Files
@ bd21c8aa7237
Branch filter:
Location: vmkdrivers/vmkdrivers/src_9/drivers/net/mlnx/mlx4_en/en_rx.c
bd21c8aa7237
32.2 KiB
text/x-csrc
ESXi-6.0.0b
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 | /*
* Copyright (c) 2007-2013 Mellanox Technologies. All rights reserved.
*
* This software is available to you 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.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*/
#include <linux/mlx4/cq.h>
#include <linux/slab.h>
#include <linux/mlx4/qp.h>
#include <linux/skbuff.h>
#include <linux/if_ether.h>
#include <linux/if_vlan.h>
#include <linux/vmalloc.h>
#ifdef __VMKERNEL_MODULE__
#include <linux/log2.h>
#endif /* __VMKERNEL_MODULE__ */
#include "mlx4_en.h"
#ifdef __VMKERNEL_MODULE__
static int mlx4_en_alloc_frag(struct mlx4_en_priv *priv,
struct mlx4_en_rx_desc *rx_desc,
struct skb_frag_struct *skb_frags,
struct mlx4_en_rx_alloc *ring_alloc,
int i)
{
struct mlx4_en_frag_info *frag_info = &priv->frag_info[i];
struct mlx4_en_rx_alloc *page_alloc = &ring_alloc[i];
struct page *page;
dma_addr_t dma;
/* Allocate new page for every fragment */
page = alloc_pages(GFP_ATOMIC | __GFP_COMP, MLX4_EN_ALLOC_ORDER);
if (!page)
return -ENOMEM;
skb_frags[i].page = page_alloc->page;
skb_frags[i].page_offset = page_alloc->offset;
page_alloc->page = page;
page_alloc->offset = frag_info->frag_align;
dma = dma_map_single(priv->ddev, page_address(skb_frags[i].page) +
skb_frags[i].page_offset, frag_info->frag_size,
PCI_DMA_FROMDEVICE);
if (unlikely(dma_mapping_error(dma))) {
en_err(priv, "Failed dma mapping page for RX buffer\n");
put_page(page);
return -EFAULT;
}
rx_desc->data[i].addr = cpu_to_be64(dma);
return 0;
}
#else
static int mlx4_en_alloc_frag(struct mlx4_en_priv *priv,
struct mlx4_en_rx_desc *rx_desc,
struct page_frag *skb_frags,
struct mlx4_en_rx_alloc *ring_alloc,
int i)
{
struct mlx4_en_frag_info *frag_info = &priv->frag_info[i];
struct mlx4_en_rx_alloc *page_alloc = &ring_alloc[i];
struct page *page;
dma_addr_t dma;
bool new_page = false;
if (page_alloc->offset == frag_info->last_offset) {
/* Allocate new page */
page = alloc_pages(GFP_ATOMIC | __GFP_COMP, MLX4_EN_ALLOC_ORDER);
if (!page)
return -ENOMEM;
skb_frags[i].page = page_alloc->page;
skb_frags[i].offset = page_alloc->offset;
page_alloc->page = page;
page_alloc->offset = frag_info->frag_align;
new_page = true;
} else {
page = page_alloc->page;
get_page(page);
skb_frags[i].page = page;
skb_frags[i].offset = page_alloc->offset;
page_alloc->offset += frag_info->frag_stride;
}
dma = dma_map_single(priv->ddev, page_address(skb_frags[i].page) +
skb_frags[i].offset, frag_info->frag_size,
PCI_DMA_FROMDEVICE);
if (unlikely(dma_mapping_error(priv->ddev, dma))) {
en_err(priv, "Failed dma mapping page for RX buffer\n");
put_page(page);
if (new_page)
page_alloc->offset = frag_info->last_offset;
else
page_alloc->offset -= frag_info->frag_stride;
return -EFAULT;
}
rx_desc->data[i].addr = cpu_to_be64(dma);
return 0;
}
#endif /* __VMKERNEL_MODULE__ */
static int mlx4_en_init_allocator(struct mlx4_en_priv *priv,
struct mlx4_en_rx_ring *ring)
{
struct mlx4_en_rx_alloc *page_alloc;
int i;
for (i = 0; i < priv->num_frags; i++) {
page_alloc = &ring->page_alloc[i];
page_alloc->page = alloc_pages(GFP_ATOMIC | __GFP_COMP,
MLX4_EN_ALLOC_ORDER);
if (!page_alloc->page)
goto out;
page_alloc->offset = priv->frag_info[i].frag_align;
en_dbg(DRV, priv, "Initialized allocator:%d with page:%p\n",
i, page_alloc->page);
}
return 0;
out:
while (i--) {
page_alloc = &ring->page_alloc[i];
put_page(page_alloc->page);
page_alloc->page = NULL;
}
return -ENOMEM;
}
static void mlx4_en_destroy_allocator(struct mlx4_en_priv *priv,
struct mlx4_en_rx_ring *ring)
{
struct mlx4_en_rx_alloc *page_alloc;
int i;
for (i = 0; i < priv->num_frags; i++) {
page_alloc = &ring->page_alloc[i];
#ifndef __VMKERNEL_MODULE__
en_dbg(DRV, priv, "Freeing allocator:%d count:%d\n",
i, page_count(page_alloc->page));
#endif /* NOT __VMKERNEL_MODULE__ */
put_page(page_alloc->page);
page_alloc->page = NULL;
}
}
static void mlx4_en_init_rx_desc(struct mlx4_en_priv *priv,
struct mlx4_en_rx_ring *ring, int index)
{
struct mlx4_en_rx_desc *rx_desc = ring->buf + ring->stride * index;
struct skb_frag_struct *skb_frags = ring->rx_info +
(index << priv->log_rx_info);
int possible_frags;
int i;
/* Set size and memtype fields */
for (i = 0; i < priv->num_frags; i++) {
skb_frag_size_set(&skb_frags[i], priv->frag_info[i].frag_size);
rx_desc->data[i].byte_count =
cpu_to_be32(priv->frag_info[i].frag_size);
rx_desc->data[i].lkey = cpu_to_be32(priv->mdev->mr.key);
}
/* If the number of used fragments does not fill up the ring stride,
* remaining (unused) fragments must be padded with null address/size
* and a special memory key */
possible_frags = (ring->stride - sizeof(struct mlx4_en_rx_desc)) / DS_SIZE;
for (i = priv->num_frags; i < possible_frags; i++) {
rx_desc->data[i].byte_count = 0;
rx_desc->data[i].lkey = cpu_to_be32(MLX4_EN_MEMTYPE_PAD);
rx_desc->data[i].addr = 0;
}
}
static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv,
struct mlx4_en_rx_ring *ring, int index)
{
struct mlx4_en_rx_desc *rx_desc = ring->buf + (index * ring->stride);
#ifndef __VMKERNEL_MODULE__
struct page_frag *skb_frags = ring->rx_info +
(index << priv->log_rx_info);
#else
struct skb_frag_struct *skb_frags = ring->rx_info +
(index << priv->log_rx_info);
#endif /* NOT __VMKERNEL_MODULE__ */
int i;
for (i = 0; i < priv->num_frags; i++)
if (mlx4_en_alloc_frag(priv, rx_desc, skb_frags, ring->page_alloc, i))
goto err;
return 0;
err:
while (i--) {
dma_addr_t dma = be64_to_cpu(rx_desc->data[i].addr);
pci_unmap_single(priv->mdev->pdev, dma, skb_frags[i].size,
PCI_DMA_FROMDEVICE);
put_page(skb_frags[i].page);
}
return -ENOMEM;
}
static inline void mlx4_en_update_rx_prod_db(struct mlx4_en_rx_ring *ring)
{
*ring->wqres.db.db = cpu_to_be32(ring->prod & 0xffff);
}
static void mlx4_en_free_rx_desc(struct mlx4_en_priv *priv,
struct mlx4_en_rx_ring *ring,
int index)
{
#ifndef __VMKERNEL_MODULE__
struct page_frag *skb_frags;
#else
struct skb_frag_struct *skb_frags;
#endif /* NOT __VMKERNEL_MODULE__ */
struct mlx4_en_rx_desc *rx_desc = ring->buf + (index << ring->log_stride);
dma_addr_t dma;
int nr;
skb_frags = ring->rx_info + (index << priv->log_rx_info);
for (nr = 0; nr < priv->num_frags; nr++) {
en_dbg(DRV, priv, "Freeing fragment:%d\n", nr);
dma = be64_to_cpu(rx_desc->data[nr].addr);
en_dbg(DRV, priv, "Unmapping buffer at dma:0x%llx\n", (u64) dma);
dma_unmap_single(priv->ddev, dma, skb_frags[nr].size,
PCI_DMA_FROMDEVICE);
put_page(skb_frags[nr].page);
}
}
static int mlx4_en_fill_rx_buffers(struct mlx4_en_priv *priv)
{
struct mlx4_en_rx_ring *ring;
int ring_ind;
int buf_ind;
int new_size;
#ifdef __VMKERNEL_MODULE__
int err;
#endif /* __VMKERNEL_MODULE__ */
for (buf_ind = 0; buf_ind < priv->prof->rx_ring_size; buf_ind++) {
for (ring_ind = 0; ring_ind < priv->rx_ring_num; ring_ind++) {
ring = &priv->rx_ring[ring_ind];
#ifndef __VMKERNEL_MODULE__
if (mlx4_en_prepare_rx_desc(priv, ring,
ring->actual_size)) {
#else
if (priv->use_rx_frags)
err = mlx4_en_prepare_rx_desc(priv, ring, ring->actual_size);
else
err = mlx4_en_prepare_rx_desc_skb(priv, ring, ring->actual_size);
if (err) {
#endif /* __VMKERNEL_MODULE__ */
if (ring->actual_size < MLX4_EN_MIN_RX_SIZE) {
en_err(priv, "Failed to allocate "
"enough rx buffers\n");
return -ENOMEM;
} else {
new_size = rounddown_pow_of_two(ring->actual_size);
en_warn(priv, "Only %d buffers allocated "
"reducing ring size to %d",
ring->actual_size, new_size);
goto reduce_rings;
}
}
ring->actual_size++;
ring->prod++;
}
}
return 0;
reduce_rings:
for (ring_ind = 0; ring_ind < priv->rx_ring_num; ring_ind++) {
ring = &priv->rx_ring[ring_ind];
while (ring->actual_size > new_size) {
ring->actual_size--;
ring->prod--;
#ifndef __VMKERNEL_MODULE__
mlx4_en_free_rx_desc(priv, ring, ring->actual_size);
#else
if (priv->use_rx_frags)
mlx4_en_free_rx_desc(priv, ring, ring->actual_size);
else
mlx4_en_free_rx_desc_skb(priv, ring, ring->actual_size);
#endif /* __VMKERNEL_MODULE__ */
}
}
return 0;
}
static void mlx4_en_free_rx_buf(struct mlx4_en_priv *priv,
struct mlx4_en_rx_ring *ring)
{
int index;
en_dbg(DRV, priv, "Freeing Rx buf - cons:%d prod:%d\n",
ring->cons, ring->prod);
/* Unmap and free Rx buffers */
BUG_ON((u32) (ring->prod - ring->cons) > ring->actual_size);
while (ring->cons != ring->prod) {
index = ring->cons & ring->size_mask;
en_dbg(DRV, priv, "Processing descriptor:%d\n", index);
#ifndef __VMKERNEL_MODULE__
mlx4_en_free_rx_desc(priv, ring, index);
#else
if (priv->use_rx_frags)
mlx4_en_free_rx_desc(priv, ring, index);
else
mlx4_en_free_rx_desc_skb(priv, ring, index);
#endif /* __VMKERNEL_MODULE__ */
++ring->cons;
}
}
int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
struct mlx4_en_rx_ring *ring, u32 size, u16 stride)
{
struct mlx4_en_dev *mdev = priv->mdev;
int err;
int tmp;
ring->prod = 0;
ring->cons = 0;
ring->size = size;
ring->size_mask = size - 1;
ring->stride = stride;
ring->log_stride = ffs(ring->stride) - 1;
ring->buf_size = ring->size * ring->stride + TXBB_SIZE;
#ifndef __VMKERNEL_MODULE__
tmp = size * roundup_pow_of_two(MLX4_EN_MAX_RX_FRAGS *
sizeof(struct skb_frag_struct));
#else
if (priv->use_rx_frags)
tmp = size * roundup_pow_of_two(MLX4_EN_MAX_RX_FRAGS *
sizeof(struct skb_frag_struct));
else
tmp = size * sizeof(struct sk_buff *);
#endif /* __VMKERNEL_MODULE__ */
ring->rx_info = vmalloc(tmp);
if (!ring->rx_info)
return -ENOMEM;
en_dbg(DRV, priv, "Allocated rx_info ring at addr:%p size:%d\n",
ring->rx_info, tmp);
err = mlx4_alloc_hwq_res(mdev->dev, &ring->wqres,
ring->buf_size, 2 * PAGE_SIZE);
if (err)
goto err_ring;
err = mlx4_en_map_buffer(&ring->wqres.buf);
if (err) {
en_err(priv, "Failed to map RX buffer\n");
goto err_hwq;
}
ring->buf = ring->wqres.buf.direct.buf;
return 0;
err_hwq:
mlx4_free_hwq_res(mdev->dev, &ring->wqres, ring->buf_size);
err_ring:
vfree(ring->rx_info);
ring->rx_info = NULL;
return err;
}
int mlx4_en_activate_rx_rings(struct mlx4_en_priv *priv)
{
struct mlx4_en_rx_ring *ring;
int i;
int ring_ind;
int err;
#ifndef __VMKERNEL_MODULE__
int stride = roundup_pow_of_two(sizeof(struct mlx4_en_rx_desc) +
DS_SIZE * priv->num_frags);
#else
int stride = priv->use_rx_frags ?
roundup_pow_of_two(sizeof(struct mlx4_en_rx_desc) +
DS_SIZE * priv->num_frags) : 0;
#endif /* __VMKERNEL_MODULE__ */
for (ring_ind = 0; ring_ind < priv->rx_ring_num; ring_ind++) {
ring = &priv->rx_ring[ring_ind];
ring->prod = 0;
ring->cons = 0;
ring->actual_size = 0;
ring->cqn = priv->rx_cq[ring_ind].mcq.cqn;
#ifndef __VMKERNEL_MODULE__
ring->stride = stride;
#else
if (priv->use_rx_frags)
ring->stride = stride;
#endif /* __VMKERNEL_MODULE__ */
if (ring->stride <= TXBB_SIZE)
ring->buf += TXBB_SIZE;
ring->log_stride = ffs(ring->stride) - 1;
ring->buf_size = ring->size * ring->stride;
memset(ring->buf, 0, ring->buf_size);
mlx4_en_update_rx_prod_db(ring);
#ifndef __VMKERNEL_MODULE__
/* Initailize all descriptors */
for (i = 0; i < ring->size; i++)
mlx4_en_init_rx_desc(priv, ring, i);
/* Initialize page allocators */
err = mlx4_en_init_allocator(priv, ring);
if (err) {
en_err(priv, "Failed initializing ring allocator\n");
if (ring->stride <= TXBB_SIZE)
ring->buf -= TXBB_SIZE;
ring_ind--;
goto err_allocator;
}
#else
/* Initailize all descriptors */
for (i = 0; i < ring->size; i++) {
if (priv->use_rx_frags)
mlx4_en_init_rx_desc(priv, ring, i);
else
mlx4_en_init_rx_desc_skb(priv, ring, i);
}
if (priv->use_rx_frags) {
/* Initialize page allocators */
err = mlx4_en_init_allocator(priv, ring);
if (err) {
en_err(priv, "Failed initializing ring allocator\n");
if (ring->stride <= TXBB_SIZE)
ring->buf -= TXBB_SIZE;
ring_ind--;
goto err_allocator;
}
}
#endif /* __VMKERNEL_MODULE__ */
}
err = mlx4_en_fill_rx_buffers(priv);
if (err)
goto err_buffers;
for (ring_ind = 0; ring_ind < priv->rx_ring_num; ring_ind++) {
ring = &priv->rx_ring[ring_ind];
ring->size_mask = ring->actual_size - 1;
mlx4_en_update_rx_prod_db(ring);
}
return 0;
err_buffers:
for (ring_ind = 0; ring_ind < priv->rx_ring_num; ring_ind++)
mlx4_en_free_rx_buf(priv, &priv->rx_ring[ring_ind]);
ring_ind = priv->rx_ring_num - 1;
err_allocator:
#ifndef __VMKERNEL_MODULE__
while (ring_ind >= 0) {
if (priv->rx_ring[ring_ind].stride <= TXBB_SIZE)
priv->rx_ring[ring_ind].buf -= TXBB_SIZE;
mlx4_en_destroy_allocator(priv, &priv->rx_ring[ring_ind]);
ring_ind--;
}
#else
while (ring_ind >= 0) {
if (priv->rx_ring[ring_ind].stride <= TXBB_SIZE)
priv->rx_ring[ring_ind].buf -= TXBB_SIZE;
if (priv->use_rx_frags)
mlx4_en_destroy_allocator(priv, &priv->rx_ring[ring_ind]);
ring_ind--;
}
#endif /* __VMKERNEL_MODULE__ */
return err;
}
void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
struct mlx4_en_rx_ring *ring, u32 size, u16 stride)
{
struct mlx4_en_dev *mdev = priv->mdev;
mlx4_en_unmap_buffer(&ring->wqres.buf);
mlx4_free_hwq_res(mdev->dev, &ring->wqres, size * stride + TXBB_SIZE);
vfree(ring->rx_info);
ring->rx_info = NULL;
}
void mlx4_en_deactivate_rx_ring(struct mlx4_en_priv *priv,
struct mlx4_en_rx_ring *ring)
{
mlx4_en_free_rx_buf(priv, ring);
if (ring->stride <= TXBB_SIZE)
ring->buf -= TXBB_SIZE;
#ifndef __VMKERNEL_MODULE__
mlx4_en_destroy_allocator(priv, ring);
#else
if (priv->use_rx_frags)
mlx4_en_destroy_allocator(priv, ring);
#endif /* __VMKERNEL_MODULE__ */
}
/* Unmap a completed descriptor and free unused pages */
static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
struct mlx4_en_rx_desc *rx_desc,
#ifndef __VMKERNEL_MODULE__
struct page_frag *skb_frags,
#else
struct skb_frag_struct *skb_frags,
#endif /* NOT __VMKERNEL_MODULE__ */
struct sk_buff *skb,
struct mlx4_en_rx_alloc *page_alloc,
int length)
{
struct skb_frag_struct *skb_frags_rx = skb_shinfo(skb)->frags;
struct mlx4_en_frag_info *frag_info;
int nr;
dma_addr_t dma;
/* Collect used fragments while replacing them in the HW descirptors */
for (nr = 0; nr < priv->num_frags; nr++) {
frag_info = &priv->frag_info[nr];
if (length <= frag_info->frag_prefix_size)
break;
/* Save page reference in skb */
__skb_frag_set_page(&skb_frags_rx[nr], skb_frags[nr].page);
skb_frag_size_set(&skb_frags_rx[nr], skb_frags[nr].size);
#ifndef __VMKERNEL_MODULE__
skb_frags_rx[nr].page_offset = skb_frags[nr].offset;
#else
skb_frags_rx[nr].page_offset = skb_frags[nr].page_offset;
#endif /* NOT __VMKERNEL_MODULE__ */
skb->truesize += frag_info->frag_stride;
dma = be64_to_cpu(rx_desc->data[nr].addr);
/* Allocate a replacement page */
if (mlx4_en_alloc_frag(priv, rx_desc, skb_frags, page_alloc, nr))
goto fail;
/* Unmap buffer */
dma_unmap_single(priv->ddev, dma, skb_frag_size(&skb_frags_rx[nr]),
PCI_DMA_FROMDEVICE);
}
/* Adjust size of last fragment to match actual length */
if (nr > 0)
skb_frag_size_set(&skb_frags_rx[nr - 1],
length - priv->frag_info[nr - 1].frag_prefix_size);
return nr;
fail:
/* Drop all accumulated fragments (which have already been replaced in
* the descriptor) of this packet; remaining fragments are reused... */
while (nr > 0) {
nr--;
__skb_frag_unref(&skb_frags_rx[nr]);
}
return 0;
}
static struct sk_buff *mlx4_en_rx_skb(struct mlx4_en_priv *priv,
struct mlx4_en_rx_desc *rx_desc,
#ifndef __VMKERNEL_MODULE__
struct page_frag *skb_frags,
#else
struct skb_frag_struct *skb_frags,
#endif /* NOT __VMKERNEL_MODULE__ */
struct mlx4_en_rx_alloc *page_alloc,
unsigned int length)
{
struct sk_buff *skb;
void *va;
int used_frags;
dma_addr_t dma;
skb = netdev_alloc_skb(priv->dev, SMALL_PACKET_SIZE + NET_IP_ALIGN);
if (!skb) {
en_dbg(RX_ERR, priv, "Failed allocating skb\n");
return NULL;
}
skb_reserve(skb, NET_IP_ALIGN);
skb->len = length;
/* Get pointer to first fragment so we could copy the headers into the
* (linear part of the) skb */
#ifndef __VMKERNEL_MODULE__
va = page_address(skb_frags[0].page) + skb_frags[0].offset;
#else
va = page_address(skb_frags[0].page) + skb_frags[0].page_offset;
#endif /* NOT __VMKERNEL_MODULE__ */
if (length <= SMALL_PACKET_SIZE) {
/* We are copying all relevant data to the skb - temporarily
* synch buffers for the copy */
dma = be64_to_cpu(rx_desc->data[0].addr);
dma_sync_single_for_cpu(priv->ddev, dma, length,
DMA_FROM_DEVICE);
skb_copy_to_linear_data(skb, va, length);
dma_sync_single_for_device(priv->ddev, dma, length,
DMA_FROM_DEVICE);
skb->tail += length;
skb->truesize = length + sizeof(struct sk_buff);
} else {
/* Move relevant fragments to skb */
used_frags = mlx4_en_complete_rx_desc(priv, rx_desc, skb_frags,
skb, page_alloc, length);
if (unlikely(!used_frags)) {
kfree_skb(skb);
return NULL;
}
skb_shinfo(skb)->nr_frags = used_frags;
/* Copy headers into the skb linear buffer */
memcpy(skb->data, va, HEADER_COPY_SIZE);
skb->tail += HEADER_COPY_SIZE;
/* Skip headers in first fragment */
skb_shinfo(skb)->frags[0].page_offset += HEADER_COPY_SIZE;
/* Adjust size of first fragment */
skb_frag_size_sub(&skb_shinfo(skb)->frags[0], HEADER_COPY_SIZE);
skb->data_len = length - HEADER_COPY_SIZE;
}
return skb;
}
#ifdef __VMKERNEL_ETHTOOL_SELF_TEST_SUPPORT__
void validate_loopback(struct mlx4_en_priv *priv, struct sk_buff *skb)
{
int i;
int offset = ETH_HLEN;
for (i = 0; i < MLX4_LOOPBACK_TEST_PAYLOAD; i++, offset++) {
if (*(skb->data + offset) != (unsigned char) (i & 0xff))
goto out_loopback;
}
/* Loopback found */
priv->loopback_ok = 1;
out_loopback:
dev_kfree_skb_any(skb);
}
#endif /* __VMKERNEL_ETHTOOL_SELF_TEST_SUPPORT__ */
int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int budget)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_cqe *cqe;
struct mlx4_en_rx_ring *ring = &priv->rx_ring[cq->ring];
#ifndef __VMKERNEL_MODULE__
struct page_frag *skb_frags;
#else
struct skb_frag_struct *skb_frags;
#endif /* NOT __VMKERNEL_MODULE__ */
struct mlx4_en_rx_desc *rx_desc;
struct sk_buff *skb;
int index;
#ifdef __VMKERNEL_NETDEV_GRO_FEATURE_SUPPORT_
int nr;
#endif /* __VMKERNEL_NETDEV_GRO_FEATURE_SUPPORT_ */
unsigned int length;
int polled = 0;
int ip_summed;
struct ethhdr *ethh;
u64 s_mac;
int factor = priv->cqe_factor;
/* We assume a 1:1 mapping between CQEs and Rx descriptors, so Rx
* descriptor offset can be deduced from the CQE index instead of
* reading 'cqe->index' */
index = cq->mcq.cons_index & ring->size_mask;
cqe = &cq->buf[(index << factor) + factor];
/* Process all completed CQEs */
while (XNOR(cqe->owner_sr_opcode & MLX4_CQE_OWNER_MASK,
cq->mcq.cons_index & cq->size)) {
skb_frags = ring->rx_info + (index << priv->log_rx_info);
rx_desc = ring->buf + (index << ring->log_stride);
/*
* make sure we read the CQE after we read the ownership bit
*/
rmb();
/* Drop packet on bad receive or bad checksum */
if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) ==
MLX4_CQE_OPCODE_ERROR)) {
en_err(priv, "CQE completed in error - vendor "
"syndrom:%d syndrom:%d\n",
((struct mlx4_err_cqe *) cqe)->vendor_err_syndrome,
((struct mlx4_err_cqe *) cqe)->syndrome);
goto next;
}
if (unlikely(cqe->badfcs_enc & MLX4_CQE_BAD_FCS)) {
en_dbg(RX_ERR, priv, "Accepted frame with bad FCS\n");
goto next;
}
/* Get pointer to first fragment since we haven't skb yet and
* cast it to ethhdr struct */
ethh = (struct ethhdr *)(page_address(skb_frags[0].page) +
#ifndef __VMKERNEL_MODULE__
skb_frags[0].offset);
#else
skb_frags[0].page_offset);
#endif /* NOT __VMKERNEL_MODULE__ */
s_mac = mlx4_en_mac_to_u64(ethh->h_source);
#ifdef __VMKERNEL_ETHTOOL_SELF_TEST_SUPPORT__
/* If source MAC is equal to our own MAC and not performing
* the selftest or flb disabled - drop the packet */
if (s_mac == priv->mac &&
(!(dev->features & NETIF_F_LOOPBACK) ||
!priv->validate_loopback))
goto next;
#else
/* If source MAC is equal to our own MAC and not performing
* the selftest */
if (s_mac == priv->mac)
goto next;
#endif /* __VMKERNEL_ETHTOOL_SELF_TEST_SUPPORT__ */
/*
* Packet is OK - process it.
*/
length = be32_to_cpu(cqe->byte_cnt);
length -= ring->fcs_del;
ring->bytes += length;
ring->packets++;
#ifdef __VMKERNEL_NETDEV_ADVANCE_FEATURES_SUPPORT__
if (likely(dev->features & NETIF_F_RXCSUM)) {
#else
if (likely(priv->rx_csum)) {
#endif /* __VMKERNEL_NETDEV_ADVANCE_FEATURES_SUPPORT__ */
if ((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) &&
(cqe->checksum == cpu_to_be16(0xffff))) {
ring->csum_ok++;
#ifdef __VMKERNEL_NETDEV_GRO_FEATURE_SUPPORT_
/* This packet is eligible for LRO if it is:
* - DIX Ethernet (type interpretation)
* - TCP/IP (v4)
* - without IP options
* - not an IP fragment */
if (dev->features & NETIF_F_GRO) {
struct sk_buff *gro_skb = napi_get_frags(&cq->napi);
if (!gro_skb)
goto next;
nr = mlx4_en_complete_rx_desc(
priv, rx_desc,
skb_frags, gro_skb,
ring->page_alloc, length);
if (!nr)
goto next;
skb_shinfo(gro_skb)->nr_frags = nr;
gro_skb->len = length;
gro_skb->data_len = length;
gro_skb->ip_summed = CHECKSUM_UNNECESSARY;
if (cqe->vlan_my_qpn &
cpu_to_be32(MLX4_CQE_VLAN_PRESENT_MASK)) {
u16 vid = be16_to_cpu(cqe->sl_vid);
__vlan_hwaccel_put_tag(gro_skb, vid);
}
#ifdef __VMKERNEL_NETDEV_ADVANCE_FEATURES_SUPPORT__
if (dev->features & NETIF_F_RXHASH)
gro_skb->rxhash = be32_to_cpu(cqe->immed_rss_invalid);
#endif /* __VMKERNEL_NETDEV_ADVANCE_FEATURES_SUPPORT__ */
#ifndef __VMKERNEL_MODULE__
skb_record_rx_queue(gro_skb, cq->ring);
#endif /* NOT __VMKERNEL_MODULE__ */
napi_gro_frags(&cq->napi);
goto next;
}
/* LRO not possible, complete processing here */
#endif /* __VMKERNEL_NETDEV_GRO_FEATURE_SUPPORT_ */
ip_summed = CHECKSUM_UNNECESSARY;
} else {
ip_summed = CHECKSUM_NONE;
ring->csum_none++;
}
} else {
ip_summed = CHECKSUM_NONE;
ring->csum_none++;
}
skb = mlx4_en_rx_skb(priv, rx_desc, skb_frags,
ring->page_alloc, length);
if (!skb) {
priv->stats.rx_dropped++;
goto next;
}
#ifdef __VMKERNEL_ETHTOOL_SELF_TEST_SUPPORT__
if (unlikely(priv->validate_loopback)) {
validate_loopback(priv, skb);
goto next;
}
#endif /* __VMKERNEL_ETHTOOL_SELF_TEST_SUPPORT__ */
skb->ip_summed = ip_summed;
skb->protocol = eth_type_trans(skb, dev);
#ifdef __VMKERNEL_MODULE__
if (priv->netq)
skb_record_rx_queue(skb, cq->ring);
#else
skb_record_rx_queue(skb, cq->ring);
#endif /* __VMKERNEL_MODULE__ */
#ifdef __VMKERNEL_NETDEV_ADVANCE_FEATURES_SUPPORT__
if (dev->features & NETIF_F_RXHASH)
skb->rxhash = be32_to_cpu(cqe->immed_rss_invalid);
#endif /* __VMKERNEL_NETDEV_ADVANCE_FEATURES_SUPPORT__ */
#ifndef __VMKERNEL_MODULE__
if (be32_to_cpu(cqe->vlan_my_qpn) &
MLX4_CQE_VLAN_PRESENT_MASK)
__vlan_hwaccel_put_tag(skb, be16_to_cpu(cqe->sl_vid));
/* Push it up the stack */
netif_receive_skb(skb);
#else
if (be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_VLAN_PRESENT_MASK)
vlan_hwaccel_receive_skb(skb, NULL, be16_to_cpu(cqe->sl_vid));
else
netif_receive_skb(skb);
#endif /* __VMKERNEL_MODULE__ */
next:
++cq->mcq.cons_index;
index = (cq->mcq.cons_index) & ring->size_mask;
cqe = &cq->buf[(index << factor) + factor];
if (++polled == budget) {
/* We are here because we reached the NAPI budget -
* flush only pending LRO sessions */
goto out;
}
}
out:
AVG_PERF_COUNTER(priv->pstats.rx_coal_avg, polled);
mlx4_cq_set_ci(&cq->mcq);
wmb(); /* ensure HW sees CQ consumer before we post new buffers */
ring->cons = cq->mcq.cons_index;
ring->prod += polled; /* Polled descriptors were realocated in place */
mlx4_en_update_rx_prod_db(ring);
return polled;
}
void mlx4_en_rx_irq(struct mlx4_cq *mcq)
{
struct mlx4_en_cq *cq = container_of(mcq, struct mlx4_en_cq, mcq);
struct mlx4_en_priv *priv = netdev_priv(cq->dev);
if (priv->port_up)
napi_schedule(&cq->napi);
else
mlx4_en_arm_cq(priv, cq);
}
/* Rx CQ polling - called by NAPI */
int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget)
{
struct mlx4_en_cq *cq = container_of(napi, struct mlx4_en_cq, napi);
struct net_device *dev = cq->dev;
struct mlx4_en_priv *priv = netdev_priv(dev);
int done;
done = mlx4_en_process_rx_cq(dev, cq, budget);
/* If we used up all the quota - we're probably not done yet... */
if (done == budget)
INC_PERF_COUNTER(priv->pstats.napi_quota_rx);
else {
/* Done for now */
napi_complete(napi);
mlx4_en_arm_cq(priv, cq);
}
return done;
}
/* Calculate the last offset position that accommodates a full fragment
* (assuming fagment size = stride-align) */
static int mlx4_en_last_alloc_offset(struct mlx4_en_priv *priv, u16 stride, u16 align)
{
u16 res = MLX4_EN_ALLOC_SIZE % stride;
u16 offset = MLX4_EN_ALLOC_SIZE - stride - res + align;
en_dbg(DRV, priv, "Calculated last offset for stride:%d align:%d "
"res:%d offset:%d\n", stride, align, res, offset);
return offset;
}
static int frag_sizes[] = {
FRAG_SZ0,
FRAG_SZ1,
FRAG_SZ2,
FRAG_SZ3
};
void mlx4_en_calc_rx_buf(struct net_device *dev)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
int eff_mtu = dev->mtu + ETH_HLEN + VLAN_HLEN + ETH_LLC_SNAP_SIZE;
int buf_size = 0;
int i = 0;
#ifdef __VMKERNEL_MODULE__
if (priv->use_rx_frags) {
#endif /* __VMKERNEL_MODULE__ */
while (buf_size < eff_mtu) {
priv->frag_info[i].frag_size =
(eff_mtu > buf_size + frag_sizes[i]) ?
frag_sizes[i] : eff_mtu - buf_size;
priv->frag_info[i].frag_prefix_size = buf_size;
if (!i) {
priv->frag_info[i].frag_align = NET_IP_ALIGN;
priv->frag_info[i].frag_stride =
ALIGN(frag_sizes[i] + NET_IP_ALIGN, SMP_CACHE_BYTES);
} else {
priv->frag_info[i].frag_align = 0;
priv->frag_info[i].frag_stride =
ALIGN(frag_sizes[i], SMP_CACHE_BYTES);
}
priv->frag_info[i].last_offset = mlx4_en_last_alloc_offset(
priv, priv->frag_info[i].frag_stride,
priv->frag_info[i].frag_align);
buf_size += priv->frag_info[i].frag_size;
i++;
}
#ifdef __VMKERNEL_MODULE__
}
#endif /* __VMKERNEL_MODULE__ */
priv->num_frags = i;
priv->rx_skb_size = eff_mtu;
#ifndef __VMKERNEL_MODULE__
priv->log_rx_info = ROUNDUP_LOG2(i * sizeof(struct skb_frag_struct));
#else
if (priv->use_rx_frags)
priv->log_rx_info = ROUNDUP_LOG2(i * sizeof(struct skb_frag_struct));
#endif /* __VMKERNEL_MODULE__ */
en_dbg(DRV, priv, "Rx buffer scatter-list (effective-mtu:%d "
"num_frags:%d):\n", eff_mtu, priv->num_frags);
for (i = 0; i < priv->num_frags; i++) {
en_dbg(DRV, priv, " frag:%d - size:%d prefix:%d align:%d "
"stride:%d last_offset:%d\n", i,
priv->frag_info[i].frag_size,
priv->frag_info[i].frag_prefix_size,
priv->frag_info[i].frag_align,
priv->frag_info[i].frag_stride,
priv->frag_info[i].last_offset);
}
}
/* RSS related functions */
#if defined(__VMKLNX__) && defined(__VMKNETDDI_QUEUEOPS__)
int mlx4_en_config_rss_qp(struct mlx4_en_priv *priv, int qpn,
struct mlx4_en_rx_ring *ring,
enum mlx4_qp_state *state,
struct mlx4_qp *qp)
#else
static int mlx4_en_config_rss_qp(struct mlx4_en_priv *priv, int qpn,
struct mlx4_en_rx_ring *ring,
enum mlx4_qp_state *state,
struct mlx4_qp *qp)
#endif /* NET QUEUE */
{
struct mlx4_en_dev *mdev = priv->mdev;
struct mlx4_qp_context *context;
int err = 0;
context = kmalloc(sizeof *context , GFP_KERNEL);
if (!context) {
en_err(priv, "Failed to allocate qp context\n");
return -ENOMEM;
}
err = mlx4_qp_alloc(mdev->dev, qpn, qp);
if (err) {
en_err(priv, "Failed to allocate qp #%x\n", qpn);
goto out;
}
qp->event = mlx4_en_sqp_event;
memset(context, 0, sizeof *context);
mlx4_en_fill_qp_context(priv, ring->actual_size, ring->stride, 0, 0,
qpn, ring->cqn, context);
context->db_rec_addr = cpu_to_be64(ring->wqres.db.dma);
/* Cancel FCS removal if FW allows */
if (mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_FCS_KEEP) {
context->param3 |= cpu_to_be32(1 << 29);
ring->fcs_del = ETH_FCS_LEN;
} else
ring->fcs_del = 0;
err = mlx4_qp_to_ready(mdev->dev, &ring->wqres.mtt, context, qp, state);
if (err) {
mlx4_qp_remove(mdev->dev, qp);
mlx4_qp_free(mdev->dev, qp);
}
mlx4_en_update_rx_prod_db(ring);
out:
kfree(context);
return err;
}
/* Allocate rx qp's and configure them according to rss map */
int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
{
struct mlx4_en_dev *mdev = priv->mdev;
struct mlx4_en_rss_map *rss_map = &priv->rss_map;
struct mlx4_qp_context context;
struct mlx4_rss_context *rss_context;
int rss_rings;
void *ptr;
u8 rss_mask = (MLX4_RSS_IPV4 | MLX4_RSS_TCP_IPV4 | MLX4_RSS_IPV6 |
MLX4_RSS_TCP_IPV6);
int i, qpn;
int err = 0;
int good_qps = 0;
static const u32 rsskey[10] = { 0xD181C62C, 0xF7F4DB5B, 0x1983A2FC,
0x943E1ADB, 0xD9389E6B, 0xD1039C2C, 0xA74499AD,
0x593D56D9, 0xF3253C06, 0x2ADC1FFC};
en_dbg(DRV, priv, "Configuring rss steering\n");
err = mlx4_qp_reserve_range(mdev->dev, priv->rx_ring_num,
priv->rx_ring_num,
&rss_map->base_qpn);
if (err) {
en_err(priv, "Failed reserving %d qps\n", priv->rx_ring_num);
return err;
}
for (i = 0; i < priv->rx_ring_num; i++) {
qpn = rss_map->base_qpn + i;
err = mlx4_en_config_rss_qp(priv, qpn, &priv->rx_ring[i],
&rss_map->state[i],
&rss_map->qps[i]);
if (err)
goto rss_err;
++good_qps;
}
/* Configure RSS indirection qp */
err = mlx4_qp_alloc(mdev->dev, priv->base_qpn, &rss_map->indir_qp);
if (err) {
en_err(priv, "Failed to allocate RSS indirection QP\n");
goto rss_err;
}
rss_map->indir_qp.event = mlx4_en_sqp_event;
mlx4_en_fill_qp_context(priv, 0, 0, 0, 1, priv->base_qpn,
priv->rx_ring[0].cqn, &context);
if (!priv->prof->rss_rings || priv->prof->rss_rings > priv->rx_ring_num)
rss_rings = priv->rx_ring_num;
else
rss_rings = priv->prof->rss_rings;
ptr = ((void *) &context) + offsetof(struct mlx4_qp_context, pri_path)
+ MLX4_RSS_OFFSET_IN_QPC_PRI_PATH;
rss_context = ptr;
rss_context->base_qpn = cpu_to_be32(ilog2(rss_rings) << 24 |
(rss_map->base_qpn));
rss_context->default_qpn = cpu_to_be32(rss_map->base_qpn);
if (priv->mdev->profile.udp_rss) {
rss_mask |= MLX4_RSS_UDP_IPV4 | MLX4_RSS_UDP_IPV6;
rss_context->base_qpn_udp = rss_context->default_qpn;
}
rss_context->flags = rss_mask;
rss_context->hash_fn = MLX4_RSS_HASH_TOP;
for (i = 0; i < 10; i++)
rss_context->rss_key[i] = cpu_to_be32(rsskey[i]);
err = mlx4_qp_to_ready(mdev->dev, &priv->res.mtt, &context,
&rss_map->indir_qp, &rss_map->indir_state);
if (err)
goto indir_err;
return 0;
indir_err:
mlx4_qp_modify(mdev->dev, NULL, rss_map->indir_state,
MLX4_QP_STATE_RST, NULL, 0, 0, &rss_map->indir_qp);
mlx4_qp_remove(mdev->dev, &rss_map->indir_qp);
mlx4_qp_free(mdev->dev, &rss_map->indir_qp);
rss_err:
for (i = 0; i < good_qps; i++) {
mlx4_qp_modify(mdev->dev, NULL, rss_map->state[i],
MLX4_QP_STATE_RST, NULL, 0, 0, &rss_map->qps[i]);
mlx4_qp_remove(mdev->dev, &rss_map->qps[i]);
mlx4_qp_free(mdev->dev, &rss_map->qps[i]);
}
mlx4_qp_release_range(mdev->dev, rss_map->base_qpn, priv->rx_ring_num);
return err;
}
void mlx4_en_release_rss_steer(struct mlx4_en_priv *priv)
{
struct mlx4_en_dev *mdev = priv->mdev;
struct mlx4_en_rss_map *rss_map = &priv->rss_map;
int i;
mlx4_qp_modify(mdev->dev, NULL, rss_map->indir_state,
MLX4_QP_STATE_RST, NULL, 0, 0, &rss_map->indir_qp);
mlx4_qp_remove(mdev->dev, &rss_map->indir_qp);
mlx4_qp_free(mdev->dev, &rss_map->indir_qp);
for (i = 0; i < priv->rx_ring_num; i++) {
mlx4_qp_modify(mdev->dev, NULL, rss_map->state[i],
MLX4_QP_STATE_RST, NULL, 0, 0, &rss_map->qps[i]);
mlx4_qp_remove(mdev->dev, &rss_map->qps[i]);
mlx4_qp_free(mdev->dev, &rss_map->qps[i]);
}
mlx4_qp_release_range(mdev->dev, rss_map->base_qpn, priv->rx_ring_num);
}
|