* [PATCH 08/10] net/e1000/base: propagate PHY control register write error
From: Ciara Loftus @ 2026-05-20 12:52 UTC (permalink / raw)
To: dev; +Cc: Dima Ruinskiy, stable, Ciara Loftus
In-Reply-To: <20260520125256.354336-1-ciara.loftus@intel.com>
From: Dima Ruinskiy <dima.ruinskiy@intel.com>
During HV PHY workaround handling, a failure writing to the PHY control
register was silently discarded rather than returned to the caller. Add
the missing early return so the error is correctly propagated.
Fixes: 5a32a257f957 ("e1000: more NICs in base driver")
Cc: stable@dpdk.org
Signed-off-by: Dima Ruinskiy <dima.ruinskiy@intel.com>
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
---
drivers/net/intel/e1000/base/e1000_ich8lan.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/intel/e1000/base/e1000_ich8lan.c b/drivers/net/intel/e1000/base/e1000_ich8lan.c
index e62847fb4e..0290a7dcb4 100644
--- a/drivers/net/intel/e1000/base/e1000_ich8lan.c
+++ b/drivers/net/intel/e1000/base/e1000_ich8lan.c
@@ -2696,6 +2696,8 @@ STATIC s32 e1000_hv_phy_workarounds_ich8lan(struct e1000_hw *hw)
e1000_phy_sw_reset_generic(hw);
ret_val = hw->phy.ops.write_reg(hw, PHY_CONTROL,
0x3140);
+ if (ret_val)
+ return ret_val;
}
}
--
2.43.0
^ permalink raw reply related
* [PATCH 07/10] net/e1000/base: fix NVM loop bounds and pointer access
From: Ciara Loftus @ 2026-05-20 12:52 UTC (permalink / raw)
To: dev; +Cc: Menachem Fogel, stable, Dima Ruinskiy, Ciara Loftus
In-Reply-To: <20260520125256.354336-1-ciara.loftus@intel.com>
From: Menachem Fogel <menachem.fogel@intel.com>
Improve the NVM checksum routines by ensuring loop bounds are compared
at the correct integer width. Use array indexing instead of explicit
pointer arithmetic.
Fixes: af75078fece3 ("first public release")
Cc: stable@dpdk.org
Signed-off-by: Menachem Fogel <menachem.fogel@intel.com>
Signed-off-by: Dima Ruinskiy <dima.ruinskiy@intel.com>
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
---
drivers/net/intel/e1000/base/e1000_82575.c | 4 ++--
drivers/net/intel/e1000/base/e1000_manage.c | 4 ++--
2 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/intel/e1000/base/e1000_82575.c b/drivers/net/intel/e1000/base/e1000_82575.c
index c263f42ca1..8ae2b77d5f 100644
--- a/drivers/net/intel/e1000/base/e1000_82575.c
+++ b/drivers/net/intel/e1000/base/e1000_82575.c
@@ -2395,7 +2395,7 @@ s32 e1000_validate_nvm_checksum_with_offset(struct e1000_hw *hw, u16 offset)
DEBUGFUNC("e1000_validate_nvm_checksum_with_offset");
- for (i = offset; i < ((NVM_CHECKSUM_REG + offset) + 1); i++) {
+ for (i = offset; i < (u16)((NVM_CHECKSUM_REG + offset) + 1); i++) {
ret_val = hw->nvm.ops.read(hw, i, 1, &nvm_data);
if (ret_val) {
DEBUGOUT("NVM Read Error\n");
@@ -2432,7 +2432,7 @@ s32 e1000_update_nvm_checksum_with_offset(struct e1000_hw *hw, u16 offset)
DEBUGFUNC("e1000_update_nvm_checksum_with_offset");
- for (i = offset; i < (NVM_CHECKSUM_REG + offset); i++) {
+ for (i = offset; i < (u16)(NVM_CHECKSUM_REG + offset); i++) {
ret_val = hw->nvm.ops.read(hw, i, 1, &nvm_data);
if (ret_val) {
DEBUGOUT("NVM Read Error while updating checksum.\n");
diff --git a/drivers/net/intel/e1000/base/e1000_manage.c b/drivers/net/intel/e1000/base/e1000_manage.c
index 4b81028302..71df2890f3 100644
--- a/drivers/net/intel/e1000/base/e1000_manage.c
+++ b/drivers/net/intel/e1000/base/e1000_manage.c
@@ -129,7 +129,7 @@ bool e1000_enable_tx_pkt_filtering_generic(struct e1000_hw *hw)
len = E1000_MNG_DHCP_COOKIE_LENGTH >> 2;
offset = E1000_MNG_DHCP_COOKIE_OFFSET >> 2;
for (i = 0; i < len; i++)
- *(buffer + i) = E1000_READ_REG_ARRAY_DWORD(hw, E1000_HOST_IF,
+ buffer[i] = E1000_READ_REG_ARRAY_DWORD(hw, E1000_HOST_IF,
offset + i);
hdr_csum = hdr->checksum;
hdr->checksum = 0;
@@ -173,7 +173,7 @@ s32 e1000_mng_write_cmd_header_generic(struct e1000_hw *hw,
/* Write the relevant command block into the ram area. */
for (i = 0; i < length; i++) {
E1000_WRITE_REG_ARRAY_DWORD(hw, E1000_HOST_IF, i,
- *((u32 *) hdr + i));
+ ((u32 *)hdr)[i]);
E1000_WRITE_FLUSH(hw);
}
--
2.43.0
^ permalink raw reply related
* [PATCH 06/10] net/e1000/base: fix coding style issues
From: Ciara Loftus @ 2026-05-20 12:52 UTC (permalink / raw)
To: dev; +Cc: Dima Ruinskiy, Ciara Loftus
In-Reply-To: <20260520125256.354336-1-ciara.loftus@intel.com>
From: Dima Ruinskiy <dima.ruinskiy@intel.com>
Fix whitespace and tab inconsistencies.
Fixes: a3358d942fa9 ("net/e1000/base: enable new I219 devices")
Fixes: bdca22d62ff0 ("net/e1000/base: add PHY read/write retry mechanism")
Signed-off-by: Dima Ruinskiy <dima.ruinskiy@intel.com>
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
---
drivers/net/intel/e1000/base/e1000_ich8lan.c | 6 +++---
drivers/net/intel/e1000/base/e1000_phy.c | 5 ++---
2 files changed, 5 insertions(+), 6 deletions(-)
diff --git a/drivers/net/intel/e1000/base/e1000_ich8lan.c b/drivers/net/intel/e1000/base/e1000_ich8lan.c
index 96b9ad6a70..e62847fb4e 100644
--- a/drivers/net/intel/e1000/base/e1000_ich8lan.c
+++ b/drivers/net/intel/e1000/base/e1000_ich8lan.c
@@ -4178,7 +4178,7 @@ STATIC s32 e1000_update_nvm_checksum_spt(struct e1000_hw *hw)
usec_delay(100);
- /* Write the data to the new bank. Offset in words*/
+ /* Write the data to the new bank. Offset in words */
act_offset = i + new_bank_offset;
ret_val = e1000_retry_write_flash_dword_ich8lan(hw, act_offset,
dword);
@@ -4201,7 +4201,7 @@ STATIC s32 e1000_update_nvm_checksum_spt(struct e1000_hw *hw)
*/
act_offset = new_bank_offset + E1000_ICH_NVM_SIG_WORD;
- /*offset in words but we read dword*/
+ /* offset in words but we read dword */
--act_offset;
ret_val = e1000_read_flash_dword_ich8lan(hw, act_offset, &dword);
@@ -4214,7 +4214,7 @@ STATIC s32 e1000_update_nvm_checksum_spt(struct e1000_hw *hw)
if (ret_val)
goto release;
- /* offset in words but we read dword*/
+ /* offset in words but we read dword */
act_offset = old_bank_offset + E1000_ICH_NVM_SIG_WORD - 1;
ret_val = e1000_read_flash_dword_ich8lan(hw, act_offset, &dword);
diff --git a/drivers/net/intel/e1000/base/e1000_phy.c b/drivers/net/intel/e1000/base/e1000_phy.c
index b449c6ef42..31ef5089ba 100644
--- a/drivers/net/intel/e1000/base/e1000_phy.c
+++ b/drivers/net/intel/e1000/base/e1000_phy.c
@@ -253,7 +253,7 @@ s32 e1000_phy_reset_dsp_generic(struct e1000_hw *hw)
return hw->phy.ops.write_reg(hw, M88E1000_PHY_GEN_CONTROL, 0);
}
-void e1000_disable_phy_retry_mechanism(struct e1000_hw* hw, u32* phy_retries_original)
+void e1000_disable_phy_retry_mechanism(struct e1000_hw *hw, u32 *phy_retries_original)
{
DEBUGFUNC("e1000_disable_phy_retry_mechanism");
@@ -262,7 +262,7 @@ void e1000_disable_phy_retry_mechanism(struct e1000_hw* hw, u32* phy_retries_ori
hw->phy.current_retry_counter = 0;
}
-void e1000_enable_phy_retry_mechanism(struct e1000_hw* hw, u32 phy_retries_original)
+void e1000_enable_phy_retry_mechanism(struct e1000_hw *hw, u32 phy_retries_original)
{
DEBUGFUNC("e1000_enable_phy_retry_mechanism");
@@ -346,7 +346,6 @@ s32 e1000_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data)
}
}
-
return -E1000_ERR_PHY;
}
--
2.43.0
^ permalink raw reply related
* [PATCH 05/10] net/e1000/base: clear DPG enable bit post MAC reset
From: Ciara Loftus @ 2026-05-20 12:52 UTC (permalink / raw)
To: dev; +Cc: Vitaly Lifshits, Ciara Loftus
In-Reply-To: <20260520125256.354336-1-ciara.loftus@intel.com>
From: Vitaly Lifshits <vitaly.lifshits@intel.com>
The GbE autonomous power gating feature was added to support G3 to S5
flow. However, this changed the reset value of DPG_EN bit to 1, causing
a possible autonomous transition to power gating state during D0. This
might result in undefined errors such as: packet loss, packet corruption
and Tx/Rx hangs. Therefore, clear DPG_EN bit after hardware reset flow.
Signed-off-by: Vitaly Lifshits <vitaly.lifshits@intel.com>
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
---
drivers/net/intel/e1000/base/e1000_defines.h | 1 +
drivers/net/intel/e1000/base/e1000_ich8lan.c | 7 +++++++
2 files changed, 8 insertions(+)
diff --git a/drivers/net/intel/e1000/base/e1000_defines.h b/drivers/net/intel/e1000/base/e1000_defines.h
index eb93675823..6c710300a6 100644
--- a/drivers/net/intel/e1000/base/e1000_defines.h
+++ b/drivers/net/intel/e1000/base/e1000_defines.h
@@ -36,6 +36,7 @@
/* Extended Device Control */
#define E1000_CTRL_EXT_LPCD 0x00000004 /* LCD Power Cycle Done */
+#define E1000_CTRL_EXT_DPG_EN 0x00000008 /* Dynamic Power Gating Enable */
#define E1000_CTRL_EXT_SDP4_DATA 0x00000010 /* SW Definable Pin 4 data */
#define E1000_CTRL_EXT_SDP6_DATA 0x00000040 /* SW Definable Pin 6 data */
#define E1000_CTRL_EXT_SDP3_DATA 0x00000080 /* SW Definable Pin 3 data */
diff --git a/drivers/net/intel/e1000/base/e1000_ich8lan.c b/drivers/net/intel/e1000/base/e1000_ich8lan.c
index 6190052368..96b9ad6a70 100644
--- a/drivers/net/intel/e1000/base/e1000_ich8lan.c
+++ b/drivers/net/intel/e1000/base/e1000_ich8lan.c
@@ -5107,6 +5107,13 @@ STATIC s32 e1000_reset_hw_ich8lan(struct e1000_hw *hw)
reg |= E1000_KABGTXD_BGSQLBIAS;
E1000_WRITE_REG(hw, E1000_KABGTXD, reg);
+ if (hw->mac.type >= e1000_pch_ptp) {
+ DEBUGOUT("Clearing DPG EN bit post reset\n");
+ reg = E1000_READ_REG(hw, E1000_CTRL_EXT);
+ reg &= ~E1000_CTRL_EXT_DPG_EN;
+ E1000_WRITE_REG(hw, E1000_CTRL_EXT, reg);
+ }
+
return E1000_SUCCESS;
}
--
2.43.0
^ permalink raw reply related
* [PATCH 04/10] net/e1000/base: reclassify MAC type
From: Ciara Loftus @ 2026-05-20 12:52 UTC (permalink / raw)
To: dev; +Cc: Vitaly Lifshits, Ciara Loftus
In-Reply-To: <20260520125256.354336-1-ciara.loftus@intel.com>
From: Vitaly Lifshits <vitaly.lifshits@intel.com>
Reclassify LM19/V19 from e1000_pch_mtp to e1000_pch_adp.
Signed-off-by: Vitaly Lifshits <vitaly.lifshits@intel.com>
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
---
drivers/net/intel/e1000/base/e1000_api.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/intel/e1000/base/e1000_api.c b/drivers/net/intel/e1000/base/e1000_api.c
index 7ff63414a7..a7877613e3 100644
--- a/drivers/net/intel/e1000/base/e1000_api.c
+++ b/drivers/net/intel/e1000/base/e1000_api.c
@@ -312,12 +312,12 @@ s32 e1000_set_mac_type(struct e1000_hw *hw)
case E1000_DEV_ID_PCH_ADL_I219_V17:
case E1000_DEV_ID_PCH_RPL_I219_LM22:
case E1000_DEV_ID_PCH_RPL_I219_V22:
+ case E1000_DEV_ID_PCH_MTP_I219_LM19:
+ case E1000_DEV_ID_PCH_MTP_I219_V19:
mac->type = e1000_pch_adp;
break;
case E1000_DEV_ID_PCH_MTP_I219_LM18:
case E1000_DEV_ID_PCH_MTP_I219_V18:
- case E1000_DEV_ID_PCH_MTP_I219_LM19:
- case E1000_DEV_ID_PCH_MTP_I219_V19:
case E1000_DEV_ID_PCH_LNL_I219_LM20:
case E1000_DEV_ID_PCH_LNL_I219_V20:
case E1000_DEV_ID_PCH_ARL_I219_LM24:
--
2.43.0
^ permalink raw reply related
* [PATCH 03/10] net/e1000/base: fix possible variable overflow
From: Ciara Loftus @ 2026-05-20 12:52 UTC (permalink / raw)
To: dev; +Cc: Lukasz Czapnik, stable, Ciara Loftus
In-Reply-To: <20260520125256.354336-1-ciara.loftus@intel.com>
From: Lukasz Czapnik <lukasz.czapnik@intel.com>
Bits can be lost as temporary math is done on signed variables and the
result is assigned to an unsigned variable. Cast to u32 to force the
compiler to do operations on unsigned temporary variables.
Fixes: af75078fece3 ("first public release")
Cc: stable@dpdk.org
Signed-off-by: Lukasz Czapnik <lukasz.czapnik@intel.com>
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
---
drivers/net/intel/e1000/base/e1000_mac.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/intel/e1000/base/e1000_mac.c b/drivers/net/intel/e1000/base/e1000_mac.c
index 41aae86ffe..408e8e46e8 100644
--- a/drivers/net/intel/e1000/base/e1000_mac.c
+++ b/drivers/net/intel/e1000/base/e1000_mac.c
@@ -1970,7 +1970,7 @@ s32 e1000_blink_led_generic(struct e1000_hw *hw)
(mode == E1000_LEDCTL_MODE_LED_OFF))) {
ledctl_blink &=
~(E1000_LEDCTL_LED0_MODE_MASK << i);
- ledctl_blink |= (E1000_LEDCTL_LED0_BLINK |
+ ledctl_blink |= (u32)(E1000_LEDCTL_LED0_BLINK |
E1000_LEDCTL_MODE_LED_ON) << i;
}
}
--
2.43.0
^ permalink raw reply related
* [PATCH 02/10] net/e1000/base: fix typo in e1000 base code
From: Ciara Loftus @ 2026-05-20 12:52 UTC (permalink / raw)
To: dev; +Cc: Vitaly Lifshits, stable, Ciara Loftus
In-Reply-To: <20260520125256.354336-1-ciara.loftus@intel.com>
From: Vitaly Lifshits <vitaly.lifshits@intel.com>
A typo was introduced in commit ba54bdc79d94 ("net/e1000/base: improve
clock synchronization workaround"). Fix it.
Fixes: ba54bdc79d94 ("net/e1000/base: improve clock synchronization workaround")
Cc: stable@dpdk.org
Signed-off-by: Vitaly Lifshits <vitaly.lifshits@intel.com>
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
---
drivers/net/intel/e1000/base/e1000_ich8lan.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/intel/e1000/base/e1000_ich8lan.c b/drivers/net/intel/e1000/base/e1000_ich8lan.c
index 58597cce8a..6190052368 100644
--- a/drivers/net/intel/e1000/base/e1000_ich8lan.c
+++ b/drivers/net/intel/e1000/base/e1000_ich8lan.c
@@ -288,7 +288,7 @@ STATIC void e1000_toggle_lanphypc_pch_lpt(struct e1000_hw *hw)
* e1000_reconfigure_k1_exit_timeout
* @hw: pointer to the HW structure
*
- * Reconfigure K1 exit timeout as a workaround to the PHY sycndhronization issue
+ * Reconfigure K1 exit timeout as a workaround to the PHY synchronization issue
* on MTL, LNL, PTL and WCL.
*
* Assuming PHY semaphore is taken prior to this function call.
--
2.43.0
^ permalink raw reply related
* [PATCH 01/10] net/e1000/base: refactor K1 exit timeout configuration
From: Ciara Loftus @ 2026-05-20 12:52 UTC (permalink / raw)
To: dev; +Cc: Vitaly Lifshits, stable, Ciara Loftus
In-Reply-To: <20260520125256.354336-1-ciara.loftus@intel.com>
From: Vitaly Lifshits <vitaly.lifshits@intel.com>
Replace magic numbers in the FEXTNVM12 register access with named bit
definitions to improve readability. Add a missing error path to ensure
ME activity blocking a PHY reset is correctly propagated to the caller.
Also improve some code formatting.
Fixes: 38db3f7f50bd ("e1000: update base driver")
Cc: stable@dpdk.org
Signed-off-by: Vitaly Lifshits <vitaly.lifshits@intel.com>
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
---
drivers/net/intel/e1000/base/e1000_ich8lan.c | 11 ++++++++---
drivers/net/intel/e1000/base/e1000_ich8lan.h | 3 +++
2 files changed, 11 insertions(+), 3 deletions(-)
diff --git a/drivers/net/intel/e1000/base/e1000_ich8lan.c b/drivers/net/intel/e1000/base/e1000_ich8lan.c
index ece61650f7..58597cce8a 100644
--- a/drivers/net/intel/e1000/base/e1000_ich8lan.c
+++ b/drivers/net/intel/e1000/base/e1000_ich8lan.c
@@ -305,8 +305,8 @@ STATIC s32 e1000_reconfigure_k1_exit_timeout(struct e1000_hw *hw)
return E1000_SUCCESS;
fextnvm12 = E1000_READ_REG(hw, E1000_FEXTNVM12);
- fextnvm12 |= (1 << 23);
- fextnvm12 &= ~((1 << 22));
+ fextnvm12 &= ~E1000_FEXTNVM12_PHYPD_CTRL_MASK;
+ fextnvm12 |= E1000_FEXTNVM12_PHYPD_CTRL_P1;
E1000_WRITE_REG(hw, E1000_FEXTNVM12, fextnvm12);
msec_delay_irq(1);
@@ -318,6 +318,9 @@ STATIC s32 e1000_reconfigure_k1_exit_timeout(struct e1000_hw *hw)
ret_val = hw->phy.ops.write_reg_locked(hw, E1000_PHY_TIMEOUTS_REG,
phy_timeout);
+ DEBUGOUT1("e1000_reconfigure_k1_exit_timeout returns %d\n",
+ ret_val);
+
return ret_val;
}
@@ -460,8 +463,10 @@ STATIC s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw)
* the PHY is in.
*/
ret_val = hw->phy.ops.check_reset_block(hw);
- if (ret_val)
+ if (ret_val) {
ERROR_REPORT("ME blocked access to PHY after reset\n");
+ goto out;
+ }
if (hw->mac.type >= e1000_pch_mtp) {
ret_val = hw->phy.ops.acquire(hw);
diff --git a/drivers/net/intel/e1000/base/e1000_ich8lan.h b/drivers/net/intel/e1000/base/e1000_ich8lan.h
index f2ba910ea6..43360400bc 100644
--- a/drivers/net/intel/e1000/base/e1000_ich8lan.h
+++ b/drivers/net/intel/e1000/base/e1000_ich8lan.h
@@ -89,6 +89,9 @@
#define E1000_FEXTNVM11_DISABLE_PB_READ 0x00000200
#define E1000_FEXTNVM11_DISABLE_MULR_FIX 0x00002000
#define E1000_FEXTNVM12_DONT_WAK_DPG_CLKREQ 0x00001000
+#define E1000_FEXTNVM12_PHYPD_CTRL_MASK 0x00C00000
+#define E1000_FEXTNVM12_PHYPD_CTRL_P1 0x00800000
+
/* bit24: RXDCTL thresholds granularity: 0 - cache lines, 1 - descriptors */
#define E1000_RXDCTL_THRESH_UNIT_DESC 0x01000000
--
2.43.0
^ permalink raw reply related
* [PATCH 00/10] e1000 base code update
From: Ciara Loftus @ 2026-05-20 12:52 UTC (permalink / raw)
To: dev; +Cc: Ciara Loftus
Update the e1000 base code. The changes are mostly fixes, refactoring,
and code cleanup.
Ciara Loftus (1):
net/e1000/base: update version info
Dima Ruinskiy (2):
net/e1000/base: fix coding style issues
net/e1000/base: propagate PHY control register write error
Lukasz Czapnik (1):
net/e1000/base: fix possible variable overflow
Mateusz Fryze (1):
net/e1000/base: auto-negotiation status for 1000BASE-T
Menachem Fogel (1):
net/e1000/base: fix NVM loop bounds and pointer access
Vitaly Lifshits (4):
net/e1000/base: refactor K1 exit timeout configuration
net/e1000/base: fix typo in e1000 base code
net/e1000/base: reclassify MAC type
net/e1000/base: clear DPG enable bit post MAC reset
.mailmap | 1 +
drivers/net/intel/e1000/base/README | 4 +-
drivers/net/intel/e1000/base/e1000_82575.c | 5 +-
drivers/net/intel/e1000/base/e1000_api.c | 20 ++++-
drivers/net/intel/e1000/base/e1000_api.h | 1 +
drivers/net/intel/e1000/base/e1000_defines.h | 23 ++++++
drivers/net/intel/e1000/base/e1000_hw.h | 9 ++
drivers/net/intel/e1000/base/e1000_ich8lan.c | 28 +++++--
drivers/net/intel/e1000/base/e1000_ich8lan.h | 3 +
drivers/net/intel/e1000/base/e1000_mac.c | 2 +-
drivers/net/intel/e1000/base/e1000_manage.c | 4 +-
drivers/net/intel/e1000/base/e1000_phy.c | 86 +++++++++++++++++++-
drivers/net/intel/e1000/base/e1000_phy.h | 2 +
13 files changed, 169 insertions(+), 19 deletions(-)
--
2.43.0
^ permalink raw reply
* [PATCH v4 11/11] test/bpf: add tests for error handling contracts
From: Marat Khalili @ 2026-05-20 12:49 UTC (permalink / raw)
To: Konstantin Ananyev; +Cc: dev
In-Reply-To: <20260520124922.42445-1-marat.khalili@huawei.com>
Verify NULL parameter rejection in load APIs, graceful failure on
argument/flag mismatch in burst execution APIs, and safe return of the
libpcap stub.
Signed-off-by: Marat Khalili <marat.khalili@huawei.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@huawei.com>
---
app/test/test_bpf.c | 128 +++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 127 insertions(+), 1 deletion(-)
diff --git a/app/test/test_bpf.c b/app/test/test_bpf.c
index 026ba18b754a..6422bae6fe5f 100644
--- a/app/test/test_bpf.c
+++ b/app/test/test_bpf.c
@@ -3514,6 +3514,121 @@ run_test(const struct bpf_test *tst)
}
+/* Test all eBPF load APIs with prm set to NULL. */
+static int
+test_bpf_load_null(void)
+{
+ struct rte_bpf *bpf;
+ int saved_errno;
+
+ rte_errno = 0;
+ bpf = rte_bpf_load(NULL);
+ saved_errno = rte_errno;
+ rte_bpf_destroy(bpf);
+ RTE_TEST_ASSERT_NULL(bpf, "rte_bpf_load(NULL) did not return NULL\n");
+ RTE_TEST_ASSERT_EQUAL(saved_errno, EINVAL,
+ "rte_bpf_load(NULL) did not set rte_errno to EINVAL\n");
+
+ rte_errno = 0;
+ bpf = rte_bpf_elf_load(NULL, "a", "b");
+ saved_errno = rte_errno;
+ rte_bpf_destroy(bpf);
+ RTE_TEST_ASSERT_NULL(bpf, "rte_bpf_elf_load(NULL, \"a\", \"b\") did not return NULL\n");
+ RTE_TEST_ASSERT_EQUAL(saved_errno, EINVAL,
+ "rte_bpf_elf_load(NULL, \"a\", \"b\") did not set rte_errno to EINVAL\n");
+
+ rte_errno = 0;
+ bpf = rte_bpf_load_ex(NULL);
+ saved_errno = rte_errno;
+ rte_bpf_destroy(bpf);
+ RTE_TEST_ASSERT_NULL(bpf, "rte_bpf_load_ex(NULL) did not return NULL\n");
+ RTE_TEST_ASSERT_EQUAL(saved_errno, EINVAL,
+ "rte_bpf_load_ex(NULL) did not set rte_errno to EINVAL\n");
+
+ return 0;
+}
+REGISTER_FAST_TEST(bpf_load_null_autotest, NOHUGE_OK, ASAN_OK, test_bpf_load_null);
+
+/* Test calling wrong API for execution of a multi-argument eBPF program. */
+static int
+test_bpf_exec_wrong_nb_prog_arg(void)
+{
+ static const struct ebpf_insn ins[] = {
+ { .code = (EBPF_ALU64 | EBPF_MOV | BPF_K), .dst_reg = EBPF_REG_0, .imm = 0 },
+ { .code = (BPF_JMP | EBPF_EXIT), }
+ };
+ static const struct rte_bpf_prm_ex prm = {
+ .sz = sizeof(struct rte_bpf_prm_ex),
+ .origin = RTE_BPF_ORIGIN_RAW,
+ .raw.ins = ins,
+ .raw.nb_ins = RTE_DIM(ins),
+ .prog_arg = {
+ { .type = RTE_BPF_ARG_RAW, .size = sizeof(uint64_t) },
+ { .type = RTE_BPF_ARG_RAW, .size = sizeof(uint64_t) },
+ },
+ .nb_prog_arg = 2, /* Intentionally mismatched: expects 2, burst gives 1 */
+ };
+
+ struct rte_bpf *bpf;
+ uint64_t rc[1];
+ void *ctx[1] = {NULL};
+ uint32_t result;
+ int saved_errno;
+
+ bpf = rte_bpf_load_ex(&prm);
+ RTE_TEST_ASSERT_NOT_NULL(bpf, "rte_bpf_load_ex failed\n");
+
+ rte_errno = 0;
+ result = rte_bpf_exec_burst(bpf, ctx, rc, 1);
+ saved_errno = rte_errno;
+ rte_bpf_destroy(bpf);
+ RTE_TEST_ASSERT_EQUAL(result, 0, "rte_bpf_exec_burst did not return 0\n");
+ RTE_TEST_ASSERT_EQUAL(saved_errno, EINVAL,
+ "rte_bpf_exec_burst did not set rte_errno to EINVAL\n");
+
+ return 0;
+}
+REGISTER_FAST_TEST(bpf_exec_wrong_nb_prog_arg_autotest, NOHUGE_OK, ASAN_OK,
+ test_bpf_exec_wrong_nb_prog_arg);
+
+/* Test passing unsupported flags when executing an eBPF program. */
+static int
+test_bpf_exec_wrong_flags(void)
+{
+ static const struct ebpf_insn ins[] = {
+ { .code = (EBPF_ALU64 | EBPF_MOV | BPF_K), .dst_reg = EBPF_REG_0, .imm = 0 },
+ { .code = (BPF_JMP | EBPF_EXIT), }
+ };
+ static const struct rte_bpf_prm_ex prm = {
+ .sz = sizeof(struct rte_bpf_prm_ex),
+ .origin = RTE_BPF_ORIGIN_RAW,
+ .raw.ins = ins,
+ .raw.nb_ins = RTE_DIM(ins),
+ .prog_arg = { { .type = RTE_BPF_ARG_RAW, .size = sizeof(uint64_t) } },
+ .nb_prog_arg = 1,
+ };
+
+ struct rte_bpf *bpf;
+ uint64_t rc[1];
+ struct rte_bpf_prog_ctx ctx_ex[1] = {};
+ uint32_t result;
+ int saved_errno;
+
+ bpf = rte_bpf_load_ex(&prm);
+ RTE_TEST_ASSERT_NOT_NULL(bpf, "rte_bpf_load_ex failed\n");
+
+ rte_errno = 0;
+ result = rte_bpf_exec_burst_ex(bpf, ctx_ex, rc, 1, UINT64_MAX);
+ saved_errno = rte_errno;
+ rte_bpf_destroy(bpf);
+ RTE_TEST_ASSERT_EQUAL(result, 0, "rte_bpf_exec_burst_ex did not return 0\n");
+ RTE_TEST_ASSERT_EQUAL(saved_errno, EINVAL,
+ "rte_bpf_exec_burst_ex did not set rte_errno to EINVAL\n");
+
+ return 0;
+}
+REGISTER_FAST_TEST(bpf_exec_wrong_flags_autotest, NOHUGE_OK, ASAN_OK, test_bpf_exec_wrong_flags);
+
static int
test_bpf(void)
{
@@ -4444,7 +4559,18 @@ REGISTER_FAST_TEST(bpf_elf_autotest, NOHUGE_OK, ASAN_OK, test_bpf_elf);
static int
test_bpf_convert(void)
{
- printf("BPF convert RTE_HAS_LIBPCAP is undefined, skipping test\n");
+ int dummy = 0;
+ struct rte_bpf_prm *prm;
+
+ prm = rte_bpf_convert(NULL);
+ rte_free(prm);
+ RTE_TEST_ASSERT_NULL(prm, "rte_bpf_convert(NULL) without libpcap did not return NULL\n");
+
+ prm = rte_bpf_convert((const struct bpf_program *)&dummy);
+ rte_free(prm);
+ RTE_TEST_ASSERT_NULL(prm, "rte_bpf_convert(&dummy) without libpcap did not return NULL\n");
+
+ printf("BPF convert RTE_HAS_LIBPCAP is undefined, skipping full test\n");
return TEST_SKIPPED;
}
--
2.43.0
^ permalink raw reply related
* [PATCH v4 10/11] doc: add load API to BPF programmer's guide
From: Marat Khalili @ 2026-05-20 12:49 UTC (permalink / raw)
To: Konstantin Ananyev; +Cc: dev
In-Reply-To: <20260520124922.42445-1-marat.khalili@huawei.com>
Rewrite the basic operations list to focus on a typical use. Provide an
end-to-end example demonstrating loading from an ELF file, executing via
JIT or the interpreter, and properly handling multiple custom arguments
using rte_bpf_prog_ctx.
Signed-off-by: Marat Khalili <marat.khalili@huawei.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@huawei.com>
---
doc/guides/prog_guide/bpf_lib.rst | 75 ++++++++++++++++++++++++++++---
1 file changed, 68 insertions(+), 7 deletions(-)
diff --git a/doc/guides/prog_guide/bpf_lib.rst b/doc/guides/prog_guide/bpf_lib.rst
index 8c820328b984..df3782508829 100644
--- a/doc/guides/prog_guide/bpf_lib.rst
+++ b/doc/guides/prog_guide/bpf_lib.rst
@@ -15,17 +15,79 @@ for more information.
Also it introduces basic framework to load/unload BPF-based filters
on eth devices (right now only via SW RX/TX callbacks).
-The library API provides the following basic operations:
+The library API provides the following basic operations for working with BPF
+programs:
-* Create a new BPF execution context and load user provided eBPF code into it.
+* **Loading:** The extensible API (``rte_bpf_load_ex``) is the recommended
+ way to load a BPF program. By utilizing ``struct rte_bpf_prm_ex``, you can
+ load an eBPF program from an ELF file on disk, or load eBPF/cBPF bytecode
+ directly from memory buffers.
-* Destroy an BPF execution context and its runtime structures and free the associated memory.
+* **Execution via Callbacks:** Once loaded, a BPF program can be attached to
+ a specific ethernet device port and queue to automatically process incoming
+ or outgoing packets using ``rte_bpf_eth_rx_install`` or
+ ``rte_bpf_eth_tx_install``.
-* Execute eBPF bytecode associated with provided input parameter.
+* **Direct Execution:** You can execute a BPF program directly from your
+ application code using ``rte_bpf_exec_ex`` (or the burst variant
+ ``rte_bpf_exec_burst_ex``). This API allows passing an execution context
+ (``struct rte_bpf_prog_ctx``) containing up to 5 custom arguments.
-* Provide information about natively compiled code for given BPF context.
+* **JIT Execution:** For maximum performance, you can retrieve the natively
+ compiled (JIT) function pointer for a loaded program using
+ ``rte_bpf_get_jit_ex`` and call it directly from your code with the same
+ arguments.
-* Load BPF program from the ELF file and install callback to execute it on given ethdev port/queue.
+* **Cleanup:** Destroy a BPF execution context and free the associated memory
+ using ``rte_bpf_destroy``.
+
+The following is a concise example of loading an eBPF program from an ELF file,
+and executing it directly, utilizing the JIT-compiled version if available:
+
+.. code-block:: c
+
+ struct rte_bpf_prm_ex prm = {
+ .sz = sizeof(struct rte_bpf_prm_ex),
+ .origin = RTE_BPF_ORIGIN_ELF_FILE,
+ .elf_file = {
+ .path = "ptype.o",
+ .section = ".text",
+ },
+ .nb_prog_arg = 2,
+ .prog_arg = {
+ [0] = {
+ .type = RTE_BPF_ARG_PTR_MBUF,
+ .size = sizeof(struct rte_mbuf),
+ .buf_size = RTE_MBUF_DEFAULT_BUF_SIZE,
+ },
+ [1] = {
+ .type = RTE_BPF_ARG_RAW,
+ .size = sizeof(uint64_t),
+ },
+ },
+ };
+ struct rte_bpf *bpf = rte_bpf_load_ex(&prm);
+ if (bpf == NULL) {
+ /* Handle load failure */
+ }
+
+ struct rte_bpf_prog_ctx ctx = {
+ .arg[0] = { .ptr = mbuf },
+ .arg[1] = { .u64 = RTE_PTYPE_L2_MASK | RTE_PTYPE_L3_MASK },
+ };
+
+ struct rte_bpf_jit_ex jit;
+ uint64_t ret;
+ if (rte_bpf_get_jit_ex(bpf, &jit) == 0 && jit.func2 != NULL) {
+ /* Call the JIT-compiled function directly for best performance */
+ ret = jit.func2(ctx.arg[0], ctx.arg[1]);
+ } else {
+ /* Fallback to interpreter */
+ uint64_t flags = 0;
+ ret = rte_bpf_exec_ex(bpf, &ctx, flags);
+ }
+
+ rte_bpf_destroy(bpf);
Packet data load instructions
-----------------------------
@@ -60,7 +122,6 @@ Not currently supported eBPF features
-------------------------------------
- JIT support only available for X86_64 and arm64 platforms
- - cBPF
- tail-pointer call
- eBPF MAP
- external function calls for 32-bit platforms
--
2.43.0
^ permalink raw reply related
* [PATCH v4 09/11] doc: add release notes for new extensible BPF API
From: Marat Khalili @ 2026-05-20 12:49 UTC (permalink / raw)
Cc: dev, Konstantin Ananyev
In-Reply-To: <20260520124922.42445-1-marat.khalili@huawei.com>
Document the following new eBPF features introduced in this release:
* Extensible BPF loading API (rte_bpf_load_ex, rte_bpf_prm_ex).
* Loading and executing eBPF programs with up to 5 arguments.
* Installing already loaded eBPF programs as port callbacks.
Signed-off-by: Marat Khalili <marat.khalili@huawei.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@huawei.com>
---
doc/guides/rel_notes/release_26_07.rst | 20 ++++++++++++++++++++
1 file changed, 20 insertions(+)
diff --git a/doc/guides/rel_notes/release_26_07.rst b/doc/guides/rel_notes/release_26_07.rst
index f012d47a4b1b..18810ab81d93 100644
--- a/doc/guides/rel_notes/release_26_07.rst
+++ b/doc/guides/rel_notes/release_26_07.rst
@@ -63,6 +63,26 @@ New Features
``rte_eal_init`` and the application is responsible for probing each device,
* ``--auto-probing`` enables the initial bus probing, which is the current default behavior.
+* **Added extensible BPF loading API.**
+
+ Added an extensible BPF loading API comprising the function
+ ``rte_bpf_load_ex`` and struct ``rte_bpf_prm_ex``. This enables new features
+ such as loading classic BPF (cBPF), loading ELF images directly from memory
+ buffers, and executing multi-argument programs, while avoiding future ABI
+ breakages.
+
+* **Added support for executing BPF programs with multiple arguments.**
+
+ Added support for loading and executing BPF programs with up to 5 arguments.
+ This introduces new API functions ``rte_bpf_exec_ex``,
+ ``rte_bpf_exec_burst_ex``, and ``rte_bpf_get_jit_ex``.
+
+* **Added BPF port callback installation API.**
+
+ Added new API functions ``rte_bpf_eth_rx_install`` and
+ ``rte_bpf_eth_tx_install`` for installing already loaded BPF programs as
+ port callbacks (as opposed to loading them directly from ELF files).
+
Removed Items
-------------
--
2.43.0
^ permalink raw reply related
* [PATCH v4 08/11] test/bpf: test loading ELF file from memory
From: Marat Khalili @ 2026-05-20 12:49 UTC (permalink / raw)
To: Konstantin Ananyev; +Cc: dev
In-Reply-To: <20260520124922.42445-1-marat.khalili@huawei.com>
Run each subtest in test_bpf_elf twice: the old way loading ELF images
via temporary file, and using the new rte_bpf_load_ex API to load them
directly from memory.
In tests loading port/queue filters use new rte_bpf_eth_(rx|tx)_install
API to install an already loaded (via one of the ways) BPF program.
Signed-off-by: Marat Khalili <marat.khalili@huawei.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@huawei.com>
---
app/test/test_bpf.c | 194 ++++++++++++++++++++++++++------------------
1 file changed, 114 insertions(+), 80 deletions(-)
diff --git a/app/test/test_bpf.c b/app/test/test_bpf.c
index c43b872a4c83..026ba18b754a 100644
--- a/app/test/test_bpf.c
+++ b/app/test/test_bpf.c
@@ -3977,12 +3977,61 @@ create_temp_bpf_file(const uint8_t *data, size_t size, const char *name)
#include "test_bpf_load.h"
+/* Function loading BPF program from ELF image in memory. */
+typedef struct rte_bpf *
+(*load_elf_image_t)(const void *data, size_t size, const char *section,
+ const struct rte_bpf_xsym *xsym, uint32_t nb_xsym, const struct rte_bpf_arg *prog_arg);
+
+/* Load BPF program by writing ELF image to temporary file and opening this file. */
+static struct rte_bpf *
+load_elf_image_temp_file(const void *data, size_t size, const char *section,
+ const struct rte_bpf_xsym *xsym, uint32_t nb_xsym, const struct rte_bpf_arg *prog_arg)
+{
+ /* Create temp file from embedded BPF object */
+ char *tmpfile = create_temp_bpf_file(data, size, "test");
+ if (tmpfile == NULL) {
+ rte_errno = EIO;
+ return NULL;
+ }
+
+ /* Try to load BPF program from temp file */
+ const struct rte_bpf_prm prm = {
+ .xsym = xsym,
+ .nb_xsym = nb_xsym,
+ .prog_arg = *prog_arg,
+ };
+
+ struct rte_bpf *bpf = rte_bpf_elf_load(&prm, tmpfile, section);
+ unlink(tmpfile);
+ free(tmpfile);
+
+ return bpf;
+}
+
+/* Load BPF program by calling rte_bpf_load_ex and specifying image as the origin. */
+static struct rte_bpf *
+load_elf_image_direct(const void *data, size_t size, const char *section,
+ const struct rte_bpf_xsym *xsym, uint32_t nb_xsym, const struct rte_bpf_arg *prog_arg)
+{
+ return rte_bpf_load_ex(&(struct rte_bpf_prm_ex){
+ .sz = sizeof(struct rte_bpf_prm_ex),
+ .origin = RTE_BPF_ORIGIN_ELF_MEMORY,
+ .elf_memory.data = data,
+ .elf_memory.size = size,
+ .elf_memory.section = section,
+ .xsym = xsym,
+ .nb_xsym = nb_xsym,
+ .prog_arg[0] = *prog_arg,
+ .nb_prog_arg = 1,
+ });
+}
+
/*
* Test loading BPF program from an object file.
* This test uses same arguments as previous test_call1 example.
*/
static int
-test_bpf_elf_load(void)
+test_bpf_elf_load(load_elf_image_t load_elf_image)
{
static const char test_section[] = "call1";
uint8_t tbuf[sizeof(struct dummy_vect8)];
@@ -4010,28 +4059,15 @@ test_bpf_elf_load(void)
},
},
};
- int ret;
-
- /* Create temp file from embedded BPF object */
- char *tmpfile = create_temp_bpf_file(app_test_bpf_load_o,
- app_test_bpf_load_o_len,
- "load");
- if (tmpfile == NULL)
- return -1;
-
- /* Try to load BPF program from temp file */
- const struct rte_bpf_prm prm = {
- .xsym = xsym,
- .nb_xsym = RTE_DIM(xsym),
- .prog_arg = {
- .type = RTE_BPF_ARG_PTR,
- .size = sizeof(tbuf),
- },
+ static const struct rte_bpf_arg prog_arg = {
+ .type = RTE_BPF_ARG_PTR,
+ .size = sizeof(tbuf),
};
+ struct rte_bpf *bpf;
+ int ret;
- struct rte_bpf *bpf = rte_bpf_elf_load(&prm, tmpfile, test_section);
- unlink(tmpfile);
- free(tmpfile);
+ bpf = load_elf_image(app_test_bpf_load_o, app_test_bpf_load_o_len, test_section,
+ xsym, RTE_DIM(xsym), &prog_arg);
/* If libelf support is not available */
if (bpf == NULL && rte_errno == ENOTSUP)
@@ -4174,22 +4210,28 @@ setup_mbufs(struct rte_mbuf *burst[], unsigned int n)
return tcp_count;
}
-static int bpf_tx_test(uint16_t port, const char *tmpfile, struct rte_mempool *pool,
- const char *section, uint32_t flags)
+static int bpf_tx_test(uint16_t port, struct rte_mempool *pool, load_elf_image_t load_elf_image,
+ const char *section, uint32_t flags)
{
- const struct rte_bpf_prm prm = {
- .prog_arg = {
- .type = RTE_BPF_ARG_PTR,
- .size = sizeof(struct dummy_net),
- },
+ static const struct rte_bpf_arg prog_arg = {
+ .type = RTE_BPF_ARG_PTR,
+ .size = sizeof(struct dummy_net),
};
+ struct rte_bpf *bpf;
int ret;
- /* Try to load BPF TX program from temp file */
- ret = rte_bpf_eth_tx_elf_load(port, 0, &prm, tmpfile, section, flags);
+ /* Try to load BPF program from image */
+ bpf = load_elf_image(app_test_bpf_filter_o, app_test_bpf_filter_o_len, section,
+ NULL, 0, &prog_arg);
+ TEST_ASSERT_NOT_NULL(bpf, "failed to load BPF filter from image, error=%d:(%s)\n",
+ rte_errno, rte_strerror(rte_errno));
+
+ /* Try to install loaded BPF program */
+ ret = rte_bpf_eth_tx_install(port, 0, bpf, flags);
if (ret != 0) {
- printf("%s@%d: failed to load BPF filter from file=%s error=%d:(%s)\n",
- __func__, __LINE__, tmpfile, rte_errno, rte_strerror(rte_errno));
+ printf("%s@%d: failed to install BPF filter, error=%d:(%s)\n",
+ __func__, __LINE__, rte_errno, rte_strerror(rte_errno));
+ rte_bpf_destroy(bpf);
return ret;
}
@@ -4217,10 +4259,9 @@ static int bpf_tx_test(uint16_t port, const char *tmpfile, struct rte_mempool *p
/* Test loading a transmit filter which only allows IPv4 packets */
static int
-test_bpf_elf_tx_load(void)
+test_bpf_elf_tx_load(load_elf_image_t load_elf_image)
{
static const char null_dev[] = "net_null_bpf0";
- char *tmpfile = NULL;
struct rte_mempool *mb_pool = NULL;
uint16_t port = UINT16_MAX;
int ret;
@@ -4237,27 +4278,17 @@ test_bpf_elf_tx_load(void)
if (ret != 0)
goto fail;
- /* Create temp file from embedded BPF object */
- tmpfile = create_temp_bpf_file(app_test_bpf_filter_o, app_test_bpf_filter_o_len, "tx");
- if (tmpfile == NULL)
- goto fail;
-
/* Do test with VM */
- ret = bpf_tx_test(port, tmpfile, mb_pool, "filter", 0);
+ ret = bpf_tx_test(port, mb_pool, load_elf_image, "filter", 0);
if (ret != 0)
goto fail;
/* Repeat with JIT */
- ret = bpf_tx_test(port, tmpfile, mb_pool, "filter", RTE_BPF_ETH_F_JIT);
+ ret = bpf_tx_test(port, mb_pool, load_elf_image, "filter", RTE_BPF_ETH_F_JIT);
if (ret == 0)
printf("%s: TX ELF load test passed\n", __func__);
fail:
- if (tmpfile) {
- unlink(tmpfile);
- free(tmpfile);
- }
-
if (port != UINT16_MAX)
rte_vdev_uninit(null_dev);
@@ -4272,23 +4303,29 @@ test_bpf_elf_tx_load(void)
}
/* Test loading a receive filter */
-static int bpf_rx_test(uint16_t port, const char *tmpfile, struct rte_mempool *pool,
- const char *section, uint32_t flags, uint16_t expected)
+static int bpf_rx_test(uint16_t port, struct rte_mempool *pool, load_elf_image_t load_elf_image,
+ const char *section, uint32_t flags, uint16_t expected)
{
- struct rte_mbuf *pkts[BPF_TEST_BURST];
- const struct rte_bpf_prm prm = {
- .prog_arg = {
- .type = RTE_BPF_ARG_PTR,
- .size = sizeof(struct dummy_net),
- },
+ static const struct rte_bpf_arg prog_arg = {
+ .type = RTE_BPF_ARG_PTR,
+ .size = sizeof(struct dummy_net),
};
+ struct rte_mbuf *pkts[BPF_TEST_BURST];
+ struct rte_bpf *bpf;
int ret;
- /* Load BPF program to drop all packets */
- ret = rte_bpf_eth_rx_elf_load(port, 0, &prm, tmpfile, section, flags);
+ /* Try to load BPF program from image */
+ bpf = load_elf_image(app_test_bpf_filter_o, app_test_bpf_filter_o_len, section,
+ NULL, 0, &prog_arg);
+ TEST_ASSERT_NOT_NULL(bpf, "failed to load BPF filter from image, error=%d:(%s)\n",
+ rte_errno, rte_strerror(rte_errno));
+
+ /* Try to install loaded BPF program */
+ ret = rte_bpf_eth_rx_install(port, 0, bpf, flags);
if (ret != 0) {
- printf("%s@%d: failed to load BPF filter from file=%s error=%d:(%s)\n",
- __func__, __LINE__, tmpfile, rte_errno, rte_strerror(rte_errno));
+ printf("%s@%d: failed to install BPF filter, error=%d:(%s)\n",
+ __func__, __LINE__, rte_errno, rte_strerror(rte_errno));
+ rte_bpf_destroy(bpf);
return ret;
}
@@ -4311,11 +4348,10 @@ static int bpf_rx_test(uint16_t port, const char *tmpfile, struct rte_mempool *p
/* Test loading a receive filters, first with drop all and then with allow all packets */
static int
-test_bpf_elf_rx_load(void)
+test_bpf_elf_rx_load(load_elf_image_t load_elf_image)
{
static const char null_dev[] = "net_null_bpf0";
struct rte_mempool *pool = NULL;
- char *tmpfile = NULL;
uint16_t port = UINT16_MAX;
int ret;
@@ -4331,28 +4367,23 @@ test_bpf_elf_rx_load(void)
if (ret != 0)
goto fail;
- /* Create temp file from embedded BPF object */
- tmpfile = create_temp_bpf_file(app_test_bpf_filter_o, app_test_bpf_filter_o_len, "rx");
- if (tmpfile == NULL)
- goto fail;
-
/* Do test with VM */
- ret = bpf_rx_test(port, tmpfile, pool, "drop", 0, 0);
+ ret = bpf_rx_test(port, pool, load_elf_image, "drop", 0, 0);
if (ret != 0)
goto fail;
/* Repeat with JIT */
- ret = bpf_rx_test(port, tmpfile, pool, "drop", RTE_BPF_ETH_F_JIT, 0);
+ ret = bpf_rx_test(port, pool, load_elf_image, "drop", RTE_BPF_ETH_F_JIT, 0);
if (ret != 0)
goto fail;
/* Repeat with allow all */
- ret = bpf_rx_test(port, tmpfile, pool, "allow", 0, BPF_TEST_BURST);
+ ret = bpf_rx_test(port, pool, load_elf_image, "allow", 0, BPF_TEST_BURST);
if (ret != 0)
goto fail;
/* Repeat with JIT */
- ret = bpf_rx_test(port, tmpfile, pool, "allow", RTE_BPF_ETH_F_JIT, BPF_TEST_BURST);
+ ret = bpf_rx_test(port, pool, load_elf_image, "allow", RTE_BPF_ETH_F_JIT, BPF_TEST_BURST);
if (ret != 0)
goto fail;
@@ -4364,11 +4395,6 @@ test_bpf_elf_rx_load(void)
"Mempool available %u != %u leaks?", avail, BPF_TEST_POOLSIZE);
fail:
- if (tmpfile) {
- unlink(tmpfile);
- free(tmpfile);
- }
-
if (port != UINT16_MAX)
rte_vdev_uninit(null_dev);
@@ -4381,13 +4407,21 @@ test_bpf_elf_rx_load(void)
static int
test_bpf_elf(void)
{
- int ret;
+ static const load_elf_image_t elf_image_loaders[] = {
+ load_elf_image_temp_file,
+ load_elf_image_direct,
+ };
- ret = test_bpf_elf_load();
- if (ret == TEST_SUCCESS)
- ret = test_bpf_elf_tx_load();
- if (ret == TEST_SUCCESS)
- ret = test_bpf_elf_rx_load();
+ int ret = TEST_SUCCESS;
+
+ for (int li = 0; li != RTE_DIM(elf_image_loaders); ++li) {
+ if (ret == TEST_SUCCESS)
+ ret = test_bpf_elf_load(elf_image_loaders[li]);
+ if (ret == TEST_SUCCESS)
+ ret = test_bpf_elf_tx_load(elf_image_loaders[li]);
+ if (ret == TEST_SUCCESS)
+ ret = test_bpf_elf_rx_load(elf_image_loaders[li]);
+ }
return ret;
}
--
2.43.0
^ permalink raw reply related
* [PATCH v4 07/11] test/bpf: test loading cBPF directly
From: Marat Khalili @ 2026-05-20 12:49 UTC (permalink / raw)
To: Konstantin Ananyev; +Cc: dev
In-Reply-To: <20260520124922.42445-1-marat.khalili@huawei.com>
Run cBPF tests twice: via rte_bpf_convert, and using
RTE_BPF_FLAG_ORIGIN_CBPF origin of new rte_bpf_load_ex API.
Signed-off-by: Marat Khalili <marat.khalili@huawei.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@huawei.com>
---
app/test/test_bpf.c | 133 +++++++++++++++++++++++++++-----------------
1 file changed, 81 insertions(+), 52 deletions(-)
diff --git a/app/test/test_bpf.c b/app/test/test_bpf.c
index dd247224504e..c43b872a4c83 100644
--- a/app/test/test_bpf.c
+++ b/app/test/test_bpf.c
@@ -4429,13 +4429,59 @@ test_bpf_dump(struct bpf_program *cbf, const struct rte_bpf_prm *prm)
}
}
+/* Function loading BPF program from cBPF instructions array. */
+typedef struct rte_bpf *
+(*load_cbpf_program_t)(struct bpf_program *cbpf_program, const char *str);
+
+/* Load BPF program by converting cBPF array to rte_bpf_prm and then opening it. */
+static struct rte_bpf *
+load_cbpf_program_convert(struct bpf_program *cbpf_program, const char *str)
+{
+ struct rte_bpf_prm *prm = NULL;
+ struct rte_bpf *bpf;
+
+ prm = rte_bpf_convert(cbpf_program);
+ if (prm == NULL) {
+ printf("%s@%d: bpf_convert(\"%s\") failed\n",
+ __func__, __LINE__, str);
+ return NULL;
+ }
+
+ printf("bpf convert(\"%s\") produced:\n", str);
+ rte_bpf_dump(stdout, prm->ins, prm->nb_ins);
+
+ printf("%s \"%s\"\n", __func__, str);
+ test_bpf_dump(cbpf_program, prm);
+
+ bpf = rte_bpf_load(prm);
+ rte_free(prm);
+
+ return bpf;
+}
+
+/* Load BPF program by calling rte_bpf_load_ex and specifying cBPF array as the origin. */
+static struct rte_bpf *
+load_cbpf_program_direct(struct bpf_program *cbpf_program, const char *str __rte_unused)
+{
+ return rte_bpf_load_ex(&(struct rte_bpf_prm_ex){
+ .sz = sizeof(struct rte_bpf_prm_ex),
+ .origin = RTE_BPF_ORIGIN_CBPF,
+ .cbpf.ins = cbpf_program->bf_insns,
+ .cbpf.nb_ins = cbpf_program->bf_len,
+ .prog_arg[0] = {
+ .type = RTE_BPF_ARG_PTR_MBUF,
+ .size = sizeof(struct rte_mbuf),
+ },
+ .nb_prog_arg = 1,
+ });
+}
+
static int
-test_bpf_match(pcap_t *pcap, const char *str,
- struct rte_mbuf *mb)
+test_bpf_match(pcap_t *pcap, const char *str, struct rte_mbuf *mb,
+ load_cbpf_program_t load_cbpf_program)
{
struct bpf_program fcode;
- struct rte_bpf_prm *prm = NULL;
- struct rte_bpf *bpf = NULL;
+ struct rte_bpf *bpf;
int ret = -1;
uint64_t rc;
@@ -4445,17 +4491,10 @@ test_bpf_match(pcap_t *pcap, const char *str,
return -1;
}
- prm = rte_bpf_convert(&fcode);
- if (prm == NULL) {
- printf("%s@%d: bpf_convert('%s') failed,, error=%d(%s);\n",
- __func__, __LINE__, str, rte_errno, strerror(rte_errno));
- goto error;
- }
-
- bpf = rte_bpf_load(prm);
+ bpf = load_cbpf_program(&fcode, str);
if (bpf == NULL) {
- printf("%s@%d: failed to load bpf code, error=%d(%s);\n",
- __func__, __LINE__, rte_errno, strerror(rte_errno));
+ printf("%s@%d: failed to load cbpf program for \"%s\", error=%d(%s);\n",
+ __func__, __LINE__, str, rte_errno, strerror(rte_errno));
goto error;
}
@@ -4465,7 +4504,6 @@ test_bpf_match(pcap_t *pcap, const char *str,
error:
if (bpf)
rte_bpf_destroy(bpf);
- rte_free(prm);
pcap_freecode(&fcode);
return ret;
}
@@ -4474,6 +4512,11 @@ test_bpf_match(pcap_t *pcap, const char *str,
static int
test_bpf_filter_sanity(pcap_t *pcap)
{
+ static const load_cbpf_program_t cbpf_program_loaders[] = {
+ load_cbpf_program_convert,
+ load_cbpf_program_direct,
+ };
+
const uint32_t plen = 100;
struct rte_mbuf mb, *m;
uint8_t tbuf[RTE_MBUF_DEFAULT_BUF_SIZE];
@@ -4500,15 +4543,17 @@ test_bpf_filter_sanity(pcap_t *pcap)
.dst_addr = rte_cpu_to_be_32(RTE_IPV4_BROADCAST),
};
- if (test_bpf_match(pcap, "ip", m) != 0) {
- printf("%s@%d: filter \"ip\" doesn't match test data\n",
- __func__, __LINE__);
- return -1;
- }
- if (test_bpf_match(pcap, "not ip", m) == 0) {
- printf("%s@%d: filter \"not ip\" does match test data\n",
- __func__, __LINE__);
- return -1;
+ for (int li = 0; li != RTE_DIM(cbpf_program_loaders); ++li) {
+ if (test_bpf_match(pcap, "ip", m, cbpf_program_loaders[li]) != 0) {
+ printf("%s@%d: filter \"ip\" doesn't match test data\n",
+ __func__, __LINE__);
+ return -1;
+ }
+ if (test_bpf_match(pcap, "not ip", m, cbpf_program_loaders[li]) == 0) {
+ printf("%s@%d: filter \"not ip\" does match test data\n",
+ __func__, __LINE__);
+ return -1;
+ }
}
return 0;
@@ -4556,44 +4601,26 @@ static const char * const sample_filters[] = {
};
static int
-test_bpf_filter(pcap_t *pcap, const char *s)
+test_bpf_filter(pcap_t *pcap, const char *s, load_cbpf_program_t load_cbpf_program)
{
struct bpf_program fcode;
- struct rte_bpf_prm *prm = NULL;
- struct rte_bpf *bpf = NULL;
+ struct rte_bpf *bpf;
if (pcap_compile(pcap, &fcode, s, 1, PCAP_NETMASK_UNKNOWN)) {
- printf("%s@%d: pcap_compile('%s') failed: %s;\n",
+ printf("%s@%d: pcap_compile(\"%s\") failed: %s;\n",
__func__, __LINE__, s, pcap_geterr(pcap));
return -1;
}
- prm = rte_bpf_convert(&fcode);
- if (prm == NULL) {
- printf("%s@%d: bpf_convert('%s') failed,, error=%d(%s);\n",
- __func__, __LINE__, s, rte_errno, strerror(rte_errno));
- goto error;
- }
-
- printf("bpf convert for \"%s\" produced:\n", s);
- rte_bpf_dump(stdout, prm->ins, prm->nb_ins);
-
- bpf = rte_bpf_load(prm);
+ bpf = load_cbpf_program(&fcode, s);
if (bpf == NULL) {
- printf("%s@%d: failed to load bpf code, error=%d(%s);\n",
- __func__, __LINE__, rte_errno, strerror(rte_errno));
- goto error;
+ printf("%s@%d: failed to load cbpf program for \"%s\" , error=%d(%s);\n",
+ __func__, __LINE__, s, rte_errno, strerror(rte_errno));
+ test_bpf_dump(&fcode, NULL);
}
-error:
- if (bpf)
- rte_bpf_destroy(bpf);
- else {
- printf("%s \"%s\"\n", __func__, s);
- test_bpf_dump(&fcode, prm);
- }
+ rte_bpf_destroy(bpf);
- rte_free(prm);
pcap_freecode(&fcode);
return (bpf == NULL) ? -1 : 0;
}
@@ -4612,8 +4639,10 @@ test_bpf_convert(void)
}
rc = test_bpf_filter_sanity(pcap);
- for (i = 0; i < RTE_DIM(sample_filters); i++)
- rc |= test_bpf_filter(pcap, sample_filters[i]);
+ for (i = 0; i < RTE_DIM(sample_filters); i++) {
+ rc |= test_bpf_filter(pcap, sample_filters[i], load_cbpf_program_convert);
+ rc |= test_bpf_filter(pcap, sample_filters[i], load_cbpf_program_direct);
+ }
pcap_close(pcap);
return rc;
--
2.43.0
^ permalink raw reply related
* [PATCH v4 06/11] bpf: support loading ELF files from memory
From: Marat Khalili @ 2026-05-20 12:49 UTC (permalink / raw)
To: Konstantin Ananyev; +Cc: dev
In-Reply-To: <20260520124922.42445-1-marat.khalili@huawei.com>
Introduce new ELF origin RTE_BPF_ORIGIN_ELF_MEMORY allowing one to
specify data area containing ELF image.
Signed-off-by: Marat Khalili <marat.khalili@huawei.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@huawei.com>
---
lib/bpf/bpf_impl.h | 5 +++++
lib/bpf/bpf_load.c | 4 ++++
lib/bpf/bpf_load_elf.c | 40 +++++++++++++++++++++++++++++++++++++++-
lib/bpf/rte_bpf.h | 6 ++++++
4 files changed, 54 insertions(+), 1 deletion(-)
diff --git a/lib/bpf/bpf_impl.h b/lib/bpf/bpf_impl.h
index 92d03583d977..14ad772d4beb 100644
--- a/lib/bpf/bpf_impl.h
+++ b/lib/bpf/bpf_impl.h
@@ -27,6 +27,7 @@ struct __rte_bpf_load {
/* Loading ELF and applying relocations. */
int elf_fd; /* ELF fd, must be negative (not zero) by default. */
void *elf; /* Using void to avoid dependency on libelf. */
+ const char *elf_section;
/* Value we are going to return, if any. */
struct rte_bpf *bpf;
@@ -53,6 +54,10 @@ __rte_bpf_load_elf_cleanup(struct __rte_bpf_load *load);
int
__rte_bpf_load_elf_file(struct __rte_bpf_load *load);
+/* Open the ELF memory image. */
+int
+__rte_bpf_load_elf_memory(struct __rte_bpf_load *load);
+
/* Get code from ELF and apply relocations to it. */
int
__rte_bpf_load_elf_code(struct __rte_bpf_load *load);
diff --git a/lib/bpf/bpf_load.c b/lib/bpf/bpf_load.c
index e3265e97ff7f..e406211e0e47 100644
--- a/lib/bpf/bpf_load.c
+++ b/lib/bpf/bpf_load.c
@@ -247,6 +247,10 @@ load_try(struct __rte_bpf_load *load, const struct rte_bpf_prm_ex *app_prm)
rc = rc < 0 ? rc : __rte_bpf_load_elf_file(load);
rc = rc < 0 ? rc : __rte_bpf_load_elf_code(load);
break;
+ case RTE_BPF_ORIGIN_ELF_MEMORY:
+ rc = rc < 0 ? rc : __rte_bpf_load_elf_memory(load);
+ rc = rc < 0 ? rc : __rte_bpf_load_elf_code(load);
+ break;
default:
rc = rc < 0 ? rc : -EINVAL;
}
diff --git a/lib/bpf/bpf_load_elf.c b/lib/bpf/bpf_load_elf.c
index 4ae7492351ae..80443cb63a61 100644
--- a/lib/bpf/bpf_load_elf.c
+++ b/lib/bpf/bpf_load_elf.c
@@ -310,6 +310,36 @@ __rte_bpf_load_elf_file(struct __rte_bpf_load *load)
return -EINVAL;
}
+ load->elf_section = prm->elf_file.section;
+
+ return 0;
+}
+
+int
+__rte_bpf_load_elf_memory(struct __rte_bpf_load *load)
+{
+ const struct rte_bpf_prm_ex *const prm = &load->prm;
+
+ RTE_ASSERT(prm->origin == RTE_BPF_ORIGIN_ELF_MEMORY);
+
+ if (prm->elf_memory.data == NULL || prm->elf_memory.section == NULL)
+ return -EINVAL;
+
+ if (elf_version(EV_CURRENT) == EV_NONE)
+ return -ENOTSUP;
+
+ load->elf = elf_memory(
+ /* Cast away const, we are not going to modify the ELF image. */
+ (char *)(uintptr_t)prm->elf_memory.data, prm->elf_memory.size);
+ if (load->elf == NULL) {
+ const int rc = elf_errno();
+ RTE_BPF_LOG_FUNC_LINE(ERR, "error %d opening ELF image: %s",
+ rc, elf_errmsg(rc));
+ return -EINVAL;
+ }
+
+ load->elf_section = prm->elf_memory.section;
+
return 0;
}
@@ -321,7 +351,7 @@ __rte_bpf_load_elf_code(struct __rte_bpf_load *load)
size_t sidx;
int rc;
- rc = find_elf_code(load->elf, prm->elf_file.section, &sd, &sidx);
+ rc = find_elf_code(load->elf, load->elf_section, &sd, &sidx);
if (rc < 0)
return rc;
@@ -353,6 +383,14 @@ __rte_bpf_load_elf_file(struct __rte_bpf_load *load)
return -ENOTSUP;
}
+int
+__rte_bpf_load_elf_memory(struct __rte_bpf_load *load)
+{
+ RTE_SET_USED(load);
+ RTE_BPF_LOG_FUNC_LINE(ERR, "not supported, rebuild with libelf installed");
+ return -ENOTSUP;
+}
+
int
__rte_bpf_load_elf_code(struct __rte_bpf_load *load)
{
diff --git a/lib/bpf/rte_bpf.h b/lib/bpf/rte_bpf.h
index da2bdea7e0a8..413ccf049755 100644
--- a/lib/bpf/rte_bpf.h
+++ b/lib/bpf/rte_bpf.h
@@ -97,6 +97,7 @@ enum rte_bpf_origin {
RTE_BPF_ORIGIN_RAW, /**< code loaded from raw array */
RTE_BPF_ORIGIN_CBPF, /**< code converted from cbpf */
RTE_BPF_ORIGIN_ELF_FILE, /**< code loaded from elf_file */
+ RTE_BPF_ORIGIN_ELF_MEMORY, /**< code loaded from elf_memory */
};
struct bpf_insn;
@@ -127,6 +128,11 @@ struct rte_bpf_prm_ex {
const char *path; /**< path to the ELF file */
const char *section; /**< ELF section with the code */
} elf_file;
+ struct {
+ const void *data; /**< pointer to the ELF image */
+ size_t size; /**< size of the ELF image */
+ const char *section; /**< ELF section with the code */
+ } elf_memory;
};
const struct rte_bpf_xsym *xsym;
--
2.43.0
^ permalink raw reply related
* [PATCH v4 05/11] bpf: support rte_bpf_prm_ex with port callbacks
From: Marat Khalili @ 2026-05-20 12:49 UTC (permalink / raw)
To: Konstantin Ananyev; +Cc: dev
In-Reply-To: <20260520124922.42445-1-marat.khalili@huawei.com>
Introduce new functions to install an already loaded BPF program into RX
or TX port/queue, since previous API was tied to rte_bpf_prm.
Signed-off-by: Marat Khalili <marat.khalili@huawei.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@huawei.com>
---
lib/bpf/bpf_pkt.c | 65 ++++++++++++++++++++++++++++++----------
lib/bpf/rte_bpf_ethdev.h | 54 +++++++++++++++++++++++++++++++++
2 files changed, 104 insertions(+), 15 deletions(-)
diff --git a/lib/bpf/bpf_pkt.c b/lib/bpf/bpf_pkt.c
index 5007f6aef57d..87065e939f31 100644
--- a/lib/bpf/bpf_pkt.c
+++ b/lib/bpf/bpf_pkt.c
@@ -490,13 +490,11 @@ rte_bpf_eth_tx_unload(uint16_t port, uint16_t queue)
}
static int
-bpf_eth_elf_load(struct bpf_eth_cbh *cbh, uint16_t port, uint16_t queue,
- const struct rte_bpf_prm *prm, const char *fname, const char *sname,
- uint32_t flags)
+bpf_eth_elf_install(struct bpf_eth_cbh *cbh, uint16_t port, uint16_t queue,
+ struct rte_bpf *bpf, uint32_t flags)
{
int32_t rc;
struct bpf_eth_cbi *bc;
- struct rte_bpf *bpf;
rte_rx_callback_fn frx;
rte_tx_callback_fn ftx;
struct rte_bpf_jit jit;
@@ -504,14 +502,17 @@ bpf_eth_elf_load(struct bpf_eth_cbh *cbh, uint16_t port, uint16_t queue,
frx = NULL;
ftx = NULL;
- if (prm == NULL || rte_eth_dev_is_valid_port(port) == 0 ||
+ if (bpf == NULL || rte_eth_dev_is_valid_port(port) == 0 ||
queue >= RTE_MAX_QUEUES_PER_PORT)
return -EINVAL;
+ if (bpf->prm.nb_prog_arg != 1)
+ return -EINVAL;
+
if (cbh->type == BPF_ETH_RX)
- frx = select_rx_callback(prm->prog_arg.type, flags);
+ frx = select_rx_callback(bpf->prm.prog_arg[0].type, flags);
else
- ftx = select_tx_callback(prm->prog_arg.type, flags);
+ ftx = select_tx_callback(bpf->prm.prog_arg[0].type, flags);
if (frx == NULL && ftx == NULL) {
RTE_BPF_LOG_LINE(ERR, "%s(%u, %u): no callback selected;",
@@ -519,16 +520,11 @@ bpf_eth_elf_load(struct bpf_eth_cbh *cbh, uint16_t port, uint16_t queue,
return -EINVAL;
}
- bpf = rte_bpf_elf_load(prm, fname, sname);
- if (bpf == NULL)
- return -rte_errno;
-
rte_bpf_get_jit(bpf, &jit);
if ((flags & RTE_BPF_ETH_F_JIT) != 0 && jit.func == NULL) {
RTE_BPF_LOG_LINE(ERR, "%s(%u, %u): no JIT generated;",
__func__, port, queue);
- rte_bpf_destroy(bpf);
return -ENOTSUP;
}
@@ -551,7 +547,6 @@ bpf_eth_elf_load(struct bpf_eth_cbh *cbh, uint16_t port, uint16_t queue,
if (bc->cb == NULL) {
rc = -rte_errno;
- rte_bpf_destroy(bpf);
bpf_eth_cbi_cleanup(bc);
} else
rc = 0;
@@ -564,13 +559,33 @@ int
rte_bpf_eth_rx_elf_load(uint16_t port, uint16_t queue,
const struct rte_bpf_prm *prm, const char *fname, const char *sname,
uint32_t flags)
+{
+ struct rte_bpf *bpf;
+ int32_t rc;
+
+ bpf = rte_bpf_elf_load(prm, fname, sname);
+ if (bpf == NULL)
+ return -rte_errno;
+
+ rc = rte_bpf_eth_rx_install(port, queue, bpf, flags);
+
+ if (rc < 0)
+ rte_bpf_destroy(bpf);
+
+ return rc;
+}
+
+RTE_EXPORT_EXPERIMENTAL_SYMBOL(rte_bpf_eth_rx_install, 26.11)
+int
+rte_bpf_eth_rx_install(uint16_t port, uint16_t queue, struct rte_bpf *bpf,
+ uint32_t flags)
{
int32_t rc;
struct bpf_eth_cbh *cbh;
cbh = &rx_cbh;
rte_spinlock_lock(&cbh->lock);
- rc = bpf_eth_elf_load(cbh, port, queue, prm, fname, sname, flags);
+ rc = bpf_eth_elf_install(cbh, port, queue, bpf, flags);
rte_spinlock_unlock(&cbh->lock);
return rc;
@@ -581,13 +596,33 @@ int
rte_bpf_eth_tx_elf_load(uint16_t port, uint16_t queue,
const struct rte_bpf_prm *prm, const char *fname, const char *sname,
uint32_t flags)
+{
+ struct rte_bpf *bpf;
+ int32_t rc;
+
+ bpf = rte_bpf_elf_load(prm, fname, sname);
+ if (bpf == NULL)
+ return -rte_errno;
+
+ rc = rte_bpf_eth_tx_install(port, queue, bpf, flags);
+
+ if (rc < 0)
+ rte_bpf_destroy(bpf);
+
+ return rc;
+}
+
+RTE_EXPORT_EXPERIMENTAL_SYMBOL(rte_bpf_eth_tx_install, 26.11)
+int
+rte_bpf_eth_tx_install(uint16_t port, uint16_t queue, struct rte_bpf *bpf,
+ uint32_t flags)
{
int32_t rc;
struct bpf_eth_cbh *cbh;
cbh = &tx_cbh;
rte_spinlock_lock(&cbh->lock);
- rc = bpf_eth_elf_load(cbh, port, queue, prm, fname, sname, flags);
+ rc = bpf_eth_elf_install(cbh, port, queue, bpf, flags);
rte_spinlock_unlock(&cbh->lock);
return rc;
diff --git a/lib/bpf/rte_bpf_ethdev.h b/lib/bpf/rte_bpf_ethdev.h
index cab8e9e3887a..5f605ec34d56 100644
--- a/lib/bpf/rte_bpf_ethdev.h
+++ b/lib/bpf/rte_bpf_ethdev.h
@@ -109,6 +109,60 @@ rte_bpf_eth_tx_elf_load(uint16_t port, uint16_t queue,
const struct rte_bpf_prm *prm, const char *fname, const char *sname,
uint32_t flags);
+/**
+ * @warning
+ * @b EXPERIMENTAL: This API may change, or be removed, without prior notice.
+ *
+ * Install callback to execute specified BPF program on given RX port/queue.
+ *
+ * On success the ownership of the program passes to the library,
+ * rte_bpf_eth_unload must be used to unload it, and rte_bpf_destroy must no
+ * longer be called.
+ *
+ * @param port
+ * The identifier of the ethernet port
+ * @param queue
+ * The identifier of the RX queue on the given port
+ * @param bpf
+ * BPF program
+ * @param flags
+ * Flags that define expected behavior of the loaded filter
+ * (i.e. jited/non-jited version to use).
+ * @return
+ * Zero on successful completion or negative error code otherwise.
+ */
+__rte_experimental
+int
+rte_bpf_eth_rx_install(uint16_t port, uint16_t queue, struct rte_bpf *bpf,
+ uint32_t flags);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: This API may change, or be removed, without prior notice.
+ *
+ * Install callback to execute specified BPF program on given TX port/queue.
+ *
+ * On success the ownership of the program passes to the library,
+ * rte_bpf_eth_unload must be used to unload it, and rte_bpf_destroy must no
+ * longer be called.
+ *
+ * @param port
+ * The identifier of the ethernet port
+ * @param queue
+ * The identifier of the TX queue on the given port
+ * @param bpf
+ * BPF program
+ * @param flags
+ * Flags that define expected behavior of the loaded filter
+ * (i.e. jited/non-jited version to use).
+ * @return
+ * Zero on successful completion or negative error code otherwise.
+ */
+__rte_experimental
+int
+rte_bpf_eth_tx_install(uint16_t port, uint16_t queue, struct rte_bpf *bpf,
+ uint32_t flags);
+
#ifdef __cplusplus
}
#endif
--
2.43.0
^ permalink raw reply related
* [PATCH v4 02/11] bpf: introduce extensible load API
From: Marat Khalili @ 2026-05-20 12:49 UTC (permalink / raw)
To: Konstantin Ananyev, Wathsala Vithanage; +Cc: dev
In-Reply-To: <20260520124922.42445-1-marat.khalili@huawei.com>
Introduce new BPF load parameters struct rte_bpf_prm_ex that can be
extended without breaking backward or forward compatibility. Introduce
new function rte_bpf_load_ex consolidating in one code path loading from
both ELF file and raw memory image, with possibility to add more options
in the future.
Some changes in code layout and sequence:
* Both old APIs now only forwarding calls to a new single entry point.
* There is now a centralized cleanup point for all temporary resources
created during the load process.
* External symbols (xsyms) are now checked for validity just after the
load started, not after they were already used for relocation.
* File bpf_load_elf.c now only handles opening ELF file and providing
patched instruction array to the load process. These are left as two
separate functions to support other ELF sources like memory image in
the future.
* Function stubs for the case libelf is not available are moved to
bpf_load_elf.c to make keeping track of them easier (forgetting to
update stubs is a common problem).
Signed-off-by: Marat Khalili <marat.khalili@huawei.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@huawei.com>
---
lib/bpf/bpf_exec.c | 10 +--
lib/bpf/bpf_impl.h | 32 ++++++-
lib/bpf/bpf_jit_arm64.c | 12 +--
lib/bpf/bpf_jit_x86.c | 8 +-
lib/bpf/bpf_load.c | 195 +++++++++++++++++++++++++++++++++++-----
lib/bpf/bpf_load_elf.c | 151 ++++++++++++++++++-------------
lib/bpf/bpf_stub.c | 17 ----
lib/bpf/bpf_validate.c | 32 +++----
lib/bpf/meson.build | 4 +-
lib/bpf/rte_bpf.h | 68 +++++++++++++-
10 files changed, 392 insertions(+), 137 deletions(-)
diff --git a/lib/bpf/bpf_exec.c b/lib/bpf/bpf_exec.c
index 18013753b147..e4668ba10b64 100644
--- a/lib/bpf/bpf_exec.c
+++ b/lib/bpf/bpf_exec.c
@@ -47,7 +47,7 @@
RTE_BPF_LOG_LINE(ERR, \
"%s(%p): division by 0 at pc: %#zx;", \
__func__, bpf, \
- (uintptr_t)(ins) - (uintptr_t)(bpf)->prm.ins); \
+ (uintptr_t)(ins) - (uintptr_t)(bpf)->prm.raw.ins); \
return 0; \
} \
} while (0)
@@ -81,7 +81,7 @@
RTE_BPF_LOG_LINE(ERR, \
"%s(%p): unsupported atomic operation at pc: %#zx;", \
__func__, bpf, \
- (uintptr_t)(ins) - (uintptr_t)(bpf)->prm.ins); \
+ (uintptr_t)(ins) - (uintptr_t)(bpf)->prm.raw.ins); \
return 0; \
} \
} while (0)
@@ -157,7 +157,7 @@ bpf_ld_mbuf(const struct rte_bpf *bpf, uint64_t reg[EBPF_REG_NUM],
RTE_BPF_LOG_LINE(DEBUG, "%s(bpf=%p, mbuf=%p, ofs=%u, len=%u): "
"load beyond packet boundary at pc: %#zx;",
__func__, bpf, mb, off, len,
- (uintptr_t)(ins) - (uintptr_t)(bpf)->prm.ins);
+ (uintptr_t)(ins) - (uintptr_t)(bpf)->prm.raw.ins);
return p;
}
@@ -166,7 +166,7 @@ bpf_exec(const struct rte_bpf *bpf, uint64_t reg[EBPF_REG_NUM])
{
const struct ebpf_insn *ins;
- for (ins = bpf->prm.ins; ; ins++) {
+ for (ins = bpf->prm.raw.ins; ; ins++) {
switch (ins->code) {
/* 32 bit ALU IMM operations */
case (BPF_ALU | BPF_ADD | BPF_K):
@@ -483,7 +483,7 @@ bpf_exec(const struct rte_bpf *bpf, uint64_t reg[EBPF_REG_NUM])
RTE_BPF_LOG_LINE(ERR,
"%s(%p): invalid opcode %#x at pc: %#zx;",
__func__, bpf, ins->code,
- (uintptr_t)ins - (uintptr_t)bpf->prm.ins);
+ (uintptr_t)ins - (uintptr_t)bpf->prm.raw.ins);
return 0;
}
}
diff --git a/lib/bpf/bpf_impl.h b/lib/bpf/bpf_impl.h
index fb5ec3c4d65f..1cee109bc98a 100644
--- a/lib/bpf/bpf_impl.h
+++ b/lib/bpf/bpf_impl.h
@@ -11,17 +11,45 @@
#define MAX_BPF_STACK_SIZE 0x200
struct rte_bpf {
- struct rte_bpf_prm prm;
+ struct rte_bpf_prm_ex prm;
struct rte_bpf_jit jit;
size_t sz;
uint32_t stack_sz;
};
+/* Temporary copies etc. used by the load process. */
+struct __rte_bpf_load {
+ struct rte_bpf_prm_ex prm;
+
+ /* Loading ELF and applying relocations. */
+ int elf_fd; /* ELF fd, must be negative (not zero) by default. */
+ void *elf; /* Using void to avoid dependency on libelf. */
+
+ /* Value we are going to return, if any. */
+ struct rte_bpf *bpf;
+};
+
/*
* Use '__rte' prefix for non-static internal functions
* to avoid potential name conflict with other libraries.
*/
-int __rte_bpf_validate(struct rte_bpf *bpf);
+
+/* Free temporary resources created by opening ELF. */
+void
+__rte_bpf_load_elf_cleanup(struct __rte_bpf_load *load);
+
+/* Open the ELF file. */
+int
+__rte_bpf_load_elf_file(struct __rte_bpf_load *load);
+
+/* Get code from ELF and apply relocations to it. */
+int
+__rte_bpf_load_elf_code(struct __rte_bpf_load *load);
+
+/* Validate final BPF code and calculate stack size. */
+int
+__rte_bpf_validate(const struct rte_bpf_prm_ex *prm, uint32_t *stack_sz);
+
int __rte_bpf_jit(struct rte_bpf *bpf);
int __rte_bpf_jit_x86(struct rte_bpf *bpf);
int __rte_bpf_jit_arm64(struct rte_bpf *bpf);
diff --git a/lib/bpf/bpf_jit_arm64.c b/lib/bpf/bpf_jit_arm64.c
index 4bbb97da1b89..9e5e142c13ba 100644
--- a/lib/bpf/bpf_jit_arm64.c
+++ b/lib/bpf/bpf_jit_arm64.c
@@ -111,12 +111,12 @@ jump_offset_init(struct a64_jit_ctx *ctx, struct rte_bpf *bpf)
{
uint32_t i;
- ctx->map = malloc(bpf->prm.nb_ins * sizeof(ctx->map[0]));
+ ctx->map = malloc(bpf->prm.raw.nb_ins * sizeof(ctx->map[0]));
if (ctx->map == NULL)
return -ENOMEM;
/* Fill with fake offsets */
- for (i = 0; i != bpf->prm.nb_ins; i++) {
+ for (i = 0; i != bpf->prm.raw.nb_ins; i++) {
ctx->map[i].off = INT32_MAX;
ctx->map[i].off_to_b = 0;
}
@@ -1130,8 +1130,8 @@ check_program_has_call(struct a64_jit_ctx *ctx, struct rte_bpf *bpf)
uint8_t op;
uint32_t i;
- for (i = 0; i != bpf->prm.nb_ins; i++) {
- ins = bpf->prm.ins + i;
+ for (i = 0; i != bpf->prm.raw.nb_ins; i++) {
+ ins = bpf->prm.raw.ins + i;
op = ins->code;
switch (op) {
@@ -1168,10 +1168,10 @@ emit(struct a64_jit_ctx *ctx, struct rte_bpf *bpf)
emit_prologue(ctx);
- for (i = 0; i != bpf->prm.nb_ins; i++) {
+ for (i = 0; i != bpf->prm.raw.nb_ins; i++) {
jump_offset_update(ctx, i);
- ins = bpf->prm.ins + i;
+ ins = bpf->prm.raw.ins + i;
op = ins->code;
off = ins->off;
imm = ins->imm;
diff --git a/lib/bpf/bpf_jit_x86.c b/lib/bpf/bpf_jit_x86.c
index 88b1b5aeab1a..6f4235d43499 100644
--- a/lib/bpf/bpf_jit_x86.c
+++ b/lib/bpf/bpf_jit_x86.c
@@ -1324,12 +1324,12 @@ emit(struct bpf_jit_state *st, const struct rte_bpf *bpf)
emit_prolog(st, bpf->stack_sz);
- for (i = 0; i != bpf->prm.nb_ins; i++) {
+ for (i = 0; i != bpf->prm.raw.nb_ins; i++) {
st->idx = i;
st->off[i] = st->sz;
- ins = bpf->prm.ins + i;
+ ins = bpf->prm.raw.ins + i;
dr = ebpf2x86[ins->dst_reg];
sr = ebpf2x86[ins->src_reg];
@@ -1532,13 +1532,13 @@ __rte_bpf_jit_x86(struct rte_bpf *bpf)
/* init state */
memset(&st, 0, sizeof(st));
- st.off = malloc(bpf->prm.nb_ins * sizeof(st.off[0]));
+ st.off = malloc(bpf->prm.raw.nb_ins * sizeof(st.off[0]));
if (st.off == NULL)
return -ENOMEM;
/* fill with fake offsets */
st.exit.off = INT32_MAX;
- for (i = 0; i != bpf->prm.nb_ins; i++)
+ for (i = 0; i != bpf->prm.raw.nb_ins; i++)
st.off[i] = INT32_MAX;
/*
diff --git a/lib/bpf/bpf_load.c b/lib/bpf/bpf_load.c
index b8a0426fe2ed..2d9e503d1f7e 100644
--- a/lib/bpf/bpf_load.c
+++ b/lib/bpf/bpf_load.c
@@ -14,14 +14,14 @@
#include "bpf_impl.h"
static struct rte_bpf *
-bpf_load(const struct rte_bpf_prm *prm)
+bpf_load(const struct rte_bpf_prm_ex *prm)
{
uint8_t *buf;
struct rte_bpf *bpf;
size_t sz, bsz, insz, xsz;
xsz = prm->nb_xsym * sizeof(prm->xsym[0]);
- insz = prm->nb_ins * sizeof(prm->ins[0]);
+ insz = prm->raw.nb_ins * sizeof(prm->raw.ins[0]);
bsz = sizeof(bpf[0]);
sz = insz + xsz + bsz;
@@ -37,10 +37,10 @@ bpf_load(const struct rte_bpf_prm *prm)
if (xsz > 0)
memcpy(buf + bsz, prm->xsym, xsz);
- memcpy(buf + bsz + xsz, prm->ins, insz);
+ memcpy(buf + bsz + xsz, prm->raw.ins, insz);
bpf->prm.xsym = (void *)(buf + bsz);
- bpf->prm.ins = (void *)(buf + bsz + xsz);
+ bpf->prm.raw.ins = (void *)(buf + bsz + xsz);
return bpf;
}
@@ -80,37 +80,44 @@ bpf_check_xsym(const struct rte_bpf_xsym *xsym)
return 0;
}
-RTE_EXPORT_SYMBOL(rte_bpf_load)
-struct rte_bpf *
-rte_bpf_load(const struct rte_bpf_prm *prm)
+static int
+bpf_check_xsyms(const struct rte_bpf_xsym *xsym, uint32_t nb_xsym)
{
- struct rte_bpf *bpf;
int32_t rc;
uint32_t i;
- if (prm == NULL || prm->ins == NULL || prm->nb_ins == 0 ||
- (prm->nb_xsym != 0 && prm->xsym == NULL)) {
- rte_errno = EINVAL;
- return NULL;
- }
+ if (nb_xsym != 0 && xsym == NULL)
+ return -EINVAL;
rc = 0;
- for (i = 0; i != prm->nb_xsym && rc == 0; i++)
- rc = bpf_check_xsym(prm->xsym + i);
+ for (i = 0; i != nb_xsym && rc == 0; i++)
+ rc = bpf_check_xsym(xsym + i);
if (rc != 0) {
- rte_errno = -rc;
RTE_BPF_LOG_FUNC_LINE(ERR, "%d-th xsym is invalid", i);
- return NULL;
+ return rc;
}
+ return 0;
+}
+
+static int
+bpf_load_raw(struct __rte_bpf_load *load)
+{
+ const struct rte_bpf_prm_ex *const prm = &load->prm;
+ struct rte_bpf *bpf;
+ int32_t rc;
+
+ RTE_ASSERT(prm->origin == RTE_BPF_ORIGIN_RAW);
+
+ if (prm->raw.ins == NULL || prm->raw.nb_ins == 0)
+ return -EINVAL;
+
bpf = bpf_load(prm);
- if (bpf == NULL) {
- rte_errno = ENOMEM;
- return NULL;
- }
+ if (bpf == NULL)
+ return -ENOMEM;
- rc = __rte_bpf_validate(bpf);
+ rc = __rte_bpf_validate(&load->prm, &bpf->stack_sz);
if (rc == 0) {
__rte_bpf_jit(bpf);
if (mprotect(bpf, bpf->sz, PROT_READ) != 0)
@@ -119,9 +126,151 @@ rte_bpf_load(const struct rte_bpf_prm *prm)
if (rc != 0) {
rte_bpf_destroy(bpf);
+ return rc;
+ }
+
+ load->bpf = bpf;
+ return 0;
+}
+
+RTE_EXPORT_SYMBOL(rte_bpf_load)
+struct rte_bpf *
+rte_bpf_load(const struct rte_bpf_prm *prm)
+{
+ if (prm == NULL) {
+ rte_errno = EINVAL;
+ return NULL;
+ }
+
+ return rte_bpf_load_ex(&(struct rte_bpf_prm_ex){
+ .sz = sizeof(struct rte_bpf_prm_ex),
+ .origin = RTE_BPF_ORIGIN_RAW,
+ .raw.ins = prm->ins,
+ .raw.nb_ins = prm->nb_ins,
+ .xsym = prm->xsym,
+ .nb_xsym = prm->nb_xsym,
+ .prog_arg = prm->prog_arg,
+ });
+}
+
+RTE_EXPORT_SYMBOL(rte_bpf_elf_load)
+struct rte_bpf *
+rte_bpf_elf_load(const struct rte_bpf_prm *prm, const char *fname,
+ const char *sname)
+{
+ if (prm == NULL) {
+ rte_errno = EINVAL;
+ return NULL;
+ }
+
+ return rte_bpf_load_ex(&(struct rte_bpf_prm_ex){
+ .sz = sizeof(struct rte_bpf_prm_ex),
+ .origin = RTE_BPF_ORIGIN_ELF_FILE,
+ .elf_file.path = fname,
+ .elf_file.section = sname,
+ .xsym = prm->xsym,
+ .nb_xsym = prm->nb_xsym,
+ .prog_arg = prm->prog_arg,
+ });
+}
+
+/*
+ * Check extensible opts for invalid size or non-zero unsupported members.
+ *
+ * This code provides forward compatibility with applications compiled against
+ * newer version of this library. `opts_sz` is the size of struct `opts` in the
+ * version used for compiling the application, read from the member `sz`;
+ * `type_sz` is the size of same struct in the version used for compiling the
+ * library.
+ *
+ * If new fields were added to the struct in the application version, `opts_sz`
+ * will be greater than `type_sz`. In this case we are making sure all bytes we
+ * don't know how to interpret are zeroes, that is any new features that are
+ * there are not being used.
+ *
+ * This function can be used to check any struct following this convention.
+ */
+static bool
+opts_valid(const void *opts, size_t opts_sz, size_t type_sz)
+{
+ if (opts == NULL)
+ return true;
+
+ if (opts_sz < sizeof(opts_sz))
+ /* Size of the struct is too small even for sz member. */
+ return false;
+
+ /* Verify that all extra bytes are zeroed. */
+ for (size_t offset = type_sz; offset < opts_sz; ++offset)
+ if (((const char *)opts)[offset] != 0)
+ return false;
+
+ return true;
+}
+
+static int
+load_try(struct __rte_bpf_load *load, const struct rte_bpf_prm_ex *app_prm)
+{
+ int rc;
+
+ if (app_prm == NULL || !opts_valid(app_prm, app_prm->sz, sizeof(load->prm)))
+ return -EINVAL;
+
+ /*
+ * Convert extensible prm of application size to the size known to us.
+ *
+ * This code provides compatibility with applications compiled against
+ * different version of this library. `app_prm->sz` is the size of
+ * struct `rte_bpf_prm_ex` in the version used for compiling the
+ * application; `sizeof(load->prm)` is the size of the same struct in
+ * the version used for compiling the library.
+ *
+ * We are copying only the fields known to the application and leave
+ * the rest filled with zeroes. Any features that not known to the
+ * application will have backward-compatible default behaviour.
+ */
+ memcpy(&load->prm, app_prm, RTE_MIN(app_prm->sz, sizeof(load->prm)));
+ load->prm.sz = sizeof(load->prm);
+
+ rc = bpf_check_xsyms(load->prm.xsym, load->prm.nb_xsym);
+
+ /* Convert prm origin to raw unless it already is. */
+ switch (load->prm.origin) {
+ case RTE_BPF_ORIGIN_RAW:
+ break;
+ case RTE_BPF_ORIGIN_ELF_FILE:
+ rc = rc < 0 ? rc : __rte_bpf_load_elf_file(load);
+ rc = rc < 0 ? rc : __rte_bpf_load_elf_code(load);
+ break;
+ default:
+ rc = rc < 0 ? rc : -EINVAL;
+ }
+
+ /* Now that it is raw load it as such. */
+ rc = rc < 0 ? rc : bpf_load_raw(load);
+
+ return rc;
+}
+
+RTE_EXPORT_EXPERIMENTAL_SYMBOL(rte_bpf_load_ex, 26.11)
+struct rte_bpf *
+rte_bpf_load_ex(const struct rte_bpf_prm_ex *prm)
+{
+ struct __rte_bpf_load load = { .elf_fd = -1 };
+
+ const int rc = load_try(&load, prm);
+
+ __rte_bpf_load_elf_cleanup(&load);
+
+ RTE_ASSERT((rc < 0) == (load.bpf == NULL));
+
+ if (rc < 0) {
+ RTE_BPF_LOG_FUNC_LINE(ERR, "failed, error code: %d", -rc);
rte_errno = -rc;
return NULL;
}
- return bpf;
+ RTE_BPF_LOG_FUNC_LINE(INFO, "successfully creates %p(jit={.func=%p,.sz=%zu});",
+ load.bpf, load.bpf->jit.raw, load.bpf->jit.sz);
+ return load.bpf;
}
diff --git a/lib/bpf/bpf_load_elf.c b/lib/bpf/bpf_load_elf.c
index 2390823cbf30..4ae7492351ae 100644
--- a/lib/bpf/bpf_load_elf.c
+++ b/lib/bpf/bpf_load_elf.c
@@ -2,6 +2,13 @@
* Copyright(c) 2018 Intel Corporation
*/
+#include "bpf_impl.h"
+
+#include <errno.h>
+
+#ifdef RTE_LIBRTE_BPF_ELF
+
+#include <inttypes.h>
#include <stdarg.h>
#include <stdio.h>
#include <string.h>
@@ -26,8 +33,6 @@
#include <rte_byteorder.h>
#include <rte_errno.h>
-#include "bpf_impl.h"
-
/* To overcome compatibility issue */
#ifndef EM_BPF
#define EM_BPF 247
@@ -56,7 +61,7 @@ bpf_find_xsym(const char *sn, enum rte_bpf_xtype type,
*/
static int
resolve_xsym(const char *sn, size_t ofs, struct ebpf_insn *ins, size_t ins_sz,
- const struct rte_bpf_prm *prm)
+ const struct rte_bpf_prm_ex *prm)
{
uint32_t idx, fidx;
enum rte_bpf_xtype type;
@@ -183,7 +188,7 @@ find_elf_code(Elf *elf, const char *section, Elf_Data **psd, size_t *pidx)
*/
static int
process_reloc(Elf *elf, size_t sym_idx, Elf64_Rel *re, size_t re_sz,
- struct ebpf_insn *ins, size_t ins_sz, const struct rte_bpf_prm *prm)
+ struct ebpf_insn *ins, size_t ins_sz, const struct rte_bpf_prm_ex *prm)
{
int32_t rc;
uint32_t i, n;
@@ -232,8 +237,8 @@ process_reloc(Elf *elf, size_t sym_idx, Elf64_Rel *re, size_t re_sz,
* and update bpf code.
*/
static int
-elf_reloc_code(Elf *elf, Elf_Data *ed, size_t sidx,
- const struct rte_bpf_prm *prm)
+elf_reloc_code(Elf *elf, struct ebpf_insn *ins, size_t ins_sz, size_t sidx,
+ const struct rte_bpf_prm_ex *prm)
{
Elf64_Rel *re;
Elf_Scn *sc;
@@ -256,7 +261,7 @@ elf_reloc_code(Elf *elf, Elf_Data *ed, size_t sidx,
sd->d_size % sizeof(re[0]) != 0)
return -EINVAL;
rc = process_reloc(elf, sh->sh_link,
- sd->d_buf, sd->d_size, ed->d_buf, ed->d_size,
+ sd->d_buf, sd->d_size, ins, ins_sz,
prm);
}
}
@@ -264,72 +269,96 @@ elf_reloc_code(Elf *elf, Elf_Data *ed, size_t sidx,
return rc;
}
-static struct rte_bpf *
-bpf_load_elf(const struct rte_bpf_prm *prm, int32_t fd, const char *section)
+void
+__rte_bpf_load_elf_cleanup(struct __rte_bpf_load *load)
{
- Elf *elf;
- Elf_Data *sd;
- size_t sidx;
- int32_t rc;
- struct rte_bpf *bpf;
- struct rte_bpf_prm np;
+ elf_end(load->elf);
- elf_version(EV_CURRENT);
- elf = elf_begin(fd, ELF_C_READ, NULL);
+ if (load->elf_fd >= 0 && close(load->elf_fd) < 0) {
+ const int close_errno = errno;
+ RTE_BPF_LOG_FUNC_LINE(ERR, "error %d closing: %s",
+ close_errno, strerror(close_errno));
+ }
+}
- rc = find_elf_code(elf, section, &sd, &sidx);
- if (rc == 0)
- rc = elf_reloc_code(elf, sd, sidx, prm);
+int
+__rte_bpf_load_elf_file(struct __rte_bpf_load *load)
+{
+ const struct rte_bpf_prm_ex *const prm = &load->prm;
- if (rc == 0) {
- np = prm[0];
- np.ins = sd->d_buf;
- np.nb_ins = sd->d_size / sizeof(struct ebpf_insn);
- bpf = rte_bpf_load(&np);
- } else {
- bpf = NULL;
- rte_errno = -rc;
+ RTE_ASSERT(prm->origin == RTE_BPF_ORIGIN_ELF_FILE);
+
+ if (prm->elf_file.path == NULL || prm->elf_file.section == NULL)
+ return -EINVAL;
+
+ if (elf_version(EV_CURRENT) == EV_NONE)
+ return -ENOTSUP;
+
+ load->elf_fd = open(prm->elf_file.path, O_RDONLY);
+ if (load->elf_fd < 0) {
+ const int open_errno = errno;
+ RTE_BPF_LOG_FUNC_LINE(ERR, "error %d opening \"%s\": %s",
+ open_errno, prm->elf_file.path, strerror(open_errno));
+ return -open_errno;
+ }
+
+ load->elf = elf_begin(load->elf_fd, ELF_C_READ, NULL);
+ if (load->elf == NULL) {
+ const int rc = elf_errno();
+ RTE_BPF_LOG_FUNC_LINE(ERR, "error %d opening ELF \"%s\": %s",
+ rc, prm->elf_file.path, elf_errmsg(rc));
+ return -EINVAL;
}
- elf_end(elf);
- return bpf;
+ return 0;
}
-RTE_EXPORT_SYMBOL(rte_bpf_elf_load)
-struct rte_bpf *
-rte_bpf_elf_load(const struct rte_bpf_prm *prm, const char *fname,
- const char *sname)
+int
+__rte_bpf_load_elf_code(struct __rte_bpf_load *load)
{
- int32_t fd, rc;
- struct rte_bpf *bpf;
+ struct rte_bpf_prm_ex *const prm = &load->prm;
+ Elf_Data *sd;
+ size_t sidx;
+ int rc;
- if (prm == NULL || fname == NULL || sname == NULL) {
- rte_errno = EINVAL;
- return NULL;
- }
+ rc = find_elf_code(load->elf, prm->elf_file.section, &sd, &sidx);
+ if (rc < 0)
+ return rc;
- fd = open(fname, O_RDONLY);
- if (fd < 0) {
- rc = errno;
- RTE_BPF_LOG_LINE(ERR, "%s(%s) error code: %d(%s)",
- __func__, fname, rc, strerror(rc));
- rte_errno = EINVAL;
- return NULL;
- }
+ prm->origin = RTE_BPF_ORIGIN_RAW;
+ prm->raw.ins = sd->d_buf;
+ prm->raw.nb_ins = sd->d_size / sizeof(struct ebpf_insn);
- bpf = bpf_load_elf(prm, fd, sname);
- close(fd);
+ rc = elf_reloc_code(load->elf, sd->d_buf, sd->d_size, sidx, prm);
+ if (rc < 0)
+ return -EINVAL;
- if (bpf == NULL) {
- RTE_BPF_LOG_LINE(ERR,
- "%s(fname=\"%s\", sname=\"%s\") failed, "
- "error code: %d",
- __func__, fname, sname, rte_errno);
- return NULL;
- }
+ return 0;
+}
+
+#else /* RTE_LIBRTE_BPF_ELF */
+
+void
+__rte_bpf_load_elf_cleanup(struct __rte_bpf_load *load)
+{
+ RTE_ASSERT(load->elf == NULL);
+ RTE_ASSERT(load->elf_fd < 0);
+}
- RTE_BPF_LOG_LINE(INFO, "%s(fname=\"%s\", sname=\"%s\") "
- "successfully creates %p(jit={.func=%p,.sz=%zu});",
- __func__, fname, sname, bpf, bpf->jit.func, bpf->jit.sz);
- return bpf;
+int
+__rte_bpf_load_elf_file(struct __rte_bpf_load *load)
+{
+ RTE_SET_USED(load);
+ RTE_BPF_LOG_FUNC_LINE(ERR, "not supported, rebuild with libelf installed");
+ return -ENOTSUP;
}
+
+int
+__rte_bpf_load_elf_code(struct __rte_bpf_load *load)
+{
+ RTE_SET_USED(load);
+ RTE_BPF_LOG_FUNC_LINE(ERR, "not supported, rebuild with libelf installed");
+ return -ENOTSUP;
+}
+
+#endif /* RTE_LIBRTE_BPF_ELF */
diff --git a/lib/bpf/bpf_stub.c b/lib/bpf/bpf_stub.c
index e06e820d8327..4c329832c264 100644
--- a/lib/bpf/bpf_stub.c
+++ b/lib/bpf/bpf_stub.c
@@ -10,23 +10,6 @@
* Contains stubs for unimplemented public API functions
*/
-#ifndef RTE_LIBRTE_BPF_ELF
-RTE_EXPORT_SYMBOL(rte_bpf_elf_load)
-struct rte_bpf *
-rte_bpf_elf_load(const struct rte_bpf_prm *prm, const char *fname,
- const char *sname)
-{
- if (prm == NULL || fname == NULL || sname == NULL) {
- rte_errno = EINVAL;
- return NULL;
- }
-
- RTE_BPF_LOG_FUNC_LINE(ERR, "not supported, rebuild with libelf installed");
- rte_errno = ENOTSUP;
- return NULL;
-}
-#endif
-
#ifndef RTE_HAS_LIBPCAP
RTE_EXPORT_SYMBOL(rte_bpf_convert)
struct rte_bpf_prm *
diff --git a/lib/bpf/bpf_validate.c b/lib/bpf/bpf_validate.c
index a7f4f576c9d6..5bfc59296d05 100644
--- a/lib/bpf/bpf_validate.c
+++ b/lib/bpf/bpf_validate.c
@@ -80,7 +80,7 @@ struct evst_pool {
};
struct bpf_verifier {
- const struct rte_bpf_prm *prm;
+ const struct rte_bpf_prm_ex *prm;
struct inst_node *in;
uint64_t stack_sz;
uint32_t nb_nodes;
@@ -1837,7 +1837,7 @@ add_edge(struct bpf_verifier *bvf, struct inst_node *node, uint32_t nidx)
{
uint32_t ne;
- if (nidx >= bvf->prm->nb_ins) {
+ if (nidx >= bvf->prm->raw.nb_ins) {
RTE_BPF_LOG_FUNC_LINE(ERR,
"program boundary violation at pc: %u, next pc: %u",
get_node_idx(bvf, node), nidx);
@@ -1946,10 +1946,10 @@ log_unreachable(const struct bpf_verifier *bvf)
struct inst_node *node;
const struct ebpf_insn *ins;
- for (i = 0; i != bvf->prm->nb_ins; i++) {
+ for (i = 0; i != bvf->prm->raw.nb_ins; i++) {
node = bvf->in + i;
- ins = bvf->prm->ins + i;
+ ins = bvf->prm->raw.ins + i;
if (node->colour == WHITE &&
ins->code != (BPF_LD | BPF_IMM | EBPF_DW))
@@ -1966,7 +1966,7 @@ log_loop(const struct bpf_verifier *bvf)
uint32_t i, j;
struct inst_node *node;
- for (i = 0; i != bvf->prm->nb_ins; i++) {
+ for (i = 0; i != bvf->prm->raw.nb_ins; i++) {
node = bvf->in + i;
if (node->colour != BLACK)
@@ -1998,9 +1998,9 @@ validate(struct bpf_verifier *bvf)
const char *err;
rc = 0;
- for (i = 0; i < bvf->prm->nb_ins; i++) {
+ for (i = 0; i < bvf->prm->raw.nb_ins; i++) {
- ins = bvf->prm->ins + i;
+ ins = bvf->prm->raw.ins + i;
node = bvf->in + i;
err = check_syntax(ins);
@@ -2432,7 +2432,7 @@ evaluate(struct bpf_verifier *bvf)
bvf->evst->rv[EBPF_REG_10] = rvfp;
- ins = bvf->prm->ins;
+ ins = bvf->prm->raw.ins;
node = bvf->in;
next = node;
rc = 0;
@@ -2522,23 +2522,23 @@ evaluate(struct bpf_verifier *bvf)
}
int
-__rte_bpf_validate(struct rte_bpf *bpf)
+__rte_bpf_validate(const struct rte_bpf_prm_ex *prm, uint32_t *stack_sz)
{
int32_t rc;
struct bpf_verifier bvf;
/* check input argument type, don't allow mbuf ptr on 32-bit */
- if (bpf->prm.prog_arg.type != RTE_BPF_ARG_RAW &&
- bpf->prm.prog_arg.type != RTE_BPF_ARG_PTR &&
+ if (prm->prog_arg.type != RTE_BPF_ARG_RAW &&
+ prm->prog_arg.type != RTE_BPF_ARG_PTR &&
(sizeof(uint64_t) != sizeof(uintptr_t) ||
- bpf->prm.prog_arg.type != RTE_BPF_ARG_PTR_MBUF)) {
+ prm->prog_arg.type != RTE_BPF_ARG_PTR_MBUF)) {
RTE_BPF_LOG_FUNC_LINE(ERR, "unsupported argument type");
return -ENOTSUP;
}
memset(&bvf, 0, sizeof(bvf));
- bvf.prm = &bpf->prm;
- bvf.in = calloc(bpf->prm.nb_ins, sizeof(bvf.in[0]));
+ bvf.prm = prm;
+ bvf.in = calloc(prm->raw.nb_ins, sizeof(bvf.in[0]));
if (bvf.in == NULL)
return -ENOMEM;
@@ -2555,11 +2555,11 @@ __rte_bpf_validate(struct rte_bpf *bpf)
/* copy collected info */
if (rc == 0) {
- bpf->stack_sz = bvf.stack_sz;
+ *stack_sz = bvf.stack_sz;
/* for LD_ABS/LD_IND, we'll need extra space on the stack */
if (bvf.nb_ldmb_nodes != 0)
- bpf->stack_sz = RTE_ALIGN_CEIL(bpf->stack_sz +
+ *stack_sz = RTE_ALIGN_CEIL(*stack_sz +
sizeof(uint64_t), sizeof(uint64_t));
}
diff --git a/lib/bpf/meson.build b/lib/bpf/meson.build
index 28df7f469a4c..4901b6ee1463 100644
--- a/lib/bpf/meson.build
+++ b/lib/bpf/meson.build
@@ -19,6 +19,7 @@ sources = files('bpf.c',
'bpf_dump.c',
'bpf_exec.c',
'bpf_load.c',
+ 'bpf_load_elf.c',
'bpf_pkt.c',
'bpf_stub.c',
'bpf_validate.c')
@@ -38,10 +39,9 @@ deps += ['mbuf', 'net', 'ethdev']
dep = dependency('libelf', required: false, method: 'pkg-config')
if dep.found()
dpdk_conf.set('RTE_LIBRTE_BPF_ELF', 1)
- sources += files('bpf_load_elf.c')
ext_deps += dep
else
- warning('libelf is missing, rte_bpf_elf_load API will be disabled')
+ warning('libelf is missing, ELF API will be disabled')
endif
if dpdk_conf.has('RTE_HAS_LIBPCAP')
diff --git a/lib/bpf/rte_bpf.h b/lib/bpf/rte_bpf.h
index 309d84bc516a..bf58a418191e 100644
--- a/lib/bpf/rte_bpf.h
+++ b/lib/bpf/rte_bpf.h
@@ -86,7 +86,47 @@ struct rte_bpf_xsym {
};
/**
- * Input parameters for loading eBPF code.
+ * Possible origins of eBPF program code.
+ */
+enum rte_bpf_origin {
+ RTE_BPF_ORIGIN_RAW, /**< code loaded from raw array */
+ RTE_BPF_ORIGIN_RESERVED, /**< reserved for cBPF */
+ RTE_BPF_ORIGIN_ELF_FILE, /**< code loaded from elf_file */
+};
+
+/**
+ * Input parameters for loading eBPF code, extensible version.
+ *
+ * Follows libbpf conventions for extensible structs.
+ */
+struct rte_bpf_prm_ex {
+ size_t sz; /**< size of this struct for backward compatibility */
+
+ uint32_t flags; /**< flags controlling eBPF load and other options */
+
+ enum rte_bpf_origin origin; /**< origin of eBPF program code */
+
+ /** program origin parameters, member in use depends on origin */
+ union {
+ struct {
+ const struct ebpf_insn *ins; /**< eBPF instructions */
+ uint32_t nb_ins; /**< number of instructions in ins */
+ } raw;
+ struct {
+ const char *path; /**< path to the ELF file */
+ const char *section; /**< ELF section with the code */
+ } elf_file;
+ };
+
+ const struct rte_bpf_xsym *xsym;
+ /**< array of external symbols that eBPF code is allowed to reference */
+ uint32_t nb_xsym; /**< number of elements in xsym */
+
+ struct rte_bpf_arg prog_arg; /**< input arg description */
+};
+
+/**
+ * Input parameters for loading eBPF code, legacy version.
*/
struct rte_bpf_prm {
const struct ebpf_insn *ins; /**< array of eBPF instructions */
@@ -116,6 +156,32 @@ struct rte_bpf;
void
rte_bpf_destroy(struct rte_bpf *bpf);
+/**
+ * @warning
+ * @b EXPERIMENTAL: This API may change, or be removed, without prior notice.
+ *
+ * Create a new eBPF execution context, load code from specified origin into it.
+ *
+ * @param prm
+ * Parameters used to create and initialise the BPF execution context.
+ *
+ * Member sz must be set to the struct size as known to the application.
+ * If it exceeds the size known to the library, and the extra part has
+ * non-zero bytes, parameter is rejected. If it's smaller than the size known
+ * to the library, defaults are used for the members that are not present.
+ * @return
+ * BPF handle that is used in future BPF operations,
+ * or NULL on error, with error code set in rte_errno.
+ * Possible rte_errno errors include:
+ * - EINVAL - invalid parameter passed to function
+ * - ENOMEM - can't reserve enough memory
+ * - ENOTSUP - requested feature is not supported (e.g. no libelf to load ELF)
+ */
+__rte_experimental
+struct rte_bpf *
+rte_bpf_load_ex(const struct rte_bpf_prm_ex *prm)
+ __rte_malloc __rte_dealloc(rte_bpf_destroy, 1);
+
/**
* Create a new eBPF execution context and load given BPF code into it.
*
--
2.43.0
^ permalink raw reply related
* [PATCH v4 04/11] bpf: add cBPF origin to rte_bpf_load_ex
From: Marat Khalili @ 2026-05-20 12:49 UTC (permalink / raw)
To: Konstantin Ananyev; +Cc: dev
In-Reply-To: <20260520124922.42445-1-marat.khalili@huawei.com>
Add cBPF origin to rte_bpf_load_ex to allow loading PCAP filters and
other cBPF code through the unified interface.
Note that for the no-libpcap stub of rte_bpf_convert, the behavior when
called with a NULL program has changed from setting rte_errno to EINVAL
to setting it to ENOTSUP. Since both cases return NULL, callers relying
on pointer checking are unaffected.
Signed-off-by: Marat Khalili <marat.khalili@huawei.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@huawei.com>
---
lib/bpf/bpf_convert.c | 81 +++++++++++++++++++++++++++++++++++++++++--
lib/bpf/bpf_impl.h | 11 ++++++
lib/bpf/bpf_load.c | 12 ++++++-
lib/bpf/bpf_stub.c | 27 ---------------
lib/bpf/meson.build | 11 +++---
lib/bpf/rte_bpf.h | 8 ++++-
6 files changed, 113 insertions(+), 37 deletions(-)
delete mode 100644 lib/bpf/bpf_stub.c
diff --git a/lib/bpf/bpf_convert.c b/lib/bpf/bpf_convert.c
index 953ca80670c4..e8074b13d037 100644
--- a/lib/bpf/bpf_convert.c
+++ b/lib/bpf/bpf_convert.c
@@ -9,6 +9,12 @@
* Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com
*/
+#include "bpf_impl.h"
+#include <eal_export.h>
+#include <rte_errno.h>
+
+#ifdef RTE_HAS_LIBPCAP
+
#include <assert.h>
#include <errno.h>
#include <stdbool.h>
@@ -17,17 +23,14 @@
#include <stdlib.h>
#include <string.h>
-#include <eal_export.h>
#include <rte_common.h>
#include <rte_bpf.h>
#include <rte_log.h>
#include <rte_malloc.h>
-#include <rte_errno.h>
#include <pcap/pcap.h>
#include <pcap/bpf.h>
-#include "bpf_impl.h"
#include "bpf_def.h"
#ifndef BPF_MAXINSNS
@@ -572,3 +575,75 @@ rte_bpf_convert(const struct bpf_program *prog)
return prm;
}
+
+void
+__rte_bpf_convert_cleanup(struct __rte_bpf_load *load)
+{
+ free(load->ins);
+}
+
+int
+__rte_bpf_convert(struct __rte_bpf_load *load)
+{
+ struct rte_bpf_prm_ex *const prm = &load->prm;
+ uint32_t nb_ins = 0;
+ int ret;
+
+ RTE_ASSERT(prm->origin == RTE_BPF_ORIGIN_CBPF);
+
+ if (prm->cbpf.ins == NULL || prm->cbpf.nb_ins == 0)
+ return -EINVAL;
+
+ /* 1st pass: calculate the eBPF program length */
+ ret = bpf_convert_filter(prm->cbpf.ins, prm->cbpf.nb_ins, NULL, &nb_ins);
+ if (ret < 0) {
+ RTE_BPF_LOG_FUNC_LINE(ERR, "cannot get eBPF length");
+ return ret;
+ }
+
+ RTE_ASSERT(load->ins == NULL);
+ load->ins = malloc(nb_ins * sizeof(load->ins[0]));
+ if (load->ins == NULL)
+ return -ENOMEM;
+
+ /* 2nd pass: remap cBPF to eBPF instructions */
+ ret = bpf_convert_filter(prm->cbpf.ins, prm->cbpf.nb_ins, load->ins, &nb_ins);
+ if (ret < 0) {
+ RTE_BPF_LOG_FUNC_LINE(ERR, "cannot convert cBPF to eBPF");
+ return ret;
+ }
+
+ prm->origin = RTE_BPF_ORIGIN_RAW;
+ prm->raw.ins = load->ins;
+ prm->raw.nb_ins = nb_ins;
+
+ return 0;
+}
+
+#else /* RTE_HAS_LIBPCAP */
+
+RTE_EXPORT_SYMBOL(rte_bpf_convert)
+struct rte_bpf_prm *
+rte_bpf_convert(const struct bpf_program *prog)
+{
+ RTE_SET_USED(prog);
+ RTE_BPF_LOG_FUNC_LINE(ERR, "not supported, rebuild with libpcap installed");
+ rte_errno = ENOTSUP;
+ return NULL;
+}
+
+void
+__rte_bpf_convert_cleanup(struct __rte_bpf_load *load)
+{
+ RTE_ASSERT(load->ins == NULL);
+}
+
+int
+__rte_bpf_convert(struct __rte_bpf_load *load)
+{
+ RTE_SET_USED(load);
+ RTE_BPF_LOG_FUNC_LINE(ERR, "not supported, rebuild with libpcap installed");
+ return -ENOTSUP;
+}
+
+#endif /* RTE_HAS_LIBPCAP */
diff --git a/lib/bpf/bpf_impl.h b/lib/bpf/bpf_impl.h
index 4a98b3373067..92d03583d977 100644
--- a/lib/bpf/bpf_impl.h
+++ b/lib/bpf/bpf_impl.h
@@ -21,6 +21,9 @@ struct rte_bpf {
struct __rte_bpf_load {
struct rte_bpf_prm_ex prm;
+ /* Conversion from cBPF. */
+ struct ebpf_insn *ins;
+
/* Loading ELF and applying relocations. */
int elf_fd; /* ELF fd, must be negative (not zero) by default. */
void *elf; /* Using void to avoid dependency on libelf. */
@@ -34,6 +37,14 @@ struct __rte_bpf_load {
* to avoid potential name conflict with other libraries.
*/
+/* Free temporary resources created by converting from cBPF to eBPF. */
+void
+__rte_bpf_convert_cleanup(struct __rte_bpf_load *load);
+
+/* Convert program from cBPF to eBPF. */
+int
+__rte_bpf_convert(struct __rte_bpf_load *load);
+
/* Free temporary resources created by opening ELF. */
void
__rte_bpf_load_elf_cleanup(struct __rte_bpf_load *load);
diff --git a/lib/bpf/bpf_load.c b/lib/bpf/bpf_load.c
index f63093b9bc09..e3265e97ff7f 100644
--- a/lib/bpf/bpf_load.c
+++ b/lib/bpf/bpf_load.c
@@ -240,6 +240,9 @@ load_try(struct __rte_bpf_load *load, const struct rte_bpf_prm_ex *app_prm)
switch (load->prm.origin) {
case RTE_BPF_ORIGIN_RAW:
break;
+ case RTE_BPF_ORIGIN_CBPF:
+ rc = rc < 0 ? rc : __rte_bpf_convert(load);
+ break;
case RTE_BPF_ORIGIN_ELF_FILE:
rc = rc < 0 ? rc : __rte_bpf_load_elf_file(load);
rc = rc < 0 ? rc : __rte_bpf_load_elf_code(load);
@@ -254,6 +257,13 @@ load_try(struct __rte_bpf_load *load, const struct rte_bpf_prm_ex *app_prm)
return rc;
}
+static void
+load_cleanup(struct __rte_bpf_load *load)
+{
+ __rte_bpf_convert_cleanup(load);
+ __rte_bpf_load_elf_cleanup(load);
+}
+
RTE_EXPORT_EXPERIMENTAL_SYMBOL(rte_bpf_load_ex, 26.11)
struct rte_bpf *
rte_bpf_load_ex(const struct rte_bpf_prm_ex *prm)
@@ -262,7 +272,7 @@ rte_bpf_load_ex(const struct rte_bpf_prm_ex *prm)
const int rc = load_try(&load, prm);
- __rte_bpf_load_elf_cleanup(&load);
+ load_cleanup(&load);
RTE_ASSERT((rc < 0) == (load.bpf == NULL));
diff --git a/lib/bpf/bpf_stub.c b/lib/bpf/bpf_stub.c
deleted file mode 100644
index 4c329832c264..000000000000
--- a/lib/bpf/bpf_stub.c
+++ /dev/null
@@ -1,27 +0,0 @@
-/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2018-2021 Intel Corporation
- */
-
-#include "bpf_impl.h"
-#include <eal_export.h>
-#include <rte_errno.h>
-
-/**
- * Contains stubs for unimplemented public API functions
- */
-
-#ifndef RTE_HAS_LIBPCAP
-RTE_EXPORT_SYMBOL(rte_bpf_convert)
-struct rte_bpf_prm *
-rte_bpf_convert(const struct bpf_program *prog)
-{
- if (prog == NULL) {
- rte_errno = EINVAL;
- return NULL;
- }
-
- RTE_BPF_LOG_FUNC_LINE(ERR, "not supported, rebuild with libpcap installed");
- rte_errno = ENOTSUP;
- return NULL;
-}
-#endif
diff --git a/lib/bpf/meson.build b/lib/bpf/meson.build
index 4901b6ee1463..7e8a300e3f87 100644
--- a/lib/bpf/meson.build
+++ b/lib/bpf/meson.build
@@ -15,14 +15,16 @@ if arch_subdir == 'x86' and dpdk_conf.get('RTE_ARCH_32')
subdir_done()
endif
-sources = files('bpf.c',
+sources = files(
+ 'bpf.c',
+ 'bpf_convert.c',
'bpf_dump.c',
'bpf_exec.c',
'bpf_load.c',
'bpf_load_elf.c',
'bpf_pkt.c',
- 'bpf_stub.c',
- 'bpf_validate.c')
+ 'bpf_validate.c',
+)
if arch_subdir == 'x86' and dpdk_conf.get('RTE_ARCH_64')
sources += files('bpf_jit_x86.c')
@@ -45,8 +47,7 @@ else
endif
if dpdk_conf.has('RTE_HAS_LIBPCAP')
- sources += files('bpf_convert.c')
ext_deps += pcap_dep
else
- warning('libpcap is missing, rte_bpf_convert API will be disabled')
+ warning('libpcap is missing, cBPF API will be disabled')
endif
diff --git a/lib/bpf/rte_bpf.h b/lib/bpf/rte_bpf.h
index 0e7eaa3c18eb..da2bdea7e0a8 100644
--- a/lib/bpf/rte_bpf.h
+++ b/lib/bpf/rte_bpf.h
@@ -95,10 +95,12 @@ struct rte_bpf_xsym {
*/
enum rte_bpf_origin {
RTE_BPF_ORIGIN_RAW, /**< code loaded from raw array */
- RTE_BPF_ORIGIN_RESERVED, /**< reserved for cBPF */
+ RTE_BPF_ORIGIN_CBPF, /**< code converted from cbpf */
RTE_BPF_ORIGIN_ELF_FILE, /**< code loaded from elf_file */
};
+struct bpf_insn;
+
/**
* Input parameters for loading eBPF code, extensible version.
*
@@ -117,6 +119,10 @@ struct rte_bpf_prm_ex {
const struct ebpf_insn *ins; /**< eBPF instructions */
uint32_t nb_ins; /**< number of instructions in ins */
} raw;
+ struct {
+ const struct bpf_insn *ins; /**< cBPF instructions */
+ uint32_t nb_ins; /**< number of instructions in ins */
+ } cbpf;
struct {
const char *path; /**< path to the ELF file */
const char *section; /**< ELF section with the code */
--
2.43.0
^ permalink raw reply related
* [PATCH v4 03/11] bpf: support up to 5 arguments
From: Marat Khalili @ 2026-05-20 12:49 UTC (permalink / raw)
To: Konstantin Ananyev, Wathsala Vithanage; +Cc: dev
In-Reply-To: <20260520124922.42445-1-marat.khalili@huawei.com>
When using rte_bpf_load_ex allow up to 5 arguments for a BPF program.
Particularly useful for call-backs and other internal functions.
Signed-off-by: Marat Khalili <marat.khalili@huawei.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@huawei.com>
---
lib/bpf/bpf.c | 32 ++++++++++-
lib/bpf/bpf_exec.c | 124 +++++++++++++++++++++++++++++++++++++++-
lib/bpf/bpf_impl.h | 2 +-
lib/bpf/bpf_jit_arm64.c | 2 +-
lib/bpf/bpf_jit_x86.c | 2 +-
lib/bpf/bpf_load.c | 6 +-
lib/bpf/bpf_validate.c | 45 +++++++++++----
lib/bpf/rte_bpf.h | 121 +++++++++++++++++++++++++++++++++++++--
8 files changed, 310 insertions(+), 24 deletions(-)
diff --git a/lib/bpf/bpf.c b/lib/bpf/bpf.c
index 5239b3e11e0e..67dededd9ae8 100644
--- a/lib/bpf/bpf.c
+++ b/lib/bpf/bpf.c
@@ -16,8 +16,8 @@ void
rte_bpf_destroy(struct rte_bpf *bpf)
{
if (bpf != NULL) {
- if (bpf->jit.func != NULL)
- munmap(bpf->jit.func, bpf->jit.sz);
+ if (bpf->jit.raw != NULL)
+ munmap(bpf->jit.raw, bpf->jit.sz);
munmap(bpf, bpf->sz);
}
}
@@ -29,7 +29,33 @@ rte_bpf_get_jit(const struct rte_bpf *bpf, struct rte_bpf_jit *jit)
if (bpf == NULL || jit == NULL)
return -EINVAL;
- jit[0] = bpf->jit;
+ if (bpf->prm.nb_prog_arg != 1) {
+ RTE_BPF_LOG_LINE(ERR,
+ "this program takes %d arguments, use rte_bpf_get_jit_ex",
+ bpf->prm.nb_prog_arg);
+ return -EINVAL;
+ }
+
+ *jit = (struct rte_bpf_jit) {
+ .func = bpf->jit.raw,
+ .sz = bpf->jit.sz,
+ };
+ return 0;
+}
+
+RTE_EXPORT_EXPERIMENTAL_SYMBOL(rte_bpf_get_jit_ex, 26.11)
+int
+rte_bpf_get_jit_ex(const struct rte_bpf *bpf, struct rte_bpf_jit_ex *jit)
+{
+ if (bpf == NULL || jit == NULL)
+ return -EINVAL;
+
+ if (bpf->jit.raw == NULL) {
+ RTE_BPF_LOG_LINE(ERR, "no JIT-compiled version");
+ return -ENOENT;
+ }
+
+ *jit = bpf->jit;
return 0;
}
diff --git a/lib/bpf/bpf_exec.c b/lib/bpf/bpf_exec.c
index e4668ba10b64..20f8d0fa29de 100644
--- a/lib/bpf/bpf_exec.c
+++ b/lib/bpf/bpf_exec.c
@@ -10,6 +10,7 @@
#include <rte_log.h>
#include <rte_debug.h>
#include <rte_byteorder.h>
+#include <rte_errno.h>
#include "bpf_impl.h"
@@ -502,6 +503,12 @@ rte_bpf_exec_burst(const struct rte_bpf *bpf, void *ctx[], uint64_t rc[],
uint64_t reg[EBPF_REG_NUM];
uint64_t stack[MAX_BPF_STACK_SIZE / sizeof(uint64_t)];
+ if (bpf->prm.nb_prog_arg != 1) {
+ /* Use rte_bpf_exec_burst_ex with this program. */
+ rte_errno = EINVAL;
+ return 0;
+ }
+
for (i = 0; i != num; i++) {
reg[EBPF_REG_1] = (uintptr_t)ctx[i];
@@ -513,12 +520,127 @@ rte_bpf_exec_burst(const struct rte_bpf *bpf, void *ctx[], uint64_t rc[],
return i;
}
+static uint32_t
+exec_vm_burst_ex(const struct rte_bpf *bpf, const struct rte_bpf_prog_ctx *ctx,
+ uint64_t rc[], uint32_t num)
+{
+ uint32_t i;
+ uint64_t reg[EBPF_REG_NUM];
+ uint64_t stack[MAX_BPF_STACK_SIZE / sizeof(uint64_t)];
+
+ for (i = 0; i != num; i++) {
+
+ switch (bpf->prm.nb_prog_arg) {
+ case 5:
+ reg[EBPF_REG_5] = ctx[i].arg[4].u64;
+ /* FALLTHROUGH */
+ case 4:
+ reg[EBPF_REG_4] = ctx[i].arg[3].u64;
+ /* FALLTHROUGH */
+ case 3:
+ reg[EBPF_REG_3] = ctx[i].arg[2].u64;
+ /* FALLTHROUGH */
+ case 2:
+ reg[EBPF_REG_2] = ctx[i].arg[1].u64;
+ /* FALLTHROUGH */
+ case 1:
+ reg[EBPF_REG_1] = ctx[i].arg[0].u64;
+ /* FALLTHROUGH */
+ case 0:
+ break;
+ }
+
+ reg[EBPF_REG_10] = (uintptr_t)(stack + RTE_DIM(stack));
+
+ rc[i] = bpf_exec(bpf, reg);
+ }
+
+ return i;
+}
+
+static uint32_t
+exec_jit_burst_ex(const struct rte_bpf *bpf, const struct rte_bpf_prog_ctx *ctx,
+ uint64_t rc[], uint32_t num)
+{
+ uint32_t i = 0;
+ const struct rte_bpf_jit_ex jit = bpf->jit;
+
+ /*
+ * Fast path: assumes application pre-validated RTE_BPF_EXEC_FLAG_JIT
+ * and successful JIT generation. No explicit NULL checks here.
+ */
+ switch (bpf->prm.nb_prog_arg) {
+ case 0:
+ for (i = 0; i != num; i++)
+ rc[i] = jit.func0();
+ break;
+ case 1:
+ for (i = 0; i != num; i++) {
+ const union rte_bpf_func_arg *const arg = ctx[i].arg;
+ rc[i] = jit.func1(arg[0]);
+ }
+ break;
+ case 2:
+ for (i = 0; i != num; i++) {
+ const union rte_bpf_func_arg *const arg = ctx[i].arg;
+ rc[i] = jit.func2(arg[0], arg[1]);
+ }
+ break;
+ case 3:
+ for (i = 0; i != num; i++) {
+ const union rte_bpf_func_arg *const arg = ctx[i].arg;
+ rc[i] = jit.func3(arg[0], arg[1], arg[2]);
+ }
+ break;
+ case 4:
+ for (i = 0; i != num; i++) {
+ const union rte_bpf_func_arg *const arg = ctx[i].arg;
+ rc[i] = jit.func4(arg[0], arg[1], arg[2], arg[3]);
+ }
+ break;
+ case 5:
+ for (i = 0; i != num; i++) {
+ const union rte_bpf_func_arg *const arg = ctx[i].arg;
+ rc[i] = jit.func5(arg[0], arg[1], arg[2], arg[3], arg[4]);
+ }
+ break;
+ }
+
+ return i;
+}
+
+RTE_EXPORT_EXPERIMENTAL_SYMBOL(rte_bpf_exec_burst_ex, 26.11)
+uint32_t
+rte_bpf_exec_burst_ex(const struct rte_bpf *bpf, const struct rte_bpf_prog_ctx *ctx,
+ uint64_t rc[], uint32_t num, uint64_t flags)
+{
+ if ((flags & ~RTE_BPF_EXEC_FLAG_MASK) != 0) {
+ rte_errno = EINVAL;
+ return 0;
+ }
+
+ return (flags & RTE_BPF_EXEC_FLAG_JIT) != 0 ?
+ exec_jit_burst_ex(bpf, ctx, rc, num) :
+ exec_vm_burst_ex(bpf, ctx, rc, num);
+}
+
RTE_EXPORT_SYMBOL(rte_bpf_exec)
uint64_t
rte_bpf_exec(const struct rte_bpf *bpf, void *ctx)
{
- uint64_t rc;
+ uint64_t rc = UINT64_MAX;
rte_bpf_exec_burst(bpf, &ctx, &rc, 1);
return rc;
}
+
+RTE_EXPORT_EXPERIMENTAL_SYMBOL(rte_bpf_exec_ex, 26.11)
+uint64_t
+rte_bpf_exec_ex(const struct rte_bpf *bpf, const struct rte_bpf_prog_ctx *ctx,
+ uint64_t flags)
+{
+ uint64_t rc = UINT64_MAX;
+
+ rte_bpf_exec_burst_ex(bpf, ctx, &rc, 1, flags);
+ return rc;
+}
diff --git a/lib/bpf/bpf_impl.h b/lib/bpf/bpf_impl.h
index 1cee109bc98a..4a98b3373067 100644
--- a/lib/bpf/bpf_impl.h
+++ b/lib/bpf/bpf_impl.h
@@ -12,7 +12,7 @@
struct rte_bpf {
struct rte_bpf_prm_ex prm;
- struct rte_bpf_jit jit;
+ struct rte_bpf_jit_ex jit;
size_t sz;
uint32_t stack_sz;
};
diff --git a/lib/bpf/bpf_jit_arm64.c b/lib/bpf/bpf_jit_arm64.c
index 9e5e142c13ba..ba7ae4d680c5 100644
--- a/lib/bpf/bpf_jit_arm64.c
+++ b/lib/bpf/bpf_jit_arm64.c
@@ -1471,7 +1471,7 @@ __rte_bpf_jit_arm64(struct rte_bpf *bpf)
/* Flush the icache */
__builtin___clear_cache((char *)ctx.ins, (char *)(ctx.ins + ctx.idx));
- bpf->jit.func = (void *)ctx.ins;
+ bpf->jit.raw = ctx.ins;
bpf->jit.sz = size;
goto finish;
diff --git a/lib/bpf/bpf_jit_x86.c b/lib/bpf/bpf_jit_x86.c
index 6f4235d43499..54eb279643b9 100644
--- a/lib/bpf/bpf_jit_x86.c
+++ b/lib/bpf/bpf_jit_x86.c
@@ -1568,7 +1568,7 @@ __rte_bpf_jit_x86(struct rte_bpf *bpf)
if (rc != 0)
munmap(st.ins, st.sz);
else {
- bpf->jit.func = (void *)st.ins;
+ bpf->jit.raw = st.ins;
bpf->jit.sz = st.sz;
}
diff --git a/lib/bpf/bpf_load.c b/lib/bpf/bpf_load.c
index 2d9e503d1f7e..f63093b9bc09 100644
--- a/lib/bpf/bpf_load.c
+++ b/lib/bpf/bpf_load.c
@@ -149,7 +149,8 @@ rte_bpf_load(const struct rte_bpf_prm *prm)
.raw.nb_ins = prm->nb_ins,
.xsym = prm->xsym,
.nb_xsym = prm->nb_xsym,
- .prog_arg = prm->prog_arg,
+ .prog_arg[0] = prm->prog_arg,
+ .nb_prog_arg = 1,
});
}
@@ -170,7 +171,8 @@ rte_bpf_elf_load(const struct rte_bpf_prm *prm, const char *fname,
.elf_file.section = sname,
.xsym = prm->xsym,
.nb_xsym = prm->nb_xsym,
- .prog_arg = prm->prog_arg,
+ .prog_arg[0] = prm->prog_arg,
+ .nb_prog_arg = 1,
});
}
diff --git a/lib/bpf/bpf_validate.c b/lib/bpf/bpf_validate.c
index 5bfc59296d05..bf8a4abb5a5a 100644
--- a/lib/bpf/bpf_validate.c
+++ b/lib/bpf/bpf_validate.c
@@ -2425,10 +2425,14 @@ evaluate(struct bpf_verifier *bvf)
.s = {.min = MAX_BPF_STACK_SIZE, .max = MAX_BPF_STACK_SIZE},
};
- bvf->evst->rv[EBPF_REG_1].v = bvf->prm->prog_arg;
- bvf->evst->rv[EBPF_REG_1].mask = UINT64_MAX;
- if (bvf->prm->prog_arg.type == RTE_BPF_ARG_RAW)
- eval_max_bound(bvf->evst->rv + EBPF_REG_1, UINT64_MAX);
+ for (uint32_t pai = 0; pai != bvf->prm->nb_prog_arg; ++pai) {
+ struct bpf_reg_val *reg = &bvf->evst->rv[EBPF_REG_1 + pai];
+
+ reg->v = bvf->prm->prog_arg[pai];
+ reg->mask = UINT64_MAX;
+ if (reg->v.type == RTE_BPF_ARG_RAW)
+ eval_max_bound(reg, UINT64_MAX);
+ }
bvf->evst->rv[EBPF_REG_10] = rvfp;
@@ -2521,21 +2525,42 @@ evaluate(struct bpf_verifier *bvf)
return rc;
}
+static bool
+prog_arg_is_valid(const struct rte_bpf_arg *prog_arg)
+{
+ /* check input argument type, don't allow mbuf ptr on 32-bit */
+ if (prog_arg->type != RTE_BPF_ARG_RAW &&
+ prog_arg->type != RTE_BPF_ARG_PTR &&
+ (sizeof(uint64_t) != sizeof(uintptr_t) ||
+ prog_arg->type != RTE_BPF_ARG_PTR_MBUF)) {
+ RTE_BPF_LOG_FUNC_LINE(ERR, "unsupported argument type");
+ return false;
+ }
+
+ return true;
+}
+
int
__rte_bpf_validate(const struct rte_bpf_prm_ex *prm, uint32_t *stack_sz)
{
int32_t rc;
struct bpf_verifier bvf;
- /* check input argument type, don't allow mbuf ptr on 32-bit */
- if (prm->prog_arg.type != RTE_BPF_ARG_RAW &&
- prm->prog_arg.type != RTE_BPF_ARG_PTR &&
- (sizeof(uint64_t) != sizeof(uintptr_t) ||
- prm->prog_arg.type != RTE_BPF_ARG_PTR_MBUF)) {
- RTE_BPF_LOG_FUNC_LINE(ERR, "unsupported argument type");
+ if (prm->nb_prog_arg > EBPF_FUNC_MAX_ARGS) {
+ RTE_BPF_LOG_FUNC_LINE(ERR,
+ "support up to %u arguments, found %u",
+ EBPF_FUNC_MAX_ARGS, prm->nb_prog_arg);
return -ENOTSUP;
}
+ for (uint32_t pai = 0; pai != prm->nb_prog_arg; ++pai)
+ if (!prog_arg_is_valid(&prm->prog_arg[pai])) {
+ RTE_BPF_LOG_FUNC_LINE(ERR,
+ "unsupported argument %d (r%d) type",
+ pai, EBPF_REG_1 + pai);
+ return -ENOTSUP;
+ }
+
memset(&bvf, 0, sizeof(bvf));
bvf.prm = prm;
bvf.in = calloc(prm->raw.nb_ins, sizeof(bvf.in[0]));
diff --git a/lib/bpf/rte_bpf.h b/lib/bpf/rte_bpf.h
index bf58a418191e..0e7eaa3c18eb 100644
--- a/lib/bpf/rte_bpf.h
+++ b/lib/bpf/rte_bpf.h
@@ -25,6 +25,11 @@
extern "C" {
#endif
+#define RTE_BPF_EXEC_FLAG_JIT RTE_BIT64(0) /**< use JIT-compiled version */
+
+/** Mask with all supported `RTE_BPF_EXEC_FLAG_*` flags set. */
+#define RTE_BPF_EXEC_FLAG_MASK RTE_BPF_EXEC_FLAG_JIT
+
/**
* Possible types for function/BPF program arguments.
*/
@@ -122,7 +127,8 @@ struct rte_bpf_prm_ex {
/**< array of external symbols that eBPF code is allowed to reference */
uint32_t nb_xsym; /**< number of elements in xsym */
- struct rte_bpf_arg prog_arg; /**< input arg description */
+ struct rte_bpf_arg prog_arg[EBPF_FUNC_MAX_ARGS]; /**< program arguments */
+ uint32_t nb_prog_arg; /**< program argument count */
};
/**
@@ -138,13 +144,49 @@ struct rte_bpf_prm {
};
/**
- * Information about compiled into native ISA eBPF code.
+ * Information about compiled into native ISA eBPF code accepting 1 argument.
*/
struct rte_bpf_jit {
uint64_t (*func)(void *); /**< JIT-ed native code */
size_t sz; /**< size of JIT-ed code */
};
+union rte_bpf_func_arg {
+ uint64_t u64;
+ void *ptr;
+};
+
+typedef uint64_t (*rte_bpf_jit_func0_t)(void);
+typedef uint64_t (*rte_bpf_jit_func1_t)(union rte_bpf_func_arg);
+typedef uint64_t (*rte_bpf_jit_func2_t)(union rte_bpf_func_arg, union rte_bpf_func_arg);
+typedef uint64_t (*rte_bpf_jit_func3_t)(union rte_bpf_func_arg, union rte_bpf_func_arg,
+ union rte_bpf_func_arg);
+typedef uint64_t (*rte_bpf_jit_func4_t)(union rte_bpf_func_arg, union rte_bpf_func_arg,
+ union rte_bpf_func_arg, union rte_bpf_func_arg);
+typedef uint64_t (*rte_bpf_jit_func5_t)(union rte_bpf_func_arg, union rte_bpf_func_arg,
+ union rte_bpf_func_arg, union rte_bpf_func_arg, union rte_bpf_func_arg);
+
+/**
+ * JIT-ed native code, member depends on number of program arguments.
+ */
+struct rte_bpf_jit_ex {
+ union {
+ void *raw;
+ rte_bpf_jit_func0_t func0; /* nullary function */
+ rte_bpf_jit_func1_t func1; /* unary function */
+ rte_bpf_jit_func2_t func2; /* binary function */
+ rte_bpf_jit_func3_t func3; /* ternary function */
+ rte_bpf_jit_func4_t func4; /* quaternary function */
+ rte_bpf_jit_func5_t func5; /* quinary function */
+ };
+ size_t sz;
+};
+
+/* Tuple of eBPF program arguments. */
+struct rte_bpf_prog_ctx {
+ union rte_bpf_func_arg arg[EBPF_FUNC_MAX_ARGS];
+};
+
struct rte_bpf;
/**
@@ -224,7 +266,7 @@ rte_bpf_elf_load(const struct rte_bpf_prm *prm, const char *fname,
__rte_malloc __rte_dealloc(rte_bpf_destroy, 1);
/**
- * Execute given BPF bytecode.
+ * Execute given BPF bytecode accepting 1 argument.
*
* @param bpf
* handle for the BPF code to execute.
@@ -237,7 +279,29 @@ uint64_t
rte_bpf_exec(const struct rte_bpf *bpf, void *ctx);
/**
- * Execute given BPF bytecode over a set of input contexts.
+ * @warning
+ * @b EXPERIMENTAL: This API may change, or be removed, without prior notice.
+ *
+ * Execute given BPF bytecode accepting any number of arguments.
+ *
+ * @param bpf
+ * handle for the BPF code to execute.
+ * @param ctx
+ * program arguments tuple.
+ * @param flags
+ * bitwise OR of `RTE_BPF_EXEC_FLAG_*` values controlling execution.
+ * Flag RTE_BPF_EXEC_FLAG_JIT requires presence of JIT version (can be checked
+ * with rte_bpf_get_jit_ex).
+ * @return
+ * BPF execution return value.
+ */
+__rte_experimental
+uint64_t
+rte_bpf_exec_ex(const struct rte_bpf *bpf, const struct rte_bpf_prog_ctx *ctx,
+ uint64_t flags);
+
+/**
+ * Execute given BPF bytecode accepting 1 argument over a set of input contexts.
*
* @param bpf
* handle for the BPF code to execute.
@@ -255,7 +319,35 @@ rte_bpf_exec_burst(const struct rte_bpf *bpf, void *ctx[], uint64_t rc[],
uint32_t num);
/**
- * Provide information about natively compiled code for given BPF handle.
+ * @warning
+ * @b EXPERIMENTAL: This API may change, or be removed, without prior notice.
+ *
+ * Execute given BPF program accepting any number of arguments over a set of
+ * input contexts.
+ *
+ * @param bpf
+ * handle for the BPF code to execute.
+ * @param ctx
+ * pointer to array of program argument tuples, can be NULL for nullary programs.
+ * @param rc
+ * array of return values (one per input).
+ * @param num
+ * number executions, number of elements in arrays ctx and rc[].
+ * @param flags
+ * bitwise OR of `RTE_BPF_EXEC_FLAG_*` values controlling execution.
+ * Flag RTE_BPF_EXEC_FLAG_JIT requires presence of JIT version (can be checked
+ * with rte_bpf_get_jit_ex).
+ * @return
+ * number of successfully processed inputs.
+ */
+__rte_experimental
+uint32_t
+rte_bpf_exec_burst_ex(const struct rte_bpf *bpf, const struct rte_bpf_prog_ctx *ctx,
+ uint64_t rc[], uint32_t num, uint64_t flags);
+
+/**
+ * Provide information about natively compiled code for given BPF program
+ * accepting 1 argument.
*
* @param bpf
* handle for the BPF code.
@@ -268,6 +360,25 @@ rte_bpf_exec_burst(const struct rte_bpf *bpf, void *ctx[], uint64_t rc[],
int
rte_bpf_get_jit(const struct rte_bpf *bpf, struct rte_bpf_jit *jit);
+/**
+ * @warning
+ * @b EXPERIMENTAL: This API may change, or be removed, without prior notice.
+ *
+ * Get function JIT-compiled from the BPF program.
+ *
+ * @param bpf
+ * handle for the BPF code.
+ * @param jit
+ * pointer to the struct rte_bpf_jit_ex.
+ * @return
+ * - -EINVAL if the parameters are invalid.
+ * - -ENOENT if there is no JIT-compiled version.
+ * - Zero if operation completed successfully.
+ */
+__rte_experimental
+int
+rte_bpf_get_jit_ex(const struct rte_bpf *bpf, struct rte_bpf_jit_ex *jit);
+
/**
* Dump epf instructions to a file.
*
--
2.43.0
^ permalink raw reply related
* [PATCH v4 01/11] bpf: make logging prefixes more consistent
From: Marat Khalili @ 2026-05-20 12:49 UTC (permalink / raw)
To: Konstantin Ananyev, Wathsala Vithanage; +Cc: dev
In-Reply-To: <20260520124922.42445-1-marat.khalili@huawei.com>
Logging in lib/bpf is inconsistent: some places use `%s()`, other just
`%s` for `__func__`.
Introduce new macro for logging prefixed with function name and use it
everywhere function name without arguments is prefixed to the log line.
Signed-off-by: Marat Khalili <marat.khalili@huawei.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@huawei.com>
---
lib/bpf/bpf_convert.c | 18 +++++++++---------
lib/bpf/bpf_impl.h | 3 +++
lib/bpf/bpf_jit_arm64.c | 4 ++--
lib/bpf/bpf_load.c | 2 +-
lib/bpf/bpf_load_elf.c | 2 +-
lib/bpf/bpf_stub.c | 6 ++----
lib/bpf/bpf_validate.c | 25 ++++++++++++-------------
7 files changed, 30 insertions(+), 30 deletions(-)
diff --git a/lib/bpf/bpf_convert.c b/lib/bpf/bpf_convert.c
index 86e703299d05..953ca80670c4 100644
--- a/lib/bpf/bpf_convert.c
+++ b/lib/bpf/bpf_convert.c
@@ -247,8 +247,8 @@ static int bpf_convert_filter(const struct bpf_insn *prog, size_t len,
uint8_t bpf_src;
if (len > BPF_MAXINSNS) {
- RTE_BPF_LOG_LINE(ERR, "%s: cBPF program too long (%zu insns)",
- __func__, len);
+ RTE_BPF_LOG_FUNC_LINE(ERR, "cBPF program too long (%zu insns)",
+ len);
return -EINVAL;
}
@@ -483,8 +483,8 @@ static int bpf_convert_filter(const struct bpf_insn *prog, size_t len,
/* Unknown instruction. */
default:
- RTE_BPF_LOG_LINE(ERR, "%s: Unknown instruction!: %#x",
- __func__, fp->code);
+ RTE_BPF_LOG_FUNC_LINE(ERR, "Unknown instruction!: %#x",
+ fp->code);
goto err;
}
@@ -528,7 +528,7 @@ rte_bpf_convert(const struct bpf_program *prog)
int ret;
if (prog == NULL) {
- RTE_BPF_LOG_LINE(ERR, "%s: NULL program", __func__);
+ RTE_BPF_LOG_FUNC_LINE(ERR, "NULL program");
rte_errno = EINVAL;
return NULL;
}
@@ -536,13 +536,13 @@ rte_bpf_convert(const struct bpf_program *prog)
/* 1st pass: calculate the eBPF program length */
ret = bpf_convert_filter(prog->bf_insns, prog->bf_len, NULL, &ebpf_len);
if (ret < 0) {
- RTE_BPF_LOG_LINE(ERR, "%s: cannot get eBPF length", __func__);
+ RTE_BPF_LOG_FUNC_LINE(ERR, "cannot get eBPF length");
rte_errno = -ret;
return NULL;
}
- RTE_BPF_LOG_LINE(DEBUG, "%s: prog len cBPF=%u -> eBPF=%u",
- __func__, prog->bf_len, ebpf_len);
+ RTE_BPF_LOG_FUNC_LINE(DEBUG, "prog len cBPF=%u -> eBPF=%u",
+ prog->bf_len, ebpf_len);
prm = rte_zmalloc("bpf_filter",
sizeof(*prm) + ebpf_len * sizeof(*ebpf), 0);
@@ -557,7 +557,7 @@ rte_bpf_convert(const struct bpf_program *prog)
/* 2nd pass: remap cBPF to eBPF instructions */
ret = bpf_convert_filter(prog->bf_insns, prog->bf_len, ebpf, &ebpf_len);
if (ret < 0) {
- RTE_BPF_LOG_LINE(ERR, "%s: cannot convert cBPF to eBPF", __func__);
+ RTE_BPF_LOG_FUNC_LINE(ERR, "cannot convert cBPF to eBPF");
rte_free(prm);
rte_errno = -ret;
return NULL;
diff --git a/lib/bpf/bpf_impl.h b/lib/bpf/bpf_impl.h
index f5fa22098489..fb5ec3c4d65f 100644
--- a/lib/bpf/bpf_impl.h
+++ b/lib/bpf/bpf_impl.h
@@ -32,6 +32,9 @@ extern int rte_bpf_logtype;
#define RTE_BPF_LOG_LINE(lvl, ...) \
RTE_LOG_LINE(lvl, BPF, __VA_ARGS__)
+#define RTE_BPF_LOG_FUNC_LINE(lvl, fmt, ...) \
+ RTE_LOG_LINE(lvl, BPF, "%s(): " fmt, __func__, ##__VA_ARGS__)
+
static inline size_t
bpf_size(uint32_t bpf_op_sz)
{
diff --git a/lib/bpf/bpf_jit_arm64.c b/lib/bpf/bpf_jit_arm64.c
index a04ef33a9c88..4bbb97da1b89 100644
--- a/lib/bpf/bpf_jit_arm64.c
+++ b/lib/bpf/bpf_jit_arm64.c
@@ -98,8 +98,8 @@ check_invalid_args(struct a64_jit_ctx *ctx, uint32_t limit)
for (idx = 0; idx < limit; idx++) {
if (rte_le_to_cpu_32(ctx->ins[idx]) == A64_INVALID_OP_CODE) {
- RTE_BPF_LOG_LINE(ERR,
- "%s: invalid opcode at %u;", __func__, idx);
+ RTE_BPF_LOG_FUNC_LINE(ERR,
+ "invalid opcode at %u;", idx);
return -EINVAL;
}
}
diff --git a/lib/bpf/bpf_load.c b/lib/bpf/bpf_load.c
index 6983c026af0e..b8a0426fe2ed 100644
--- a/lib/bpf/bpf_load.c
+++ b/lib/bpf/bpf_load.c
@@ -100,7 +100,7 @@ rte_bpf_load(const struct rte_bpf_prm *prm)
if (rc != 0) {
rte_errno = -rc;
- RTE_BPF_LOG_LINE(ERR, "%s: %d-th xsym is invalid", __func__, i);
+ RTE_BPF_LOG_FUNC_LINE(ERR, "%d-th xsym is invalid", i);
return NULL;
}
diff --git a/lib/bpf/bpf_load_elf.c b/lib/bpf/bpf_load_elf.c
index 1d30ba17e25d..2390823cbf30 100644
--- a/lib/bpf/bpf_load_elf.c
+++ b/lib/bpf/bpf_load_elf.c
@@ -122,7 +122,7 @@ check_elf_header(const Elf64_Ehdr *eh)
err = "unexpected machine type";
if (err != NULL) {
- RTE_BPF_LOG_LINE(ERR, "%s(): %s", __func__, err);
+ RTE_BPF_LOG_FUNC_LINE(ERR, "%s", err);
return -EINVAL;
}
diff --git a/lib/bpf/bpf_stub.c b/lib/bpf/bpf_stub.c
index dea0d703ca27..e06e820d8327 100644
--- a/lib/bpf/bpf_stub.c
+++ b/lib/bpf/bpf_stub.c
@@ -21,8 +21,7 @@ rte_bpf_elf_load(const struct rte_bpf_prm *prm, const char *fname,
return NULL;
}
- RTE_BPF_LOG_LINE(ERR, "%s() is not supported, rebuild with libelf installed",
- __func__);
+ RTE_BPF_LOG_FUNC_LINE(ERR, "not supported, rebuild with libelf installed");
rte_errno = ENOTSUP;
return NULL;
}
@@ -38,8 +37,7 @@ rte_bpf_convert(const struct bpf_program *prog)
return NULL;
}
- RTE_BPF_LOG_LINE(ERR, "%s() is not supported, rebuild with libpcap installed",
- __func__);
+ RTE_BPF_LOG_FUNC_LINE(ERR, "not supported, rebuild with libpcap installed");
rte_errno = ENOTSUP;
return NULL;
}
diff --git a/lib/bpf/bpf_validate.c b/lib/bpf/bpf_validate.c
index e8dbec282779..a7f4f576c9d6 100644
--- a/lib/bpf/bpf_validate.c
+++ b/lib/bpf/bpf_validate.c
@@ -1838,16 +1838,16 @@ add_edge(struct bpf_verifier *bvf, struct inst_node *node, uint32_t nidx)
uint32_t ne;
if (nidx >= bvf->prm->nb_ins) {
- RTE_BPF_LOG_LINE(ERR,
- "%s: program boundary violation at pc: %u, next pc: %u",
- __func__, get_node_idx(bvf, node), nidx);
+ RTE_BPF_LOG_FUNC_LINE(ERR,
+ "program boundary violation at pc: %u, next pc: %u",
+ get_node_idx(bvf, node), nidx);
return -EINVAL;
}
ne = node->nb_edge;
if (ne >= RTE_DIM(node->edge_dest)) {
- RTE_BPF_LOG_LINE(ERR, "%s: internal error at pc: %u",
- __func__, get_node_idx(bvf, node));
+ RTE_BPF_LOG_FUNC_LINE(ERR, "internal error at pc: %u",
+ get_node_idx(bvf, node));
return -EINVAL;
}
@@ -2005,8 +2005,7 @@ validate(struct bpf_verifier *bvf)
err = check_syntax(ins);
if (err != 0) {
- RTE_BPF_LOG_LINE(ERR, "%s: %s at pc: %u",
- __func__, err, i);
+ RTE_BPF_LOG_FUNC_LINE(ERR, "%s at pc: %u", err, i);
rc |= -EINVAL;
}
@@ -2230,9 +2229,9 @@ save_cur_eval_state(struct bpf_verifier *bvf, struct inst_node *node)
/* get new eval_state for this node */
st = pull_eval_state(&bvf->evst_sr_pool);
if (st == NULL) {
- RTE_BPF_LOG_LINE(ERR,
- "%s: internal error (out of space) at pc: %u",
- __func__, get_node_idx(bvf, node));
+ RTE_BPF_LOG_FUNC_LINE(ERR,
+ "internal error (out of space) at pc: %u",
+ get_node_idx(bvf, node));
return -ENOMEM;
}
@@ -2462,8 +2461,8 @@ evaluate(struct bpf_verifier *bvf)
err = ins_chk[op].eval(bvf, ins + idx);
stats.nb_eval++;
if (err != NULL) {
- RTE_BPF_LOG_LINE(ERR, "%s: %s at pc: %u",
- __func__, err, idx);
+ RTE_BPF_LOG_FUNC_LINE(ERR,
+ "%s at pc: %u", err, idx);
rc = -EINVAL;
}
}
@@ -2533,7 +2532,7 @@ __rte_bpf_validate(struct rte_bpf *bpf)
bpf->prm.prog_arg.type != RTE_BPF_ARG_PTR &&
(sizeof(uint64_t) != sizeof(uintptr_t) ||
bpf->prm.prog_arg.type != RTE_BPF_ARG_PTR_MBUF)) {
- RTE_BPF_LOG_LINE(ERR, "%s: unsupported argument type", __func__);
+ RTE_BPF_LOG_FUNC_LINE(ERR, "unsupported argument type");
return -ENOTSUP;
}
--
2.43.0
^ permalink raw reply related
* [PATCH v4 00/11] bpf: introduce extensible load API
From: Marat Khalili @ 2026-05-20 12:49 UTC (permalink / raw)
Cc: dev
In-Reply-To: <20260518084912.57006-1-marat.khalili@huawei.com>
This patchset introduces an extensible load API for the BPF library in
DPDK, addressing current limitations regarding ABI stability and feature
constraints.
Currently, `rte_bpf_load` relies on a fixed `struct rte_bpf_prm`, which
makes it difficult to add new loading options or parameters without
breaking the ABI.
To resolve these issues, this series introduces `rte_bpf_load_ex` taking
`struct rte_bpf_prm_ex`. The new parameter structure includes a `sz`
field for backward compatibility, allowing future extensions.
Taking advantage of the new extensible API, this patchset also adds
several new features:
* Support for loading and executing BPF programs with up to 5 arguments.
* Support for loading classic BPF (cBPF) directly.
* Support for loading ELF files directly from memory buffers.
* New API functions (`rte_bpf_eth_rx_install` and `rte_bpf_eth_tx_install`)
to install an already loaded BPF program as a port callback, decoupling
the loading phase from the installation phase.
v4:
* Restored missing NULL checks in wrapper functions `rte_bpf_load` and
`rte_bpf_elf_load`.
* Fixed the burst execution functions (`rte_bpf_exec_burst*`) to return
`0` and set `rte_errno = EINVAL` on failure, preventing `-EINVAL`
being reinterpreted as a large `uint32_t` value. Initialized `rc`
properly in scalar execution wrappers for this case.
* Swapped the Doxygen comments in `rte_bpf_ethdev.h` for RX and TX functions.
* Added diagnostic dump on failure path in `test_bpf_filter`.
* Fixed memory leak of the BPF handle in `bpf_rx_test` upon install failure.
* Added tests for NULL parameter rejection, mismatched execution arguments,
unsupported execution flags, and the libpcap-less `rte_bpf_convert` stub.
v3:
* Appended Acked-by tags to all individual commits to align with
patchwork requirements.
v2:
* Fixed a potential segmentation fault in `exec_vm_burst_ex` by deferring
the dereference of `ctx[i].arg` until it is confirmed that `nb_prog_arg > 0`.
* Clarified documentation and code comments for `RTE_BPF_EXEC_FLAG_JIT`
requirements and fast-path expectations.
---
To the AI reviewer:
Thank you for the review. Several of your points were very helpful and
have been addressed in v2 (e.g. the potential null pointer dereference
in `exec_vm_burst_ex`, and documenting the `RTE_BPF_EXEC_FLAG_JIT`
expectations). The remaining points were investigated but do not require
code changes for the following reasons:
> Can the macro [RTE_BPF_LOG_FUNC_LINE] be enhanced for type safety?
> Does string literal concatenation support logging format modifiers
> consistently across all call sites?
`RTE_LOG_LINE` uses compiler attributes (`__attribute__((format(printf,
...)))`) to strictly enforce format type safety. Furthermore, standard C
preprocessors inherently support string literal concatenation prior to
format checking, ensuring it works safely across all macro invocations.
> Does `bpf_load()` always set `rte_errno` to `ENOMEM` when returning
> `NULL`, or could it mask other errors by hardcoding `-ENOMEM`?
By design, the internal `bpf_load()` function only returns `NULL` when
its internal memory allocation (`mmap`) fails. Returning `-ENOMEM`
perfectly accurately reflects the nature of this failure.
> Can the loop go out of bounds? When `opts_sz` is larger than
> `type_sz`, does this code read beyond the allocated memory region
> pointed to by `opts`?
The bounds are established by the application-supplied `opts_sz`.
Standard C semantics dictate that if a caller declares a size larger
than the actual allocated memory, it generates undefined behavior on
their end. `opts_valid` iterates exactly within the declared limits.
> Does the `memcpy()` handle the case where `app_prm->sz` is larger than
> `sizeof(load->prm)` correctly? Can partial copies lead to inconsistent
> state if the struct has pointer members?
The call to `opts_valid()` happens prior to `memcpy()` and guarantees
that any extra trailing space is definitively filled with zeroes. This
implies the application relies entirely on default functionality for the
newer unknown fields, making a truncated partial copy completely sound.
> Can `elf_end()` be called with `NULL` safely? Does it cause undefined
> behavior if `load->elf` is `NULL`?
`elf_end()` in `libelf` is explicitly defined to handle `NULL` pointers
as a safe no-op.
> Can this logic handle uninitialized or out-of-range `prog_arg->type`
> values? Does `RTE_BPF_ARG_PTR_MBUF` have a specific numeric value that
> should be validated before use?
The function utilizes strict positive equality checks against valid enum
values (`RTE_BPF_ARG_RAW`, `RTE_BPF_ARG_PTR`, `RTE_BPF_ARG_PTR_MBUF`).
Invalid or uninitialized types simply fall through and cleanly return
`false`.
> Does the `malloc` check for integer overflow in the size calculation
> `nb_ins * sizeof(load->ins[0])`?
`bpf_convert_filter()` acts as a strict gatekeeper and enforces an upper
bound limit (`BPF_MAXINSNS` = 4096) on instruction count. This extremely
small ceiling makes an arithmetic overflow in `malloc` mathematically
impossible.
> Does `bpf_eth_elf_install()` acquire any additional locks? Can this
> lead to a deadlock?
No secondary lock acquisitions exist inside `bpf_eth_elf_install()`. It
executes standard initialization logic and callback registrations
without touching threading constructs, ensuring a deadlock-free flow.
> Are we standardizing on this specific format ["%s(): "]?
Yes, we are standardizing on this specific formatting for BPF logs.
> Does this properly handle the error string in all cases?
Yes, `err` is a statically assigned string literal in this context, so
passing it to `%s` is perfectly safe.
> Does this code dereference app_prm->sz before checking if app_prm is
> NULL?
The code relies on standard C short-circuit evaluation
(`app_prm == NULL || !opts_valid(...)`), which guarantees safety.
> When app_prm->sz is smaller than sizeof(load->prm), does this code
> leave portions of load->prm uninitialized?
No. `load` is zero-initialized upon declaration (`struct __rte_bpf_load
load = { .elf_fd = -1 };`), meaning any tail space is already securely
zeroed.
> If the user-supplied paths are invalid, does this check prevent
> filesystem attacks like path traversal?
In DPDK, path validation and access control are strictly the caller's
responsibility.
> Does this code risk out-of-bounds access if the union or array layout
> changes?
Structural changes to ABI types like `ctx` are major ABI breaks, which
DPDK explicitly manages across releases.
> Does bpf_convert_filter modify nb_ins even on failure? Is checking ret
> sufficient?
The code explicitly checks if `ret < 0` and immediately bails out,
safely ignoring the state of `nb_ins` on error.
> Does this code leak load->ins if called twice without cleanup between
> invocations?
No. `load` is stack-allocated internally for a single `rte_bpf_load_ex`
invocation and never reused.
> When bpf_eth_elf_install returns an error, does this code still
> transfer ownership of the bpf pointer?
On error, ownership is not transferred. The caller retains
responsibility to call `rte_bpf_destroy()`.
> Does elf_memory() actually guarantee not to modify its input buffer?
Yes, `elf_memory` treats the buffer as read-only memory unless explicit
`ELF_C_WRITE` operations are executed, which DPDK does not do here.
> Is the graceful rejection of NULL parameters by the load APIs covered
> by tests?
We have now added `test_bpf_load_null` to verify that `rte_bpf_load`,
`rte_bpf_elf_load`, and `rte_bpf_load_ex` return `NULL` and set
`rte_errno = EINVAL` when called with a `NULL` parameter.
> Does the test suite verify that mismatched arguments or invalid flags
> are correctly rejected during execution?
Yes, we have introduced tests in v4 to explicitly verify that
`rte_bpf_exec_burst` and `rte_bpf_exec_burst_ex` return `0` and set
`rte_errno = EINVAL` under these invalid conditions.
> Is the libpcap-less stub for rte_bpf_convert tested to ensure it
> doesn't crash?
A test has been added to ensure the stub safely returns `NULL` and
doesn't crash, regardless of the exact error code it might return.
Marat Khalili (11):
bpf: make logging prefixes more consistent
bpf: introduce extensible load API
bpf: support up to 5 arguments
bpf: add cBPF origin to rte_bpf_load_ex
bpf: support rte_bpf_prm_ex with port callbacks
bpf: support loading ELF files from memory
test/bpf: test loading cBPF directly
test/bpf: test loading ELF file from memory
doc: add release notes for new extensible BPF API
doc: add load API to BPF programmer's guide
test/bpf: add tests for error handling contracts
app/test/test_bpf.c | 455 +++++++++++++++++--------
doc/guides/prog_guide/bpf_lib.rst | 75 +++-
doc/guides/rel_notes/release_26_07.rst | 20 ++
lib/bpf/bpf.c | 32 +-
lib/bpf/bpf_convert.c | 99 +++++-
lib/bpf/bpf_exec.c | 134 +++++++-
lib/bpf/bpf_impl.h | 53 ++-
lib/bpf/bpf_jit_arm64.c | 18 +-
lib/bpf/bpf_jit_x86.c | 10 +-
lib/bpf/bpf_load.c | 213 ++++++++++--
lib/bpf/bpf_load_elf.c | 189 ++++++----
lib/bpf/bpf_pkt.c | 65 +++-
lib/bpf/bpf_stub.c | 46 ---
lib/bpf/bpf_validate.c | 94 +++--
lib/bpf/meson.build | 15 +-
lib/bpf/rte_bpf.h | 199 ++++++++++-
lib/bpf/rte_bpf_ethdev.h | 54 +++
17 files changed, 1400 insertions(+), 371 deletions(-)
delete mode 100644 lib/bpf/bpf_stub.c
--
2.43.0
^ permalink raw reply
* Re: [PATCH dpdk v5 2/5] net: support multiple stacked VLAN tags
From: David Marchand @ 2026-05-20 12:42 UTC (permalink / raw)
To: Robin Jarry; +Cc: dev, Kevin Traynor
In-Reply-To: <DINGHEW3M9WT.3F4XUUTLNKEL3@redhat.com>
On Wed, 20 May 2026 at 13:09, Robin Jarry <rjarry@redhat.com> wrote:
> >> - } else if (proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_QINQ)) {
> >> - const struct rte_vlan_hdr *vh;
> >> - struct rte_vlan_hdr vh_copy;
> >> + if (proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_VLAN))
> >> + pkt_type = RTE_PTYPE_L2_ETHER_VLAN;
> >> + else
> >> + pkt_type = RTE_PTYPE_L2_ETHER_QINQ;
> >> +
> >> + do {
> >> + vh = rte_pktmbuf_read(m, off, sizeof(*vh), &vh_copy);
> >> + if (unlikely(vh == NULL))
> >> + return pkt_type;
> >
> > Kevin noted that it is weird to report back some packet type when the
> > packet is malformed.
> > Maybe return RTE_PTYPE_UNKNOWN here so that the application is forced
> > to validate the packet? (it should already be doing it, in any
> > case..).
>
> If we do this, we need to fix it in the entire function. There are
> several other places where the "current" value of pkt_type is returned
> on error.
There is this point and the code has been behaving like this for
years, so some applications may have been relying on this behavior.
I don't mind leaving as is.
--
David Marchand
^ permalink raw reply
* Re: [PATCH 0/6] net/idpf: fix split queue AVX2 datapath
From: Bruce Richardson @ 2026-05-20 12:36 UTC (permalink / raw)
To: Shaiq Wani; +Cc: dev, aman.deep.singh
In-Reply-To: <20260511090935.2288837-1-shaiq.wani@intel.com>
On Mon, May 11, 2026 at 02:39:29PM +0530, Shaiq Wani wrote:
> Fix the split queue AVX2 vectorized path to correctly handle the
> virtchnl2_rx_flex_desc_adv_nic_3 completion descriptor format and
> the flex scheduled Tx descriptor encoding.
>
> The split queue completion descriptor layout is significantly
> different from the single queue path — the generation bit, DD bit,
> and packet length occupy different positions than the base Rx
> descriptor, and the buffer queue owns the mbuf pool rather than the
> completion queue.
>
> On Rx, four issues are fixed:
> - Generation bit extraction order (mask-before-shift)
> - DD bit byte offset (byte 8 not byte 1)
> - mbuf initializer sourced from bufq2 instead of the completion queue
> - Packet type inserted into the correct AVX2 lane
>
> On Tx, two issues are fixed:
> - Buffer size shift corrected from 34 to 48 for flex descriptors
> - Burst clamped to tx_rs_thresh with proper tx_next_rs tracking
>
> Shaiq Wani (6):
> net/idpf: fix gen bit extraction in split queue AVX2 Rx
> net/idpf: fix DD bit byte offset in split queue AVX2 Rx
> net/idpf: fix mbuf initializer source in split queue AVX2 Rx
> net/idpf: fix ptype insert position in split queue AVX2 Rx
> net/idpf: fix split queue AVX2 Tx buffer size shift
> net/idpf: fix split queue AVX2 Tx burst and completion
>
Series applied to dpdk-next-net-intel
Thanks,
/Bruce
^ permalink raw reply
* Re: [PATCH 6/6] net/idpf: fix split queue AVX2 Tx burst and completion
From: Bruce Richardson @ 2026-05-20 12:25 UTC (permalink / raw)
To: Shaiq Wani; +Cc: dev, aman.deep.singh
In-Reply-To: <20260511090935.2288837-7-shaiq.wani@intel.com>
On Mon, May 11, 2026 at 02:39:35PM +0530, Shaiq Wani wrote:
> Clamp burst size to tx_rs_thresh to prevent crossing completion
> boundaries. Update tx_next_rs on ring wrap and after each burst
> so that completion tracking in idpf_splitq_scan_cq_ring works
> correctly. Fix sw_ring pointer to use base-plus-offset.
>
> Fixes: 57560a92167a ("net/idpf: add AVX2 Tx path for split queue config")
> Signed-off-by: Shaiq Wani <shaiq.wani@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
> ---
> .../net/intel/idpf/idpf_common_rxtx_avx2.c | 24 ++++++++++++++-----
> 1 file changed, 18 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/net/intel/idpf/idpf_common_rxtx_avx2.c b/drivers/net/intel/idpf/idpf_common_rxtx_avx2.c
> index 7c547b5f09..b6c4fdf20e 100644
> --- a/drivers/net/intel/idpf/idpf_common_rxtx_avx2.c
> +++ b/drivers/net/intel/idpf/idpf_common_rxtx_avx2.c
> @@ -884,17 +884,21 @@ idpf_splitq_xmit_fixed_burst_vec_avx2(void *tx_queue, struct rte_mbuf **tx_pkts,
> struct ci_tx_queue *txq = (struct ci_tx_queue *)tx_queue;
> struct idpf_flex_tx_sched_desc *txdp;
> struct ci_tx_entry_vec *txep;
> - uint16_t n, nb_commit;
> + uint16_t n, nb_commit, tx_id;
> uint64_t cmd_dtype = IDPF_TXD_FLEX_FLOW_CMD_EOP;
> - uint16_t tx_id = txq->tx_tail;
>
> - nb_commit = (uint16_t)RTE_MIN(txq->nb_tx_free, nb_pkts);
> - nb_pkts = nb_commit;
> + /* cross rs_thresh boundary is not allowed */
> + nb_pkts = RTE_MIN(nb_pkts, txq->tx_rs_thresh);
> +
> + nb_pkts = (uint16_t)RTE_MIN(txq->nb_tx_free, nb_pkts);
> + nb_commit = nb_pkts;
> if (unlikely(nb_pkts == 0))
> return 0;
>
> - txdp = (struct idpf_flex_tx_sched_desc *)&txq->desc_ring[tx_id];
> - txep = &txq->sw_ring_vec[tx_id];
> + tx_id = txq->tx_tail;
> + txdp = &txq->desc_ring[tx_id];
> + txep = (void *)txq->sw_ring;
> + txep += tx_id;
>
> txq->nb_tx_free = (uint16_t)(txq->nb_tx_free - nb_pkts);
>
> @@ -909,10 +913,14 @@ idpf_splitq_xmit_fixed_burst_vec_avx2(void *tx_queue, struct rte_mbuf **tx_pkts,
> idpf_splitq_vtx1_avx2(txdp, *tx_pkts++, cmd_dtype);
>
> nb_commit = (uint16_t)(nb_commit - n);
> +
> tx_id = 0;
> + txq->tx_next_rs = (uint16_t)(txq->tx_rs_thresh - 1);
>
> + /* avoid reach the end of ring */
> txdp = &txq->desc_ring[tx_id];
> txep = (void *)txq->sw_ring;
> + txep += tx_id;
> }
>
> ci_tx_backlog_entry_vec(txep, tx_pkts, nb_commit);
> @@ -920,6 +928,10 @@ idpf_splitq_xmit_fixed_burst_vec_avx2(void *tx_queue, struct rte_mbuf **tx_pkts,
> idpf_splitq_vtx_avx2(txdp, tx_pkts, nb_commit, cmd_dtype);
>
> tx_id = (uint16_t)(tx_id + nb_commit);
> + if (tx_id > txq->tx_next_rs)
> + txq->tx_next_rs =
> + (uint16_t)(txq->tx_next_rs + txq->tx_rs_thresh);
> +
> txq->tx_tail = tx_id;
>
> IDPF_PCI_REG_WRITE(txq->qtx_tail, txq->tx_tail);
> --
> 2.34.1
>
^ permalink raw reply
* Re: [PATCH 5/6] net/idpf: fix split queue AVX2 Tx buffer size shift
From: Bruce Richardson @ 2026-05-20 12:23 UTC (permalink / raw)
To: Shaiq Wani; +Cc: dev, aman.deep.singh
In-Reply-To: <20260511090935.2288837-6-shaiq.wani@intel.com>
On Mon, May 11, 2026 at 02:39:34PM +0530, Shaiq Wani wrote:
> The flex scheduled Tx descriptor (DTYPE 0x0C) used in split queue mode
> places the buffer size at bits 48-63 of QW1, requiring a left-shift
> of 48. The code incorrectly used IDPF_TXD_QW1_TX_BUF_SZ_S (34),
> which is the shift for base Tx descriptors (DTYPE 0x0) used in single
> queue mode.
>
> This caused the data_len to be placed in the wrong bit position,
> resulting in hardware reading an incorrect buffer size of zero.
>
> Define IDPF_TXD_FLEX_QW1_TX_BUF_SZ_S (48) for the flex descriptor
> layout and use it in both vtx1 and vtx_avx2, consistent with the
> AVX512 split queue Tx path.
>
> Fixes: 57560a92167a ("net/idpf: add AVX2 Tx path for split queue config")
> Signed-off-by: Shaiq Wani <shaiq.wani@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
> ---
> drivers/net/intel/idpf/idpf_common_rxtx_avx2.c | 12 +++++++-----
> 1 file changed, 7 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/net/intel/idpf/idpf_common_rxtx_avx2.c b/drivers/net/intel/idpf/idpf_common_rxtx_avx2.c
> index e66dcc7a14..7c547b5f09 100644
> --- a/drivers/net/intel/idpf/idpf_common_rxtx_avx2.c
> +++ b/drivers/net/intel/idpf/idpf_common_rxtx_avx2.c
> @@ -819,6 +819,8 @@ idpf_splitq_scan_cq_ring(struct ci_tx_queue *cq)
> cq->tx_tail = cq_qid;
> }
>
> +#define IDPF_TXD_FLEX_QW1_TX_BUF_SZ_S 48
> +
> static __rte_always_inline void
> idpf_splitq_vtx1_avx2(struct idpf_flex_tx_sched_desc *txdp,
> struct rte_mbuf *pkt, uint64_t flags)
> @@ -826,7 +828,7 @@ idpf_splitq_vtx1_avx2(struct idpf_flex_tx_sched_desc *txdp,
> uint64_t high_qw =
> IDPF_TX_DESC_DTYPE_FLEX_FLOW_SCHE |
> ((uint64_t)flags) |
> - ((uint64_t)pkt->data_len << IDPF_TXD_QW1_TX_BUF_SZ_S);
> + ((uint64_t)pkt->data_len << IDPF_TXD_FLEX_QW1_TX_BUF_SZ_S);
>
> __m128i descriptor = _mm_set_epi64x(high_qw,
> pkt->buf_iova + pkt->data_off);
> @@ -848,13 +850,13 @@ idpf_splitq_vtx_avx2(struct idpf_flex_tx_sched_desc *txdp,
> for (; nb_pkts >= IDPF_VPMD_DESCS_PER_LOOP; txdp += IDPF_VPMD_DESCS_PER_LOOP,
> pkt += IDPF_VPMD_DESCS_PER_LOOP, nb_pkts -= IDPF_VPMD_DESCS_PER_LOOP) {
> uint64_t hi_qw0 = hi_qw_tmpl |
> - ((uint64_t)pkt[0]->data_len << IDPF_TXD_QW1_TX_BUF_SZ_S);
> + ((uint64_t)pkt[0]->data_len << IDPF_TXD_FLEX_QW1_TX_BUF_SZ_S);
> uint64_t hi_qw1 = hi_qw_tmpl |
> - ((uint64_t)pkt[1]->data_len << IDPF_TXD_QW1_TX_BUF_SZ_S);
> + ((uint64_t)pkt[1]->data_len << IDPF_TXD_FLEX_QW1_TX_BUF_SZ_S);
> uint64_t hi_qw2 = hi_qw_tmpl |
> - ((uint64_t)pkt[2]->data_len << IDPF_TXD_QW1_TX_BUF_SZ_S);
> + ((uint64_t)pkt[2]->data_len << IDPF_TXD_FLEX_QW1_TX_BUF_SZ_S);
> uint64_t hi_qw3 = hi_qw_tmpl |
> - ((uint64_t)pkt[3]->data_len << IDPF_TXD_QW1_TX_BUF_SZ_S);
> + ((uint64_t)pkt[3]->data_len << IDPF_TXD_FLEX_QW1_TX_BUF_SZ_S);
>
> __m256i desc0_1 = _mm256_set_epi64x(hi_qw1,
> pkt[1]->buf_iova + pkt[1]->data_off,
> --
> 2.34.1
>
^ 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