Export callback to register supported intrinsic instructions to speed
up reading EDC and MC. By default, use 32-bit reads. Also rework
logic to read EDC and MC.
Signed-off-by: Rahul Lakkireddy <rahul.lakkire...@chelsio.com>
Signed-off-by: Ganesh Goudar <ganes...@chelsio.com>
---
drivers/net/ethernet/chelsio/cxgb4/Makefile | 2 +-
drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h | 6 +
.../net/ethernet/chelsio/cxgb4/cudbg_intrinsic.c | 38 ++++
.../net/ethernet/chelsio/cxgb4/cudbg_intrinsic.h | 25 +++
drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c | 70 +++++++-
drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 5 +
drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c | 2 +
drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 193 +++++++++++++--------
8 files changed, 267 insertions(+), 74 deletions(-)
create mode 100644 drivers/net/ethernet/chelsio/cxgb4/cudbg_intrinsic.c
create mode 100644 drivers/net/ethernet/chelsio/cxgb4/cudbg_intrinsic.h
diff --git a/drivers/net/ethernet/chelsio/cxgb4/Makefile
b/drivers/net/ethernet/chelsio/cxgb4/Makefile
index 8c9c6b0d2e5d..0dbaf1b18bac 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/Makefile
+++ b/drivers/net/ethernet/chelsio/cxgb4/Makefile
@@ -8,7 +8,7 @@ obj-$(CONFIG_CHELSIO_T4) += cxgb4.o
cxgb4-objs := cxgb4_main.o l2t.o smt.o t4_hw.o sge.o clip_tbl.o
cxgb4_ethtool.o \
cxgb4_uld.o sched.o cxgb4_filter.o cxgb4_tc_u32.o \
cxgb4_ptp.o cxgb4_tc_flower.o cxgb4_cudbg.o \
- cudbg_common.o cudbg_lib.o
+ cudbg_common.o cudbg_lib.o cudbg_intrinsic.o
cxgb4-$(CONFIG_CHELSIO_T4_DCB) += cxgb4_dcb.o
cxgb4-$(CONFIG_CHELSIO_T4_FCOE) += cxgb4_fcoe.o
cxgb4-$(CONFIG_DEBUG_FS) += cxgb4_debugfs.o
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h
b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h
index 88e740082a02..456d61eacb27 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h
@@ -83,10 +83,16 @@ enum cudbg_dbg_entity_type {
CUDBG_MAX_ENTITY = 70,
};
+struct cudbg_init;
+typedef unsigned int (*cudbg_intrinsic_t)(struct cudbg_init *pdbg_init,
+ u32 start, u32 offset, u32 size,
+ u32 max_size, u8 *buf);
+
struct cudbg_init {
struct adapter *adap; /* Pointer to adapter structure */
void *outbuf; /* Output buffer */
u32 outbuf_size; /* Output buffer size */
+ cudbg_intrinsic_t intrinsic_cb; /* CPU intrinsic callback */
};
static inline unsigned int cudbg_mbytes_to_bytes(unsigned int size)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_intrinsic.c
b/drivers/net/ethernet/chelsio/cxgb4/cudbg_intrinsic.c
new file mode 100644
index 000000000000..0b80512e5c0c
--- /dev/null
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_intrinsic.c
@@ -0,0 +1,38 @@
+/*
+ * Copyright (C) 2018 Chelsio Communications. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ */
+
+#include "cxgb4.h"
+#include "cudbg_if.h"
+#include "cudbg_intrinsic.h"
+
+unsigned int cudbg_mem_read_def(struct cudbg_init *pdbg_init,
+ u32 start, u32 offset, u32 size,
+ u32 mem_aperture, u8 *outbuf)
+{
+ struct adapter *adap = pdbg_init->adap;
+ __be32 *buf = (__be32 *)outbuf;
+
+ *buf = le32_to_cpu((__force __le32)
+ t4_read_reg(adap, start + offset));
+
+ return sizeof(__be32);
+}
+
+void cudbg_set_intrinsic_callback(struct cudbg_init *pdbg_init)
+{
+ pdbg_init->intrinsic_cb = cudbg_mem_read_def;
+}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_intrinsic.h
b/drivers/net/ethernet/chelsio/cxgb4/cudbg_intrinsic.h
new file mode 100644
index 000000000000..3af0f07311ec
--- /dev/null
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_intrinsic.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2018 Chelsio Communications. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ */
+
+#ifndef __CUDBG_INTRINSIC_H__
+#define __CUDBG_INTRINSIC_H__
+
+unsigned int cudbg_mem_read_def(struct cudbg_init *pdbg_init,
+ u32 start, u32 offset, u32 size,
+ u32 mem_aperture, u8 *outbuf);
+void cudbg_set_intrinsic_callback(struct cudbg_init *pdbg_init);
+#endif /* __CUDBG_INTRINSIC_H__ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
index 0a3871f10787..4921460aa787 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
@@ -18,6 +18,7 @@
#include <linux/sort.h>
#include "t4_regs.h"
+#include "t4_values.h"
#include "cxgb4.h"
#include "cudbg_if.h"
#include "cudbg_lib_common.h"
@@ -840,6 +841,69 @@ static int cudbg_get_payload_range(struct adapter *padap,
u8 mem_type,
&payload->start, &payload->end);
}
+static int cudbg_memory_read(struct cudbg_init *pdbg_init, int win,
+ int mtype, u32 addr, u32 len, void *hbuf)
+{
+ u32 win_pf, memoffset, mem_aperture, mem_base;
+ struct adapter *adap = pdbg_init->adap;
+ u32 pos, offset, resid, read_len;
+ u8 *buf;
+ int ret;
+
+ /* Argument sanity checks ...
+ */
+ if (addr & 0x3 || (uintptr_t)hbuf & 0x3)
+ return -EINVAL;
+
+ buf = (u8 *)hbuf;
+
+ /* Try to do 32-bit reads. Residual will be handled later. */
+ resid = len & 0x3;
+ len -= resid;
+
+ ret = t4_memory_rw_init(adap, win, mtype, &memoffset, &mem_base,
+ &mem_aperture);
+ if (ret)
+ return ret;
+
+ addr = addr + memoffset;
+ win_pf = is_t4(adap->params.chip) ? 0 : PFNUM_V(adap->pf);
+
+ pos = addr & ~(mem_aperture - 1);
+ offset = addr - pos;
+
+ /* Set up initial PCI-E Memory Window to cover the start of our
+ * transfer.
+ */
+ t4_memory_update_win(adap, win, pos | win_pf);
+
+ /* Transfer data from the adapter */
+ while (len > 0) {
+ read_len = pdbg_init->intrinsic_cb(pdbg_init, mem_base,
+ offset, len, mem_aperture,
+ buf);
+ buf += read_len;
+ offset += read_len;
+ len -= read_len;
+
+ /* If we've reached the end of our current window aperture,
+ * move the PCI-E Memory Window on to the next.
+ */
+ if (offset == mem_aperture) {
+ pos += mem_aperture;
+ offset = 0;
+ t4_memory_update_win(adap, win, pos | win_pf);
+ }
+ }
+
+ /* Transfer residual */
+ if (resid)
+ t4_memory_rw_residual(adap, resid, mem_base + offset, buf,
+ T4_MEMORY_READ);
+
+ return 0;
+}
+
#define CUDBG_YIELD_ITERATION 256
static int cudbg_read_fw_mem(struct cudbg_init *pdbg_init,
@@ -899,10 +963,8 @@ static int cudbg_read_fw_mem(struct cudbg_init *pdbg_init,
goto skip_read;
spin_lock(&padap->win0_lock);
- rc = t4_memory_rw(padap, MEMWIN_NIC, mem_type,
- bytes_read, bytes,
- (__be32 *)temp_buff.data,
- 1);
+ rc = cudbg_memory_read(pdbg_init, MEMWIN_NIC, mem_type,
+ bytes_read, bytes, temp_buff.data);
spin_unlock(&padap->win0_lock);
if (rc) {
cudbg_err->sys_err = rc;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index baa67d362051..92f1d87adf9f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -1471,6 +1471,11 @@ u32 t4_read_pcie_cfg4(struct adapter *adap, int reg);
u32 t4_get_util_window(struct adapter *adap);
void t4_setup_memwin(struct adapter *adap, u32 memwin_base, u32 window);
+int t4_memory_rw_init(struct adapter *adap, int win, int mtype, u32 *mem_off,
+ u32 *mem_base, u32 *mem_aperture);
+void t4_memory_update_win(struct adapter *adap, int win, u32 addr);
+void t4_memory_rw_residual(struct adapter *adap, u32 off, u32 addr, u8 *buf,
+ int dir);
#define T4_MEMORY_WRITE 0
#define T4_MEMORY_READ 1
int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr, u32 len,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
index a2d6c8a69c52..db1b57a09887 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
@@ -18,6 +18,7 @@
#include "t4_regs.h"
#include "cxgb4.h"
#include "cxgb4_cudbg.h"
+#include "cudbg_intrinsic.h"
static const struct cxgb4_collect_entity cxgb4_collect_mem_dump[] = {
{ CUDBG_EDC0, cudbg_collect_edc0_meminfo },
@@ -395,6 +396,7 @@ int cxgb4_cudbg_collect(struct adapter *adap, void *buf,
u32 *buf_size,
cudbg_init.adap = adap;
cudbg_init.outbuf = buf;
cudbg_init.outbuf_size = size;
+ cudbg_set_intrinsic_callback(&cudbg_init);
dbg_buff.data = buf;
dbg_buff.size = size;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 6d76851a4da9..e4d7da15c3b6 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -481,6 +481,117 @@ static int t4_edc_err_read(struct adapter *adap, int idx)
return 0;
}
+/**
+ * t4_memory_rw_init - Get memory window relative offset, base, and size.
+ * @adap: the adapter
+ * @win: PCI-E Memory Window to use
+ * @mtype: memory type: MEM_EDC0, MEM_EDC1 or MEM_MC
+ * @mem_off: memory relative offset with respect to @mtype.
+ * @mem_base: configured memory base address.
+ * @mem_aperture: configured memory window aperture.
+ *
+ * Get the configured memory window's relative offset, base, and size.
+ */
+int t4_memory_rw_init(struct adapter *adap, int win, int mtype, u32 *mem_off,
+ u32 *mem_base, u32 *mem_aperture)
+{
+ u32 edc_size, mc_size, mem_reg;
+
+ /* Offset into the region of memory which is being accessed
+ * MEM_EDC0 = 0
+ * MEM_EDC1 = 1
+ * MEM_MC = 2 -- MEM_MC for chips with only 1 memory controller
+ * MEM_MC1 = 3 -- for chips with 2 memory controllers (e.g. T5)
+ * MEM_HMA = 4
+ */
+ edc_size = EDRAM0_SIZE_G(t4_read_reg(adap, MA_EDRAM0_BAR_A));
+ if (mtype == MEM_HMA) {
+ *mem_off = 2 * (edc_size * 1024 * 1024);
+ } else if (mtype != MEM_MC1) {
+ *mem_off = (mtype * (edc_size * 1024 * 1024));
+ } else {
+ mc_size = EXT_MEM0_SIZE_G(t4_read_reg(adap,
+ MA_EXT_MEMORY0_BAR_A));
+ *mem_off = (MEM_MC0 * edc_size + mc_size) * 1024 * 1024;
+ }
+
+ /* Each PCI-E Memory Window is programmed with a window size -- or
+ * "aperture" -- which controls the granularity of its mapping onto
+ * adapter memory. We need to grab that aperture in order to know
+ * how to use the specified window. The window is also programmed
+ * with the base address of the Memory Window in BAR0's address
+ * space. For T4 this is an absolute PCI-E Bus Address. For T5
+ * the address is relative to BAR0.
+ */
+ mem_reg = t4_read_reg(adap,
+ PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_BASE_WIN_A,
+ win));
+ /* a dead adapter will return 0xffffffff for PIO reads */
+ if (mem_reg == 0xffffffff)
+ return -ENXIO;
+
+ *mem_aperture = 1 << (WINDOW_G(mem_reg) + WINDOW_SHIFT_X);
+ *mem_base = PCIEOFST_G(mem_reg) << PCIEOFST_SHIFT_X;
+ if (is_t4(adap->params.chip))
+ *mem_base -= adap->t4_bar0;
+
+ return 0;
+}
+
+/**
+ * t4_memory_update_win - Move memory window to specified address.
+ * @adap: the adapter
+ * @win: PCI-E Memory Window to use
+ * @addr: location to move.
+ *
+ * Move memory window to specified address.
+ */
+void t4_memory_update_win(struct adapter *adap, int win, u32 addr)
+{
+ t4_write_reg(adap,
+ PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_OFFSET_A, win),
+ addr);
+ /* Read it back to ensure that changes propagate before we
+ * attempt to use the new value.
+ */
+ t4_read_reg(adap,
+ PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_OFFSET_A, win));
+}
+
+/**
+ * t4_memory_rw_residual - Read/Write residual data.
+ * @adap: the adapter
+ * @off: relative offset within residual to start read/write.
+ * @addr: address within indicated memory type.
+ * @buf: host memory buffer
+ * @dir: direction of transfer T4_MEMORY_READ (1) or T4_MEMORY_WRITE (0)
+ *
+ * Read/Write residual data less than 32-bits.
+ */
+void t4_memory_rw_residual(struct adapter *adap, u32 off, u32 addr, u8 *buf,
+ int dir)
+{
+ union {
+ u32 word;
+ char byte[4];
+ } last;
+ unsigned char *bp;
+ int i;
+
+ if (dir == T4_MEMORY_READ) {
+ last.word = le32_to_cpu((__force __le32)
+ t4_read_reg(adap, addr));
+ for (bp = (unsigned char *)buf, i = off; i < 4; i++)
+ bp[i] = last.byte[i];
+ } else {
+ last.word = *buf;
+ for (i = off; i < 4; i++)
+ last.byte[i] = 0;
+ t4_write_reg(adap, addr,
+ (__force u32)cpu_to_le32(last.word));
+ }
+}
+
/**
* t4_memory_rw - read/write EDC 0, EDC 1 or MC via PCIE memory window
* @adap: the adapter
@@ -502,8 +613,9 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype,
u32 addr,
u32 len, void *hbuf, int dir)
{
u32 pos, offset, resid, memoffset;
- u32 edc_size, mc_size, win_pf, mem_reg, mem_aperture, mem_base;
+ u32 win_pf, mem_aperture, mem_base;
u32 *buf;
+ int ret;
/* Argument sanity checks ...
*/
@@ -519,59 +631,26 @@ int t4_memory_rw(struct adapter *adap, int win, int
mtype, u32 addr,
resid = len & 0x3;
len -= resid;
- /* Offset into the region of memory which is being accessed
- * MEM_EDC0 = 0
- * MEM_EDC1 = 1
- * MEM_MC = 2 -- MEM_MC for chips with only 1 memory controller
- * MEM_MC1 = 3 -- for chips with 2 memory controllers (e.g. T5)
- * MEM_HMA = 4
- */
- edc_size = EDRAM0_SIZE_G(t4_read_reg(adap, MA_EDRAM0_BAR_A));
- if (mtype == MEM_HMA) {
- memoffset = 2 * (edc_size * 1024 * 1024);
- } else if (mtype != MEM_MC1) {
- memoffset = (mtype * (edc_size * 1024 * 1024));
- } else {
- mc_size = EXT_MEM0_SIZE_G(t4_read_reg(adap,
- MA_EXT_MEMORY0_BAR_A));
- memoffset = (MEM_MC0 * edc_size + mc_size) * 1024 * 1024;
- }
+ ret = t4_memory_rw_init(adap, win, mtype, &memoffset, &mem_base,
+ &mem_aperture);
+ if (ret)
+ return ret;
/* Determine the PCIE_MEM_ACCESS_OFFSET */
addr = addr + memoffset;
- /* Each PCI-E Memory Window is programmed with a window size -- or
- * "aperture" -- which controls the granularity of its mapping onto
- * adapter memory. We need to grab that aperture in order to know
- * how to use the specified window. The window is also programmed
- * with the base address of the Memory Window in BAR0's address
- * space. For T4 this is an absolute PCI-E Bus Address. For T5
- * the address is relative to BAR0.
- */
- mem_reg = t4_read_reg(adap,
- PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_BASE_WIN_A,
- win));
- mem_aperture = 1 << (WINDOW_G(mem_reg) + WINDOW_SHIFT_X);
- mem_base = PCIEOFST_G(mem_reg) << PCIEOFST_SHIFT_X;
- if (is_t4(adap->params.chip))
- mem_base -= adap->t4_bar0;
win_pf = is_t4(adap->params.chip) ? 0 : PFNUM_V(adap->pf);
/* Calculate our initial PCI-E Memory Window Position and Offset into
* that Window.
*/
- pos = addr & ~(mem_aperture-1);
+ pos = addr & ~(mem_aperture - 1);
offset = addr - pos;
/* Set up initial PCI-E Memory Window to cover the start of our
- * transfer. (Read it back to ensure that changes propagate before we
- * attempt to use the new value.)
+ * transfer.
*/
- t4_write_reg(adap,
- PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_OFFSET_A, win),
- pos | win_pf);
- t4_read_reg(adap,
- PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_OFFSET_A, win));
+ t4_memory_update_win(adap, win, pos | win_pf);
/* Transfer data to/from the adapter as long as there's an integral
* number of 32-bit transfers to complete.
@@ -626,12 +705,7 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype,
u32 addr,
if (offset == mem_aperture) {
pos += mem_aperture;
offset = 0;
- t4_write_reg(adap,
- PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_OFFSET_A,
- win), pos | win_pf);
- t4_read_reg(adap,
- PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_OFFSET_A,
- win));
+ t4_memory_update_win(adap, win, pos | win_pf);
}
}
@@ -640,28 +714,9 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype,
u32 addr,
* residual amount. The PCI-E Memory Window has already been moved
* above (if necessary) to cover this final transfer.
*/
- if (resid) {
- union {
- u32 word;
- char byte[4];
- } last;
- unsigned char *bp;
- int i;
-
- if (dir == T4_MEMORY_READ) {
- last.word = le32_to_cpu(
- (__force __le32)t4_read_reg(adap,
- mem_base + offset));
- for (bp = (unsigned char *)buf, i = resid; i < 4; i++)
- bp[i] = last.byte[i];
- } else {
- last.word = *buf;
- for (i = resid; i < 4; i++)
- last.byte[i] = 0;
- t4_write_reg(adap, mem_base + offset,
- (__force u32)cpu_to_le32(last.word));
- }
- }
+ if (resid)
+ t4_memory_rw_residual(adap, resid, mem_base + offset,
+ (u8 *)buf, dir);
return 0;
}
--
2.14.1
