This patch adds some general cleanup/consistency to RMPP handling.
* Update MAD API documentation.
* Saves RMPP information when a MAD is created, avoiding the need to
re-calculate it when it is sent.
* Hides RMPP segmentation details from the user. Makes ib_rmpp_segment
an internal data structure, and changes ib_get_rmpp_segment to return
the data buffer directly.
* ib_get_rmpp_segment is updated to work with all segment numbers, rather
than just segments >= 2.
* Fixes RMPP usage of ib_create_send_mad when allocating non-data MADs.
* Overall, this reduces about 50 lines of code.
This patch includes removing the receive side data copy for userspace, as
it depends on that patch.
Signed-off-by: Sean Hefty <[EMAIL PROTECTED]>
---
Index: core/mad.c
===================================================================
--- core/mad.c (revision 5552)
+++ core/mad.c (working copy)
@@ -765,18 +765,16 @@ out:
return ret;
}
-static int get_buf_length(int hdr_len, int data_len)
+static int get_pad_size(int hdr_len, int data_len)
{
int seg_size, pad;
seg_size = sizeof(struct ib_mad) - hdr_len;
if (data_len && seg_size) {
pad = seg_size - data_len % seg_size;
- if (pad == seg_size)
- pad = 0;
+ return pad == seg_size ? 0 : pad;
} else
- pad = seg_size;
- return hdr_len + data_len + pad;
+ return seg_size;
}
static void free_send_rmpp_list(struct ib_mad_send_wr_private *mad_send_wr)
@@ -789,40 +787,44 @@ static void free_send_rmpp_list(struct i
}
}
-static inline int alloc_send_rmpp_list(struct ib_mad_send_wr_private *send_wr,
- int message_size, int hdr_len,
- int data_len, u8 rmpp_version,
- gfp_t gfp_mask)
-{
- struct ib_rmpp_segment *seg;
- struct ib_rmpp_mad *rmpp_mad = send_wr->send_buf.mad;
- int seg_size, i = 2;
-
- rmpp_mad->rmpp_hdr.paylen_newwin =
- cpu_to_be32(hdr_len - IB_MGMT_RMPP_HDR + data_len);
- rmpp_mad->rmpp_hdr.rmpp_version = rmpp_version;
- rmpp_mad->rmpp_hdr.rmpp_type = IB_MGMT_RMPP_TYPE_DATA;
- ib_set_rmpp_flags(&rmpp_mad->rmpp_hdr, IB_MGMT_RMPP_FLAG_ACTIVE);
- send_wr->total_length = message_size;
- /* allocate RMPP buffers */
- message_size -= sizeof(struct ib_mad);
- seg_size = sizeof(struct ib_mad) - hdr_len;
- while (message_size > 0) {
- seg = kmalloc(sizeof(struct ib_rmpp_segment) + seg_size,
- gfp_mask);
+static int alloc_send_rmpp_list(struct ib_mad_send_wr_private *send_wr,
+ gfp_t gfp_mask)
+{
+ struct ib_mad_send_buf *send_buf = &send_wr->send_buf;
+ struct ib_rmpp_mad *rmpp_mad = send_buf->mad;
+ struct ib_rmpp_segment *seg = NULL;
+ int left, seg_size, pad;
+
+ send_buf->seg_size = sizeof (struct ib_mad) - send_buf->hdr_len;
+ seg_size = send_buf->seg_size;
+ pad = send_wr->pad;
+
+ /* Allocate data segments. */
+ for (left = send_buf->data_len + pad; left > 0; left -= seg_size) {
+ seg = kmalloc(sizeof (*seg) + seg_size, gfp_mask);
if (!seg) {
- printk(KERN_ERR "ib_create_send_mad: RMPP mem "
+ printk(KERN_ERR "alloc_send_rmpp_segs: RMPP mem "
"alloc failed for len %zd, gfp %#x\n",
- sizeof(struct ib_rmpp_segment) + seg_size,
- gfp_mask);
+ sizeof (*seg) + seg_size, gfp_mask);
free_send_rmpp_list(send_wr);
return -ENOMEM;
}
- seg->size = seg_size;
- seg->num = i++;
+ seg->num = ++send_buf->seg_count;
list_add_tail(&seg->list, &send_wr->rmpp_list);
- message_size -= seg_size;
}
+
+ /* Zero any padding */
+ if (pad)
+ memset(seg->data + seg_size - pad, 0, pad);
+
+ rmpp_mad->rmpp_hdr.rmpp_version = send_wr->mad_agent_priv->
+ agent.rmpp_version;
+ rmpp_mad->rmpp_hdr.rmpp_type = IB_MGMT_RMPP_TYPE_DATA;
+ ib_set_rmpp_flags(&rmpp_mad->rmpp_hdr, IB_MGMT_RMPP_FLAG_ACTIVE);
+
+ send_wr->cur_seg = container_of(send_wr->rmpp_list.next,
+ struct ib_rmpp_segment, list);
+ send_wr->last_ack_seg = send_wr->cur_seg;
return 0;
}
@@ -834,28 +836,30 @@ struct ib_mad_send_buf * ib_create_send_
{
struct ib_mad_agent_private *mad_agent_priv;
struct ib_mad_send_wr_private *mad_send_wr;
- int length, message_size, ret;
+ int pad, message_size, ret, size;
void *buf;
mad_agent_priv = container_of(mad_agent, struct ib_mad_agent_private,
agent);
- message_size = get_buf_length(hdr_len, data_len);
+ pad = get_pad_size(hdr_len, data_len);
+ message_size = hdr_len + data_len + pad;
if ((!mad_agent->rmpp_version &&
(rmpp_active || message_size > sizeof(struct ib_mad))) ||
(!rmpp_active && message_size > sizeof(struct ib_mad)))
return ERR_PTR(-EINVAL);
- length = sizeof *mad_send_wr + message_size;
- buf = kzalloc(sizeof *mad_send_wr + sizeof(struct ib_mad), gfp_mask);
-
+ size = rmpp_active ? hdr_len : sizeof(struct ib_mad);
+ buf = kzalloc(sizeof *mad_send_wr + size, gfp_mask);
if (!buf)
return ERR_PTR(-ENOMEM);
- mad_send_wr = buf + sizeof(struct ib_mad);
+ mad_send_wr = buf + size;
INIT_LIST_HEAD(&mad_send_wr->rmpp_list);
mad_send_wr->send_buf.mad = buf;
- mad_send_wr->mad_payload = buf + hdr_len;
+ mad_send_wr->send_buf.hdr_len = hdr_len;
+ mad_send_wr->send_buf.data_len = data_len;
+ mad_send_wr->pad = pad;
mad_send_wr->mad_agent_priv = mad_agent_priv;
mad_send_wr->sg_list[0].length = hdr_len;
@@ -871,13 +875,9 @@ struct ib_mad_send_buf * ib_create_send_
mad_send_wr->send_wr.wr.ud.remote_qpn = remote_qpn;
mad_send_wr->send_wr.wr.ud.remote_qkey = IB_QP_SET_QKEY;
mad_send_wr->send_wr.wr.ud.pkey_index = pkey_index;
- mad_send_wr->last_ack_seg = NULL;
- mad_send_wr->cur_seg = NULL;
if (rmpp_active) {
- ret = alloc_send_rmpp_list(mad_send_wr, message_size, hdr_len,
- data_len, mad_agent->rmpp_version,
- gfp_mask);
+ ret = alloc_send_rmpp_list(mad_send_wr, gfp_mask);
if (ret) {
kfree(buf);
return ERR_PTR(ret);
@@ -890,55 +890,37 @@ struct ib_mad_send_buf * ib_create_send_
}
EXPORT_SYMBOL(ib_create_send_mad);
-struct ib_rmpp_segment *ib_get_segment(struct ib_mad_send_wr_private
*mad_send_wr,
- int seg_num)
+void *ib_get_rmpp_segment(struct ib_mad_send_buf *send_buf, int seg_num)
{
- struct ib_rmpp_segment *seg;
+ struct ib_mad_send_wr_private *mad_send_wr;
+ struct list_head *list;
- if (seg_num == 2) {
- mad_send_wr->cur_seg = container_of(mad_send_wr->rmpp_list.next,
- struct ib_rmpp_segment,
list);
- return mad_send_wr->cur_seg;
- }
-
- /* get first list entry if was not already done */
- if (!mad_send_wr->cur_seg)
- mad_send_wr->cur_seg = container_of(mad_send_wr->rmpp_list.next,
- struct ib_rmpp_segment,
list);
-
- if (mad_send_wr->cur_seg->num == seg_num)
- return mad_send_wr->cur_seg;
- else if (mad_send_wr->cur_seg->num < seg_num) {
- list_for_each_entry(seg, &mad_send_wr->cur_seg->list, list) {
- if (seg->num == seg_num) {
- mad_send_wr->cur_seg = seg;
- return mad_send_wr->cur_seg;
- }
- }
- } else {
- list_for_each_entry_reverse(seg, &mad_send_wr->cur_seg->list,
- list) {
- if (seg->num == seg_num) {
- mad_send_wr->cur_seg = seg;
- return mad_send_wr->cur_seg;
- }
- }
+ mad_send_wr = container_of(send_buf, struct ib_mad_send_wr_private,
+ send_buf);
+ list = &mad_send_wr->cur_seg->list;
+
+ if (mad_send_wr->cur_seg->num < seg_num) {
+ list_for_each_entry(mad_send_wr->cur_seg, list, list)
+ if (mad_send_wr->cur_seg->num == seg_num)
+ break;
+ } else if (mad_send_wr->cur_seg->num > seg_num) {
+ list_for_each_entry_reverse(mad_send_wr->cur_seg, list, list)
+ if (mad_send_wr->cur_seg->num == seg_num)
+ break;
}
- return NULL;
+ return mad_send_wr->cur_seg->data;
}
+EXPORT_SYMBOL(ib_get_rmpp_segment);
-struct ib_rmpp_segment *ib_get_rmpp_segment(struct ib_mad_send_buf *send_buf,
- int seg_num)
+static inline void *ib_get_payload(struct ib_mad_send_wr_private *mad_send_wr)
{
- struct ib_mad_send_wr_private *wr;
-
- if (seg_num < 2)
- return NULL;
-
- wr = container_of(send_buf, struct ib_mad_send_wr_private, send_buf);
- return ib_get_segment(wr, seg_num);
+ if (mad_send_wr->send_buf.seg_count)
+ return ib_get_rmpp_segment(&mad_send_wr->send_buf,
+ mad_send_wr->seg_num);
+ else
+ return mad_send_wr->send_buf.mad +
+ mad_send_wr->send_buf.hdr_len;
}
-EXPORT_SYMBOL(ib_get_rmpp_segment);
void ib_free_send_mad(struct ib_mad_send_buf *send_buf)
{
@@ -981,7 +963,7 @@ int ib_send_mad(struct ib_mad_send_wr_pr
pci_unmap_addr_set(mad_send_wr, header_mapping, sge[0].addr);
sge[1].addr = dma_map_single(mad_agent->device->dma_device,
- mad_send_wr->mad_payload,
+ ib_get_payload(mad_send_wr),
sge[1].length,
DMA_TO_DEVICE);
pci_unmap_addr_set(mad_send_wr, payload_mapping, sge[1].addr);
@@ -1005,7 +987,6 @@ int ib_send_mad(struct ib_mad_send_wr_pr
dma_unmap_single(mad_agent->device->dma_device,
pci_unmap_addr(mad_send_wr, header_mapping),
sge[0].length, DMA_TO_DEVICE);
-
dma_unmap_single(mad_agent->device->dma_device,
pci_unmap_addr(mad_send_wr, payload_mapping),
sge[1].length, DMA_TO_DEVICE);
Index: core/mad_priv.h
===================================================================
--- core/mad_priv.h (revision 5552)
+++ core/mad_priv.h (working copy)
@@ -85,6 +85,12 @@ struct ib_mad_private {
} mad;
} __attribute__ ((packed));
+struct ib_rmpp_segment {
+ struct list_head list;
+ u32 num;
+ u8 data[0];
+};
+
struct ib_mad_agent_private {
struct list_head agent_list;
struct ib_mad_agent agent;
@@ -124,7 +130,6 @@ struct ib_mad_send_wr_private {
struct ib_send_wr send_wr;
struct ib_sge sg_list[IB_MAD_SEND_REQ_MAX_SG];
__be64 tid;
- void *mad_payload; /* RMPP: changed per segment */
unsigned long timeout;
int retries;
int retry;
@@ -138,9 +143,6 @@ struct ib_mad_send_wr_private {
int last_ack;
int seg_num;
int newwin;
- int total_length;
- int total_seg;
- int data_offset;
int pad;
};
@@ -225,7 +227,4 @@ void ib_mark_mad_done(struct ib_mad_send
void ib_reset_mad_timeout(struct ib_mad_send_wr_private *mad_send_wr,
int timeout_ms);
-struct ib_rmpp_segment *ib_get_segment(struct ib_mad_send_wr_private
*mad_send_wr,
- int seg_num);
-
#endif /* __IB_MAD_PRIV_H__ */
Index: core/mad_rmpp.c
===================================================================
--- core/mad_rmpp.c (revision 5552)
+++ core/mad_rmpp.c (working copy)
@@ -111,14 +111,14 @@ static int data_offset(u8 mgmt_class)
return IB_MGMT_RMPP_HDR;
}
-static void format_ack(struct ib_rmpp_mad *ack,
+static void format_ack(struct ib_mad_send_buf *msg,
struct ib_rmpp_mad *data,
struct mad_rmpp_recv *rmpp_recv)
{
+ struct ib_rmpp_mad *ack = msg->mad;
unsigned long flags;
- memcpy(&ack->mad_hdr, &data->mad_hdr,
- data_offset(data->mad_hdr.mgmt_class));
+ memcpy(ack, &data->mad_hdr, msg->hdr_len);
ack->mad_hdr.method ^= IB_MGMT_METHOD_RESP;
ack->rmpp_hdr.rmpp_type = IB_MGMT_RMPP_TYPE_ACK;
@@ -135,16 +135,16 @@ static void ack_recv(struct mad_rmpp_rec
struct ib_mad_recv_wc *recv_wc)
{
struct ib_mad_send_buf *msg;
- int ret;
+ int ret, hdr_len;
+ hdr_len = data_offset(recv_wc->recv_buf.mad->mad_hdr.mgmt_class);
msg = ib_create_send_mad(&rmpp_recv->agent->agent, recv_wc->wc->src_qp,
- recv_wc->wc->pkey_index, 1, IB_MGMT_RMPP_HDR,
- IB_MGMT_RMPP_DATA, GFP_KERNEL);
+ recv_wc->wc->pkey_index, 1, hdr_len,
+ 0, GFP_KERNEL);
if (!msg)
return;
- format_ack(msg->mad, (struct ib_rmpp_mad *) recv_wc->recv_buf.mad,
- rmpp_recv);
+ format_ack(msg, (struct ib_rmpp_mad *) recv_wc->recv_buf.mad,
rmpp_recv);
msg->ah = rmpp_recv->ah;
ret = ib_post_send_mad(msg, NULL);
if (ret)
@@ -156,16 +156,17 @@ static struct ib_mad_send_buf *alloc_res
{
struct ib_mad_send_buf *msg;
struct ib_ah *ah;
+ int hdr_len;
ah = ib_create_ah_from_wc(agent->qp->pd, recv_wc->wc,
recv_wc->recv_buf.grh, agent->port_num);
if (IS_ERR(ah))
return (void *) ah;
+ hdr_len = data_offset(recv_wc->recv_buf.mad->mad_hdr.mgmt_class);
msg = ib_create_send_mad(agent, recv_wc->wc->src_qp,
recv_wc->wc->pkey_index, 1,
- IB_MGMT_RMPP_HDR, IB_MGMT_RMPP_DATA,
- GFP_KERNEL);
+ hdr_len, 0, GFP_KERNEL);
if (IS_ERR(msg))
ib_destroy_ah(ah);
else
@@ -195,8 +196,7 @@ static void nack_recv(struct ib_mad_agen
return;
rmpp_mad = msg->mad;
- memcpy(rmpp_mad, recv_wc->recv_buf.mad,
- data_offset(recv_wc->recv_buf.mad->mad_hdr.mgmt_class));
+ memcpy(rmpp_mad, recv_wc->recv_buf.mad, msg->hdr_len);
rmpp_mad->mad_hdr.method ^= IB_MGMT_METHOD_RESP;
rmpp_mad->rmpp_hdr.rmpp_version = IB_MGMT_RMPP_VERSION;
@@ -535,42 +535,30 @@ start_rmpp(struct ib_mad_agent_private *
static int send_next_seg(struct ib_mad_send_wr_private *mad_send_wr)
{
struct ib_rmpp_mad *rmpp_mad;
- struct ib_rmpp_segment *seg;
int timeout;
- u32 paylen;
+ u32 paylen = 0;
rmpp_mad = mad_send_wr->send_buf.mad;
ib_set_rmpp_flags(&rmpp_mad->rmpp_hdr, IB_MGMT_RMPP_FLAG_ACTIVE);
- rmpp_mad->rmpp_hdr.seg_num = cpu_to_be32(mad_send_wr->seg_num);
+ rmpp_mad->rmpp_hdr.seg_num = cpu_to_be32(++mad_send_wr->seg_num);
if (mad_send_wr->seg_num == 1) {
rmpp_mad->rmpp_hdr.rmpp_rtime_flags |= IB_MGMT_RMPP_FLAG_FIRST;
- paylen = mad_send_wr->total_seg * IB_MGMT_RMPP_DATA -
+ paylen = mad_send_wr->send_buf.seg_count * IB_MGMT_RMPP_DATA -
mad_send_wr->pad;
- rmpp_mad->rmpp_hdr.paylen_newwin = cpu_to_be32(paylen);
- } else {
- seg = ib_get_segment(mad_send_wr, mad_send_wr->seg_num);
- if (!seg) {
- printk(KERN_ERR PFX "send_next_seg: "
- "could not find segment %d\n",
- mad_send_wr->seg_num);
- return -EINVAL;
- }
- mad_send_wr->mad_payload = seg->data;
- rmpp_mad->rmpp_hdr.paylen_newwin = 0;
}
- if (mad_send_wr->seg_num == mad_send_wr->total_seg) {
+ if (mad_send_wr->seg_num == mad_send_wr->send_buf.seg_count) {
rmpp_mad->rmpp_hdr.rmpp_rtime_flags |= IB_MGMT_RMPP_FLAG_LAST;
paylen = IB_MGMT_RMPP_DATA - mad_send_wr->pad;
- rmpp_mad->rmpp_hdr.paylen_newwin = cpu_to_be32(paylen);
}
+ rmpp_mad->rmpp_hdr.paylen_newwin = cpu_to_be32(paylen);
/* 2 seconds for an ACK until we can find the packet lifetime */
timeout = mad_send_wr->send_buf.timeout_ms;
if (!timeout || timeout > 2000)
mad_send_wr->timeout = msecs_to_jiffies(2000);
- mad_send_wr->seg_num++;
+
return ib_send_mad(mad_send_wr);
}
@@ -586,7 +574,7 @@ static void abort_send(struct ib_mad_age
if (!mad_send_wr)
goto out; /* Unmatched send */
- if ((mad_send_wr->last_ack == mad_send_wr->total_seg) ||
+ if ((mad_send_wr->last_ack == mad_send_wr->send_buf.seg_count) ||
(!mad_send_wr->timeout) || (mad_send_wr->status != IB_WC_SUCCESS))
goto out; /* Send is already done */
@@ -602,26 +590,16 @@ out:
spin_unlock_irqrestore(&agent->lock, flags);
}
-static inline void adjust_last_ack(struct ib_mad_send_wr_private *wr)
+static inline void adjust_last_ack(struct ib_mad_send_wr_private *wr,
+ int seg_num)
{
- struct ib_rmpp_segment *seg;
+ struct list_head *list;
- if (wr->last_ack < 2)
- return;
- else if (!wr->last_ack_seg)
- list_for_each_entry(seg, &wr->rmpp_list, list) {
- if (wr->last_ack == seg->num) {
- wr->last_ack_seg = seg;
- break;
- }
- }
- else
- list_for_each_entry(seg, &wr->last_ack_seg->list, list) {
- if (wr->last_ack == seg->num) {
- wr->last_ack_seg = seg;
- break;
- }
- }
+ wr->last_ack = seg_num;
+ list = &wr->last_ack_seg->list;
+ list_for_each_entry(wr->last_ack_seg, list, list)
+ if (wr->last_ack_seg->num == seg_num)
+ break;
}
static void process_rmpp_ack(struct ib_mad_agent_private *agent,
@@ -652,11 +630,12 @@ static void process_rmpp_ack(struct ib_m
if (!mad_send_wr)
goto out; /* Unmatched ACK */
- if ((mad_send_wr->last_ack == mad_send_wr->total_seg) ||
+ if ((mad_send_wr->last_ack == mad_send_wr->send_buf.seg_count) ||
(!mad_send_wr->timeout) || (mad_send_wr->status != IB_WC_SUCCESS))
goto out; /* Send is already done */
- if (seg_num > mad_send_wr->total_seg || seg_num > mad_send_wr->newwin) {
+ if (seg_num > mad_send_wr->send_buf.seg_count ||
+ seg_num > mad_send_wr->newwin) {
spin_unlock_irqrestore(&agent->lock, flags);
abort_send(agent, mad_recv_wc, IB_MGMT_RMPP_STATUS_S2B);
nack_recv(agent, mad_recv_wc, IB_MGMT_RMPP_STATUS_S2B);
@@ -667,12 +646,11 @@ static void process_rmpp_ack(struct ib_m
goto out; /* Old ACK */
if (seg_num > mad_send_wr->last_ack) {
- mad_send_wr->last_ack = seg_num;
- adjust_last_ack(mad_send_wr);
+ adjust_last_ack(mad_send_wr, seg_num);
mad_send_wr->retries = mad_send_wr->send_buf.retries;
}
mad_send_wr->newwin = newwin;
- if (mad_send_wr->last_ack == mad_send_wr->total_seg) {
+ if (mad_send_wr->last_ack == mad_send_wr->send_buf.seg_count) {
/* If no response is expected, the ACK completes the send */
if (!mad_send_wr->send_buf.timeout_ms) {
struct ib_mad_send_wc wc;
@@ -691,7 +669,7 @@ static void process_rmpp_ack(struct ib_m
mad_send_wr->send_buf.timeout_ms);
} else if (mad_send_wr->refcount == 1 &&
mad_send_wr->seg_num < mad_send_wr->newwin &&
- mad_send_wr->seg_num <= mad_send_wr->total_seg) {
+ mad_send_wr->seg_num < mad_send_wr->send_buf.seg_count) {
/* Send failure will just result in a timeout/retry */
ret = send_next_seg(mad_send_wr);
if (ret)
@@ -816,20 +794,12 @@ int ib_send_rmpp_mad(struct ib_mad_send_
IB_MGMT_RMPP_FLAG_ACTIVE))
return IB_RMPP_RESULT_UNHANDLED;
- if (rmpp_mad->rmpp_hdr.rmpp_type != IB_MGMT_RMPP_TYPE_DATA)
+ if (rmpp_mad->rmpp_hdr.rmpp_type != IB_MGMT_RMPP_TYPE_DATA) {
+ mad_send_wr->seg_num = 1;
return IB_RMPP_RESULT_INTERNAL;
+ }
- if (mad_send_wr->send_wr.num_sge != 2)
- return -EINVAL;
-
- mad_send_wr->seg_num = 1;
mad_send_wr->newwin = 1;
- mad_send_wr->data_offset = data_offset(rmpp_mad->mad_hdr.mgmt_class);
-
- mad_send_wr->total_seg = (mad_send_wr->total_length -
mad_send_wr->data_offset) /
- (sizeof(struct ib_rmpp_mad) - mad_send_wr->data_offset);
- mad_send_wr->pad = mad_send_wr->total_length - IB_MGMT_RMPP_HDR -
- be32_to_cpu(rmpp_mad->rmpp_hdr.paylen_newwin);
/* We need to wait for the final ACK even if there isn't a response */
mad_send_wr->refcount += (mad_send_wr->timeout == 0);
@@ -860,14 +830,14 @@ int ib_process_rmpp_send_wc(struct ib_ma
if (!mad_send_wr->timeout)
return IB_RMPP_RESULT_PROCESSED; /* Response received */
- if (mad_send_wr->last_ack == mad_send_wr->total_seg) {
+ if (mad_send_wr->last_ack == mad_send_wr->send_buf.seg_count) {
mad_send_wr->timeout =
msecs_to_jiffies(mad_send_wr->send_buf.timeout_ms);
return IB_RMPP_RESULT_PROCESSED; /* Send done */
}
- if (mad_send_wr->seg_num > mad_send_wr->newwin ||
- mad_send_wr->seg_num > mad_send_wr->total_seg)
+ if (mad_send_wr->seg_num == mad_send_wr->newwin ||
+ mad_send_wr->seg_num == mad_send_wr->send_buf.seg_count)
return IB_RMPP_RESULT_PROCESSED; /* Wait for ACK */
ret = send_next_seg(mad_send_wr);
@@ -888,10 +858,10 @@ int ib_retry_rmpp(struct ib_mad_send_wr_
IB_MGMT_RMPP_FLAG_ACTIVE))
return IB_RMPP_RESULT_UNHANDLED; /* RMPP not active */
- if (mad_send_wr->last_ack == mad_send_wr->total_seg)
+ if (mad_send_wr->last_ack == mad_send_wr->send_buf.seg_count)
return IB_RMPP_RESULT_PROCESSED;
- mad_send_wr->seg_num = mad_send_wr->last_ack + 1;
+ mad_send_wr->seg_num = mad_send_wr->last_ack;
mad_send_wr->cur_seg = mad_send_wr->last_ack_seg;
ret = send_next_seg(mad_send_wr);
Index: core/user_mad.c
===================================================================
--- core/user_mad.c (revision 5552)
+++ core/user_mad.c (working copy)
@@ -121,9 +121,9 @@ struct ib_umad_file {
struct ib_umad_packet {
struct ib_mad_send_buf *msg;
+ struct ib_mad_recv_wc *recv_wc;
struct list_head list;
int length;
- struct list_head seg_list;
struct ib_user_mad mad;
};
@@ -188,62 +188,6 @@ static int data_offset(u8 mgmt_class)
return IB_MGMT_RMPP_HDR;
}
-static int copy_recv_mad(struct ib_mad_recv_wc *mad_recv_wc,
- struct ib_umad_packet *packet)
-{
- struct ib_mad_recv_buf *seg_buf;
- struct ib_rmpp_mad *rmpp_mad;
- void *data;
- struct ib_rmpp_segment *seg;
- int size, len, offset;
- u8 flags;
-
- len = mad_recv_wc->mad_len;
- if (len <= sizeof(struct ib_mad)) {
- memcpy(&packet->mad.data, mad_recv_wc->recv_buf.mad, len);
- return 0;
- }
-
- /* Multipacket (RMPP) MAD */
- offset = data_offset(mad_recv_wc->recv_buf.mad->mad_hdr.mgmt_class);
-
- list_for_each_entry(seg_buf, &mad_recv_wc->rmpp_list, list) {
- rmpp_mad = (struct ib_rmpp_mad *) seg_buf->mad;
- flags = ib_get_rmpp_flags(&rmpp_mad->rmpp_hdr);
-
- if (flags & IB_MGMT_RMPP_FLAG_FIRST) {
- size = sizeof(*rmpp_mad);
- memcpy(&packet->mad.data, rmpp_mad, size);
- } else {
- data = (void *) rmpp_mad + offset;
- if (flags & IB_MGMT_RMPP_FLAG_LAST)
- size = len;
- else
- size = sizeof(*rmpp_mad) - offset;
- seg = kmalloc(sizeof(struct ib_rmpp_segment) +
- sizeof(struct ib_rmpp_mad) - offset,
- GFP_KERNEL);
- if (!seg)
- return -ENOMEM;
- memcpy(seg->data, data, size);
- list_add_tail(&seg->list, &packet->seg_list);
- }
- len -= size;
- }
- return 0;
-}
-
-static void free_packet(struct ib_umad_packet *packet)
-{
- struct ib_rmpp_segment *seg, *tmp;
-
- list_for_each_entry_safe(seg, tmp, &packet->seg_list, list) {
- list_del(&seg->list);
- kfree(seg);
- }
- kfree(packet);
-}
-
static void send_handler(struct ib_mad_agent *agent,
struct ib_mad_send_wc *send_wc)
{
@@ -268,25 +212,20 @@ static void recv_handler(struct ib_mad_a
{
struct ib_umad_file *file = agent->context;
struct ib_umad_packet *packet;
- int length;
if (mad_recv_wc->wc->status != IB_WC_SUCCESS)
- goto out;
+ goto err1;
- length = mad_recv_wc->mad_len;
- packet = kzalloc(sizeof *packet + sizeof(struct ib_mad), GFP_KERNEL);
+ packet = kzalloc(sizeof *packet, GFP_KERNEL);
if (!packet)
- goto out;
- INIT_LIST_HEAD(&packet->seg_list);
- packet->length = length;
+ goto err1;
- if (copy_recv_mad(mad_recv_wc, packet)) {
- free_packet(packet);
- goto out;
- }
+ packet->length = mad_recv_wc->mad_len;
+ packet->recv_wc = mad_recv_wc;
packet->mad.hdr.status = 0;
- packet->mad.hdr.length = length + sizeof (struct ib_user_mad);
+ packet->mad.hdr.length = sizeof (struct ib_user_mad) +
+ mad_recv_wc->mad_len;
packet->mad.hdr.qpn = cpu_to_be32(mad_recv_wc->wc->src_qp);
packet->mad.hdr.lid = cpu_to_be16(mad_recv_wc->wc->slid);
packet->mad.hdr.sl = mad_recv_wc->wc->sl;
@@ -302,21 +241,87 @@ static void recv_handler(struct ib_mad_a
}
if (queue_packet(file, agent, packet))
- free_packet(packet);
+ goto err2;
+ return;
-out:
+err2:
+ kfree(packet);
+err1:
ib_free_recv_mad(mad_recv_wc);
}
+static ssize_t copy_recv_mad(char __user *buf, struct ib_umad_packet *packet,
+ size_t count)
+{
+ struct ib_mad_recv_buf *recv_buf;
+ int left, seg_payload, offset, max_seg_payload;
+
+ /* We need enough room to copy the first (or only) MAD segment. */
+ recv_buf = &packet->recv_wc->recv_buf;
+ if ((packet->length <= sizeof (*recv_buf->mad) &&
+ count < sizeof (packet->mad) + packet->length) ||
+ (packet->length > sizeof (*recv_buf->mad) &&
+ count < sizeof (packet->mad) + sizeof (*recv_buf->mad)))
+ return -EINVAL;
+
+ if (copy_to_user(buf, &packet->mad, sizeof (packet->mad)))
+ return -EFAULT;
+
+ buf += sizeof (packet->mad);
+ seg_payload = min_t(int, packet->length, sizeof (*recv_buf->mad));
+ if (copy_to_user(buf, recv_buf->mad, seg_payload))
+ return -EFAULT;
+
+ if (seg_payload < packet->length) {
+ /*
+ * Multipacket RMPP MAD message. Copy remainder of message.
+ * Note that last segment may have a shorter payload.
+ */
+ if (count < sizeof (packet->mad) + packet->length) {
+ /*
+ * The buffer is too small, return the first RMPP
segment,
+ * which includes the RMPP message length.
+ */
+ return -ENOSPC;
+ }
+ offset = data_offset(recv_buf->mad->mad_hdr.mgmt_class);
+ max_seg_payload = sizeof (struct ib_mad) - offset;
+
+ for (left = packet->length - seg_payload, buf += seg_payload;
+ left; left -= seg_payload, buf += seg_payload) {
+ recv_buf = container_of(recv_buf->list.next,
+ struct ib_mad_recv_buf, list);
+ seg_payload = min(left, max_seg_payload);
+ if (copy_to_user(buf, ((void *) recv_buf->mad) + offset,
+ seg_payload))
+ return -EFAULT;
+ }
+ }
+ return sizeof (packet->mad) + packet->length;
+}
+
+static ssize_t copy_send_mad(char __user *buf, struct ib_umad_packet *packet,
+ size_t count)
+{
+ ssize_t size = sizeof (packet->mad) + packet->length;
+
+ if (count < size)
+ return -EINVAL;
+
+ if (copy_to_user(buf, &packet->mad, size))
+ return -EFAULT;
+
+ return size;
+}
+
static ssize_t ib_umad_read(struct file *filp, char __user *buf,
size_t count, loff_t *pos)
{
struct ib_umad_file *file = filp->private_data;
- struct ib_rmpp_segment *seg;
struct ib_umad_packet *packet;
- ssize_t ret, size;
+ ssize_t ret;
- if (count < sizeof (struct ib_user_mad) + sizeof (struct ib_mad))
+ if (count < sizeof (struct ib_user_mad))
return -EINVAL;
spin_lock_irq(&file->recv_lock);
@@ -339,55 +344,44 @@ static ssize_t ib_umad_read(struct file
spin_unlock_irq(&file->recv_lock);
- size = min_t(int, sizeof (struct ib_mad), packet->length);
- if (copy_to_user(buf, &packet->mad,
- sizeof(struct ib_user_mad) + size)) {
- ret = -EFAULT;
- goto err;
- }
+ if (packet->recv_wc)
+ ret = copy_recv_mad(buf, packet, count);
+ else
+ ret = copy_send_mad(buf, packet, count);
- if (count < packet->length + sizeof (struct ib_user_mad))
- /*
- * User buffer too small. Return first RMPP segment (which
- * includes RMPP message length).
- */
- ret = -ENOSPC;
- else if (packet->length <= sizeof(struct ib_mad))
- ret = packet->length + sizeof(struct ib_user_mad);
- else {
- int len = packet->length - sizeof(struct ib_mad);
- struct ib_rmpp_mad *rmpp_mad =
- (struct ib_rmpp_mad *) packet->mad.data;
- int max_seg_payload = sizeof(struct ib_mad) -
- data_offset(rmpp_mad->mad_hdr.mgmt_class);
- int seg_payload;
- /*
- * Multipacket RMPP MAD message. Copy remainder of message.
- * Note that last segment may have a shorter payload.
- */
- buf += sizeof(struct ib_user_mad) + sizeof(struct ib_mad);
- list_for_each_entry(seg, &packet->seg_list, list) {
- seg_payload = min_t(int, len, max_seg_payload);
- if (copy_to_user(buf, seg->data, seg_payload)) {
- ret = -EFAULT;
- goto err;
- }
- buf += seg_payload;
- len -= seg_payload;
- }
- ret = packet->length + sizeof (struct ib_user_mad);
- }
-err:
if (ret < 0) {
/* Requeue packet */
spin_lock_irq(&file->recv_lock);
list_add(&packet->list, &file->recv_list);
spin_unlock_irq(&file->recv_lock);
- } else
- free_packet(packet);
+ } else {
+ if (packet->recv_wc)
+ ib_free_recv_mad(packet->recv_wc);
+ kfree(packet);
+ }
return ret;
}
+static int copy_rmpp_mad(struct ib_mad_send_buf *msg, const char __user *buf)
+{
+ int left, seg;
+
+ /* Copy class specific header */
+ if ((msg->hdr_len > IB_MGMT_RMPP_HDR) &&
+ copy_from_user(msg->mad + IB_MGMT_RMPP_HDR, buf + IB_MGMT_RMPP_HDR,
+ msg->hdr_len - IB_MGMT_RMPP_HDR))
+ return -EFAULT;
+
+ /* All headers are in place. Copy data segments. */
+ for (seg = 1, left = msg->data_len, buf += msg->hdr_len; left > 0;
+ seg++, left -= msg->seg_size, buf += msg->seg_size) {
+ if (copy_from_user(ib_get_rmpp_segment(msg, seg), buf,
+ min(left, msg->seg_size)))
+ return -EFAULT;
+ }
+ return 0;
+}
+
static ssize_t ib_umad_write(struct file *filp, const char __user *buf,
size_t count, loff_t *pos)
{
@@ -399,16 +393,12 @@ static ssize_t ib_umad_write(struct file
struct ib_rmpp_mad *rmpp_mad;
u8 method;
__be64 *tid;
- int ret, length, hdr_len, copy_offset;
- int rmpp_active, has_rmpp_header;
- int s, seg_num;
- struct ib_rmpp_segment *seg;
+ int ret, data_len, hdr_len, copy_offset, rmpp_active;
if (count < sizeof (struct ib_user_mad) + IB_MGMT_RMPP_HDR)
return -EINVAL;
- length = count - sizeof (struct ib_user_mad);
- packet = kmalloc(sizeof *packet + IB_MGMT_RMPP_HDR, GFP_KERNEL);
+ packet = kzalloc(sizeof *packet + IB_MGMT_RMPP_HDR, GFP_KERNEL);
if (!packet)
return -ENOMEM;
@@ -455,40 +445,25 @@ static ssize_t ib_umad_write(struct file
if (rmpp_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_ADM) {
hdr_len = IB_MGMT_SA_HDR;
copy_offset = IB_MGMT_RMPP_HDR;
- has_rmpp_header = 1;
+ rmpp_active = ib_get_rmpp_flags(&rmpp_mad->rmpp_hdr) &
+ IB_MGMT_RMPP_FLAG_ACTIVE;
} else if (rmpp_mad->mad_hdr.mgmt_class >=
IB_MGMT_CLASS_VENDOR_RANGE2_START &&
rmpp_mad->mad_hdr.mgmt_class <=
IB_MGMT_CLASS_VENDOR_RANGE2_END) {
- hdr_len = IB_MGMT_VENDOR_HDR;
- copy_offset = IB_MGMT_RMPP_HDR;
- has_rmpp_header = 1;
+ hdr_len = IB_MGMT_VENDOR_HDR;
+ copy_offset = IB_MGMT_RMPP_HDR;
+ rmpp_active = ib_get_rmpp_flags(&rmpp_mad->rmpp_hdr) &
+ IB_MGMT_RMPP_FLAG_ACTIVE;
} else {
hdr_len = IB_MGMT_MAD_HDR;
copy_offset = IB_MGMT_MAD_HDR;
- has_rmpp_header = 0;
- }
-
- if (has_rmpp_header)
- rmpp_active = ib_get_rmpp_flags(&rmpp_mad->rmpp_hdr) &
- IB_MGMT_RMPP_FLAG_ACTIVE;
- else
rmpp_active = 0;
-
- /* Validate that the management class can support RMPP */
- if (rmpp_active && !agent->rmpp_version) {
- ret = -EINVAL;
- goto err_ah;
- }
-
- if (!rmpp_active && length > sizeof(struct ib_mad)) {
- ret = -EINVAL;
- goto err_ah;
}
+ data_len = count - sizeof (struct ib_user_mad) - hdr_len;
packet->msg = ib_create_send_mad(agent,
be32_to_cpu(packet->mad.hdr.qpn),
- 0, rmpp_active,
- hdr_len, length - hdr_len,
- GFP_KERNEL);
+ 0, rmpp_active, hdr_len,
+ data_len, GFP_KERNEL);
if (IS_ERR(packet->msg)) {
ret = PTR_ERR(packet->msg);
goto err_ah;
@@ -499,32 +474,21 @@ static ssize_t ib_umad_write(struct file
packet->msg->retries = packet->mad.hdr.retries;
packet->msg->context[0] = packet;
- /* Copy MAD headers (RMPP header in place) */
+ /* Copy MAD header. Any RMPP header is already in place. */
memcpy(packet->msg->mad, packet->mad.data, IB_MGMT_MAD_HDR);
- /* complete copying first 256 bytes of message into send buffer */
- if (copy_from_user(packet->msg->mad + copy_offset,
- buf + sizeof (struct ib_user_mad) + copy_offset,
- min_t(int, length, sizeof(struct ib_mad)) -
copy_offset)) {
- ret = -EFAULT;
- goto err_msg;
- }
+ buf += sizeof (struct ib_user_mad);
- /* if RMPP, copy rest of send message from user to multipacket list */
- length -= sizeof(struct ib_mad);
- if (length > 0) {
- buf += sizeof (struct ib_user_mad) + sizeof(struct ib_mad);
- for (seg_num = 2; length > 0; ++seg_num, buf += s, length -= s)
{
- seg = ib_get_rmpp_segment(packet->msg, seg_num);
- BUG_ON(!seg);
- s = min_t(int, length, seg->size);
- if (copy_from_user(seg->data, buf, s)) {
- ret = -EFAULT;
- goto err_msg;
- }
+ if (!rmpp_active) {
+ if (copy_from_user(packet->msg->mad + copy_offset,
+ buf + copy_offset,
+ hdr_len + data_len - copy_offset)) {
+ ret = -EFAULT;
+ goto err_msg;
}
- /* Pad last segment with zeroes. */
- if (seg->size - s)
- memset(seg->data + s, 0, seg->size - s);
+ } else {
+ ret = copy_rmpp_mad(packet->msg, buf);
+ if (ret)
+ goto err_msg;
}
/*
@@ -548,18 +512,14 @@ static ssize_t ib_umad_write(struct file
goto err_msg;
up_read(&file->port->mutex);
-
return count;
err_msg:
ib_free_send_mad(packet->msg);
-
err_ah:
ib_destroy_ah(ah);
-
err_up:
up_read(&file->port->mutex);
-
err:
kfree(packet);
return ret;
Index: include/rdma/ib_mad.h
===================================================================
--- include/rdma/ib_mad.h (revision 5552)
+++ include/rdma/ib_mad.h (working copy)
@@ -141,13 +141,6 @@ struct ib_rmpp_hdr {
__be32 paylen_newwin;
};
-struct ib_rmpp_segment {
- struct list_head list;
- u32 num;
- u16 size;
- u8 data[0];
-};
-
typedef u64 __bitwise ib_sa_comp_mask;
#define IB_SA_COMP_MASK(n) ((__force ib_sa_comp_mask) cpu_to_be64(1ull << n))
@@ -215,15 +208,23 @@ struct ib_class_port_info
/**
* ib_mad_send_buf - MAD data buffer and work request for sends.
* @next: A pointer used to chain together MADs for posting.
- * @mad: References an allocated MAD data buffer.
+ * @mad: References an allocated MAD data buffer for MADs that do not have
+ * RMPP active. For MADs using RMPP, references the common and management
+ * class specific headers.
* @mad_agent: MAD agent that allocated the buffer.
* @ah: The address handle to use when sending the MAD.
* @context: User-controlled context fields.
+ * @hdr_len: Indicates the size of the data header of the MAD. This length
+ * includes the common MAD, RMPP, and class specific headers.
+ * @data_len: Indicates the total size of user-transferred data.
+ * @seg_count: The number of RMPP segments allocated for this send.
+ * @seg_size: Size of each RMPP segment.
* @timeout_ms: Time to wait for a response.
* @retries: Number of times to retry a request for a response.
*
* Users are responsible for initializing the MAD buffer itself, with the
- * exception of specifying the payload length field in any RMPP MAD.
+ * exception of any RMPP header. Additional segment buffer space allocated
+ * beyond data_len is padding.
*/
struct ib_mad_send_buf {
struct ib_mad_send_buf *next;
@@ -231,6 +232,10 @@ struct ib_mad_send_buf {
struct ib_mad_agent *mad_agent;
struct ib_ah *ah;
void *context[2];
+ int hdr_len;
+ int data_len;
+ int seg_count;
+ int seg_size;
int timeout_ms;
int retries;
};
@@ -586,9 +591,10 @@ int ib_process_mad_wc(struct ib_mad_agen
* with an initialized work request structure. Users may modify the returned
* MAD data buffer before posting the send.
*
- * The returned data buffer will be cleared. Users are responsible for
- * initializing the common MAD and any class specific headers. If @rmpp_active
- * is set, the RMPP header will be initialized for sending.
+ * The returned MAD header, class specific headers, and any padding will be
+ * cleared. Users are responsible for initializing the common MAD header,
+ * any class specific header, and MAD data area.
+ * If @rmpp_active is set, the RMPP header will be initialized for sending.
*/
struct ib_mad_send_buf * ib_create_send_mad(struct ib_mad_agent *mad_agent,
u32 remote_qpn, u16 pkey_index,
@@ -597,14 +603,14 @@ struct ib_mad_send_buf * ib_create_send_
gfp_t gfp_mask);
/**
- * *ib_get_rmpp_segment - returns a given RMPP segment.
+ * ib_get_rmpp_segment - returns the data buffer for a given RMPP segment.
* @send_buf: Previously allocated send data buffer.
* @seg_num: number of segment to return
*
- * This routine returns a pointer to a segment of an RMPP message.
+ * This routine returns a pointer to the data buffer of an RMPP MAD.
+ * Users must provide synchronization to @send_buf around this call.
*/
-struct ib_rmpp_segment *ib_get_rmpp_segment(struct ib_mad_send_buf *send_buf,
- int seg_num);
+void *ib_get_rmpp_segment(struct ib_mad_send_buf *send_buf, int seg_num);
/**
* ib_free_send_mad - Returns data buffers used to send a MAD.
_______________________________________________
openib-general mailing list
[email protected]
http://openib.org/mailman/listinfo/openib-general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
