UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge branch 'for-davem' of git://git.kernel.org/pub/scm/linux/kernel/git/bwh/sfc-next 

Ben Hutchings says:

====================
1. Some cleanup from Fengguang Wu and his kbuild robot.
2. Support for ethtool register dump on EF10.
3. Change soft-TSO to take advantage of firmware assistance on EF10.
4. Support for PIO TX buffers and descriptors on EF10, enabled on
architectures that support write-combining mappings.
5. Accelerated RFS support for TCP/IPv6 and UDP/IPv6 on EF10.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
David S. Miller 2013-09-23 16:09:36 -04:00
parent f6982299f2 c47b2d9d56
commit 27c90dcb9c
10 changed files with 807 additions and 159 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

319
drivers/net/ethernet/sfc/ef10.c
View File

@ -285,6 +285,181 @@ static int efx_ef10_free_vis(struct efx_nic *efx)
return rc;
}
#ifdef EFX_USE_PIO
static void efx_ef10_free_piobufs(struct efx_nic *efx)
{
struct efx_ef10_nic_data *nic_data = efx->nic_data;
MCDI_DECLARE_BUF(inbuf, MC_CMD_FREE_PIOBUF_IN_LEN);
unsigned int i;
int rc;
BUILD_BUG_ON(MC_CMD_FREE_PIOBUF_OUT_LEN != 0);
for (i = 0; i < nic_data->n_piobufs; i++) {
MCDI_SET_DWORD(inbuf, FREE_PIOBUF_IN_PIOBUF_HANDLE,
nic_data->piobuf_handle[i]);
rc = efx_mcdi_rpc(efx, MC_CMD_FREE_PIOBUF, inbuf, sizeof(inbuf),
NULL, 0, NULL);
WARN_ON(rc);
}
nic_data->n_piobufs = 0;
}
static int efx_ef10_alloc_piobufs(struct efx_nic *efx, unsigned int n)
{
struct efx_ef10_nic_data *nic_data = efx->nic_data;
MCDI_DECLARE_BUF(outbuf, MC_CMD_ALLOC_PIOBUF_OUT_LEN);
unsigned int i;
size_t outlen;
int rc = 0;
BUILD_BUG_ON(MC_CMD_ALLOC_PIOBUF_IN_LEN != 0);
for (i = 0; i < n; i++) {
rc = efx_mcdi_rpc(efx, MC_CMD_ALLOC_PIOBUF, NULL, 0,
outbuf, sizeof(outbuf), &outlen);
if (rc)
break;
if (outlen < MC_CMD_ALLOC_PIOBUF_OUT_LEN) {
rc = -EIO;
break;
}
nic_data->piobuf_handle[i] =
MCDI_DWORD(outbuf, ALLOC_PIOBUF_OUT_PIOBUF_HANDLE);
netif_dbg(efx, probe, efx->net_dev,
"allocated PIO buffer %u handle %x\n", i,
nic_data->piobuf_handle[i]);
}
nic_data->n_piobufs = i;
if (rc)
efx_ef10_free_piobufs(efx);
return rc;
}
static int efx_ef10_link_piobufs(struct efx_nic *efx)
{
struct efx_ef10_nic_data *nic_data = efx->nic_data;
MCDI_DECLARE_BUF(inbuf,
max(MC_CMD_LINK_PIOBUF_IN_LEN,
MC_CMD_UNLINK_PIOBUF_IN_LEN));
struct efx_channel *channel;
struct efx_tx_queue *tx_queue;
unsigned int offset, index;
int rc;
BUILD_BUG_ON(MC_CMD_LINK_PIOBUF_OUT_LEN != 0);
BUILD_BUG_ON(MC_CMD_UNLINK_PIOBUF_OUT_LEN != 0);
/* Link a buffer to each VI in the write-combining mapping */
for (index = 0; index < nic_data->n_piobufs; ++index) {
MCDI_SET_DWORD(inbuf, LINK_PIOBUF_IN_PIOBUF_HANDLE,
nic_data->piobuf_handle[index]);
MCDI_SET_DWORD(inbuf, LINK_PIOBUF_IN_TXQ_INSTANCE,
nic_data->pio_write_vi_base + index);
rc = efx_mcdi_rpc(efx, MC_CMD_LINK_PIOBUF,
inbuf, MC_CMD_LINK_PIOBUF_IN_LEN,
NULL, 0, NULL);
if (rc) {
netif_err(efx, drv, efx->net_dev,
"failed to link VI %u to PIO buffer %u (%d)\n",
nic_data->pio_write_vi_base + index, index,
rc);
goto fail;
}
netif_dbg(efx, probe, efx->net_dev,
"linked VI %u to PIO buffer %u\n",
nic_data->pio_write_vi_base + index, index);
}
/* Link a buffer to each TX queue */
efx_for_each_channel(channel, efx) {
efx_for_each_channel_tx_queue(tx_queue, channel) {
/* We assign the PIO buffers to queues in
* reverse order to allow for the following
* special case.
*/
offset = ((efx->tx_channel_offset + efx->n_tx_channels -
tx_queue->channel->channel - 1) *
efx_piobuf_size);
index = offset / ER_DZ_TX_PIOBUF_SIZE;
offset = offset % ER_DZ_TX_PIOBUF_SIZE;
/* When the host page size is 4K, the first
* host page in the WC mapping may be within
* the same VI page as the last TX queue. We
* can only link one buffer to each VI.
*/
if (tx_queue->queue == nic_data->pio_write_vi_base) {
BUG_ON(index != 0);
rc = 0;
} else {
MCDI_SET_DWORD(inbuf,
LINK_PIOBUF_IN_PIOBUF_HANDLE,
nic_data->piobuf_handle[index]);
MCDI_SET_DWORD(inbuf,
LINK_PIOBUF_IN_TXQ_INSTANCE,
tx_queue->queue);
rc = efx_mcdi_rpc(efx, MC_CMD_LINK_PIOBUF,
inbuf, MC_CMD_LINK_PIOBUF_IN_LEN,
NULL, 0, NULL);
}
if (rc) {
/* This is non-fatal; the TX path just
* won't use PIO for this queue
*/
netif_err(efx, drv, efx->net_dev,
"failed to link VI %u to PIO buffer %u (%d)\n",
tx_queue->queue, index, rc);
tx_queue->piobuf = NULL;
} else {
tx_queue->piobuf =
nic_data->pio_write_base +
index * EFX_VI_PAGE_SIZE + offset;
tx_queue->piobuf_offset = offset;
netif_dbg(efx, probe, efx->net_dev,
"linked VI %u to PIO buffer %u offset %x addr %p\n",
tx_queue->queue, index,
tx_queue->piobuf_offset,
tx_queue->piobuf);
}
}
}
return 0;
fail:
while (index--) {
MCDI_SET_DWORD(inbuf, UNLINK_PIOBUF_IN_TXQ_INSTANCE,
nic_data->pio_write_vi_base + index);
efx_mcdi_rpc(efx, MC_CMD_UNLINK_PIOBUF,
inbuf, MC_CMD_UNLINK_PIOBUF_IN_LEN,
NULL, 0, NULL);
}
return rc;
}
#else /* !EFX_USE_PIO */
static int efx_ef10_alloc_piobufs(struct efx_nic *efx, unsigned int n)
{
return n == 0 ? 0 : -ENOBUFS;
}
static int efx_ef10_link_piobufs(struct efx_nic *efx)
{
return 0;
}
static void efx_ef10_free_piobufs(struct efx_nic *efx)
{
}
#endif /* EFX_USE_PIO */
static void efx_ef10_remove(struct efx_nic *efx)
{
struct efx_ef10_nic_data *nic_data = efx->nic_data;
@ -295,9 +470,15 @@ static void efx_ef10_remove(struct efx_nic *efx)
/* This needs to be after efx_ptp_remove_channel() with no filters */
efx_ef10_rx_free_indir_table(efx);
if (nic_data->wc_membase)
iounmap(nic_data->wc_membase);
rc = efx_ef10_free_vis(efx);
WARN_ON(rc != 0);
if (!nic_data->must_restore_piobufs)
efx_ef10_free_piobufs(efx);
efx_mcdi_fini(efx);
efx_nic_free_buffer(efx, &nic_data->mcdi_buf);
kfree(nic_data);
@ -330,12 +511,126 @@ static int efx_ef10_alloc_vis(struct efx_nic *efx,
return 0;
}
/* Note that the failure path of this function does not free
* resources, as this will be done by efx_ef10_remove().
*/
static int efx_ef10_dimension_resources(struct efx_nic *efx)
{
unsigned int n_vis =
max(efx->n_channels, efx->n_tx_channels * EFX_TXQ_TYPES);
struct efx_ef10_nic_data *nic_data = efx->nic_data;
unsigned int uc_mem_map_size, wc_mem_map_size;
unsigned int min_vis, pio_write_vi_base, max_vis;
void __iomem *membase;
int rc;
return efx_ef10_alloc_vis(efx, n_vis, n_vis);
min_vis = max(efx->n_channels, efx->n_tx_channels * EFX_TXQ_TYPES);
#ifdef EFX_USE_PIO
/* Try to allocate PIO buffers if wanted and if the full
* number of PIO buffers would be sufficient to allocate one
* copy-buffer per TX channel. Failure is non-fatal, as there
* are only a small number of PIO buffers shared between all
* functions of the controller.
*/
if (efx_piobuf_size != 0 &&
ER_DZ_TX_PIOBUF_SIZE / efx_piobuf_size * EF10_TX_PIOBUF_COUNT >=
efx->n_tx_channels) {
unsigned int n_piobufs =
DIV_ROUND_UP(efx->n_tx_channels,
ER_DZ_TX_PIOBUF_SIZE / efx_piobuf_size);
rc = efx_ef10_alloc_piobufs(efx, n_piobufs);
if (rc)
netif_err(efx, probe, efx->net_dev,
"failed to allocate PIO buffers (%d)\n", rc);
else
netif_dbg(efx, probe, efx->net_dev,
"allocated %u PIO buffers\n", n_piobufs);
}
#else
nic_data->n_piobufs = 0;
#endif
/* PIO buffers should be mapped with write-combining enabled,
* and we want to make single UC and WC mappings rather than
* several of each (in fact that's the only option if host
* page size is >4K). So we may allocate some extra VIs just
* for writing PIO buffers through.
*/
uc_mem_map_size = PAGE_ALIGN((min_vis - 1) * EFX_VI_PAGE_SIZE +
ER_DZ_TX_PIOBUF);
if (nic_data->n_piobufs) {
pio_write_vi_base = uc_mem_map_size / EFX_VI_PAGE_SIZE;
wc_mem_map_size = (PAGE_ALIGN((pio_write_vi_base +
nic_data->n_piobufs) *
EFX_VI_PAGE_SIZE) -
uc_mem_map_size);
max_vis = pio_write_vi_base + nic_data->n_piobufs;
} else {
pio_write_vi_base = 0;
wc_mem_map_size = 0;
max_vis = min_vis;
}
/* In case the last attached driver failed to free VIs, do it now */
rc = efx_ef10_free_vis(efx);
if (rc != 0)
return rc;
rc = efx_ef10_alloc_vis(efx, min_vis, max_vis);
if (rc != 0)
return rc;
/* If we didn't get enough VIs to map all the PIO buffers, free the
* PIO buffers
*/
if (nic_data->n_piobufs &&
nic_data->n_allocated_vis <
pio_write_vi_base + nic_data->n_piobufs) {
netif_dbg(efx, probe, efx->net_dev,
"%u VIs are not sufficient to map %u PIO buffers\n",
nic_data->n_allocated_vis, nic_data->n_piobufs);
efx_ef10_free_piobufs(efx);
}
/* Shrink the original UC mapping of the memory BAR */
membase = ioremap_nocache(efx->membase_phys, uc_mem_map_size);
if (!membase) {
netif_err(efx, probe, efx->net_dev,
"could not shrink memory BAR to %x\n",
uc_mem_map_size);
return -ENOMEM;
}
iounmap(efx->membase);
efx->membase = membase;
/* Set up the WC mapping if needed */
if (wc_mem_map_size) {
nic_data->wc_membase = ioremap_wc(efx->membase_phys +
uc_mem_map_size,
wc_mem_map_size);
if (!nic_data->wc_membase) {
netif_err(efx, probe, efx->net_dev,
"could not allocate WC mapping of size %x\n",
wc_mem_map_size);
return -ENOMEM;
}
nic_data->pio_write_vi_base = pio_write_vi_base;
nic_data->pio_write_base =
nic_data->wc_membase +
(pio_write_vi_base * EFX_VI_PAGE_SIZE + ER_DZ_TX_PIOBUF -
uc_mem_map_size);
rc = efx_ef10_link_piobufs(efx);
if (rc)
efx_ef10_free_piobufs(efx);
}
netif_dbg(efx, probe, efx->net_dev,
"memory BAR at %pa (virtual %p+%x UC, %p+%x WC)\n",
&efx->membase_phys, efx->membase, uc_mem_map_size,
nic_data->wc_membase, wc_mem_map_size);
return 0;
}
static int efx_ef10_init_nic(struct efx_nic *efx)
@ -359,6 +654,21 @@ static int efx_ef10_init_nic(struct efx_nic *efx)
nic_data->must_realloc_vis = false;
}
if (nic_data->must_restore_piobufs && nic_data->n_piobufs) {
rc = efx_ef10_alloc_piobufs(efx, nic_data->n_piobufs);
if (rc == 0) {
rc = efx_ef10_link_piobufs(efx);
if (rc)
efx_ef10_free_piobufs(efx);
}
/* Log an error on failure, but this is non-fatal */
if (rc)
netif_err(efx, drv, efx->net_dev,
"failed to restore PIO buffers (%d)\n", rc);
nic_data->must_restore_piobufs = false;
}
efx_ef10_rx_push_indir_table(efx);
return 0;
}
@ -716,6 +1026,7 @@ static int efx_ef10_mcdi_poll_reboot(struct efx_nic *efx)
/* All our allocations have been reset */
nic_data->must_realloc_vis = true;
nic_data->must_restore_filters = true;
nic_data->must_restore_piobufs = true;
nic_data->rx_rss_context = EFX_EF10_RSS_CONTEXT_INVALID;
/* The datapath firmware might have been changed */
@ -2137,7 +2448,7 @@ out_unlock:
return rc;
}
void efx_ef10_filter_update_rx_scatter(struct efx_nic *efx)
static void efx_ef10_filter_update_rx_scatter(struct efx_nic *efx)
{
/* no need to do anything here on EF10 */
}

1
drivers/net/ethernet/sfc/ef10_regs.h
View File

@ -315,6 +315,7 @@
#define ESF_DZ_TX_PIO_TYPE_WIDTH 1
#define ESF_DZ_TX_PIO_OPT_LBN 60
#define ESF_DZ_TX_PIO_OPT_WIDTH 3
#define ESE_DZ_TX_OPTION_DESC_PIO 1
#define ESF_DZ_TX_PIO_CONT_LBN 59
#define ESF_DZ_TX_PIO_CONT_WIDTH 1
#define ESF_DZ_TX_PIO_BYTE_CNT_LBN 32

1
drivers/net/ethernet/sfc/efx.h
View File

@ -30,6 +30,7 @@ efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb);
extern void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index);
extern int efx_setup_tc(struct net_device *net_dev, u8 num_tc);
extern unsigned int efx_tx_max_skb_descs(struct efx_nic *efx);
extern unsigned int efx_piobuf_size;
/* RX */
extern void efx_rx_config_page_split(struct efx_nic *efx);

5
drivers/net/ethernet/sfc/ethtool.c
View File

@ -70,6 +70,7 @@ static const struct efx_sw_stat_desc efx_sw_stat_desc[] = {
EFX_ETHTOOL_UINT_TXQ_STAT(tso_long_headers),
EFX_ETHTOOL_UINT_TXQ_STAT(tso_packets),
EFX_ETHTOOL_UINT_TXQ_STAT(pushes),
EFX_ETHTOOL_UINT_TXQ_STAT(pio_packets),
EFX_ETHTOOL_ATOMIC_NIC_ERROR_STAT(rx_reset),
EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_tobe_disc),
EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_ip_hdr_chksum_err),
@ -1035,8 +1036,8 @@ static int efx_ethtool_set_rxfh_indir(struct net_device *net_dev,
return 0;
}
int efx_ethtool_get_ts_info(struct net_device *net_dev,
struct ethtool_ts_info *ts_info)
static int efx_ethtool_get_ts_info(struct net_device *net_dev,
struct ethtool_ts_info *ts_info)
{
struct efx_nic *efx = netdev_priv(net_dev);

5
drivers/net/ethernet/sfc/io.h
View File

@ -66,6 +66,11 @@
#define EFX_USE_QWORD_IO 1
#endif
/* PIO is a win only if write-combining is possible */
#ifdef ARCH_HAS_IOREMAP_WC
#define EFX_USE_PIO 1
#endif
#ifdef EFX_USE_QWORD_IO
static inline void _efx_writeq(struct efx_nic *efx, __le64 value,
unsigned int reg)

7
drivers/net/ethernet/sfc/net_driver.h
View File

@ -182,6 +182,9 @@ struct efx_tx_buffer {
* @tsoh_page: Array of pages of TSO header buffers
* @txd: The hardware descriptor ring
* @ptr_mask: The size of the ring minus 1.
* @piobuf: PIO buffer region for this TX queue (shared with its partner).
* Size of the region is efx_piobuf_size.
* @piobuf_offset: Buffer offset to be specified in PIO descriptors
* @initialised: Has hardware queue been initialised?
* @read_count: Current read pointer.
* This is the number of buffers that have been removed from both rings.
@ -209,6 +212,7 @@ struct efx_tx_buffer {
* blocks
* @tso_packets: Number of packets via the TSO xmit path
* @pushes: Number of times the TX push feature has been used
* @pio_packets: Number of times the TX PIO feature has been used
* @empty_read_count: If the completion path has seen the queue as empty
* and the transmission path has not yet checked this, the value of
* @read_count bitwise-added to %EFX_EMPTY_COUNT_VALID; otherwise 0.
@ -223,6 +227,8 @@ struct efx_tx_queue {
struct efx_buffer *tsoh_page;
struct efx_special_buffer txd;
unsigned int ptr_mask;
void __iomem *piobuf;
unsigned int piobuf_offset;
bool initialised;
/* Members used mainly on the completion path */
@ -238,6 +244,7 @@ struct efx_tx_queue {
unsigned int tso_long_headers;
unsigned int tso_packets;
unsigned int pushes;
unsigned int pio_packets;
/* Members shared between paths and sometimes updated */
unsigned int empty_read_count ____cacheline_aligned_in_smp;

73
drivers/net/ethernet/sfc/nic.c
View File

@ -19,6 +19,7 @@
#include "bitfield.h"
#include "efx.h"
#include "nic.h"
#include "ef10_regs.h"
#include "farch_regs.h"
#include "io.h"
#include "workarounds.h"
@ -166,26 +167,30 @@ void efx_nic_fini_interrupt(struct efx_nic *efx)
/* Register dump */
#define REGISTER_REVISION_A 1
#define REGISTER_REVISION_B 2
#define REGISTER_REVISION_C 3
#define REGISTER_REVISION_Z 3 /* latest revision */
#define REGISTER_REVISION_FA 1
#define REGISTER_REVISION_FB 2
#define REGISTER_REVISION_FC 3
#define REGISTER_REVISION_FZ 3 /* last Falcon arch revision */
#define REGISTER_REVISION_ED 4
#define REGISTER_REVISION_EZ 4 /* latest EF10 revision */
struct efx_nic_reg {
u32 offset:24;
u32 min_revision:2, max_revision:2;
u32 min_revision:3, max_revision:3;
};
#define REGISTER(name, min_rev, max_rev) { \
FR_ ## min_rev ## max_rev ## _ ## name, \
REGISTER_REVISION_ ## min_rev, REGISTER_REVISION_ ## max_rev \
#define REGISTER(name, arch, min_rev, max_rev) { \
arch ## R_ ## min_rev ## max_rev ## _ ## name, \
REGISTER_REVISION_ ## arch ## min_rev, \
REGISTER_REVISION_ ## arch ## max_rev \
}
#define REGISTER_AA(name) REGISTER(name, A, A)
#define REGISTER_AB(name) REGISTER(name, A, B)
#define REGISTER_AZ(name) REGISTER(name, A, Z)
#define REGISTER_BB(name) REGISTER(name, B, B)
#define REGISTER_BZ(name) REGISTER(name, B, Z)
#define REGISTER_CZ(name) REGISTER(name, C, Z)
#define REGISTER_AA(name) REGISTER(name, F, A, A)
#define REGISTER_AB(name) REGISTER(name, F, A, B)
#define REGISTER_AZ(name) REGISTER(name, F, A, Z)
#define REGISTER_BB(name) REGISTER(name, F, B, B)
#define REGISTER_BZ(name) REGISTER(name, F, B, Z)
#define REGISTER_CZ(name) REGISTER(name, F, C, Z)
#define REGISTER_DZ(name) REGISTER(name, E, D, Z)
static const struct efx_nic_reg efx_nic_regs[] = {
REGISTER_AZ(ADR_REGION),
@ -292,37 +297,42 @@ static const struct efx_nic_reg efx_nic_regs[] = {
REGISTER_AB(XX_TXDRV_CTL),
/* XX_PRBS_CTL, XX_PRBS_CHK and XX_PRBS_ERR are not used */
/* XX_CORE_STAT is partly RC */
REGISTER_DZ(BIU_HW_REV_ID),
REGISTER_DZ(MC_DB_LWRD),
REGISTER_DZ(MC_DB_HWRD),
};
struct efx_nic_reg_table {
u32 offset:24;
u32 min_revision:2, max_revision:2;
u32 min_revision:3, max_revision:3;
u32 step:6, rows:21;
};
#define REGISTER_TABLE_DIMENSIONS(_, offset, min_rev, max_rev, step, rows) { \
#define REGISTER_TABLE_DIMENSIONS(_, offset, arch, min_rev, max_rev, step, rows) { \
offset, \
REGISTER_REVISION_ ## min_rev, REGISTER_REVISION_ ## max_rev, \
REGISTER_REVISION_ ## arch ## min_rev, \
REGISTER_REVISION_ ## arch ## max_rev, \
step, rows \
}
#define REGISTER_TABLE(name, min_rev, max_rev) \
#define REGISTER_TABLE(name, arch, min_rev, max_rev) \
REGISTER_TABLE_DIMENSIONS( \
name, FR_ ## min_rev ## max_rev ## _ ## name, \
min_rev, max_rev, \
FR_ ## min_rev ## max_rev ## _ ## name ## _STEP, \
FR_ ## min_rev ## max_rev ## _ ## name ## _ROWS)
#define REGISTER_TABLE_AA(name) REGISTER_TABLE(name, A, A)
#define REGISTER_TABLE_AZ(name) REGISTER_TABLE(name, A, Z)
#define REGISTER_TABLE_BB(name) REGISTER_TABLE(name, B, B)
#define REGISTER_TABLE_BZ(name) REGISTER_TABLE(name, B, Z)
name, arch ## R_ ## min_rev ## max_rev ## _ ## name, \
arch, min_rev, max_rev, \
arch ## R_ ## min_rev ## max_rev ## _ ## name ## _STEP, \
arch ## R_ ## min_rev ## max_rev ## _ ## name ## _ROWS)
#define REGISTER_TABLE_AA(name) REGISTER_TABLE(name, F, A, A)
#define REGISTER_TABLE_AZ(name) REGISTER_TABLE(name, F, A, Z)
#define REGISTER_TABLE_BB(name) REGISTER_TABLE(name, F, B, B)
#define REGISTER_TABLE_BZ(name) REGISTER_TABLE(name, F, B, Z)
#define REGISTER_TABLE_BB_CZ(name) \
REGISTER_TABLE_DIMENSIONS(name, FR_BZ_ ## name, B, B, \
REGISTER_TABLE_DIMENSIONS(name, FR_BZ_ ## name, F, B, B, \
FR_BZ_ ## name ## _STEP, \
FR_BB_ ## name ## _ROWS), \
REGISTER_TABLE_DIMENSIONS(name, FR_BZ_ ## name, C, Z, \
REGISTER_TABLE_DIMENSIONS(name, FR_BZ_ ## name, F, C, Z, \
FR_BZ_ ## name ## _STEP, \
FR_CZ_ ## name ## _ROWS)
#define REGISTER_TABLE_CZ(name) REGISTER_TABLE(name, C, Z)
#define REGISTER_TABLE_CZ(name) REGISTER_TABLE(name, F, C, Z)
#define REGISTER_TABLE_DZ(name) REGISTER_TABLE(name, E, D, Z)
static const struct efx_nic_reg_table efx_nic_reg_tables[] = {
/* DRIVER is not used */
@ -340,9 +350,9 @@ static const struct efx_nic_reg_table efx_nic_reg_tables[] = {
* 1K entries allows for some expansion of queue count and
* size before we need to change the version. */
REGISTER_TABLE_DIMENSIONS(BUF_FULL_TBL_KER, FR_AA_BUF_FULL_TBL_KER,
A, A, 8, 1024),
F, A, A, 8, 1024),
REGISTER_TABLE_DIMENSIONS(BUF_FULL_TBL, FR_BZ_BUF_FULL_TBL,
B, Z, 8, 1024),
F, B, Z, 8, 1024),
REGISTER_TABLE_CZ(RX_MAC_FILTER_TBL0),
REGISTER_TABLE_BB_CZ(TIMER_TBL),
REGISTER_TABLE_BB_CZ(TX_PACE_TBL),
@ -353,6 +363,7 @@ static const struct efx_nic_reg_table efx_nic_reg_tables[] = {
/* MSIX_PBA_TABLE is not mapped */
/* SRM_DBG is not mapped (and is redundant with BUF_FLL_TBL) */
REGISTER_TABLE_BZ(RX_FILTER_TBL0),
REGISTER_TABLE_DZ(BIU_MC_SFT_STATUS),
};
size_t efx_nic_get_regs_len(struct efx_nic *efx)

46
drivers/net/ethernet/sfc/nic.h
View File

@ -71,6 +71,26 @@ efx_tx_desc(struct efx_tx_queue *tx_queue, unsigned int index)
return ((efx_qword_t *) (tx_queue->txd.buf.addr)) + index;
}
/* Report whether the NIC considers this TX queue empty, given the
* write_count used for the last doorbell push. May return false
* negative.
*/
static inline bool __efx_nic_tx_is_empty(struct efx_tx_queue *tx_queue,
unsigned int write_count)
{
unsigned int empty_read_count = ACCESS_ONCE(tx_queue->empty_read_count);
if (empty_read_count == 0)
return false;
return ((empty_read_count ^ write_count) & ~EFX_EMPTY_COUNT_VALID) == 0;
}
static inline bool efx_nic_tx_is_empty(struct efx_tx_queue *tx_queue)
{
return __efx_nic_tx_is_empty(tx_queue, tx_queue->write_count);
}
/* Decide whether to push a TX descriptor to the NIC vs merely writing
* the doorbell. This can reduce latency when we are adding a single
* descriptor to an empty queue, but is otherwise pointless. Further,
@ -80,14 +100,10 @@ efx_tx_desc(struct efx_tx_queue *tx_queue, unsigned int index)
static inline bool efx_nic_may_push_tx_desc(struct efx_tx_queue *tx_queue,
unsigned int write_count)
{
unsigned empty_read_count = ACCESS_ONCE(tx_queue->empty_read_count);
if (empty_read_count == 0)
return false;
bool was_empty = __efx_nic_tx_is_empty(tx_queue, write_count);
tx_queue->empty_read_count = 0;
return ((empty_read_count ^ write_count) & ~EFX_EMPTY_COUNT_VALID) == 0
&& tx_queue->write_count - write_count == 1;
return was_empty && tx_queue->write_count - write_count == 1;
}
/* Returns a pointer to the specified descriptor in the RX descriptor queue */
@ -389,6 +405,12 @@ enum {
EF10_STAT_COUNT
};
/* Maximum number of TX PIO buffers we may allocate to a function.
* This matches the total number of buffers on each SFC9100-family
* controller.
*/
#define EF10_TX_PIOBUF_COUNT 16
/**
* struct efx_ef10_nic_data - EF10 architecture NIC state
* @mcdi_buf: DMA buffer for MCDI
@ -397,6 +419,13 @@ enum {
* @n_allocated_vis: Number of VIs allocated to this function
* @must_realloc_vis: Flag: VIs have yet to be reallocated after MC reboot
* @must_restore_filters: Flag: filters have yet to be restored after MC reboot
* @n_piobufs: Number of PIO buffers allocated to this function
* @wc_membase: Base address of write-combining mapping of the memory BAR
* @pio_write_base: Base address for writing PIO buffers
* @pio_write_vi_base: Relative VI number for @pio_write_base
* @piobuf_handle: Handle of each PIO buffer allocated
* @must_restore_piobufs: Flag: PIO buffers have yet to be restored after MC
* reboot
* @rx_rss_context: Firmware handle for our RSS context
* @stats: Hardware statistics
* @workaround_35388: Flag: firmware supports workaround for bug 35388
@ -412,6 +441,11 @@ struct efx_ef10_nic_data {
unsigned int n_allocated_vis;
bool must_realloc_vis;
bool must_restore_filters;
unsigned int n_piobufs;
void __iomem *wc_membase, *pio_write_base;
unsigned int pio_write_vi_base;
unsigned int piobuf_handle[EF10_TX_PIOBUF_COUNT];
bool must_restore_piobufs;
u32 rx_rss_context;
u64 stats[EF10_STAT_COUNT];
bool workaround_35388;

90
drivers/net/ethernet/sfc/rx.c
View File

@ -12,6 +12,7 @@
#include <linux/in.h>
#include <linux/slab.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/prefetch.h>
@ -818,44 +819,70 @@ int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
struct efx_nic *efx = netdev_priv(net_dev);
struct efx_channel *channel;
struct efx_filter_spec spec;
const struct iphdr *ip;
const __be16 *ports;
__be16 ether_type;
int nhoff;
int rc;
nhoff = skb_network_offset(skb);
/* The core RPS/RFS code has already parsed and validated
* VLAN, IP and transport headers. We assume they are in the
* header area.
*/
if (skb->protocol == htons(ETH_P_8021Q)) {
EFX_BUG_ON_PARANOID(skb_headlen(skb) <
nhoff + sizeof(struct vlan_hdr));
if (((const struct vlan_hdr *)skb->data + nhoff)->
h_vlan_encapsulated_proto != htons(ETH_P_IP))
return -EPROTONOSUPPORT;
const struct vlan_hdr *vh =
(const struct vlan_hdr *)skb->data;
/* This is IP over 802.1q VLAN. We can't filter on the
* IP 5-tuple and the vlan together, so just strip the
* vlan header and filter on the IP part.
/* We can't filter on the IP 5-tuple and the vlan
* together, so just strip the vlan header and filter
* on the IP part.
*/
nhoff += sizeof(struct vlan_hdr);
} else if (skb->protocol != htons(ETH_P_IP)) {
return -EPROTONOSUPPORT;
EFX_BUG_ON_PARANOID(skb_headlen(skb) < sizeof(*vh));
ether_type = vh->h_vlan_encapsulated_proto;
nhoff = sizeof(struct vlan_hdr);
} else {
ether_type = skb->protocol;
nhoff = 0;
}
/* RFS must validate the IP header length before calling us */
EFX_BUG_ON_PARANOID(skb_headlen(skb) < nhoff + sizeof(*ip));
ip = (const struct iphdr *)(skb->data + nhoff);
if (ip_is_fragment(ip))
if (ether_type != htons(ETH_P_IP) && ether_type != htons(ETH_P_IPV6))
return -EPROTONOSUPPORT;
EFX_BUG_ON_PARANOID(skb_headlen(skb) < nhoff + 4 * ip->ihl + 4);
ports = (const __be16 *)(skb->data + nhoff + 4 * ip->ihl);
efx_filter_init_rx(&spec, EFX_FILTER_PRI_HINT,
efx->rx_scatter ? EFX_FILTER_FLAG_RX_SCATTER : 0,
rxq_index);
rc = efx_filter_set_ipv4_full(&spec, ip->protocol,
ip->daddr, ports[1], ip->saddr, ports[0]);
if (rc)
return rc;
spec.match_flags =
EFX_FILTER_MATCH_ETHER_TYPE | EFX_FILTER_MATCH_IP_PROTO |
EFX_FILTER_MATCH_LOC_HOST | EFX_FILTER_MATCH_LOC_PORT |
EFX_FILTER_MATCH_REM_HOST | EFX_FILTER_MATCH_REM_PORT;
spec.ether_type = ether_type;
if (ether_type == htons(ETH_P_IP)) {
const struct iphdr *ip =
(const struct iphdr *)(skb->data + nhoff);
EFX_BUG_ON_PARANOID(skb_headlen(skb) < nhoff + sizeof(*ip));
if (ip_is_fragment(ip))
return -EPROTONOSUPPORT;
spec.ip_proto = ip->protocol;
spec.rem_host[0] = ip->saddr;
spec.loc_host[0] = ip->daddr;
EFX_BUG_ON_PARANOID(skb_headlen(skb) < nhoff + 4 * ip->ihl + 4);
ports = (const __be16 *)(skb->data + nhoff + 4 * ip->ihl);
} else {
const struct ipv6hdr *ip6 =
(const struct ipv6hdr *)(skb->data + nhoff);
EFX_BUG_ON_PARANOID(skb_headlen(skb) <
nhoff + sizeof(*ip6) + 4);
spec.ip_proto = ip6->nexthdr;
memcpy(spec.rem_host, &ip6->saddr, sizeof(ip6->saddr));
memcpy(spec.loc_host, &ip6->daddr, sizeof(ip6->daddr));
ports = (const __be16 *)(ip6 + 1);
}
spec.rem_port = ports[0];
spec.loc_port = ports[1];
rc = efx->type->filter_rfs_insert(efx, &spec);
if (rc < 0)
@ -866,11 +893,18 @@ int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
channel = efx_get_channel(efx, skb_get_rx_queue(skb));
++channel->rfs_filters_added;
netif_info(efx, rx_status, efx->net_dev,
"steering %s %pI4:%u:%pI4:%u to queue %u [flow %u filter %d]\n",
(ip->protocol == IPPROTO_TCP) ? "TCP" : "UDP",
&ip->saddr, ntohs(ports[0]), &ip->daddr, ntohs(ports[1]),
rxq_index, flow_id, rc);
if (ether_type == htons(ETH_P_IP))
netif_info(efx, rx_status, efx->net_dev,
"steering %s %pI4:%u:%pI4:%u to queue %u [flow %u filter %d]\n",
(spec.ip_proto == IPPROTO_TCP) ? "TCP" : "UDP",
spec.rem_host, ntohs(ports[0]), spec.loc_host,
ntohs(ports[1]), rxq_index, flow_id, rc);
else
netif_info(efx, rx_status, efx->net_dev,
"steering %s [%pI6]:%u:[%pI6]:%u to queue %u [flow %u filter %d]\n",
(spec.ip_proto == IPPROTO_TCP) ? "TCP" : "UDP",
spec.rem_host, ntohs(ports[0]), spec.loc_host,
ntohs(ports[1]), rxq_index, flow_id, rc);
return rc;
}

419
drivers/net/ethernet/sfc/tx.c
View File

@ -17,10 +17,46 @@
#include <net/ipv6.h>
#include <linux/if_ether.h>
#include <linux/highmem.h>
#include <linux/cache.h>
#include "net_driver.h"
#include "efx.h"
#include "io.h"
#include "nic.h"
#include "workarounds.h"
#include "ef10_regs.h"
#ifdef EFX_USE_PIO
#define EFX_PIOBUF_SIZE_MAX ER_DZ_TX_PIOBUF_SIZE
#define EFX_PIOBUF_SIZE_DEF ALIGN(256, L1_CACHE_BYTES)
unsigned int efx_piobuf_size __read_mostly = EFX_PIOBUF_SIZE_DEF;
#endif /* EFX_USE_PIO */
static inline unsigned int
efx_tx_queue_get_insert_index(const struct efx_tx_queue *tx_queue)
{
return tx_queue->insert_count & tx_queue->ptr_mask;
}
static inline struct efx_tx_buffer *
__efx_tx_queue_get_insert_buffer(const struct efx_tx_queue *tx_queue)
{
return &tx_queue->buffer[efx_tx_queue_get_insert_index(tx_queue)];
}
static inline struct efx_tx_buffer *
efx_tx_queue_get_insert_buffer(const struct efx_tx_queue *tx_queue)
{
struct efx_tx_buffer *buffer =
__efx_tx_queue_get_insert_buffer(tx_queue);
EFX_BUG_ON_PARANOID(buffer->len);
EFX_BUG_ON_PARANOID(buffer->flags);
EFX_BUG_ON_PARANOID(buffer->unmap_len);
return buffer;
}
static void efx_dequeue_buffer(struct efx_tx_queue *tx_queue,
struct efx_tx_buffer *buffer,
@ -83,8 +119,10 @@ unsigned int efx_tx_max_skb_descs(struct efx_nic *efx)
*/
unsigned int max_descs = EFX_TSO_MAX_SEGS * 2 + MAX_SKB_FRAGS;
/* Possibly one more per segment for the alignment workaround */
if (EFX_WORKAROUND_5391(efx))
/* Possibly one more per segment for the alignment workaround,
* or for option descriptors
*/
if (EFX_WORKAROUND_5391(efx) || efx_nic_rev(efx) >= EFX_REV_HUNT_A0)
max_descs += EFX_TSO_MAX_SEGS;
/* Possibly more for PCIe page boundaries within input fragments */
@ -145,6 +183,145 @@ static void efx_tx_maybe_stop_queue(struct efx_tx_queue *txq1)
}
}
#ifdef EFX_USE_PIO
struct efx_short_copy_buffer {
int used;
u8 buf[L1_CACHE_BYTES];
};
/* Copy to PIO, respecting that writes to PIO buffers must be dword aligned.
* Advances piobuf pointer. Leaves additional data in the copy buffer.
*/
static void efx_memcpy_toio_aligned(struct efx_nic *efx, u8 __iomem **piobuf,
u8 *data, int len,
struct efx_short_copy_buffer *copy_buf)
{
int block_len = len & ~(sizeof(copy_buf->buf) - 1);
memcpy_toio(*piobuf, data, block_len);
*piobuf += block_len;
len -= block_len;
if (len) {
data += block_len;
BUG_ON(copy_buf->used);
BUG_ON(len > sizeof(copy_buf->buf));
memcpy(copy_buf->buf, data, len);
copy_buf->used = len;
}
}
/* Copy to PIO, respecting dword alignment, popping data from copy buffer first.
* Advances piobuf pointer. Leaves additional data in the copy buffer.
*/
static void efx_memcpy_toio_aligned_cb(struct efx_nic *efx, u8 __iomem **piobuf,
u8 *data, int len,
struct efx_short_copy_buffer *copy_buf)
{
if (copy_buf->used) {
/* if the copy buffer is partially full, fill it up and write */
int copy_to_buf =
min_t(int, sizeof(copy_buf->buf) - copy_buf->used, len);
memcpy(copy_buf->buf + copy_buf->used, data, copy_to_buf);
copy_buf->used += copy_to_buf;
/* if we didn't fill it up then we're done for now */
if (copy_buf->used < sizeof(copy_buf->buf))
return;
memcpy_toio(*piobuf, copy_buf->buf, sizeof(copy_buf->buf));
*piobuf += sizeof(copy_buf->buf);
data += copy_to_buf;
len -= copy_to_buf;
copy_buf->used = 0;
}
efx_memcpy_toio_aligned(efx, piobuf, data, len, copy_buf);
}
static void efx_flush_copy_buffer(struct efx_nic *efx, u8 __iomem *piobuf,
struct efx_short_copy_buffer *copy_buf)
{
/* if there's anything in it, write the whole buffer, including junk */
if (copy_buf->used)
memcpy_toio(piobuf, copy_buf->buf, sizeof(copy_buf->buf));
}
/* Traverse skb structure and copy fragments in to PIO buffer.
* Advances piobuf pointer.
*/
static void efx_skb_copy_bits_to_pio(struct efx_nic *efx, struct sk_buff *skb,
u8 __iomem **piobuf,
struct efx_short_copy_buffer *copy_buf)
{
int i;
efx_memcpy_toio_aligned(efx, piobuf, skb->data, skb_headlen(skb),
copy_buf);
for (i = 0; i < skb_shinfo(skb)->nr_frags; ++i) {
skb_frag_t *f = &skb_shinfo(skb)->frags[i];
u8 *vaddr;
vaddr = kmap_atomic(skb_frag_page(f));
efx_memcpy_toio_aligned_cb(efx, piobuf, vaddr + f->page_offset,
skb_frag_size(f), copy_buf);
kunmap_atomic(vaddr);
}
EFX_BUG_ON_PARANOID(skb_shinfo(skb)->frag_list);
}
static struct efx_tx_buffer *
efx_enqueue_skb_pio(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
{
struct efx_tx_buffer *buffer =
efx_tx_queue_get_insert_buffer(tx_queue);
u8 __iomem *piobuf = tx_queue->piobuf;
/* Copy to PIO buffer. Ensure the writes are padded to the end
* of a cache line, as this is required for write-combining to be
* effective on at least x86.
*/
if (skb_shinfo(skb)->nr_frags) {
/* The size of the copy buffer will ensure all writes
* are the size of a cache line.
*/
struct efx_short_copy_buffer copy_buf;
copy_buf.used = 0;
efx_skb_copy_bits_to_pio(tx_queue->efx, skb,
&piobuf, &copy_buf);
efx_flush_copy_buffer(tx_queue->efx, piobuf, &copy_buf);
} else {
/* Pad the write to the size of a cache line.
* We can do this because we know the skb_shared_info sruct is
* after the source, and the destination buffer is big enough.
*/
BUILD_BUG_ON(L1_CACHE_BYTES >
SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
memcpy_toio(tx_queue->piobuf, skb->data,
ALIGN(skb->len, L1_CACHE_BYTES));
}
EFX_POPULATE_QWORD_5(buffer->option,
ESF_DZ_TX_DESC_IS_OPT, 1,
ESF_DZ_TX_OPTION_TYPE, ESE_DZ_TX_OPTION_DESC_PIO,
ESF_DZ_TX_PIO_CONT, 0,
ESF_DZ_TX_PIO_BYTE_CNT, skb->len,
ESF_DZ_TX_PIO_BUF_ADDR,
tx_queue->piobuf_offset);
++tx_queue->pio_packets;
++tx_queue->insert_count;
return buffer;
}
#endif /* EFX_USE_PIO */
/*
* Add a socket buffer to a TX queue
*
@ -167,7 +344,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
struct device *dma_dev = &efx->pci_dev->dev;
struct efx_tx_buffer *buffer;
skb_frag_t *fragment;
unsigned int len, unmap_len = 0, insert_ptr;
unsigned int len, unmap_len = 0;
dma_addr_t dma_addr, unmap_addr = 0;
unsigned int dma_len;
unsigned short dma_flags;
@ -189,6 +366,17 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
return NETDEV_TX_OK;
}
/* Consider using PIO for short packets */
#ifdef EFX_USE_PIO
if (skb->len <= efx_piobuf_size && tx_queue->piobuf &&
efx_nic_tx_is_empty(tx_queue) &&
efx_nic_tx_is_empty(efx_tx_queue_partner(tx_queue))) {
buffer = efx_enqueue_skb_pio(tx_queue, skb);
dma_flags = EFX_TX_BUF_OPTION;
goto finish_packet;
}
#endif
/* Map for DMA. Use dma_map_single rather than dma_map_page
* since this is more efficient on machines with sparse
* memory.
@ -208,11 +396,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
/* Add to TX queue, splitting across DMA boundaries */
do {
insert_ptr = tx_queue->insert_count & tx_queue->ptr_mask;
buffer = &tx_queue->buffer[insert_ptr];
EFX_BUG_ON_PARANOID(buffer->flags);
EFX_BUG_ON_PARANOID(buffer->len);
EFX_BUG_ON_PARANOID(buffer->unmap_len);
buffer = efx_tx_queue_get_insert_buffer(tx_queue);
dma_len = efx_max_tx_len(efx, dma_addr);
if (likely(dma_len >= len))
@ -245,6 +429,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
}
/* Transfer ownership of the skb to the final buffer */
finish_packet:
buffer->skb = skb;
buffer->flags = EFX_TX_BUF_SKB | dma_flags;
@ -270,8 +455,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
while (tx_queue->insert_count != tx_queue->write_count) {
unsigned int pkts_compl = 0, bytes_compl = 0;
--tx_queue->insert_count;
insert_ptr = tx_queue->insert_count & tx_queue->ptr_mask;
buffer = &tx_queue->buffer[insert_ptr];
buffer = __efx_tx_queue_get_insert_buffer(tx_queue);
efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl);
}
@ -628,6 +812,9 @@ void efx_remove_tx_queue(struct efx_tx_queue *tx_queue)
* @tcp_off: Offset of TCP header
* @header_len: Number of bytes of header
* @ip_base_len: IPv4 tot_len or IPv6 payload_len, before TCP payload
* @header_dma_addr: Header DMA address, when using option descriptors
* @header_unmap_len: Header DMA mapped length, or 0 if not using option
* descriptors
*
* The state used during segmentation. It is put into this data structure
* just to make it easy to pass into inline functions.
@ -636,7 +823,7 @@ struct tso_state {
/* Output position */
unsigned out_len;
unsigned seqnum;
unsigned ipv4_id;
u16 ipv4_id;
unsigned packet_space;
/* Input position */
@ -651,6 +838,8 @@ struct tso_state {
unsigned int tcp_off;
unsigned header_len;
unsigned int ip_base_len;
dma_addr_t header_dma_addr;
unsigned int header_unmap_len;
};
@ -737,23 +926,18 @@ static void efx_tx_queue_insert(struct efx_tx_queue *tx_queue,
{
struct efx_tx_buffer *buffer;
struct efx_nic *efx = tx_queue->efx;
unsigned dma_len, insert_ptr;
unsigned dma_len;
EFX_BUG_ON_PARANOID(len <= 0);
while (1) {
insert_ptr = tx_queue->insert_count & tx_queue->ptr_mask;
buffer = &tx_queue->buffer[insert_ptr];
buffer = efx_tx_queue_get_insert_buffer(tx_queue);
++tx_queue->insert_count;
EFX_BUG_ON_PARANOID(tx_queue->insert_count -
tx_queue->read_count >=
efx->txq_entries);
EFX_BUG_ON_PARANOID(buffer->len);
EFX_BUG_ON_PARANOID(buffer->unmap_len);
EFX_BUG_ON_PARANOID(buffer->flags);
buffer->dma_addr = dma_addr;
dma_len = efx_max_tx_len(efx, dma_addr);
@ -814,19 +998,27 @@ static void efx_enqueue_unwind(struct efx_tx_queue *tx_queue)
/* Work backwards until we hit the original insert pointer value */
while (tx_queue->insert_count != tx_queue->write_count) {
--tx_queue->insert_count;
buffer = &tx_queue->buffer[tx_queue->insert_count &
tx_queue->ptr_mask];
buffer = __efx_tx_queue_get_insert_buffer(tx_queue);
efx_dequeue_buffer(tx_queue, buffer, NULL, NULL);
}
}
/* Parse the SKB header and initialise state. */
static void tso_start(struct tso_state *st, const struct sk_buff *skb)
static int tso_start(struct tso_state *st, struct efx_nic *efx,
const struct sk_buff *skb)
{
bool use_options = efx_nic_rev(efx) >= EFX_REV_HUNT_A0;
struct device *dma_dev = &efx->pci_dev->dev;
unsigned int header_len, in_len;
dma_addr_t dma_addr;
st->ip_off = skb_network_header(skb) - skb->data;
st->tcp_off = skb_transport_header(skb) - skb->data;
st->header_len = st->tcp_off + (tcp_hdr(skb)->doff << 2u);
header_len = st->tcp_off + (tcp_hdr(skb)->doff << 2u);
in_len = skb_headlen(skb) - header_len;
st->header_len = header_len;
st->in_len = in_len;
if (st->protocol == htons(ETH_P_IP)) {
st->ip_base_len = st->header_len - st->ip_off;
st->ipv4_id = ntohs(ip_hdr(skb)->id);
@ -840,9 +1032,34 @@ static void tso_start(struct tso_state *st, const struct sk_buff *skb)
EFX_BUG_ON_PARANOID(tcp_hdr(skb)->syn);
EFX_BUG_ON_PARANOID(tcp_hdr(skb)->rst);
st->out_len = skb->len - st->header_len;
st->unmap_len = 0;
st->dma_flags = 0;
st->out_len = skb->len - header_len;
if (!use_options) {
st->header_unmap_len = 0;
if (likely(in_len == 0)) {
st->dma_flags = 0;
st->unmap_len = 0;
return 0;
}
dma_addr = dma_map_single(dma_dev, skb->data + header_len,
in_len, DMA_TO_DEVICE);
st->dma_flags = EFX_TX_BUF_MAP_SINGLE;
st->dma_addr = dma_addr;
st->unmap_addr = dma_addr;
st->unmap_len = in_len;
} else {
dma_addr = dma_map_single(dma_dev, skb->data,
skb_headlen(skb), DMA_TO_DEVICE);
st->header_dma_addr = dma_addr;
st->header_unmap_len = skb_headlen(skb);
st->dma_flags = 0;
st->dma_addr = dma_addr + header_len;
st->unmap_len = 0;
}
return unlikely(dma_mapping_error(dma_dev, dma_addr)) ? -ENOMEM : 0;
}
static int tso_get_fragment(struct tso_state *st, struct efx_nic *efx,
@ -860,24 +1077,6 @@ static int tso_get_fragment(struct tso_state *st, struct efx_nic *efx,
return -ENOMEM;
}
static int tso_get_head_fragment(struct tso_state *st, struct efx_nic *efx,
const struct sk_buff *skb)
{
int hl = st->header_len;
int len = skb_headlen(skb) - hl;
st->unmap_addr = dma_map_single(&efx->pci_dev->dev, skb->data + hl,
len, DMA_TO_DEVICE);
if (likely(!dma_mapping_error(&efx->pci_dev->dev, st->unmap_addr))) {
st->dma_flags = EFX_TX_BUF_MAP_SINGLE;
st->unmap_len = len;
st->in_len = len;
st->dma_addr = st->unmap_addr;
return 0;
}
return -ENOMEM;
}
/**
* tso_fill_packet_with_fragment - form descriptors for the current fragment
@ -944,55 +1143,97 @@ static int tso_start_new_packet(struct efx_tx_queue *tx_queue,
struct tso_state *st)
{
struct efx_tx_buffer *buffer =
&tx_queue->buffer[tx_queue->insert_count & tx_queue->ptr_mask];
struct tcphdr *tsoh_th;
unsigned ip_length;
u8 *header;
int rc;
efx_tx_queue_get_insert_buffer(tx_queue);
bool is_last = st->out_len <= skb_shinfo(skb)->gso_size;
u8 tcp_flags_clear;
/* Allocate and insert a DMA-mapped header buffer. */
header = efx_tsoh_get_buffer(tx_queue, buffer, st->header_len);
if (!header)
return -ENOMEM;
tsoh_th = (struct tcphdr *)(header + st->tcp_off);
/* Copy and update the headers. */
memcpy(header, skb->data, st->header_len);
tsoh_th->seq = htonl(st->seqnum);
st->seqnum += skb_shinfo(skb)->gso_size;
if (st->out_len > skb_shinfo(skb)->gso_size) {
/* This packet will not finish the TSO burst. */
if (!is_last) {
st->packet_space = skb_shinfo(skb)->gso_size;
tsoh_th->fin = 0;
tsoh_th->psh = 0;
tcp_flags_clear = 0x09; /* mask out FIN and PSH */
} else {
/* This packet will be the last in the TSO burst. */
st->packet_space = st->out_len;
tsoh_th->fin = tcp_hdr(skb)->fin;
tsoh_th->psh = tcp_hdr(skb)->psh;
tcp_flags_clear = 0x00;
}
ip_length = st->ip_base_len + st->packet_space;
if (st->protocol == htons(ETH_P_IP)) {
struct iphdr *tsoh_iph = (struct iphdr *)(header + st->ip_off);
if (!st->header_unmap_len) {
/* Allocate and insert a DMA-mapped header buffer. */
struct tcphdr *tsoh_th;
unsigned ip_length;
u8 *header;
int rc;
tsoh_iph->tot_len = htons(ip_length);
header = efx_tsoh_get_buffer(tx_queue, buffer, st->header_len);
if (!header)
return -ENOMEM;
/* Linux leaves suitable gaps in the IP ID space for us to fill. */
tsoh_iph->id = htons(st->ipv4_id);
st->ipv4_id++;
tsoh_th = (struct tcphdr *)(header + st->tcp_off);
/* Copy and update the headers. */
memcpy(header, skb->data, st->header_len);
tsoh_th->seq = htonl(st->seqnum);
((u8 *)tsoh_th)[13] &= ~tcp_flags_clear;
ip_length = st->ip_base_len + st->packet_space;
if (st->protocol == htons(ETH_P_IP)) {
struct iphdr *tsoh_iph =
(struct iphdr *)(header + st->ip_off);
tsoh_iph->tot_len = htons(ip_length);
tsoh_iph->id = htons(st->ipv4_id);
} else {
struct ipv6hdr *tsoh_iph =
(struct ipv6hdr *)(header + st->ip_off);
tsoh_iph->payload_len = htons(ip_length);
}
rc = efx_tso_put_header(tx_queue, buffer, header);
if (unlikely(rc))
return rc;
} else {
struct ipv6hdr *tsoh_iph =
(struct ipv6hdr *)(header + st->ip_off);
/* Send the original headers with a TSO option descriptor
* in front
*/
u8 tcp_flags = ((u8 *)tcp_hdr(skb))[13] & ~tcp_flags_clear;
tsoh_iph->payload_len = htons(ip_length);
buffer->flags = EFX_TX_BUF_OPTION;
buffer->len = 0;
buffer->unmap_len = 0;
EFX_POPULATE_QWORD_5(buffer->option,
ESF_DZ_TX_DESC_IS_OPT, 1,
ESF_DZ_TX_OPTION_TYPE,
ESE_DZ_TX_OPTION_DESC_TSO,
ESF_DZ_TX_TSO_TCP_FLAGS, tcp_flags,
ESF_DZ_TX_TSO_IP_ID, st->ipv4_id,
ESF_DZ_TX_TSO_TCP_SEQNO, st->seqnum);
++tx_queue->insert_count;
/* We mapped the headers in tso_start(). Unmap them
* when the last segment is completed.
*/
buffer = efx_tx_queue_get_insert_buffer(tx_queue);
buffer->dma_addr = st->header_dma_addr;
buffer->len = st->header_len;
if (is_last) {
buffer->flags = EFX_TX_BUF_CONT | EFX_TX_BUF_MAP_SINGLE;
buffer->unmap_len = st->header_unmap_len;
/* Ensure we only unmap them once in case of a
* later DMA mapping error and rollback
*/
st->header_unmap_len = 0;
} else {
buffer->flags = EFX_TX_BUF_CONT;
buffer->unmap_len = 0;
}
++tx_queue->insert_count;
}
rc = efx_tso_put_header(tx_queue, buffer, header);
if (unlikely(rc))
return rc;
st->seqnum += skb_shinfo(skb)->gso_size;
/* Linux leaves suitable gaps in the IP ID space for us to fill. */
++st->ipv4_id;
++tx_queue->tso_packets;
@ -1023,12 +1264,11 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
EFX_BUG_ON_PARANOID(tx_queue->write_count != tx_queue->insert_count);
tso_start(&state, skb);
rc = tso_start(&state, efx, skb);
if (rc)
goto mem_err;
/* Assume that skb header area contains exactly the headers, and
* all payload is in the frag list.
*/
if (skb_headlen(skb) == state.header_len) {
if (likely(state.in_len == 0)) {
/* Grab the first payload fragment. */
EFX_BUG_ON_PARANOID(skb_shinfo(skb)->nr_frags < 1);
frag_i = 0;
@ -1037,9 +1277,7 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
if (rc)
goto mem_err;
} else {
rc = tso_get_head_fragment(&state, efx, skb);
if (rc)
goto mem_err;
/* Payload starts in the header area. */
frag_i = -1;
}
@ -1091,6 +1329,11 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
state.unmap_len, DMA_TO_DEVICE);
}
/* Free the header DMA mapping, if using option descriptors */
if (state.header_unmap_len)
dma_unmap_single(&efx->pci_dev->dev, state.header_dma_addr,
state.header_unmap_len, DMA_TO_DEVICE);
efx_enqueue_unwind(tx_queue);
return NETDEV_TX_OK;
}