int hns_roce_alloc_pd(struct ib_pd *ibpd, struct ib_ucontext *context,
struct ib_udata *udata)
{
struct ib_device *ib_dev = ibpd->device;
struct hns_roce_dev *hr_dev = to_hr_dev(ib_dev);
struct device *dev = hr_dev->dev;
struct hns_roce_pd *pd = to_hr_pd(ibpd);
int ret;
ret = hns_roce_pd_alloc(to_hr_dev(ib_dev), &pd->pdn);
if (ret) {
dev_err(dev, "[alloc_pd]hns_roce_pd_alloc failed!\n");
return ret;
}
if (context) {
struct hns_roce_ib_alloc_pd_resp uresp = {.pdn = pd->pdn};
if (ib_copy_to_udata(udata, &uresp, sizeof(uresp))) {
hns_roce_pd_free(to_hr_dev(ib_dev), pd->pdn);
dev_err(dev, "[alloc_pd]ib_copy_to_udata failed!\n");
return -EFAULT;
}
}
return 0;
}
EXPORT_SYMBOL_GPL(hns_roce_alloc_pd);
void hns_roce_dealloc_pd(struct ib_pd *pd)
{
hns_roce_pd_free(to_hr_dev(pd->device), to_hr_pd(pd)->pdn);
}
/*
* Set up a pNFS Data Server client over NFSv3.
*
* Return any existing nfs_client that matches server address,port,version
* and minorversion.
*
* For a new nfs_client, use a soft mount (default), a low retrans and a
* low timeout interval so that if a connection is lost, we retry through
* the MDS.
*/
struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv,
const struct sockaddr *ds_addr, int ds_addrlen,
int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans)
{
struct rpc_timeout ds_timeout;
struct nfs_client *mds_clp = mds_srv->nfs_client;
struct nfs_client_initdata cl_init = {
.addr = ds_addr,
.addrlen = ds_addrlen,
.nodename = mds_clp->cl_rpcclient->cl_nodename,
.ip_addr = mds_clp->cl_ipaddr,
.nfs_mod = &nfs_v3,
.proto = ds_proto,
.net = mds_clp->cl_net,
.timeparms = &ds_timeout,
.cred = mds_srv->cred,
};
struct nfs_client *clp;
char buf[INET6_ADDRSTRLEN + 1];
/* fake a hostname because lockd wants it */
if (rpc_ntop(ds_addr, buf, sizeof(buf)) <= 0)
return ERR_PTR(-EINVAL);
cl_init.hostname = buf;
if (mds_srv->flags & NFS_MOUNT_NORESVPORT)
set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
/* Use the MDS nfs_client cl_ipaddr. */
nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);
clp = nfs_get_client(&cl_init);
return clp;
}
EXPORT_SYMBOL_GPL(nfs3_set_ds_client);
void gcore_input_report_key(struct gcore_data *gdata, int scancode, int value)
{
struct input_dev *idev = gdata->input_dev;
int error;
struct input_keymap_entry ke = {
.flags = 0,
.len = sizeof(scancode),
};
*((int *) ke.scancode) = scancode;
error = input_get_keycode(idev, &ke);
if (!error && ke.keycode != KEY_UNKNOWN && ke.keycode != KEY_RESERVED) {
/* Only report mapped keys */
input_report_key(idev, ke.keycode, value);
} else if (!!value) {
/* Or report MSC_SCAN on keypress of an unmapped key */
input_event(idev, EV_MSC, MSC_SCAN, scancode);
}
}
EXPORT_SYMBOL_GPL(gcore_input_report_key);
void gcore_input_remove(struct gcore_data *gdata)
{
input_unregister_device(gdata->input_dev);
kfree(gdata->input_dev->keycode);
}
/**
* dax_zero_page_range - zero a range within a page of a DAX file
* @inode: The file being truncated
* @from: The file offset that is being truncated to
* @length: The number of bytes to zero
* @get_block: The filesystem method used to translate file offsets to blocks
*
* This function can be called by a filesystem when it is zeroing part of a
* page in a DAX file. This is intended for hole-punch operations. If
* you are truncating a file, the helper function dax_truncate_page() may be
* more convenient.
*
* We work in terms of PAGE_SIZE here for commonality with
* block_truncate_page(), but we could go down to PAGE_SIZE if the filesystem
* took care of disposing of the unnecessary blocks. Even if the filesystem
* block size is smaller than PAGE_SIZE, we have to zero the rest of the page
* since the file might be mmapped.
*/
int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length,
get_block_t get_block)
{
struct buffer_head bh;
pgoff_t index = from >> PAGE_SHIFT;
unsigned offset = from & (PAGE_SIZE-1);
int err;
/* Block boundary? Nothing to do */
if (!length)
return 0;
BUG_ON((offset + length) > PAGE_SIZE);
memset(&bh, 0, sizeof(bh));
bh.b_bdev = inode->i_sb->s_bdev;
bh.b_size = PAGE_SIZE;
err = get_block(inode, index, &bh, 0);
if (err < 0)
return err;
if (buffer_written(&bh)) {
struct block_device *bdev = bh.b_bdev;
struct blk_dax_ctl dax = {
.sector = to_sector(&bh, inode),
.size = PAGE_SIZE,
};
if (dax_map_atomic(bdev, &dax) < 0)
return PTR_ERR(dax.addr);
clear_pmem(dax.addr + offset, length);
wmb_pmem();
dax_unmap_atomic(bdev, &dax);
}
return 0;
}
EXPORT_SYMBOL_GPL(dax_zero_page_range);
/**
* dax_truncate_page - handle a partial page being truncated in a DAX file
* @inode: The file being truncated
* @from: The file offset that is being truncated to
* @get_block: The filesystem method used to translate file offsets to blocks
*
* Similar to block_truncate_page(), this function can be called by a
* filesystem when it is truncating a DAX file to handle the partial page.
*
* We work in terms of PAGE_SIZE here for commonality with
* block_truncate_page(), but we could go down to PAGE_SIZE if the filesystem
* took care of disposing of the unnecessary blocks. Even if the filesystem
* block size is smaller than PAGE_SIZE, we have to zero the rest of the page
* since the file might be mmapped.
*/
int dax_truncate_page(struct inode *inode, loff_t from, get_block_t get_block)
{
unsigned length = PAGE_ALIGN(from) - from;
return dax_zero_page_range(inode, from, length, get_block);
}
/**
* ad_sd_write_reg() - Write a register
*
* @sigma_delta: The sigma delta device
* @reg: Address of the register
* @size: Size of the register (0-3)
* @val: Value to write to the register
*
* Returns 0 on success, an error code otherwise.
**/
int ad_sd_write_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg,
unsigned int size, unsigned int val)
{
uint8_t *data = sigma_delta->data;
struct spi_transfer t = {
.tx_buf = data,
.len = size + 1,
.cs_change = sigma_delta->bus_locked,
};
struct spi_message m;
int ret;
data[0] = (reg << sigma_delta->info->addr_shift) | sigma_delta->comm;
switch (size) {
case 3:
data[1] = val >> 16;
data[2] = val >> 8;
data[3] = val;
break;
case 2:
put_unaligned_be16(val, &data[1]);
break;
case 1:
data[1] = val;
break;
case 0:
break;
default:
return -EINVAL;
}
spi_message_init(&m);
spi_message_add_tail(&t, &m);
if (sigma_delta->bus_locked)
ret = spi_sync_locked(sigma_delta->spi, &m);
else
ret = spi_sync(sigma_delta->spi, &m);
return ret;
}
EXPORT_SYMBOL_GPL(ad_sd_write_reg);
static int ad_sd_read_reg_raw(struct ad_sigma_delta *sigma_delta,
unsigned int reg, unsigned int size, uint8_t *val)
{
uint8_t *data = sigma_delta->data;
int ret;
struct spi_transfer t[] = {
{
.tx_buf = data,
.len = 1,
}, {
.rx_buf = val,
int rave_sp_exec(struct rave_sp *sp,
void *__data, size_t data_size,
void *reply_data, size_t reply_data_size)
{
struct rave_sp_reply reply = {
.data = reply_data,
.length = reply_data_size,
.received = COMPLETION_INITIALIZER_ONSTACK(reply.received),
};
unsigned char *data = __data;
int command, ret = 0;
u8 ackid;
command = sp->variant->cmd.translate(data[0]);
if (command < 0)
return command;
ackid = atomic_inc_return(&sp->ackid);
reply.ackid = ackid;
reply.code = rave_sp_reply_code((u8)command),
mutex_lock(&sp->bus_lock);
mutex_lock(&sp->reply_lock);
sp->reply = &reply;
mutex_unlock(&sp->reply_lock);
data[0] = command;
data[1] = ackid;
rave_sp_write(sp, data, data_size);
if (!wait_for_completion_timeout(&reply.received, HZ)) {
dev_err(&sp->serdev->dev, "Command timeout\n");
ret = -ETIMEDOUT;
mutex_lock(&sp->reply_lock);
sp->reply = NULL;
mutex_unlock(&sp->reply_lock);
}
mutex_unlock(&sp->bus_lock);
return ret;
}
EXPORT_SYMBOL_GPL(rave_sp_exec);
static void rave_sp_receive_event(struct rave_sp *sp,
const unsigned char *data, size_t length)
{
u8 cmd[] = {
[0] = rave_sp_reply_code(data[0]),
[1] = data[1],
};
static int acpi_ec_query_unlocked(struct acpi_ec *ec, u8 * data)
{
int result;
u8 d;
struct transaction t = {.command = ACPI_EC_COMMAND_QUERY,
.wdata = NULL, .rdata = &d,
.wlen = 0, .rlen = 1};
if (!ec || !data)
return -EINVAL;
/*
* Query the EC to find out which _Qxx method we need to evaluate.
* Note that successful completion of the query causes the ACPI_EC_SCI
* bit to be cleared (and thus clearing the interrupt source).
*/
result = acpi_ec_transaction_unlocked(ec, &t);
if (result)
return result;
if (!d)
return -ENODATA;
*data = d;
return 0;
}
/* --------------------------------------------------------------------------
Event Management
-------------------------------------------------------------------------- */
int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit,
acpi_handle handle, acpi_ec_query_func func,
void *data)
{
struct acpi_ec_query_handler *handler =
kzalloc(sizeof(struct acpi_ec_query_handler), GFP_KERNEL);
if (!handler)
return -ENOMEM;
handler->query_bit = query_bit;
handler->handle = handle;
handler->func = func;
handler->data = data;
mutex_lock(&ec->lock);
list_add(&handler->node, &ec->list);
mutex_unlock(&ec->lock);
return 0;
}
EXPORT_SYMBOL_GPL(acpi_ec_add_query_handler);
void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit)
{
struct acpi_ec_query_handler *handler, *tmp;
mutex_lock(&ec->lock);
list_for_each
void save_stack_trace_tsk(struct task_struct *task, struct stack_trace *trace)
{
struct stack_trace_data trace_data = {
.trace = trace,
.skip = trace->skip,
};
walk_stackframe(stack_pointer(task), stack_trace_cb, &trace_data);
}
EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
void save_stack_trace(struct stack_trace *trace)
{
save_stack_trace_tsk(current, trace);
}
/**
* nfs_do_submount - set up mountpoint when crossing a filesystem boundary
* @dentry - parent directory
* @fh - filehandle for new root dentry
* @fattr - attributes for new root inode
* @authflavor - security flavor to use when performing the mount
*
*/
struct vfsmount *nfs_do_submount(struct dentry *dentry, struct nfs_fh *fh,
struct nfs_fattr *fattr, rpc_authflavor_t authflavor)
{
struct nfs_clone_mount mountdata = {
.sb = dentry->d_sb,
.dentry = dentry,
.fh = fh,
.fattr = fattr,
.authflavor = authflavor,
};
struct vfsmount *mnt = ERR_PTR(-ENOMEM);
char *page = (char *) __get_free_page(GFP_USER);
char *devname;
dprintk("--> nfs_do_submount()\n");
dprintk("%s: submounting on %s/%s\n", __func__,
dentry->d_parent->d_name.name,
dentry->d_name.name);
if (page == NULL)
goto out;
devname = nfs_devname(dentry, page, PAGE_SIZE);
mnt = (struct vfsmount *)devname;
if (IS_ERR(devname))
goto free_page;
mnt = nfs_do_clone_mount(NFS_SB(dentry->d_sb), devname, &mountdata);
free_page:
free_page((unsigned long)page);
out:
dprintk("%s: done\n", __func__);
dprintk("<-- nfs_do_submount() = %p\n", mnt);
return mnt;
}
EXPORT_SYMBOL_GPL(nfs_do_submount);
struct vfsmount *nfs_submount(struct nfs_server *server, struct dentry *dentry,
struct nfs_fh *fh, struct nfs_fattr *fattr)
{
int err;
struct dentry *parent = dget_parent(dentry);
/* Look it up again to get its attributes */
err = server->nfs_client->rpc_ops->lookup(parent->d_inode, &dentry->d_name, fh, fattr);
dput(parent);
if (err != 0)
return ERR_PTR(err);
return nfs_do_submount(dentry, fh, fattr, server->client->cl_auth->au_flavor);
}
int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id,
u32 ts, u32 tsage, long expires, u32 error)
{
struct rta_cacheinfo ci = {
.rta_lastuse = jiffies_to_clock_t(jiffies - dst->lastuse),
.rta_used = dst->__use,
.rta_clntref = atomic_read(&(dst->__refcnt)),
.rta_error = error,
.rta_id = id,
.rta_ts = ts,
.rta_tsage = tsage,
};
if (expires)
ci.rta_expires = jiffies_to_clock_t(expires);
return nla_put(skb, RTA_CACHEINFO, sizeof(ci), &ci);
}
EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo);
static void set_operstate(struct net_device *dev, unsigned char transition)
{
unsigned char operstate = dev->operstate;
switch(transition) {
case IF_OPER_UP:
if ((operstate == IF_OPER_DORMANT ||
operstate == IF_OPER_UNKNOWN) &&
!netif_dormant(dev))
operstate = IF_OPER_UP;
break;
case IF_OPER_DORMANT:
if (operstate == IF_OPER_UP ||
operstate == IF_OPER_UNKNOWN)
operstate = IF_OPER_DORMANT;
break;
}
if (dev->operstate != operstate) {
write_lock_bh(&dev_base_lock);
dev->operstate = operstate;
write_unlock_bh(&dev_base_lock);
netdev_state_change(dev);
}
}
static int pmf_get_detect(struct gpio_runtime *rt,
enum notify_type type)
{
char *name;
int err = -EBUSY, ret;
struct pmf_args args = { .count = 1, .u[0].p = &ret };
switch (type) {
case AOA_NOTIFY_HEADPHONE:
name = "headphone-detect";
break;
case AOA_NOTIFY_LINE_IN:
name = "linein-detect";
break;
case AOA_NOTIFY_LINE_OUT:
name = "lineout-detect";
break;
default:
return -EINVAL;
}
err = pmf_call_function(rt->node, name, &args);
if (err)
return err;
return ret;
}
static struct gpio_methods methods = {
.init = pmf_gpio_init,
.exit = pmf_gpio_exit,
.all_amps_off = pmf_gpio_all_amps_off,
.all_amps_restore = pmf_gpio_all_amps_restore,
.set_headphone = pmf_gpio_set_headphone,
.set_speakers = pmf_gpio_set_amp,
.set_lineout = pmf_gpio_set_lineout,
.set_hw_reset = pmf_gpio_set_hw_reset,
.get_headphone = pmf_gpio_get_headphone,
.get_speakers = pmf_gpio_get_amp,
.get_lineout = pmf_gpio_get_lineout,
.set_notify = pmf_set_notify,
.get_detect = pmf_get_detect,
};
struct gpio_methods *pmf_gpio_methods = &methods;
EXPORT_SYMBOL_GPL(pmf_gpio_methods);
/* Extract info for Tcp socket info provided via netlink. */
void tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb)
{
const struct vegas *ca = inet_csk_ca(sk);
if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
struct tcpvegas_info info = {
.tcpv_enabled = ca->doing_vegas_now,
.tcpv_rttcnt = ca->cntRTT,
.tcpv_rtt = ca->baseRTT,
.tcpv_minrtt = ca->minRTT,
};
nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info);
}
}
EXPORT_SYMBOL_GPL(tcp_vegas_get_info);
static struct tcp_congestion_ops tcp_vegas __read_mostly = {
.flags = TCP_CONG_RTT_STAMP,
.init = tcp_vegas_init,
.ssthresh = tcp_reno_ssthresh,
.cong_avoid = tcp_vegas_cong_avoid,
.min_cwnd = tcp_reno_min_cwnd,
.pkts_acked = tcp_vegas_pkts_acked,
.set_state = tcp_vegas_state,
.cwnd_event = tcp_vegas_cwnd_event,
.get_info = tcp_vegas_get_info,
.owner = THIS_MODULE,
.name = "vegas",
};
static int __init tcp_vegas_register(void)
{
BUILD_BUG_ON(sizeof(struct vegas) > ICSK_CA_PRIV_SIZE);
tcp_register_congestion_control(&tcp_vegas);
return 0;
}
static void __exit tcp_vegas_unregister(void)
{
tcp_unregister_congestion_control(&tcp_vegas);
}
/**
* nfs_do_submount - set up mountpoint when crossing a filesystem boundary
* @dentry - parent directory
* @fh - filehandle for new root dentry
* @fattr - attributes for new root inode
* @authflavor - security flavor to use when performing the mount
*
*/
struct vfsmount *nfs_do_submount(struct dentry *dentry, struct nfs_fh *fh,
struct nfs_fattr *fattr, rpc_authflavor_t authflavor)
{
struct nfs_clone_mount mountdata = {
.sb = dentry->d_sb,
.dentry = dentry,
.fh = fh,
.fattr = fattr,
.authflavor = authflavor,
};
struct vfsmount *mnt;
char *page = (char *) __get_free_page(GFP_USER);
char *devname;
if (page == NULL)
return ERR_PTR(-ENOMEM);
devname = nfs_devname(dentry, page, PAGE_SIZE);
if (IS_ERR(devname))
mnt = (struct vfsmount *)devname;
else
mnt = nfs_do_clone_mount(NFS_SB(dentry->d_sb), devname, &mountdata);
free_page((unsigned long)page);
return mnt;
}
EXPORT_SYMBOL_GPL(nfs_do_submount);
struct vfsmount *nfs_submount(struct nfs_server *server, struct dentry *dentry,
struct nfs_fh *fh, struct nfs_fattr *fattr)
{
int err;
struct dentry *parent = dget_parent(dentry);
/* Look it up again to get its attributes */
err = server->nfs_client->rpc_ops->lookup(d_inode(parent), &dentry->d_name, fh, fattr, NULL);
dput(parent);
if (err != 0)
return ERR_PTR(err);
return nfs_do_submount(dentry, fh, fattr, server->client->cl_auth->au_flavor);
}
void xen_free_vm_area(struct vm_struct *area)
{
unsigned int order = get_order(area->size);
unsigned long i;
unsigned long phys_addr = __pa(area->addr);
/* This area is used for foreign page mappping.
* So underlying machine page may not be assigned. */
for (i = 0; i < (1 << order); i++) {
unsigned long ret;
unsigned long gpfn = (phys_addr >> PAGE_SHIFT) + i;
struct xen_memory_reservation reservation = {
.nr_extents = 1,
.address_bits = 0,
.extent_order = 0,
.domid = DOMID_SELF
};
set_xen_guest_handle(reservation.extent_start, &gpfn);
ret = HYPERVISOR_memory_op(XENMEM_populate_physmap,
&reservation);
BUG_ON(ret != 1);
}
free_pages((unsigned long)area->addr, order);
kfree(area);
}
EXPORT_SYMBOL_GPL(xen_free_vm_area);
/****************************************************************************
* grant table hack
* cmd: GNTTABOP_xxx
*/
int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
unsigned long max_nr_gframes,
struct grant_entry **__shared)
{
*__shared = __va(frames[0] << PAGE_SHIFT);
return 0;
}
/*
* get_kernel_page() - pin a kernel page in memory
* @start: starting kernel address
* @write: pinning for read/write, currently ignored
* @pages: array that receives pointer to the page pinned.
* Must be at least nr_segs long.
*
* Returns 1 if page is pinned. If the page was not pinned, returns
* -errno. The page returned must be released with a put_page() call
* when it is finished with.
*/
int get_kernel_page(unsigned long start, int write, struct page **pages)
{
const struct kvec kiov = {
.iov_base = (void *)start,
.iov_len = PAGE_SIZE
};
return get_kernel_pages(&kiov, 1, write, pages);
}
EXPORT_SYMBOL_GPL(get_kernel_page);
static void pagevec_lru_move_fn(struct pagevec *pvec,
void (*move_fn)(struct page *page, struct lruvec *lruvec, void *arg),
void *arg)
{
int i;
struct zone *zone = NULL;
struct lruvec *lruvec;
unsigned long flags = 0;
for (i = 0; i < pagevec_count(pvec); i++) {
struct page *page = pvec->pages[i];
struct zone *pagezone = page_zone(page);
if (pagezone != zone) {
if (zone)
spin_unlock_irqrestore(&zone->lru_lock, flags);
zone = pagezone;
spin_lock_irqsave(&zone->lru_lock, flags);
}
lruvec = mem_cgroup_page_lruvec(page, zone);
(*move_fn)(page, lruvec, arg);
}
if (zone)
spin_unlock_irqrestore(&zone->lru_lock, flags);
release_pages(pvec->pages, pvec->nr, pvec->cold);
pagevec_reinit(pvec);
}
/*
* dax_clear_blocks() is called from within transaction context from XFS,
* and hence this means the stack from this point must follow GFP_NOFS
* semantics for all operations.
*/
int dax_clear_blocks(struct inode *inode, sector_t block, long _size)
{
struct block_device *bdev = inode->i_sb->s_bdev;
struct blk_dax_ctl dax = {
.sector = block << (inode->i_blkbits - 9),
.size = _size,
};
might_sleep();
do {
long count, sz;
count = dax_map_atomic(bdev, &dax);
if (count < 0)
return count;
sz = min_t(long, count, SZ_128K);
clear_pmem(dax.addr, sz);
dax.size -= sz;
dax.sector += sz / 512;
dax_unmap_atomic(bdev, &dax);
cond_resched();
} while (dax.size);
wmb_pmem();
return 0;
}
EXPORT_SYMBOL_GPL(dax_clear_blocks);
/* the clear_pmem() calls are ordered by a wmb_pmem() in the caller */
static void dax_new_buf(void __pmem *addr, unsigned size, unsigned first,
loff_t pos, loff_t end)
{
loff_t final = end - pos + first; /* The final byte of the buffer */
if (first > 0)
clear_pmem(addr, first);
if (final < size)
clear_pmem(addr + final, size - final);
}
void mars_digest(unsigned char *digest, void *data, int len)
{
struct hash_desc desc = {
.tfm = mars_tfm,
.flags = 0,
};
struct scatterlist sg;
memset(digest, 0, mars_digest_size);
// TODO: use per-thread instance, omit locking
down(&tfm_sem);
crypto_hash_init(&desc);
sg_init_table(&sg, 1);
sg_set_buf(&sg, data, len);
crypto_hash_update(&desc, &sg, sg.length);
crypto_hash_final(&desc, digest);
up(&tfm_sem);
}
EXPORT_SYMBOL_GPL(mars_digest);
void mref_checksum(struct mref_object *mref)
{
unsigned char checksum[mars_digest_size];
int len;
if (mref->ref_cs_mode <= 0 || !mref->ref_data)
return;
mars_digest(checksum, mref->ref_data, mref->ref_len);
len = sizeof(mref->ref_checksum);
if (len > mars_digest_size)
len = mars_digest_size;
memcpy(&mref->ref_checksum, checksum, len);
}
/**
* stack_trace_save - Save a stack trace into a storage array
* @store: Pointer to storage array
* @size: Size of the storage array
* @skipnr: Number of entries to skip at the start of the stack trace
*
* Return: Number of trace entries stored
*/
unsigned int stack_trace_save(unsigned long *store, unsigned int size,
unsigned int skipnr)
{
struct stack_trace trace = {
.entries = store,
.max_entries = size,
.skip = skipnr + 1,
};
save_stack_trace(&trace);
return trace.nr_entries;
}
EXPORT_SYMBOL_GPL(stack_trace_save);
/**
* stack_trace_save_tsk - Save a task stack trace into a storage array
* @task: The task to examine
* @store: Pointer to storage array
* @size: Size of the storage array
* @skipnr: Number of entries to skip at the start of the stack trace
*
* Return: Number of trace entries stored
*/
unsigned int stack_trace_save_tsk(struct task_struct *task,
unsigned long *store, unsigned int size,
unsigned int skipnr)
{
struct stack_trace trace = {
.entries = store,
.max_entries = size,
.skip = skipnr + 1,
};
save_stack_trace_tsk(task, &trace);
return trace.nr_entries;
}
/**
* stack_trace_save_regs - Save a stack trace based on pt_regs into a storage array
* @regs: Pointer to pt_regs to examine
* @store: Pointer to storage array
* @size: Size of the storage array
* @skipnr: Number of entries to skip at the start of the stack trace
*
* Return: Number of trace entries stored
*/
unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store,
unsigned int size, unsigned int skipnr)
{
struct stack_trace trace = {
.entries = store,
.max_entries = size,
.skip = skipnr,
};
save_stack_trace_regs(regs, &trace);
return trace.nr_entries;
}
#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE
/**
* stack_trace_save_tsk_reliable - Save task stack with verification
* @tsk: Pointer to the task to examine
* @store: Pointer to storage array
* @size: Size of the storage array
*
* Return: An error if it detects any unreliable features of the
* stack. Otherwise it guarantees that the stack trace is
* reliable and returns the number of entries stored.
*
* If the task is not 'current', the caller *must* ensure the task is inactive.
*/
int stack_trace_save_tsk_reliable(struct task_struct *tsk, unsigned long *store,
unsigned int size)
{
struct stack_trace trace = {
.entries = store,
.max_entries = size,
};
int ret = save_stack_trace_tsk_reliable(tsk, &trace);
return ret ? ret : trace.nr_entries;
}
#endif
#ifdef CONFIG_USER_STACKTRACE_SUPPORT
/**
* stack_trace_save_user - Save a user space stack trace into a storage array
* @store: Pointer to storage array
* @size: Size of the storage array
*
* Return: Number of trace entries stored
*/
unsigned int stack_trace_save_user(unsigned long *store, unsigned int size)
{
struct stack_trace trace = {
.entries = store,
.max_entries = size,
};
save_stack_trace_user(&trace);
return trace.nr_entries;
}
/**
* stack_trace_save - Save a stack trace into a storage array
* @store: Pointer to storage array
* @size: Size of the storage array
* @skipnr: Number of entries to skip at the start of the stack trace
*
* Return: Number of trace entries stored.
*/
unsigned int stack_trace_save(unsigned long *store, unsigned int size,
unsigned int skipnr)
{
stack_trace_consume_fn consume_entry = stack_trace_consume_entry;
struct stacktrace_cookie c = {
.store = store,
.size = size,
.skip = skipnr + 1,
};
arch_stack_walk(consume_entry, &c, current, NULL);
return c.len;
}
EXPORT_SYMBOL_GPL(stack_trace_save);
/**
* stack_trace_save_tsk - Save a task stack trace into a storage array
* @task: The task to examine
* @store: Pointer to storage array
* @size: Size of the storage array
* @skipnr: Number of entries to skip at the start of the stack trace
*
* Return: Number of trace entries stored.
*/
unsigned int stack_trace_save_tsk(struct task_struct *tsk, unsigned long *store,
unsigned int size, unsigned int skipnr)
{
stack_trace_consume_fn consume_entry = stack_trace_consume_entry_nosched;
struct stacktrace_cookie c = {
.store = store,
.size = size,
.skip = skipnr + 1,
};
if (!try_get_task_stack(tsk))
return 0;
arch_stack_walk(consume_entry, &c, tsk, NULL);
put_task_stack(tsk);
return c.len;
}
/**
* stack_trace_save_regs - Save a stack trace based on pt_regs into a storage array
* @regs: Pointer to pt_regs to examine
* @store: Pointer to storage array
* @size: Size of the storage array
* @skipnr: Number of entries to skip at the start of the stack trace
*
* Return: Number of trace entries stored.
*/
unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store,
unsigned int size, unsigned int skipnr)
{
stack_trace_consume_fn consume_entry = stack_trace_consume_entry;
struct stacktrace_cookie c = {
.store = store,
.size = size,
.skip = skipnr,
};
arch_stack_walk(consume_entry, &c, current, regs);
return c.len;
}
int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmd, unsigned int flags, get_block_t get_block,
dax_iodone_t complete_unwritten)
{
struct file *file = vma->vm_file;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
struct buffer_head bh;
unsigned blkbits = inode->i_blkbits;
unsigned long pmd_addr = address & PMD_MASK;
bool write = flags & FAULT_FLAG_WRITE;
struct block_device *bdev;
pgoff_t size, pgoff;
sector_t block;
int error, result = 0;
bool alloc = false;
/* dax pmd mappings require pfn_t_devmap() */
if (!IS_ENABLED(CONFIG_FS_DAX_PMD))
return VM_FAULT_FALLBACK;
/* Fall back to PTEs if we're going to COW */
if (write && !(vma->vm_flags & VM_SHARED)) {
split_huge_pmd(vma, pmd, address);
dax_pmd_dbg(NULL, address, "cow write");
return VM_FAULT_FALLBACK;
}
/* If the PMD would extend outside the VMA */
if (pmd_addr < vma->vm_start) {
dax_pmd_dbg(NULL, address, "vma start unaligned");
return VM_FAULT_FALLBACK;
}
if ((pmd_addr + PMD_SIZE) > vma->vm_end) {
dax_pmd_dbg(NULL, address, "vma end unaligned");
return VM_FAULT_FALLBACK;
}
pgoff = linear_page_index(vma, pmd_addr);
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (pgoff >= size)
return VM_FAULT_SIGBUS;
/* If the PMD would cover blocks out of the file */
if ((pgoff | PG_PMD_COLOUR) >= size) {
dax_pmd_dbg(NULL, address,
"offset + huge page size > file size");
return VM_FAULT_FALLBACK;
}
memset(&bh, 0, sizeof(bh));
bh.b_bdev = inode->i_sb->s_bdev;
block = (sector_t)pgoff << (PAGE_SHIFT - blkbits);
bh.b_size = PMD_SIZE;
if (get_block(inode, block, &bh, 0) != 0)
return VM_FAULT_SIGBUS;
if (!buffer_mapped(&bh) && write) {
if (get_block(inode, block, &bh, 1) != 0)
return VM_FAULT_SIGBUS;
alloc = true;
}
bdev = bh.b_bdev;
/*
* If the filesystem isn't willing to tell us the length of a hole,
* just fall back to PTEs. Calling get_block 512 times in a loop
* would be silly.
*/
if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE) {
dax_pmd_dbg(&bh, address, "allocated block too small");
return VM_FAULT_FALLBACK;
}
/*
* If we allocated new storage, make sure no process has any
* zero pages covering this hole
*/
if (alloc) {
loff_t lstart = pgoff << PAGE_SHIFT;
loff_t lend = lstart + PMD_SIZE - 1; /* inclusive */
truncate_pagecache_range(inode, lstart, lend);
}
i_mmap_lock_read(mapping);
/*
* If a truncate happened while we were allocating blocks, we may
* leave blocks allocated to the file that are beyond EOF. We can't
* take i_mutex here, so just leave them hanging; they'll be freed
* when the file is deleted.
*/
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (pgoff >= size) {
result = VM_FAULT_SIGBUS;
goto out;
}
if ((pgoff | PG_PMD_COLOUR) >= size) {
dax_pmd_dbg(&bh, address,
"offset + huge page size > file size");
goto fallback;
}
if (!write && !buffer_mapped(&bh) && buffer_uptodate(&bh)) {
spinlock_t *ptl;
pmd_t entry;
struct page *zero_page = get_huge_zero_page();
if (unlikely(!zero_page)) {
dax_pmd_dbg(&bh, address, "no zero page");
goto fallback;
}
ptl = pmd_lock(vma->vm_mm, pmd);
if (!pmd_none(*pmd)) {
spin_unlock(ptl);
dax_pmd_dbg(&bh, address, "pmd already present");
goto fallback;
}
dev_dbg(part_to_dev(bdev->bd_part),
"%s: %s addr: %lx pfn: <zero> sect: %llx\n",
__func__, current->comm, address,
(unsigned long long) to_sector(&bh, inode));
entry = mk_pmd(zero_page, vma->vm_page_prot);
entry = pmd_mkhuge(entry);
set_pmd_at(vma->vm_mm, pmd_addr, pmd, entry);
result = VM_FAULT_NOPAGE;
spin_unlock(ptl);
} else {
struct blk_dax_ctl dax = {
.sector = to_sector(&bh, inode),
.size = PMD_SIZE,
};
long length = dax_map_atomic(bdev, &dax);
if (length < 0) {
result = VM_FAULT_SIGBUS;
goto out;
}
if (length < PMD_SIZE) {
dax_pmd_dbg(&bh, address, "dax-length too small");
dax_unmap_atomic(bdev, &dax);
goto fallback;
}
if (pfn_t_to_pfn(dax.pfn) & PG_PMD_COLOUR) {
dax_pmd_dbg(&bh, address, "pfn unaligned");
dax_unmap_atomic(bdev, &dax);
goto fallback;
}
if (!pfn_t_devmap(dax.pfn)) {
dax_unmap_atomic(bdev, &dax);
dax_pmd_dbg(&bh, address, "pfn not in memmap");
goto fallback;
}
if (buffer_unwritten(&bh) || buffer_new(&bh)) {
clear_pmem(dax.addr, PMD_SIZE);
wmb_pmem();
count_vm_event(PGMAJFAULT);
mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
result |= VM_FAULT_MAJOR;
}
dax_unmap_atomic(bdev, &dax);
/*
* For PTE faults we insert a radix tree entry for reads, and
* leave it clean. Then on the first write we dirty the radix
* tree entry via the dax_pfn_mkwrite() path. This sequence
* allows the dax_pfn_mkwrite() call to be simpler and avoid a
* call into get_block() to translate the pgoff to a sector in
* order to be able to create a new radix tree entry.
*
* The PMD path doesn't have an equivalent to
* dax_pfn_mkwrite(), though, so for a read followed by a
* write we traverse all the way through __dax_pmd_fault()
* twice. This means we can just skip inserting a radix tree
* entry completely on the initial read and just wait until
* the write to insert a dirty entry.
*/
if (write) {
error = dax_radix_entry(mapping, pgoff, dax.sector,
true, true);
if (error) {
dax_pmd_dbg(&bh, address,
"PMD radix insertion failed");
goto fallback;
}
}
dev_dbg(part_to_dev(bdev->bd_part),
"%s: %s addr: %lx pfn: %lx sect: %llx\n",
__func__, current->comm, address,
pfn_t_to_pfn(dax.pfn),
(unsigned long long) dax.sector);
result |= vmf_insert_pfn_pmd(vma, address, pmd,
dax.pfn, write);
}
out:
i_mmap_unlock_read(mapping);
if (buffer_unwritten(&bh))
complete_unwritten(&bh, !(result & VM_FAULT_ERROR));
return result;
fallback:
count_vm_event(THP_FAULT_FALLBACK);
result = VM_FAULT_FALLBACK;
goto out;
}
EXPORT_SYMBOL_GPL(__dax_pmd_fault);
/**
* dax_pmd_fault - handle a PMD fault on a DAX file
* @vma: The virtual memory area where the fault occurred
* @vmf: The description of the fault
* @get_block: The filesystem method used to translate file offsets to blocks
*
* When a page fault occurs, filesystems may call this helper in their
* pmd_fault handler for DAX files.
*/
int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmd, unsigned int flags, get_block_t get_block,
dax_iodone_t complete_unwritten)
{
int result;
struct super_block *sb = file_inode(vma->vm_file)->i_sb;
if (flags & FAULT_FLAG_WRITE) {
sb_start_pagefault(sb);
file_update_time(vma->vm_file);
}
result = __dax_pmd_fault(vma, address, pmd, flags, get_block,
complete_unwritten);
if (flags & FAULT_FLAG_WRITE)
sb_end_pagefault(sb);
return result;
}
struct page *read_dax_sector(struct block_device *bdev, sector_t n)
{
struct page *page = alloc_pages(GFP_KERNEL, 0);
struct blk_dax_ctl dax = {
.size = PAGE_SIZE,
.sector = n & ~((((int) PAGE_SIZE) / 512) - 1),
};
long rc;
if (!page)
return ERR_PTR(-ENOMEM);
rc = dax_map_atomic(bdev, &dax);
if (rc < 0)
return ERR_PTR(rc);
memcpy_from_pmem(page_address(page), dax.addr, PAGE_SIZE);
dax_unmap_atomic(bdev, &dax);
return page;
}
/*
* dax_clear_sectors() is called from within transaction context from XFS,
* and hence this means the stack from this point must follow GFP_NOFS
* semantics for all operations.
*/
int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size)
{
struct blk_dax_ctl dax = {
.sector = _sector,
.size = _size,
};
might_sleep();
do {
long count, sz;
count = dax_map_atomic(bdev, &dax);
if (count < 0)
return count;
sz = min_t(long, count, SZ_128K);
clear_pmem(dax.addr, sz);
dax.size -= sz;
dax.sector += sz / 512;
dax_unmap_atomic(bdev, &dax);
cond_resched();
} while (dax.size);
wmb_pmem();
return 0;
}
EXPORT_SYMBOL_GPL(dax_clear_sectors);
/* the clear_pmem() calls are ordered by a wmb_pmem() in the caller */
static void dax_new_buf(void __pmem *addr, unsigned size, unsigned first,
loff_t pos, loff_t end)
{
loff_t final = end - pos + first; /* The final byte of the buffer */
if (first > 0)
clear_pmem(addr, first);
if (final < size)
clear_pmem(addr + final, size - final);
}
static int copy_user_bh(struct page *to, struct inode *inode,
struct buffer_head *bh, unsigned long vaddr)
{
struct blk_dax_ctl dax = {
.sector = to_sector(bh, inode),
.size = bh->b_size,
};
struct block_device *bdev = bh->b_bdev;
void *vto;
if (dax_map_atomic(bdev, &dax) < 0)
return PTR_ERR(dax.addr);
vto = kmap_atomic(to);
copy_user_page(vto, (void __force *)dax.addr, vaddr, to);
kunmap_atomic(vto);
dax_unmap_atomic(bdev, &dax);
return 0;
}
#define NO_SECTOR -1
#define DAX_PMD_INDEX(page_index) (page_index & (PMD_MASK >> PAGE_SHIFT))
static int dax_radix_entry(struct address_space *mapping, pgoff_t index,
sector_t sector, bool pmd_entry, bool dirty)
{
struct radix_tree_root *page_tree = &mapping->page_tree;
pgoff_t pmd_index = DAX_PMD_INDEX(index);
int type, error = 0;
void *entry;
WARN_ON_ONCE(pmd_entry && !dirty);
if (dirty)
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
spin_lock_irq(&mapping->tree_lock);
entry = radix_tree_lookup(page_tree, pmd_index);
if (entry && RADIX_DAX_TYPE(entry) == RADIX_DAX_PMD) {
index = pmd_index;
goto dirty;
}
entry = radix_tree_lookup(page_tree, index);
if (entry) {
type = RADIX_DAX_TYPE(entry);
if (WARN_ON_ONCE(type != RADIX_DAX_PTE &&
type != RADIX_DAX_PMD)) {
error = -EIO;
goto unlock;
}
if (!pmd_entry || type == RADIX_DAX_PMD)
goto dirty;
/*
* We only insert dirty PMD entries into the radix tree. This
* means we don't need to worry about removing a dirty PTE
* entry and inserting a clean PMD entry, thus reducing the
* range we would flush with a follow-up fsync/msync call.
*/
radix_tree_delete(&mapping->page_tree, index);
mapping->nrexceptional--;
}
if (sector == NO_SECTOR) {
/*
* This can happen during correct operation if our pfn_mkwrite
* fault raced against a hole punch operation. If this
* happens the pte that was hole punched will have been
* unmapped and the radix tree entry will have been removed by
* the time we are called, but the call will still happen. We
* will return all the way up to wp_pfn_shared(), where the
* pte_same() check will fail, eventually causing page fault
* to be retried by the CPU.
*/
goto unlock;
}
error = radix_tree_insert(page_tree, index,
RADIX_DAX_ENTRY(sector, pmd_entry));
if (error)
goto unlock;
mapping->nrexceptional++;
dirty:
if (dirty)
radix_tree_tag_set(page_tree, index, PAGECACHE_TAG_DIRTY);
unlock:
spin_unlock_irq(&mapping->tree_lock);
return error;
}
static int dax_writeback_one(struct block_device *bdev,
struct address_space *mapping, pgoff_t index, void *entry)
{
struct radix_tree_root *page_tree = &mapping->page_tree;
int type = RADIX_DAX_TYPE(entry);
struct radix_tree_node *node;
struct blk_dax_ctl dax;
void **slot;
int ret = 0;
spin_lock_irq(&mapping->tree_lock);
/*
* Regular page slots are stabilized by the page lock even
* without the tree itself locked. These unlocked entries
* need verification under the tree lock.
*/
if (!__radix_tree_lookup(page_tree, index, &node, &slot))
goto unlock;
if (*slot != entry)
goto unlock;
/* another fsync thread may have already written back this entry */
if (!radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))
goto unlock;
if (WARN_ON_ONCE(type != RADIX_DAX_PTE && type != RADIX_DAX_PMD)) {
ret = -EIO;
goto unlock;
}
dax.sector = RADIX_DAX_SECTOR(entry);
dax.size = (type == RADIX_DAX_PMD ? PMD_SIZE : PAGE_SIZE);
spin_unlock_irq(&mapping->tree_lock);
/*
* We cannot hold tree_lock while calling dax_map_atomic() because it
* eventually calls cond_resched().
*/
ret = dax_map_atomic(bdev, &dax);
if (ret < 0)
return ret;
if (WARN_ON_ONCE(ret < dax.size)) {
ret = -EIO;
goto unmap;
}
wb_cache_pmem(dax.addr, dax.size);
spin_lock_irq(&mapping->tree_lock);
radix_tree_tag_clear(page_tree, index, PAGECACHE_TAG_TOWRITE);
spin_unlock_irq(&mapping->tree_lock);
unmap:
dax_unmap_atomic(bdev, &dax);
return ret;
unlock:
spin_unlock_irq(&mapping->tree_lock);
return ret;
}
/*
* Flush the mapping to the persistent domain within the byte range of [start,
* end]. This is required by data integrity operations to ensure file data is
* on persistent storage prior to completion of the operation.
*/
int dax_writeback_mapping_range(struct address_space *mapping,
struct block_device *bdev, struct writeback_control *wbc)
{
struct inode *inode = mapping->host;
pgoff_t start_index, end_index, pmd_index;
pgoff_t indices[PAGEVEC_SIZE];
struct pagevec pvec;
bool done = false;
int i, ret = 0;
void *entry;
if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT))
return -EIO;
if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL)
return 0;
start_index = wbc->range_start >> PAGE_SHIFT;
end_index = wbc->range_end >> PAGE_SHIFT;
pmd_index = DAX_PMD_INDEX(start_index);
rcu_read_lock();
entry = radix_tree_lookup(&mapping->page_tree, pmd_index);
rcu_read_unlock();
/* see if the start of our range is covered by a PMD entry */
if (entry && RADIX_DAX_TYPE(entry) == RADIX_DAX_PMD)
start_index = pmd_index;
tag_pages_for_writeback(mapping, start_index, end_index);
pagevec_init(&pvec, 0);
while (!done) {
pvec.nr = find_get_entries_tag(mapping, start_index,
PAGECACHE_TAG_TOWRITE, PAGEVEC_SIZE,
pvec.pages, indices);
if (pvec.nr == 0)
break;
for (i = 0; i < pvec.nr; i++) {
if (indices[i] > end_index) {
done = true;
break;
}
ret = dax_writeback_one(bdev, mapping, indices[i],
pvec.pages[i]);
if (ret < 0)
return ret;
}
}
wmb_pmem();
return 0;
}
EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);
static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
struct vm_area_struct *vma, struct vm_fault *vmf)
{
unsigned long vaddr = (unsigned long)vmf->virtual_address;
struct address_space *mapping = inode->i_mapping;
struct block_device *bdev = bh->b_bdev;
struct blk_dax_ctl dax = {
.sector = to_sector(bh, inode),
.size = bh->b_size,
};
pgoff_t size;
int error;
i_mmap_lock_read(mapping);
/*
* Check truncate didn't happen while we were allocating a block.
* If it did, this block may or may not be still allocated to the
* file. We can't tell the filesystem to free it because we can't
* take i_mutex here. In the worst case, the file still has blocks
* allocated past the end of the file.
*/
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (unlikely(vmf->pgoff >= size)) {
error = -EIO;
goto out;
}
if (dax_map_atomic(bdev, &dax) < 0) {
error = PTR_ERR(dax.addr);
goto out;
}
if (buffer_unwritten(bh) || buffer_new(bh)) {
clear_pmem(dax.addr, PAGE_SIZE);
wmb_pmem();
}
dax_unmap_atomic(bdev, &dax);
error = dax_radix_entry(mapping, vmf->pgoff, dax.sector, false,
vmf->flags & FAULT_FLAG_WRITE);
if (error)
goto out;
error = vm_insert_mixed(vma, vaddr, dax.pfn);
out:
i_mmap_unlock_read(mapping);
return error;
}
/**
* __dax_fault - handle a page fault on a DAX file
* @vma: The virtual memory area where the fault occurred
* @vmf: The description of the fault
* @get_block: The filesystem method used to translate file offsets to blocks
* @complete_unwritten: The filesystem method used to convert unwritten blocks
* to written so the data written to them is exposed. This is required for
* required by write faults for filesystems that will return unwritten
* extent mappings from @get_block, but it is optional for reads as
* dax_insert_mapping() will always zero unwritten blocks. If the fs does
* not support unwritten extents, the it should pass NULL.
*
* When a page fault occurs, filesystems may call this helper in their
* fault handler for DAX files. __dax_fault() assumes the caller has done all
* the necessary locking for the page fault to proceed successfully.
*/
int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
get_block_t get_block, dax_iodone_t complete_unwritten)
{
struct file *file = vma->vm_file;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
struct page *page;
struct buffer_head bh;
unsigned long vaddr = (unsigned long)vmf->virtual_address;
unsigned blkbits = inode->i_blkbits;
sector_t block;
pgoff_t size;
int error;
int major = 0;
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (vmf->pgoff >= size)
return VM_FAULT_SIGBUS;
memset(&bh, 0, sizeof(bh));
block = (sector_t)vmf->pgoff << (PAGE_SHIFT - blkbits);
bh.b_bdev = inode->i_sb->s_bdev;
bh.b_size = PAGE_SIZE;
repeat:
page = find_get_page(mapping, vmf->pgoff);
if (page) {
if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) {
put_page(page);
return VM_FAULT_RETRY;
}
if (unlikely(page->mapping != mapping)) {
unlock_page(page);
put_page(page);
goto repeat;
}
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (unlikely(vmf->pgoff >= size)) {
/*
* We have a struct page covering a hole in the file
* from a read fault and we've raced with a truncate
*/
error = -EIO;
goto unlock_page;
}
}
error = get_block(inode, block, &bh, 0);
if (!error && (bh.b_size < PAGE_SIZE))
error = -EIO; /* fs corruption? */
if (error)
goto unlock_page;
if (!buffer_mapped(&bh) && !buffer_unwritten(&bh) && !vmf->cow_page) {
if (vmf->flags & FAULT_FLAG_WRITE) {
error = get_block(inode, block, &bh, 1);
count_vm_event(PGMAJFAULT);
mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
major = VM_FAULT_MAJOR;
if (!error && (bh.b_size < PAGE_SIZE))
error = -EIO;
if (error)
goto unlock_page;
} else {
return dax_load_hole(mapping, page, vmf);
}
}
if (vmf->cow_page) {
struct page *new_page = vmf->cow_page;
if (buffer_written(&bh))
error = copy_user_bh(new_page, inode, &bh, vaddr);
else
clear_user_highpage(new_page, vaddr);
if (error)
goto unlock_page;
vmf->page = page;
if (!page) {
i_mmap_lock_read(mapping);
/* Check we didn't race with truncate */
size = (i_size_read(inode) + PAGE_SIZE - 1) >>
PAGE_SHIFT;
if (vmf->pgoff >= size) {
i_mmap_unlock_read(mapping);
error = -EIO;
goto out;
}
}
return VM_FAULT_LOCKED;
}
/* Check we didn't race with a read fault installing a new page */
if (!page && major)
page = find_lock_page(mapping, vmf->pgoff);
if (page) {
unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT,
PAGE_SIZE, 0);
delete_from_page_cache(page);
unlock_page(page);
put_page(page);
page = NULL;
}
/*
* If we successfully insert the new mapping over an unwritten extent,
* we need to ensure we convert the unwritten extent. If there is an
* error inserting the mapping, the filesystem needs to leave it as
* unwritten to prevent exposure of the stale underlying data to
* userspace, but we still need to call the completion function so
* the private resources on the mapping buffer can be released. We
* indicate what the callback should do via the uptodate variable, same
* as for normal BH based IO completions.
*/
error = dax_insert_mapping(inode, &bh, vma, vmf);
if (buffer_unwritten(&bh)) {
if (complete_unwritten)
complete_unwritten(&bh, !error);
else
WARN_ON_ONCE(!(vmf->flags & FAULT_FLAG_WRITE));
}
out:
if (error == -ENOMEM)
return VM_FAULT_OOM | major;
/* -EBUSY is fine, somebody else faulted on the same PTE */
if ((error < 0) && (error != -EBUSY))
return VM_FAULT_SIGBUS | major;
return VM_FAULT_NOPAGE | major;
unlock_page:
if (page) {
unlock_page(page);
put_page(page);
}
goto out;
}
int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
struct cpufreq_frequency_table *table,
unsigned int target_freq,
unsigned int relation,
unsigned int *index)
{
struct cpufreq_frequency_table optimal = {
.index = ~0,
.frequency = 0,
};
struct cpufreq_frequency_table suboptimal = {
.index = ~0,
.frequency = 0,
};
unsigned int diff, i = 0;
pr_debug("request for target %u kHz (relation: %u) for cpu %u\n",
target_freq, relation, policy->cpu);
switch (relation) {
case CPUFREQ_RELATION_H:
suboptimal.frequency = ~0;
break;
case CPUFREQ_RELATION_L:
case CPUFREQ_RELATION_C:
optimal.frequency = ~0;
break;
}
if (!cpu_online(policy->cpu))
return -EINVAL;
for (i = 0; (table[i].frequency != CPUFREQ_TABLE_END); i++) {
unsigned int freq = table[i].frequency;
if (freq == CPUFREQ_ENTRY_INVALID)
continue;
if ((freq < policy->min) || (freq > policy->max))
continue;
if (freq == target_freq) {
optimal.index = i;
break;
}
switch (relation) {
case CPUFREQ_RELATION_H:
if (freq < target_freq) {
if (freq >= optimal.frequency) {
optimal.frequency = freq;
optimal.index = i;
}
} else {
if (freq <= suboptimal.frequency) {
suboptimal.frequency = freq;
suboptimal.index = i;
}
}
break;
case CPUFREQ_RELATION_L:
if (freq > target_freq) {
if (freq <= optimal.frequency) {
optimal.frequency = freq;
optimal.index = i;
}
} else {
if (freq >= suboptimal.frequency) {
suboptimal.frequency = freq;
suboptimal.index = i;
}
}
break;
case CPUFREQ_RELATION_C:
diff = abs(freq - target_freq);
if (diff < optimal.frequency ||
(diff == optimal.frequency &&
freq > table[optimal.index].frequency)) {
optimal.frequency = diff;
optimal.index = i;
}
break;
}
}
if (optimal.index > i) {
if (suboptimal.index > i)
return -EINVAL;
*index = suboptimal.index;
} else
*index = optimal.index;
pr_debug("target is %u (%u kHz, %u)\n", *index, table[*index].frequency,
table[*index].index);
return 0;
}
EXPORT_SYMBOL_GPL(cpufreq_frequency_table_target);
static DEFINE_PER_CPU(struct cpufreq_frequency_table *, cpufreq_show_table);
/**
* show_available_freqs - show available frequencies for the specified CPU
*/
static ssize_t show_available_freqs(struct cpufreq_policy *policy, char *buf)
{
unsigned int i = 0;
unsigned int cpu = policy->cpu;
ssize_t count = 0;
struct cpufreq_frequency_table *table;
if (!per_cpu(cpufreq_show_table, cpu))
return -ENODEV;
table = per_cpu(cpufreq_show_table, cpu);
for (i = 0; (table[i].frequency != CPUFREQ_TABLE_END); i++) {
if (table[i].frequency == CPUFREQ_ENTRY_INVALID)
continue;
count += sprintf(&buf[count], "%d ", table[i].frequency);
}
count += sprintf(&buf[count], "\n");
return count;
}
struct freq_attr cpufreq_freq_attr_scaling_available_freqs = {
.attr = { .name = "scaling_available_frequencies",
.mode = 0444,
},
.show = show_available_freqs,
};
/**
* xenbus_map_ring_valloc
* @dev: xenbus device
* @gnt_ref: grant reference
* @vaddr: pointer to address to be filled out by mapping
*
* Based on Rusty Russell's skeleton driver's map_page.
* Map a page of memory into this domain from another domain's grant table.
* xenbus_map_ring_valloc allocates a page of virtual address space, maps the
* page to that address, and sets *vaddr to that address.
* Returns 0 on success, and GNTST_* (see xen/include/interface/grant_table.h)
* or -ENOMEM on error. If an error is returned, device will switch to
* XenbusStateClosing and the error message will be saved in XenStore.
*/
int xenbus_map_ring_valloc(struct xenbus_device *dev, int gnt_ref, void **vaddr)
{
struct gnttab_map_grant_ref op = {
.flags = GNTMAP_host_map,
.ref = gnt_ref,
.dom = dev->otherend_id,
};
struct vm_struct *area;
*vaddr = NULL;
area = xen_alloc_vm_area(PAGE_SIZE);
if (!area)
return -ENOMEM;
op.host_addr = (unsigned long)area->addr;
if (HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, &op, 1))
BUG();
if (op.status != GNTST_okay) {
xen_free_vm_area(area);
xenbus_dev_fatal(dev, op.status,
"mapping in shared page %d from domain %d",
gnt_ref, dev->otherend_id);
return op.status;
}
/* Stuff the handle in an unused field */
area->phys_addr = (unsigned long)op.handle;
*vaddr = area->addr;
return 0;
}
EXPORT_SYMBOL_GPL(xenbus_map_ring_valloc);
/**
* xenbus_map_ring
* @dev: xenbus device
* @gnt_ref: grant reference
* @handle: pointer to grant handle to be filled
* @vaddr: address to be mapped to
*
* Map a page of memory into this domain from another domain's grant table.
* xenbus_map_ring does not allocate the virtual address space (you must do
* this yourself!). It only maps in the page to the specified address.
* Returns 0 on success, and GNTST_* (see xen/include/interface/grant_table.h)
* or -ENOMEM on error. If an error is returned, device will switch to
* XenbusStateClosing and the error message will be saved in XenStore.
*/
int xenbus_map_ring(struct xenbus_device *dev, int gnt_ref,
grant_handle_t *handle, void *vaddr)
{
struct gnttab_map_grant_ref op = {
.host_addr = (unsigned long)vaddr,
.flags = GNTMAP_host_map,
.ref = gnt_ref,
.dom = dev->otherend_id,
};
if (HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, &op, 1))
BUG();
if (op.status != GNTST_okay) {
xenbus_dev_fatal(dev, op.status,
"mapping in shared page %d from domain %d",
gnt_ref, dev->otherend_id);
} else
*handle = op.handle;
return op.status;
}
EXPORT_SYMBOL_GPL(xenbus_map_ring);
/**
* xenbus_unmap_ring_vfree
* @dev: xenbus device
* @vaddr: addr to unmap
*
* Based on Rusty Russell's skeleton driver's unmap_page.
* Unmap a page of memory in this domain that was imported from another domain.
* Use xenbus_unmap_ring_vfree if you mapped in your memory with
* xenbus_map_ring_valloc (it will free the virtual address space).
* Returns 0 on success and returns GNTST_* on error
* (see xen/include/interface/grant_table.h).
*/
int xenbus_unmap_ring_vfree(struct xenbus_device *dev, void *vaddr)
{
struct vm_struct *area;
struct gnttab_unmap_grant_ref op = {
.host_addr = (unsigned long)vaddr,
};
/* It'd be nice if linux/vmalloc.h provided a find_vm_area(void *addr)
* method so that we don't have to muck with vmalloc internals here.
* We could force the user to hang on to their struct vm_struct from
* xenbus_map_ring_valloc, but these 6 lines considerably simplify
* this API.
*/
read_lock(&vmlist_lock);
for (area = vmlist; area != NULL; area = area->next) {
if (area->addr == vaddr)
break;
}
read_unlock(&vmlist_lock);
if (!area) {
xenbus_dev_error(dev, -ENOENT,
"can't find mapped virtual address %p", vaddr);
return GNTST_bad_virt_addr;
}
op.handle = (grant_handle_t)area->phys_addr;
if (HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, &op, 1))
BUG();
if (op.status == GNTST_okay)
xen_free_vm_area(area);
else
xenbus_dev_error(dev, op.status,
"unmapping page at handle %d error %d",
(int16_t)area->phys_addr, op.status);
return op.status;
}
EXPORT_SYMBOL_GPL(xenbus_unmap_ring_vfree);
/**
* xenbus_unmap_ring
* @dev: xenbus device
* @handle: grant handle
* @vaddr: addr to unmap
*
* Unmap a page of memory in this domain that was imported from another domain.
* Returns 0 on success and returns GNTST_* on error
* (see xen/include/interface/grant_table.h).
*/
int xenbus_unmap_ring(struct xenbus_device *dev,
grant_handle_t handle, void *vaddr)
{
struct gnttab_unmap_grant_ref op = {
.host_addr = (unsigned long)vaddr,
.handle = handle,
};
if (HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, &op, 1))
BUG();
if (op.status != GNTST_okay)
xenbus_dev_error(dev, op.status,
"unmapping page at handle %d error %d",
handle, op.status);
return op.status;
}
EXPORT_SYMBOL_GPL(xenbus_unmap_ring);
/**
* xenbus_read_driver_state
* @path: path for driver
*
* Return the state of the driver rooted at the given store path, or
* XenbusStateUnknown if no state can be read.
*/
enum xenbus_state xenbus_read_driver_state(const char *path)
{
enum xenbus_state result;
int err = xenbus_gather(XBT_NIL, path, "state", "%d", &result, NULL);
if (err)
result = XenbusStateUnknown;
return result;
}
EXPORT_SYMBOL_GPL(xenbus_read_driver_state);
int cw1200_core_probe(const struct sbus_ops *sbus_ops,
struct sbus_priv *sbus,
struct device *pdev,
struct cw1200_common **pself,
u8 *mac_addr)
{
int err = -ENOMEM;
u16 ctrl_reg;
struct ieee80211_hw *dev;
struct cw1200_common *priv;
struct wsm_operational_mode mode = {
.power_mode = wsm_power_mode_quiescent,
.disableMoreFlagUsage = true,
};
dev = cw1200_init_common(sizeof(struct cw1200_common), mac_addr);
if (!dev)
goto err;
priv = dev->priv;
priv->sbus_ops = sbus_ops;
priv->sbus_priv = sbus;
priv->pdev = pdev;
SET_IEEE80211_DEV(priv->hw, pdev);
/* WSM callbacks. */
priv->wsm_cbc.scan_complete = cw1200_scan_complete_cb;
priv->wsm_cbc.tx_confirm = cw1200_tx_confirm_cb;
priv->wsm_cbc.rx = cw1200_rx_cb;
priv->wsm_cbc.suspend_resume = cw1200_suspend_resume;
/* priv->wsm_cbc.set_pm_complete = cw1200_set_pm_complete_cb; */
priv->wsm_cbc.channel_switch = cw1200_channel_switch_cb;
err = cw1200_register_bh(priv);
if (err)
goto err1;
err = cw1200_load_firmware(priv);
if (err)
goto err2;
priv->sbus_ops->lock(priv->sbus_priv);
WARN_ON(priv->sbus_ops->set_block_size(priv->sbus_priv,
SDIO_BLOCK_SIZE));
priv->sbus_ops->unlock(priv->sbus_priv);
if (wait_event_interruptible_timeout(priv->wsm_startup_done,
priv->wsm_caps.firmwareReady, 3*HZ) <= 0) {
/* TODO: Needs to find how to reset device */
/* in QUEUE mode properly. */
goto err3;
}
WARN_ON(cw1200_reg_write_16(priv, ST90TDS_CONTROL_REG_ID,
ST90TDS_CONT_WUP_BIT));
if (cw1200_reg_read_16(priv,ST90TDS_CONTROL_REG_ID, &ctrl_reg))
WARN_ON(cw1200_reg_read_16(priv,ST90TDS_CONTROL_REG_ID,
&ctrl_reg));
WARN_ON(!(ctrl_reg & ST90TDS_CONT_RDY_BIT));
/* Set low-power mode. */
WARN_ON(wsm_set_operational_mode(priv, &mode));
/* Enable multi-TX confirmation */
WARN_ON(wsm_use_multi_tx_conf(priv, true));
err = cw1200_register_common(dev);
if (err) {
priv->sbus_ops->irq_unsubscribe(priv->sbus_priv);
goto err3;
}
*pself = dev->priv;
return err;
err3:
sbus_ops->reset(sbus);
err2:
cw1200_unregister_bh(priv);
err1:
cw1200_free_common(dev);
err:
return err;
}
EXPORT_SYMBOL_GPL(cw1200_core_probe);
void cw1200_core_release(struct cw1200_common *self)
{
cw1200_unregister_common(self->hw);
cw1200_free_common(self->hw);
return;
}
int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
struct sk_buff *skb, const struct inet_diag_req_v2 *req,
struct user_namespace *user_ns,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
const struct inet_sock *inet = inet_sk(sk);
const struct tcp_congestion_ops *ca_ops;
const struct inet_diag_handler *handler;
int ext = req->idiag_ext;
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
struct nlattr *attr;
void *info = NULL;
handler = inet_diag_table[req->sdiag_protocol];
BUG_ON(!handler);
nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
r = nlmsg_data(nlh);
BUG_ON(!sk_fullsock(sk));
inet_diag_msg_common_fill(r, sk);
r->idiag_state = sk->sk_state;
r->idiag_timer = 0;
r->idiag_retrans = 0;
if (nla_put_u8(skb, INET_DIAG_SHUTDOWN, sk->sk_shutdown))
goto errout;
/* IPv6 dual-stack sockets use inet->tos for IPv4 connections,
* hence this needs to be included regardless of socket family.
*/
if (ext & (1 << (INET_DIAG_TOS - 1)))
if (nla_put_u8(skb, INET_DIAG_TOS, inet->tos) < 0)
goto errout;
#if IS_ENABLED(CONFIG_IPV6)
if (r->idiag_family == AF_INET6) {
if (ext & (1 << (INET_DIAG_TCLASS - 1)))
if (nla_put_u8(skb, INET_DIAG_TCLASS,
inet6_sk(sk)->tclass) < 0)
goto errout;
if (((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) &&
nla_put_u8(skb, INET_DIAG_SKV6ONLY, ipv6_only_sock(sk)))
goto errout;
}
#endif
r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk));
r->idiag_inode = sock_i_ino(sk);
if (ext & (1 << (INET_DIAG_MEMINFO - 1))) {
struct inet_diag_meminfo minfo = {
.idiag_rmem = sk_rmem_alloc_get(sk),
.idiag_wmem = sk->sk_wmem_queued,
.idiag_fmem = sk->sk_forward_alloc,
.idiag_tmem = sk_wmem_alloc_get(sk),
};
if (nla_put(skb, INET_DIAG_MEMINFO, sizeof(minfo), &minfo) < 0)
goto errout;
}
if (ext & (1 << (INET_DIAG_SKMEMINFO - 1)))
if (sock_diag_put_meminfo(sk, skb, INET_DIAG_SKMEMINFO))
goto errout;
if (!icsk) {
handler->idiag_get_info(sk, r, NULL);
goto out;
}
#define EXPIRES_IN_MS(tmo) DIV_ROUND_UP((tmo - jiffies) * 1000, HZ)
if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
r->idiag_timer = 1;
r->idiag_retrans = icsk->icsk_retransmits;
r->idiag_expires = EXPIRES_IN_MS(icsk->icsk_timeout);
} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
r->idiag_timer = 4;
r->idiag_retrans = icsk->icsk_probes_out;
r->idiag_expires = EXPIRES_IN_MS(icsk->icsk_timeout);
} else if (timer_pending(&sk->sk_timer)) {
r->idiag_timer = 2;
r->idiag_retrans = icsk->icsk_probes_out;
r->idiag_expires = EXPIRES_IN_MS(sk->sk_timer.expires);
} else {
r->idiag_timer = 0;
r->idiag_expires = 0;
}
#undef EXPIRES_IN_MS
if ((ext & (1 << (INET_DIAG_INFO - 1))) && handler->idiag_info_size) {
attr = nla_reserve(skb, INET_DIAG_INFO,
handler->idiag_info_size);
if (!attr)
goto errout;
info = nla_data(attr);
}
if (ext & (1 << (INET_DIAG_CONG - 1))) {
int err = 0;
rcu_read_lock();
ca_ops = READ_ONCE(icsk->icsk_ca_ops);
if (ca_ops)
err = nla_put_string(skb, INET_DIAG_CONG, ca_ops->name);
rcu_read_unlock();
if (err < 0)
goto errout;
}
handler->idiag_get_info(sk, r, info);
if (sk->sk_state < TCP_TIME_WAIT) {
union tcp_cc_info info;
size_t sz = 0;
int attr;
rcu_read_lock();
ca_ops = READ_ONCE(icsk->icsk_ca_ops);
if (ca_ops && ca_ops->get_info)
sz = ca_ops->get_info(sk, ext, &attr, &info);
rcu_read_unlock();
if (sz && nla_put(skb, attr, sz, &info) < 0)
goto errout;
}
out:
nlmsg_end(skb, nlh);
return 0;
errout:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
EXPORT_SYMBOL_GPL(inet_sk_diag_fill);
static int inet_csk_diag_fill(struct sock *sk,
struct sk_buff *skb,
const struct inet_diag_req_v2 *req,
struct user_namespace *user_ns,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
return inet_sk_diag_fill(sk, inet_csk(sk), skb, req,
user_ns, portid, seq, nlmsg_flags, unlh);
}
static int inet_twsk_diag_fill(struct sock *sk,
struct sk_buff *skb,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
struct inet_timewait_sock *tw = inet_twsk(sk);
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
long tmo;
nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
r = nlmsg_data(nlh);
BUG_ON(tw->tw_state != TCP_TIME_WAIT);
tmo = tw->tw_timer.expires - jiffies;
if (tmo < 0)
tmo = 0;
inet_diag_msg_common_fill(r, sk);
r->idiag_retrans = 0;
r->idiag_state = tw->tw_substate;
r->idiag_timer = 3;
r->idiag_expires = jiffies_to_msecs(tmo);
r->idiag_rqueue = 0;
r->idiag_wqueue = 0;
r->idiag_uid = 0;
r->idiag_inode = 0;
nlmsg_end(skb, nlh);
return 0;
}
static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
long tmo;
nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
r = nlmsg_data(nlh);
inet_diag_msg_common_fill(r, sk);
r->idiag_state = TCP_SYN_RECV;
r->idiag_timer = 1;
r->idiag_retrans = inet_reqsk(sk)->num_retrans;
BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) !=
offsetof(struct sock, sk_cookie));
tmo = inet_reqsk(sk)->rsk_timer.expires - jiffies;
r->idiag_expires = (tmo >= 0) ? jiffies_to_msecs(tmo) : 0;
r->idiag_rqueue = 0;
r->idiag_wqueue = 0;
r->idiag_uid = 0;
r->idiag_inode = 0;
nlmsg_end(skb, nlh);
return 0;
}
static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
const struct inet_diag_req_v2 *r,
struct user_namespace *user_ns,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
if (sk->sk_state == TCP_TIME_WAIT)
return inet_twsk_diag_fill(sk, skb, portid, seq,
nlmsg_flags, unlh);
if (sk->sk_state == TCP_NEW_SYN_RECV)
return inet_req_diag_fill(sk, skb, portid, seq,
nlmsg_flags, unlh);
return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq,
nlmsg_flags, unlh);
}
struct sock *inet_diag_find_one_icsk(struct net *net,
struct inet_hashinfo *hashinfo,
const struct inet_diag_req_v2 *req)
{
struct sock *sk;
if (req->sdiag_family == AF_INET)
sk = inet_lookup(net, hashinfo, req->id.idiag_dst[0],
req->id.idiag_dport, req->id.idiag_src[0],
req->id.idiag_sport, req->id.idiag_if);
#if IS_ENABLED(CONFIG_IPV6)
else if (req->sdiag_family == AF_INET6) {
if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) &&
ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src))
sk = inet_lookup(net, hashinfo, req->id.idiag_dst[3],
req->id.idiag_dport, req->id.idiag_src[3],
req->id.idiag_sport, req->id.idiag_if);
else
sk = inet6_lookup(net, hashinfo,
(struct in6_addr *)req->id.idiag_dst,
req->id.idiag_dport,
(struct in6_addr *)req->id.idiag_src,
req->id.idiag_sport,
req->id.idiag_if);
}
#endif
else
return ERR_PTR(-EINVAL);
if (!sk)
return ERR_PTR(-ENOENT);
if (sock_diag_check_cookie(sk, req->id.idiag_cookie)) {
sock_gen_put(sk);
return ERR_PTR(-ENOENT);
}
return sk;
}
EXPORT_SYMBOL_GPL(inet_diag_find_one_icsk);
int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo,
struct sk_buff *in_skb,
const struct nlmsghdr *nlh,
const struct inet_diag_req_v2 *req)
{
struct net *net = sock_net(in_skb->sk);
struct sk_buff *rep;
struct sock *sk;
int err;
sk = inet_diag_find_one_icsk(net, hashinfo, req);
if (IS_ERR(sk))
return PTR_ERR(sk);
rep = nlmsg_new(inet_sk_attr_size(), GFP_KERNEL);
if (!rep) {
err = -ENOMEM;
goto out;
}
err = sk_diag_fill(sk, rep, req,
sk_user_ns(NETLINK_CB(in_skb).sk),
NETLINK_CB(in_skb).portid,
nlh->nlmsg_seq, 0, nlh);
if (err < 0) {
WARN_ON(err == -EMSGSIZE);
nlmsg_free(rep);
goto out;
}
err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
MSG_DONTWAIT);
if (err > 0)
err = 0;
out:
if (sk)
sock_gen_put(sk);
return err;
}
EXPORT_SYMBOL_GPL(inet_diag_dump_one_icsk);
static int inet_diag_cmd_exact(int cmd, struct sk_buff *in_skb,
const struct nlmsghdr *nlh,
const struct inet_diag_req_v2 *req)
{
const struct inet_diag_handler *handler;
int err;
handler = inet_diag_lock_handler(req->sdiag_protocol);
if (IS_ERR(handler))
err = PTR_ERR(handler);
else if (cmd == SOCK_DIAG_BY_FAMILY)
err = handler->dump_one(in_skb, nlh, req);
else if (cmd == SOCK_DESTROY_BACKPORT && handler->destroy)
err = handler->destroy(in_skb, req);
else
err = -EOPNOTSUPP;
inet_diag_unlock_handler(handler);
return err;
}
static int bitstring_match(const __be32 *a1, const __be32 *a2, int bits)
{
int words = bits >> 5;
bits &= 0x1f;
if (words) {
if (memcmp(a1, a2, words << 2))
return 0;
}
if (bits) {
__be32 w1, w2;
__be32 mask;
w1 = a1[words];
w2 = a2[words];
mask = htonl((0xffffffff) << (32 - bits));
if ((w1 ^ w2) & mask)
return 0;
}
return 1;
}
static int can_fill_info(struct sk_buff *skb, const struct net_device *dev)
{
struct can_priv *priv = netdev_priv(dev);
struct can_ctrlmode cm = {.flags = priv->ctrlmode};
struct can_berr_counter bec;
enum can_state state = priv->state;
if (priv->do_get_state)
priv->do_get_state(dev, &state);
NLA_PUT_U32(skb, IFLA_CAN_STATE, state);
NLA_PUT(skb, IFLA_CAN_CTRLMODE, sizeof(cm), &cm);
NLA_PUT_U32(skb, IFLA_CAN_RESTART_MS, priv->restart_ms);
NLA_PUT(skb, IFLA_CAN_BITTIMING,
sizeof(priv->bittiming), &priv->bittiming);
NLA_PUT(skb, IFLA_CAN_CLOCK, sizeof(cm), &priv->clock);
if (priv->do_get_berr_counter && !priv->do_get_berr_counter(dev, &bec))
NLA_PUT(skb, IFLA_CAN_BERR_COUNTER, sizeof(bec), &bec);
if (priv->bittiming_const)
NLA_PUT(skb, IFLA_CAN_BITTIMING_CONST,
sizeof(*priv->bittiming_const), priv->bittiming_const);
return 0;
nla_put_failure:
return -EMSGSIZE;
}
static size_t can_get_xstats_size(const struct net_device *dev)
{
return sizeof(struct can_device_stats);
}
static int can_fill_xstats(struct sk_buff *skb, const struct net_device *dev)
{
struct can_priv *priv = netdev_priv(dev);
NLA_PUT(skb, IFLA_INFO_XSTATS,
sizeof(priv->can_stats), &priv->can_stats);
return 0;
nla_put_failure:
return -EMSGSIZE;
}
static int can_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
return -EOPNOTSUPP;
}
static struct rtnl_link_ops can_link_ops __read_mostly = {
.kind = "can",
.maxtype = IFLA_CAN_MAX,
.policy = can_policy,
.setup = can_setup,
.newlink = can_newlink,
.changelink = can_changelink,
.get_size = can_get_size,
.fill_info = can_fill_info,
.get_xstats_size = can_get_xstats_size,
.fill_xstats = can_fill_xstats,
};
int register_candev(struct net_device *dev)
{
dev->rtnl_link_ops = &can_link_ops;
return register_netdev(dev);
}
EXPORT_SYMBOL_GPL(register_candev);
void unregister_candev(struct net_device *dev)
{
unregister_netdev(dev);
}
static int async_encrypt(struct ablkcipher_request *req)
{
struct crypto_tfm *tfm = req->base.tfm;
struct blkcipher_alg *alg = &tfm->__crt_alg->cra_blkcipher;
struct blkcipher_desc desc = {
.tfm = __crypto_blkcipher_cast(tfm),
.info = req->info,
.flags = req->base.flags,
};
return alg->encrypt(&desc, req->dst, req->src, req->nbytes);
}
static int async_decrypt(struct ablkcipher_request *req)
{
struct crypto_tfm *tfm = req->base.tfm;
struct blkcipher_alg *alg = &tfm->__crt_alg->cra_blkcipher;
struct blkcipher_desc desc = {
.tfm = __crypto_blkcipher_cast(tfm),
.info = req->info,
.flags = req->base.flags,
};
return alg->decrypt(&desc, req->dst, req->src, req->nbytes);
}
static unsigned int crypto_blkcipher_ctxsize(struct crypto_alg *alg, u32 type,
u32 mask)
{
struct blkcipher_alg *cipher = &alg->cra_blkcipher;
unsigned int len = alg->cra_ctxsize;
if ((mask & CRYPTO_ALG_TYPE_MASK) == CRYPTO_ALG_TYPE_MASK &&
cipher->ivsize) {
len = ALIGN(len, (unsigned long)alg->cra_alignmask + 1);
len += cipher->ivsize;
}
return len;
}
static int crypto_init_blkcipher_ops_async(struct crypto_tfm *tfm)
{
struct ablkcipher_tfm *crt = &tfm->crt_ablkcipher;
struct blkcipher_alg *alg = &tfm->__crt_alg->cra_blkcipher;
crt->setkey = async_setkey;
crt->encrypt = async_encrypt;
crt->decrypt = async_decrypt;
if (!alg->ivsize) {
crt->givencrypt = skcipher_null_givencrypt;
crt->givdecrypt = skcipher_null_givdecrypt;
}
crt->base = __crypto_ablkcipher_cast(tfm);
crt->ivsize = alg->ivsize;
return 0;
}
static int crypto_init_blkcipher_ops_sync(struct crypto_tfm *tfm)
{
struct blkcipher_tfm *crt = &tfm->crt_blkcipher;
struct blkcipher_alg *alg = &tfm->__crt_alg->cra_blkcipher;
unsigned long align = crypto_tfm_alg_alignmask(tfm) + 1;
unsigned long addr;
crt->setkey = setkey;
crt->encrypt = alg->encrypt;
crt->decrypt = alg->decrypt;
addr = (unsigned long)crypto_tfm_ctx(tfm);
addr = ALIGN(addr, align);
addr += ALIGN(tfm->__crt_alg->cra_ctxsize, align);
crt->iv = (void *)addr;
return 0;
}
static int crypto_init_blkcipher_ops(struct crypto_tfm *tfm, u32 type, u32 mask)
{
struct blkcipher_alg *alg = &tfm->__crt_alg->cra_blkcipher;
if (alg->ivsize > PAGE_SIZE / 8)
return -EINVAL;
if ((mask & CRYPTO_ALG_TYPE_MASK) == CRYPTO_ALG_TYPE_MASK)
return crypto_init_blkcipher_ops_sync(tfm);
else
return crypto_init_blkcipher_ops_async(tfm);
}
static void crypto_blkcipher_show(struct seq_file *m, struct crypto_alg *alg)
__attribute__ ((unused));
static void crypto_blkcipher_show(struct seq_file *m, struct crypto_alg *alg)
{
seq_printf(m, "type : blkcipher\n");
seq_printf(m, "blocksize : %u\n", alg->cra_blocksize);
seq_printf(m, "min keysize : %u\n", alg->cra_blkcipher.min_keysize);
seq_printf(m, "max keysize : %u\n", alg->cra_blkcipher.max_keysize);
seq_printf(m, "ivsize : %u\n", alg->cra_blkcipher.ivsize);
seq_printf(m, "geniv : %s\n", alg->cra_blkcipher.geniv ?:
"<default>");
}
const struct crypto_type crypto_blkcipher_type = {
.ctxsize = crypto_blkcipher_ctxsize,
.init = crypto_init_blkcipher_ops,
#ifdef CONFIG_PROC_FS
.show = crypto_blkcipher_show,
#endif
};
EXPORT_SYMBOL_GPL(crypto_blkcipher_type);
static int crypto_grab_nivcipher(struct crypto_skcipher_spawn *spawn,
const char *name, u32 type, u32 mask)
{
struct crypto_alg *alg;
int err;
type = crypto_skcipher_type(type);
mask = crypto_skcipher_mask(mask)| CRYPTO_ALG_GENIV;
alg = crypto_alg_mod_lookup(name, type, mask);
if (IS_ERR(alg))
return PTR_ERR(alg);
err = crypto_init_spawn(&spawn->base, alg, spawn->base.inst, mask);
crypto_mod_put(alg);
return err;
}
struct crypto_instance *skcipher_geniv_alloc(struct crypto_template *tmpl,
struct rtattr **tb, u32 type,
u32 mask)
{
struct {
int (*setkey)(struct crypto_ablkcipher *tfm, const u8 *key,
unsigned int keylen);
int (*encrypt)(struct ablkcipher_request *req);
int (*decrypt)(struct ablkcipher_request *req);
unsigned int min_keysize;
unsigned int max_keysize;
unsigned int ivsize;
const char *geniv;
} balg;
const char *name;
struct crypto_skcipher_spawn *spawn;
struct crypto_attr_type *algt;
struct crypto_instance *inst;
struct crypto_alg *alg;
int err;
algt = crypto_get_attr_type(tb);
err = PTR_ERR(algt);
if (IS_ERR(algt))
return ERR_PTR(err);
if ((algt->type ^ (CRYPTO_ALG_TYPE_GIVCIPHER | CRYPTO_ALG_GENIV)) &
algt->mask)
return ERR_PTR(-EINVAL);
name = crypto_attr_alg_name(tb[1]);
err = PTR_ERR(name);
if (IS_ERR(name))
return ERR_PTR(err);
inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL);
if (!inst)
return ERR_PTR(-ENOMEM);
spawn = crypto_instance_ctx(inst);
/* Ignore async algorithms if necessary. */
mask |= crypto_requires_sync(algt->type, algt->mask);
crypto_set_skcipher_spawn(spawn, inst);
err = crypto_grab_nivcipher(spawn, name, type, mask);
if (err)
goto err_free_inst;
alg = crypto_skcipher_spawn_alg(spawn);
if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) ==
CRYPTO_ALG_TYPE_BLKCIPHER) {
balg.ivsize = alg->cra_blkcipher.ivsize;
balg.min_keysize = alg->cra_blkcipher.min_keysize;
balg.max_keysize = alg->cra_blkcipher.max_keysize;
balg.setkey = async_setkey;
balg.encrypt = async_encrypt;
balg.decrypt = async_decrypt;
balg.geniv = alg->cra_blkcipher.geniv;
} else {
balg.ivsize = alg->cra_ablkcipher.ivsize;
balg.min_keysize = alg->cra_ablkcipher.min_keysize;
balg.max_keysize = alg->cra_ablkcipher.max_keysize;
balg.setkey = alg->cra_ablkcipher.setkey;
balg.encrypt = alg->cra_ablkcipher.encrypt;
balg.decrypt = alg->cra_ablkcipher.decrypt;
balg.geniv = alg->cra_ablkcipher.geniv;
}
err = -EINVAL;
if (!balg.ivsize)
goto err_drop_alg;
/*
* This is only true if we're constructing an algorithm with its
* default IV generator. For the default generator we elide the
* template name and double-check the IV generator.
*/
if (algt->mask & CRYPTO_ALG_GENIV) {
if (!balg.geniv)
balg.geniv = crypto_default_geniv(alg);
err = -EAGAIN;
if (strcmp(tmpl->name, balg.geniv))
goto err_drop_alg;
memcpy(inst->alg.cra_name, alg->cra_name, CRYPTO_MAX_ALG_NAME);
memcpy(inst->alg.cra_driver_name, alg->cra_driver_name,
CRYPTO_MAX_ALG_NAME);
} else {
err = -ENAMETOOLONG;
if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME,
"%s(%s)", tmpl->name, alg->cra_name) >=
CRYPTO_MAX_ALG_NAME)
goto err_drop_alg;
if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
"%s(%s)", tmpl->name, alg->cra_driver_name) >=
CRYPTO_MAX_ALG_NAME)
goto err_drop_alg;
}
inst->alg.cra_flags = CRYPTO_ALG_TYPE_GIVCIPHER | CRYPTO_ALG_GENIV;
inst->alg.cra_flags |= alg->cra_flags & CRYPTO_ALG_ASYNC;
inst->alg.cra_priority = alg->cra_priority;
inst->alg.cra_blocksize = alg->cra_blocksize;
inst->alg.cra_alignmask = alg->cra_alignmask;
inst->alg.cra_type = &crypto_givcipher_type;
inst->alg.cra_ablkcipher.ivsize = balg.ivsize;
inst->alg.cra_ablkcipher.min_keysize = balg.min_keysize;
inst->alg.cra_ablkcipher.max_keysize = balg.max_keysize;
inst->alg.cra_ablkcipher.geniv = balg.geniv;
inst->alg.cra_ablkcipher.setkey = balg.setkey;
inst->alg.cra_ablkcipher.encrypt = balg.encrypt;
inst->alg.cra_ablkcipher.decrypt = balg.decrypt;
out:
return inst;
err_drop_alg:
crypto_drop_skcipher(spawn);
err_free_inst:
kfree(inst);
inst = ERR_PTR(err);
goto out;
}
EXPORT_SYMBOL_GPL(skcipher_geniv_alloc);
void skcipher_geniv_free(struct crypto_instance *inst)
{
crypto_drop_skcipher(crypto_instance_ctx(inst));
kfree(inst);
}
static void acpi_bus_osc_support(void)
{
u32 capbuf[2];
struct acpi_osc_context context = {
.uuid_str = sb_uuid_str,
.rev = 1,
.cap.length = 8,
.cap.pointer = capbuf,
};
acpi_handle handle;
capbuf[OSC_QUERY_TYPE] = OSC_QUERY_ENABLE;
capbuf[OSC_SUPPORT_TYPE] = OSC_SB_PR3_SUPPORT; /* _PR3 is in use */
#if defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR) || \
defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR_MODULE)
capbuf[OSC_SUPPORT_TYPE] |= OSC_SB_PAD_SUPPORT;
#endif
#if defined(CONFIG_ACPI_PROCESSOR) || defined(CONFIG_ACPI_PROCESSOR_MODULE)
capbuf[OSC_SUPPORT_TYPE] |= OSC_SB_PPC_OST_SUPPORT;
#endif
if (ACPI_FAILURE(acpi_get_handle(NULL, "\\_SB", &handle)))
return;
if (ACPI_SUCCESS(acpi_run_osc(handle, &context)))
kfree(context.ret.pointer);
/* do we need to check the returned cap? Sounds no */
}
/* --------------------------------------------------------------------------
Event Management
-------------------------------------------------------------------------- */
#ifdef CONFIG_ACPI_PROC_EVENT
static DEFINE_SPINLOCK(acpi_bus_event_lock);
LIST_HEAD(acpi_bus_event_list);
DECLARE_WAIT_QUEUE_HEAD(acpi_bus_event_queue);
extern int event_is_open;
int acpi_bus_generate_proc_event4(const char *device_class, const char *bus_id, u8 type, int data)
{
struct acpi_bus_event *event;
unsigned long flags = 0;
/* drop event on the floor if no one's listening */
if (!event_is_open)
return 0;
event = kzalloc(sizeof(struct acpi_bus_event), GFP_ATOMIC);
if (!event)
return -ENOMEM;
strcpy(event->device_class, device_class);
strcpy(event->bus_id, bus_id);
event->type = type;
event->data = data;
spin_lock_irqsave(&acpi_bus_event_lock, flags);
list_add_tail(&event->node, &acpi_bus_event_list);
spin_unlock_irqrestore(&acpi_bus_event_lock, flags);
wake_up_interruptible(&acpi_bus_event_queue);
return 0;
}
EXPORT_SYMBOL_GPL(acpi_bus_generate_proc_event4);
int acpi_bus_generate_proc_event(struct acpi_device *device, u8 type, int data)
{
if (!device)
return -EINVAL;
return acpi_bus_generate_proc_event4(device->pnp.device_class,
device->pnp.bus_id, type, data);
}
EXPORT_SYMBOL(acpi_bus_generate_proc_event);
int acpi_bus_receive_event(struct acpi_bus_event *event)
{
unsigned long flags = 0;
struct acpi_bus_event *entry = NULL;
DECLARE_WAITQUEUE(wait, current);
if (!event)
return -EINVAL;
if (list_empty(&acpi_bus_event_list)) {
set_current_state(TASK_INTERRUPTIBLE);
add_wait_queue(&acpi_bus_event_queue, &wait);
if (list_empty(&acpi_bus_event_list))
schedule();
remove_wait_queue(&acpi_bus_event_queue, &wait);
set_current_state(TASK_RUNNING);
if (signal_pending(current))
return -ERESTARTSYS;
}
spin_lock_irqsave(&acpi_bus_event_lock, flags);
if (!list_empty(&acpi_bus_event_list)) {
entry = list_entry(acpi_bus_event_list.next,
struct acpi_bus_event, node);
list_del(&entry->node);
}
int em28xx_init_camera(struct em28xx *dev)
{
char clk_name[V4L2_SUBDEV_NAME_SIZE];
struct i2c_client *client = &dev->i2c_client[dev->def_i2c_bus];
struct i2c_adapter *adap = &dev->i2c_adap[dev->def_i2c_bus];
struct em28xx_v4l2 *v4l2 = dev->v4l2;
int ret = 0;
v4l2_clk_name_i2c(clk_name, sizeof(clk_name),
i2c_adapter_id(adap), client->addr);
v4l2->clk = v4l2_clk_register_fixed(clk_name, -EINVAL);
if (IS_ERR(v4l2->clk))
return PTR_ERR(v4l2->clk);
switch (dev->em28xx_sensor) {
case EM28XX_MT9V011:
{
struct mt9v011_platform_data pdata;
struct i2c_board_info mt9v011_info = {
.type = "mt9v011",
.addr = client->addr,
.platform_data = &pdata,
};
v4l2->sensor_xres = 640;
v4l2->sensor_yres = 480;
/*
* FIXME: mt9v011 uses I2S speed as xtal clk - at least with
* the Silvercrest cam I have here for testing - for higher
* resolutions, a high clock cause horizontal artifacts, so we
* need to use a lower xclk frequency.
* Yet, it would be possible to adjust xclk depending on the
* desired resolution, since this affects directly the
* frame rate.
*/
dev->board.xclk = EM28XX_XCLK_FREQUENCY_4_3MHZ;
em28xx_write_reg(dev, EM28XX_R0F_XCLK, dev->board.xclk);
v4l2->sensor_xtal = 4300000;
pdata.xtal = v4l2->sensor_xtal;
if (NULL ==
v4l2_i2c_new_subdev_board(&v4l2->v4l2_dev, adap,
&mt9v011_info, NULL)) {
ret = -ENODEV;
break;
}
/* probably means GRGB 16 bit bayer */
v4l2->vinmode = 0x0d;
v4l2->vinctl = 0x00;
break;
}
case EM28XX_MT9M001:
v4l2->sensor_xres = 1280;
v4l2->sensor_yres = 1024;
em28xx_initialize_mt9m001(dev);
/* probably means BGGR 16 bit bayer */
v4l2->vinmode = 0x0c;
v4l2->vinctl = 0x00;
break;
case EM28XX_MT9M111:
v4l2->sensor_xres = 640;
v4l2->sensor_yres = 512;
dev->board.xclk = EM28XX_XCLK_FREQUENCY_48MHZ;
em28xx_write_reg(dev, EM28XX_R0F_XCLK, dev->board.xclk);
em28xx_initialize_mt9m111(dev);
v4l2->vinmode = 0x0a;
v4l2->vinctl = 0x00;
break;
case EM28XX_OV2640:
{
struct v4l2_subdev *subdev;
struct i2c_board_info ov2640_info = {
.type = "ov2640",
.flags = I2C_CLIENT_SCCB,
.addr = client->addr,
.platform_data = &camlink,
};
struct v4l2_mbus_framefmt fmt;
/*
* FIXME: sensor supports resolutions up to 1600x1200, but
* resolution setting/switching needs to be modified to
* - switch sensor output resolution (including further
* configuration changes)
* - adjust bridge xclk
* - disable 16 bit (12 bit) output formats on high resolutions
*/
v4l2->sensor_xres = 640;
v4l2->sensor_yres = 480;
subdev =
v4l2_i2c_new_subdev_board(&v4l2->v4l2_dev, adap,
&ov2640_info, NULL);
if (NULL == subdev) {
ret = -ENODEV;
break;
}
fmt.code = MEDIA_BUS_FMT_YUYV8_2X8;
fmt.width = 640;
fmt.height = 480;
v4l2_subdev_call(subdev, video, s_mbus_fmt, &fmt);
/* NOTE: for UXGA=1600x1200 switch to 12MHz */
dev->board.xclk = EM28XX_XCLK_FREQUENCY_24MHZ;
em28xx_write_reg(dev, EM28XX_R0F_XCLK, dev->board.xclk);
v4l2->vinmode = 0x08;
v4l2->vinctl = 0x00;
break;
}
case EM28XX_NOSENSOR:
default:
ret = -EINVAL;
}
if (ret < 0) {
v4l2_clk_unregister_fixed(v4l2->clk);
v4l2->clk = NULL;
}
return ret;
}
EXPORT_SYMBOL_GPL(em28xx_init_camera);