[dpdk-dev,v2] i40e: workaround for XL710 performance
Commit Message
On XL710, performance number is far from the expectation on recent
firmware versions, if promiscuous mode is disabled, or promiscuous
mode is enabled and port MAC address is equal to the packet
destination MAC address. The fix for this issue may not be
integrated in the following firmware version. So the workaround in
software driver is needed. For XL710, it needs to modify the initial
values of 3 internal only registers, which are the same as X710.
Note that the values for X710 and XL710 registers could be different,
and the workaround can be removed when it is fixed in firmware in
the future.
Signed-off-by: Helin Zhang <helin.zhang@intel.com>
---
lib/librte_pmd_i40e/i40e_ethdev.c | 44 ++++++++++++++++++++++++++-------------
1 file changed, 30 insertions(+), 14 deletions(-)
v2 changes:
* Supported modifying the address of 0x269FBC of XL710 during
initialization, to fix the minor performance gap to expectation.
That means XL710 can meet the performance expectation with this
workaround.
Comments
> -----Original Message-----
> From: Zhang, Helin
> Sent: Monday, December 29, 2014 9:41 AM
> To: dev@dpdk.org
> Cc: nhorman@tuxdriver.com; Xu, Qian Q; Cao, Waterman; Lu, Patrick; Liu,
> Jijiang; Wu, Jingjing; Zhang, Helin
> Subject: [PATCH v2] i40e: workaround for XL710 performance
>
> On XL710, performance number is far from the expectation on recent
> firmware versions, if promiscuous mode is disabled, or promiscuous mode is
> enabled and port MAC address is equal to the packet destination MAC
> address. The fix for this issue may not be integrated in the following
> firmware version. So the workaround in software driver is needed. For XL710,
> it needs to modify the initial values of 3 internal only registers, which are the
> same as X710.
> Note that the values for X710 and XL710 registers could be different, and the
> workaround can be removed when it is fixed in firmware in the future.
>
> Signed-off-by: Helin Zhang <helin.zhang@intel.com>
> ---
> lib/librte_pmd_i40e/i40e_ethdev.c | 44 ++++++++++++++++++++++++++---
> ----------
> 1 file changed, 30 insertions(+), 14 deletions(-)
>
> v2 changes:
> * Supported modifying the address of 0x269FBC of XL710 during
> initialization, to fix the minor performance gap to expectation.
> That means XL710 can meet the performance expectation with this
> workaround.
>
> diff --git a/lib/librte_pmd_i40e/i40e_ethdev.c
> b/lib/librte_pmd_i40e/i40e_ethdev.c
> index b47a3d2..8982920 100644
> --- a/lib/librte_pmd_i40e/i40e_ethdev.c
> +++ b/lib/librte_pmd_i40e/i40e_ethdev.c
> @@ -5327,38 +5327,54 @@ i40e_debug_read_register(struct i40e_hw *hw,
> uint32_t addr, uint64_t *val)
>
> /*
> * On X710, performance number is far from the expectation on recent
> firmware
> - * versions. The fix for this issue may not be integrated in the following
> + * versions; on XL710, performance number is also far from the
> + expectation on
> + * recent firmware versions, if promiscuous mode is disabled, or
> + promiscuous
> + * mode is enabled and port MAC address is equal to the packet
> + destination MAC
> + * address. The fix for this issue may not be integrated in the
> + following
> * firmware version. So the workaround in software driver is needed. It
> needs
> - * to modify the initial values of 3 internal only registers. Note that the
> + * to modify the initial values of 3 internal only registers for both
> + X710 and
> + * XL710. Note that the values for X710 or XL710 could be different,
> + and the
> * workaround can be removed when it is fixed in firmware in the future.
> */
> -static void
> -i40e_configure_registers(struct i40e_hw *hw) -{
> +
> +/* For both X710 and XL710 */
> +#define I40E_GL_SWR_PRI_JOIN_MAP_0_VALUE 0x10000200
> #define I40E_GL_SWR_PRI_JOIN_MAP_0 0x26CE00
> +
> +#define I40E_GL_SWR_PRI_JOIN_MAP_2_VALUE 0x011f0200
> #define I40E_GL_SWR_PRI_JOIN_MAP_2 0x26CE08
> +
> +/* For X710 */
> +#define I40E_GL_SWR_PM_UP_THR_EF_VALUE 0x03030303
> +/* For XL710 */
> +#define I40E_GL_SWR_PM_UP_THR_SF_VALUE 0x06060606
> #define I40E_GL_SWR_PM_UP_THR 0x269FBC
> -#define I40E_GL_SWR_PRI_JOIN_MAP_0_VALUE 0x10000200 -#define
> I40E_GL_SWR_PRI_JOIN_MAP_2_VALUE 0x011f0200
> -#define I40E_GL_SWR_PM_UP_THR_VALUE 0x03030303
>
> - static const struct {
> +static void
> +i40e_configure_registers(struct i40e_hw *hw) {
> + static struct {
> uint32_t addr;
> uint64_t val;
> } reg_table[] = {
> {I40E_GL_SWR_PRI_JOIN_MAP_0,
> I40E_GL_SWR_PRI_JOIN_MAP_0_VALUE},
> {I40E_GL_SWR_PRI_JOIN_MAP_2,
> I40E_GL_SWR_PRI_JOIN_MAP_2_VALUE},
> - {I40E_GL_SWR_PM_UP_THR,
> I40E_GL_SWR_PM_UP_THR_VALUE},
> + {I40E_GL_SWR_PM_UP_THR, 0}, /* Compute value
> dynamically */
> };
> uint64_t reg;
> uint32_t i;
> int ret;
>
> - /* Below fix is for X710 only */
> - if (i40e_is_40G_device(hw->device_id))
> - return;
> -
> for (i = 0; i < RTE_DIM(reg_table); i++) {
> + if (reg_table[i].addr == I40E_GL_SWR_PM_UP_THR) {
> + if (i40e_is_40G_device(hw->device_id)) /* For XL710
> */
> + reg_table[i].val =
> +
> I40E_GL_SWR_PM_UP_THR_SF_VALUE;
> + else /* For X710 */
> + reg_table[i].val =
> +
> I40E_GL_SWR_PM_UP_THR_EF_VALUE;
> + }
> +
> ret = i40e_debug_read_register(hw, reg_table[i].addr, ®);
> if (ret < 0) {
> PMD_DRV_LOG(ERR, "Failed to read from
> 0x%"PRIx32,
> --
> 1.9.3
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Thank you, Jingjing!
Regards,
Helin
> -----Original Message-----
> From: Wu, Jingjing
> Sent: Monday, January 12, 2015 3:34 PM
> To: Zhang, Helin; dev@dpdk.org
> Cc: nhorman@tuxdriver.com; Xu, Qian Q; Cao, Waterman; Lu, Patrick; Liu,
> Jijiang
> Subject: RE: [PATCH v2] i40e: workaround for XL710 performance
>
>
>
> > -----Original Message-----
> > From: Zhang, Helin
> > Sent: Monday, December 29, 2014 9:41 AM
> > To: dev@dpdk.org
> > Cc: nhorman@tuxdriver.com; Xu, Qian Q; Cao, Waterman; Lu, Patrick;
> > Liu, Jijiang; Wu, Jingjing; Zhang, Helin
> > Subject: [PATCH v2] i40e: workaround for XL710 performance
> >
> > On XL710, performance number is far from the expectation on recent
> > firmware versions, if promiscuous mode is disabled, or promiscuous
> > mode is enabled and port MAC address is equal to the packet
> > destination MAC address. The fix for this issue may not be integrated
> > in the following firmware version. So the workaround in software
> > driver is needed. For XL710, it needs to modify the initial values of
> > 3 internal only registers, which are the same as X710.
> > Note that the values for X710 and XL710 registers could be different,
> > and the workaround can be removed when it is fixed in firmware in the future.
> >
> > Signed-off-by: Helin Zhang <helin.zhang@intel.com>
> > ---
> > lib/librte_pmd_i40e/i40e_ethdev.c | 44 ++++++++++++++++++++++++++---
> > ----------
> > 1 file changed, 30 insertions(+), 14 deletions(-)
> >
> > v2 changes:
> > * Supported modifying the address of 0x269FBC of XL710 during
> > initialization, to fix the minor performance gap to expectation.
> > That means XL710 can meet the performance expectation with this
> > workaround.
> >
> > diff --git a/lib/librte_pmd_i40e/i40e_ethdev.c
> > b/lib/librte_pmd_i40e/i40e_ethdev.c
> > index b47a3d2..8982920 100644
> > --- a/lib/librte_pmd_i40e/i40e_ethdev.c
> > +++ b/lib/librte_pmd_i40e/i40e_ethdev.c
> > @@ -5327,38 +5327,54 @@ i40e_debug_read_register(struct i40e_hw *hw,
> > uint32_t addr, uint64_t *val)
> >
> > /*
> > * On X710, performance number is far from the expectation on recent
> > firmware
> > - * versions. The fix for this issue may not be integrated in the
> > following
> > + * versions; on XL710, performance number is also far from the
> > + expectation on
> > + * recent firmware versions, if promiscuous mode is disabled, or
> > + promiscuous
> > + * mode is enabled and port MAC address is equal to the packet
> > + destination MAC
> > + * address. The fix for this issue may not be integrated in the
> > + following
> > * firmware version. So the workaround in software driver is needed.
> > It needs
> > - * to modify the initial values of 3 internal only registers. Note
> > that the
> > + * to modify the initial values of 3 internal only registers for both
> > + X710 and
> > + * XL710. Note that the values for X710 or XL710 could be different,
> > + and the
> > * workaround can be removed when it is fixed in firmware in the future.
> > */
> > -static void
> > -i40e_configure_registers(struct i40e_hw *hw) -{
> > +
> > +/* For both X710 and XL710 */
> > +#define I40E_GL_SWR_PRI_JOIN_MAP_0_VALUE 0x10000200
> > #define I40E_GL_SWR_PRI_JOIN_MAP_0 0x26CE00
> > +
> > +#define I40E_GL_SWR_PRI_JOIN_MAP_2_VALUE 0x011f0200
> > #define I40E_GL_SWR_PRI_JOIN_MAP_2 0x26CE08
> > +
> > +/* For X710 */
> > +#define I40E_GL_SWR_PM_UP_THR_EF_VALUE 0x03030303
> > +/* For XL710 */
> > +#define I40E_GL_SWR_PM_UP_THR_SF_VALUE 0x06060606
> > #define I40E_GL_SWR_PM_UP_THR 0x269FBC
> > -#define I40E_GL_SWR_PRI_JOIN_MAP_0_VALUE 0x10000200 -#define
> > I40E_GL_SWR_PRI_JOIN_MAP_2_VALUE 0x011f0200
> > -#define I40E_GL_SWR_PM_UP_THR_VALUE 0x03030303
> >
> > - static const struct {
> > +static void
> > +i40e_configure_registers(struct i40e_hw *hw) {
> > + static struct {
> > uint32_t addr;
> > uint64_t val;
> > } reg_table[] = {
> > {I40E_GL_SWR_PRI_JOIN_MAP_0,
> > I40E_GL_SWR_PRI_JOIN_MAP_0_VALUE},
> > {I40E_GL_SWR_PRI_JOIN_MAP_2,
> > I40E_GL_SWR_PRI_JOIN_MAP_2_VALUE},
> > - {I40E_GL_SWR_PM_UP_THR,
> > I40E_GL_SWR_PM_UP_THR_VALUE},
> > + {I40E_GL_SWR_PM_UP_THR, 0}, /* Compute value
> > dynamically */
> > };
> > uint64_t reg;
> > uint32_t i;
> > int ret;
> >
> > - /* Below fix is for X710 only */
> > - if (i40e_is_40G_device(hw->device_id))
> > - return;
> > -
> > for (i = 0; i < RTE_DIM(reg_table); i++) {
> > + if (reg_table[i].addr == I40E_GL_SWR_PM_UP_THR) {
> > + if (i40e_is_40G_device(hw->device_id)) /* For XL710
> > */
> > + reg_table[i].val =
> > +
> > I40E_GL_SWR_PM_UP_THR_SF_VALUE;
> > + else /* For X710 */
> > + reg_table[i].val =
> > +
> > I40E_GL_SWR_PM_UP_THR_EF_VALUE;
> > + }
> > +
> > ret = i40e_debug_read_register(hw, reg_table[i].addr, ®);
> > if (ret < 0) {
> > PMD_DRV_LOG(ERR, "Failed to read from 0x%"PRIx32,
> > --
> > 1.9.3
>
> Acked-by: Jingjing Wu <jingjing.wu@intel.com>
> Subject: [PATCH v2] i40e: workaround for XL710 performance
>
> On XL710, performance number is far from the expectation on recent firmware
> versions, if promiscuous mode is disabled, or promiscuous mode is enabled and
> port MAC address is equal to the packet destination MAC address. The fix for
> this issue may not be integrated in the following firmware version. So the
> workaround in software driver is needed. For XL710, it needs to modify the
> initial values of 3 internal only registers, which are the same as X710.
> Note that the values for X710 and XL710 registers could be different, and the
> workaround can be removed when it is fixed in firmware in the future.
>
> Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
> ---
> lib/librte_pmd_i40e/i40e_ethdev.c | 44
> ++++++++++++++++++++++++++-------------
> 1 file changed, 30 insertions(+), 14 deletions(-)
>
> v2 changes:
> * Supported modifying the address of 0x269FBC of XL710 during
> initialization, to fix the minor performance gap to expectation.
> That means XL710 can meet the performance expectation with this
> workaround.
Applied. Thanks to Neil's for his reviewing efforts on v1 version!
Thanks,
Helin
@@ -5327,38 +5327,54 @@ i40e_debug_read_register(struct i40e_hw *hw, uint32_t addr, uint64_t *val)
/*
* On X710, performance number is far from the expectation on recent firmware
- * versions. The fix for this issue may not be integrated in the following
+ * versions; on XL710, performance number is also far from the expectation on
+ * recent firmware versions, if promiscuous mode is disabled, or promiscuous
+ * mode is enabled and port MAC address is equal to the packet destination MAC
+ * address. The fix for this issue may not be integrated in the following
* firmware version. So the workaround in software driver is needed. It needs
- * to modify the initial values of 3 internal only registers. Note that the
+ * to modify the initial values of 3 internal only registers for both X710 and
+ * XL710. Note that the values for X710 or XL710 could be different, and the
* workaround can be removed when it is fixed in firmware in the future.
*/
-static void
-i40e_configure_registers(struct i40e_hw *hw)
-{
+
+/* For both X710 and XL710 */
+#define I40E_GL_SWR_PRI_JOIN_MAP_0_VALUE 0x10000200
#define I40E_GL_SWR_PRI_JOIN_MAP_0 0x26CE00
+
+#define I40E_GL_SWR_PRI_JOIN_MAP_2_VALUE 0x011f0200
#define I40E_GL_SWR_PRI_JOIN_MAP_2 0x26CE08
+
+/* For X710 */
+#define I40E_GL_SWR_PM_UP_THR_EF_VALUE 0x03030303
+/* For XL710 */
+#define I40E_GL_SWR_PM_UP_THR_SF_VALUE 0x06060606
#define I40E_GL_SWR_PM_UP_THR 0x269FBC
-#define I40E_GL_SWR_PRI_JOIN_MAP_0_VALUE 0x10000200
-#define I40E_GL_SWR_PRI_JOIN_MAP_2_VALUE 0x011f0200
-#define I40E_GL_SWR_PM_UP_THR_VALUE 0x03030303
- static const struct {
+static void
+i40e_configure_registers(struct i40e_hw *hw)
+{
+ static struct {
uint32_t addr;
uint64_t val;
} reg_table[] = {
{I40E_GL_SWR_PRI_JOIN_MAP_0, I40E_GL_SWR_PRI_JOIN_MAP_0_VALUE},
{I40E_GL_SWR_PRI_JOIN_MAP_2, I40E_GL_SWR_PRI_JOIN_MAP_2_VALUE},
- {I40E_GL_SWR_PM_UP_THR, I40E_GL_SWR_PM_UP_THR_VALUE},
+ {I40E_GL_SWR_PM_UP_THR, 0}, /* Compute value dynamically */
};
uint64_t reg;
uint32_t i;
int ret;
- /* Below fix is for X710 only */
- if (i40e_is_40G_device(hw->device_id))
- return;
-
for (i = 0; i < RTE_DIM(reg_table); i++) {
+ if (reg_table[i].addr == I40E_GL_SWR_PM_UP_THR) {
+ if (i40e_is_40G_device(hw->device_id)) /* For XL710 */
+ reg_table[i].val =
+ I40E_GL_SWR_PM_UP_THR_SF_VALUE;
+ else /* For X710 */
+ reg_table[i].val =
+ I40E_GL_SWR_PM_UP_THR_EF_VALUE;
+ }
+
ret = i40e_debug_read_register(hw, reg_table[i].addr, ®);
if (ret < 0) {
PMD_DRV_LOG(ERR, "Failed to read from 0x%"PRIx32,