qed: Revise load sequence to avoid PCI errors

Initiating final cleanup after an ungraceful driver unload can lead to bad
PCI accesses towards the host.
This patch revises the load sequence so final cleanup is sent while the
internal master enable is cleared, to prevent the host accesses, and clears
the internal error indications just before enabling the internal master
enable.

Signed-off-by: Tomer Tayar <tomer.tayar@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: Michal Kalderon <michal.kalderon@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Tomer Tayar 2019-01-20 11:36:37 +02:00 committed by David S. Miller
parent 1518039f6b
commit cfdb1b63ee
7 changed files with 179 additions and 113 deletions

View File

@ -554,7 +554,6 @@ struct qed_hwfn {
u8 dp_level;
char name[NAME_SIZE];
bool first_on_engine;
bool hw_init_done;
u8 num_funcs_on_engine;

View File

@ -1959,11 +1959,6 @@ static int qed_hw_init_pf(struct qed_hwfn *p_hwfn,
(p_hwfn->hw_info.personality == QED_PCI_FCOE) ? 1 : 0);
STORE_RT_REG(p_hwfn, PRS_REG_SEARCH_ROCE_RT_OFFSET, 0);
/* Cleanup chip from previous driver if such remains exist */
rc = qed_final_cleanup(p_hwfn, p_ptt, rel_pf_id, false);
if (rc)
return rc;
/* Sanity check before the PF init sequence that uses DMAE */
rc = qed_dmae_sanity(p_hwfn, p_ptt, "pf_phase");
if (rc)
@ -2007,17 +2002,15 @@ static int qed_hw_init_pf(struct qed_hwfn *p_hwfn,
return rc;
}
static int qed_change_pci_hwfn(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt,
u8 enable)
int qed_pglueb_set_pfid_enable(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt, bool b_enable)
{
u32 delay_idx = 0, val, set_val = enable ? 1 : 0;
u32 delay_idx = 0, val, set_val = b_enable ? 1 : 0;
/* Change PF in PXP */
qed_wr(p_hwfn, p_ptt,
PGLUE_B_REG_INTERNAL_PFID_ENABLE_MASTER, set_val);
/* Configure the PF's internal FID_enable for master transactions */
qed_wr(p_hwfn, p_ptt, PGLUE_B_REG_INTERNAL_PFID_ENABLE_MASTER, set_val);
/* wait until value is set - try for 1 second every 50us */
/* Wait until value is set - try for 1 second every 50us */
for (delay_idx = 0; delay_idx < 20000; delay_idx++) {
val = qed_rd(p_hwfn, p_ptt,
PGLUE_B_REG_INTERNAL_PFID_ENABLE_MASTER);
@ -2071,13 +2064,19 @@ static int qed_vf_start(struct qed_hwfn *p_hwfn,
return 0;
}
static void qed_pglueb_clear_err(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
{
qed_wr(p_hwfn, p_ptt, PGLUE_B_REG_WAS_ERROR_PF_31_0_CLR,
BIT(p_hwfn->abs_pf_id));
}
int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
{
struct qed_load_req_params load_req_params;
u32 load_code, resp, param, drv_mb_param;
bool b_default_mtu = true;
struct qed_hwfn *p_hwfn;
int rc = 0, mfw_rc, i;
int rc = 0, i;
u16 ether_type;
if ((p_params->int_mode == QED_INT_MODE_MSI) && (cdev->num_hwfns > 1)) {
@ -2092,7 +2091,7 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
}
for_each_hwfn(cdev, i) {
struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
p_hwfn = &cdev->hwfns[i];
/* If management didn't provide a default, set one of our own */
if (!p_hwfn->hw_info.mtu) {
@ -2105,9 +2104,6 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
continue;
}
/* Enable DMAE in PXP */
rc = qed_change_pci_hwfn(p_hwfn, p_hwfn->p_main_ptt, true);
rc = qed_calc_hw_mode(p_hwfn);
if (rc)
return rc;
@ -2148,8 +2144,34 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
qed_reset_mb_shadow(p_hwfn, p_hwfn->p_main_ptt);
p_hwfn->first_on_engine = (load_code ==
FW_MSG_CODE_DRV_LOAD_ENGINE);
/* Clean up chip from previous driver if such remains exist.
* This is not needed when the PF is the first one on the
* engine, since afterwards we are going to init the FW.
*/
if (load_code != FW_MSG_CODE_DRV_LOAD_ENGINE) {
rc = qed_final_cleanup(p_hwfn, p_hwfn->p_main_ptt,
p_hwfn->rel_pf_id, false);
if (rc) {
DP_NOTICE(p_hwfn, "Final cleanup failed\n");
goto load_err;
}
}
/* Log and clear previous pglue_b errors if such exist */
qed_pglueb_rbc_attn_handler(p_hwfn, p_hwfn->p_main_ptt);
/* Enable the PF's internal FID_enable in the PXP */
rc = qed_pglueb_set_pfid_enable(p_hwfn, p_hwfn->p_main_ptt,
true);
if (rc)
goto load_err;
/* Clear the pglue_b was_error indication.
* In E4 it must be done after the BME and the internal
* FID_enable for the PF are set, since VDMs may cause the
* indication to be set again.
*/
qed_pglueb_clear_err(p_hwfn, p_hwfn->p_main_ptt);
switch (load_code) {
case FW_MSG_CODE_DRV_LOAD_ENGINE:
@ -2180,39 +2202,29 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
break;
}
if (rc)
if (rc) {
DP_NOTICE(p_hwfn,
"init phase failed for loadcode 0x%x (rc %d)\n",
load_code, rc);
/* ACK mfw regardless of success or failure of initialization */
mfw_rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
DRV_MSG_CODE_LOAD_DONE,
0, &load_code, &param);
if (rc)
return rc;
if (mfw_rc) {
DP_NOTICE(p_hwfn, "Failed sending LOAD_DONE command\n");
return mfw_rc;
load_code, rc);
goto load_err;
}
/* Check if there is a DID mismatch between nvm-cfg/efuse */
if (param & FW_MB_PARAM_LOAD_DONE_DID_EFUSE_ERROR)
DP_NOTICE(p_hwfn,
"warning: device configuration is not supported on this board type. The device may not function as expected.\n");
rc = qed_mcp_load_done(p_hwfn, p_hwfn->p_main_ptt);
if (rc)
return rc;
/* send DCBX attention request command */
DP_VERBOSE(p_hwfn,
QED_MSG_DCB,
"sending phony dcbx set command to trigger DCBx attention handling\n");
mfw_rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
DRV_MSG_CODE_SET_DCBX,
1 << DRV_MB_PARAM_DCBX_NOTIFY_SHIFT,
&load_code, &param);
if (mfw_rc) {
rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
DRV_MSG_CODE_SET_DCBX,
1 << DRV_MB_PARAM_DCBX_NOTIFY_SHIFT,
&resp, &param);
if (rc) {
DP_NOTICE(p_hwfn,
"Failed to send DCBX attention request\n");
return mfw_rc;
return rc;
}
p_hwfn->hw_init_done = true;
@ -2261,6 +2273,12 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
}
return 0;
load_err:
/* The MFW load lock should be released also when initialization fails.
*/
qed_mcp_load_done(p_hwfn, p_hwfn->p_main_ptt);
return rc;
}
#define QED_HW_STOP_RETRY_LIMIT (10)
@ -2395,14 +2413,16 @@ int qed_hw_stop(struct qed_dev *cdev)
p_hwfn = QED_LEADING_HWFN(cdev);
p_ptt = QED_LEADING_HWFN(cdev)->p_main_ptt;
/* Disable DMAE in PXP - in CMT, this should only be done for
* first hw-function, and only after all transactions have
* stopped for all active hw-functions.
/* Clear the PF's internal FID_enable in the PXP.
* In CMT this should only be done for first hw-function, and
* only after all transactions have stopped for all active
* hw-functions.
*/
rc = qed_change_pci_hwfn(p_hwfn, p_ptt, false);
rc = qed_pglueb_set_pfid_enable(p_hwfn, p_ptt, false);
if (rc) {
DP_NOTICE(p_hwfn,
"qed_change_pci_hwfn failed. rc = %d.\n", rc);
"qed_pglueb_set_pfid_enable() failed. rc = %d.\n",
rc);
rc2 = -EINVAL;
}
}
@ -2502,9 +2522,8 @@ static void qed_hw_hwfn_prepare(struct qed_hwfn *p_hwfn)
PGLUE_B_REG_PGL_ADDR_94_F0_BB, 0);
}
/* Clean Previous errors if such exist */
qed_wr(p_hwfn, p_hwfn->p_main_ptt,
PGLUE_B_REG_WAS_ERROR_PF_31_0_CLR, 1 << p_hwfn->abs_pf_id);
/* Clean previous pglue_b errors if such exist */
qed_pglueb_clear_err(p_hwfn, p_hwfn->p_main_ptt);
/* enable internal target-read */
qed_wr(p_hwfn, p_hwfn->p_main_ptt,

View File

@ -472,6 +472,18 @@ int qed_get_queue_coalesce(struct qed_hwfn *p_hwfn, u16 *coal, void *handle);
int
qed_set_queue_coalesce(u16 rx_coal, u16 tx_coal, void *p_handle);
/**
* @brief qed_pglueb_set_pfid_enable - Enable or disable PCI BUS MASTER
*
* @param p_hwfn
* @param p_ptt
* @param b_enable - true/false
*
* @return int
*/
int qed_pglueb_set_pfid_enable(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt, bool b_enable);
/**
* @brief db_recovery_add - add doorbell information to the doorbell
* recovery mechanism.

View File

@ -255,112 +255,114 @@ out:
#define PGLUE_ATTENTION_ICPL_VALID (1 << 23)
#define PGLUE_ATTENTION_ZLR_VALID (1 << 25)
#define PGLUE_ATTENTION_ILT_VALID (1 << 23)
static int qed_pglub_rbc_attn_cb(struct qed_hwfn *p_hwfn)
int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt)
{
u32 tmp;
tmp = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
PGLUE_B_REG_TX_ERR_WR_DETAILS2);
tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_WR_DETAILS2);
if (tmp & PGLUE_ATTENTION_VALID) {
u32 addr_lo, addr_hi, details;
addr_lo = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
addr_lo = qed_rd(p_hwfn, p_ptt,
PGLUE_B_REG_TX_ERR_WR_ADD_31_0);
addr_hi = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
addr_hi = qed_rd(p_hwfn, p_ptt,
PGLUE_B_REG_TX_ERR_WR_ADD_63_32);
details = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
details = qed_rd(p_hwfn, p_ptt,
PGLUE_B_REG_TX_ERR_WR_DETAILS);
DP_INFO(p_hwfn,
"Illegal write by chip to [%08x:%08x] blocked.\n"
"Details: %08x [PFID %02x, VFID %02x, VF_VALID %02x]\n"
"Details2 %08x [Was_error %02x BME deassert %02x FID_enable deassert %02x]\n",
addr_hi, addr_lo, details,
(u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_PFID),
(u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VFID),
GET_FIELD(details,
PGLUE_ATTENTION_DETAILS_VF_VALID) ? 1 : 0,
tmp,
GET_FIELD(tmp,
PGLUE_ATTENTION_DETAILS2_WAS_ERR) ? 1 : 0,
GET_FIELD(tmp,
PGLUE_ATTENTION_DETAILS2_BME) ? 1 : 0,
GET_FIELD(tmp,
PGLUE_ATTENTION_DETAILS2_FID_EN) ? 1 : 0);
DP_NOTICE(p_hwfn,
"Illegal write by chip to [%08x:%08x] blocked.\n"
"Details: %08x [PFID %02x, VFID %02x, VF_VALID %02x]\n"
"Details2 %08x [Was_error %02x BME deassert %02x FID_enable deassert %02x]\n",
addr_hi, addr_lo, details,
(u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_PFID),
(u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VFID),
GET_FIELD(details,
PGLUE_ATTENTION_DETAILS_VF_VALID) ? 1 : 0,
tmp,
GET_FIELD(tmp,
PGLUE_ATTENTION_DETAILS2_WAS_ERR) ? 1 : 0,
GET_FIELD(tmp,
PGLUE_ATTENTION_DETAILS2_BME) ? 1 : 0,
GET_FIELD(tmp,
PGLUE_ATTENTION_DETAILS2_FID_EN) ? 1 : 0);
}
tmp = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
PGLUE_B_REG_TX_ERR_RD_DETAILS2);
tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_RD_DETAILS2);
if (tmp & PGLUE_ATTENTION_RD_VALID) {
u32 addr_lo, addr_hi, details;
addr_lo = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
addr_lo = qed_rd(p_hwfn, p_ptt,
PGLUE_B_REG_TX_ERR_RD_ADD_31_0);
addr_hi = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
addr_hi = qed_rd(p_hwfn, p_ptt,
PGLUE_B_REG_TX_ERR_RD_ADD_63_32);
details = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
details = qed_rd(p_hwfn, p_ptt,
PGLUE_B_REG_TX_ERR_RD_DETAILS);
DP_INFO(p_hwfn,
"Illegal read by chip from [%08x:%08x] blocked.\n"
" Details: %08x [PFID %02x, VFID %02x, VF_VALID %02x]\n"
" Details2 %08x [Was_error %02x BME deassert %02x FID_enable deassert %02x]\n",
addr_hi, addr_lo, details,
(u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_PFID),
(u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VFID),
GET_FIELD(details,
PGLUE_ATTENTION_DETAILS_VF_VALID) ? 1 : 0,
tmp,
GET_FIELD(tmp, PGLUE_ATTENTION_DETAILS2_WAS_ERR) ? 1
: 0,
GET_FIELD(tmp, PGLUE_ATTENTION_DETAILS2_BME) ? 1 : 0,
GET_FIELD(tmp, PGLUE_ATTENTION_DETAILS2_FID_EN) ? 1
: 0);
DP_NOTICE(p_hwfn,
"Illegal read by chip from [%08x:%08x] blocked.\n"
"Details: %08x [PFID %02x, VFID %02x, VF_VALID %02x]\n"
"Details2 %08x [Was_error %02x BME deassert %02x FID_enable deassert %02x]\n",
addr_hi, addr_lo, details,
(u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_PFID),
(u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VFID),
GET_FIELD(details,
PGLUE_ATTENTION_DETAILS_VF_VALID) ? 1 : 0,
tmp,
GET_FIELD(tmp,
PGLUE_ATTENTION_DETAILS2_WAS_ERR) ? 1 : 0,
GET_FIELD(tmp,
PGLUE_ATTENTION_DETAILS2_BME) ? 1 : 0,
GET_FIELD(tmp,
PGLUE_ATTENTION_DETAILS2_FID_EN) ? 1 : 0);
}
tmp = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
PGLUE_B_REG_TX_ERR_WR_DETAILS_ICPL);
tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_WR_DETAILS_ICPL);
if (tmp & PGLUE_ATTENTION_ICPL_VALID)
DP_INFO(p_hwfn, "ICPL error - %08x\n", tmp);
DP_NOTICE(p_hwfn, "ICPL error - %08x\n", tmp);
tmp = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
PGLUE_B_REG_MASTER_ZLR_ERR_DETAILS);
tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_MASTER_ZLR_ERR_DETAILS);
if (tmp & PGLUE_ATTENTION_ZLR_VALID) {
u32 addr_hi, addr_lo;
addr_lo = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
addr_lo = qed_rd(p_hwfn, p_ptt,
PGLUE_B_REG_MASTER_ZLR_ERR_ADD_31_0);
addr_hi = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
addr_hi = qed_rd(p_hwfn, p_ptt,
PGLUE_B_REG_MASTER_ZLR_ERR_ADD_63_32);
DP_INFO(p_hwfn, "ZLR eror - %08x [Address %08x:%08x]\n",
tmp, addr_hi, addr_lo);
DP_NOTICE(p_hwfn, "ZLR error - %08x [Address %08x:%08x]\n",
tmp, addr_hi, addr_lo);
}
tmp = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
PGLUE_B_REG_VF_ILT_ERR_DETAILS2);
tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_VF_ILT_ERR_DETAILS2);
if (tmp & PGLUE_ATTENTION_ILT_VALID) {
u32 addr_hi, addr_lo, details;
addr_lo = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
addr_lo = qed_rd(p_hwfn, p_ptt,
PGLUE_B_REG_VF_ILT_ERR_ADD_31_0);
addr_hi = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
addr_hi = qed_rd(p_hwfn, p_ptt,
PGLUE_B_REG_VF_ILT_ERR_ADD_63_32);
details = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
details = qed_rd(p_hwfn, p_ptt,
PGLUE_B_REG_VF_ILT_ERR_DETAILS);
DP_INFO(p_hwfn,
"ILT error - Details %08x Details2 %08x [Address %08x:%08x]\n",
details, tmp, addr_hi, addr_lo);
DP_NOTICE(p_hwfn,
"ILT error - Details %08x Details2 %08x [Address %08x:%08x]\n",
details, tmp, addr_hi, addr_lo);
}
/* Clear the indications */
qed_wr(p_hwfn, p_hwfn->p_dpc_ptt,
PGLUE_B_REG_LATCHED_ERRORS_CLR, (1 << 2));
qed_wr(p_hwfn, p_ptt, PGLUE_B_REG_LATCHED_ERRORS_CLR, BIT(2));
return 0;
}
static int qed_pglueb_rbc_attn_cb(struct qed_hwfn *p_hwfn)
{
return qed_pglueb_rbc_attn_handler(p_hwfn, p_hwfn->p_dpc_ptt);
}
#define QED_DORQ_ATTENTION_REASON_MASK (0xfffff)
#define QED_DORQ_ATTENTION_OPAQUE_MASK (0xffff)
#define QED_DORQ_ATTENTION_OPAQUE_SHIFT (0x0)
@ -540,7 +542,7 @@ static struct aeu_invert_reg aeu_descs[NUM_ATTN_REGS] = {
{"PGLUE misc_flr", ATTENTION_SINGLE,
NULL, MAX_BLOCK_ID},
{"PGLUE B RBC", ATTENTION_PAR_INT,
qed_pglub_rbc_attn_cb, BLOCK_PGLUE_B},
qed_pglueb_rbc_attn_cb, BLOCK_PGLUE_B},
{"PGLUE misc_mctp", ATTENTION_SINGLE,
NULL, MAX_BLOCK_ID},
{"Flash event", ATTENTION_SINGLE, NULL, MAX_BLOCK_ID},

View File

@ -431,4 +431,7 @@ int qed_int_set_timer_res(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
#define QED_MAPPING_MEMORY_SIZE(dev) (NUM_OF_SBS(dev))
int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt);
#endif

View File

@ -1070,6 +1070,27 @@ int qed_mcp_load_req(struct qed_hwfn *p_hwfn,
return 0;
}
int qed_mcp_load_done(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
{
u32 resp = 0, param = 0;
int rc;
rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_LOAD_DONE, 0, &resp,
&param);
if (rc) {
DP_NOTICE(p_hwfn,
"Failed to send a LOAD_DONE command, rc = %d\n", rc);
return rc;
}
/* Check if there is a DID mismatch between nvm-cfg/efuse */
if (param & FW_MB_PARAM_LOAD_DONE_DID_EFUSE_ERROR)
DP_NOTICE(p_hwfn,
"warning: device configuration is not supported on this board type. The device may not function as expected.\n");
return 0;
}
int qed_mcp_unload_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
{
struct qed_mcp_mb_params mb_params;

View File

@ -800,6 +800,16 @@ int qed_mcp_load_req(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt,
struct qed_load_req_params *p_params);
/**
* @brief Sends a LOAD_DONE message to the MFW
*
* @param p_hwfn
* @param p_ptt
*
* @return int - 0 - Operation was successful.
*/
int qed_mcp_load_done(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
/**
* @brief Sends a UNLOAD_REQ message to the MFW
*