* [PATCH 5/7] drm/nouveau: tegra: Use nvmem API
From: Thierry Reding @ 2019-08-29 22:19 UTC (permalink / raw)
To: Thierry Reding
Cc: linux-tegra, Nagarjuna Kristam, linux-arm-kernel, Jon Hunter
In-Reply-To: <20190829221911.24876-1-thierry.reding@gmail.com>
From: Thierry Reding <treding@nvidia.com>
Instead of using the custom Tegra FUSE API to read the calibration fuse
for the clock on GM20B, use the nvmem API. This makes the dependency
between the two devices more explicit and decouples the driver from one
another.
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
drivers/gpu/drm/nouveau/nvkm/subdev/clk/gm20b.c | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gm20b.c
index b284e949f732..096a8b4b9bb5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gm20b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gm20b.c
@@ -20,6 +20,8 @@
* DEALINGS IN THE SOFTWARE.
*/
+#include <linux/nvmem-consumer.h>
+
#include <subdev/clk.h>
#include <subdev/volt.h>
#include <subdev/timer.h>
@@ -929,7 +931,6 @@ gm20b_clk_new_speedo0(struct nvkm_device *device, int index,
}
/* FUSE register */
-#define FUSE_RESERVED_CALIB0 0x204
#define FUSE_RESERVED_CALIB0_INTERCEPT_FRAC_SHIFT 0
#define FUSE_RESERVED_CALIB0_INTERCEPT_FRAC_WIDTH 4
#define FUSE_RESERVED_CALIB0_INTERCEPT_INT_SHIFT 4
@@ -945,14 +946,17 @@ static int
gm20b_clk_init_fused_params(struct gm20b_clk *clk)
{
struct nvkm_subdev *subdev = &clk->base.base.subdev;
+ struct nvkm_device *device = subdev->device;
u32 val = 0;
u32 rev = 0;
+ int ret;
+
+ ret = nvmem_cell_read_u32(device->dev, "calibration", &val);
+ if (ret < 0)
+ return ret;
-#if IS_ENABLED(CONFIG_ARCH_TEGRA)
- tegra_fuse_readl(FUSE_RESERVED_CALIB0, &val);
rev = (val >> FUSE_RESERVED_CALIB0_FUSE_REV_SHIFT) &
MASK(FUSE_RESERVED_CALIB0_FUSE_REV_WIDTH);
-#endif
/* No fused parameters, we will calibrate later */
if (rev == 0)
--
2.22.0
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related
* [PATCH 6/7] phy: tegra: xusb: Use nvmem API
From: Thierry Reding @ 2019-08-29 22:19 UTC (permalink / raw)
To: Thierry Reding
Cc: linux-tegra, Nagarjuna Kristam, linux-arm-kernel, Jon Hunter
In-Reply-To: <20190829221911.24876-1-thierry.reding@gmail.com>
From: Thierry Reding <treding@nvidia.com>
Instead of using the custom Tegra FUSE API to read the calibration fuses
for the UPHY, use the nvmem API. This makes the dependency between the
two devices more explicit and decouples the drivers from one another.
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
drivers/phy/tegra/xusb-tegra124.c | 10 +++++-----
drivers/phy/tegra/xusb-tegra186.c | 7 +++----
drivers/phy/tegra/xusb-tegra210.c | 10 ++++++----
3 files changed, 14 insertions(+), 13 deletions(-)
diff --git a/drivers/phy/tegra/xusb-tegra124.c b/drivers/phy/tegra/xusb-tegra124.c
index 98d84920c676..f62905ea4ca5 100644
--- a/drivers/phy/tegra/xusb-tegra124.c
+++ b/drivers/phy/tegra/xusb-tegra124.c
@@ -7,6 +7,7 @@
#include <linux/io.h>
#include <linux/mailbox_client.h>
#include <linux/module.h>
+#include <linux/nvmem-consumer.h>
#include <linux/of.h>
#include <linux/phy/phy.h>
#include <linux/platform_device.h>
@@ -14,8 +15,6 @@
#include <linux/reset.h>
#include <linux/slab.h>
-#include <soc/tegra/fuse.h>
-
#include "xusb.h"
#define FUSE_SKU_CALIB_HS_CURR_LEVEL_PADX_SHIFT(x) ((x) ? 15 : 0)
@@ -1653,13 +1652,14 @@ static const struct tegra_xusb_port_ops tegra124_usb3_port_ops = {
};
static int
-tegra124_xusb_read_fuse_calibration(struct tegra124_xusb_fuse_calibration *fuse)
+tegra124_xusb_read_fuse_calibration(struct tegra124_xusb_padctl *padctl)
{
+ struct tegra124_xusb_fuse_calibration *fuse = &padctl->fuse;
unsigned int i;
int err;
u32 value;
- err = tegra_fuse_readl(TEGRA_FUSE_SKU_CALIB_0, &value);
+ err = nvmem_cell_read_u32(padctl->base.dev, "calibration", &value);
if (err < 0)
return err;
@@ -1695,7 +1695,7 @@ tegra124_xusb_padctl_probe(struct device *dev,
padctl->base.dev = dev;
padctl->base.soc = soc;
- err = tegra124_xusb_read_fuse_calibration(&padctl->fuse);
+ err = tegra124_xusb_read_fuse_calibration(padctl);
if (err < 0)
return ERR_PTR(err);
diff --git a/drivers/phy/tegra/xusb-tegra186.c b/drivers/phy/tegra/xusb-tegra186.c
index 6f3afaf9398f..0663ed00d748 100644
--- a/drivers/phy/tegra/xusb-tegra186.c
+++ b/drivers/phy/tegra/xusb-tegra186.c
@@ -6,6 +6,7 @@
#include <linux/delay.h>
#include <linux/io.h>
#include <linux/module.h>
+#include <linux/nvmem-consumer.h>
#include <linux/of.h>
#include <linux/phy/phy.h>
#include <linux/regulator/consumer.h>
@@ -13,8 +14,6 @@
#include <linux/clk.h>
#include <linux/slab.h>
-#include <soc/tegra/fuse.h>
-
#include "xusb.h"
/* FUSE USB_CALIB registers */
@@ -800,7 +799,7 @@ tegra186_xusb_read_fuse_calibration(struct tegra186_xusb_padctl *padctl)
if (!level)
return -ENOMEM;
- err = tegra_fuse_readl(TEGRA_FUSE_SKU_CALIB_0, &value);
+ err = nvmem_cell_read_u32(dev, "calibration", &value);
if (err) {
dev_err(dev, "failed to read calibration fuse: %d\n", err);
return err;
@@ -819,7 +818,7 @@ tegra186_xusb_read_fuse_calibration(struct tegra186_xusb_padctl *padctl)
padctl->calib.hs_term_range_adj = (value >> HS_TERM_RANGE_ADJ_SHIFT) &
HS_TERM_RANGE_ADJ_MASK;
- err = tegra_fuse_readl(TEGRA_FUSE_USB_CALIB_EXT_0, &value);
+ err = nvmem_cell_read_u32(dev, "calibration-ext", &value);
if (err) {
dev_err(dev, "failed to read calibration fuse: %d\n", err);
return err;
diff --git a/drivers/phy/tegra/xusb-tegra210.c b/drivers/phy/tegra/xusb-tegra210.c
index 0c0df6897a3b..659b62867012 100644
--- a/drivers/phy/tegra/xusb-tegra210.c
+++ b/drivers/phy/tegra/xusb-tegra210.c
@@ -10,6 +10,7 @@
#include <linux/io.h>
#include <linux/mailbox_client.h>
#include <linux/module.h>
+#include <linux/nvmem-consumer.h>
#include <linux/of.h>
#include <linux/phy/phy.h>
#include <linux/platform_device.h>
@@ -1946,13 +1947,14 @@ static const struct tegra_xusb_port_ops tegra210_usb3_port_ops = {
};
static int
-tegra210_xusb_read_fuse_calibration(struct tegra210_xusb_fuse_calibration *fuse)
+tegra210_xusb_read_fuse_calibration(struct tegra210_xusb_padctl *padctl)
{
+ struct tegra210_xusb_fuse_calibration *fuse = &padctl->fuse;
unsigned int i;
u32 value;
int err;
- err = tegra_fuse_readl(TEGRA_FUSE_SKU_CALIB_0, &value);
+ err = nvmem_cell_read_u32(padctl->base.dev, "calibration", &value);
if (err < 0)
return err;
@@ -1966,7 +1968,7 @@ tegra210_xusb_read_fuse_calibration(struct tegra210_xusb_fuse_calibration *fuse)
(value >> FUSE_SKU_CALIB_HS_TERM_RANGE_ADJ_SHIFT) &
FUSE_SKU_CALIB_HS_TERM_RANGE_ADJ_MASK;
- err = tegra_fuse_readl(TEGRA_FUSE_USB_CALIB_EXT_0, &value);
+ err = nvmem_cell_read_u32(padctl->base.dev, "calibration-ext", &value);
if (err < 0)
return err;
@@ -1991,7 +1993,7 @@ tegra210_xusb_padctl_probe(struct device *dev,
padctl->base.dev = dev;
padctl->base.soc = soc;
- err = tegra210_xusb_read_fuse_calibration(&padctl->fuse);
+ err = tegra210_xusb_read_fuse_calibration(padctl);
if (err < 0)
return ERR_PTR(err);
--
2.22.0
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related
* [PATCH 7/7] thermal: tegra: Use nvmem API
From: Thierry Reding @ 2019-08-29 22:19 UTC (permalink / raw)
To: Thierry Reding
Cc: linux-tegra, Nagarjuna Kristam, linux-arm-kernel, Jon Hunter
In-Reply-To: <20190829221911.24876-1-thierry.reding@gmail.com>
From: Thierry Reding <treding@nvidia.com>
Instead of using the custom Tegra FUSE API to read the fuses for TSENSOR
configuration, use the nvmem API. This makes the dependency between the
two devices more explicit and decouples the driver from one another.
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
drivers/thermal/tegra/soctherm-fuse.c | 19 ++++++++++---------
drivers/thermal/tegra/soctherm.c | 4 ++--
drivers/thermal/tegra/soctherm.h | 9 ++++++---
drivers/thermal/tegra/tegra124-soctherm.c | 8 --------
drivers/thermal/tegra/tegra132-soctherm.c | 8 --------
drivers/thermal/tegra/tegra210-soctherm.c | 8 --------
6 files changed, 18 insertions(+), 38 deletions(-)
diff --git a/drivers/thermal/tegra/soctherm-fuse.c b/drivers/thermal/tegra/soctherm-fuse.c
index 190f95280e0b..c63bef809004 100644
--- a/drivers/thermal/tegra/soctherm-fuse.c
+++ b/drivers/thermal/tegra/soctherm-fuse.c
@@ -4,6 +4,7 @@
*/
#include <linux/module.h>
+#include <linux/nvmem-consumer.h>
#include <linux/platform_device.h>
#include <soc/tegra/fuse.h>
@@ -70,14 +71,15 @@ static s64 div64_s64_precise(s64 a, s32 b)
return r >> 16;
}
-int tegra_calc_shared_calib(const struct tegra_soctherm_fuse *tfuse,
+int tegra_calc_shared_calib(struct device *dev,
+ const struct tegra_soctherm_fuse *tfuse,
struct tsensor_shared_calib *shared)
{
u32 val;
s32 shifted_cp, shifted_ft;
int err;
- err = tegra_fuse_readl(FUSE_TSENSOR_COMMON, &val);
+ err = nvmem_cell_read_u32(dev, "common", &val);
if (err)
return err;
@@ -90,11 +92,9 @@ int tegra_calc_shared_calib(const struct tegra_soctherm_fuse *tfuse,
tfuse->fuse_shift_ft_shift;
shifted_ft = sign_extend32(shifted_ft, 4);
- if (tfuse->fuse_spare_realignment) {
- err = tegra_fuse_readl(tfuse->fuse_spare_realignment, &val);
- if (err)
- return err;
- }
+ err = nvmem_cell_read_u32(dev, "realignment", &val);
+ if (err != -ENOENT)
+ return err;
shifted_cp = sign_extend32(val, 5);
@@ -104,7 +104,8 @@ int tegra_calc_shared_calib(const struct tegra_soctherm_fuse *tfuse,
return 0;
}
-int tegra_calc_tsensor_calib(const struct tegra_tsensor *sensor,
+int tegra_calc_tsensor_calib(struct device *dev,
+ const struct tegra_tsensor *sensor,
const struct tsensor_shared_calib *shared,
u32 *calibration)
{
@@ -119,7 +120,7 @@ int tegra_calc_tsensor_calib(const struct tegra_tsensor *sensor,
sensor_group = sensor->group;
- err = tegra_fuse_readl(sensor->calib_fuse_offset, &val);
+ err = nvmem_cell_read_u32(dev, sensor->name, &val);
if (err)
return err;
diff --git a/drivers/thermal/tegra/soctherm.c b/drivers/thermal/tegra/soctherm.c
index 43941eb734eb..e632888ff1ae 100644
--- a/drivers/thermal/tegra/soctherm.c
+++ b/drivers/thermal/tegra/soctherm.c
@@ -2180,13 +2180,13 @@ static int tegra_soctherm_probe(struct platform_device *pdev)
return -ENOMEM;
/* calculate shared calibration data */
- err = tegra_calc_shared_calib(soc->tfuse, &shared_calib);
+ err = tegra_calc_shared_calib(&pdev->dev, soc->tfuse, &shared_calib);
if (err)
return err;
/* calculate tsensor calibaration data */
for (i = 0; i < soc->num_tsensors; ++i) {
- err = tegra_calc_tsensor_calib(&soc->tsensors[i],
+ err = tegra_calc_tsensor_calib(&pdev->dev, &soc->tsensors[i],
&shared_calib,
&tegra->calib[i]);
if (err)
diff --git a/drivers/thermal/tegra/soctherm.h b/drivers/thermal/tegra/soctherm.h
index 70501e73d586..715b4f06e162 100644
--- a/drivers/thermal/tegra/soctherm.h
+++ b/drivers/thermal/tegra/soctherm.h
@@ -93,7 +93,6 @@ struct tegra_tsensor {
const char *name;
const u32 base;
const struct tegra_tsensor_configuration *config;
- const u32 calib_fuse_offset;
/*
* Correction values used to modify values read from
* calibration fuses
@@ -131,9 +130,13 @@ struct tegra_soctherm_soc {
struct tsensor_group_thermtrips *thermtrips;
};
-int tegra_calc_shared_calib(const struct tegra_soctherm_fuse *tfuse,
+struct tegra_soctherm;
+
+int tegra_calc_shared_calib(struct device *dev,
+ const struct tegra_soctherm_fuse *tfuse,
struct tsensor_shared_calib *shared);
-int tegra_calc_tsensor_calib(const struct tegra_tsensor *sensor,
+int tegra_calc_tsensor_calib(struct device *dev,
+ const struct tegra_tsensor *sensor,
const struct tsensor_shared_calib *shared,
u32 *calib);
diff --git a/drivers/thermal/tegra/tegra124-soctherm.c b/drivers/thermal/tegra/tegra124-soctherm.c
index 20ad27f4d1a1..e5bd080e3632 100644
--- a/drivers/thermal/tegra/tegra124-soctherm.c
+++ b/drivers/thermal/tegra/tegra124-soctherm.c
@@ -129,7 +129,6 @@ static const struct tegra_tsensor tegra124_tsensors[] = {
.name = "cpu0",
.base = 0xc0,
.config = &tegra124_tsensor_config,
- .calib_fuse_offset = 0x098,
.fuse_corr_alpha = 1135400,
.fuse_corr_beta = -6266900,
.group = &tegra124_tsensor_group_cpu,
@@ -137,7 +136,6 @@ static const struct tegra_tsensor tegra124_tsensors[] = {
.name = "cpu1",
.base = 0xe0,
.config = &tegra124_tsensor_config,
- .calib_fuse_offset = 0x084,
.fuse_corr_alpha = 1122220,
.fuse_corr_beta = -5700700,
.group = &tegra124_tsensor_group_cpu,
@@ -145,7 +143,6 @@ static const struct tegra_tsensor tegra124_tsensors[] = {
.name = "cpu2",
.base = 0x100,
.config = &tegra124_tsensor_config,
- .calib_fuse_offset = 0x088,
.fuse_corr_alpha = 1127000,
.fuse_corr_beta = -6768200,
.group = &tegra124_tsensor_group_cpu,
@@ -153,7 +150,6 @@ static const struct tegra_tsensor tegra124_tsensors[] = {
.name = "cpu3",
.base = 0x120,
.config = &tegra124_tsensor_config,
- .calib_fuse_offset = 0x12c,
.fuse_corr_alpha = 1110900,
.fuse_corr_beta = -6232000,
.group = &tegra124_tsensor_group_cpu,
@@ -161,7 +157,6 @@ static const struct tegra_tsensor tegra124_tsensors[] = {
.name = "mem0",
.base = 0x140,
.config = &tegra124_tsensor_config,
- .calib_fuse_offset = 0x158,
.fuse_corr_alpha = 1122300,
.fuse_corr_beta = -5936400,
.group = &tegra124_tsensor_group_mem,
@@ -169,7 +164,6 @@ static const struct tegra_tsensor tegra124_tsensors[] = {
.name = "mem1",
.base = 0x160,
.config = &tegra124_tsensor_config,
- .calib_fuse_offset = 0x15c,
.fuse_corr_alpha = 1145700,
.fuse_corr_beta = -7124600,
.group = &tegra124_tsensor_group_mem,
@@ -177,7 +171,6 @@ static const struct tegra_tsensor tegra124_tsensors[] = {
.name = "gpu",
.base = 0x180,
.config = &tegra124_tsensor_config,
- .calib_fuse_offset = 0x154,
.fuse_corr_alpha = 1120100,
.fuse_corr_beta = -6000500,
.group = &tegra124_tsensor_group_gpu,
@@ -185,7 +178,6 @@ static const struct tegra_tsensor tegra124_tsensors[] = {
.name = "pllx",
.base = 0x1a0,
.config = &tegra124_tsensor_config,
- .calib_fuse_offset = 0x160,
.fuse_corr_alpha = 1106500,
.fuse_corr_beta = -6729300,
.group = &tegra124_tsensor_group_pll,
diff --git a/drivers/thermal/tegra/tegra132-soctherm.c b/drivers/thermal/tegra/tegra132-soctherm.c
index b76308fdad9e..2f211ae4d6e8 100644
--- a/drivers/thermal/tegra/tegra132-soctherm.c
+++ b/drivers/thermal/tegra/tegra132-soctherm.c
@@ -129,7 +129,6 @@ static struct tegra_tsensor tegra132_tsensors[] = {
.name = "cpu0",
.base = 0xc0,
.config = &tegra132_tsensor_config,
- .calib_fuse_offset = 0x098,
.fuse_corr_alpha = 1126600,
.fuse_corr_beta = -9433500,
.group = &tegra132_tsensor_group_cpu,
@@ -137,7 +136,6 @@ static struct tegra_tsensor tegra132_tsensors[] = {
.name = "cpu1",
.base = 0xe0,
.config = &tegra132_tsensor_config,
- .calib_fuse_offset = 0x084,
.fuse_corr_alpha = 1110800,
.fuse_corr_beta = -7383000,
.group = &tegra132_tsensor_group_cpu,
@@ -145,7 +143,6 @@ static struct tegra_tsensor tegra132_tsensors[] = {
.name = "cpu2",
.base = 0x100,
.config = &tegra132_tsensor_config,
- .calib_fuse_offset = 0x088,
.fuse_corr_alpha = 1113800,
.fuse_corr_beta = -6215200,
.group = &tegra132_tsensor_group_cpu,
@@ -153,7 +150,6 @@ static struct tegra_tsensor tegra132_tsensors[] = {
.name = "cpu3",
.base = 0x120,
.config = &tegra132_tsensor_config,
- .calib_fuse_offset = 0x12c,
.fuse_corr_alpha = 1129600,
.fuse_corr_beta = -8196100,
.group = &tegra132_tsensor_group_cpu,
@@ -161,7 +157,6 @@ static struct tegra_tsensor tegra132_tsensors[] = {
.name = "mem0",
.base = 0x140,
.config = &tegra132_tsensor_config,
- .calib_fuse_offset = 0x158,
.fuse_corr_alpha = 1132900,
.fuse_corr_beta = -6755300,
.group = &tegra132_tsensor_group_mem,
@@ -169,7 +164,6 @@ static struct tegra_tsensor tegra132_tsensors[] = {
.name = "mem1",
.base = 0x160,
.config = &tegra132_tsensor_config,
- .calib_fuse_offset = 0x15c,
.fuse_corr_alpha = 1142300,
.fuse_corr_beta = -7374200,
.group = &tegra132_tsensor_group_mem,
@@ -177,7 +171,6 @@ static struct tegra_tsensor tegra132_tsensors[] = {
.name = "gpu",
.base = 0x180,
.config = &tegra132_tsensor_config,
- .calib_fuse_offset = 0x154,
.fuse_corr_alpha = 1125100,
.fuse_corr_beta = -6350400,
.group = &tegra132_tsensor_group_gpu,
@@ -185,7 +178,6 @@ static struct tegra_tsensor tegra132_tsensors[] = {
.name = "pllx",
.base = 0x1a0,
.config = &tegra132_tsensor_config,
- .calib_fuse_offset = 0x160,
.fuse_corr_alpha = 1118100,
.fuse_corr_beta = -8208800,
.group = &tegra132_tsensor_group_pll,
diff --git a/drivers/thermal/tegra/tegra210-soctherm.c b/drivers/thermal/tegra/tegra210-soctherm.c
index d0ff793f18c5..b2f3c775c1bb 100644
--- a/drivers/thermal/tegra/tegra210-soctherm.c
+++ b/drivers/thermal/tegra/tegra210-soctherm.c
@@ -130,7 +130,6 @@ static const struct tegra_tsensor tegra210_tsensors[] = {
.name = "cpu0",
.base = 0xc0,
.config = &tegra210_tsensor_config,
- .calib_fuse_offset = 0x098,
.fuse_corr_alpha = 1085000,
.fuse_corr_beta = 3244200,
.group = &tegra210_tsensor_group_cpu,
@@ -138,7 +137,6 @@ static const struct tegra_tsensor tegra210_tsensors[] = {
.name = "cpu1",
.base = 0xe0,
.config = &tegra210_tsensor_config,
- .calib_fuse_offset = 0x084,
.fuse_corr_alpha = 1126200,
.fuse_corr_beta = -67500,
.group = &tegra210_tsensor_group_cpu,
@@ -146,7 +144,6 @@ static const struct tegra_tsensor tegra210_tsensors[] = {
.name = "cpu2",
.base = 0x100,
.config = &tegra210_tsensor_config,
- .calib_fuse_offset = 0x088,
.fuse_corr_alpha = 1098400,
.fuse_corr_beta = 2251100,
.group = &tegra210_tsensor_group_cpu,
@@ -154,7 +151,6 @@ static const struct tegra_tsensor tegra210_tsensors[] = {
.name = "cpu3",
.base = 0x120,
.config = &tegra210_tsensor_config,
- .calib_fuse_offset = 0x12c,
.fuse_corr_alpha = 1108000,
.fuse_corr_beta = 602700,
.group = &tegra210_tsensor_group_cpu,
@@ -162,7 +158,6 @@ static const struct tegra_tsensor tegra210_tsensors[] = {
.name = "mem0",
.base = 0x140,
.config = &tegra210_tsensor_config,
- .calib_fuse_offset = 0x158,
.fuse_corr_alpha = 1069200,
.fuse_corr_beta = 3549900,
.group = &tegra210_tsensor_group_mem,
@@ -170,7 +165,6 @@ static const struct tegra_tsensor tegra210_tsensors[] = {
.name = "mem1",
.base = 0x160,
.config = &tegra210_tsensor_config,
- .calib_fuse_offset = 0x15c,
.fuse_corr_alpha = 1173700,
.fuse_corr_beta = -6263600,
.group = &tegra210_tsensor_group_mem,
@@ -178,7 +172,6 @@ static const struct tegra_tsensor tegra210_tsensors[] = {
.name = "gpu",
.base = 0x180,
.config = &tegra210_tsensor_config,
- .calib_fuse_offset = 0x154,
.fuse_corr_alpha = 1074300,
.fuse_corr_beta = 2734900,
.group = &tegra210_tsensor_group_gpu,
@@ -186,7 +179,6 @@ static const struct tegra_tsensor tegra210_tsensors[] = {
.name = "pllx",
.base = 0x1a0,
.config = &tegra210_tsensor_config,
- .calib_fuse_offset = 0x160,
.fuse_corr_alpha = 1039700,
.fuse_corr_beta = 6829100,
.group = &tegra210_tsensor_group_pll,
--
2.22.0
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related
* Re: [PATCH 01/11] xen/arm: use dma-noncoherent.h calls for xen-swiotlb cache maintainance
From: Stefano Stabellini @ 2019-08-29 22:41 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Stefano Stabellini, Konrad Rzeszutek Wilk, x86, linux-kernel,
iommu, xen-devel, linux-arm-kernel
In-Reply-To: <20190826121944.515-2-hch@lst.de>
On Mon, 26 Aug 2019, Christoph Hellwig wrote:
> Reuse the arm64 code that uses the dma-direct/swiotlb helpers for DMA
> non-coherent devices.
This patch does a bunch of things not listed in the commit message, such
as moving the static inline functions to include/xen/arm/page-coherent.h
and removing xen_swiotlb_dma_mmap and xen_swiotlb_get_sgtable because
unnecessary.
I would prefer if they were separate patches (for bisectability). It's
OK if you want to keep it all in one patch but please list all changes
the commit message.
In any case, I looked at the patch in details and it does all the right
things -- it's correct.
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
> arch/arm/include/asm/device.h | 3 -
> arch/arm/include/asm/xen/page-coherent.h | 93 ----------------------
> arch/arm/mm/dma-mapping.c | 8 +-
> arch/arm64/include/asm/xen/page-coherent.h | 75 -----------------
> drivers/xen/swiotlb-xen.c | 49 +-----------
> include/xen/arm/page-coherent.h | 80 +++++++++++++++++++
> 6 files changed, 83 insertions(+), 225 deletions(-)
>
> diff --git a/arch/arm/include/asm/device.h b/arch/arm/include/asm/device.h
> index f6955b55c544..c675bc0d5aa8 100644
> --- a/arch/arm/include/asm/device.h
> +++ b/arch/arm/include/asm/device.h
> @@ -14,9 +14,6 @@ struct dev_archdata {
> #endif
> #ifdef CONFIG_ARM_DMA_USE_IOMMU
> struct dma_iommu_mapping *mapping;
> -#endif
> -#ifdef CONFIG_XEN
> - const struct dma_map_ops *dev_dma_ops;
> #endif
> unsigned int dma_coherent:1;
> unsigned int dma_ops_setup:1;
> diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h
> index 2c403e7c782d..27e984977402 100644
> --- a/arch/arm/include/asm/xen/page-coherent.h
> +++ b/arch/arm/include/asm/xen/page-coherent.h
> @@ -1,95 +1,2 @@
> /* SPDX-License-Identifier: GPL-2.0 */
> -#ifndef _ASM_ARM_XEN_PAGE_COHERENT_H
> -#define _ASM_ARM_XEN_PAGE_COHERENT_H
> -
> -#include <linux/dma-mapping.h>
> -#include <asm/page.h>
> #include <xen/arm/page-coherent.h>
> -
> -static inline const struct dma_map_ops *xen_get_dma_ops(struct device *dev)
> -{
> - if (dev && dev->archdata.dev_dma_ops)
> - return dev->archdata.dev_dma_ops;
> - return get_arch_dma_ops(NULL);
> -}
> -
> -static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
> - dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs)
> -{
> - return xen_get_dma_ops(hwdev)->alloc(hwdev, size, dma_handle, flags, attrs);
> -}
> -
> -static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
> - void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
> -{
> - xen_get_dma_ops(hwdev)->free(hwdev, size, cpu_addr, dma_handle, attrs);
> -}
> -
> -static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
> - dma_addr_t dev_addr, unsigned long offset, size_t size,
> - enum dma_data_direction dir, unsigned long attrs)
> -{
> - unsigned long page_pfn = page_to_xen_pfn(page);
> - unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
> - unsigned long compound_pages =
> - (1<<compound_order(page)) * XEN_PFN_PER_PAGE;
> - bool local = (page_pfn <= dev_pfn) &&
> - (dev_pfn - page_pfn < compound_pages);
> -
> - /*
> - * Dom0 is mapped 1:1, while the Linux page can span across
> - * multiple Xen pages, it's not possible for it to contain a
> - * mix of local and foreign Xen pages. So if the first xen_pfn
> - * == mfn the page is local otherwise it's a foreign page
> - * grant-mapped in dom0. If the page is local we can safely
> - * call the native dma_ops function, otherwise we call the xen
> - * specific function.
> - */
> - if (local)
> - xen_get_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
> - else
> - __xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
> -}
> -
> -static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
> - size_t size, enum dma_data_direction dir, unsigned long attrs)
> -{
> - unsigned long pfn = PFN_DOWN(handle);
> - /*
> - * Dom0 is mapped 1:1, while the Linux page can be spanned accross
> - * multiple Xen page, it's not possible to have a mix of local and
> - * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a
> - * foreign mfn will always return false. If the page is local we can
> - * safely call the native dma_ops function, otherwise we call the xen
> - * specific function.
> - */
> - if (pfn_valid(pfn)) {
> - if (xen_get_dma_ops(hwdev)->unmap_page)
> - xen_get_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
> - } else
> - __xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
> -}
> -
> -static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
> - dma_addr_t handle, size_t size, enum dma_data_direction dir)
> -{
> - unsigned long pfn = PFN_DOWN(handle);
> - if (pfn_valid(pfn)) {
> - if (xen_get_dma_ops(hwdev)->sync_single_for_cpu)
> - xen_get_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir);
> - } else
> - __xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
> -}
> -
> -static inline void xen_dma_sync_single_for_device(struct device *hwdev,
> - dma_addr_t handle, size_t size, enum dma_data_direction dir)
> -{
> - unsigned long pfn = PFN_DOWN(handle);
> - if (pfn_valid(pfn)) {
> - if (xen_get_dma_ops(hwdev)->sync_single_for_device)
> - xen_get_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir);
> - } else
> - __xen_dma_sync_single_for_device(hwdev, handle, size, dir);
> -}
> -
> -#endif /* _ASM_ARM_XEN_PAGE_COHERENT_H */
> diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
> index d42557ee69c2..738097396445 100644
> --- a/arch/arm/mm/dma-mapping.c
> +++ b/arch/arm/mm/dma-mapping.c
> @@ -1132,10 +1132,6 @@ static const struct dma_map_ops *arm_get_dma_map_ops(bool coherent)
> * 32-bit DMA.
> * Use the generic dma-direct / swiotlb ops code in that case, as that
> * handles bounce buffering for us.
> - *
> - * Note: this checks CONFIG_ARM_LPAE instead of CONFIG_SWIOTLB as the
> - * latter is also selected by the Xen code, but that code for now relies
> - * on non-NULL dev_dma_ops. To be cleaned up later.
> */
> if (IS_ENABLED(CONFIG_ARM_LPAE))
> return NULL;
> @@ -2363,10 +2359,8 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
> set_dma_ops(dev, dma_ops);
>
> #ifdef CONFIG_XEN
> - if (xen_initial_domain()) {
> - dev->archdata.dev_dma_ops = dev->dma_ops;
> + if (xen_initial_domain())
> dev->dma_ops = xen_dma_ops;
> - }
> #endif
> dev->archdata.dma_ops_setup = true;
> }
> diff --git a/arch/arm64/include/asm/xen/page-coherent.h b/arch/arm64/include/asm/xen/page-coherent.h
> index d88e56b90b93..27e984977402 100644
> --- a/arch/arm64/include/asm/xen/page-coherent.h
> +++ b/arch/arm64/include/asm/xen/page-coherent.h
> @@ -1,77 +1,2 @@
> /* SPDX-License-Identifier: GPL-2.0 */
> -#ifndef _ASM_ARM64_XEN_PAGE_COHERENT_H
> -#define _ASM_ARM64_XEN_PAGE_COHERENT_H
> -
> -#include <linux/dma-mapping.h>
> -#include <asm/page.h>
> #include <xen/arm/page-coherent.h>
> -
> -static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
> - dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs)
> -{
> - return dma_direct_alloc(hwdev, size, dma_handle, flags, attrs);
> -}
> -
> -static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
> - void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
> -{
> - dma_direct_free(hwdev, size, cpu_addr, dma_handle, attrs);
> -}
> -
> -static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
> - dma_addr_t handle, size_t size, enum dma_data_direction dir)
> -{
> - unsigned long pfn = PFN_DOWN(handle);
> -
> - if (pfn_valid(pfn))
> - dma_direct_sync_single_for_cpu(hwdev, handle, size, dir);
> - else
> - __xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
> -}
> -
> -static inline void xen_dma_sync_single_for_device(struct device *hwdev,
> - dma_addr_t handle, size_t size, enum dma_data_direction dir)
> -{
> - unsigned long pfn = PFN_DOWN(handle);
> - if (pfn_valid(pfn))
> - dma_direct_sync_single_for_device(hwdev, handle, size, dir);
> - else
> - __xen_dma_sync_single_for_device(hwdev, handle, size, dir);
> -}
> -
> -static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
> - dma_addr_t dev_addr, unsigned long offset, size_t size,
> - enum dma_data_direction dir, unsigned long attrs)
> -{
> - unsigned long page_pfn = page_to_xen_pfn(page);
> - unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
> - unsigned long compound_pages =
> - (1<<compound_order(page)) * XEN_PFN_PER_PAGE;
> - bool local = (page_pfn <= dev_pfn) &&
> - (dev_pfn - page_pfn < compound_pages);
> -
> - if (local)
> - dma_direct_map_page(hwdev, page, offset, size, dir, attrs);
> - else
> - __xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
> -}
> -
> -static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
> - size_t size, enum dma_data_direction dir, unsigned long attrs)
> -{
> - unsigned long pfn = PFN_DOWN(handle);
> - /*
> - * Dom0 is mapped 1:1, while the Linux page can be spanned accross
> - * multiple Xen page, it's not possible to have a mix of local and
> - * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a
> - * foreign mfn will always return false. If the page is local we can
> - * safely call the native dma_ops function, otherwise we call the xen
> - * specific function.
> - */
> - if (pfn_valid(pfn))
> - dma_direct_unmap_page(hwdev, handle, size, dir, attrs);
> - else
> - __xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
> -}
> -
> -#endif /* _ASM_ARM64_XEN_PAGE_COHERENT_H */
> diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
> index ae1df496bf38..b8808677ae1d 100644
> --- a/drivers/xen/swiotlb-xen.c
> +++ b/drivers/xen/swiotlb-xen.c
> @@ -547,51 +547,6 @@ xen_swiotlb_dma_supported(struct device *hwdev, u64 mask)
> return xen_virt_to_bus(xen_io_tlb_end - 1) <= mask;
> }
>
> -/*
> - * Create userspace mapping for the DMA-coherent memory.
> - * This function should be called with the pages from the current domain only,
> - * passing pages mapped from other domains would lead to memory corruption.
> - */
> -static int
> -xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma,
> - void *cpu_addr, dma_addr_t dma_addr, size_t size,
> - unsigned long attrs)
> -{
> -#ifdef CONFIG_ARM
> - if (xen_get_dma_ops(dev)->mmap)
> - return xen_get_dma_ops(dev)->mmap(dev, vma, cpu_addr,
> - dma_addr, size, attrs);
> -#endif
> - return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
> -}
> -
> -/*
> - * This function should be called with the pages from the current domain only,
> - * passing pages mapped from other domains would lead to memory corruption.
> - */
> -static int
> -xen_swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
> - void *cpu_addr, dma_addr_t handle, size_t size,
> - unsigned long attrs)
> -{
> -#ifdef CONFIG_ARM
> - if (xen_get_dma_ops(dev)->get_sgtable) {
> -#if 0
> - /*
> - * This check verifies that the page belongs to the current domain and
> - * is not one mapped from another domain.
> - * This check is for debug only, and should not go to production build
> - */
> - unsigned long bfn = PHYS_PFN(dma_to_phys(dev, handle));
> - BUG_ON (!page_is_ram(bfn));
> -#endif
> - return xen_get_dma_ops(dev)->get_sgtable(dev, sgt, cpu_addr,
> - handle, size, attrs);
> - }
> -#endif
> - return dma_common_get_sgtable(dev, sgt, cpu_addr, handle, size, attrs);
> -}
> -
> const struct dma_map_ops xen_swiotlb_dma_ops = {
> .alloc = xen_swiotlb_alloc_coherent,
> .free = xen_swiotlb_free_coherent,
> @@ -604,6 +559,6 @@ const struct dma_map_ops xen_swiotlb_dma_ops = {
> .map_page = xen_swiotlb_map_page,
> .unmap_page = xen_swiotlb_unmap_page,
> .dma_supported = xen_swiotlb_dma_supported,
> - .mmap = xen_swiotlb_dma_mmap,
> - .get_sgtable = xen_swiotlb_get_sgtable,
> + .mmap = dma_common_mmap,
> + .get_sgtable = dma_common_get_sgtable,
> };
> diff --git a/include/xen/arm/page-coherent.h b/include/xen/arm/page-coherent.h
> index 2ca9164a79bf..a840d6949a87 100644
> --- a/include/xen/arm/page-coherent.h
> +++ b/include/xen/arm/page-coherent.h
> @@ -2,6 +2,9 @@
> #ifndef _XEN_ARM_PAGE_COHERENT_H
> #define _XEN_ARM_PAGE_COHERENT_H
>
> +#include <linux/dma-mapping.h>
> +#include <asm/page.h>
> +
> void __xen_dma_map_page(struct device *hwdev, struct page *page,
> dma_addr_t dev_addr, unsigned long offset, size_t size,
> enum dma_data_direction dir, unsigned long attrs);
> @@ -13,4 +16,81 @@ void __xen_dma_sync_single_for_cpu(struct device *hwdev,
> void __xen_dma_sync_single_for_device(struct device *hwdev,
> dma_addr_t handle, size_t size, enum dma_data_direction dir);
>
> +static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
> + dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs)
> +{
> + return dma_direct_alloc(hwdev, size, dma_handle, flags, attrs);
> +}
> +
> +static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
> + void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
> +{
> + dma_direct_free(hwdev, size, cpu_addr, dma_handle, attrs);
> +}
> +
> +static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
> + dma_addr_t handle, size_t size, enum dma_data_direction dir)
> +{
> + unsigned long pfn = PFN_DOWN(handle);
> +
> + if (pfn_valid(pfn))
> + dma_direct_sync_single_for_cpu(hwdev, handle, size, dir);
> + else
> + __xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
> +}
> +
> +static inline void xen_dma_sync_single_for_device(struct device *hwdev,
> + dma_addr_t handle, size_t size, enum dma_data_direction dir)
> +{
> + unsigned long pfn = PFN_DOWN(handle);
> + if (pfn_valid(pfn))
> + dma_direct_sync_single_for_device(hwdev, handle, size, dir);
> + else
> + __xen_dma_sync_single_for_device(hwdev, handle, size, dir);
> +}
> +
> +static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
> + dma_addr_t dev_addr, unsigned long offset, size_t size,
> + enum dma_data_direction dir, unsigned long attrs)
> +{
> + unsigned long page_pfn = page_to_xen_pfn(page);
> + unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
> + unsigned long compound_pages =
> + (1<<compound_order(page)) * XEN_PFN_PER_PAGE;
> + bool local = (page_pfn <= dev_pfn) &&
> + (dev_pfn - page_pfn < compound_pages);
> +
> + /*
> + * Dom0 is mapped 1:1, while the Linux page can span across
> + * multiple Xen pages, it's not possible for it to contain a
> + * mix of local and foreign Xen pages. So if the first xen_pfn
> + * == mfn the page is local otherwise it's a foreign page
> + * grant-mapped in dom0. If the page is local we can safely
> + * call the native dma_ops function, otherwise we call the xen
> + * specific function.
> + */
> + if (local)
> + dma_direct_map_page(hwdev, page, offset, size, dir, attrs);
> + else
> + __xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
> +}
> +
> +static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
> + size_t size, enum dma_data_direction dir, unsigned long attrs)
> +{
> + unsigned long pfn = PFN_DOWN(handle);
> + /*
> + * Dom0 is mapped 1:1, while the Linux page can be spanned accross
> + * multiple Xen page, it's not possible to have a mix of local and
> + * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a
> + * foreign mfn will always return false. If the page is local we can
> + * safely call the native dma_ops function, otherwise we call the xen
> + * specific function.
> + */
> + if (pfn_valid(pfn))
> + dma_direct_unmap_page(hwdev, handle, size, dir, attrs);
> + else
> + __xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
> +}
> +
> #endif /* _XEN_ARM_PAGE_COHERENT_H */
> --
> 2.20.1
>
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply
* Re: [PATCH 02/11] xen/arm: use dev_is_dma_coherent
From: Stefano Stabellini @ 2019-08-29 22:41 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Julien Grall, Stefano Stabellini, Konrad Rzeszutek Wilk, x86,
linux-kernel, iommu, xen-devel, linux-arm-kernel
In-Reply-To: <20190826121944.515-3-hch@lst.de>
On Mon, 26 Aug 2019, Christoph Hellwig wrote:
> Use the dma-noncoherent dev_is_dma_coherent helper instead of the home
> grown variant. Note that both are always initialized to the same
> value in arch_setup_dma_ops.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> Reviewed-by: Julien Grall <julien.grall@arm.com>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
> ---
> arch/arm/include/asm/dma-mapping.h | 6 ------
> arch/arm/xen/mm.c | 12 ++++++------
> arch/arm64/include/asm/dma-mapping.h | 9 ---------
> 3 files changed, 6 insertions(+), 21 deletions(-)
>
> diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
> index dba9355e2484..bdd80ddbca34 100644
> --- a/arch/arm/include/asm/dma-mapping.h
> +++ b/arch/arm/include/asm/dma-mapping.h
> @@ -91,12 +91,6 @@ static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
> }
> #endif
>
> -/* do not use this function in a driver */
> -static inline bool is_device_dma_coherent(struct device *dev)
> -{
> - return dev->archdata.dma_coherent;
> -}
> -
> /**
> * arm_dma_alloc - allocate consistent memory for DMA
> * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
> diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
> index d33b77e9add3..90574d89d0d4 100644
> --- a/arch/arm/xen/mm.c
> +++ b/arch/arm/xen/mm.c
> @@ -1,6 +1,6 @@
> // SPDX-License-Identifier: GPL-2.0-only
> #include <linux/cpu.h>
> -#include <linux/dma-mapping.h>
> +#include <linux/dma-noncoherent.h>
> #include <linux/gfp.h>
> #include <linux/highmem.h>
> #include <linux/export.h>
> @@ -99,7 +99,7 @@ void __xen_dma_map_page(struct device *hwdev, struct page *page,
> dma_addr_t dev_addr, unsigned long offset, size_t size,
> enum dma_data_direction dir, unsigned long attrs)
> {
> - if (is_device_dma_coherent(hwdev))
> + if (dev_is_dma_coherent(hwdev))
> return;
> if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
> return;
> @@ -112,7 +112,7 @@ void __xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
> unsigned long attrs)
>
> {
> - if (is_device_dma_coherent(hwdev))
> + if (dev_is_dma_coherent(hwdev))
> return;
> if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
> return;
> @@ -123,7 +123,7 @@ void __xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
> void __xen_dma_sync_single_for_cpu(struct device *hwdev,
> dma_addr_t handle, size_t size, enum dma_data_direction dir)
> {
> - if (is_device_dma_coherent(hwdev))
> + if (dev_is_dma_coherent(hwdev))
> return;
> __xen_dma_page_dev_to_cpu(hwdev, handle, size, dir);
> }
> @@ -131,7 +131,7 @@ void __xen_dma_sync_single_for_cpu(struct device *hwdev,
> void __xen_dma_sync_single_for_device(struct device *hwdev,
> dma_addr_t handle, size_t size, enum dma_data_direction dir)
> {
> - if (is_device_dma_coherent(hwdev))
> + if (dev_is_dma_coherent(hwdev))
> return;
> __xen_dma_page_cpu_to_dev(hwdev, handle, size, dir);
> }
> @@ -159,7 +159,7 @@ bool xen_arch_need_swiotlb(struct device *dev,
> * memory and we are not able to flush the cache.
> */
> return (!hypercall_cflush && (xen_pfn != bfn) &&
> - !is_device_dma_coherent(dev));
> + !dev_is_dma_coherent(dev));
> }
>
> int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
> diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
> index bdcb0922a40c..67243255a858 100644
> --- a/arch/arm64/include/asm/dma-mapping.h
> +++ b/arch/arm64/include/asm/dma-mapping.h
> @@ -18,14 +18,5 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
> return NULL;
> }
>
> -/*
> - * Do not use this function in a driver, it is only provided for
> - * arch/arm/mm/xen.c, which is used by arm64 as well.
> - */
> -static inline bool is_device_dma_coherent(struct device *dev)
> -{
> - return dev->dma_coherent;
> -}
> -
> #endif /* __KERNEL__ */
> #endif /* __ASM_DMA_MAPPING_H */
> --
> 2.20.1
>
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply
* Re: [PATCH 03/11] xen/arm: simplify dma_cache_maint
From: Stefano Stabellini @ 2019-08-29 22:41 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Stefano Stabellini, Konrad Rzeszutek Wilk, x86, linux-kernel,
iommu, xen-devel, linux-arm-kernel
In-Reply-To: <20190826121944.515-4-hch@lst.de>
On Mon, 26 Aug 2019, Christoph Hellwig wrote:
> Calculate the required operation in the caller, and pass it directly
> instead of recalculating it for each page, and use simple arithmetics
> to get from the physical address to Xen page size aligned chunks.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
> arch/arm/xen/mm.c | 62 +++++++++++++++++------------------------------
> 1 file changed, 22 insertions(+), 40 deletions(-)
>
> diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
> index 90574d89d0d4..14210ebdea1a 100644
> --- a/arch/arm/xen/mm.c
> +++ b/arch/arm/xen/mm.c
> @@ -35,64 +35,46 @@ unsigned long xen_get_swiotlb_free_pages(unsigned int order)
> return __get_free_pages(flags, order);
> }
>
> -enum dma_cache_op {
> - DMA_UNMAP,
> - DMA_MAP,
> -};
> static bool hypercall_cflush = false;
>
> -/* functions called by SWIOTLB */
> -
> -static void dma_cache_maint(dma_addr_t handle, unsigned long offset,
> - size_t size, enum dma_data_direction dir, enum dma_cache_op op)
> +/* buffers in highmem or foreign pages cannot cross page boundaries */
> +static void dma_cache_maint(dma_addr_t handle, size_t size, u32 op)
> {
> struct gnttab_cache_flush cflush;
> - unsigned long xen_pfn;
> - size_t left = size;
>
> - xen_pfn = (handle >> XEN_PAGE_SHIFT) + offset / XEN_PAGE_SIZE;
> - offset %= XEN_PAGE_SIZE;
> + cflush.a.dev_bus_addr = handle & XEN_PAGE_MASK;
> + cflush.offset = xen_offset_in_page(handle);
> + cflush.op = op;
>
> do {
> - size_t len = left;
> -
> - /* buffers in highmem or foreign pages cannot cross page
> - * boundaries */
> - if (len + offset > XEN_PAGE_SIZE)
> - len = XEN_PAGE_SIZE - offset;
> -
> - cflush.op = 0;
> - cflush.a.dev_bus_addr = xen_pfn << XEN_PAGE_SHIFT;
> - cflush.offset = offset;
> - cflush.length = len;
> -
> - if (op == DMA_UNMAP && dir != DMA_TO_DEVICE)
> - cflush.op = GNTTAB_CACHE_INVAL;
> - if (op == DMA_MAP) {
> - if (dir == DMA_FROM_DEVICE)
> - cflush.op = GNTTAB_CACHE_INVAL;
> - else
> - cflush.op = GNTTAB_CACHE_CLEAN;
> - }
> - if (cflush.op)
> - HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1);
> + if (size + cflush.offset > XEN_PAGE_SIZE)
> + cflush.length = XEN_PAGE_SIZE - cflush.offset;
> + else
> + cflush.length = size;
isn't it missing a:
cflush.a.dev_bus_addr = handle & XEN_PAGE_MASK;
here?
> + HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1);
> +
> + handle += cflush.length;
> + size -= cflush.length;
>
> - offset = 0;
> - xen_pfn++;
> - left -= len;
> - } while (left);
> + cflush.offset = 0;
> + } while (size);
> }
>
> static void __xen_dma_page_dev_to_cpu(struct device *hwdev, dma_addr_t handle,
> size_t size, enum dma_data_direction dir)
> {
> - dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, DMA_UNMAP);
> + if (dir != DMA_TO_DEVICE)
> + dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL);
> }
>
> static void __xen_dma_page_cpu_to_dev(struct device *hwdev, dma_addr_t handle,
> size_t size, enum dma_data_direction dir)
> {
> - dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, DMA_MAP);
> + if (dir == DMA_FROM_DEVICE)
> + dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL);
> + else
> + dma_cache_maint(handle, size, GNTTAB_CACHE_CLEAN);
> }
>
> void __xen_dma_map_page(struct device *hwdev, struct page *page,
> --
> 2.20.1
>
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply
* Re: [PATCH 04/11] xen/arm: remove xen_dma_ops
From: Stefano Stabellini @ 2019-08-29 22:42 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Julien Grall, Stefano Stabellini, Konrad Rzeszutek Wilk, x86,
linux-kernel, iommu, xen-devel, linux-arm-kernel
In-Reply-To: <20190826121944.515-5-hch@lst.de>
On Mon, 26 Aug 2019, Christoph Hellwig wrote:
> arm and arm64 can just use xen_swiotlb_dma_ops directly like x86, no
> need for a pointer indirection.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> Reviewed-by: Julien Grall <julien.grall@arm.com>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
> ---
> arch/arm/mm/dma-mapping.c | 3 ++-
> arch/arm/xen/mm.c | 4 ----
> arch/arm64/mm/dma-mapping.c | 3 ++-
> include/xen/arm/hypervisor.h | 2 --
> 4 files changed, 4 insertions(+), 8 deletions(-)
>
> diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
> index 738097396445..2661cad36359 100644
> --- a/arch/arm/mm/dma-mapping.c
> +++ b/arch/arm/mm/dma-mapping.c
> @@ -35,6 +35,7 @@
> #include <asm/mach/map.h>
> #include <asm/system_info.h>
> #include <asm/dma-contiguous.h>
> +#include <xen/swiotlb-xen.h>
>
> #include "dma.h"
> #include "mm.h"
> @@ -2360,7 +2361,7 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
>
> #ifdef CONFIG_XEN
> if (xen_initial_domain())
> - dev->dma_ops = xen_dma_ops;
> + dev->dma_ops = &xen_swiotlb_dma_ops;
> #endif
> dev->archdata.dma_ops_setup = true;
> }
> diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
> index 14210ebdea1a..9b3a6c0ca681 100644
> --- a/arch/arm/xen/mm.c
> +++ b/arch/arm/xen/mm.c
> @@ -163,16 +163,12 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
> }
> EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region);
>
> -const struct dma_map_ops *xen_dma_ops;
> -EXPORT_SYMBOL(xen_dma_ops);
> -
> int __init xen_mm_init(void)
> {
> struct gnttab_cache_flush cflush;
> if (!xen_initial_domain())
> return 0;
> xen_swiotlb_init(1, false);
> - xen_dma_ops = &xen_swiotlb_dma_ops;
>
> cflush.op = 0;
> cflush.a.dev_bus_addr = 0;
> diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
> index bd2b039f43a6..4b244a037349 100644
> --- a/arch/arm64/mm/dma-mapping.c
> +++ b/arch/arm64/mm/dma-mapping.c
> @@ -8,6 +8,7 @@
> #include <linux/cache.h>
> #include <linux/dma-noncoherent.h>
> #include <linux/dma-iommu.h>
> +#include <xen/swiotlb-xen.h>
>
> #include <asm/cacheflush.h>
>
> @@ -64,6 +65,6 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
>
> #ifdef CONFIG_XEN
> if (xen_initial_domain())
> - dev->dma_ops = xen_dma_ops;
> + dev->dma_ops = &xen_swiotlb_dma_ops;
> #endif
> }
> diff --git a/include/xen/arm/hypervisor.h b/include/xen/arm/hypervisor.h
> index 2982571f7cc1..43ef24dd030e 100644
> --- a/include/xen/arm/hypervisor.h
> +++ b/include/xen/arm/hypervisor.h
> @@ -19,8 +19,6 @@ static inline enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
> return PARAVIRT_LAZY_NONE;
> }
>
> -extern const struct dma_map_ops *xen_dma_ops;
> -
> #ifdef CONFIG_XEN
> void __init xen_early_init(void);
> #else
> --
> 2.20.1
>
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply
* Re: [PATCH 05/11] xen: remove the exports for xen_{create,destroy}_contiguous_region
From: Stefano Stabellini @ 2019-08-29 22:42 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Stefano Stabellini, Konrad Rzeszutek Wilk, x86, linux-kernel,
iommu, xen-devel, linux-arm-kernel
In-Reply-To: <20190826121944.515-6-hch@lst.de>
On Mon, 26 Aug 2019, Christoph Hellwig wrote:
> These routines are only used by swiotlb-xen, which cannot be modular.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
> ---
> arch/arm/xen/mm.c | 2 --
> arch/x86/xen/mmu_pv.c | 2 --
> 2 files changed, 4 deletions(-)
>
> diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
> index 9b3a6c0ca681..b7d53415532b 100644
> --- a/arch/arm/xen/mm.c
> +++ b/arch/arm/xen/mm.c
> @@ -155,13 +155,11 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
> *dma_handle = pstart;
> return 0;
> }
> -EXPORT_SYMBOL_GPL(xen_create_contiguous_region);
>
> void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
> {
> return;
> }
> -EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region);
>
> int __init xen_mm_init(void)
> {
> diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
> index 26e8b326966d..c8dbee62ec2a 100644
> --- a/arch/x86/xen/mmu_pv.c
> +++ b/arch/x86/xen/mmu_pv.c
> @@ -2625,7 +2625,6 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
> *dma_handle = virt_to_machine(vstart).maddr;
> return success ? 0 : -ENOMEM;
> }
> -EXPORT_SYMBOL_GPL(xen_create_contiguous_region);
>
> void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
> {
> @@ -2660,7 +2659,6 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
>
> spin_unlock_irqrestore(&xen_reservation_lock, flags);
> }
> -EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region);
>
> static noinline void xen_flush_tlb_all(void)
> {
> --
> 2.20.1
>
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply
* Re: [RESEND PATCH 1/5] dt-bindings: net: Add compatible for BCM4345C5 bluetooth device
From: Rob Herring @ 2019-08-29 22:45 UTC (permalink / raw)
To: megous
Cc: Mark Rutland, devicetree, Ondrej Jirman, Johan Hedberg, netdev,
Marcel Holtmann, linux-kernel, Maxime Ripard, linux-bluetooth,
Chen-Yu Tsai, David S. Miller, linux-arm-kernel
In-Reply-To: <20190823103139.17687-2-megous@megous.com>
On Fri, 23 Aug 2019 12:31:35 +0200, megous@megous.com wrote:
> From: Ondrej Jirman <megous@megous.com>
>
> This is present in the AP6526 WiFi/Bluetooth 5.0 module.
>
> Signed-off-by: Ondrej Jirman <megous@megous.com>
> ---
> Documentation/devicetree/bindings/net/broadcom-bluetooth.txt | 1 +
> 1 file changed, 1 insertion(+)
>
Acked-by: Rob Herring <robh@kernel.org>
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply
* [PATCH 2/7] dt-bindings: arm-smmu: Add binding for nvidia,smmu-v2
From: Krishna Reddy @ 2019-08-29 22:47 UTC (permalink / raw)
Cc: snikam, thomasz, jtukkinen, mperttunen, praithatha, iommu,
linux-kernel, talho, olof, yhsu, linux-tegra, treding, avanbrunt,
linux-arm-kernel
In-Reply-To: <1567118827-26358-1-git-send-email-vdumpa@nvidia.com>
Add binding doc for Nvidia's smmu-v2 implementation.
Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
---
Documentation/devicetree/bindings/iommu/arm,smmu.txt | 1 +
1 file changed, 1 insertion(+)
diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.txt b/Documentation/devicetree/bindings/iommu/arm,smmu.txt
index 3133f3b..0de3759 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu.txt
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu.txt
@@ -17,6 +17,7 @@ conditions.
"arm,mmu-401"
"arm,mmu-500"
"cavium,smmu-v2"
+ "nidia,smmu-v2"
"qcom,smmu-v2"
depending on the particular implementation and/or the
--
2.1.4
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related
* [PATCH 6/7] arm64: tegra: Add DT node for T194 SMMU
From: Krishna Reddy @ 2019-08-29 22:47 UTC (permalink / raw)
Cc: snikam, thomasz, jtukkinen, mperttunen, praithatha, iommu,
linux-kernel, talho, olof, yhsu, linux-tegra, treding, avanbrunt,
linux-arm-kernel
In-Reply-To: <1567118827-26358-1-git-send-email-vdumpa@nvidia.com>
Add DT node for T194 SMMU to enable SMMU support.
Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
---
arch/arm64/boot/dts/nvidia/tegra194.dtsi | 75 ++++++++++++++++++++++++++++++++
1 file changed, 75 insertions(+)
diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
index d906958..ad509bb 100644
--- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
@@ -1401,6 +1401,81 @@
0x82000000 0x0 0x40000000 0x1f 0x40000000 0x0 0xc0000000>; /* non-prefetchable memory (3GB) */
};
+ smmu: iommu@12000000 {
+ compatible = "nvidia,smmu-v2";
+ reg = <0 0x12000000 0 0x800000>,
+ <0 0x11000000 0 0x800000>,
+ <0 0x10000000 0 0x800000>;
+ interrupts = <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 232 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 240 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>;
+ stream-match-mask = <0x7f80>;
+ #global-interrupts = <1>;
+ #iommu-cells = <1>;
+ };
+
sysram@40000000 {
compatible = "nvidia,tegra194-sysram", "mmio-sram";
reg = <0x0 0x40000000 0x0 0x50000>;
--
2.1.4
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related
* [PATCH 7/7] arm64: tegra: enable SMMU for SDHCI and EQOS
From: Krishna Reddy @ 2019-08-29 22:47 UTC (permalink / raw)
Cc: snikam, thomasz, jtukkinen, mperttunen, praithatha, iommu,
linux-kernel, talho, olof, yhsu, linux-tegra, treding, avanbrunt,
linux-arm-kernel
In-Reply-To: <1567118827-26358-1-git-send-email-vdumpa@nvidia.com>
Enable SMMU translations for SDHCI and EQOS transactions.
Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
---
arch/arm64/boot/dts/nvidia/tegra194.dtsi | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
index ad509bb..0496a87 100644
--- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
@@ -51,6 +51,7 @@
clock-names = "master_bus", "slave_bus", "rx", "tx", "ptp_ref";
resets = <&bpmp TEGRA194_RESET_EQOS>;
reset-names = "eqos";
+ iommus = <&smmu TEGRA186_SID_EQOS>;
status = "disabled";
snps,write-requests = <1>;
@@ -381,6 +382,7 @@
clock-names = "sdhci";
resets = <&bpmp TEGRA194_RESET_SDMMC1>;
reset-names = "sdhci";
+ iommus = <&smmu TEGRA186_SID_SDMMC1>;
nvidia,pad-autocal-pull-up-offset-3v3-timeout =
<0x07>;
nvidia,pad-autocal-pull-down-offset-3v3-timeout =
@@ -403,6 +405,7 @@
clock-names = "sdhci";
resets = <&bpmp TEGRA194_RESET_SDMMC3>;
reset-names = "sdhci";
+ iommus = <&smmu TEGRA186_SID_SDMMC3>;
nvidia,pad-autocal-pull-up-offset-1v8 = <0x00>;
nvidia,pad-autocal-pull-down-offset-1v8 = <0x7a>;
nvidia,pad-autocal-pull-up-offset-3v3-timeout = <0x07>;
@@ -430,6 +433,7 @@
<&bpmp TEGRA194_CLK_PLLC4>;
resets = <&bpmp TEGRA194_RESET_SDMMC4>;
reset-names = "sdhci";
+ iommus = <&smmu TEGRA186_SID_SDMMC4>;
nvidia,pad-autocal-pull-up-offset-hs400 = <0x00>;
nvidia,pad-autocal-pull-down-offset-hs400 = <0x00>;
nvidia,pad-autocal-pull-up-offset-1v8-timeout = <0x0a>;
--
2.1.4
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related
* [PATCH 5/7] arm64: tegra: Add Memory controller DT node on T194
From: Krishna Reddy @ 2019-08-29 22:47 UTC (permalink / raw)
Cc: snikam, thomasz, jtukkinen, mperttunen, praithatha, iommu,
linux-kernel, talho, olof, yhsu, linux-tegra, treding, avanbrunt,
linux-arm-kernel
In-Reply-To: <1567118827-26358-1-git-send-email-vdumpa@nvidia.com>
Add Memory controller DT node on T194 and enable it.
This patch is a prerequisite for SMMU enable on T194.
Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
---
arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi | 4 ++++
arch/arm64/boot/dts/nvidia/tegra194.dtsi | 7 +++++++
2 files changed, 11 insertions(+)
diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi b/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi
index 62e07e11..4b3441b 100644
--- a/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi
@@ -47,6 +47,10 @@
};
};
+ memory-controller@2c00000 {
+ status = "okay";
+ };
+
serial@3110000 {
status = "okay";
};
diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
index adebbbf..d906958 100644
--- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
@@ -6,6 +6,7 @@
#include <dt-bindings/reset/tegra194-reset.h>
#include <dt-bindings/power/tegra194-powergate.h>
#include <dt-bindings/thermal/tegra194-bpmp-thermal.h>
+#include <dt-bindings/memory/tegra186-mc.h>
/ {
compatible = "nvidia,tegra194";
@@ -130,6 +131,12 @@
};
};
+ memory-controller@2c00000 {
+ compatible = "nvidia,tegra186-mc";
+ reg = <0x02c00000 0xb0000>;
+ status = "disabled";
+ };
+
uarta: serial@3100000 {
compatible = "nvidia,tegra194-uart", "nvidia,tegra20-uart";
reg = <0x03100000 0x40>;
--
2.1.4
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related
* [PATCH 1/7] iommu/arm-smmu: add Nvidia SMMUv2 implementation
From: Krishna Reddy @ 2019-08-29 22:47 UTC (permalink / raw)
Cc: snikam, thomasz, jtukkinen, mperttunen, praithatha, iommu,
linux-kernel, talho, olof, yhsu, linux-tegra, treding, avanbrunt,
linux-arm-kernel
In-Reply-To: <1567118827-26358-1-git-send-email-vdumpa@nvidia.com>
Add Nvidia SMMUv2 implementation and model info.
Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
---
MAINTAINERS | 2 +
drivers/iommu/Makefile | 2 +-
drivers/iommu/arm-smmu-impl.c | 2 +
drivers/iommu/arm-smmu-nvidia.c | 97 +++++++++++++++++++++++++++++++++++++++++
drivers/iommu/arm-smmu.c | 2 +
drivers/iommu/arm-smmu.h | 2 +
6 files changed, 106 insertions(+), 1 deletion(-)
create mode 100644 drivers/iommu/arm-smmu-nvidia.c
diff --git a/MAINTAINERS b/MAINTAINERS
index 289fb06..b9d59e51 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15785,9 +15785,11 @@ F: drivers/i2c/busses/i2c-tegra.c
TEGRA IOMMU DRIVERS
M: Thierry Reding <thierry.reding@gmail.com>
+R: Krishna Reddy <vdumpa@nvidia.com>
L: linux-tegra@vger.kernel.org
S: Supported
F: drivers/iommu/tegra*
+F: drivers/iommu/arm-smmu-nvidia.c
TEGRA KBC DRIVER
M: Laxman Dewangan <ldewangan@nvidia.com>
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index a2729aa..7f5489e 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -13,7 +13,7 @@ obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o
obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o
obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd_iommu_debugfs.o
obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o
-obj-$(CONFIG_ARM_SMMU) += arm-smmu.o arm-smmu-impl.o
+obj-$(CONFIG_ARM_SMMU) += arm-smmu.o arm-smmu-impl.o arm-smmu-nvidia.o
obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o
obj-$(CONFIG_DMAR_TABLE) += dmar.o
obj-$(CONFIG_INTEL_IOMMU) += intel-iommu.o intel-pasid.o
diff --git a/drivers/iommu/arm-smmu-impl.c b/drivers/iommu/arm-smmu-impl.c
index 5c87a38..e5e595f 100644
--- a/drivers/iommu/arm-smmu-impl.c
+++ b/drivers/iommu/arm-smmu-impl.c
@@ -162,6 +162,8 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
break;
case CAVIUM_SMMUV2:
return cavium_smmu_impl_init(smmu);
+ case NVIDIA_SMMUV2:
+ return nvidia_smmu_impl_init(smmu);
default:
break;
}
diff --git a/drivers/iommu/arm-smmu-nvidia.c b/drivers/iommu/arm-smmu-nvidia.c
new file mode 100644
index 0000000..d93ceda
--- /dev/null
+++ b/drivers/iommu/arm-smmu-nvidia.c
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Nvidia ARM SMMU v2 implementation quirks
+// Copyright (C) 2019 NVIDIA CORPORATION. All rights reserved.
+
+#define pr_fmt(fmt) "nvidia-smmu: " fmt
+
+#include <linux/bitfield.h>
+#include <linux/delay.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include "arm-smmu.h"
+
+#define NUM_SMMU_INSTANCES 3
+
+struct nvidia_smmu {
+ struct arm_smmu_device smmu;
+ int num_inst;
+ void __iomem *bases[NUM_SMMU_INSTANCES];
+};
+
+#define to_nsmmu(s) container_of(s, struct nvidia_smmu, smmu)
+
+#define nsmmu_page(smmu, inst, page) \
+ (((inst) ? to_nsmmu(smmu)->bases[(inst)] : smmu->base) + \
+ ((page) << smmu->pgshift))
+
+static u32 nsmmu_read_reg(struct arm_smmu_device *smmu,
+ int page, int offset)
+{
+ return readl_relaxed(nsmmu_page(smmu, 0, page) + offset);
+}
+
+static void nsmmu_write_reg(struct arm_smmu_device *smmu,
+ int page, int offset, u32 val)
+{
+ int i;
+
+ for (i = 0; i < to_nsmmu(smmu)->num_inst; i++)
+ writel_relaxed(val, nsmmu_page(smmu, i, page) + offset);
+}
+
+static u64 nsmmu_read_reg64(struct arm_smmu_device *smmu,
+ int page, int offset)
+{
+ return readq_relaxed(nsmmu_page(smmu, 0, page) + offset);
+}
+
+static void nsmmu_write_reg64(struct arm_smmu_device *smmu,
+ int page, int offset, u64 val)
+{
+ int i;
+
+ for (i = 0; i < to_nsmmu(smmu)->num_inst; i++)
+ writeq_relaxed(val, nsmmu_page(smmu, i, page) + offset);
+}
+
+static const struct arm_smmu_impl nsmmu_impl = {
+ .read_reg = nsmmu_read_reg,
+ .write_reg = nsmmu_write_reg,
+ .read_reg64 = nsmmu_read_reg64,
+ .write_reg64 = nsmmu_write_reg64,
+};
+
+struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu)
+{
+ int i;
+ struct nvidia_smmu *nsmmu;
+ struct resource *res;
+ struct device *dev = smmu->dev;
+ struct platform_device *pdev = to_platform_device(smmu->dev);
+
+ nsmmu = devm_kzalloc(smmu->dev, sizeof(*nsmmu), GFP_KERNEL);
+ if (!nsmmu)
+ return ERR_PTR(-ENOMEM);
+
+ nsmmu->smmu = *smmu;
+ /* Instance 0 is ioremapped by arm-smmu.c */
+ nsmmu->num_inst = 1;
+
+ for (i = 1; i < NUM_SMMU_INSTANCES; i++) {
+ res = platform_get_resource(pdev, IORESOURCE_MEM, i);
+ if (!res)
+ break;
+ nsmmu->bases[i] = devm_ioremap_resource(dev, res);
+ if (IS_ERR(nsmmu->bases[i]))
+ return (struct arm_smmu_device *)nsmmu->bases[i];
+ nsmmu->num_inst++;
+ }
+
+ nsmmu->smmu.impl = &nsmmu_impl;
+ devm_kfree(smmu->dev, smmu);
+ pr_info("Nvidia SMMUv2, Instances=%d\n", nsmmu->num_inst);
+
+ return &nsmmu->smmu;
+}
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 5b93c79..46e1641 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -1871,6 +1871,7 @@ ARM_SMMU_MATCH_DATA(arm_mmu401, ARM_SMMU_V1_64K, GENERIC_SMMU);
ARM_SMMU_MATCH_DATA(arm_mmu500, ARM_SMMU_V2, ARM_MMU500);
ARM_SMMU_MATCH_DATA(cavium_smmuv2, ARM_SMMU_V2, CAVIUM_SMMUV2);
ARM_SMMU_MATCH_DATA(qcom_smmuv2, ARM_SMMU_V2, QCOM_SMMUV2);
+ARM_SMMU_MATCH_DATA(nvidia_smmuv2, ARM_SMMU_V2, NVIDIA_SMMUV2);
static const struct of_device_id arm_smmu_of_match[] = {
{ .compatible = "arm,smmu-v1", .data = &smmu_generic_v1 },
@@ -1880,6 +1881,7 @@ static const struct of_device_id arm_smmu_of_match[] = {
{ .compatible = "arm,mmu-500", .data = &arm_mmu500 },
{ .compatible = "cavium,smmu-v2", .data = &cavium_smmuv2 },
{ .compatible = "qcom,smmu-v2", .data = &qcom_smmuv2 },
+ { .compatible = "nvidia,smmu-v2", .data = &nvidia_smmuv2 },
{ },
};
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index b19b6ca..9645bf1 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -220,6 +220,7 @@ enum arm_smmu_implementation {
ARM_MMU500,
CAVIUM_SMMUV2,
QCOM_SMMUV2,
+ NVIDIA_SMMUV2,
};
struct arm_smmu_device {
@@ -398,5 +399,6 @@ static inline void arm_smmu_writeq(struct arm_smmu_device *smmu, int page,
arm_smmu_writeq((s), ARM_SMMU_CB((s), (n)), (o), (v))
struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu);
+struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu);
#endif /* _ARM_SMMU_H */
--
2.1.4
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related
* [PATCH 0/7] Nvidia Arm SMMUv2 Implementation
From: Krishna Reddy @ 2019-08-29 22:47 UTC (permalink / raw)
Cc: snikam, thomasz, jtukkinen, mperttunen, praithatha, iommu,
linux-kernel, talho, olof, yhsu, linux-tegra, treding, avanbrunt,
linux-arm-kernel
Hi All,
Nvidia Arm SMMUv2 implementation has two ARM SMMU(MMU-500) instances
that are used together for SMMU translations. The IOVA accesses from
HW devices are interleaved across these two SMMU instances and need
to be programmed identical except during tlb sync and fault handling.
This patch set adds Nvidia Arm SMMUv2 Implementation on top of ARM SMMU
driver to handle Nvidia specific implementation. It is also adding
hooks for tlb sync and fault handling to allow vendor specific
implementation for the same.
Please review the patch set and provide the feedback.
This patch set is based on the following branch as it is dependent on the
Arm SMMU Refactor changes from Robin Murphy that are present in this branch.
https://git.kernel.org/pub/scm/linux/kernel/git/will/linux.git for-joerg/arm-smmu/updates
Krishna Reddy (7):
iommu/arm-smmu: add Nvidia SMMUv2 implementation
dt-bindings: arm-smmu: Add binding for nvidia,smmu-v2
iommu/arm-smmu: Add tlb_sync implementation hook
iommu/arm-smmu: Add global/context fault implementation hooks
arm64: tegra: Add Memory controller DT node on T194
arm64: tegra: Add DT node for T194 SMMU
arm64: tegra: enable SMMU for SDHCI and EQOS
.../devicetree/bindings/iommu/arm,smmu.txt | 1 +
MAINTAINERS | 2 +
arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi | 4 +
arch/arm64/boot/dts/nvidia/tegra194.dtsi | 86 +++++++
drivers/iommu/Makefile | 2 +-
drivers/iommu/arm-smmu-impl.c | 2 +
drivers/iommu/arm-smmu-nvidia.c | 256 +++++++++++++++++++++
drivers/iommu/arm-smmu.c | 16 +-
drivers/iommu/arm-smmu.h | 10 +
9 files changed, 375 insertions(+), 4 deletions(-)
create mode 100644 drivers/iommu/arm-smmu-nvidia.c
--
2.1.4
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply
* [PATCH 3/7] iommu/arm-smmu: Add tlb_sync implementation hook
From: Krishna Reddy @ 2019-08-29 22:47 UTC (permalink / raw)
Cc: snikam, thomasz, jtukkinen, mperttunen, praithatha, iommu,
linux-kernel, talho, olof, yhsu, linux-tegra, treding, avanbrunt,
linux-arm-kernel
In-Reply-To: <1567118827-26358-1-git-send-email-vdumpa@nvidia.com>
tlb_sync hook allows nvidia smmu handle tlb sync
across multiple SMMUs as necessary.
Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
---
drivers/iommu/arm-smmu-nvidia.c | 32 ++++++++++++++++++++++++++++++++
drivers/iommu/arm-smmu.c | 8 +++++---
drivers/iommu/arm-smmu.h | 4 ++++
3 files changed, 41 insertions(+), 3 deletions(-)
diff --git a/drivers/iommu/arm-smmu-nvidia.c b/drivers/iommu/arm-smmu-nvidia.c
index d93ceda..a429b2c 100644
--- a/drivers/iommu/arm-smmu-nvidia.c
+++ b/drivers/iommu/arm-smmu-nvidia.c
@@ -56,11 +56,43 @@ static void nsmmu_write_reg64(struct arm_smmu_device *smmu,
writeq_relaxed(val, nsmmu_page(smmu, i, page) + offset);
}
+static void nsmmu_tlb_sync_wait(struct arm_smmu_device *smmu, int page,
+ int sync, int status, int inst)
+{
+ u32 reg;
+ unsigned int spin_cnt, delay;
+
+ for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) {
+ for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
+ reg = readl_relaxed(
+ nsmmu_page(smmu, inst, page) + status);
+ if (!(reg & sTLBGSTATUS_GSACTIVE))
+ return;
+ cpu_relax();
+ }
+ udelay(delay);
+ }
+ dev_err_ratelimited(smmu->dev,
+ "TLB sync timed out -- SMMU may be deadlocked\n");
+}
+
+static void nsmmu_tlb_sync(struct arm_smmu_device *smmu, int page,
+ int sync, int status)
+{
+ int i;
+
+ arm_smmu_writel(smmu, page, sync, 0);
+
+ for (i = 0; i < to_nsmmu(smmu)->num_inst; i++)
+ nsmmu_tlb_sync_wait(smmu, page, sync, status, i);
+}
+
static const struct arm_smmu_impl nsmmu_impl = {
.read_reg = nsmmu_read_reg,
.write_reg = nsmmu_write_reg,
.read_reg64 = nsmmu_read_reg64,
.write_reg64 = nsmmu_write_reg64,
+ .tlb_sync = nsmmu_tlb_sync,
};
struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu)
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 46e1641..f5454e71 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -52,9 +52,6 @@
*/
#define QCOM_DUMMY_VAL -1
-#define TLB_LOOP_TIMEOUT 1000000 /* 1s! */
-#define TLB_SPIN_COUNT 10
-
#define MSI_IOVA_BASE 0x8000000
#define MSI_IOVA_LENGTH 0x100000
@@ -244,6 +241,11 @@ static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
unsigned int spin_cnt, delay;
u32 reg;
+ if (smmu->impl->tlb_sync) {
+ smmu->impl->tlb_sync(smmu, page, sync, status);
+ return;
+ }
+
arm_smmu_writel(smmu, page, sync, QCOM_DUMMY_VAL);
for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) {
for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index 9645bf1..d3217f1 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -207,6 +207,8 @@ enum arm_smmu_cbar_type {
/* Maximum number of context banks per SMMU */
#define ARM_SMMU_MAX_CBS 128
+#define TLB_LOOP_TIMEOUT 1000000 /* 1s! */
+#define TLB_SPIN_COUNT 10
/* Shared driver definitions */
enum arm_smmu_arch_version {
@@ -336,6 +338,8 @@ struct arm_smmu_impl {
int (*cfg_probe)(struct arm_smmu_device *smmu);
int (*reset)(struct arm_smmu_device *smmu);
int (*init_context)(struct arm_smmu_domain *smmu_domain);
+ void (*tlb_sync)(struct arm_smmu_device *smmu, int page, int sync,
+ int status);
};
static inline void __iomem *arm_smmu_page(struct arm_smmu_device *smmu, int n)
--
2.1.4
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related
* [PATCH 4/7] iommu/arm-smmu: Add global/context fault implementation hooks
From: Krishna Reddy @ 2019-08-29 22:47 UTC (permalink / raw)
Cc: snikam, thomasz, jtukkinen, mperttunen, praithatha, iommu,
linux-kernel, talho, olof, yhsu, linux-tegra, treding, avanbrunt,
linux-arm-kernel
In-Reply-To: <1567118827-26358-1-git-send-email-vdumpa@nvidia.com>
Add global/context fault hooks to allow Nvidia SMMU implementation
handle faults across multiple SMMUs.
Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
---
drivers/iommu/arm-smmu-nvidia.c | 127 ++++++++++++++++++++++++++++++++++++++++
drivers/iommu/arm-smmu.c | 6 ++
drivers/iommu/arm-smmu.h | 4 ++
3 files changed, 137 insertions(+)
diff --git a/drivers/iommu/arm-smmu-nvidia.c b/drivers/iommu/arm-smmu-nvidia.c
index a429b2c..b2a3c49 100644
--- a/drivers/iommu/arm-smmu-nvidia.c
+++ b/drivers/iommu/arm-smmu-nvidia.c
@@ -14,6 +14,10 @@
#define NUM_SMMU_INSTANCES 3
+static irqreturn_t nsmmu_context_fault_inst(int irq,
+ struct arm_smmu_device *smmu,
+ int idx, int inst);
+
struct nvidia_smmu {
struct arm_smmu_device smmu;
int num_inst;
@@ -87,12 +91,135 @@ static void nsmmu_tlb_sync(struct arm_smmu_device *smmu, int page,
nsmmu_tlb_sync_wait(smmu, page, sync, status, i);
}
+static irqreturn_t nsmmu_global_fault_inst(int irq,
+ struct arm_smmu_device *smmu,
+ int inst)
+{
+ u32 gfsr, gfsynr0, gfsynr1, gfsynr2;
+
+ gfsr = readl_relaxed(nsmmu_page(smmu, inst, 0) + ARM_SMMU_GR0_sGFSR);
+ gfsynr0 = readl_relaxed(nsmmu_page(smmu, inst, 0) +
+ ARM_SMMU_GR0_sGFSYNR0);
+ gfsynr1 = readl_relaxed(nsmmu_page(smmu, inst, 0) +
+ ARM_SMMU_GR0_sGFSYNR1);
+ gfsynr2 = readl_relaxed(nsmmu_page(smmu, inst, 0) +
+ ARM_SMMU_GR0_sGFSYNR2);
+
+ if (!gfsr)
+ return IRQ_NONE;
+
+ dev_err_ratelimited(smmu->dev,
+ "Unexpected global fault, this could be serious\n");
+ dev_err_ratelimited(smmu->dev,
+ "\tGFSR 0x%08x, GFSYNR0 0x%08x, GFSYNR1 0x%08x, GFSYNR2 0x%08x\n",
+ gfsr, gfsynr0, gfsynr1, gfsynr2);
+
+ writel_relaxed(gfsr, nsmmu_page(smmu, inst, 0) + ARM_SMMU_GR0_sGFSR);
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t nsmmu_global_fault(int irq, struct arm_smmu_device *smmu)
+{
+ int i;
+ irqreturn_t irq_ret = IRQ_NONE;
+
+ /* Interrupt line is shared between global and context faults.
+ * Check for both type of interrupts on either fault handlers.
+ */
+ for (i = 0; i < to_nsmmu(smmu)->num_inst; i++) {
+ irq_ret = nsmmu_context_fault_inst(irq, smmu, 0, i);
+ if (irq_ret == IRQ_HANDLED)
+ return irq_ret;
+ }
+
+ for (i = 0; i < to_nsmmu(smmu)->num_inst; i++) {
+ irq_ret = nsmmu_global_fault_inst(irq, smmu, i);
+ if (irq_ret == IRQ_HANDLED)
+ return irq_ret;
+ }
+
+ return irq_ret;
+}
+
+static irqreturn_t nsmmu_context_fault_bank(int irq,
+ struct arm_smmu_device *smmu,
+ int idx, int inst)
+{
+ u32 fsr, fsynr, cbfrsynra;
+ unsigned long iova;
+
+ fsr = arm_smmu_cb_read(smmu, idx, ARM_SMMU_CB_FSR);
+ if (!(fsr & FSR_FAULT))
+ return IRQ_NONE;
+
+ fsynr = readl_relaxed(nsmmu_page(smmu, inst, smmu->numpage + idx) +
+ ARM_SMMU_CB_FSYNR0);
+ iova = readq_relaxed(nsmmu_page(smmu, inst, smmu->numpage + idx) +
+ ARM_SMMU_CB_FAR);
+ cbfrsynra = readl_relaxed(nsmmu_page(smmu, inst, 1) +
+ ARM_SMMU_GR1_CBFRSYNRA(idx));
+
+ dev_err_ratelimited(smmu->dev,
+ "Unhandled context fault: fsr=0x%x, iova=0x%08lx, fsynr=0x%x, cbfrsynra=0x%x, cb=%d\n",
+ fsr, iova, fsynr, cbfrsynra, idx);
+
+ writel_relaxed(fsr, nsmmu_page(smmu, inst, smmu->numpage + idx) +
+ ARM_SMMU_CB_FSR);
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t nsmmu_context_fault_inst(int irq,
+ struct arm_smmu_device *smmu,
+ int idx, int inst)
+{
+ irqreturn_t irq_ret = IRQ_NONE;
+
+ /* Interrupt line shared between global and all context faults.
+ * Check for faults across all contexts.
+ */
+ for (idx = 0; idx < smmu->num_context_banks; idx++) {
+ irq_ret = nsmmu_context_fault_bank(irq, smmu, idx, inst);
+
+ if (irq_ret == IRQ_HANDLED)
+ break;
+ }
+
+ return irq_ret;
+}
+
+static irqreturn_t nsmmu_context_fault(int irq,
+ struct arm_smmu_device *smmu,
+ int cbndx)
+{
+ int i;
+ irqreturn_t irq_ret = IRQ_NONE;
+
+ /* Interrupt line is shared between global and context faults.
+ * Check for both type of interrupts on either fault handlers.
+ */
+ for (i = 0; i < to_nsmmu(smmu)->num_inst; i++) {
+ irq_ret = nsmmu_global_fault_inst(irq, smmu, i);
+ if (irq_ret == IRQ_HANDLED)
+ return irq_ret;
+ }
+
+ for (i = 0; i < to_nsmmu(smmu)->num_inst; i++) {
+ irq_ret = nsmmu_context_fault_inst(irq, smmu, cbndx, i);
+ if (irq_ret == IRQ_HANDLED)
+ return irq_ret;
+ }
+
+ return irq_ret;
+}
+
static const struct arm_smmu_impl nsmmu_impl = {
.read_reg = nsmmu_read_reg,
.write_reg = nsmmu_write_reg,
.read_reg64 = nsmmu_read_reg64,
.write_reg64 = nsmmu_write_reg64,
.tlb_sync = nsmmu_tlb_sync,
+ .global_fault = nsmmu_global_fault,
+ .context_fault = nsmmu_context_fault,
};
struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu)
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index f5454e71..9cc532d 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -454,6 +454,9 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
struct arm_smmu_device *smmu = smmu_domain->smmu;
int idx = smmu_domain->cfg.cbndx;
+ if (smmu->impl->context_fault)
+ return smmu->impl->context_fault(irq, smmu, idx);
+
fsr = arm_smmu_cb_read(smmu, idx, ARM_SMMU_CB_FSR);
if (!(fsr & FSR_FAULT))
return IRQ_NONE;
@@ -475,6 +478,9 @@ static irqreturn_t arm_smmu_global_fault(int irq, void *dev)
u32 gfsr, gfsynr0, gfsynr1, gfsynr2;
struct arm_smmu_device *smmu = dev;
+ if (smmu->impl->global_fault)
+ return smmu->impl->global_fault(irq, smmu);
+
gfsr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sGFSR);
gfsynr0 = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sGFSYNR0);
gfsynr1 = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sGFSYNR1);
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index d3217f1..dec5e1a 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -17,6 +17,7 @@
#include <linux/io-64-nonatomic-hi-lo.h>
#include <linux/io-pgtable.h>
#include <linux/iommu.h>
+#include <linux/irqreturn.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
#include <linux/types.h>
@@ -340,6 +341,9 @@ struct arm_smmu_impl {
int (*init_context)(struct arm_smmu_domain *smmu_domain);
void (*tlb_sync)(struct arm_smmu_device *smmu, int page, int sync,
int status);
+ irqreturn_t (*global_fault)(int irq, struct arm_smmu_device *smmu);
+ irqreturn_t (*context_fault)(int irq, struct arm_smmu_device *smmu,
+ int cbndx);
};
static inline void __iomem *arm_smmu_page(struct arm_smmu_device *smmu, int n)
--
2.1.4
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related
* Re: [PATCH 06/11] swiotlb-xen: always use dma-direct helpers to alloc coherent pages
From: Stefano Stabellini @ 2019-08-29 22:46 UTC (permalink / raw)
To: Christoph Hellwig
Cc: jgross, Stefano Stabellini, Konrad Rzeszutek Wilk, x86,
linux-kernel, iommu, xen-devel, boris.ostrovsky, linux-arm-kernel
In-Reply-To: <20190826121944.515-7-hch@lst.de>
+ Boris, Juergen
On Mon, 26 Aug 2019, Christoph Hellwig wrote:
> x86 currently calls alloc_pages, but using dma-direct works as well
> there, with the added benefit of using the CMA pool if available.
> The biggest advantage is of course to remove a pointless bit of
> architecture specific code.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
> arch/x86/include/asm/xen/page-coherent.h | 16 ----------------
> drivers/xen/swiotlb-xen.c | 7 +++----
> include/xen/arm/page-coherent.h | 12 ------------
> 3 files changed, 3 insertions(+), 32 deletions(-)
>
> diff --git a/arch/x86/include/asm/xen/page-coherent.h b/arch/x86/include/asm/xen/page-coherent.h
> index 116777e7f387..8ee33c5edded 100644
> --- a/arch/x86/include/asm/xen/page-coherent.h
> +++ b/arch/x86/include/asm/xen/page-coherent.h
> @@ -5,22 +5,6 @@
> #include <asm/page.h>
> #include <linux/dma-mapping.h>
>
> -static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
> - dma_addr_t *dma_handle, gfp_t flags,
> - unsigned long attrs)
> -{
> - void *vstart = (void*)__get_free_pages(flags, get_order(size));
> - *dma_handle = virt_to_phys(vstart);
This is where we need Boris and Juergen's opinion. From an ARM POV it
looks OK.
> - return vstart;
> -}
> -
> -static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
> - void *cpu_addr, dma_addr_t dma_handle,
> - unsigned long attrs)
> -{
> - free_pages((unsigned long) cpu_addr, get_order(size));
> -}
> -
> static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
> dma_addr_t dev_addr, unsigned long offset, size_t size,
> enum dma_data_direction dir, unsigned long attrs) { }
> diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
> index b8808677ae1d..f9dd4cb6e4b3 100644
> --- a/drivers/xen/swiotlb-xen.c
> +++ b/drivers/xen/swiotlb-xen.c
> @@ -299,8 +299,7 @@ xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
> * address. In fact on ARM virt_to_phys only works for kernel direct
> * mapped RAM memory. Also see comment below.
> */
> - ret = xen_alloc_coherent_pages(hwdev, size, dma_handle, flags, attrs);
> -
> + ret = dma_direct_alloc(hwdev, size, dma_handle, flags, attrs);
> if (!ret)
> return ret;
>
> @@ -319,7 +318,7 @@ xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
> else {
> if (xen_create_contiguous_region(phys, order,
> fls64(dma_mask), dma_handle) != 0) {
> - xen_free_coherent_pages(hwdev, size, ret, (dma_addr_t)phys, attrs);
> + dma_direct_free(hwdev, size, ret, (dma_addr_t)phys, attrs);
> return NULL;
> }
> SetPageXenRemapped(virt_to_page(ret));
> @@ -351,7 +350,7 @@ xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
> TestClearPageXenRemapped(virt_to_page(vaddr)))
> xen_destroy_contiguous_region(phys, order);
>
> - xen_free_coherent_pages(hwdev, size, vaddr, (dma_addr_t)phys, attrs);
> + dma_direct_free(hwdev, size, vaddr, (dma_addr_t)phys, attrs);
> }
>
> /*
> diff --git a/include/xen/arm/page-coherent.h b/include/xen/arm/page-coherent.h
> index a840d6949a87..0e244f4fec1a 100644
> --- a/include/xen/arm/page-coherent.h
> +++ b/include/xen/arm/page-coherent.h
> @@ -16,18 +16,6 @@ void __xen_dma_sync_single_for_cpu(struct device *hwdev,
> void __xen_dma_sync_single_for_device(struct device *hwdev,
> dma_addr_t handle, size_t size, enum dma_data_direction dir);
>
> -static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
> - dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs)
> -{
> - return dma_direct_alloc(hwdev, size, dma_handle, flags, attrs);
> -}
> -
> -static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
> - void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
> -{
> - dma_direct_free(hwdev, size, cpu_addr, dma_handle, attrs);
> -}
> -
> static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
> dma_addr_t handle, size_t size, enum dma_data_direction dir)
> {
> --
> 2.20.1
>
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply
* Re: [PATCH 07/11] swiotlb-xen: use the same foreign page check everywhere
From: Stefano Stabellini @ 2019-08-29 22:47 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Stefano Stabellini, Konrad Rzeszutek Wilk, x86, linux-kernel,
iommu, xen-devel, linux-arm-kernel
In-Reply-To: <20190826121944.515-8-hch@lst.de>
On Mon, 26 Aug 2019, Christoph Hellwig wrote:
> xen_dma_map_page uses a different and more complicated check for foreign
> pages than the other three cache maintainance helpers. Switch it to the
> simpler pfn_valid method a well, and document the scheme with a single
> improved comment in xen_dma_map_page.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
> ---
> include/xen/arm/page-coherent.h | 31 +++++++++----------------------
> 1 file changed, 9 insertions(+), 22 deletions(-)
>
> diff --git a/include/xen/arm/page-coherent.h b/include/xen/arm/page-coherent.h
> index 0e244f4fec1a..07c104dbc21f 100644
> --- a/include/xen/arm/page-coherent.h
> +++ b/include/xen/arm/page-coherent.h
> @@ -41,23 +41,17 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
> dma_addr_t dev_addr, unsigned long offset, size_t size,
> enum dma_data_direction dir, unsigned long attrs)
> {
> - unsigned long page_pfn = page_to_xen_pfn(page);
> - unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
> - unsigned long compound_pages =
> - (1<<compound_order(page)) * XEN_PFN_PER_PAGE;
> - bool local = (page_pfn <= dev_pfn) &&
> - (dev_pfn - page_pfn < compound_pages);
> + unsigned long pfn = PFN_DOWN(dev_addr);
>
> /*
> - * Dom0 is mapped 1:1, while the Linux page can span across
> - * multiple Xen pages, it's not possible for it to contain a
> - * mix of local and foreign Xen pages. So if the first xen_pfn
> - * == mfn the page is local otherwise it's a foreign page
> - * grant-mapped in dom0. If the page is local we can safely
> - * call the native dma_ops function, otherwise we call the xen
> - * specific function.
> + * Dom0 is mapped 1:1, and while the Linux page can span across multiple
> + * Xen pages, it is not possible for it to contain a mix of local and
> + * foreign Xen pages. Calling pfn_valid on a foreign mfn will always
> + * return false, so if pfn_valid returns true the pages is local and we
> + * can use the native dma-direct functions, otherwise we call the Xen
> + * specific version.
> */
> - if (local)
> + if (pfn_valid(pfn))
> dma_direct_map_page(hwdev, page, offset, size, dir, attrs);
> else
> __xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
> @@ -67,14 +61,7 @@ static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
> size_t size, enum dma_data_direction dir, unsigned long attrs)
> {
> unsigned long pfn = PFN_DOWN(handle);
> - /*
> - * Dom0 is mapped 1:1, while the Linux page can be spanned accross
> - * multiple Xen page, it's not possible to have a mix of local and
> - * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a
> - * foreign mfn will always return false. If the page is local we can
> - * safely call the native dma_ops function, otherwise we call the xen
> - * specific function.
> - */
> +
> if (pfn_valid(pfn))
> dma_direct_unmap_page(hwdev, handle, size, dir, attrs);
> else
> --
> 2.20.1
>
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply
* Re: [PATCH 4/5] dt-bindings: dma: ti-edma: Add option for reserved channel ranges
From: Rob Herring @ 2019-08-29 22:47 UTC (permalink / raw)
To: Peter Ujfalusi
Cc: devicetree, linux-kernel, vkoul, dmaengine, dan.j.williams,
linux-omap, linux-arm-kernel
In-Reply-To: <20190823125618.8133-5-peter.ujfalusi@ti.com>
On Fri, Aug 23, 2019 at 03:56:17PM +0300, Peter Ujfalusi wrote:
> Similarly to paRAM slots, channels can be used by other cores.
>
> Add optional property to configure the reserved channel ranges.
>
> Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
> ---
> Documentation/devicetree/bindings/dma/ti-edma.txt | 5 +++++
> 1 file changed, 5 insertions(+)
>
> diff --git a/Documentation/devicetree/bindings/dma/ti-edma.txt b/Documentation/devicetree/bindings/dma/ti-edma.txt
> index 4bbc94d829c8..1198682ada99 100644
> --- a/Documentation/devicetree/bindings/dma/ti-edma.txt
> +++ b/Documentation/devicetree/bindings/dma/ti-edma.txt
> @@ -42,6 +42,9 @@ Optional properties:
> - ti,edma-reserved-slot-ranges: PaRAM slot ranges which should not be used by
> the driver, they are allocated to be used by for example the
> DSP. See example.
> +- ti,edma-reserved-chan-ranges: channel ranges which should not be used by
> + the driver, they are allocated to be used by for example the
> + DSP. See example.
Based on the other thread, I think extending dma-channel-mask to a
uint32-array makes sense here.
Rob
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply
* Re: [PATCH 08/11] swiotlb-xen: simplify cache maintainance
From: Stefano Stabellini @ 2019-08-29 22:47 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Stefano Stabellini, Konrad Rzeszutek Wilk, x86, linux-kernel,
iommu, xen-devel, linux-arm-kernel
In-Reply-To: <20190826121944.515-9-hch@lst.de>
On Mon, 26 Aug 2019, Christoph Hellwig wrote:
> Now that we know we always have the dma-noncoherent.h helpers available
> if we are on an architecture with support for non-coherent devices,
> we can just call them directly, and remove the calls to the dma-direct
> routines, including the fact that we call the dma_direct_map_page
> routines but ignore the value returned from it. Instead we now have
> Xen wrappers for the arch_sync_dma_for_{device,cpu} helpers that call
> the special Xen versions of those routines for foreign pages.
>
> Note that the new helpers get the physical address passed in addition
> to the dma address to avoid another translation for the local cache
> maintainance. The pfn_valid checks remain on the dma address as in
> the old code, even if that looks a little funny.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
>
> ---
> arch/arm/xen/mm.c | 64 ++++++----------------
> arch/x86/include/asm/xen/page-coherent.h | 11 ----
> drivers/xen/swiotlb-xen.c | 20 +++----
> include/xen/arm/page-coherent.h | 69 ++----------------------
> 4 files changed, 31 insertions(+), 133 deletions(-)
WOW nice! Now I really can see why this series was worth doing :-)
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
> diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
> index b7d53415532b..7096652f5a1e 100644
> --- a/arch/arm/xen/mm.c
> +++ b/arch/arm/xen/mm.c
> @@ -61,63 +61,33 @@ static void dma_cache_maint(dma_addr_t handle, size_t size, u32 op)
> } while (size);
> }
>
> -static void __xen_dma_page_dev_to_cpu(struct device *hwdev, dma_addr_t handle,
> - size_t size, enum dma_data_direction dir)
> +/*
> + * Dom0 is mapped 1:1, and while the Linux page can span across multiple Xen
> + * pages, it is not possible for it to contain a mix of local and foreign Xen
> + * pages. Calling pfn_valid on a foreign mfn will always return false, so if
> + * pfn_valid returns true the pages is local and we can use the native
> + * dma-direct functions, otherwise we call the Xen specific version.
> + */
> +void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle,
> + phys_addr_t paddr, size_t size, enum dma_data_direction dir)
> {
> - if (dir != DMA_TO_DEVICE)
> + if (pfn_valid(PFN_DOWN(handle)))
> + arch_sync_dma_for_cpu(dev, paddr, size, dir);
> + else if (dir != DMA_TO_DEVICE)
> dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL);
> }
>
> -static void __xen_dma_page_cpu_to_dev(struct device *hwdev, dma_addr_t handle,
> - size_t size, enum dma_data_direction dir)
> +void xen_dma_sync_for_device(struct device *dev, dma_addr_t handle,
> + phys_addr_t paddr, size_t size, enum dma_data_direction dir)
> {
> - if (dir == DMA_FROM_DEVICE)
> + if (pfn_valid(PFN_DOWN(handle)))
> + arch_sync_dma_for_device(dev, paddr, size, dir);
> + else if (dir == DMA_FROM_DEVICE)
> dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL);
> else
> dma_cache_maint(handle, size, GNTTAB_CACHE_CLEAN);
> }
>
> -void __xen_dma_map_page(struct device *hwdev, struct page *page,
> - dma_addr_t dev_addr, unsigned long offset, size_t size,
> - enum dma_data_direction dir, unsigned long attrs)
> -{
> - if (dev_is_dma_coherent(hwdev))
> - return;
> - if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
> - return;
> -
> - __xen_dma_page_cpu_to_dev(hwdev, dev_addr, size, dir);
> -}
> -
> -void __xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
> - size_t size, enum dma_data_direction dir,
> - unsigned long attrs)
> -
> -{
> - if (dev_is_dma_coherent(hwdev))
> - return;
> - if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
> - return;
> -
> - __xen_dma_page_dev_to_cpu(hwdev, handle, size, dir);
> -}
> -
> -void __xen_dma_sync_single_for_cpu(struct device *hwdev,
> - dma_addr_t handle, size_t size, enum dma_data_direction dir)
> -{
> - if (dev_is_dma_coherent(hwdev))
> - return;
> - __xen_dma_page_dev_to_cpu(hwdev, handle, size, dir);
> -}
> -
> -void __xen_dma_sync_single_for_device(struct device *hwdev,
> - dma_addr_t handle, size_t size, enum dma_data_direction dir)
> -{
> - if (dev_is_dma_coherent(hwdev))
> - return;
> - __xen_dma_page_cpu_to_dev(hwdev, handle, size, dir);
> -}
> -
> bool xen_arch_need_swiotlb(struct device *dev,
> phys_addr_t phys,
> dma_addr_t dev_addr)
> diff --git a/arch/x86/include/asm/xen/page-coherent.h b/arch/x86/include/asm/xen/page-coherent.h
> index 8ee33c5edded..c9c8398a31ff 100644
> --- a/arch/x86/include/asm/xen/page-coherent.h
> +++ b/arch/x86/include/asm/xen/page-coherent.h
> @@ -2,17 +2,6 @@
> #ifndef _ASM_X86_XEN_PAGE_COHERENT_H
> #define _ASM_X86_XEN_PAGE_COHERENT_H
>
> -#include <asm/page.h>
> -#include <linux/dma-mapping.h>
> -
> -static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
> - dma_addr_t dev_addr, unsigned long offset, size_t size,
> - enum dma_data_direction dir, unsigned long attrs) { }
> -
> -static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
> - size_t size, enum dma_data_direction dir,
> - unsigned long attrs) { }
> -
> static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
> dma_addr_t handle, size_t size, enum dma_data_direction dir) { }
>
> diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
> index f9dd4cb6e4b3..a642e284f1e2 100644
> --- a/drivers/xen/swiotlb-xen.c
> +++ b/drivers/xen/swiotlb-xen.c
> @@ -28,6 +28,7 @@
>
> #include <linux/memblock.h>
> #include <linux/dma-direct.h>
> +#include <linux/dma-noncoherent.h>
> #include <linux/export.h>
> #include <xen/swiotlb-xen.h>
> #include <xen/page.h>
> @@ -390,6 +391,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
> if (map == (phys_addr_t)DMA_MAPPING_ERROR)
> return DMA_MAPPING_ERROR;
>
> + phys = map;
> dev_addr = xen_phys_to_bus(map);
>
> /*
> @@ -401,14 +403,9 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
> return DMA_MAPPING_ERROR;
> }
>
> - page = pfn_to_page(map >> PAGE_SHIFT);
> - offset = map & ~PAGE_MASK;
> done:
> - /*
> - * we are not interested in the dma_addr returned by xen_dma_map_page,
> - * only in the potential cache flushes executed by the function.
> - */
> - xen_dma_map_page(dev, page, dev_addr, offset, size, dir, attrs);
> + if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
> + xen_dma_sync_for_device(dev, dev_addr, phys, size, dir);
> return dev_addr;
> }
>
> @@ -428,7 +425,8 @@ static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
>
> BUG_ON(dir == DMA_NONE);
>
> - xen_dma_unmap_page(hwdev, dev_addr, size, dir, attrs);
> + if (!dev_is_dma_coherent(hwdev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
> + xen_dma_sync_for_cpu(hwdev, dev_addr, paddr, size, dir);
>
> /* NOTE: We use dev_addr here, not paddr! */
> if (is_xen_swiotlb_buffer(dev_addr))
> @@ -448,7 +446,8 @@ xen_swiotlb_sync_single_for_cpu(struct device *dev, dma_addr_t dma_addr,
> {
> phys_addr_t paddr = xen_bus_to_phys(dma_addr);
>
> - xen_dma_sync_single_for_cpu(dev, dma_addr, size, dir);
> + if (!dev_is_dma_coherent(dev))
> + xen_dma_sync_for_cpu(dev, dma_addr, paddr, size, dir);
>
> if (is_xen_swiotlb_buffer(dma_addr))
> swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
> @@ -463,7 +462,8 @@ xen_swiotlb_sync_single_for_device(struct device *dev, dma_addr_t dma_addr,
> if (is_xen_swiotlb_buffer(dma_addr))
> swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
>
> - xen_dma_sync_single_for_device(dev, dma_addr, size, dir);
> + if (!dev_is_dma_coherent(dev))
> + xen_dma_sync_for_device(dev, dma_addr, paddr, size, dir);
> }
>
> /*
> diff --git a/include/xen/arm/page-coherent.h b/include/xen/arm/page-coherent.h
> index 07c104dbc21f..635492d41ebe 100644
> --- a/include/xen/arm/page-coherent.h
> +++ b/include/xen/arm/page-coherent.h
> @@ -2,70 +2,9 @@
> #ifndef _XEN_ARM_PAGE_COHERENT_H
> #define _XEN_ARM_PAGE_COHERENT_H
>
> -#include <linux/dma-mapping.h>
> -#include <asm/page.h>
> -
> -void __xen_dma_map_page(struct device *hwdev, struct page *page,
> - dma_addr_t dev_addr, unsigned long offset, size_t size,
> - enum dma_data_direction dir, unsigned long attrs);
> -void __xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
> - size_t size, enum dma_data_direction dir,
> - unsigned long attrs);
> -void __xen_dma_sync_single_for_cpu(struct device *hwdev,
> - dma_addr_t handle, size_t size, enum dma_data_direction dir);
> -void __xen_dma_sync_single_for_device(struct device *hwdev,
> - dma_addr_t handle, size_t size, enum dma_data_direction dir);
> -
> -static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
> - dma_addr_t handle, size_t size, enum dma_data_direction dir)
> -{
> - unsigned long pfn = PFN_DOWN(handle);
> -
> - if (pfn_valid(pfn))
> - dma_direct_sync_single_for_cpu(hwdev, handle, size, dir);
> - else
> - __xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
> -}
> -
> -static inline void xen_dma_sync_single_for_device(struct device *hwdev,
> - dma_addr_t handle, size_t size, enum dma_data_direction dir)
> -{
> - unsigned long pfn = PFN_DOWN(handle);
> - if (pfn_valid(pfn))
> - dma_direct_sync_single_for_device(hwdev, handle, size, dir);
> - else
> - __xen_dma_sync_single_for_device(hwdev, handle, size, dir);
> -}
> -
> -static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
> - dma_addr_t dev_addr, unsigned long offset, size_t size,
> - enum dma_data_direction dir, unsigned long attrs)
> -{
> - unsigned long pfn = PFN_DOWN(dev_addr);
> -
> - /*
> - * Dom0 is mapped 1:1, and while the Linux page can span across multiple
> - * Xen pages, it is not possible for it to contain a mix of local and
> - * foreign Xen pages. Calling pfn_valid on a foreign mfn will always
> - * return false, so if pfn_valid returns true the pages is local and we
> - * can use the native dma-direct functions, otherwise we call the Xen
> - * specific version.
> - */
> - if (pfn_valid(pfn))
> - dma_direct_map_page(hwdev, page, offset, size, dir, attrs);
> - else
> - __xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
> -}
> -
> -static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
> - size_t size, enum dma_data_direction dir, unsigned long attrs)
> -{
> - unsigned long pfn = PFN_DOWN(handle);
> -
> - if (pfn_valid(pfn))
> - dma_direct_unmap_page(hwdev, handle, size, dir, attrs);
> - else
> - __xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
> -}
> +void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle,
> + phys_addr_t paddr, size_t size, enum dma_data_direction dir);
> +void xen_dma_sync_for_device(struct device *dev, dma_addr_t handle,
> + phys_addr_t paddr, size_t size, enum dma_data_direction dir);
>
> #endif /* _XEN_ARM_PAGE_COHERENT_H */
> --
> 2.20.1
>
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply
* Re: [PATCH 09/11] swiotlb-xen: remove page-coherent.h
From: Stefano Stabellini @ 2019-08-29 22:48 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Stefano Stabellini, Konrad Rzeszutek Wilk, x86, linux-kernel,
iommu, xen-devel, linux-arm-kernel
In-Reply-To: <20190826121944.515-10-hch@lst.de>
On Mon, 26 Aug 2019, Christoph Hellwig wrote:
> The only thing left of page-coherent.h is two functions implemented by
> the architecture for non-coherent DMA support that are never called for
> fully coherent architectures. Just move the prototypes for those to
> swiotlb-xen.h instead.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
> ---
> arch/arm/include/asm/xen/page-coherent.h | 2 --
> arch/arm64/include/asm/xen/page-coherent.h | 2 --
> arch/x86/include/asm/xen/page-coherent.h | 11 -----------
> drivers/xen/swiotlb-xen.c | 3 ---
> include/Kbuild | 1 -
> include/xen/arm/page-coherent.h | 10 ----------
> include/xen/swiotlb-xen.h | 6 ++++++
> 7 files changed, 6 insertions(+), 29 deletions(-)
> delete mode 100644 arch/arm/include/asm/xen/page-coherent.h
> delete mode 100644 arch/arm64/include/asm/xen/page-coherent.h
> delete mode 100644 arch/x86/include/asm/xen/page-coherent.h
> delete mode 100644 include/xen/arm/page-coherent.h
>
> diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h
> deleted file mode 100644
> index 27e984977402..000000000000
> --- a/arch/arm/include/asm/xen/page-coherent.h
> +++ /dev/null
> @@ -1,2 +0,0 @@
> -/* SPDX-License-Identifier: GPL-2.0 */
> -#include <xen/arm/page-coherent.h>
> diff --git a/arch/arm64/include/asm/xen/page-coherent.h b/arch/arm64/include/asm/xen/page-coherent.h
> deleted file mode 100644
> index 27e984977402..000000000000
> --- a/arch/arm64/include/asm/xen/page-coherent.h
> +++ /dev/null
> @@ -1,2 +0,0 @@
> -/* SPDX-License-Identifier: GPL-2.0 */
> -#include <xen/arm/page-coherent.h>
> diff --git a/arch/x86/include/asm/xen/page-coherent.h b/arch/x86/include/asm/xen/page-coherent.h
> deleted file mode 100644
> index c9c8398a31ff..000000000000
> --- a/arch/x86/include/asm/xen/page-coherent.h
> +++ /dev/null
> @@ -1,11 +0,0 @@
> -/* SPDX-License-Identifier: GPL-2.0 */
> -#ifndef _ASM_X86_XEN_PAGE_COHERENT_H
> -#define _ASM_X86_XEN_PAGE_COHERENT_H
> -
> -static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
> - dma_addr_t handle, size_t size, enum dma_data_direction dir) { }
> -
> -static inline void xen_dma_sync_single_for_device(struct device *hwdev,
> - dma_addr_t handle, size_t size, enum dma_data_direction dir) { }
> -
> -#endif /* _ASM_X86_XEN_PAGE_COHERENT_H */
> diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
> index a642e284f1e2..95911ff9c11c 100644
> --- a/drivers/xen/swiotlb-xen.c
> +++ b/drivers/xen/swiotlb-xen.c
> @@ -35,9 +35,6 @@
> #include <xen/xen-ops.h>
> #include <xen/hvc-console.h>
>
> -#include <asm/dma-mapping.h>
> -#include <asm/xen/page-coherent.h>
> -
> #include <trace/events/swiotlb.h>
> /*
> * Used to do a quick range check in swiotlb_tbl_unmap_single and
> diff --git a/include/Kbuild b/include/Kbuild
> index c38f0d46b267..cce5cf6abf89 100644
> --- a/include/Kbuild
> +++ b/include/Kbuild
> @@ -1189,7 +1189,6 @@ header-test- += video/vga.h
> header-test- += video/w100fb.h
> header-test- += xen/acpi.h
> header-test- += xen/arm/hypercall.h
> -header-test- += xen/arm/page-coherent.h
> header-test- += xen/arm/page.h
> header-test- += xen/balloon.h
> header-test- += xen/events.h
> diff --git a/include/xen/arm/page-coherent.h b/include/xen/arm/page-coherent.h
> deleted file mode 100644
> index 635492d41ebe..000000000000
> --- a/include/xen/arm/page-coherent.h
> +++ /dev/null
> @@ -1,10 +0,0 @@
> -/* SPDX-License-Identifier: GPL-2.0 */
> -#ifndef _XEN_ARM_PAGE_COHERENT_H
> -#define _XEN_ARM_PAGE_COHERENT_H
> -
> -void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle,
> - phys_addr_t paddr, size_t size, enum dma_data_direction dir);
> -void xen_dma_sync_for_device(struct device *dev, dma_addr_t handle,
> - phys_addr_t paddr, size_t size, enum dma_data_direction dir);
> -
> -#endif /* _XEN_ARM_PAGE_COHERENT_H */
> diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h
> index 5e4b83f83dbc..a7c642872568 100644
> --- a/include/xen/swiotlb-xen.h
> +++ b/include/xen/swiotlb-xen.h
> @@ -2,8 +2,14 @@
> #ifndef __LINUX_SWIOTLB_XEN_H
> #define __LINUX_SWIOTLB_XEN_H
>
> +#include <linux/dma-mapping.h>
> #include <linux/swiotlb.h>
>
> +void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle,
> + phys_addr_t paddr, size_t size, enum dma_data_direction dir);
> +void xen_dma_sync_for_device(struct device *dev, dma_addr_t handle,
> + phys_addr_t paddr, size_t size, enum dma_data_direction dir);
> +
> extern int xen_swiotlb_init(int verbose, bool early);
> extern const struct dma_map_ops xen_swiotlb_dma_ops;
>
> --
> 2.20.1
>
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply
* Re: [PATCH 10/11] swiotlb-xen: merge xen_unmap_single into xen_swiotlb_unmap_page
From: Stefano Stabellini @ 2019-08-29 22:48 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Stefano Stabellini, Konrad Rzeszutek Wilk, x86, linux-kernel,
iommu, xen-devel, linux-arm-kernel
In-Reply-To: <20190826121944.515-11-hch@lst.de>
On Mon, 26 Aug 2019, Christoph Hellwig wrote:
> No need for a no-op wrapper.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
> ---
> drivers/xen/swiotlb-xen.c | 15 ++++-----------
> 1 file changed, 4 insertions(+), 11 deletions(-)
>
> diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
> index 95911ff9c11c..384304a77020 100644
> --- a/drivers/xen/swiotlb-xen.c
> +++ b/drivers/xen/swiotlb-xen.c
> @@ -414,9 +414,8 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
> * After this call, reads by the cpu to the buffer are guaranteed to see
> * whatever the device wrote there.
> */
> -static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
> - size_t size, enum dma_data_direction dir,
> - unsigned long attrs)
> +static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
> + size_t size, enum dma_data_direction dir, unsigned long attrs)
> {
> phys_addr_t paddr = xen_bus_to_phys(dev_addr);
>
> @@ -430,13 +429,6 @@ static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
> swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs);
> }
>
> -static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
> - size_t size, enum dma_data_direction dir,
> - unsigned long attrs)
> -{
> - xen_unmap_single(hwdev, dev_addr, size, dir, attrs);
> -}
> -
> static void
> xen_swiotlb_sync_single_for_cpu(struct device *dev, dma_addr_t dma_addr,
> size_t size, enum dma_data_direction dir)
> @@ -477,7 +469,8 @@ xen_swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
> BUG_ON(dir == DMA_NONE);
>
> for_each_sg(sgl, sg, nelems, i)
> - xen_unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir, attrs);
> + xen_swiotlb_unmap_page(hwdev, sg->dma_address, sg_dma_len(sg),
> + dir, attrs);
>
> }
>
> --
> 2.20.1
>
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply
* Re: [PATCH 11/11] arm64: use asm-generic/dma-mapping.h
From: Stefano Stabellini @ 2019-08-29 22:48 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Stefano Stabellini, Konrad Rzeszutek Wilk, x86, linux-kernel,
iommu, xen-devel, Will Deacon, linux-arm-kernel
In-Reply-To: <20190826121944.515-12-hch@lst.de>
On Mon, 26 Aug 2019, Christoph Hellwig wrote:
> Now that the Xen special cases are gone nothing worth mentioning is
> left in the arm64 <asm/dma-mapping.h> file, so switch to use the
> asm-generic version instead.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> Acked-by: Will Deacon <will@kernel.org>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
> ---
> arch/arm64/include/asm/Kbuild | 1 +
> arch/arm64/include/asm/dma-mapping.h | 22 ----------------------
> arch/arm64/mm/dma-mapping.c | 1 +
> 3 files changed, 2 insertions(+), 22 deletions(-)
> delete mode 100644 arch/arm64/include/asm/dma-mapping.h
>
> diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
> index c52e151afab0..98a5405c8558 100644
> --- a/arch/arm64/include/asm/Kbuild
> +++ b/arch/arm64/include/asm/Kbuild
> @@ -4,6 +4,7 @@ generic-y += delay.h
> generic-y += div64.h
> generic-y += dma.h
> generic-y += dma-contiguous.h
> +generic-y += dma-mapping.h
> generic-y += early_ioremap.h
> generic-y += emergency-restart.h
> generic-y += hw_irq.h
> diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
> deleted file mode 100644
> index 67243255a858..000000000000
> --- a/arch/arm64/include/asm/dma-mapping.h
> +++ /dev/null
> @@ -1,22 +0,0 @@
> -/* SPDX-License-Identifier: GPL-2.0-only */
> -/*
> - * Copyright (C) 2012 ARM Ltd.
> - */
> -#ifndef __ASM_DMA_MAPPING_H
> -#define __ASM_DMA_MAPPING_H
> -
> -#ifdef __KERNEL__
> -
> -#include <linux/types.h>
> -#include <linux/vmalloc.h>
> -
> -#include <xen/xen.h>
> -#include <asm/xen/hypervisor.h>
> -
> -static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
> -{
> - return NULL;
> -}
> -
> -#endif /* __KERNEL__ */
> -#endif /* __ASM_DMA_MAPPING_H */
> diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
> index 4b244a037349..6578abcfbbc7 100644
> --- a/arch/arm64/mm/dma-mapping.c
> +++ b/arch/arm64/mm/dma-mapping.c
> @@ -8,6 +8,7 @@
> #include <linux/cache.h>
> #include <linux/dma-noncoherent.h>
> #include <linux/dma-iommu.h>
> +#include <xen/xen.h>
> #include <xen/swiotlb-xen.h>
>
> #include <asm/cacheflush.h>
> --
> 2.20.1
>
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply
* Re: [PATCH 03/11] xen/arm: simplify dma_cache_maint
From: Stefano Stabellini @ 2019-08-29 22:49 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Stefano Stabellini, Konrad Rzeszutek Wilk, x86, linux-kernel,
iommu, xen-devel, linux-arm-kernel
In-Reply-To: <20190827063754.GA32045@lst.de>
On Tue, 27 Aug 2019, Christoph Hellwig wrote:
> And this was still buggy I think, it really needs some real Xen/Arm
> testing which I can't do. Hopefully better version below:
>
> --
> >From 5ad4b6e291dbb49f65480c9b769414931cbd485a Mon Sep 17 00:00:00 2001
> From: Christoph Hellwig <hch@lst.de>
> Date: Wed, 24 Jul 2019 15:26:08 +0200
> Subject: xen/arm: simplify dma_cache_maint
>
> Calculate the required operation in the caller, and pass it directly
> instead of recalculating it for each page, and use simple arithmetics
> to get from the physical address to Xen page size aligned chunks.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
> arch/arm/xen/mm.c | 61 ++++++++++++++++-------------------------------
> 1 file changed, 21 insertions(+), 40 deletions(-)
>
> diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
> index 90574d89d0d4..2fde161733b0 100644
> --- a/arch/arm/xen/mm.c
> +++ b/arch/arm/xen/mm.c
> @@ -35,64 +35,45 @@ unsigned long xen_get_swiotlb_free_pages(unsigned int order)
> return __get_free_pages(flags, order);
> }
>
> -enum dma_cache_op {
> - DMA_UNMAP,
> - DMA_MAP,
> -};
> static bool hypercall_cflush = false;
>
> -/* functions called by SWIOTLB */
> -
> -static void dma_cache_maint(dma_addr_t handle, unsigned long offset,
> - size_t size, enum dma_data_direction dir, enum dma_cache_op op)
> +/* buffers in highmem or foreign pages cannot cross page boundaries */
> +static void dma_cache_maint(dma_addr_t handle, size_t size, u32 op)
> {
> struct gnttab_cache_flush cflush;
> - unsigned long xen_pfn;
> - size_t left = size;
>
> - xen_pfn = (handle >> XEN_PAGE_SHIFT) + offset / XEN_PAGE_SIZE;
> - offset %= XEN_PAGE_SIZE;
> + cflush.a.dev_bus_addr = handle & XEN_PAGE_MASK;
> + cflush.offset = xen_offset_in_page(handle);
> + cflush.op = op;
>
> do {
> - size_t len = left;
> -
> - /* buffers in highmem or foreign pages cannot cross page
> - * boundaries */
> - if (len + offset > XEN_PAGE_SIZE)
> - len = XEN_PAGE_SIZE - offset;
> -
> - cflush.op = 0;
> - cflush.a.dev_bus_addr = xen_pfn << XEN_PAGE_SHIFT;
> - cflush.offset = offset;
> - cflush.length = len;
> -
> - if (op == DMA_UNMAP && dir != DMA_TO_DEVICE)
> - cflush.op = GNTTAB_CACHE_INVAL;
> - if (op == DMA_MAP) {
> - if (dir == DMA_FROM_DEVICE)
> - cflush.op = GNTTAB_CACHE_INVAL;
> - else
> - cflush.op = GNTTAB_CACHE_CLEAN;
> - }
> - if (cflush.op)
> - HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1);
> + if (size + cflush.offset > XEN_PAGE_SIZE)
> + cflush.length = XEN_PAGE_SIZE - cflush.offset;
> + else
> + cflush.length = size;
> +
> + HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1);
>
> - offset = 0;
> - xen_pfn++;
> - left -= len;
> - } while (left);
> + cflush.offset = 0;
> + cflush.a.dev_bus_addr += cflush.length;
> + size -= cflush.length;
Yes that's better
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
> + } while (size);
> }
>
> static void __xen_dma_page_dev_to_cpu(struct device *hwdev, dma_addr_t handle,
> size_t size, enum dma_data_direction dir)
> {
> - dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, DMA_UNMAP);
> + if (dir != DMA_TO_DEVICE)
> + dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL);
> }
>
> static void __xen_dma_page_cpu_to_dev(struct device *hwdev, dma_addr_t handle,
> size_t size, enum dma_data_direction dir)
> {
> - dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, DMA_MAP);
> + if (dir == DMA_FROM_DEVICE)
> + dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL);
> + else
> + dma_cache_maint(handle, size, GNTTAB_CACHE_CLEAN);
> }
>
> void __xen_dma_map_page(struct device *hwdev, struct page *page,
> --
> 2.20.1
>
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply
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