* [PATCH 08/12] IB/hfi1: Add active channel and backplane support for integrated devices
From: Dennis Dalessandro @ 2016-10-17 11:19 UTC (permalink / raw)
To: dledford-H+wXaHxf7aLQT0dZR+AlfA
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, Easwar Hariharan, Dean Luick,
Ira Weiny
In-Reply-To: <20161017103326.7934.21558.stgit-9QXIwq+3FY+1XWohqUldA0EOCMrvLtNR@public.gmane.org>
From: Easwar Hariharan <easwar.hariharan-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Use scratch registers within the HFI1 device to recover signal
integrity information that is then used to tune the channel. While
there, update error messages to better convey the result of falling
back to a backup file.
Reviewed-by: Ira Weiny <ira.weiny-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Reviewed-by: Dean Luick <dean.luick-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Easwar Hariharan <easwar.hariharan-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/hw/hfi1/chip_registers.h | 3 +
drivers/infiniband/hw/hfi1/firmware.c | 136 +++++++++++++++++++++----
drivers/infiniband/hw/hfi1/hfi.h | 16 +++
drivers/infiniband/hw/hfi1/platform.c | 149 ++++++++++++++++++++++-----
drivers/infiniband/hw/hfi1/platform.h | 117 +++++++++++++++++++++
5 files changed, 376 insertions(+), 45 deletions(-)
diff --git a/drivers/infiniband/hw/hfi1/chip_registers.h b/drivers/infiniband/hw/hfi1/chip_registers.h
index 5b99938..5bfa839 100644
--- a/drivers/infiniband/hw/hfi1/chip_registers.h
+++ b/drivers/infiniband/hw/hfi1/chip_registers.h
@@ -415,6 +415,9 @@
#define ASIC_CFG_SBUS_REQUEST_DATA_IN_SHIFT 32
#define ASIC_CFG_SBUS_REQUEST_RECEIVER_ADDR_SHIFT 0
#define ASIC_CFG_SCRATCH (ASIC + 0x000000000020)
+#define ASIC_CFG_SCRATCH_1 (ASIC_CFG_SCRATCH + 0x08)
+#define ASIC_CFG_SCRATCH_2 (ASIC_CFG_SCRATCH + 0x10)
+#define ASIC_CFG_SCRATCH_3 (ASIC_CFG_SCRATCH + 0x18)
#define ASIC_CFG_THERM_POLL_EN (ASIC + 0x000000000050)
#define ASIC_EEP_ADDR_CMD (ASIC + 0x000000000308)
#define ASIC_EEP_ADDR_CMD_EP_ADDR_MASK 0xFFFFFFull
diff --git a/drivers/infiniband/hw/hfi1/firmware.c b/drivers/infiniband/hw/hfi1/firmware.c
index 13db8eb..9a36c8c 100644
--- a/drivers/infiniband/hw/hfi1/firmware.c
+++ b/drivers/infiniband/hw/hfi1/firmware.c
@@ -707,6 +707,9 @@ static int obtain_firmware(struct hfi1_devdata *dd)
&dd->pcidev->dev);
if (err) {
platform_config = NULL;
+ dd_dev_err(dd,
+ "%s: No default platform config file found\n",
+ __func__);
goto done;
}
dd->platform_config.data = platform_config->data;
@@ -1761,8 +1764,17 @@ int parse_platform_config(struct hfi1_devdata *dd)
u32 record_idx = 0, table_type = 0, table_length_dwords = 0;
int ret = -EINVAL; /* assume failure */
+ /*
+ * For integrated devices that did not fall back to the default file,
+ * the SI tuning information for active channels is acquired from the
+ * scratch register bitmap, thus there is no platform config to parse.
+ * Skip parsing in these situations.
+ */
+ if (is_integrated(dd) && !platform_config_load)
+ return 0;
+
if (!dd->platform_config.data) {
- dd_dev_info(dd, "%s: Missing config file\n", __func__);
+ dd_dev_err(dd, "%s: Missing config file\n", __func__);
goto bail;
}
ptr = (u32 *)dd->platform_config.data;
@@ -1770,7 +1782,7 @@ int parse_platform_config(struct hfi1_devdata *dd)
magic_num = *ptr;
ptr++;
if (magic_num != PLATFORM_CONFIG_MAGIC_NUM) {
- dd_dev_info(dd, "%s: Bad config file\n", __func__);
+ dd_dev_err(dd, "%s: Bad config file\n", __func__);
goto bail;
}
@@ -1797,9 +1809,9 @@ int parse_platform_config(struct hfi1_devdata *dd)
header1 = *ptr;
header2 = *(ptr + 1);
if (header1 != ~header2) {
- dd_dev_info(dd, "%s: Failed validation at offset %ld\n",
- __func__, (ptr - (u32 *)
- dd->platform_config.data));
+ dd_dev_err(dd, "%s: Failed validation at offset %ld\n",
+ __func__, (ptr - (u32 *)
+ dd->platform_config.data));
goto bail;
}
@@ -1841,11 +1853,11 @@ int parse_platform_config(struct hfi1_devdata *dd)
table_length_dwords;
break;
default:
- dd_dev_info(dd,
- "%s: Unknown data table %d, offset %ld\n",
- __func__, table_type,
- (ptr - (u32 *)
- dd->platform_config.data));
+ dd_dev_err(dd,
+ "%s: Unknown data table %d, offset %ld\n",
+ __func__, table_type,
+ (ptr - (u32 *)
+ dd->platform_config.data));
goto bail; /* We don't trust this file now */
}
pcfgcache->config_tables[table_type].table = ptr;
@@ -1865,11 +1877,11 @@ int parse_platform_config(struct hfi1_devdata *dd)
case PLATFORM_CONFIG_VARIABLE_SETTINGS_TABLE:
break;
default:
- dd_dev_info(dd,
- "%s: Unknown meta table %d, offset %ld\n",
- __func__, table_type,
- (ptr -
- (u32 *)dd->platform_config.data));
+ dd_dev_err(dd,
+ "%s: Unknown meta table %d, offset %ld\n",
+ __func__, table_type,
+ (ptr -
+ (u32 *)dd->platform_config.data));
goto bail; /* We don't trust this file now */
}
pcfgcache->config_tables[table_type].table_metadata =
@@ -1884,10 +1896,9 @@ int parse_platform_config(struct hfi1_devdata *dd)
/* Jump the table */
ptr += table_length_dwords;
if (crc != *ptr) {
- dd_dev_info(dd, "%s: Failed CRC check at offset %ld\n",
- __func__, (ptr -
- (u32 *)
- dd->platform_config.data));
+ dd_dev_err(dd, "%s: Failed CRC check at offset %ld\n",
+ __func__, (ptr -
+ (u32 *)dd->platform_config.data));
goto bail;
}
/* Jump the CRC DWORD */
@@ -1901,6 +1912,84 @@ bail:
return ret;
}
+static void get_integrated_platform_config_field(
+ struct hfi1_devdata *dd,
+ enum platform_config_table_type_encoding table_type,
+ int field_index, u32 *data)
+{
+ struct hfi1_pportdata *ppd = dd->pport;
+ u8 *cache = ppd->qsfp_info.cache;
+ u32 tx_preset = 0;
+
+ switch (table_type) {
+ case PLATFORM_CONFIG_SYSTEM_TABLE:
+ if (field_index == SYSTEM_TABLE_QSFP_POWER_CLASS_MAX)
+ *data = ppd->max_power_class;
+ else if (field_index == SYSTEM_TABLE_QSFP_ATTENUATION_DEFAULT_25G)
+ *data = ppd->default_atten;
+ break;
+ case PLATFORM_CONFIG_PORT_TABLE:
+ if (field_index == PORT_TABLE_PORT_TYPE)
+ *data = ppd->port_type;
+ else if (field_index == PORT_TABLE_LOCAL_ATTEN_25G)
+ *data = ppd->local_atten;
+ else if (field_index == PORT_TABLE_REMOTE_ATTEN_25G)
+ *data = ppd->remote_atten;
+ break;
+ case PLATFORM_CONFIG_RX_PRESET_TABLE:
+ if (field_index == RX_PRESET_TABLE_QSFP_RX_CDR_APPLY)
+ *data = (ppd->rx_preset & QSFP_RX_CDR_APPLY_SMASK) >>
+ QSFP_RX_CDR_APPLY_SHIFT;
+ else if (field_index == RX_PRESET_TABLE_QSFP_RX_EMP_APPLY)
+ *data = (ppd->rx_preset & QSFP_RX_EMP_APPLY_SMASK) >>
+ QSFP_RX_EMP_APPLY_SHIFT;
+ else if (field_index == RX_PRESET_TABLE_QSFP_RX_AMP_APPLY)
+ *data = (ppd->rx_preset & QSFP_RX_AMP_APPLY_SMASK) >>
+ QSFP_RX_AMP_APPLY_SHIFT;
+ else if (field_index == RX_PRESET_TABLE_QSFP_RX_CDR)
+ *data = (ppd->rx_preset & QSFP_RX_CDR_SMASK) >>
+ QSFP_RX_CDR_SHIFT;
+ else if (field_index == RX_PRESET_TABLE_QSFP_RX_EMP)
+ *data = (ppd->rx_preset & QSFP_RX_EMP_SMASK) >>
+ QSFP_RX_EMP_SHIFT;
+ else if (field_index == RX_PRESET_TABLE_QSFP_RX_AMP)
+ *data = (ppd->rx_preset & QSFP_RX_AMP_SMASK) >>
+ QSFP_RX_AMP_SHIFT;
+ break;
+ case PLATFORM_CONFIG_TX_PRESET_TABLE:
+ if (cache[QSFP_EQ_INFO_OFFS] & 0x4)
+ tx_preset = ppd->tx_preset_eq;
+ else
+ tx_preset = ppd->tx_preset_noeq;
+ if (field_index == TX_PRESET_TABLE_PRECUR)
+ *data = (tx_preset & TX_PRECUR_SMASK) >>
+ TX_PRECUR_SHIFT;
+ else if (field_index == TX_PRESET_TABLE_ATTN)
+ *data = (tx_preset & TX_ATTN_SMASK) >>
+ TX_ATTN_SHIFT;
+ else if (field_index == TX_PRESET_TABLE_POSTCUR)
+ *data = (tx_preset & TX_POSTCUR_SMASK) >>
+ TX_POSTCUR_SHIFT;
+ else if (field_index == TX_PRESET_TABLE_QSFP_TX_CDR_APPLY)
+ *data = (tx_preset & QSFP_TX_CDR_APPLY_SMASK) >>
+ QSFP_TX_CDR_APPLY_SHIFT;
+ else if (field_index == TX_PRESET_TABLE_QSFP_TX_EQ_APPLY)
+ *data = (tx_preset & QSFP_TX_EQ_APPLY_SMASK) >>
+ QSFP_TX_EQ_APPLY_SHIFT;
+ else if (field_index == TX_PRESET_TABLE_QSFP_TX_CDR)
+ *data = (tx_preset & QSFP_TX_CDR_SMASK) >>
+ QSFP_TX_CDR_SHIFT;
+ else if (field_index == TX_PRESET_TABLE_QSFP_TX_EQ)
+ *data = (tx_preset & QSFP_TX_EQ_SMASK) >>
+ QSFP_TX_EQ_SHIFT;
+ break;
+ case PLATFORM_CONFIG_QSFP_ATTEN_TABLE:
+ case PLATFORM_CONFIG_VARIABLE_SETTINGS_TABLE:
+ default:
+ break;
+ }
+}
+
static int get_platform_fw_field_metadata(struct hfi1_devdata *dd, int table,
int field, u32 *field_len_bits,
u32 *field_start_bits)
@@ -1976,6 +2065,15 @@ int get_platform_config_field(struct hfi1_devdata *dd,
else
return -EINVAL;
+ if (is_integrated(dd) && !platform_config_load) {
+ /*
+ * Use saved configuration from ppd for integrated platforms
+ */
+ get_integrated_platform_config_field(dd, table_type,
+ field_index, data);
+ return 0;
+ }
+
ret = get_platform_fw_field_metadata(dd, table_type, field_index,
&field_len_bits,
&field_start_bits);
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index bec4607..94cc5f2 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -582,8 +582,16 @@ struct hfi1_pportdata {
struct kobject vl2mtu_kobj;
/* PHY support */
- u32 port_type;
struct qsfp_data qsfp_info;
+ /* Values for SI tuning of SerDes */
+ u32 port_type;
+ u32 tx_preset_eq;
+ u32 tx_preset_noeq;
+ u32 rx_preset;
+ u8 local_atten;
+ u8 remote_atten;
+ u8 default_atten;
+ u8 max_power_class;
/* GUIDs for this interface, in host order, guids[0] is a port guid */
u64 guids[HFI1_GUIDS_PER_PORT];
@@ -2037,6 +2045,12 @@ static inline u32 qsfp_resource(struct hfi1_devdata *dd)
return i2c_target(dd->hfi1_id);
}
+/* Is this device integrated or discrete? */
+static inline bool is_integrated(struct hfi1_devdata *dd)
+{
+ return dd->pcidev->device == PCI_DEVICE_ID_INTEL1;
+}
+
int hfi1_tempsense_rd(struct hfi1_devdata *dd, struct hfi1_temp *temp);
#define DD_DEV_ENTRY(dd) __string(dev, dev_name(&(dd)->pcidev->dev))
diff --git a/drivers/infiniband/hw/hfi1/platform.c b/drivers/infiniband/hw/hfi1/platform.c
index 2024331..0e70438 100644
--- a/drivers/infiniband/hw/hfi1/platform.c
+++ b/drivers/infiniband/hw/hfi1/platform.c
@@ -49,6 +49,90 @@
#include "efivar.h"
#include "eprom.h"
+static int validate_scratch_checksum(struct hfi1_devdata *dd)
+{
+ u64 checksum = 0, temp_scratch = 0;
+ int i, j, version;
+
+ temp_scratch = read_csr(dd, ASIC_CFG_SCRATCH);
+ version = (temp_scratch & BITMAP_VERSION_SMASK) >> BITMAP_VERSION_SHIFT;
+
+ /* Prevent power on default of all zeroes from passing checksum */
+ if (!version)
+ return 0;
+
+ /*
+ * ASIC scratch 0 only contains the checksum and bitmap version as
+ * fields of interest, both of which are handled separately from the
+ * loop below, so skip it
+ */
+ checksum += version;
+ for (i = 1; i < ASIC_NUM_SCRATCH; i++) {
+ temp_scratch = read_csr(dd, ASIC_CFG_SCRATCH + (8 * i));
+ for (j = sizeof(u64); j != 0; j -= 2) {
+ checksum += (temp_scratch & 0xFFFF);
+ temp_scratch >>= 16;
+ }
+ }
+
+ while (checksum >> 16)
+ checksum = (checksum & CHECKSUM_MASK) + (checksum >> 16);
+
+ temp_scratch = read_csr(dd, ASIC_CFG_SCRATCH);
+ temp_scratch &= CHECKSUM_SMASK;
+ temp_scratch >>= CHECKSUM_SHIFT;
+
+ if (checksum + temp_scratch == 0xFFFF)
+ return 1;
+ return 0;
+}
+
+static void save_platform_config_fields(struct hfi1_devdata *dd)
+{
+ struct hfi1_pportdata *ppd = dd->pport;
+ u64 temp_scratch = 0, temp_dest = 0;
+
+ temp_scratch = read_csr(dd, ASIC_CFG_SCRATCH_1);
+
+ temp_dest = temp_scratch &
+ (dd->hfi1_id ? PORT1_PORT_TYPE_SMASK :
+ PORT0_PORT_TYPE_SMASK);
+ ppd->port_type = temp_dest >>
+ (dd->hfi1_id ? PORT1_PORT_TYPE_SHIFT :
+ PORT0_PORT_TYPE_SHIFT);
+
+ temp_dest = temp_scratch &
+ (dd->hfi1_id ? PORT1_LOCAL_ATTEN_SMASK :
+ PORT0_LOCAL_ATTEN_SMASK);
+ ppd->local_atten = temp_dest >>
+ (dd->hfi1_id ? PORT1_LOCAL_ATTEN_SHIFT :
+ PORT0_LOCAL_ATTEN_SHIFT);
+
+ temp_dest = temp_scratch &
+ (dd->hfi1_id ? PORT1_REMOTE_ATTEN_SMASK :
+ PORT0_REMOTE_ATTEN_SMASK);
+ ppd->remote_atten = temp_dest >>
+ (dd->hfi1_id ? PORT1_REMOTE_ATTEN_SHIFT :
+ PORT0_REMOTE_ATTEN_SHIFT);
+
+ temp_dest = temp_scratch &
+ (dd->hfi1_id ? PORT1_DEFAULT_ATTEN_SMASK :
+ PORT0_DEFAULT_ATTEN_SMASK);
+ ppd->default_atten = temp_dest >>
+ (dd->hfi1_id ? PORT1_DEFAULT_ATTEN_SHIFT :
+ PORT0_DEFAULT_ATTEN_SHIFT);
+
+ temp_scratch = read_csr(dd, dd->hfi1_id ? ASIC_CFG_SCRATCH_3 :
+ ASIC_CFG_SCRATCH_2);
+
+ ppd->tx_preset_eq = (temp_scratch & TX_EQ_SMASK) >> TX_EQ_SHIFT;
+ ppd->tx_preset_noeq = (temp_scratch & TX_NO_EQ_SMASK) >> TX_NO_EQ_SHIFT;
+ ppd->rx_preset = (temp_scratch & RX_SMASK) >> RX_SHIFT;
+
+ ppd->max_power_class = (temp_scratch & QSFP_MAX_POWER_SMASK) >>
+ QSFP_MAX_POWER_SHIFT;
+}
+
void get_platform_config(struct hfi1_devdata *dd)
{
int ret = 0;
@@ -56,38 +140,49 @@ void get_platform_config(struct hfi1_devdata *dd)
u8 *temp_platform_config = NULL;
u32 esize;
- ret = eprom_read_platform_config(dd, (void **)&temp_platform_config,
- &esize);
- if (!ret) {
- /* success */
- size = esize;
- goto success;
+ if (is_integrated(dd)) {
+ if (validate_scratch_checksum(dd)) {
+ save_platform_config_fields(dd);
+ return;
+ }
+ dd_dev_err(dd, "%s: Config bitmap corrupted/uninitialized\n",
+ __func__);
+ dd_dev_err(dd,
+ "%s: Please update your BIOS to support active channels\n",
+ __func__);
+ } else {
+ ret = eprom_read_platform_config(dd,
+ (void **)&temp_platform_config,
+ &esize);
+ if (!ret) {
+ /* success */
+ dd->platform_config.data = temp_platform_config;
+ dd->platform_config.size = esize;
+ return;
+ }
+ /* fail, try EFI variable */
+
+ ret = read_hfi1_efi_var(dd, "configuration", &size,
+ (void **)&temp_platform_config);
+ if (!ret) {
+ dd->platform_config.data = temp_platform_config;
+ dd->platform_config.size = size;
+ return;
+ }
}
- /* fail, try EFI variable */
-
- ret = read_hfi1_efi_var(dd, "configuration", &size,
- (void **)&temp_platform_config);
- if (!ret)
- goto success;
-
- dd_dev_info(dd,
- "%s: Failed to get platform config from UEFI, falling back to request firmware\n",
- __func__);
+ dd_dev_err(dd,
+ "%s: Failed to get platform config, falling back to sub-optimal default file\n",
+ __func__);
/* fall back to request firmware */
platform_config_load = 1;
- return;
-
-success:
- dd->platform_config.data = temp_platform_config;
- dd->platform_config.size = size;
}
void free_platform_config(struct hfi1_devdata *dd)
{
if (!platform_config_load) {
/*
- * was loaded from EFI, release memory
- * allocated by read_efi_var
+ * was loaded from EFI or the EPROM, release memory
+ * allocated by read_efi_var/eprom_read_platform_config
*/
kfree(dd->platform_config.data);
}
@@ -100,12 +195,16 @@ void free_platform_config(struct hfi1_devdata *dd)
void get_port_type(struct hfi1_pportdata *ppd)
{
int ret;
+ u32 temp;
ret = get_platform_config_field(ppd->dd, PLATFORM_CONFIG_PORT_TABLE, 0,
- PORT_TABLE_PORT_TYPE, &ppd->port_type,
+ PORT_TABLE_PORT_TYPE, &temp,
4);
- if (ret)
+ if (ret) {
ppd->port_type = PORT_TYPE_UNKNOWN;
+ return;
+ }
+ ppd->port_type = temp;
}
int set_qsfp_tx(struct hfi1_pportdata *ppd, int on)
diff --git a/drivers/infiniband/hw/hfi1/platform.h b/drivers/infiniband/hw/hfi1/platform.h
index e2c2161..3115540 100644
--- a/drivers/infiniband/hw/hfi1/platform.h
+++ b/drivers/infiniband/hw/hfi1/platform.h
@@ -295,6 +295,123 @@ enum link_tuning_encoding {
OPA_UNKNOWN_TUNING
};
+/*
+ * Shifts and masks for the link SI tuning values stuffed into the ASIC scratch
+ * registers for integrated platforms
+ */
+#define PORT0_PORT_TYPE_SHIFT 0
+#define PORT0_LOCAL_ATTEN_SHIFT 4
+#define PORT0_REMOTE_ATTEN_SHIFT 10
+#define PORT0_DEFAULT_ATTEN_SHIFT 32
+
+#define PORT1_PORT_TYPE_SHIFT 16
+#define PORT1_LOCAL_ATTEN_SHIFT 20
+#define PORT1_REMOTE_ATTEN_SHIFT 26
+#define PORT1_DEFAULT_ATTEN_SHIFT 40
+
+#define PORT0_PORT_TYPE_MASK 0xFUL
+#define PORT0_LOCAL_ATTEN_MASK 0x3FUL
+#define PORT0_REMOTE_ATTEN_MASK 0x3FUL
+#define PORT0_DEFAULT_ATTEN_MASK 0xFFUL
+
+#define PORT1_PORT_TYPE_MASK 0xFUL
+#define PORT1_LOCAL_ATTEN_MASK 0x3FUL
+#define PORT1_REMOTE_ATTEN_MASK 0x3FUL
+#define PORT1_DEFAULT_ATTEN_MASK 0xFFUL
+
+#define PORT0_PORT_TYPE_SMASK (PORT0_PORT_TYPE_MASK << \
+ PORT0_PORT_TYPE_SHIFT)
+#define PORT0_LOCAL_ATTEN_SMASK (PORT0_LOCAL_ATTEN_MASK << \
+ PORT0_LOCAL_ATTEN_SHIFT)
+#define PORT0_REMOTE_ATTEN_SMASK (PORT0_REMOTE_ATTEN_MASK << \
+ PORT0_REMOTE_ATTEN_SHIFT)
+#define PORT0_DEFAULT_ATTEN_SMASK (PORT0_DEFAULT_ATTEN_MASK << \
+ PORT0_DEFAULT_ATTEN_SHIFT)
+
+#define PORT1_PORT_TYPE_SMASK (PORT1_PORT_TYPE_MASK << \
+ PORT1_PORT_TYPE_SHIFT)
+#define PORT1_LOCAL_ATTEN_SMASK (PORT1_LOCAL_ATTEN_MASK << \
+ PORT1_LOCAL_ATTEN_SHIFT)
+#define PORT1_REMOTE_ATTEN_SMASK (PORT1_REMOTE_ATTEN_MASK << \
+ PORT1_REMOTE_ATTEN_SHIFT)
+#define PORT1_DEFAULT_ATTEN_SMASK (PORT1_DEFAULT_ATTEN_MASK << \
+ PORT1_DEFAULT_ATTEN_SHIFT)
+
+#define QSFP_MAX_POWER_SHIFT 0
+#define TX_NO_EQ_SHIFT 4
+#define TX_EQ_SHIFT 25
+#define RX_SHIFT 46
+
+#define QSFP_MAX_POWER_MASK 0xFUL
+#define TX_NO_EQ_MASK 0x1FFFFFUL
+#define TX_EQ_MASK 0x1FFFFFUL
+#define RX_MASK 0xFFFFUL
+
+#define QSFP_MAX_POWER_SMASK (QSFP_MAX_POWER_MASK << \
+ QSFP_MAX_POWER_SHIFT)
+#define TX_NO_EQ_SMASK (TX_NO_EQ_MASK << TX_NO_EQ_SHIFT)
+#define TX_EQ_SMASK (TX_EQ_MASK << TX_EQ_SHIFT)
+#define RX_SMASK (RX_MASK << RX_SHIFT)
+
+#define TX_PRECUR_SHIFT 0
+#define TX_ATTN_SHIFT 4
+#define QSFP_TX_CDR_APPLY_SHIFT 9
+#define QSFP_TX_EQ_APPLY_SHIFT 10
+#define QSFP_TX_CDR_SHIFT 11
+#define QSFP_TX_EQ_SHIFT 12
+#define TX_POSTCUR_SHIFT 16
+
+#define TX_PRECUR_MASK 0xFUL
+#define TX_ATTN_MASK 0x1FUL
+#define QSFP_TX_CDR_APPLY_MASK 0x1UL
+#define QSFP_TX_EQ_APPLY_MASK 0x1UL
+#define QSFP_TX_CDR_MASK 0x1UL
+#define QSFP_TX_EQ_MASK 0xFUL
+#define TX_POSTCUR_MASK 0x1FUL
+
+#define TX_PRECUR_SMASK (TX_PRECUR_MASK << TX_PRECUR_SHIFT)
+#define TX_ATTN_SMASK (TX_ATTN_MASK << TX_ATTN_SHIFT)
+#define QSFP_TX_CDR_APPLY_SMASK (QSFP_TX_CDR_APPLY_MASK << \
+ QSFP_TX_CDR_APPLY_SHIFT)
+#define QSFP_TX_EQ_APPLY_SMASK (QSFP_TX_EQ_APPLY_MASK << \
+ QSFP_TX_EQ_APPLY_SHIFT)
+#define QSFP_TX_CDR_SMASK (QSFP_TX_CDR_MASK << QSFP_TX_CDR_SHIFT)
+#define QSFP_TX_EQ_SMASK (QSFP_TX_EQ_MASK << QSFP_TX_EQ_SHIFT)
+#define TX_POSTCUR_SMASK (TX_POSTCUR_MASK << TX_POSTCUR_SHIFT)
+
+#define QSFP_RX_CDR_APPLY_SHIFT 0
+#define QSFP_RX_EMP_APPLY_SHIFT 1
+#define QSFP_RX_AMP_APPLY_SHIFT 2
+#define QSFP_RX_CDR_SHIFT 3
+#define QSFP_RX_EMP_SHIFT 4
+#define QSFP_RX_AMP_SHIFT 8
+
+#define QSFP_RX_CDR_APPLY_MASK 0x1UL
+#define QSFP_RX_EMP_APPLY_MASK 0x1UL
+#define QSFP_RX_AMP_APPLY_MASK 0x1UL
+#define QSFP_RX_CDR_MASK 0x1UL
+#define QSFP_RX_EMP_MASK 0xFUL
+#define QSFP_RX_AMP_MASK 0x3UL
+
+#define QSFP_RX_CDR_APPLY_SMASK (QSFP_RX_CDR_APPLY_MASK << \
+ QSFP_RX_CDR_APPLY_SHIFT)
+#define QSFP_RX_EMP_APPLY_SMASK (QSFP_RX_EMP_APPLY_MASK << \
+ QSFP_RX_EMP_APPLY_SHIFT)
+#define QSFP_RX_AMP_APPLY_SMASK (QSFP_RX_AMP_APPLY_MASK << \
+ QSFP_RX_AMP_APPLY_SHIFT)
+#define QSFP_RX_CDR_SMASK (QSFP_RX_CDR_MASK << QSFP_RX_CDR_SHIFT)
+#define QSFP_RX_EMP_SMASK (QSFP_RX_EMP_MASK << QSFP_RX_EMP_SHIFT)
+#define QSFP_RX_AMP_SMASK (QSFP_RX_AMP_MASK << QSFP_RX_AMP_SHIFT)
+
+#define BITMAP_VERSION 1
+#define BITMAP_VERSION_SHIFT 44
+#define BITMAP_VERSION_MASK 0xFUL
+#define BITMAP_VERSION_SMASK (BITMAP_VERSION_MASK << \
+ BITMAP_VERSION_SHIFT)
+#define CHECKSUM_SHIFT 48
+#define CHECKSUM_MASK 0xFFFFUL
+#define CHECKSUM_SMASK (CHECKSUM_MASK << CHECKSUM_SHIFT)
+
/* platform.c */
void get_platform_config(struct hfi1_devdata *dd);
void free_platform_config(struct hfi1_devdata *dd);
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 09/12] IB/hfi1: Remove leftover snoop references
From: Dennis Dalessandro @ 2016-10-17 11:19 UTC (permalink / raw)
To: dledford-H+wXaHxf7aLQT0dZR+AlfA
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, Dean Luick
In-Reply-To: <20161017103326.7934.21558.stgit-9QXIwq+3FY+1XWohqUldA0EOCMrvLtNR@public.gmane.org>
A few snoop related variables were missed in the snoop/capture removal
to get out of staging. Go back and clean those up too.
Reviewed-by: Dean Luick <dean.luick-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/hw/hfi1/chip.c | 18 +---------
drivers/infiniband/hw/hfi1/hfi.h | 40 +---------------------
drivers/infiniband/hw/hfi1/trace_rx.h | 60 ---------------------------------
3 files changed, 4 insertions(+), 114 deletions(-)
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index a0f05d7..bf645e9 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -6301,19 +6301,8 @@ void set_up_vl15(struct hfi1_devdata *dd, u8 vau, u16 vl15buf)
/* leave shared count at zero for both global and VL15 */
write_global_credit(dd, vau, vl15buf, 0);
- /* We may need some credits for another VL when sending packets
- * with the snoop interface. Dividing it down the middle for VL15
- * and VL0 should suffice.
- */
- if (unlikely(dd->hfi1_snoop.mode_flag == HFI1_PORT_SNOOP_MODE)) {
- write_csr(dd, SEND_CM_CREDIT_VL15, (u64)(vl15buf >> 1)
- << SEND_CM_CREDIT_VL15_DEDICATED_LIMIT_VL_SHIFT);
- write_csr(dd, SEND_CM_CREDIT_VL, (u64)(vl15buf >> 1)
- << SEND_CM_CREDIT_VL_DEDICATED_LIMIT_VL_SHIFT);
- } else {
- write_csr(dd, SEND_CM_CREDIT_VL15, (u64)vl15buf
- << SEND_CM_CREDIT_VL15_DEDICATED_LIMIT_VL_SHIFT);
- }
+ write_csr(dd, SEND_CM_CREDIT_VL15, (u64)vl15buf
+ << SEND_CM_CREDIT_VL15_DEDICATED_LIMIT_VL_SHIFT);
}
/*
@@ -9915,9 +9904,6 @@ static void set_lidlmc(struct hfi1_pportdata *ppd)
u32 mask = ~((1U << ppd->lmc) - 1);
u64 c1 = read_csr(ppd->dd, DCC_CFG_PORT_CONFIG1);
- if (dd->hfi1_snoop.mode_flag)
- dd_dev_info(dd, "Set lid/lmc while snooping");
-
c1 &= ~(DCC_CFG_PORT_CONFIG1_TARGET_DLID_SMASK
| DCC_CFG_PORT_CONFIG1_DLID_MASK_SMASK);
c1 |= ((ppd->lid & DCC_CFG_PORT_CONFIG1_TARGET_DLID_MASK)
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 94cc5f2..1453c5c 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -367,26 +367,6 @@ struct hfi1_packet {
u8 etype;
};
-/*
- * Private data for snoop/capture support.
- */
-struct hfi1_snoop_data {
- int mode_flag;
- struct cdev cdev;
- struct device *class_dev;
- /* protect snoop data */
- spinlock_t snoop_lock;
- struct list_head queue;
- wait_queue_head_t waitq;
- void *filter_value;
- int (*filter_callback)(void *hdr, void *data, void *value);
- u64 dcc_cfg; /* saved value of DCC Cfg register */
-};
-
-/* snoop mode_flag values */
-#define HFI1_PORT_SNOOP_MODE 1U
-#define HFI1_PORT_CAPTURE_MODE 2U
-
struct rvt_sge_state;
/*
@@ -1094,8 +1074,6 @@ struct hfi1_devdata {
char *portcntrnames;
size_t portcntrnameslen;
- struct hfi1_snoop_data hfi1_snoop;
-
struct err_info_rcvport err_info_rcvport;
struct err_info_constraint err_info_rcv_constraint;
struct err_info_constraint err_info_xmit_constraint;
@@ -1133,8 +1111,8 @@ struct hfi1_devdata {
u64 lcb_err_en;
/*
- * Handlers for outgoing data so that snoop/capture does not
- * have to have its hooks in the send path
+ * Capability to have different send engines simply by changing a
+ * pointer value.
*/
send_routine process_pio_send ____cacheline_aligned_in_smp;
send_routine process_dma_send;
@@ -1238,8 +1216,6 @@ struct hfi1_devdata *hfi1_lookup(int unit);
extern u32 hfi1_cpulist_count;
extern unsigned long *hfi1_cpulist;
-extern unsigned int snoop_drop_send;
-extern unsigned int snoop_force_capture;
int hfi1_init(struct hfi1_devdata *, int);
int hfi1_count_units(int *npresentp, int *nupp);
int hfi1_count_active_units(void);
@@ -1574,13 +1550,6 @@ void set_up_vl15(struct hfi1_devdata *dd, u8 vau, u16 vl15buf);
void reset_link_credits(struct hfi1_devdata *dd);
void assign_remote_cm_au_table(struct hfi1_devdata *dd, u8 vcu);
-int snoop_recv_handler(struct hfi1_packet *packet);
-int snoop_send_dma_handler(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
- u64 pbc);
-int snoop_send_pio_handler(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
- u64 pbc);
-void snoop_inline_pio_send(struct hfi1_devdata *dd, struct pio_buf *pbuf,
- u64 pbc, const void *from, size_t count);
int set_buffer_control(struct hfi1_pportdata *ppd, struct buffer_control *bc);
static inline struct hfi1_devdata *dd_from_ppd(struct hfi1_pportdata *ppd)
@@ -1827,8 +1796,6 @@ int kdeth_process_expected(struct hfi1_packet *packet);
int kdeth_process_eager(struct hfi1_packet *packet);
int process_receive_invalid(struct hfi1_packet *packet);
-extern rhf_rcv_function_ptr snoop_rhf_rcv_functions[8];
-
void update_sge(struct rvt_sge_state *ss, u32 length);
/* global module parameter variables */
@@ -1855,9 +1822,6 @@ extern struct mutex hfi1_mutex;
#define DRIVER_NAME "hfi1"
#define HFI1_USER_MINOR_BASE 0
#define HFI1_TRACE_MINOR 127
-#define HFI1_DIAGPKT_MINOR 128
-#define HFI1_DIAG_MINOR_BASE 129
-#define HFI1_SNOOP_CAPTURE_BASE 200
#define HFI1_NMINORS 255
#define PCI_VENDOR_ID_INTEL 0x8086
diff --git a/drivers/infiniband/hw/hfi1/trace_rx.h b/drivers/infiniband/hw/hfi1/trace_rx.h
index 11e02b2..f77e59f 100644
--- a/drivers/infiniband/hw/hfi1/trace_rx.h
+++ b/drivers/infiniband/hw/hfi1/trace_rx.h
@@ -253,66 +253,6 @@ TRACE_EVENT(hfi1_mmu_invalidate,
)
);
-#define SNOOP_PRN \
- "slid %.4x dlid %.4x qpn 0x%.6x opcode 0x%.2x,%s " \
- "svc lvl %d pkey 0x%.4x [header = %d bytes] [data = %d bytes]"
-
-TRACE_EVENT(snoop_capture,
- TP_PROTO(struct hfi1_devdata *dd,
- int hdr_len,
- struct ib_header *hdr,
- int data_len,
- void *data),
- TP_ARGS(dd, hdr_len, hdr, data_len, data),
- TP_STRUCT__entry(
- DD_DEV_ENTRY(dd)
- __field(u16, slid)
- __field(u16, dlid)
- __field(u32, qpn)
- __field(u8, opcode)
- __field(u8, sl)
- __field(u16, pkey)
- __field(u32, hdr_len)
- __field(u32, data_len)
- __field(u8, lnh)
- __dynamic_array(u8, raw_hdr, hdr_len)
- __dynamic_array(u8, raw_pkt, data_len)
- ),
- TP_fast_assign(
- struct ib_other_headers *ohdr;
-
- __entry->lnh = (u8)(be16_to_cpu(hdr->lrh[0]) & 3);
- if (__entry->lnh == HFI1_LRH_BTH)
- ohdr = &hdr->u.oth;
- else
- ohdr = &hdr->u.l.oth;
- DD_DEV_ASSIGN(dd);
- __entry->slid = be16_to_cpu(hdr->lrh[3]);
- __entry->dlid = be16_to_cpu(hdr->lrh[1]);
- __entry->qpn = be32_to_cpu(ohdr->bth[1]) & RVT_QPN_MASK;
- __entry->opcode = (be32_to_cpu(ohdr->bth[0]) >> 24) & 0xff;
- __entry->sl = (u8)(be16_to_cpu(hdr->lrh[0]) >> 4) & 0xf;
- __entry->pkey = be32_to_cpu(ohdr->bth[0]) & 0xffff;
- __entry->hdr_len = hdr_len;
- __entry->data_len = data_len;
- memcpy(__get_dynamic_array(raw_hdr), hdr, hdr_len);
- memcpy(__get_dynamic_array(raw_pkt), data, data_len);
- ),
- TP_printk(
- "[%s] " SNOOP_PRN,
- __get_str(dev),
- __entry->slid,
- __entry->dlid,
- __entry->qpn,
- __entry->opcode,
- show_ib_opcode(__entry->opcode),
- __entry->sl,
- __entry->pkey,
- __entry->hdr_len,
- __entry->data_len
- )
-);
-
#endif /* __HFI1_TRACE_RX_H */
#undef TRACE_INCLUDE_PATH
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 10/12] IB/hfi1: Clean up unused argument
From: Dennis Dalessandro @ 2016-10-17 11:19 UTC (permalink / raw)
To: dledford-H+wXaHxf7aLQT0dZR+AlfA
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, Easwar Hariharan
In-Reply-To: <20161017103326.7934.21558.stgit-9QXIwq+3FY+1XWohqUldA0EOCMrvLtNR@public.gmane.org>
From: Easwar Hariharan <easwar.hariharan-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
hfi1_pcie_ddinit takes the PCI device id as an argument but never
uses it. Clean it up.
Reviewed-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Easwar Hariharan <easwar.hariharan-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/hw/hfi1/chip.c | 2 +-
drivers/infiniband/hw/hfi1/hfi.h | 3 +--
drivers/infiniband/hw/hfi1/pcie.c | 3 +--
3 files changed, 3 insertions(+), 5 deletions(-)
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index bf645e9..3371361 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -14449,7 +14449,7 @@ struct hfi1_devdata *hfi1_init_dd(struct pci_dev *pdev,
* Any error printing is already done by the init code.
* On return, we have the chip mapped.
*/
- ret = hfi1_pcie_ddinit(dd, pdev, ent);
+ ret = hfi1_pcie_ddinit(dd, pdev);
if (ret < 0)
goto bail_free;
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 1453c5c..6f05f68 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -1760,8 +1760,7 @@ int qsfp_dump(struct hfi1_pportdata *ppd, char *buf, int len);
int hfi1_pcie_init(struct pci_dev *, const struct pci_device_id *);
void hfi1_pcie_cleanup(struct pci_dev *);
-int hfi1_pcie_ddinit(struct hfi1_devdata *, struct pci_dev *,
- const struct pci_device_id *);
+int hfi1_pcie_ddinit(struct hfi1_devdata *, struct pci_dev *);
void hfi1_pcie_ddcleanup(struct hfi1_devdata *);
void hfi1_pcie_flr(struct hfi1_devdata *);
int pcie_speeds(struct hfi1_devdata *);
diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c
index 89c68da..4ac8f33 100644
--- a/drivers/infiniband/hw/hfi1/pcie.c
+++ b/drivers/infiniband/hw/hfi1/pcie.c
@@ -157,8 +157,7 @@ void hfi1_pcie_cleanup(struct pci_dev *pdev)
* fields required to re-initialize after a chip reset, or for
* various other purposes
*/
-int hfi1_pcie_ddinit(struct hfi1_devdata *dd, struct pci_dev *pdev,
- const struct pci_device_id *ent)
+int hfi1_pcie_ddinit(struct hfi1_devdata *dd, struct pci_dev *pdev)
{
unsigned long len;
resource_size_t addr;
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 11/12] IB/hfi1: Delete unused lock
From: Dennis Dalessandro @ 2016-10-17 11:20 UTC (permalink / raw)
To: dledford-H+wXaHxf7aLQT0dZR+AlfA
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, Mike Marciniszyn,
Easwar Hariharan
In-Reply-To: <20161017103326.7934.21558.stgit-9QXIwq+3FY+1XWohqUldA0EOCMrvLtNR@public.gmane.org>
From: Easwar Hariharan <easwar.hariharan-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
The lock is an unused vestige from qib. Remove it.
Reviewed-by: Mike Marciniszyn <mike.marciniszyn-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Easwar Hariharan <easwar.hariharan-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/hw/hfi1/hfi.h | 2 --
drivers/infiniband/hw/hfi1/init.c | 1 -
2 files changed, 0 insertions(+), 3 deletions(-)
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 6f05f68..1707334 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -605,8 +605,6 @@ struct hfi1_pportdata {
struct mutex hls_lock;
u32 host_link_state;
- spinlock_t sdma_alllock ____cacheline_aligned_in_smp;
-
u32 lstate; /* logical link state */
/* these are the "32 bit" regs */
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 4a7e741..c317e69 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -507,7 +507,6 @@ void hfi1_init_pportdata(struct pci_dev *pdev, struct hfi1_pportdata *ppd,
INIT_WORK(&ppd->qsfp_info.qsfp_work, qsfp_event);
mutex_init(&ppd->hls_lock);
- spin_lock_init(&ppd->sdma_alllock);
spin_lock_init(&ppd->qsfp_info.qsfp_lock);
ppd->qsfp_info.ppd = ppd;
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 12/12] IB/hfi1: Fix rnr_timer addition
From: Dennis Dalessandro @ 2016-10-17 11:20 UTC (permalink / raw)
To: dledford; +Cc: linux-rdma, Mike Marciniszyn, Ira Weiny, stable
In-Reply-To: <20161017103326.7934.21558.stgit@scvm10.sc.intel.com>
From: Ira Weiny <ira.weiny@intel.com>
The new s_rnr_timeout was not properly being set and the code was
incorrectly setting a different timer.
Found by code inspection.
Cc: <stable@vger.kernel.org> # 4.7.x
Fixes: 08279d5c9424 ("staging/rdma/hfi1: use new RNR timer")
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
---
drivers/infiniband/hw/hfi1/rc.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c
index 8bc5013..83198a8 100644
--- a/drivers/infiniband/hw/hfi1/rc.c
+++ b/drivers/infiniband/hw/hfi1/rc.c
@@ -89,7 +89,7 @@ void hfi1_add_rnr_timer(struct rvt_qp *qp, u32 to)
lockdep_assert_held(&qp->s_lock);
qp->s_flags |= RVT_S_WAIT_RNR;
- qp->s_timer.expires = jiffies + usecs_to_jiffies(to);
+ priv->s_rnr_timer.expires = jiffies + usecs_to_jiffies(to);
add_timer(&priv->s_rnr_timer);
}
^ permalink raw reply related
* Re: 【For help】 some tips for upstream the userspace driver code of hns_roce
From: oulijun @ 2016-10-17 11:29 UTC (permalink / raw)
To: Leon Romanovsky; +Cc: Doug Ledford, Linuxarm, linux-rdma
In-Reply-To: <20161013093659.GA9282-2ukJVAZIZ/Y@public.gmane.org>
在 2016/10/13 17:36, Leon Romanovsky 写道:
> On Thu, Oct 13, 2016 at 04:09:46PM +0800, oulijun wrote:
>> Hi, Doug Ledford
>> Now, I am preparing for upstreaming the userspace driver code of hns_roce. But, we have
>> some difficulty how to upstream it. for example,
>> i) which branch of ofed should we upstream ?
>> ii) if want to upstream the userspace driver of hns_roce successfully, how we should do?
>>
>> Can you give me some guides?
>
> Hi Lijun,
>
> Our main library for all user-space stack is located at github [1].
> Please see similar question from Ram [2] and Jason's response [3] to it.
>
> [1] github.com/linux-rdma/rdma-core
> [2[ http://marc.info/?l=linux-rdma&m=147574131706820&w=2
> [3] http://marc.info/?l=linux-rdma&m=147577168016989&w=2
>
> Thanks.
>
>>
>> thanks
>> Lijun Ou
>>
Hi, leon
if i will upstream the patch for user-space code, how to guarantee the code format satisfied the rdma-core.git?
As is known to all, the kernel driver code will be checked by checkpatch.pl, the rdma-core.git also use the
checkpatch.pl script?
thanks
>> --
>> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
>> the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
>> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH net-next 02/11] net: Introduce new api for walking upper and lower devices
From: Stephen Hemminger @ 2016-10-17 12:21 UTC (permalink / raw)
To: David Ahern
Cc: jiri-VPRAkNaXOzVWk0Htik3J/w, netdev-u79uwXL29TY76Z2rM5mHXA,
davem-fT/PcQaiUtIeIZ0/mPfg9Q, dledford-H+wXaHxf7aLQT0dZR+AlfA,
sean.hefty-ral2JQCrhuEAvxtiuMwx3w,
hal.rosenstock-Re5JQEeQqe8AvxtiuMwx3w,
linux-rdma-u79uwXL29TY76Z2rM5mHXA,
j.vosburgh-Re5JQEeQqe8AvxtiuMwx3w, vfalico-Re5JQEeQqe8AvxtiuMwx3w,
andy-QlMahl40kYEqcZcGjlUOXw,
jeffrey.t.kirsher-ral2JQCrhuEAvxtiuMwx3w,
intel-wired-lan-qjLDD68F18P21nG7glBr7A
In-Reply-To: <1476494931-31813-3-git-send-email-dsa-qUQiAmfTcIp+XZJcv9eMoEEOCMrvLtNR@public.gmane.org>
On Fri, 14 Oct 2016 18:28:42 -0700
David Ahern <dsa-qUQiAmfTcIp+XZJcv9eMoEEOCMrvLtNR@public.gmane.org> wrote:
>
> /**
> + * netdev_has_upper_dev_all - Check if device is linked to an upper device
> + * @dev: device
> + * @upper_dev: upper device to check
> + *
> + * Find out if a device is linked to specified upper device and return true
> + * in case it is. Note that this checks the entire upper device chain.
> + * The caller must hold rcu lock.
> + */
> +
> +static int __netdev_has_upper_dev(struct net_device *upper_dev, void *data)
> +{
> + struct net_device *dev = (struct net_device *)data;
> +
> + if (upper_dev == dev)
> + return 1;
> +
> + return 0;
> +}
> +
> +bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
> + struct net_device *upper_dev)
> +{
> + if (netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev,
> + upper_dev))
> + return true;
> +
> + return false;
> +}
> +EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu);
You should write this more succinctly as:
static bool __netdev_has_upper_dev(struct net_device *upper_dev, void *data)
{
struct net_device *dev = data;
return upper_dev == dev;
}
bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
struct net_device *upper_dev)
{
return netdev_walk_all_upper_dev_rcu(dev,
__netdev_has_upper_dev, upper_dev);
}
No if/else needed. No cast of void * ptr need. Use const if possible?
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH net-next 02/11] net: Introduce new api for walking upper and lower devices
From: David Miller @ 2016-10-17 14:42 UTC (permalink / raw)
To: stephen
Cc: dsa, jiri, netdev, dledford, sean.hefty, hal.rosenstock,
linux-rdma, j.vosburgh, vfalico, andy, jeffrey.t.kirsher,
intel-wired-lan
In-Reply-To: <20161017052121.2322279d@xeon-e3>
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Mon, 17 Oct 2016 05:21:21 -0700
> You should write this more succinctly as:
>
> static bool __netdev_has_upper_dev(struct net_device *upper_dev, void *data)
> {
> struct net_device *dev = data;
>
> return upper_dev == dev;
> }
>
> bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
> struct net_device *upper_dev)
> {
> return netdev_walk_all_upper_dev_rcu(dev,
> __netdev_has_upper_dev, upper_dev);
> }
>
> No if/else needed. No cast of void * ptr need. Use const if possible?
Agreed.
^ permalink raw reply
* RE: [PATCH rdma-core 3/8] verbs: Use cmake to detect if net/if.h vs netling/route/link.h is broken
From: Steve Wise @ 2016-10-17 14:48 UTC (permalink / raw)
To: 'Jason Gunthorpe', 'Doug Ledford',
linux-rdma-u79uwXL29TY76Z2rM5mHXA
Cc: 'Christoph Hellwig', 'Sean Hefty'
In-Reply-To: <1476483257-16308-4-git-send-email-jgunthorpe-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
> Subject: [PATCH rdma-core 3/8] verbs: Use cmake to detect if net/if.h vs
> netling/route/link.h is broken
nit: netling -> netlink
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH 1/2] rds: Remove unused rds_conn_error
From: David Miller @ 2016-10-17 15:07 UTC (permalink / raw)
To: joe; +Cc: santosh.shilimkar, netdev, linux-rdma, rds-devel, linux-kernel
In-Reply-To: <01fddf3af8f7757d0e79e4f25d7eb8b246e3d695.1476557523.git.joe@perches.com>
From: Joe Perches <joe@perches.com>
Date: Sat, 15 Oct 2016 11:53:21 -0700
> This macro's last use was removed in commit d769ef81d5b59
> ("RDS: Update rds_conn_shutdown to work with rds_conn_path")
> so make the macro and the __rds_conn_error function definition
> and declaration disappear.
>
> Signed-off-by: Joe Perches <joe@perches.com>
Applied.
^ permalink raw reply
* Re: [PATCH 2/2] rds: Remove duplicate prefix from rds_conn_path_error use
From: David Miller @ 2016-10-17 15:07 UTC (permalink / raw)
To: joe; +Cc: santosh.shilimkar, netdev, linux-rdma, rds-devel, linux-kernel
In-Reply-To: <832b0d2c1b31c10db7692f65f1ba77e779db15e1.1476557523.git.joe@perches.com>
From: Joe Perches <joe@perches.com>
Date: Sat, 15 Oct 2016 11:53:22 -0700
> rds_conn_path_error already prefixes "RDS:" to the output.
>
> Signed-off-by: Joe Perches <joe@perches.com>
Applied.
^ permalink raw reply
* [PATCH] IB/fmr_pool: Convert the cleanup thread into kthread worker API
From: Petr Mladek @ 2016-10-17 15:39 UTC (permalink / raw)
To: Doug Ledford
Cc: Sean Hefty, Hal Rosenstock, linux-rdma-u79uwXL29TY76Z2rM5mHXA,
Tejun Heo, linux-kernel-u79uwXL29TY76Z2rM5mHXA, Petr Mladek
Kthreads are currently implemented as an infinite loop. Each
has its own variant of checks for terminating, freezing,
awakening. In many cases it is unclear to say in which state
it is and sometimes it is done a wrong way.
The plan is to convert kthreads into kthread_worker or workqueues
API. It allows to split the functionality into separate operations.
It helps to make a better structure. Also it defines a clean state
where no locks are taken, IRQs blocked, the kthread might sleep
or even be safely migrated.
The kthread worker API is useful when we want to have a dedicated
single thread for the work. It helps to make sure that it is
available when needed. Also it allows a better control, e.g.
define a scheduling priority.
This patch converts the frm_pool kthread into the kthread worker
API because I am not sure how busy the thread is. It is well
possible that it does not need a dedicated kthread and workqueues
would be perfectly fine. Well, the conversion between kthread
worker API and workqueues is pretty trivial.
The patch moves one iteration from the kthread into the work function.
It is queued only when there is a pending work. Therefore we do not
need to compare flush_ser and req_ser at the beginning. On the contrary,
the same work could be queued only once at a time. Therefore it has to
re-queue itself if some requests are pending.
Otherwise, wake_up_process() is replaced by queuing the work.
Important: The change is only compile tested. I did not find an easy
way how to check it in a real life.
Signed-off-by: Petr Mladek <pmladek-IBi9RG/b67k@public.gmane.org>
TO: Doug Ledford <dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
CC: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
CC: Hal Rosenstock <hal.rosenstock-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
CC: linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
---
The kthread worker API improvements are in 4.9-rc1. Therefore
we could finally start converting kthreads that fit this API.
drivers/infiniband/core/fmr_pool.c | 49 +++++++++++++++-----------------------
1 file changed, 19 insertions(+), 30 deletions(-)
diff --git a/drivers/infiniband/core/fmr_pool.c b/drivers/infiniband/core/fmr_pool.c
index cdbb1f1a6d97..5ec8cf398d02 100644
--- a/drivers/infiniband/core/fmr_pool.c
+++ b/drivers/infiniband/core/fmr_pool.c
@@ -96,7 +96,8 @@ struct ib_fmr_pool {
void * arg);
void *flush_arg;
- struct task_struct *thread;
+ struct kthread_worker *worker;
+ struct kthread_work work;
atomic_t req_ser;
atomic_t flush_ser;
@@ -174,29 +175,19 @@ static void ib_fmr_batch_release(struct ib_fmr_pool *pool)
spin_unlock_irq(&pool->pool_lock);
}
-static int ib_fmr_cleanup_thread(void *pool_ptr)
+static void ib_fmr_cleanup_func(struct kthread_work *work)
{
- struct ib_fmr_pool *pool = pool_ptr;
+ struct ib_fmr_pool *pool = container_of(work, struct ib_fmr_pool, work);
- do {
- if (atomic_read(&pool->flush_ser) - atomic_read(&pool->req_ser) < 0) {
- ib_fmr_batch_release(pool);
-
- atomic_inc(&pool->flush_ser);
- wake_up_interruptible(&pool->force_wait);
-
- if (pool->flush_function)
- pool->flush_function(pool, pool->flush_arg);
- }
+ ib_fmr_batch_release(pool);
+ atomic_inc(&pool->flush_ser);
+ wake_up_interruptible(&pool->force_wait);
- set_current_state(TASK_INTERRUPTIBLE);
- if (atomic_read(&pool->flush_ser) - atomic_read(&pool->req_ser) >= 0 &&
- !kthread_should_stop())
- schedule();
- __set_current_state(TASK_RUNNING);
- } while (!kthread_should_stop());
+ if (pool->flush_function)
+ pool->flush_function(pool, pool->flush_arg);
- return 0;
+ if (atomic_read(&pool->flush_ser) - atomic_read(&pool->req_ser) < 0)
+ kthread_queue_work(pool->worker, &pool->work);
}
/**
@@ -266,15 +257,13 @@ struct ib_fmr_pool *ib_create_fmr_pool(struct ib_pd *pd,
atomic_set(&pool->flush_ser, 0);
init_waitqueue_head(&pool->force_wait);
- pool->thread = kthread_run(ib_fmr_cleanup_thread,
- pool,
- "ib_fmr(%s)",
- device->name);
- if (IS_ERR(pool->thread)) {
- pr_warn(PFX "couldn't start cleanup thread\n");
- ret = PTR_ERR(pool->thread);
+ pool->worker = kthread_create_worker(0, "ib_fmr(%s)", device->name);
+ if (IS_ERR(pool->worker)) {
+ pr_warn(PFX "couldn't start cleanup kthread worker\n");
+ ret = PTR_ERR(pool->worker);
goto out_free_pool;
}
+ kthread_init_work(&pool->work, ib_fmr_cleanup_func);
{
struct ib_pool_fmr *fmr;
@@ -339,7 +328,7 @@ void ib_destroy_fmr_pool(struct ib_fmr_pool *pool)
LIST_HEAD(fmr_list);
int i;
- kthread_stop(pool->thread);
+ kthread_destroy_worker(pool->worker);
ib_fmr_batch_release(pool);
i = 0;
@@ -389,7 +378,7 @@ int ib_flush_fmr_pool(struct ib_fmr_pool *pool)
spin_unlock_irq(&pool->pool_lock);
serial = atomic_inc_return(&pool->req_ser);
- wake_up_process(pool->thread);
+ kthread_queue_work(pool->worker, &pool->work);
if (wait_event_interruptible(pool->force_wait,
atomic_read(&pool->flush_ser) - serial >= 0))
@@ -503,7 +492,7 @@ int ib_fmr_pool_unmap(struct ib_pool_fmr *fmr)
list_add_tail(&fmr->list, &pool->dirty_list);
if (++pool->dirty_len >= pool->dirty_watermark) {
atomic_inc(&pool->req_ser);
- wake_up_process(pool->thread);
+ kthread_queue_work(pool->worker, &pool->work);
}
}
}
--
1.8.5.6
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* Re: [PATCH rdma-core 0/4] rdma-core infrastructure
From: Jarod Wilson @ 2016-10-17 15:43 UTC (permalink / raw)
To: Jason Gunthorpe; +Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <20161014223308.GA16509-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
On Fri, Oct 14, 2016 at 04:33:08PM -0600, Jason Gunthorpe wrote:
> On Fri, Oct 14, 2016 at 03:21:32PM -0400, Jarod Wilson wrote:
> > This is a set of patches to make some minor changes to the stock spec file,
> > add a bunch of userspace glue that Red Hat has been shipping on it's own in
> > Red Hat Enterprise Linux and Fedora for a while now, and a revised split
> > package spec file that we're likely to use in at least RHEL, to preserve the
> > current packaging split.
>
> Is this just for EL7, or do you plan to keep going this way
> indefinitely in EL8 and FC25?
Kind of TBD at the moment. We could probably go either way for Fedora and
a new EL major release.
--
Jarod Wilson
jarod-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH rdma-core 0/4] rdma-core infrastructure
From: Jarod Wilson @ 2016-10-17 15:51 UTC (permalink / raw)
To: Leon Romanovsky; +Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <20161015092619.GJ9282-2ukJVAZIZ/Y@public.gmane.org>
On Sat, Oct 15, 2016 at 12:26:19PM +0300, Leon Romanovsky wrote:
> On Fri, Oct 14, 2016 at 03:21:32PM -0400, Jarod Wilson wrote:
> > This is a set of patches to make some minor changes to the stock spec file,
> > add a bunch of userspace glue that Red Hat has been shipping on it's own in
> > Red Hat Enterprise Linux and Fedora for a while now, and a revised split
> > package spec file that we're likely to use in at least RHEL, to preserve the
> > current packaging split.
>
> Jarod,
>
> I'm far a way from packaging, so I have very general questions.
> 1. You mentioned FC, but used glue/redhat/. Is it applicable for Centos?
Red Hat is the driving force behind Red Hat Enterprise Linux, CentOS (or
any other clone) and Fedora, so it would generally be applicable for all
of them, similar to how the 'debian' stuff is generally applicable to
derivatives like ubuntu as well.
> 2. Do FC and Centos need similar files in structure?
For the most part, they should be identical.
> 3. Does it make sense to rename glue/ to be packages/ and move debian there?
That, or as Jason has suggested, just have a top-level redhat directory,
same as the debian one. Don't really care much what it's called, just as
long as we can get (at least most of) this stuff into the tree, rather
than having it lingering in our own special package.
--
Jarod Wilson
jarod-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH rdma-core 1/4] rpm spec: install documentation too
From: Jarod Wilson @ 2016-10-17 15:53 UTC (permalink / raw)
To: Jason Gunthorpe; +Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <20161014225204.GB16509-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
On Fri, Oct 14, 2016 at 04:52:04PM -0600, Jason Gunthorpe wrote:
> On Fri, Oct 14, 2016 at 03:21:33PM -0400, Jarod Wilson wrote:
> > At least in the Red Hat world, we like to install the documentation files
> > provided in a given source tree.
>
> I think other distros would like to do this too, can you use this
> patch instead?
Ah. Yeah. My cmake-fu is ... lacking. That does look like a better way to
go. I'll pull this into my working tree and play with it.
> From a23838ccc05574b1975741770abcbd66f7587293 Mon Sep 17 00:00:00 2001
> From: Jarod Wilson <jarod-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
> Date: Fri, 14 Oct 2016 15:21:33 -0400
> Subject: [PATCH] Install end user focused documentation files
>
> We recommend that all distros ship these.
>
> Suggested-by: Jarod Wilson <jarod-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
> Signed-off-by: Jason Gunthorpe <jgunthorpe-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
> ---
> CMakeLists.txt | 3 ++-
> Documentation/CMakeLists.txt | 8 ++++++++
> debian/ibacm.install | 1 +
> debian/ibverbs-providers.install | 1 +
> debian/libibcm1.install | 1 +
> debian/libibverbs1.install | 1 +
> debian/librdmacm1.install | 1 +
> debian/srptools.install | 1 +
> rdma-core.spec | 4 +++-
> 9 files changed, 19 insertions(+), 2 deletions(-)
> create mode 100644 Documentation/CMakeLists.txt
...
--
Jarod Wilson
jarod-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH 03/12] IB/hfi1: Fix an Oops on pci device force remove
From: Jason Gunthorpe @ 2016-10-17 16:07 UTC (permalink / raw)
To: Dennis Dalessandro
Cc: dledford-H+wXaHxf7aLQT0dZR+AlfA,
linux-rdma-u79uwXL29TY76Z2rM5mHXA, Dean Luick, Ira Weiny,
Tadeusz Struk
In-Reply-To: <20161017111918.7934.72325.stgit-9QXIwq+3FY+1XWohqUldA0EOCMrvLtNR@public.gmane.org>
On Mon, Oct 17, 2016 at 04:19:19AM -0700, Dennis Dalessandro wrote:
> @@ -183,6 +183,7 @@ static int hfi1_file_open(struct inode *inode, struct file *fp)
> fd->rec_cpu_num = -1; /* no cpu affinity by default */
> fd->mm = current->mm;
> atomic_inc(&fd->mm->mm_count);
> + atomic_inc(&dd->user_refcount);
This doesn't look like enough locking on acquire.. What prevents the
driver from already having been unloaded at this point?
> +static void wait_for_clients(struct hfi1_devdata *dd)
> +{
> + /*
> + * Remove the device init value and wait for active
> + * users to finish if there are any.
> + */
> + if (atomic_sub_return(1, &dd->user_refcount))
> + wait_for_completion(&dd->user_comp);
> +}
Shouldn't this be a while loop to avoid races?
.. and shouldn't the inc 'latch off' once the removal process starts?
I think you need to study how kernfs_drain is implemented and
basically copy that approach, including the locking.
FWIW, it is much easier and probably long term better to arrange
things so the FD can remain open but just return ENODEV to all calls.
Eg the srcu based approach in uverbs.
Jason
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH rdma-core 0/4] rdma-core infrastructure
From: Jason Gunthorpe @ 2016-10-17 16:11 UTC (permalink / raw)
To: Jarod Wilson; +Cc: Leon Romanovsky, linux-rdma-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <20161017155159.GG14983-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
On Mon, Oct 17, 2016 at 11:51:59AM -0400, Jarod Wilson wrote:
> > 3. Does it make sense to rename glue/ to be packages/ and move debian there?
>
> That, or as Jason has suggested, just have a top-level redhat directory,
> same as the debian one. Don't really care much what it's called, just as
> long as we can get (at least most of) this stuff into the tree, rather
> than having it lingering in our own special package.
The debian/ directory has to be top level for debian tools, so I'm
inclined to just follow the pattern and go with redhat/.
I think it is no problem to take what you have right away, but lets
try to move as much as is trivial/sensible into common places.
Maybe we can tackle the larger questions (eg systemd) later..
Jason
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH rdma-core 2/4] glue/redhat: add udev/systemd/etc infrastructure bits
From: Jarod Wilson @ 2016-10-17 16:22 UTC (permalink / raw)
To: Jason Gunthorpe; +Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, Doug Ledford
In-Reply-To: <20161014231934.GC16509-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
On Fri, Oct 14, 2016 at 05:19:34PM -0600, Jason Gunthorpe wrote:
> On Fri, Oct 14, 2016 at 03:21:34PM -0400, Jarod Wilson wrote:
> > Red Hat has been shipping an "rdma" package, as well as it's own systemd
> > unit files for some daemons for a while now, in both Fedora and Red Hat
> > Enterprise Linux. Some of these are fairly RH-specific, but might be of
> > use to others, so we'd like to move them into the upstream source tree.
>
> We have a directory called 'debian', so lets just have one called
> 'redhat'..
Worksforme. As mentioned in reply to Leon, I really don't care what the
directory is called, just that we get this stuff out there, instead of
being in our own custom glue package. I do think maybe Leon's suggestion
of having a directory to put a bunch of distro-specific directories under
would be good for cleanliness, but I also seem to recall that debian
actually looks for a directory in the root of the tarball, so it may need
to stay like it is.
> The below comments are my view on what we should try and move into
> common cross-distro locations..
I should have been more clear: some of this is just an initial dump of
everything we ship, and there's absolutely a desire to extract anything
from this pile that is generic and usable by all distros into a common
location. Just pressed for time, and sending it out this way was the
fastest way to get it in front of eyeballs. :)
> Common stuff should be installed via cmake
>
> > diff --git a/glue/redhat/ibacm.service b/glue/redhat/ibacm.service
> > new file mode 100644
> > index 0000000..1cd031a
> > +++ b/glue/redhat/ibacm.service
>
> Can we just put this in ibacm/ ?
Probably.
> > +Requires=rdma.service
> > +After=rdma.service opensm.service
>
> This is the only RH specific thiing I see.. Could we standardize on
> something here and use it on all distros? rdma-available.target?
I'll defer to what Doug said on this one.
> > +++ b/glue/redhat/iwpmd.service
> > @@ -0,0 +1,12 @@
> > +[Unit]
> > +Description=Starts the IWPMD daemon
> > +Documentation=file:///usr/share/doc/iwpmd/README
>
> File does not exit? There is a man page now
>
> We already have a iwpmd/iwpmd.service that is almost identical, can you
> you just update it and drop this version?
Bah, that's a carryover from our individually packaged iwpmd, didn't look
closely enough. Can we merge a bit from ours into the 'stock' one? The
main relevant difference I see is we have ours set to load after
syslog.target as well as network.target.
> > +++ b/glue/redhat/rdma.cxgb3.sys.modprobe
> > @@ -0,0 +1 @@
> > +install cxgb3 /sbin/modprobe --ignore-install cxgb3 $CMDLINE_OPTS && /sbin/modprobe iw_cxgb3
> > diff --git a/glue/redhat/rdma.cxgb4.sys.modprobe b/glue/redhat/rdma.cxgb4.sys.modprobe
> > new file mode 100644
> > index 0000000..44163ab
> > +++ b/glue/redhat/rdma.cxgb4.sys.modprobe
> > @@ -0,0 +1 @@
> > +install cxgb4 /sbin/modprobe --ignore-install cxgb4 $CMDLINE_OPTS && /sbin/modprobe iw_cxgb4
>
> What are these for? Should they be cross distro? Why are only a few
> drivers this special?
What Doug said.
> > +++ b/glue/redhat/rdma.fixup-mtrr.awk
> > @@ -0,0 +1,160 @@
> > +# This is a simple script that checks the contents of /proc/mtrr to see if
> > +# the BIOS maker for the computer took the easy way out in terms of
> > +# specifying memory regions when there is a hole below 4GB for PCI access
> > +# and the machine has 4GB or more of RAM. When the contents of /proc/mtrr
> > +# show a 4GB mapping of write-back cached RAM, minus punch out hole(s) of
> > +# uncacheable regions (the area reserved for PCI access), then it becomes
> > +# impossible for the ib_ipath driver to set write_combining on its PIO
> > +# buffers. To correct the problem, remap the lower memory region in various
> > +# chunks up to the start of the punch out hole(s), then delete the punch out
> > +# hole(s) entirely as they aren't needed any more. That way, ib_ipath will
> > +# be able to set write_combining on its PIO memory access region.
>
> Yuk, a thousand times yuk.
>
> I thought the mtrr cleanup built into modern kernel took care of this?
>
> Really though, this needs to be fixed upstream in the kernel :|
Yeah, this is still floating around for hysterical raisins, as Doug said.
We might be able to drop this, or at least relegate it to a dark corner
with a huge warning label...
> > diff --git a/glue/redhat/rdma.kernel-init b/glue/redhat/rdma.kernel-init
> > new file mode 100644
> > index 0000000..6cb4732
> > +++ b/glue/redhat/rdma.kernel-init
>
> I wonder if this could be split into a generic 'load the modules' part
> and a distro specific part? Every distro needs systemd to load the
> extra modules because out auto-loading is broken - IMHO, and that is
> pretty complex unfortunately.
Possibly. Not sure how much you'd save by splitting it though, the added
complexity of playing connect the dots to see how things come up could be
counter-productive. Haven't looked very closely at that though.
> > +errata_58()
> > +{
> > + # Check AMD chipset issue Errata #58
> > + if test -x /sbin/lspci && test -x /sbin/setpci; then
> > + if ( /sbin/lspci -nd 1022:1100 | grep "1100" > /dev/null ) &&
> > + ( /sbin/lspci -nd 1022:7450 | grep "7450" > /dev/null ) &&
> > + ( /sbin/lspci -nd 15b3:5a46 | grep "5a46" > /dev/null ); then
> > + CURVAL=`/sbin/setpci -d 1022:1100 69`
>
> Another yuk. Why isn't this handled upstream in drivers/pci/quirks.c
> with the rest of the 8131 errata?
>
> Fortunately I expect all 8131 hardware is long since gone, that chip
> was end-of-manufacturing'd very quickly 2003ish IIRC.
More hysterical raisins.
> > +++ b/glue/redhat/rdma.service
> > @@ -0,0 +1,15 @@
> > +[Unit]
> > +Description=Initialize the iWARP/InfiniBand/RDMA stack in the kernel
> > +Documentation=file:/etc/rdma/rdma.conf
> > +RefuseManualStop=true
> > +DefaultDependencies=false
> > +Conflicts=emergency.target emergency.service
> > +Before=network.target remote-fs-pre.target
>
> This is an area we really need to cross-distro standardize - we really
> need a set of rdma-*.targets.
>
> eg
> rdma-available.target
> - RDMA hardware is available and all prep is done
> opensm (if installed) is started, etc
> Use in place of rdma.service
> rdma-detected.target
> - udev detected rdma hardware
Deferring to Doug ehre too.
> > +++ b/glue/redhat/rdma.udev-ipoib-naming.rules
> > @@ -0,0 +1,13 @@
> > +# This is a sample udev rules file that demonstrates how to get udev to
> > +# set the name of IPoIB interfaces to whatever you wish. There is a
> > +# 16 character limit on network device names though, so don't go too nuts
> > +#
> > +# Important items to note: ATTR{type}=="32" is IPoIB interfaces, and the
> > +# ATTR{address} match must start with ?* and only reference the last 8
> > +# bytes of the address or else the address might not match on any given
> > +# start of the IPoIB stack
> > +#
> > +# Note: as of rhel7, udev is case sensitive on the address field match
> > +# and all addresses need to be in lower case.
> > +#
> > +# ACTION=="add", SUBSYSTEM=="net", DRIVERS=="?*", ATTR{type}=="32", ATTR{address}=="?*00:02:c9:03:00:31:78:f2", NAME="mlx4_ib3"
>
> This should be a cross distro file.
>
> > +++ b/glue/redhat/rdma.udev-rules
> > @@ -0,0 +1,18 @@
> > +# We list all the various kernel modules that drive hardware in the
> > +# InfiniBand stack (and a few in the network stack that might not actually
> > +# be RDMA capable, but we don't know that at this time and it's safe to
> > +# enable the IB stack, so do so unilaterally) and on load of any of that
> > +# hardware, we trigger the rdma.service load in systemd
> > +
> > +SUBSYSTEM=="module", KERNEL=="cxgb*", ACTION=="add", TAG+="systemd", ENV{SYSTEMD_WANTS}="rdma.service"
> > +SUBSYSTEM=="module", KERNEL=="ib_*", ACTION=="add", TAG+="systemd", ENV{SYSTEMD_WANTS}="rdma.service"
> > +SUBSYSTEM=="module", KERNEL=="mlx*", ACTION=="add", TAG+="systemd", ENV{SYSTEMD_WANTS}="rdma.service"
> > +SUBSYSTEM=="module", KERNEL=="iw_*", ACTION=="add", TAG+="systemd", ENV{SYSTEMD_WANTS}="rdma.service"
> > +SUBSYSTEM=="module", KERNEL=="be2net", ACTION=="add", TAG+="systemd", ENV{SYSTEMD_WANTS}="rdma.service"
> > +SUBSYSTEM=="module", KERNEL=="enic", ACTION=="add", TAG+="systemd", ENV{SYSTEMD_WANTS}="rdma.service"
>
> Also cross distro
Yeah, these are definitely prime candidates for being cross-distro. And
really, I was thinking maybe these should be part of the core upstream
udev/systemd rules set, rather than something we ship here.
> > +# When we detect a new verbs device is added to the system, set the node
> > +# description on that device
> > +# If rdma-ndd is installed, defer the setting of the node description to it.
> > +SUBSYSTEM=="infiniband", KERNEL=="*", ACTION=="add", TEST!="/usr/sbin/rdma-ndd", RUN+="/bin/bash -c 'sleep 1; echo -n `hostname -s` %k > /sys/class/infiniband/%k/node_desc'"
>
> Shouldn't this udev drop-in by in the rdma-ndd package?
Honestly don't even have a clue what rdma-ndd is. :) Don't remember what
Doug said about this one...
> > +++ b/glue/redhat/srp_daemon.service
> > @@ -0,0 +1,17 @@
> > +[Unit]
> > +Description=Start or stop the daemon that attaches to SRP devices
> > +Documentation=file:///etc/rdma/rdma.conf file:///etc/srp_daemon.conf
> > +DefaultDependencies=false
> > +Conflicts=emergency.target emergency.service
> > +Requires=rdma.service
> > +Wants=opensm.service
> > +After=rdma.service opensm.service
> > +After=network.target
> > +Before=remote-fs-pre.target
>
> Also should be common, why does it reference opensm.service?
>
> > +
> > +[Service]
> > +Type=simple
> > +ExecStart=/usr/sbin/srp_daemon.sh
>
> Hurm, someday we have to make better systemd integration for these
> daemons..
More deferrals to Doug!
--
Jarod Wilson
jarod-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH rdma-core 0/4] rdma-core infrastructure
From: Jarod Wilson @ 2016-10-17 16:26 UTC (permalink / raw)
To: Jason Gunthorpe; +Cc: Leon Romanovsky, linux-rdma-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <20161017161154.GB5679-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
On Mon, Oct 17, 2016 at 10:11:54AM -0600, Jason Gunthorpe wrote:
> On Mon, Oct 17, 2016 at 11:51:59AM -0400, Jarod Wilson wrote:
>
> > > 3. Does it make sense to rename glue/ to be packages/ and move debian there?
> >
> > That, or as Jason has suggested, just have a top-level redhat directory,
> > same as the debian one. Don't really care much what it's called, just as
> > long as we can get (at least most of) this stuff into the tree, rather
> > than having it lingering in our own special package.
>
> The debian/ directory has to be top level for debian tools, so I'm
> inclined to just follow the pattern and go with redhat/.
Okay, good, my vague recollection of that was correct.
> I think it is no problem to take what you have right away, but lets
> try to move as much as is trivial/sensible into common places.
I'm shuffling things around locally to redhat/ and have pulled in your
Docs install change. Want me to finish cleaning up, double-check that it
all builds, and ship a v2 set?
> Maybe we can tackle the larger questions (eg systemd) later..
Some of these issues might be better addressed once more distros have had
a chance to digest the new package and see what they still need. Entirely
possible others have a similar pile of glue for their distro, including
generic parts, and their generic parts are more polished than ours.
--
Jarod Wilson
jarod-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH 0/8] infiniband: Remove semaphores
From: Binoy Jayan @ 2016-10-17 16:30 UTC (permalink / raw)
To: Doug Ledford, Sean Hefty, Hal Rosenstock
Cc: Arnd Bergmann, linux-rdma, linux-kernel, Binoy Jayan
Hi,
These are a set of patches which removes semaphores from infiniband.
These are part of a bigger effort to eliminate all semaphores from the
linux kernel.
NB: A few semaphores which are counting ones are replaced with an open-coded
implementation by introducing a new type in 'include/rdma/ib_sa.h'. Need to
see if this can be programmed in a generic way using wait queues.
Thanks,
Binoy
Binoy Jayan (8):
IB/core: iwpm_nlmsg_request: Replace semaphore with completion
IB/core: Replace semaphore sm_sem with completion
IB/hns: Replace semaphore poll_sem with mutex
IB/mthca: Replace semaphore poll_sem with mutex
IB/isert: Replace semaphore sem with completion
IB/hns: Replace counting semaphore event_sem with wait condition
IB/mthca: Replace counting semaphore event_sem with wait condition
IB/mlx5: Replace counting semaphore sem with wait condition
drivers/infiniband/core/iwpm_msg.c | 8 ++++----
drivers/infiniband/core/iwpm_util.c | 7 +++----
drivers/infiniband/core/iwpm_util.h | 3 ++-
drivers/infiniband/core/user_mad.c | 14 ++++++++------
drivers/infiniband/hw/hns/hns_roce_cmd.c | 28 ++++++++++++++++++----------
drivers/infiniband/hw/hns/hns_roce_device.h | 6 ++++--
drivers/infiniband/hw/mlx5/main.c | 3 ++-
drivers/infiniband/hw/mlx5/mlx5_ib.h | 3 ++-
drivers/infiniband/hw/mlx5/mr.c | 28 +++++++++++++++++++---------
drivers/infiniband/hw/mthca/mthca_cmd.c | 22 +++++++++++++---------
drivers/infiniband/hw/mthca/mthca_cmd.h | 1 +
drivers/infiniband/hw/mthca/mthca_dev.h | 5 +++--
drivers/infiniband/ulp/isert/ib_isert.c | 6 +++---
drivers/infiniband/ulp/isert/ib_isert.h | 3 ++-
include/rdma/ib_sa.h | 5 +++++
15 files changed, 89 insertions(+), 53 deletions(-)
--
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project
^ permalink raw reply
* [PATCH 1/8] IB/core: iwpm_nlmsg_request: Replace semaphore with completion
From: Binoy Jayan @ 2016-10-17 16:30 UTC (permalink / raw)
To: Doug Ledford, Sean Hefty, Hal Rosenstock
Cc: Arnd Bergmann, linux-rdma-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA, Binoy Jayan
In-Reply-To: <1476721862-7070-1-git-send-email-binoy.jayan-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>
Semaphore sem in iwpm_nlmsg_request is used as completion, so
convert it to a struct completion type. Semaphores are going
away in the future.
Signed-off-by: Binoy Jayan <binoy.jayan-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>
---
drivers/infiniband/core/iwpm_msg.c | 8 ++++----
drivers/infiniband/core/iwpm_util.c | 7 +++----
drivers/infiniband/core/iwpm_util.h | 3 ++-
3 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c
index 1c41b95..761358f 100644
--- a/drivers/infiniband/core/iwpm_msg.c
+++ b/drivers/infiniband/core/iwpm_msg.c
@@ -394,7 +394,7 @@ int iwpm_register_pid_cb(struct sk_buff *skb, struct netlink_callback *cb)
/* always for found nlmsg_request */
kref_put(&nlmsg_request->kref, iwpm_free_nlmsg_request);
barrier();
- up(&nlmsg_request->sem);
+ complete(&nlmsg_request->comp);
return 0;
}
EXPORT_SYMBOL(iwpm_register_pid_cb);
@@ -463,7 +463,7 @@ int iwpm_add_mapping_cb(struct sk_buff *skb, struct netlink_callback *cb)
/* always for found request */
kref_put(&nlmsg_request->kref, iwpm_free_nlmsg_request);
barrier();
- up(&nlmsg_request->sem);
+ complete(&nlmsg_request->comp);
return 0;
}
EXPORT_SYMBOL(iwpm_add_mapping_cb);
@@ -555,7 +555,7 @@ int iwpm_add_and_query_mapping_cb(struct sk_buff *skb,
/* always for found request */
kref_put(&nlmsg_request->kref, iwpm_free_nlmsg_request);
barrier();
- up(&nlmsg_request->sem);
+ complete(&nlmsg_request->comp);
return 0;
}
EXPORT_SYMBOL(iwpm_add_and_query_mapping_cb);
@@ -749,7 +749,7 @@ int iwpm_mapping_error_cb(struct sk_buff *skb, struct netlink_callback *cb)
/* always for found request */
kref_put(&nlmsg_request->kref, iwpm_free_nlmsg_request);
barrier();
- up(&nlmsg_request->sem);
+ complete(&nlmsg_request->comp);
return 0;
}
EXPORT_SYMBOL(iwpm_mapping_error_cb);
diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c
index ade71e7..08ddd2e 100644
--- a/drivers/infiniband/core/iwpm_util.c
+++ b/drivers/infiniband/core/iwpm_util.c
@@ -323,8 +323,7 @@ struct iwpm_nlmsg_request *iwpm_get_nlmsg_request(__u32 nlmsg_seq,
nlmsg_request->nl_client = nl_client;
nlmsg_request->request_done = 0;
nlmsg_request->err_code = 0;
- sema_init(&nlmsg_request->sem, 1);
- down(&nlmsg_request->sem);
+ init_completion(&nlmsg_request->comp);
return nlmsg_request;
}
@@ -368,8 +367,8 @@ int iwpm_wait_complete_req(struct iwpm_nlmsg_request *nlmsg_request)
{
int ret;
- ret = down_timeout(&nlmsg_request->sem, IWPM_NL_TIMEOUT);
- if (ret) {
+ ret = wait_for_completion_timeout(&nlmsg_request->comp, IWPM_NL_TIMEOUT);
+ if (!ret) {
ret = -EINVAL;
pr_info("%s: Timeout %d sec for netlink request (seq = %u)\n",
__func__, (IWPM_NL_TIMEOUT/HZ), nlmsg_request->nlmsg_seq);
diff --git a/drivers/infiniband/core/iwpm_util.h b/drivers/infiniband/core/iwpm_util.h
index af1fc14..ea6c299 100644
--- a/drivers/infiniband/core/iwpm_util.h
+++ b/drivers/infiniband/core/iwpm_util.h
@@ -43,6 +43,7 @@
#include <linux/delay.h>
#include <linux/workqueue.h>
#include <linux/mutex.h>
+#include <linux/completion.h>
#include <linux/jhash.h>
#include <linux/kref.h>
#include <net/netlink.h>
@@ -69,7 +70,7 @@ struct iwpm_nlmsg_request {
u8 nl_client;
u8 request_done;
u16 err_code;
- struct semaphore sem;
+ struct completion comp;
struct kref kref;
};
--
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 2/8] IB/core: Replace semaphore sm_sem with completion
From: Binoy Jayan @ 2016-10-17 16:30 UTC (permalink / raw)
To: Doug Ledford, Sean Hefty, Hal Rosenstock
Cc: Arnd Bergmann, linux-rdma, linux-kernel, Binoy Jayan
In-Reply-To: <1476721862-7070-1-git-send-email-binoy.jayan@linaro.org>
The semaphore 'sm_sem' is used as completion, so convert it to
struct completion. Semaphores are going away in the future. The initial
status of the completion variable is marked as completed by a call to
the function 'complete' immediately following the initialization.
Signed-off-by: Binoy Jayan <binoy.jayan@linaro.org>
---
drivers/infiniband/core/user_mad.c | 14 ++++++++------
1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c
index 415a318..df070cc 100644
--- a/drivers/infiniband/core/user_mad.c
+++ b/drivers/infiniband/core/user_mad.c
@@ -47,6 +47,7 @@
#include <linux/kref.h>
#include <linux/compat.h>
#include <linux/sched.h>
+#include <linux/completion.h>
#include <linux/semaphore.h>
#include <linux/slab.h>
@@ -87,7 +88,7 @@ struct ib_umad_port {
struct cdev sm_cdev;
struct device *sm_dev;
- struct semaphore sm_sem;
+ struct completion sm_comp;
struct mutex file_mutex;
struct list_head file_list;
@@ -1030,12 +1031,12 @@ static int ib_umad_sm_open(struct inode *inode, struct file *filp)
port = container_of(inode->i_cdev, struct ib_umad_port, sm_cdev);
if (filp->f_flags & O_NONBLOCK) {
- if (down_trylock(&port->sm_sem)) {
+ if (!try_wait_for_completion(&port->sm_comp)) {
ret = -EAGAIN;
goto fail;
}
} else {
- if (down_interruptible(&port->sm_sem)) {
+ if (wait_for_completion_interruptible(&port->sm_comp)) {
ret = -ERESTARTSYS;
goto fail;
}
@@ -1060,7 +1061,7 @@ static int ib_umad_sm_open(struct inode *inode, struct file *filp)
ib_modify_port(port->ib_dev, port->port_num, 0, &props);
err_up_sem:
- up(&port->sm_sem);
+ complete(&port->sm_comp);
fail:
return ret;
@@ -1079,7 +1080,7 @@ static int ib_umad_sm_close(struct inode *inode, struct file *filp)
ret = ib_modify_port(port->ib_dev, port->port_num, 0, &props);
mutex_unlock(&port->file_mutex);
- up(&port->sm_sem);
+ complete(&port->sm_comp);
kobject_put(&port->umad_dev->kobj);
@@ -1177,7 +1178,8 @@ static int ib_umad_init_port(struct ib_device *device, int port_num,
port->ib_dev = device;
port->port_num = port_num;
- sema_init(&port->sm_sem, 1);
+ init_completion(&port->sm_comp);
+ complete(&port->sm_comp);
mutex_init(&port->file_mutex);
INIT_LIST_HEAD(&port->file_list);
--
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project
^ permalink raw reply related
* [PATCH 3/8] IB/hns: Replace semaphore poll_sem with mutex
From: Binoy Jayan @ 2016-10-17 16:30 UTC (permalink / raw)
To: Doug Ledford, Sean Hefty, Hal Rosenstock
Cc: Arnd Bergmann, linux-rdma-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA, Binoy Jayan
In-Reply-To: <1476721862-7070-1-git-send-email-binoy.jayan-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>
The semaphore 'poll_sem' is a simple mutex, so it should be written as one.
Semaphores are going away in the future.
Signed-off-by: Binoy Jayan <binoy.jayan-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>
---
drivers/infiniband/hw/hns/hns_roce_cmd.c | 12 ++++++------
drivers/infiniband/hw/hns/hns_roce_device.h | 3 ++-
2 files changed, 8 insertions(+), 7 deletions(-)
diff --git a/drivers/infiniband/hw/hns/hns_roce_cmd.c b/drivers/infiniband/hw/hns/hns_roce_cmd.c
index 2a0b6c0..1421fdb 100644
--- a/drivers/infiniband/hw/hns/hns_roce_cmd.c
+++ b/drivers/infiniband/hw/hns/hns_roce_cmd.c
@@ -119,7 +119,7 @@ static int hns_roce_cmd_mbox_post_hw(struct hns_roce_dev *hr_dev, u64 in_param,
return ret;
}
-/* this should be called with "poll_sem" */
+/* this should be called with "poll_mutex" */
static int __hns_roce_cmd_mbox_poll(struct hns_roce_dev *hr_dev, u64 in_param,
u64 out_param, unsigned long in_modifier,
u8 op_modifier, u16 op,
@@ -167,10 +167,10 @@ static int hns_roce_cmd_mbox_poll(struct hns_roce_dev *hr_dev, u64 in_param,
{
int ret;
- down(&hr_dev->cmd.poll_sem);
+ mutex_lock(&hr_dev->cmd.poll_mutex);
ret = __hns_roce_cmd_mbox_poll(hr_dev, in_param, out_param, in_modifier,
op_modifier, op, timeout);
- up(&hr_dev->cmd.poll_sem);
+ mutex_unlock(&hr_dev->cmd.poll_mutex);
return ret;
}
@@ -275,7 +275,7 @@ int hns_roce_cmd_init(struct hns_roce_dev *hr_dev)
struct device *dev = &hr_dev->pdev->dev;
mutex_init(&hr_dev->cmd.hcr_mutex);
- sema_init(&hr_dev->cmd.poll_sem, 1);
+ mutex_init(&hr_dev->cmd.poll_mutex);
hr_dev->cmd.use_events = 0;
hr_dev->cmd.toggle = 1;
hr_dev->cmd.max_cmds = CMD_MAX_NUM;
@@ -319,7 +319,7 @@ int hns_roce_cmd_use_events(struct hns_roce_dev *hr_dev)
hr_cmd->token_mask = CMD_TOKEN_MASK;
hr_cmd->use_events = 1;
- down(&hr_cmd->poll_sem);
+ mutex_lock(&hr_cmd->poll_mutex);
return 0;
}
@@ -335,7 +335,7 @@ void hns_roce_cmd_use_polling(struct hns_roce_dev *hr_dev)
down(&hr_cmd->event_sem);
kfree(hr_cmd->context);
- up(&hr_cmd->poll_sem);
+ mutex_unlock(&hr_cmd->poll_mutex);
}
struct hns_roce_cmd_mailbox
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index 3417315..2afe075 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -34,6 +34,7 @@
#define _HNS_ROCE_DEVICE_H
#include <rdma/ib_verbs.h>
+#include <linux/mutex.h>
#define DRV_NAME "hns_roce"
@@ -358,7 +359,7 @@ struct hns_roce_cmdq {
struct dma_pool *pool;
u8 __iomem *hcr;
struct mutex hcr_mutex;
- struct semaphore poll_sem;
+ struct mutex poll_mutex;
/*
* Event mode: cmd register mutex protection,
* ensure to not exceed max_cmds and user use limit region
--
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 4/8] IB/mthca: Replace semaphore poll_sem with mutex
From: Binoy Jayan @ 2016-10-17 16:30 UTC (permalink / raw)
To: Doug Ledford, Sean Hefty, Hal Rosenstock
Cc: Arnd Bergmann, linux-rdma, linux-kernel, Binoy Jayan
In-Reply-To: <1476721862-7070-1-git-send-email-binoy.jayan@linaro.org>
The semaphore 'poll_sem' is a simple mutex, so it should be written as one.
Semaphores are going away in the future.
Signed-off-by: Binoy Jayan <binoy.jayan@linaro.org>
---
drivers/infiniband/hw/mthca/mthca_cmd.c | 10 +++++-----
drivers/infiniband/hw/mthca/mthca_cmd.h | 1 +
drivers/infiniband/hw/mthca/mthca_dev.h | 2 +-
3 files changed, 7 insertions(+), 6 deletions(-)
diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.c b/drivers/infiniband/hw/mthca/mthca_cmd.c
index c7f49bb..0cb58ea 100644
--- a/drivers/infiniband/hw/mthca/mthca_cmd.c
+++ b/drivers/infiniband/hw/mthca/mthca_cmd.c
@@ -347,7 +347,7 @@ static int mthca_cmd_poll(struct mthca_dev *dev,
unsigned long end;
u8 status;
- down(&dev->cmd.poll_sem);
+ mutex_lock(&dev->cmd.poll_mutex);
err = mthca_cmd_post(dev, in_param,
out_param ? *out_param : 0,
@@ -382,7 +382,7 @@ static int mthca_cmd_poll(struct mthca_dev *dev,
}
out:
- up(&dev->cmd.poll_sem);
+ mutex_unlock(&dev->cmd.poll_mutex);
return err;
}
@@ -520,7 +520,7 @@ static int mthca_cmd_imm(struct mthca_dev *dev,
int mthca_cmd_init(struct mthca_dev *dev)
{
mutex_init(&dev->cmd.hcr_mutex);
- sema_init(&dev->cmd.poll_sem, 1);
+ mutex_init(&dev->cmd.poll_mutex);
dev->cmd.flags = 0;
dev->hcr = ioremap(pci_resource_start(dev->pdev, 0) + MTHCA_HCR_BASE,
@@ -582,7 +582,7 @@ int mthca_cmd_use_events(struct mthca_dev *dev)
dev->cmd.flags |= MTHCA_CMD_USE_EVENTS;
- down(&dev->cmd.poll_sem);
+ mutex_lock(&dev->cmd.poll_mutex);
return 0;
}
@@ -601,7 +601,7 @@ void mthca_cmd_use_polling(struct mthca_dev *dev)
kfree(dev->cmd.context);
- up(&dev->cmd.poll_sem);
+ mutex_unlock(&dev->cmd.poll_mutex);
}
struct mthca_mailbox *mthca_alloc_mailbox(struct mthca_dev *dev,
diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.h b/drivers/infiniband/hw/mthca/mthca_cmd.h
index d2e5b19..a7f197e 100644
--- a/drivers/infiniband/hw/mthca/mthca_cmd.h
+++ b/drivers/infiniband/hw/mthca/mthca_cmd.h
@@ -35,6 +35,7 @@
#ifndef MTHCA_CMD_H
#define MTHCA_CMD_H
+#include <linux/mutex.h>
#include <rdma/ib_verbs.h>
#define MTHCA_MAILBOX_SIZE 4096
diff --git a/drivers/infiniband/hw/mthca/mthca_dev.h b/drivers/infiniband/hw/mthca/mthca_dev.h
index 4393a02..87ab964 100644
--- a/drivers/infiniband/hw/mthca/mthca_dev.h
+++ b/drivers/infiniband/hw/mthca/mthca_dev.h
@@ -120,7 +120,7 @@ enum {
struct mthca_cmd {
struct pci_pool *pool;
struct mutex hcr_mutex;
- struct semaphore poll_sem;
+ struct mutex poll_mutex;
struct semaphore event_sem;
int max_cmds;
spinlock_t context_lock;
--
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project
^ permalink raw reply related
* [PATCH 5/8] IB/isert: Replace semaphore sem with completion
From: Binoy Jayan @ 2016-10-17 16:30 UTC (permalink / raw)
To: Doug Ledford, Sean Hefty, Hal Rosenstock
Cc: Arnd Bergmann, linux-rdma-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA, Binoy Jayan
In-Reply-To: <1476721862-7070-1-git-send-email-binoy.jayan-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>
The semaphore 'sem' in isert_device is used as completion, so convert
it to struct completion. Semaphores are going away in the future.
Signed-off-by: Binoy Jayan <binoy.jayan-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>
---
drivers/infiniband/ulp/isert/ib_isert.c | 6 +++---
drivers/infiniband/ulp/isert/ib_isert.h | 3 ++-
2 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 6dd43f6..de80f56 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -619,7 +619,7 @@
mutex_unlock(&isert_np->mutex);
isert_info("np %p: Allow accept_np to continue\n", isert_np);
- up(&isert_np->sem);
+ complete(&isert_np->comp);
}
static void
@@ -2311,7 +2311,7 @@ struct rdma_cm_id *
isert_err("Unable to allocate struct isert_np\n");
return -ENOMEM;
}
- sema_init(&isert_np->sem, 0);
+ init_completion(&isert_np->comp);
mutex_init(&isert_np->mutex);
INIT_LIST_HEAD(&isert_np->accepted);
INIT_LIST_HEAD(&isert_np->pending);
@@ -2427,7 +2427,7 @@ struct rdma_cm_id *
int ret;
accept_wait:
- ret = down_interruptible(&isert_np->sem);
+ ret = wait_for_completion_interruptible(&isert_np->comp);
if (ret)
return -ENODEV;
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index c02ada5..a1277c0 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -3,6 +3,7 @@
#include <linux/in6.h>
#include <rdma/ib_verbs.h>
#include <rdma/rdma_cm.h>
+#include <linux/completion.h>
#include <rdma/rw.h>
#include <scsi/iser.h>
@@ -190,7 +191,7 @@ struct isert_device {
struct isert_np {
struct iscsi_np *np;
- struct semaphore sem;
+ struct completion comp;
struct rdma_cm_id *cm_id;
struct mutex mutex;
struct list_head accepted;
--
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox