summaryrefslogtreecommitdiff
path: root/include/linux
diff options
context:
space:
mode:
Diffstat (limited to 'include/linux')
-rw-r--r--include/linux/aer.h1
-rw-r--r--include/linux/bio.h32
-rw-r--r--include/linux/blk-iopoll.h46
-rw-r--r--include/linux/blk_types.h2
-rw-r--r--include/linux/blkdev.h1
-rw-r--r--include/linux/ceph/ceph_frag.h37
-rw-r--r--include/linux/ceph/messenger.h2
-rw-r--r--include/linux/dax.h7
-rw-r--r--include/linux/drbd.h26
-rw-r--r--include/linux/drbd_genl.h149
-rw-r--r--include/linux/fs.h32
-rw-r--r--include/linux/huge_mm.h16
-rw-r--r--include/linux/idr.h14
-rw-r--r--include/linux/interrupt.h2
-rw-r--r--include/linux/irq_poll.h25
-rw-r--r--include/linux/lightnvm.h238
-rw-r--r--include/linux/lru_cache.h2
-rw-r--r--include/linux/mlx4/cmd.h3
-rw-r--r--include/linux/mlx4/device.h15
-rw-r--r--include/linux/mlx4/qp.h15
-rw-r--r--include/linux/mlx5/device.h40
-rw-r--r--include/linux/mlx5/driver.h20
-rw-r--r--include/linux/mlx5/mlx5_ifc.h48
-rw-r--r--include/linux/mlx5/qp.h46
-rw-r--r--include/linux/mlx5/transobj.h78
-rw-r--r--include/linux/mlx5/vport.h8
-rw-r--r--include/linux/nvme.h27
-rw-r--r--include/linux/pagemap.h3
-rw-r--r--include/linux/pipe_fs_i.h4
-rw-r--r--include/linux/pmem.h22
-rw-r--r--include/linux/radix-tree.h9
-rw-r--r--include/linux/sched.h1
-rw-r--r--include/linux/shmem_fs.h5
-rw-r--r--include/linux/sunrpc/svc_rdma.h39
-rw-r--r--include/linux/thermal.h5
35 files changed, 773 insertions, 247 deletions
diff --git a/include/linux/aer.h b/include/linux/aer.h
index 744b997d6a94..164049357e5c 100644
--- a/include/linux/aer.h
+++ b/include/linux/aer.h
@@ -7,6 +7,7 @@
#ifndef _AER_H_
#define _AER_H_
+#include <linux/errno.h>
#include <linux/types.h>
#define AER_NONFATAL 0
diff --git a/include/linux/bio.h b/include/linux/bio.h
index b9b6e046b52e..5349e6816cbb 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -318,16 +318,6 @@ enum bip_flags {
BIP_IP_CHECKSUM = 1 << 4, /* IP checksum */
};
-#if defined(CONFIG_BLK_DEV_INTEGRITY)
-
-static inline struct bio_integrity_payload *bio_integrity(struct bio *bio)
-{
- if (bio->bi_rw & REQ_INTEGRITY)
- return bio->bi_integrity;
-
- return NULL;
-}
-
/*
* bio integrity payload
*/
@@ -349,6 +339,16 @@ struct bio_integrity_payload {
struct bio_vec bip_inline_vecs[0];/* embedded bvec array */
};
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+
+static inline struct bio_integrity_payload *bio_integrity(struct bio *bio)
+{
+ if (bio->bi_rw & REQ_INTEGRITY)
+ return bio->bi_integrity;
+
+ return NULL;
+}
+
static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag)
{
struct bio_integrity_payload *bip = bio_integrity(bio);
@@ -795,6 +795,18 @@ static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag)
return false;
}
+static inline void *bio_integrity_alloc(struct bio * bio, gfp_t gfp,
+ unsigned int nr)
+{
+ return ERR_PTR(-EINVAL);
+}
+
+static inline int bio_integrity_add_page(struct bio *bio, struct page *page,
+ unsigned int len, unsigned int offset)
+{
+ return 0;
+}
+
#endif /* CONFIG_BLK_DEV_INTEGRITY */
#endif /* CONFIG_BLOCK */
diff --git a/include/linux/blk-iopoll.h b/include/linux/blk-iopoll.h
deleted file mode 100644
index 77ae77c0b704..000000000000
--- a/include/linux/blk-iopoll.h
+++ /dev/null
@@ -1,46 +0,0 @@
-#ifndef BLK_IOPOLL_H
-#define BLK_IOPOLL_H
-
-struct blk_iopoll;
-typedef int (blk_iopoll_fn)(struct blk_iopoll *, int);
-
-struct blk_iopoll {
- struct list_head list;
- unsigned long state;
- unsigned long data;
- int weight;
- int max;
- blk_iopoll_fn *poll;
-};
-
-enum {
- IOPOLL_F_SCHED = 0,
- IOPOLL_F_DISABLE = 1,
-};
-
-/*
- * Returns 0 if we successfully set the IOPOLL_F_SCHED bit, indicating
- * that we were the first to acquire this iop for scheduling. If this iop
- * is currently disabled, return "failure".
- */
-static inline int blk_iopoll_sched_prep(struct blk_iopoll *iop)
-{
- if (!test_bit(IOPOLL_F_DISABLE, &iop->state))
- return test_and_set_bit(IOPOLL_F_SCHED, &iop->state);
-
- return 1;
-}
-
-static inline int blk_iopoll_disable_pending(struct blk_iopoll *iop)
-{
- return test_bit(IOPOLL_F_DISABLE, &iop->state);
-}
-
-extern void blk_iopoll_sched(struct blk_iopoll *);
-extern void blk_iopoll_init(struct blk_iopoll *, int, blk_iopoll_fn *);
-extern void blk_iopoll_complete(struct blk_iopoll *);
-extern void __blk_iopoll_complete(struct blk_iopoll *);
-extern void blk_iopoll_enable(struct blk_iopoll *);
-extern void blk_iopoll_disable(struct blk_iopoll *);
-
-#endif
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 0fb65843ec1e..86a38ea1823f 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -188,7 +188,6 @@ enum rq_flag_bits {
__REQ_PM, /* runtime pm request */
__REQ_HASHED, /* on IO scheduler merge hash */
__REQ_MQ_INFLIGHT, /* track inflight for MQ */
- __REQ_NO_TIMEOUT, /* requests may never expire */
__REQ_NR_BITS, /* stops here */
};
@@ -242,7 +241,6 @@ enum rq_flag_bits {
#define REQ_PM (1ULL << __REQ_PM)
#define REQ_HASHED (1ULL << __REQ_HASHED)
#define REQ_MQ_INFLIGHT (1ULL << __REQ_MQ_INFLIGHT)
-#define REQ_NO_TIMEOUT (1ULL << __REQ_NO_TIMEOUT)
typedef unsigned int blk_qc_t;
#define BLK_QC_T_NONE -1U
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d372ea87ead5..29189aeace19 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -409,6 +409,7 @@ struct request_queue {
unsigned int rq_timeout;
struct timer_list timeout;
+ struct work_struct timeout_work;
struct list_head timeout_list;
struct list_head icq_list;
diff --git a/include/linux/ceph/ceph_frag.h b/include/linux/ceph/ceph_frag.h
index 5babb8e95352..b827e066e55a 100644
--- a/include/linux/ceph/ceph_frag.h
+++ b/include/linux/ceph/ceph_frag.h
@@ -40,46 +40,11 @@ static inline __u32 ceph_frag_mask_shift(__u32 f)
return 24 - ceph_frag_bits(f);
}
-static inline int ceph_frag_contains_value(__u32 f, __u32 v)
+static inline bool ceph_frag_contains_value(__u32 f, __u32 v)
{
return (v & ceph_frag_mask(f)) == ceph_frag_value(f);
}
-static inline int ceph_frag_contains_frag(__u32 f, __u32 sub)
-{
- /* is sub as specific as us, and contained by us? */
- return ceph_frag_bits(sub) >= ceph_frag_bits(f) &&
- (ceph_frag_value(sub) & ceph_frag_mask(f)) == ceph_frag_value(f);
-}
-static inline __u32 ceph_frag_parent(__u32 f)
-{
- return ceph_frag_make(ceph_frag_bits(f) - 1,
- ceph_frag_value(f) & (ceph_frag_mask(f) << 1));
-}
-static inline int ceph_frag_is_left_child(__u32 f)
-{
- return ceph_frag_bits(f) > 0 &&
- (ceph_frag_value(f) & (0x1000000 >> ceph_frag_bits(f))) == 0;
-}
-static inline int ceph_frag_is_right_child(__u32 f)
-{
- return ceph_frag_bits(f) > 0 &&
- (ceph_frag_value(f) & (0x1000000 >> ceph_frag_bits(f))) == 1;
-}
-static inline __u32 ceph_frag_sibling(__u32 f)
-{
- return ceph_frag_make(ceph_frag_bits(f),
- ceph_frag_value(f) ^ (0x1000000 >> ceph_frag_bits(f)));
-}
-static inline __u32 ceph_frag_left_child(__u32 f)
-{
- return ceph_frag_make(ceph_frag_bits(f)+1, ceph_frag_value(f));
-}
-static inline __u32 ceph_frag_right_child(__u32 f)
-{
- return ceph_frag_make(ceph_frag_bits(f)+1,
- ceph_frag_value(f) | (0x1000000 >> (1+ceph_frag_bits(f))));
-}
static inline __u32 ceph_frag_make_child(__u32 f, int by, int i)
{
int newbits = ceph_frag_bits(f) + by;
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 71b1d6cdcb5d..8dbd7879fdc6 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -220,6 +220,7 @@ struct ceph_connection {
struct ceph_entity_addr actual_peer_addr;
/* message out temps */
+ struct ceph_msg_header out_hdr;
struct ceph_msg *out_msg; /* sending message (== tail of
out_sent) */
bool out_msg_done;
@@ -229,7 +230,6 @@ struct ceph_connection {
int out_kvec_left; /* kvec's left in out_kvec */
int out_skip; /* skip this many bytes */
int out_kvec_bytes; /* total bytes left */
- bool out_kvec_is_msg; /* kvec refers to out_msg */
int out_more; /* there is more data after the kvecs */
__le64 out_temp_ack; /* for writing an ack */
struct ceph_timespec out_temp_keepalive2; /* for writing keepalive2
diff --git a/include/linux/dax.h b/include/linux/dax.h
index b415e521528d..8204c3dc3800 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -36,4 +36,11 @@ static inline bool vma_is_dax(struct vm_area_struct *vma)
{
return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
}
+
+static inline bool dax_mapping(struct address_space *mapping)
+{
+ return mapping->host && IS_DAX(mapping->host);
+}
+int dax_writeback_mapping_range(struct address_space *mapping, loff_t start,
+ loff_t end);
#endif
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 8723f2a99e15..d6b3c9943a2c 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -25,7 +25,6 @@
*/
#ifndef DRBD_H
#define DRBD_H
-#include <linux/connector.h>
#include <asm/types.h>
#ifdef __KERNEL__
@@ -52,7 +51,7 @@
#endif
extern const char *drbd_buildtag(void);
-#define REL_VERSION "8.4.5"
+#define REL_VERSION "8.4.6"
#define API_VERSION 1
#define PRO_VERSION_MIN 86
#define PRO_VERSION_MAX 101
@@ -339,6 +338,8 @@ enum drbd_state_rv {
#define MDF_AL_CLEAN (1 << 7)
#define MDF_AL_DISABLED (1 << 8)
+#define MAX_PEERS 32
+
enum drbd_uuid_index {
UI_CURRENT,
UI_BITMAP,
@@ -349,14 +350,35 @@ enum drbd_uuid_index {
UI_EXTENDED_SIZE /* Everything. */
};
+#define HISTORY_UUIDS MAX_PEERS
+
enum drbd_timeout_flag {
UT_DEFAULT = 0,
UT_DEGRADED = 1,
UT_PEER_OUTDATED = 2,
};
+enum drbd_notification_type {
+ NOTIFY_EXISTS,
+ NOTIFY_CREATE,
+ NOTIFY_CHANGE,
+ NOTIFY_DESTROY,
+ NOTIFY_CALL,
+ NOTIFY_RESPONSE,
+
+ NOTIFY_CONTINUES = 0x8000,
+ NOTIFY_FLAGS = NOTIFY_CONTINUES,
+};
+
#define UUID_JUST_CREATED ((__u64)4)
+enum write_ordering_e {
+ WO_NONE,
+ WO_DRAIN_IO,
+ WO_BDEV_FLUSH,
+ WO_BIO_BARRIER
+};
+
/* magic numbers used in meta data and network packets */
#define DRBD_MAGIC 0x83740267
#define DRBD_MAGIC_BIG 0x835a
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 7b131ed8f9c6..2d0e5ad5de9d 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -250,6 +250,76 @@ GENL_struct(DRBD_NLA_DETACH_PARMS, 13, detach_parms,
__flg_field(1, DRBD_GENLA_F_MANDATORY, force_detach)
)
+GENL_struct(DRBD_NLA_RESOURCE_INFO, 15, resource_info,
+ __u32_field(1, 0, res_role)
+ __flg_field(2, 0, res_susp)
+ __flg_field(3, 0, res_susp_nod)
+ __flg_field(4, 0, res_susp_fen)
+ /* __flg_field(5, 0, res_weak) */
+)
+
+GENL_struct(DRBD_NLA_DEVICE_INFO, 16, device_info,
+ __u32_field(1, 0, dev_disk_state)
+)
+
+GENL_struct(DRBD_NLA_CONNECTION_INFO, 17, connection_info,
+ __u32_field(1, 0, conn_connection_state)
+ __u32_field(2, 0, conn_role)
+)
+
+GENL_struct(DRBD_NLA_PEER_DEVICE_INFO, 18, peer_device_info,
+ __u32_field(1, 0, peer_repl_state)
+ __u32_field(2, 0, peer_disk_state)
+ __u32_field(3, 0, peer_resync_susp_user)
+ __u32_field(4, 0, peer_resync_susp_peer)
+ __u32_field(5, 0, peer_resync_susp_dependency)
+)
+
+GENL_struct(DRBD_NLA_RESOURCE_STATISTICS, 19, resource_statistics,
+ __u32_field(1, 0, res_stat_write_ordering)
+)
+
+GENL_struct(DRBD_NLA_DEVICE_STATISTICS, 20, device_statistics,
+ __u64_field(1, 0, dev_size) /* (sectors) */
+ __u64_field(2, 0, dev_read) /* (sectors) */
+ __u64_field(3, 0, dev_write) /* (sectors) */
+ __u64_field(4, 0, dev_al_writes) /* activity log writes (count) */
+ __u64_field(5, 0, dev_bm_writes) /* bitmap writes (count) */
+ __u32_field(6, 0, dev_upper_pending) /* application requests in progress */
+ __u32_field(7, 0, dev_lower_pending) /* backing device requests in progress */
+ __flg_field(8, 0, dev_upper_blocked)
+ __flg_field(9, 0, dev_lower_blocked)
+ __flg_field(10, 0, dev_al_suspended) /* activity log suspended */
+ __u64_field(11, 0, dev_exposed_data_uuid)
+ __u64_field(12, 0, dev_current_uuid)
+ __u32_field(13, 0, dev_disk_flags)
+ __bin_field(14, 0, history_uuids, HISTORY_UUIDS * sizeof(__u64))
+)
+
+GENL_struct(DRBD_NLA_CONNECTION_STATISTICS, 21, connection_statistics,
+ __flg_field(1, 0, conn_congested)
+)
+
+GENL_struct(DRBD_NLA_PEER_DEVICE_STATISTICS, 22, peer_device_statistics,
+ __u64_field(1, 0, peer_dev_received) /* sectors */
+ __u64_field(2, 0, peer_dev_sent) /* sectors */
+ __u32_field(3, 0, peer_dev_pending) /* number of requests */
+ __u32_field(4, 0, peer_dev_unacked) /* number of requests */
+ __u64_field(5, 0, peer_dev_out_of_sync) /* sectors */
+ __u64_field(6, 0, peer_dev_resync_failed) /* sectors */
+ __u64_field(7, 0, peer_dev_bitmap_uuid)
+ __u32_field(9, 0, peer_dev_flags)
+)
+
+GENL_struct(DRBD_NLA_NOTIFICATION_HEADER, 23, drbd_notification_header,
+ __u32_field(1, DRBD_GENLA_F_MANDATORY, nh_type)
+)
+
+GENL_struct(DRBD_NLA_HELPER, 24, drbd_helper_info,
+ __str_field(1, DRBD_GENLA_F_MANDATORY, helper_name, 32)
+ __u32_field(2, DRBD_GENLA_F_MANDATORY, helper_status)
+)
+
/*
* Notifications and commands (genlmsghdr->cmd)
*/
@@ -382,3 +452,82 @@ GENL_op(DRBD_ADM_GET_TIMEOUT_TYPE, 26, GENL_doit(drbd_adm_get_timeout_type),
GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
GENL_op(DRBD_ADM_DOWN, 27, GENL_doit(drbd_adm_down),
GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
+
+GENL_op(DRBD_ADM_GET_RESOURCES, 30,
+ GENL_op_init(
+ .dumpit = drbd_adm_dump_resources,
+ ),
+ GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_GENLA_F_MANDATORY)
+ GENL_tla_expected(DRBD_NLA_RESOURCE_INFO, DRBD_GENLA_F_MANDATORY)
+ GENL_tla_expected(DRBD_NLA_RESOURCE_STATISTICS, DRBD_GENLA_F_MANDATORY))
+
+GENL_op(DRBD_ADM_GET_DEVICES, 31,
+ GENL_op_init(
+ .dumpit = drbd_adm_dump_devices,
+ .done = drbd_adm_dump_devices_done,
+ ),
+ GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_GENLA_F_MANDATORY)
+ GENL_tla_expected(DRBD_NLA_DEVICE_INFO, DRBD_GENLA_F_MANDATORY)
+ GENL_tla_expected(DRBD_NLA_DEVICE_STATISTICS, DRBD_GENLA_F_MANDATORY))
+
+GENL_op(DRBD_ADM_GET_CONNECTIONS, 32,
+ GENL_op_init(
+ .dumpit = drbd_adm_dump_connections,
+ .done = drbd_adm_dump_connections_done,
+ ),
+ GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_GENLA_F_MANDATORY)
+ GENL_tla_expected(DRBD_NLA_CONNECTION_INFO, DRBD_GENLA_F_MANDATORY)
+ GENL_tla_expected(DRBD_NLA_CONNECTION_STATISTICS, DRBD_GENLA_F_MANDATORY))
+
+GENL_op(DRBD_ADM_GET_PEER_DEVICES, 33,
+ GENL_op_init(
+ .dumpit = drbd_adm_dump_peer_devices,
+ .done = drbd_adm_dump_peer_devices_done,
+ ),
+ GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_GENLA_F_MANDATORY)
+ GENL_tla_expected(DRBD_NLA_PEER_DEVICE_INFO, DRBD_GENLA_F_MANDATORY)
+ GENL_tla_expected(DRBD_NLA_PEER_DEVICE_STATISTICS, DRBD_GENLA_F_MANDATORY))
+
+GENL_notification(
+ DRBD_RESOURCE_STATE, 34, events,
+ GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
+ GENL_tla_expected(DRBD_NLA_NOTIFICATION_HEADER, DRBD_F_REQUIRED)
+ GENL_tla_expected(DRBD_NLA_RESOURCE_INFO, DRBD_F_REQUIRED)
+ GENL_tla_expected(DRBD_NLA_RESOURCE_STATISTICS, DRBD_F_REQUIRED))
+
+GENL_notification(
+ DRBD_DEVICE_STATE, 35, events,
+ GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
+ GENL_tla_expected(DRBD_NLA_NOTIFICATION_HEADER, DRBD_F_REQUIRED)
+ GENL_tla_expected(DRBD_NLA_DEVICE_INFO, DRBD_F_REQUIRED)
+ GENL_tla_expected(DRBD_NLA_DEVICE_STATISTICS, DRBD_F_REQUIRED))
+
+GENL_notification(
+ DRBD_CONNECTION_STATE, 36, events,
+ GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
+ GENL_tla_expected(DRBD_NLA_NOTIFICATION_HEADER, DRBD_F_REQUIRED)
+ GENL_tla_expected(DRBD_NLA_CONNECTION_INFO, DRBD_F_REQUIRED)
+ GENL_tla_expected(DRBD_NLA_CONNECTION_STATISTICS, DRBD_F_REQUIRED))
+
+GENL_notification(
+ DRBD_PEER_DEVICE_STATE, 37, events,
+ GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
+ GENL_tla_expected(DRBD_NLA_NOTIFICATION_HEADER, DRBD_F_REQUIRED)
+ GENL_tla_expected(DRBD_NLA_PEER_DEVICE_INFO, DRBD_F_REQUIRED)
+ GENL_tla_expected(DRBD_NLA_PEER_DEVICE_STATISTICS, DRBD_F_REQUIRED))
+
+GENL_op(
+ DRBD_ADM_GET_INITIAL_STATE, 38,
+ GENL_op_init(
+ .dumpit = drbd_adm_get_initial_state,
+ ),
+ GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_GENLA_F_MANDATORY))
+
+GENL_notification(
+ DRBD_HELPER, 40, events,
+ GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED)
+ GENL_tla_expected(DRBD_NLA_HELPER, DRBD_F_REQUIRED))
+
+GENL_notification(
+ DRBD_INITIAL_STATE_DONE, 41, events,
+ GENL_tla_expected(DRBD_NLA_NOTIFICATION_HEADER, DRBD_F_REQUIRED))
diff --git a/include/linux/fs.h b/include/linux/fs.h
index eb73d74ed992..1a2046275cdf 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -433,7 +433,8 @@ struct address_space {
struct rw_semaphore i_mmap_rwsem; /* protect tree, count, list */
/* Protected by tree_lock together with the radix tree */
unsigned long nrpages; /* number of total pages */
- unsigned long nrshadows; /* number of shadow entries */
+ /* number of shadow or DAX exceptional entries */
+ unsigned long nrexceptional;
pgoff_t writeback_index;/* writeback starts here */
const struct address_space_operations *a_ops; /* methods */
unsigned long flags; /* error bits/gfp mask */
@@ -714,6 +715,31 @@ enum inode_i_mutex_lock_class
I_MUTEX_PARENT2,
};
+static inline void inode_lock(struct inode *inode)
+{
+ mutex_lock(&inode->i_mutex);
+}
+
+static inline void inode_unlock(struct inode *inode)
+{
+ mutex_unlock(&inode->i_mutex);
+}
+
+static inline int inode_trylock(struct inode *inode)
+{
+ return mutex_trylock(&inode->i_mutex);
+}
+
+static inline int inode_is_locked(struct inode *inode)
+{
+ return mutex_is_locked(&inode->i_mutex);
+}
+
+static inline void inode_lock_nested(struct inode *inode, unsigned subclass)
+{
+ mutex_lock_nested(&inode->i_mutex, subclass);
+}
+
void lock_two_nondirectories(struct inode *, struct inode*);
void unlock_two_nondirectories(struct inode *, struct inode*);
@@ -3047,8 +3073,8 @@ static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx)
}
static inline bool dir_relax(struct inode *inode)
{
- mutex_unlock(&inode->i_mutex);
- mutex_lock(&inode->i_mutex);
+ inode_unlock(inode);
+ inode_lock(inode);
return !IS_DEADDIR(inode);
}
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index cfe81e10bd54..459fd25b378e 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -120,15 +120,15 @@ extern void vma_adjust_trans_huge(struct vm_area_struct *vma,
unsigned long start,
unsigned long end,
long adjust_next);
-extern bool __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
- spinlock_t **ptl);
+extern spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd,
+ struct vm_area_struct *vma);
/* mmap_sem must be held on entry */
-static inline bool pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
- spinlock_t **ptl)
+static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
+ struct vm_area_struct *vma)
{
VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma);
if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd))
- return __pmd_trans_huge_lock(pmd, vma, ptl);
+ return __pmd_trans_huge_lock(pmd, vma);
else
return false;
}
@@ -190,10 +190,10 @@ static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
long adjust_next)
{
}
-static inline bool pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
- spinlock_t **ptl)
+static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
+ struct vm_area_struct *vma)
{
- return false;
+ return NULL;
}
static inline int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
diff --git a/include/linux/idr.h b/include/linux/idr.h
index 013fd9bc4cb6..083d61e92706 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -135,6 +135,20 @@ static inline void *idr_find(struct idr *idr, int id)
#define idr_for_each_entry(idp, entry, id) \
for (id = 0; ((entry) = idr_get_next(idp, &(id))) != NULL; ++id)
+/**
+ * idr_for_each_entry - continue iteration over an idr's elements of a given type
+ * @idp: idr handle
+ * @entry: the type * to use as cursor
+ * @id: id entry's key
+ *
+ * Continue to iterate over list of given type, continuing after
+ * the current position.
+ */
+#define idr_for_each_entry_continue(idp, entry, id) \
+ for ((entry) = idr_get_next((idp), &(id)); \
+ entry; \
+ ++id, (entry) = idr_get_next((idp), &(id)))
+
/*
* IDA - IDR based id allocator, use when translation from id to
* pointer isn't necessary.
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index cb30edbfe9fc..0e95fcc75b2a 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -413,7 +413,7 @@ enum
NET_TX_SOFTIRQ,
NET_RX_SOFTIRQ,
BLOCK_SOFTIRQ,
- BLOCK_IOPOLL_SOFTIRQ,
+ IRQ_POLL_SOFTIRQ,
TASKLET_SOFTIRQ,
SCHED_SOFTIRQ,
HRTIMER_SOFTIRQ, /* Unused, but kept as tools rely on the
diff --git a/include/linux/irq_poll.h b/include/linux/irq_poll.h
new file mode 100644
index 000000000000..3e8c1b8fb9be
--- /dev/null
+++ b/include/linux/irq_poll.h
@@ -0,0 +1,25 @@
+#ifndef IRQ_POLL_H
+#define IRQ_POLL_H
+
+struct irq_poll;
+typedef int (irq_poll_fn)(struct irq_poll *, int);
+
+struct irq_poll {
+ struct list_head list;
+ unsigned long state;
+ int weight;
+ irq_poll_fn *poll;
+};
+
+enum {
+ IRQ_POLL_F_SCHED = 0,
+ IRQ_POLL_F_DISABLE = 1,
+};
+
+extern void irq_poll_sched(struct irq_poll *);
+extern void irq_poll_init(struct irq_poll *, int, irq_poll_fn *);
+extern void irq_poll_complete(struct irq_poll *);
+extern void irq_poll_enable(struct irq_poll *);
+extern void irq_poll_disable(struct irq_poll *);
+
+#endif
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index 034117b3be5f..d6750111e48e 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -1,6 +1,8 @@
#ifndef NVM_H
#define NVM_H
+#include <linux/types.h>
+
enum {
NVM_IO_OK = 0,
NVM_IO_REQUEUE = 1,
@@ -11,12 +13,74 @@ enum {
NVM_IOTYPE_GC = 1,
};
+#define NVM_BLK_BITS (16)
+#define NVM_PG_BITS (16)
+#define NVM_SEC_BITS (8)
+#define NVM_PL_BITS (8)
+#define NVM_LUN_BITS (8)
+#define NVM_CH_BITS (8)
+
+struct ppa_addr {
+ /* Generic structure for all addresses */
+ union {
+ struct {
+ u64 blk : NVM_BLK_BITS;
+ u64 pg : NVM_PG_BITS;
+ u64 sec : NVM_SEC_BITS;
+ u64 pl : NVM_PL_BITS;
+ u64 lun : NVM_LUN_BITS;
+ u64 ch : NVM_CH_BITS;
+ } g;
+
+ u64 ppa;
+ };
+};
+
+struct nvm_rq;
+struct nvm_id;
+struct nvm_dev;
+
+typedef int (nvm_l2p_update_fn)(u64, u32, __le64 *, void *);
+typedef int (nvm_bb_update_fn)(struct ppa_addr, int, u8 *, void *);
+typedef int (nvm_id_fn)(struct nvm_dev *, struct nvm_id *);
+typedef int (nvm_get_l2p_tbl_fn)(struct nvm_dev *, u64, u32,
+ nvm_l2p_update_fn *, void *);
+typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, int,
+ nvm_bb_update_fn *, void *);
+typedef int (nvm_op_set_bb_fn)(struct nvm_dev *, struct nvm_rq *, int);
+typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *);
+typedef int (nvm_erase_blk_fn)(struct nvm_dev *, struct nvm_rq *);
+typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *);
+typedef void (nvm_destroy_dma_pool_fn)(void *);
+typedef void *(nvm_dev_dma_alloc_fn)(struct nvm_dev *, void *, gfp_t,
+ dma_addr_t *);
+typedef void (nvm_dev_dma_free_fn)(void *, void*, dma_addr_t);
+
+struct nvm_dev_ops {
+ nvm_id_fn *identity;
+ nvm_get_l2p_tbl_fn *get_l2p_tbl;
+ nvm_op_bb_tbl_fn *get_bb_tbl;
+ nvm_op_set_bb_fn *set_bb_tbl;
+
+ nvm_submit_io_fn *submit_io;
+ nvm_erase_blk_fn *erase_block;
+
+ nvm_create_dma_pool_fn *create_dma_pool;
+ nvm_destroy_dma_pool_fn *destroy_dma_pool;
+ nvm_dev_dma_alloc_fn *dev_dma_alloc;
+ nvm_dev_dma_free_fn *dev_dma_free;
+
+ unsigned int max_phys_sect;
+};
+
+
+
#ifdef CONFIG_NVM
#include <linux/blkdev.h>
-#include <linux/types.h>
#include <linux/file.h>
#include <linux/dmapool.h>
+#include <uapi/linux/lightnvm.h>
enum {
/* HW Responsibilities */
@@ -58,8 +122,29 @@ enum {
/* Block Types */
NVM_BLK_T_FREE = 0x0,
NVM_BLK_T_BAD = 0x1,
- NVM_BLK_T_DEV = 0x2,
- NVM_BLK_T_HOST = 0x4,
+ NVM_BLK_T_GRWN_BAD = 0x2,
+ NVM_BLK_T_DEV = 0x4,
+ NVM_BLK_T_HOST = 0x8,
+
+ /* Memory capabilities */
+ NVM_ID_CAP_SLC = 0x1,
+ NVM_ID_CAP_CMD_SUSPEND = 0x2,
+ NVM_ID_CAP_SCRAMBLE = 0x4,
+ NVM_ID_CAP_ENCRYPT = 0x8,
+
+ /* Memory types */
+ NVM_ID_FMTYPE_SLC = 0,
+ NVM_ID_FMTYPE_MLC = 1,
+};
+
+struct nvm_id_lp_mlc {
+ u16 num_pairs;
+ u8 pairs[886];
+};
+
+struct nvm_id_lp_tbl {
+ __u8 id[8];
+ struct nvm_id_lp_mlc mlc;
};
struct nvm_id_group {
@@ -82,6 +167,8 @@ struct nvm_id_group {
u32 mpos;
u32 mccap;
u16 cpar;
+
+ struct nvm_id_lp_tbl lptbl;
};
struct nvm_addr_format {
@@ -125,28 +212,8 @@ struct nvm_tgt_instance {
#define NVM_VERSION_MINOR 0
#define NVM_VERSION_PATCH 0
-#define NVM_BLK_BITS (16)
-#define NVM_PG_BITS (16)
-#define NVM_SEC_BITS (8)
-#define NVM_PL_BITS (8)
-#define NVM_LUN_BITS (8)
-#define NVM_CH_BITS (8)
-
-struct ppa_addr {
- /* Generic structure for all addresses */
- union {
- struct {
- u64 blk : NVM_BLK_BITS;
- u64 pg : NVM_PG_BITS;
- u64 sec : NVM_SEC_BITS;
- u64 pl : NVM_PL_BITS;
- u64 lun : NVM_LUN_BITS;
- u64 ch : NVM_CH_BITS;
- } g;
-
- u64 ppa;
- };
-};
+struct nvm_rq;
+typedef void (nvm_end_io_fn)(struct nvm_rq *);
struct nvm_rq {
struct nvm_tgt_instance *ins;
@@ -164,9 +231,14 @@ struct nvm_rq {
void *metadata;
dma_addr_t dma_metadata;
+ struct completion *wait;
+ nvm_end_io_fn *end_io;
+
uint8_t opcode;
uint16_t nr_pages;
uint16_t flags;
+
+ int error;
};
static inline struct nvm_rq *nvm_rq_from_pdu(void *pdu)
@@ -181,51 +253,31 @@ static inline void *nvm_rq_to_pdu(struct nvm_rq *rqdata)
struct nvm_block;
-typedef int (nvm_l2p_update_fn)(u64, u32, __le64 *, void *);
-typedef int (nvm_bb_update_fn)(struct ppa_addr, int, u8 *, void *);
-typedef int (nvm_id_fn)(struct nvm_dev *, struct nvm_id *);
-typedef int (nvm_get_l2p_tbl_fn)(struct nvm_dev *, u64, u32,
- nvm_l2p_update_fn *, void *);
-typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, int,
- nvm_bb_update_fn *, void *);
-typedef int (nvm_op_set_bb_fn)(struct nvm_dev *, struct nvm_rq *, int);
-typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *);
-typedef int (nvm_erase_blk_fn)(struct nvm_dev *, struct nvm_rq *);
-typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *);
-typedef void (nvm_destroy_dma_pool_fn)(void *);
-typedef void *(nvm_dev_dma_alloc_fn)(struct nvm_dev *, void *, gfp_t,
- dma_addr_t *);
-typedef void (nvm_dev_dma_free_fn)(void *, void*, dma_addr_t);
-
-struct nvm_dev_ops {
- nvm_id_fn *identity;
- nvm_get_l2p_tbl_fn *get_l2p_tbl;
- nvm_op_bb_tbl_fn *get_bb_tbl;
- nvm_op_set_bb_fn *set_bb_tbl;
-
- nvm_submit_io_fn *submit_io;
- nvm_erase_blk_fn *erase_block;
-
- nvm_create_dma_pool_fn *create_dma_pool;
- nvm_destroy_dma_pool_fn *destroy_dma_pool;
- nvm_dev_dma_alloc_fn *dev_dma_alloc;
- nvm_dev_dma_free_fn *dev_dma_free;
-
- unsigned int max_phys_sect;
-};
-
struct nvm_lun {
int id;
int lun_id;
int chnl_id;
- unsigned int nr_inuse_blocks; /* Number of used blocks */
+ /* It is up to the target to mark blocks as closed. If the target does
+ * not do it, all blocks are marked as open, and nr_open_blocks
+ * represents the number of blocks in use
+ */
+ unsigned int nr_open_blocks; /* Number of used, writable blocks */
+ unsigned int nr_closed_blocks; /* Number of used, read-only blocks */
unsigned int nr_free_blocks; /* Number of unused blocks */
unsigned int nr_bad_blocks; /* Number of bad blocks */
- struct nvm_block *blocks;
spinlock_t lock;
+
+ struct nvm_block *blocks;
+};
+
+enum {
+ NVM_BLK_ST_FREE = 0x1, /* Free block */
+ NVM_BLK_ST_OPEN = 0x2, /* Open block - read-write */
+ NVM_BLK_ST_CLOSED = 0x4, /* Closed block - read-only */
+ NVM_BLK_ST_BAD = 0x8, /* Bad block */
};
struct nvm_block {
@@ -234,7 +286,16 @@ struct nvm_block {
unsigned long id;
void *priv;
- int type;
+ int state;
+};
+
+/* system block cpu representation */
+struct nvm_sb_info {
+ unsigned long seqnr;
+ unsigned long erase_cnt;
+ unsigned int version;
+ char mmtype[NVM_MMTYPE_LEN];
+ struct ppa_addr fs_ppa;
};
struct nvm_dev {
@@ -247,6 +308,9 @@ struct nvm_dev {
struct nvmm_type *mt;
void *mp;
+ /* System blocks */
+ struct nvm_sb_info sb;
+
/* Device information */
int nr_chnls;
int nr_planes;
@@ -256,6 +320,7 @@ struct nvm_dev {
int blks_per_lun;
int sec_size;
int oob_size;
+ int mccap;
struct nvm_addr_format ppaf;
/* Calculated/Cached values. These do not reflect the actual usable
@@ -268,6 +333,10 @@ struct nvm_dev {
int sec_per_blk;
int sec_per_lun;
+ /* lower page table */
+ int lps_per_blk;
+ int *lptbl;
+
unsigned long total_pages;
unsigned long total_blocks;
int nr_luns;
@@ -280,6 +349,8 @@ struct nvm_dev {
/* Backend device */
struct request_queue *q;
char name[DISK_NAME_LEN];
+
+ struct mutex mlock;
};
static inline struct ppa_addr generic_to_dev_addr(struct nvm_dev *dev,
@@ -345,9 +416,13 @@ static inline struct ppa_addr block_to_ppa(struct nvm_dev *dev,
return ppa;
}
+static inline int ppa_to_slc(struct nvm_dev *dev, int slc_pg)
+{
+ return dev->lptbl[slc_pg];
+}
+
typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *);
typedef sector_t (nvm_tgt_capacity_fn)(void *);
-typedef int (nvm_tgt_end_io_fn)(struct nvm_rq *, int);
typedef void *(nvm_tgt_init_fn)(struct nvm_dev *, struct gendisk *, int, int);
typedef void (nvm_tgt_exit_fn)(void *);
@@ -358,7 +433,7 @@ struct nvm_tgt_type {
/* target entry points */
nvm_tgt_make_rq_fn *make_rq;
nvm_tgt_capacity_fn *capacity;
- nvm_tgt_end_io_fn *end_io;
+ nvm_end_io_fn *end_io;
/* module-specific init/teardown */
nvm_tgt_init_fn *init;
@@ -383,7 +458,6 @@ typedef int (nvmm_open_blk_fn)(struct nvm_dev *, struct nvm_block *);
typedef int (nvmm_close_blk_fn)(struct nvm_dev *, struct nvm_block *);
typedef void (nvmm_flush_blk_fn)(struct nvm_dev *, struct nvm_block *);
typedef int (nvmm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *);
-typedef int (nvmm_end_io_fn)(struct nvm_rq *, int);
typedef int (nvmm_erase_blk_fn)(struct nvm_dev *, struct nvm_block *,
unsigned long);
typedef struct nvm_lun *(nvmm_get_lun_fn)(struct nvm_dev *, int);
@@ -397,6 +471,8 @@ struct nvmm_type {
nvmm_unregister_fn *unregister_mgr;
/* Block administration callbacks */
+ nvmm_get_blk_fn *get_blk_unlocked;
+ nvmm_put_blk_fn *put_blk_unlocked;
nvmm_get_blk_fn *get_blk;
nvmm_put_blk_fn *put_blk;
nvmm_open_blk_fn *open_blk;
@@ -404,7 +480,6 @@ struct nvmm_type {
nvmm_flush_blk_fn *flush_blk;
nvmm_submit_io_fn *submit_io;
- nvmm_end_io_fn *end_io;
nvmm_erase_blk_fn *erase_blk;
/* Configuration management */
@@ -418,6 +493,10 @@ struct nvmm_type {
extern int nvm_register_mgr(struct nvmm_type *);
extern void nvm_unregister_mgr(struct nvmm_type *);
+extern struct nvm_block *nvm_get_blk_unlocked(struct nvm_dev *,
+ struct nvm_lun *, unsigned long);
+extern void nvm_put_blk_unlocked(struct nvm_dev *, struct nvm_block *);
+
extern struct nvm_block *nvm_get_blk(struct nvm_dev *, struct nvm_lun *,
unsigned long);
extern void nvm_put_blk(struct nvm_dev *, struct nvm_block *);
@@ -427,7 +506,36 @@ extern int nvm_register(struct request_queue *, char *,
extern void nvm_unregister(char *);
extern int nvm_submit_io(struct nvm_dev *, struct nvm_rq *);
+extern void nvm_generic_to_addr_mode(struct nvm_dev *, struct nvm_rq *);
+extern void nvm_addr_to_generic_mode(struct nvm_dev *, struct nvm_rq *);
+extern int nvm_set_rqd_ppalist(struct nvm_dev *, struct nvm_rq *,
+ struct ppa_addr *, int);
+extern void nvm_free_rqd_ppalist(struct nvm_dev *, struct nvm_rq *);
+extern int nvm_erase_ppa(struct nvm_dev *, struct ppa_addr *, int);
extern int nvm_erase_blk(struct nvm_dev *, struct nvm_block *);
+extern void nvm_end_io(struct nvm_rq *, int);
+extern int nvm_submit_ppa(struct nvm_dev *, struct ppa_addr *, int, int, int,
+ void *, int);
+
+/* sysblk.c */
+#define NVM_SYSBLK_MAGIC 0x4E564D53 /* "NVMS" */
+
+/* system block on disk representation */
+struct nvm_system_block {
+ __be32 magic; /* magic signature */
+ __be32 seqnr; /* sequence number */
+ __be32 erase_cnt; /* erase count */
+ __be16 version; /* version number */
+ u8 mmtype[NVM_MMTYPE_LEN]; /* media manager name */
+ __be64 fs_ppa; /* PPA for media manager
+ * superblock */
+};
+
+extern int nvm_get_sysblock(struct nvm_dev *, struct nvm_sb_info *);
+extern int nvm_update_sysblock(struct nvm_dev *, struct nvm_sb_info *);
+extern int nvm_init_sysblock(struct nvm_dev *, struct nvm_sb_info *);
+
+extern int nvm_dev_factory(struct nvm_dev *, int flags);
#else /* CONFIG_NVM */
struct nvm_dev_ops;
diff --git a/include/linux/lru_cache.h b/include/linux/lru_cache.h
index 46262284de47..04fc6e6c7ff0 100644
--- a/include/linux/lru_cache.h
+++ b/include/linux/lru_cache.h
@@ -264,7 +264,7 @@ extern unsigned int lc_put(struct lru_cache *lc, struct lc_element *e);
extern void lc_committed(struct lru_cache *lc);
struct seq_file;
-extern size_t lc_seq_printf_stats(struct seq_file *seq, struct lru_cache *lc);
+extern void lc_seq_printf_stats(struct seq_file *seq, struct lru_cache *lc);
extern void lc_seq_dump_details(struct seq_file *seq, struct lru_cache *lc, char *utext,
void (*detail) (struct seq_file *, struct lc_element *));
diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h
index 58391f2e0414..116b284bc4ce 100644
--- a/include/linux/mlx4/cmd.h
+++ b/include/linux/mlx4/cmd.h
@@ -206,7 +206,8 @@ enum {
MLX4_SET_PORT_GID_TABLE = 0x5,
MLX4_SET_PORT_PRIO2TC = 0x8,
MLX4_SET_PORT_SCHEDULER = 0x9,
- MLX4_SET_PORT_VXLAN = 0xB
+ MLX4_SET_PORT_VXLAN = 0xB,
+ MLX4_SET_PORT_ROCE_ADDR = 0xD
};
enum {
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index d3133be12d92..430a929f048b 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -216,6 +216,7 @@ enum {
MLX4_DEV_CAP_FLAG2_SKIP_OUTER_VLAN = 1LL << 30,
MLX4_DEV_CAP_FLAG2_UPDATE_QP_SRC_CHECK_LB = 1ULL << 31,
MLX4_DEV_CAP_FLAG2_LB_SRC_CHK = 1ULL << 32,
+ MLX4_DEV_CAP_FLAG2_ROCE_V1_V2 = 1ULL << 33,
};
enum {
@@ -267,12 +268,14 @@ enum {
MLX4_BMME_FLAG_TYPE_2_WIN = 1 << 9,
MLX4_BMME_FLAG_RESERVED_LKEY = 1 << 10,
MLX4_BMME_FLAG_FAST_REG_WR = 1 << 11,
+ MLX4_BMME_FLAG_ROCE_V1_V2 = 1 << 19,
MLX4_BMME_FLAG_PORT_REMAP = 1 << 24,
MLX4_BMME_FLAG_VSD_INIT2RTR = 1 << 28,
};
enum {
- MLX4_FLAG_PORT_REMAP = MLX4_BMME_FLAG_PORT_REMAP
+ MLX4_FLAG_PORT_REMAP = MLX4_BMME_FLAG_PORT_REMAP,
+ MLX4_FLAG_ROCE_V1_V2 = MLX4_BMME_FLAG_ROCE_V1_V2
};
enum mlx4_event {
@@ -979,14 +982,11 @@ struct mlx4_mad_ifc {
for ((port) = 1; (port) <= (dev)->caps.num_ports; (port)++) \
if ((type) == (dev)->caps.port_mask[(port)])
-#define mlx4_foreach_non_ib_transport_port(port, dev) \
- for ((port) = 1; (port) <= (dev)->caps.num_ports; (port)++) \
- if (((dev)->caps.port_mask[port] != MLX4_PORT_TYPE_IB))
-
#define mlx4_foreach_ib_transport_port(port, dev) \
- for ((port) = 1; (port) <= (dev)->caps.num_ports; (port)++) \
+ for ((port) = 1; (port) <= (dev)->caps.num_ports; (port)++) \
if (((dev)->caps.port_mask[port] == MLX4_PORT_TYPE_IB) || \
- ((dev)->caps.flags & MLX4_DEV_CAP_FLAG_IBOE))
+ ((dev)->caps.flags & MLX4_DEV_CAP_FLAG_IBOE) || \
+ ((dev)->caps.flags2 & MLX4_DEV_CAP_FLAG2_ROCE_V1_V2))
#define MLX4_INVALID_SLAVE_ID 0xFF
#define MLX4_SINK_COUNTER_INDEX(dev) (dev->caps.max_counters - 1)
@@ -1457,6 +1457,7 @@ int mlx4_get_base_gid_ix(struct mlx4_dev *dev, int slave, int port);
int mlx4_config_vxlan_port(struct mlx4_dev *dev, __be16 udp_port);
int mlx4_disable_rx_port_check(struct mlx4_dev *dev, bool dis);
+int mlx4_config_roce_v2_port(struct mlx4_dev *dev, u16 udp_port);
int mlx4_virt2phy_port_map(struct mlx4_dev *dev, u32 port1, u32 port2);
int mlx4_vf_smi_enabled(struct mlx4_dev *dev, int slave, int port);
int mlx4_vf_get_enable_smi_admin(struct mlx4_dev *dev, int slave, int port);
diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h
index fe052e234906..587cdf943b52 100644
--- a/include/linux/mlx4/qp.h
+++ b/include/linux/mlx4/qp.h
@@ -194,7 +194,7 @@ struct mlx4_qp_context {
u8 mtu_msgmax;
u8 rq_size_stride;
u8 sq_size_stride;
- u8 rlkey;
+ u8 rlkey_roce_mode;
__be32 usr_page;
__be32 local_qpn;
__be32 remote_qpn;
@@ -204,7 +204,8 @@ struct mlx4_qp_context {
u32 reserved1;
__be32 next_send_psn;
__be32 cqn_send;
- u32 reserved2[2];
+ __be16 roce_entropy;
+ __be16 reserved2[3];
__be32 last_acked_psn;
__be32 ssn;
__be32 params2;
@@ -487,4 +488,14 @@ static inline struct mlx4_qp *__mlx4_qp_lookup(struct mlx4_dev *dev, u32 qpn)
void mlx4_qp_remove(struct mlx4_dev *dev, struct mlx4_qp *qp);
+static inline u16 folded_qp(u32 q)
+{
+ u16 res;
+
+ res = ((q & 0xff) ^ ((q & 0xff0000) >> 16)) | (q & 0xff00);
+ return res;
+}
+
+u16 mlx4_qp_roce_entropy(struct mlx4_dev *dev, u32 qpn);
+
#endif /* MLX4_QP_H */
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 7be845e30689..987764afa65c 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -223,6 +223,14 @@ enum {
#define MLX5_UMR_MTT_MASK (MLX5_UMR_MTT_ALIGNMENT - 1)
#define MLX5_UMR_MTT_MIN_CHUNK_SIZE MLX5_UMR_MTT_ALIGNMENT
+#define MLX5_USER_INDEX_LEN (MLX5_FLD_SZ_BYTES(qpc, user_index) * 8)
+
+enum {
+ MLX5_EVENT_QUEUE_TYPE_QP = 0,
+ MLX5_EVENT_QUEUE_TYPE_RQ = 1,
+ MLX5_EVENT_QUEUE_TYPE_SQ = 2,
+};
+
enum mlx5_event {
MLX5_EVENT_TYPE_COMP = 0x0,
@@ -280,6 +288,26 @@ enum {
};
enum {
+ MLX5_ROCE_VERSION_1 = 0,
+ MLX5_ROCE_VERSION_2 = 2,
+};
+
+enum {
+ MLX5_ROCE_VERSION_1_CAP = 1 << MLX5_ROCE_VERSION_1,
+ MLX5_ROCE_VERSION_2_CAP = 1 << MLX5_ROCE_VERSION_2,
+};
+
+enum {
+ MLX5_ROCE_L3_TYPE_IPV4 = 0,
+ MLX5_ROCE_L3_TYPE_IPV6 = 1,
+};
+
+enum {
+ MLX5_ROCE_L3_TYPE_IPV4_CAP = 1 << 1,
+ MLX5_ROCE_L3_TYPE_IPV6_CAP = 1 << 2,
+};
+
+enum {
MLX5_OPCODE_NOP = 0x00,
MLX5_OPCODE_SEND_INVAL = 0x01,
MLX5_OPCODE_RDMA_WRITE = 0x08,
@@ -446,7 +474,7 @@ struct mlx5_init_seg {
__be32 rsvd2[880];
__be32 internal_timer_h;
__be32 internal_timer_l;
- __be32 rsrv3[2];
+ __be32 rsvd3[2];
__be32 health_counter;
__be32 rsvd4[1019];
__be64 ieee1588_clk;
@@ -460,7 +488,9 @@ struct mlx5_eqe_comp {
};
struct mlx5_eqe_qp_srq {
- __be32 reserved[6];
+ __be32 reserved1[5];
+ u8 type;
+ u8 reserved2[3];
__be32 qp_srq_n;
};
@@ -651,6 +681,12 @@ enum {
};
enum {
+ MLX5_CQE_ROCE_L3_HEADER_TYPE_GRH = 0x0,
+ MLX5_CQE_ROCE_L3_HEADER_TYPE_IPV6 = 0x1,
+ MLX5_CQE_ROCE_L3_HEADER_TYPE_IPV4 = 0x2,
+};
+
+enum {
CQE_L2_OK = 1 << 0,
CQE_L3_OK = 1 << 1,
CQE_L4_OK = 1 << 2,
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 5162f3533042..1e3006dcf35d 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -115,6 +115,11 @@ enum {
MLX5_REG_HOST_ENDIANNESS = 0x7004,
};
+enum {
+ MLX5_ATOMIC_OPS_CMP_SWAP = 1 << 0,
+ MLX5_ATOMIC_OPS_FETCH_ADD = 1 << 1,
+};
+
enum mlx5_page_fault_resume_flags {
MLX5_PAGE_FAULT_RESUME_REQUESTOR = 1 << 0,
MLX5_PAGE_FAULT_RESUME_WRITE = 1 << 1,
@@ -341,9 +346,11 @@ struct mlx5_core_mr {
};
enum mlx5_res_type {
- MLX5_RES_QP,
- MLX5_RES_SRQ,
- MLX5_RES_XSRQ,
+ MLX5_RES_QP = MLX5_EVENT_QUEUE_TYPE_QP,
+ MLX5_RES_RQ = MLX5_EVENT_QUEUE_TYPE_RQ,
+ MLX5_RES_SQ = MLX5_EVENT_QUEUE_TYPE_SQ,
+ MLX5_RES_SRQ = 3,
+ MLX5_RES_XSRQ = 4,
};
struct mlx5_core_rsc_common {
@@ -651,13 +658,6 @@ extern struct workqueue_struct *mlx5_core_wq;
.struct_offset_bytes = offsetof(struct ib_unpacked_ ## header, field), \
.struct_size_bytes = sizeof((struct ib_unpacked_ ## header *)0)->field
-struct ib_field {
- size_t struct_offset_bytes;
- size_t struct_size_bytes;
- int offset_bits;
- int size_bits;
-};
-
static inline struct mlx5_core_dev *pci2mlx5_core_dev(struct pci_dev *pdev)
{
return pci_get_drvdata(pdev);
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 68d73f82e009..231ab6bcea76 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -67,6 +67,11 @@ enum {
};
enum {
+ MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE = 0x0,
+ MLX5_SET_HCA_CAP_OP_MOD_ATOMIC = 0x3,
+};
+
+enum {
MLX5_CMD_OP_QUERY_HCA_CAP = 0x100,
MLX5_CMD_OP_QUERY_ADAPTER = 0x101,
MLX5_CMD_OP_INIT_HCA = 0x102,
@@ -573,21 +578,24 @@ enum {
struct mlx5_ifc_atomic_caps_bits {
u8 reserved_0[0x40];
- u8 atomic_req_endianness[0x1];
- u8 reserved_1[0x1f];
+ u8 atomic_req_8B_endianess_mode[0x2];
+ u8 reserved_1[0x4];
+ u8 supported_atomic_req_8B_endianess_mode_1[0x1];
- u8 reserved_2[0x20];
+ u8 reserved_2[0x19];
- u8 reserved_3[0x10];
- u8 atomic_operations[0x10];
+ u8 reserved_3[0x20];
u8 reserved_4[0x10];
- u8 atomic_size_qp[0x10];
+ u8 atomic_operations[0x10];
u8 reserved_5[0x10];
+ u8 atomic_size_qp[0x10];
+
+ u8 reserved_6[0x10];
u8 atomic_size_dc[0x10];
- u8 reserved_6[0x720];
+ u8 reserved_7[0x720];
};
struct mlx5_ifc_odp_cap_bits {
@@ -850,7 +858,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
u8 reserved_66[0x8];
u8 log_uar_page_sz[0x10];
- u8 reserved_67[0x40];
+ u8 reserved_67[0x20];
+ u8 device_frequency_mhz[0x20];
u8 device_frequency_khz[0x20];
u8 reserved_68[0x5f];
u8 cqe_zip[0x1];
@@ -2215,19 +2224,25 @@ struct mlx5_ifc_nic_vport_context_bits {
u8 mtu[0x10];
- u8 reserved_3[0x640];
+ u8 system_image_guid[0x40];
+ u8 port_guid[0x40];
+ u8 node_guid[0x40];
+
+ u8 reserved_3[0x140];
+ u8 qkey_violation_counter[0x10];
+ u8 reserved_4[0x430];
u8 promisc_uc[0x1];
u8 promisc_mc[0x1];
u8 promisc_all[0x1];
- u8 reserved_4[0x2];
+ u8 reserved_5[0x2];
u8 allowed_list_type[0x3];
- u8 reserved_5[0xc];
+ u8 reserved_6[0xc];
u8 allowed_list_size[0xc];
struct mlx5_ifc_mac_address_layout_bits permanent_address;
- u8 reserved_6[0x20];
+ u8 reserved_7[0x20];
u8 current_uc_mac_address[0][0x40];
};
@@ -4199,6 +4214,13 @@ struct mlx5_ifc_modify_tis_out_bits {
u8 reserved_1[0x40];
};
+struct mlx5_ifc_modify_tis_bitmask_bits {
+ u8 reserved_0[0x20];
+
+ u8 reserved_1[0x1f];
+ u8 prio[0x1];
+};
+
struct mlx5_ifc_modify_tis_in_bits {
u8 opcode[0x10];
u8 reserved_0[0x10];
@@ -4211,7 +4233,7 @@ struct mlx5_ifc_modify_tis_in_bits {
u8 reserved_3[0x20];
- u8 modify_bitmask[0x40];
+ struct mlx5_ifc_modify_tis_bitmask_bits bitmask;
u8 reserved_4[0x40];
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index f079fb1a31f7..5b8c89ffaa58 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -85,7 +85,16 @@ enum mlx5_qp_state {
MLX5_QP_STATE_ERR = 6,
MLX5_QP_STATE_SQ_DRAINING = 7,
MLX5_QP_STATE_SUSPENDED = 9,
- MLX5_QP_NUM_STATE
+ MLX5_QP_NUM_STATE,
+ MLX5_QP_STATE,
+ MLX5_QP_STATE_BAD,
+};
+
+enum {
+ MLX5_SQ_STATE_NA = MLX5_SQC_STATE_ERR + 1,
+ MLX5_SQ_NUM_STATE = MLX5_SQ_STATE_NA + 1,
+ MLX5_RQ_STATE_NA = MLX5_RQC_STATE_ERR + 1,
+ MLX5_RQ_NUM_STATE = MLX5_RQ_STATE_NA + 1,
};
enum {
@@ -130,6 +139,9 @@ enum {
MLX5_QP_BIT_RWE = 1 << 14,
MLX5_QP_BIT_RAE = 1 << 13,
MLX5_QP_BIT_RIC = 1 << 4,
+ MLX5_QP_BIT_CC_SLAVE_RECV = 1 << 2,
+ MLX5_QP_BIT_CC_SLAVE_SEND = 1 << 1,
+ MLX5_QP_BIT_CC_MASTER = 1 << 0
};
enum {
@@ -248,8 +260,12 @@ struct mlx5_av {
__be32 dqp_dct;
u8 stat_rate_sl;
u8 fl_mlid;
- __be16 rlid;
- u8 reserved0[10];
+ union {
+ __be16 rlid;
+ __be16 udp_sport;
+ };
+ u8 reserved0[4];
+ u8 rmac[6];
u8 tclass;
u8 hop_limit;
__be32 grh_gid_fl;
@@ -456,11 +472,16 @@ struct mlx5_qp_path {
u8 static_rate;
u8 hop_limit;
__be32 tclass_flowlabel;
- u8 rgid[16];
- u8 rsvd1[4];
- u8 sl;
+ union {
+ u8 rgid[16];
+ u8 rip[16];
+ };
+ u8 f_dscp_ecn_prio;
+ u8 ecn_dscp;
+ __be16 udp_sport;
+ u8 dci_cfi_prio_sl;
u8 port;
- u8 rsvd2[6];
+ u8 rmac[6];
};
struct mlx5_qp_context {
@@ -620,8 +641,7 @@ int mlx5_core_create_qp(struct mlx5_core_dev *dev,
struct mlx5_core_qp *qp,
struct mlx5_create_qp_mbox_in *in,
int inlen);
-int mlx5_core_qp_modify(struct mlx5_core_dev *dev, enum mlx5_qp_state cur_state,
- enum mlx5_qp_state new_state,
+int mlx5_core_qp_modify(struct mlx5_core_dev *dev, u16 operation,
struct mlx5_modify_qp_mbox_in *in, int sqd_event,
struct mlx5_core_qp *qp);
int mlx5_core_destroy_qp(struct mlx5_core_dev *dev,
@@ -639,6 +659,14 @@ void mlx5_debug_qp_remove(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp);
int mlx5_core_page_fault_resume(struct mlx5_core_dev *dev, u32 qpn,
u8 context, int error);
#endif
+int mlx5_core_create_rq_tracked(struct mlx5_core_dev *dev, u32 *in, int inlen,
+ struct mlx5_core_qp *rq);
+void mlx5_core_destroy_rq_tracked(struct mlx5_core_dev *dev,
+ struct mlx5_core_qp *rq);
+int mlx5_core_create_sq_tracked(struct mlx5_core_dev *dev, u32 *in, int inlen,
+ struct mlx5_core_qp *sq);
+void mlx5_core_destroy_sq_tracked(struct mlx5_core_dev *dev,
+ struct mlx5_core_qp *sq);
static inline const char *mlx5_qp_type_str(int type)
{
diff --git a/include/linux/mlx5/transobj.h b/include/linux/mlx5/transobj.h
new file mode 100644
index 000000000000..88441f5ece25
--- /dev/null
+++ b/include/linux/mlx5/transobj.h
@@ -0,0 +1,78 @@
+/*
+ * Copyright (c) 2013-2015, Mellanox Technologies, Ltd. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef __TRANSOBJ_H__
+#define __TRANSOBJ_H__
+
+#include <linux/mlx5/driver.h>
+
+int mlx5_core_alloc_transport_domain(struct mlx5_core_dev *dev, u32 *tdn);
+void mlx5_core_dealloc_transport_domain(struct mlx5_core_dev *dev, u32 tdn);
+int mlx5_core_create_rq(struct mlx5_core_dev *dev, u32 *in, int inlen,
+ u32 *rqn);
+int mlx5_core_modify_rq(struct mlx5_core_dev *dev, u32 rqn, u32 *in, int inlen);
+void mlx5_core_destroy_rq(struct mlx5_core_dev *dev, u32 rqn);
+int mlx5_core_query_rq(struct mlx5_core_dev *dev, u32 rqn, u32 *out);
+int mlx5_core_create_sq(struct mlx5_core_dev *dev, u32 *in, int inlen,
+ u32 *sqn);
+int mlx5_core_modify_sq(struct mlx5_core_dev *dev, u32 sqn, u32 *in, int inlen);
+void mlx5_core_destroy_sq(struct mlx5_core_dev *dev, u32 sqn);
+int mlx5_core_query_sq(struct mlx5_core_dev *dev, u32 sqn, u32 *out);
+int mlx5_core_create_tir(struct mlx5_core_dev *dev, u32 *in, int inlen,
+ u32 *tirn);
+int mlx5_core_modify_tir(struct mlx5_core_dev *dev, u32 tirn, u32 *in,
+ int inlen);
+void mlx5_core_destroy_tir(struct mlx5_core_dev *dev, u32 tirn);
+int mlx5_core_create_tis(struct mlx5_core_dev *dev, u32 *in, int inlen,
+ u32 *tisn);
+int mlx5_core_modify_tis(struct mlx5_core_dev *dev, u32 tisn, u32 *in,
+ int inlen);
+void mlx5_core_destroy_tis(struct mlx5_core_dev *dev, u32 tisn);
+int mlx5_core_create_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen,
+ u32 *rmpn);
+int mlx5_core_modify_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen);
+int mlx5_core_destroy_rmp(struct mlx5_core_dev *dev, u32 rmpn);
+int mlx5_core_query_rmp(struct mlx5_core_dev *dev, u32 rmpn, u32 *out);
+int mlx5_core_arm_rmp(struct mlx5_core_dev *dev, u32 rmpn, u16 lwm);
+int mlx5_core_create_xsrq(struct mlx5_core_dev *dev, u32 *in, int inlen,
+ u32 *rmpn);
+int mlx5_core_destroy_xsrq(struct mlx5_core_dev *dev, u32 rmpn);
+int mlx5_core_query_xsrq(struct mlx5_core_dev *dev, u32 rmpn, u32 *out);
+int mlx5_core_arm_xsrq(struct mlx5_core_dev *dev, u32 rmpn, u16 lwm);
+
+int mlx5_core_create_rqt(struct mlx5_core_dev *dev, u32 *in, int inlen,
+ u32 *rqtn);
+int mlx5_core_modify_rqt(struct mlx5_core_dev *dev, u32 rqtn, u32 *in,
+ int inlen);
+void mlx5_core_destroy_rqt(struct mlx5_core_dev *dev, u32 rqtn);
+
+#endif /* __TRANSOBJ_H__ */
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index 638f2ca7a527..123771003e68 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -45,6 +45,11 @@ int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev,
u16 vport, u8 *addr);
int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *dev,
u16 vport, u8 *addr);
+int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev,
+ u64 *system_image_guid);
+int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid);
+int mlx5_query_nic_vport_qkey_viol_cntr(struct mlx5_core_dev *mdev,
+ u16 *qkey_viol_cntr);
int mlx5_query_hca_vport_gid(struct mlx5_core_dev *dev, u8 other_vport,
u8 port_num, u16 vf_num, u16 gid_index,
union ib_gid *gid);
@@ -85,4 +90,7 @@ int mlx5_modify_nic_vport_vlans(struct mlx5_core_dev *dev,
u16 vlans[],
int list_size);
+int mlx5_nic_vport_enable_roce(struct mlx5_core_dev *mdev);
+int mlx5_nic_vport_disable_roce(struct mlx5_core_dev *mdev);
+
#endif /* __MLX5_VPORT_H__ */
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 3af5f454c04a..a55986f6fe38 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -17,20 +17,19 @@
#include <linux/types.h>
-struct nvme_bar {
- __u64 cap; /* Controller Capabilities */
- __u32 vs; /* Version */
- __u32 intms; /* Interrupt Mask Set */
- __u32 intmc; /* Interrupt Mask Clear */
- __u32 cc; /* Controller Configuration */
- __u32 rsvd1; /* Reserved */
- __u32 csts; /* Controller Status */
- __u32 nssr; /* Subsystem Reset */
- __u32 aqa; /* Admin Queue Attributes */
- __u64 asq; /* Admin SQ Base Address */
- __u64 acq; /* Admin CQ Base Address */
- __u32 cmbloc; /* Controller Memory Buffer Location */
- __u32 cmbsz; /* Controller Memory Buffer Size */
+enum {
+ NVME_REG_CAP = 0x0000, /* Controller Capabilities */
+ NVME_REG_VS = 0x0008, /* Version */
+ NVME_REG_INTMS = 0x000c, /* Interrupt Mask Set */
+ NVME_REG_INTMC = 0x0010, /* Interrupt Mask Set */
+ NVME_REG_CC = 0x0014, /* Controller Configuration */
+ NVME_REG_CSTS = 0x001c, /* Controller Status */
+ NVME_REG_NSSR = 0x0020, /* NVM Subsystem Reset */
+ NVME_REG_AQA = 0x0024, /* Admin Queue Attributes */
+ NVME_REG_ASQ = 0x0028, /* Admin SQ Base Address */
+ NVME_REG_ACQ = 0x0030, /* Admin SQ Base Address */
+ NVME_REG_CMBLOC = 0x0038, /* Controller Memory Buffer Location */
+ NVME_REG_CMBSZ = 0x003c, /* Controller Memory Buffer Size */
};
#define NVME_CAP_MQES(cap) ((cap) & 0xffff)
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 4d08b6c33557..92395a0a7dc5 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -361,6 +361,9 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start,
unsigned int nr_pages, struct page **pages);
unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
int tag, unsigned int nr_pages, struct page **pages);
+unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
+ int tag, unsigned int nr_entries,
+ struct page **entries, pgoff_t *indices);
struct page *grab_cache_page_write_begin(struct address_space *mapping,
pgoff_t index, unsigned flags);
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index eb8b8ac6df3c..24f5470d3944 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -42,6 +42,7 @@ struct pipe_buffer {
* @fasync_readers: reader side fasync
* @fasync_writers: writer side fasync
* @bufs: the circular array of pipe buffers
+ * @user: the user who created this pipe
**/
struct pipe_inode_info {
struct mutex mutex;
@@ -57,6 +58,7 @@ struct pipe_inode_info {
struct fasync_struct *fasync_readers;
struct fasync_struct *fasync_writers;
struct pipe_buffer *bufs;
+ struct user_struct *user;
};
/*
@@ -123,6 +125,8 @@ void pipe_unlock(struct pipe_inode_info *);
void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *);
extern unsigned int pipe_max_size, pipe_min_size;
+extern unsigned long pipe_user_pages_hard;
+extern unsigned long pipe_user_pages_soft;
int pipe_proc_fn(struct ctl_table *, int, void __user *, size_t *, loff_t *);
diff --git a/include/linux/pmem.h b/include/linux/pmem.h
index acfea8ce4a07..7c3d11a6b4ad 100644
--- a/include/linux/pmem.h
+++ b/include/linux/pmem.h
@@ -53,12 +53,18 @@ static inline void arch_clear_pmem(void __pmem *addr, size_t size)
{
BUG();
}
+
+static inline void arch_wb_cache_pmem(void __pmem *addr, size_t size)
+{
+ BUG();
+}
#endif
/*
* Architectures that define ARCH_HAS_PMEM_API must provide
* implementations for arch_memcpy_to_pmem(), arch_wmb_pmem(),
- * arch_copy_from_iter_pmem(), arch_clear_pmem() and arch_has_wmb_pmem().
+ * arch_copy_from_iter_pmem(), arch_clear_pmem(), arch_wb_cache_pmem()
+ * and arch_has_wmb_pmem().
*/
static inline void memcpy_from_pmem(void *dst, void __pmem const *src, size_t size)
{
@@ -178,4 +184,18 @@ static inline void clear_pmem(void __pmem *addr, size_t size)
else
default_clear_pmem(addr, size);
}
+
+/**
+ * wb_cache_pmem - write back processor cache for PMEM memory range
+ * @addr: virtual start address
+ * @size: number of bytes to write back
+ *
+ * Write back the processor cache range starting at 'addr' for 'size' bytes.
+ * This function requires explicit ordering with a wmb_pmem() call.
+ */
+static inline void wb_cache_pmem(void __pmem *addr, size_t size)
+{
+ if (arch_has_pmem_api())
+ arch_wb_cache_pmem(addr, size);
+}
#endif /* __PMEM_H__ */
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 57e7d87d2d4c..7c88ad156a29 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -51,6 +51,15 @@
#define RADIX_TREE_EXCEPTIONAL_ENTRY 2
#define RADIX_TREE_EXCEPTIONAL_SHIFT 2
+#define RADIX_DAX_MASK 0xf
+#define RADIX_DAX_SHIFT 4
+#define RADIX_DAX_PTE (0x4 | RADIX_TREE_EXCEPTIONAL_ENTRY)
+#define RADIX_DAX_PMD (0x8 | RADIX_TREE_EXCEPTIONAL_ENTRY)
+#define RADIX_DAX_TYPE(entry) ((unsigned long)entry & RADIX_DAX_MASK)
+#define RADIX_DAX_SECTOR(entry) (((unsigned long)entry >> RADIX_DAX_SHIFT))
+#define RADIX_DAX_ENTRY(sector, pmd) ((void *)((unsigned long)sector << \
+ RADIX_DAX_SHIFT | (pmd ? RADIX_DAX_PMD : RADIX_DAX_PTE)))
+
static inline int radix_tree_is_indirect_ptr(void *ptr)
{
return (int)((unsigned long)ptr & RADIX_TREE_INDIRECT_PTR);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f1e81e128592..a10494a94cc3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -835,6 +835,7 @@ struct user_struct {
#endif
unsigned long locked_shm; /* How many pages of mlocked shm ? */
unsigned long unix_inflight; /* How many files in flight in unix sockets */
+ atomic_long_t pipe_bufs; /* how many pages are allocated in pipe buffers */
#ifdef CONFIG_KEYS
struct key *uid_keyring; /* UID specific keyring */
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index a43f41cb3c43..4d4780c00d34 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -15,10 +15,7 @@ struct shmem_inode_info {
unsigned int seals; /* shmem seals */
unsigned long flags;
unsigned long alloced; /* data pages alloced to file */
- union {
- unsigned long swapped; /* subtotal assigned to swap */
- char *symlink; /* unswappable short symlink */
- };
+ unsigned long swapped; /* subtotal assigned to swap */
struct shared_policy policy; /* NUMA memory alloc policy */
struct list_head swaplist; /* chain of maybes on swap */
struct simple_xattrs xattrs; /* list of xattrs */
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index f869807a0d0e..5322fea6fe4c 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -51,6 +51,7 @@
/* RPC/RDMA parameters and stats */
extern unsigned int svcrdma_ord;
extern unsigned int svcrdma_max_requests;
+extern unsigned int svcrdma_max_bc_requests;
extern unsigned int svcrdma_max_req_size;
extern atomic_t rdma_stat_recv;
@@ -69,6 +70,7 @@ extern atomic_t rdma_stat_sq_prod;
* completes.
*/
struct svc_rdma_op_ctxt {
+ struct list_head free;
struct svc_rdma_op_ctxt *read_hdr;
struct svc_rdma_fastreg_mr *frmr;
int hdr_count;
@@ -112,6 +114,7 @@ struct svc_rdma_fastreg_mr {
struct list_head frmr_list;
};
struct svc_rdma_req_map {
+ struct list_head free;
unsigned long count;
union {
struct kvec sge[RPCSVC_MAXPAGES];
@@ -132,28 +135,32 @@ struct svcxprt_rdma {
int sc_max_sge;
int sc_max_sge_rd; /* max sge for read target */
- int sc_sq_depth; /* Depth of SQ */
atomic_t sc_sq_count; /* Number of SQ WR on queue */
-
- int sc_max_requests; /* Depth of RQ */
+ unsigned int sc_sq_depth; /* Depth of SQ */
+ unsigned int sc_rq_depth; /* Depth of RQ */
+ u32 sc_max_requests; /* Forward credits */
+ u32 sc_max_bc_requests;/* Backward credits */
int sc_max_req_size; /* Size of each RQ WR buf */
struct ib_pd *sc_pd;
atomic_t sc_dma_used;
- atomic_t sc_ctxt_used;
+ spinlock_t sc_ctxt_lock;
+ struct list_head sc_ctxts;
+ int sc_ctxt_used;
+ spinlock_t sc_map_lock;
+ struct list_head sc_maps;
+
struct list_head sc_rq_dto_q;
spinlock_t sc_rq_dto_lock;
struct ib_qp *sc_qp;
struct ib_cq *sc_rq_cq;
struct ib_cq *sc_sq_cq;
- struct ib_mr *sc_phys_mr; /* MR for server memory */
int (*sc_reader)(struct svcxprt_rdma *,
struct svc_rqst *,
struct svc_rdma_op_ctxt *,
int *, u32 *, u32, u32, u64, bool);
u32 sc_dev_caps; /* distilled device caps */
- u32 sc_dma_lkey; /* local dma key */
unsigned int sc_frmr_pg_list_len;
struct list_head sc_frmr_q;
spinlock_t sc_frmr_q_lock;
@@ -179,8 +186,18 @@ struct svcxprt_rdma {
#define RPCRDMA_MAX_REQUESTS 32
#define RPCRDMA_MAX_REQ_SIZE 4096
+/* Typical ULP usage of BC requests is NFSv4.1 backchannel. Our
+ * current NFSv4.1 implementation supports one backchannel slot.
+ */
+#define RPCRDMA_MAX_BC_REQUESTS 2
+
#define RPCSVC_MAXPAYLOAD_RDMA RPCSVC_MAXPAYLOAD
+/* svc_rdma_backchannel.c */
+extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt,
+ struct rpcrdma_msg *rmsgp,
+ struct xdr_buf *rcvbuf);
+
/* svc_rdma_marshal.c */
extern int svc_rdma_xdr_decode_req(struct rpcrdma_msg **, struct svc_rqst *);
extern int svc_rdma_xdr_encode_error(struct svcxprt_rdma *,
@@ -206,6 +223,8 @@ extern int rdma_read_chunk_frmr(struct svcxprt_rdma *, struct svc_rqst *,
u32, u32, u64, bool);
/* svc_rdma_sendto.c */
+extern int svc_rdma_map_xdr(struct svcxprt_rdma *, struct xdr_buf *,
+ struct svc_rdma_req_map *);
extern int svc_rdma_sendto(struct svc_rqst *);
extern struct rpcrdma_read_chunk *
svc_rdma_get_read_chunk(struct rpcrdma_msg *);
@@ -214,13 +233,14 @@ extern struct rpcrdma_read_chunk *
extern int svc_rdma_send(struct svcxprt_rdma *, struct ib_send_wr *);
extern void svc_rdma_send_error(struct svcxprt_rdma *, struct rpcrdma_msg *,
enum rpcrdma_errcode);
-extern int svc_rdma_post_recv(struct svcxprt_rdma *);
+extern int svc_rdma_post_recv(struct svcxprt_rdma *, gfp_t);
extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *);
extern struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *);
extern void svc_rdma_put_context(struct svc_rdma_op_ctxt *, int);
extern void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt);
-extern struct svc_rdma_req_map *svc_rdma_get_req_map(void);
-extern void svc_rdma_put_req_map(struct svc_rdma_req_map *);
+extern struct svc_rdma_req_map *svc_rdma_get_req_map(struct svcxprt_rdma *);
+extern void svc_rdma_put_req_map(struct svcxprt_rdma *,
+ struct svc_rdma_req_map *);
extern struct svc_rdma_fastreg_mr *svc_rdma_get_frmr(struct svcxprt_rdma *);
extern void svc_rdma_put_frmr(struct svcxprt_rdma *,
struct svc_rdma_fastreg_mr *);
@@ -234,6 +254,7 @@ extern struct svc_xprt_class svc_rdma_bc_class;
#endif
/* svc_rdma.c */
+extern struct workqueue_struct *svc_rdma_wq;
extern int svc_rdma_init(void);
extern void svc_rdma_cleanup(void);
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 613c29bd6baf..e13a1ace50e9 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -43,6 +43,9 @@
/* Default weight of a bound cooling device */
#define THERMAL_WEIGHT_DEFAULT 0
+/* use value, which < 0K, to indicate an invalid/uninitialized temperature */
+#define THERMAL_TEMP_INVALID -274000
+
/* Unit conversion macros */
#define DECI_KELVIN_TO_CELSIUS(t) ({ \
long _t = (t); \
@@ -167,6 +170,7 @@ struct thermal_attr {
* @forced_passive: If > 0, temperature at which to switch on all ACPI
* processor cooling devices. Currently only used by the
* step-wise governor.
+ * @need_update: if equals 1, thermal_zone_device_update needs to be invoked.
* @ops: operations this &thermal_zone_device supports
* @tzp: thermal zone parameters
* @governor: pointer to the governor for this thermal zone
@@ -194,6 +198,7 @@ struct thermal_zone_device {
int emul_temperature;
int passive;
unsigned int forced_passive;
+ atomic_t need_update;
struct thermal_zone_device_ops *ops;
struct thermal_zone_params *tzp;
struct thermal_governor *governor;