode;
struct nd_namespace_io *nsio;
unsigned long align, start_pad;
struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
struct nd_namespace_common *ndns = nd_pfn->ndns;
const u8 *parent_uuid = nd_dev_to_uuid(&ndns->dev);
if (!pfn_sb || !ndns)
return -ENODEV;
if (!is_nd_pmem(nd_pfn->dev.parent))
return -ENODEV;
if (nvdimm_read_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb)))
return -ENXIO;
if (memcmp(pfn_sb->signature, sig, PFN_SIG_LEN) != 0)
return -ENODEV;
checksum = le64_to_cpu(pfn_sb->checksum);
pfn_sb->checksum = 0;
if (checksum != nd_sb_checksum((struct nd_gen_sb *) pfn_sb))
return -ENODEV;
pfn_sb->checksum = cpu_to_le64(checksum);
if (memcmp(pfn_sb->parent_uuid, parent_uuid, 16) != 0)
return -ENODEV;
if (__le16_to_cpu(pfn_sb->version_minor) < 1) {
pfn_sb->start_pad = 0;
pfn_sb->end_trunc = 0;
}
if (__le16_to_cpu(pfn_sb->version_minor) < 2)
pfn_sb->align = 0;
switch (le32_to_cpu(pfn_sb->mode)) {
case PFN_MODE_RAM:
case PFN_MODE_PMEM:
break;
default:
return -ENXIO;
}
align = le32_to_cpu(pfn_sb->align);
offset = le64_to_cpu(pfn_sb->dataoff);
start_pad = le32_to_cpu(pfn_sb->start_pad);
if (align == 0)
align = 1UL << ilog2(offset);
mode = le32_to_cpu(pfn_sb->mode);
if (!nd_pfn->uuid) {
/*
* When probing a namepace via nd_pfn_probe() the uuid
* is NULL (see: nd_pfn_devinit()) we init settings from
* pfn_sb
*/
nd_pfn->uuid = kmemdup(pfn_sb->uuid, 16, GFP_KERNEL);
if (!nd_pfn->uuid)
return -ENOMEM;
nd_pfn->align = align;
nd_pfn->mode = mode;
} else {
/*
* When probing a pfn / dax instance we validate the
* live settings against the pfn_sb
*/
if (memcmp(nd_pfn->uuid, pfn_sb->uuid, 16) != 0)
return -ENODEV;
/*
* If the uuid validates, but other settings mismatch
* return EINVAL because userspace has managed to change
* the configuration without specifying new
* identification.
*/
if (nd_pfn->align != align || nd_pfn->mode != mode) {
dev_err(&nd_pfn->dev,
"init failed, settings mismatch\n");
dev_dbg(&nd_pfn->dev, "align: %lx:%lx mode: %d:%d\n",
nd_pfn->align, align, nd_pfn->mode,
mode);
return -EINVAL;
}
}
if (align > nvdimm_namespace_capacity(ndns)) {
dev_err(&nd_pfn->dev, "alignment: %lx exceeds capacity %llx\n",
align, nvdimm_namespace_capacity(ndns));
return -EINVAL;
}
/*
* These warnings are verbose because they can only trigger in
* the case where the physical address alignment of the
* namespace has changed since the pfn superblock was
* established.
*/
nsio = to_nd_namespace_io(&ndns->dev);
if (offset >= resource_size(&nsio->res)) {
dev_err(&nd_pfn->dev, "pfn array size exceeds capacity of %s\n",
dev_name(&ndns->dev));
return -EBUSY;
}
if ((align && !IS_ALIGNED(nsio->res.start + offset + start_pad, align))
|| !IS_ALIGNED(offset, PAGE_SIZE)) {
dev_err(&nd_pfn->dev,
"bad offset: %#llx dax disabled align: %#lx\n",
offset, align);
return -ENXIO;
}
return 0;
}
EXPORT_SYMBOL(nd_pfn_validate);
int nd_pfn_probe(struct device *dev, struct nd_namespace_common *ndns)
{
int rc;
struct nd_pfn *nd_pfn;
struct device *pfn_dev;
struct nd_pfn_sb *pfn_sb;
struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
if (ndns->force_raw)
return -ENODEV;
nvdimm_bus_lock(&ndns->dev);
nd_pfn = nd_pfn_alloc(nd_region);
pfn_dev = nd_pfn_devinit(nd_pfn, ndns);
nvdimm_bus_unlock(&ndns->dev);
if (!pfn_dev)
return -ENOMEM;
pfn_sb = devm_kmalloc(dev, sizeof(*pfn_sb), GFP_KERNEL);
nd_pfn = to_nd_pfn(pfn_dev);
nd_pfn->pfn_sb = pfn_sb;
rc = nd_pfn_validate(nd_pfn, PFN_SIG);
dev_dbg(dev, "%s: pfn: %s\n", __func__,
rc == 0 ? dev_name(pfn_dev) : "<none>");
if (rc < 0) {
__nd_detach_ndns(pfn_dev, &nd_pfn->ndns);
put_device(pfn_dev);
} else
__nd_device_register(pfn_dev);
return rc;
}
EXPORT_SYMBOL(nd_pfn_probe);
/*
* We hotplug memory at section granularity, pad the reserved area from
* the previous section base to the namespace base address.
*/
static unsigned long init_altmap_base(resource_size_t base)
{
unsigned long base_pfn = PHYS_PFN(base);
return PFN_SECTION_ALIGN_DOWN(base_pfn);
}
static unsigned long init_altmap_reserve(resource_size_t base)
{
unsigned long reserve = PFN_UP(SZ_8K);
unsigned long base_pfn = PHYS_PFN(base);
reserve += base_pfn - PFN_SECTION_ALIGN_DOWN(base_pfn);
return reserve;
}
static struct vmem_altmap *__nvdimm_setup_pfn(struct nd_pfn *nd_pfn,
struct resource *res, struct vmem_altmap *altmap)
{
struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
u64 offset = le64_to_cpu(pfn_sb->dataoff);
u32 start_pad = __le32_to_cpu(pfn_sb->start_pad);
u32 end_trunc = __le32_to_cpu(pfn_sb->end_trunc);
struct nd_namespace_common *ndns = nd_pfn->ndns;
struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
resource_size_t base = nsio->res.start + start_pad;
struct vmem_altmap __altmap = {
.base_pfn = init_altmap_base(base),
.reserve = init_altmap_reserve(base),
};
memcpy(res, &nsio->res, sizeof(*res));
res->start += start_pad;
res->end -= end_trunc;
if (nd_pfn->mode == PFN_MODE_RAM) {
if (offset < SZ_8K)
return ERR_PTR(-EINVAL);
nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns);
altmap = NULL;
} else if (nd_pfn->mode == PFN_MODE_PMEM) {
nd_pfn->npfns = PFN_SECTION_ALIGN_UP((resource_size(res)
- offset) / PAGE_SIZE);
if (le64_to_cpu(nd_pfn->pfn_sb->npfns) > nd_pfn->npfns)
dev_info(&nd_pfn->dev,
"number of pfns truncated from %lld to %ld\n",
le64_to_cpu(nd_pfn->pfn_sb->npfns),
nd_pfn->npfns);
memcpy(altmap, &__altmap, sizeof(*altmap));
altmap->free = PHYS_PFN(offset - SZ_8K);
altmap->alloc = 0;
} else
return ERR_PTR(-ENXIO);
return altmap;
}
static u64 phys_pmem_align_down(struct nd_pfn *nd_pfn, u64 phys)
{
return min_t(u64, PHYS_SECTION_ALIGN_DOWN(phys),
ALIGN_DOWN(phys, nd_pfn->align));
}
static int nd_pfn_init(struct nd_pfn *nd_pfn)
{
u32 dax_label_reserve = is_nd_dax(&nd_pfn->dev) ? SZ_128K : 0;
struct nd_namespace_common *ndns = nd_pfn->ndns;
u32 start_pad = 0, end_trunc = 0;
resource_size_t start, size;
struct nd_namespace_io *nsio;
struct nd_region *nd_region;
struct nd_pfn_sb *pfn_sb;
unsigned long npfns;
phys_addr_t offset;
const char *sig;
u64 checksum;
int rc;
pfn_sb = devm_kmalloc(&nd_pfn->dev, sizeof(*pfn_sb), GFP_KERNEL);
if (!pfn_sb)
return -ENOMEM;
nd_pfn->pfn_sb = pfn_sb;
if (is_nd_dax(&nd_pfn->dev))
sig = DAX_SIG;
else
sig = PFN_SIG;
rc = nd_pfn_validate(nd_pfn, sig);
if (rc != -ENODEV)
return rc;
/* no info block, do init */;
memset(pfn_sb, 0, sizeof(*pfn_sb));
nd_region = to_nd_region(nd_pfn->dev.parent);
if (nd_region->ro) {
dev_info(&nd_pfn->dev,
"%s is read-only, unable to init metadata\n",
dev_name(&nd_region->dev));
return -ENXIO;
}
memset(pfn_sb, 0, sizeof(*pfn_sb));
/*
* Check if pmem collides with 'System RAM' when section aligned and
* trim it accordingly
*/
nsio = to_nd_namespace_io(&ndns->dev);
start = PHYS_SECTION_ALIGN_DOWN(nsio->res.start);
size = resource_size(&nsio->res);
if (region_intersects(start, size, IORESOURCE_SYSTEM_RAM,
IORES_DESC_NONE) == REGION_MIXED) {
start = nsio->res.start;
start_pad = PHYS_SECTION_ALIGN_UP(start) - start;
}
start = nsio->res.start;
size = PHYS_SECTION_ALIGN_UP(start + size) - start;
if (region_intersects(start, size, IORESOURCE_SYSTEM_RAM,
IORES_DESC_NONE) == REGION_MIXED
|| !IS_ALIGNED(start + resource_size(&nsio->res),
nd_pfn->align)) {
size = resource_size(&nsio->res);
end_trunc = start + size - phys_pmem_align_down(nd_pfn,
start + size);
}
if (start_pad + end_trunc)
dev_info(&nd_pfn->dev, "%s alignment collision, truncate %d bytes\n",
dev_name(&ndns->dev), start_pad + end_trunc);
/*
* Note, we use 64 here for the standard size of struct page,
* debugging options may cause it to be larger in which case the
* implementation will limit the pfns advertised through
* ->direct_access() to those that are included in the memmap.
*/
start += start_pad;
size = resource_size(&nsio->res);
npfns = PFN_SECTION_ALIGN_UP((size - start_pad - end_trunc - SZ_8K)
/ PAGE_SIZE);
if (nd_pfn->mode == PFN_MODE_PMEM) {
/*
* vmemmap_populate_hugepages() allocates the memmap array in
* HPAGE_SIZE chunks.
*/
offset = ALIGN(start + SZ_8K + 64 * npfns + dax_label_reserve,
max(nd_pfn->align, HPAGE_SIZE)) - start;
} else if (nd_pfn->mode == PFN_MODE_RAM)
offset = ALIGN(start + SZ_8K + dax_label_reserve,
nd_pfn->align) - start;
else
return -ENXIO;
if (offset + start_pad + end_trunc >= size) {
dev_err(&nd_pfn->dev, "%s unable to satisfy requested alignment\n",
dev_name(&ndns->dev));
return -ENXIO;
}
npfns = (size - offset - start_pad - end_trunc) / SZ_4K;
pfn_sb->mode = cpu_to_le32(nd_pfn->mode);
pfn_sb->dataoff = cpu_to_le64(offset);
pfn_sb->npfns = cpu_to_le64(npfns);
memcpy(pfn_sb->signature, sig, PFN_SIG_LEN);
memcpy(pfn_sb->uuid, nd_pfn->uuid, 16);
memcpy(pfn_sb->parent_uuid, nd_dev_to_uuid(&ndns->dev), 16);
pfn_sb->version_major = cpu_to_le16(1);
pfn_sb->version_minor = cpu_to_le16(3);
pfn_sb->start_pad = cpu_to_le32(start_pad);
pfn_sb->end_trunc = cpu_to_le32(end_trunc);
pfn_sb->align = cpu_to_le32(nd_pfn->align);
checksum = nd_sb_checksum((struct nd_gen_sb *) pfn_sb);
pfn_sb->checksum = cpu_to_le64(checksum);
return nvdimm_write_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb));
}
/*
* Determine the effective resource range and vmem_altmap from an nd_pfn
* instance.
*/
struct vmem_altmap *nvdimm_setup_pfn(struct nd_pfn *nd_pfn,
struct resource *res, struct vmem_altmap *altmap)
{
int rc;
if (!nd_pfn->uuid || !nd_pfn->ndns)
return ERR_PTR(-ENODEV);
rc = nd_pfn_init(nd_pfn);
if (rc)
return ERR_PTR(rc);
/* we need a valid pfn_sb before we can init a vmem_altmap */
return __nvdimm_setup_pfn(nd_pfn, res, altmap);
}
EXPORT_SYMBOL_GPL(nvdimm_setup_pfn);