The HW always works on a 4K page size. When the OS supports larger pages, we fragment them across multiple BDQ descriptors. We were not properly incrementing the descriptor, which resulted in us specifying the last chunks id/addr and then 15 zero descriptors. This would cause packet loss and driver crashes. This is not a fix since the Kconfig prevents use outside of x86. Signed-off-by: Dimitri Daskalakis Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/meta/fbnic/fbnic_txrx.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c index b1e8ce89870f..57e18a68f5d2 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c @@ -887,6 +887,7 @@ static void fbnic_bd_prep(struct fbnic_ring *bdq, u16 id, netmem_ref netmem) *bdq_desc = cpu_to_le64(bd); bd += FIELD_PREP(FBNIC_BD_DESC_ADDR_MASK, 1) | FIELD_PREP(FBNIC_BD_DESC_ID_MASK, 1); + bdq_desc++; } while (--i); } -- 2.47.3 This enables aarch64 testing, but there's no reason we cannot support other architectures. Signed-off-by: Dimitri Daskalakis Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/meta/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/meta/Kconfig b/drivers/net/ethernet/meta/Kconfig index 3ba527514f1e..dff51f23d295 100644 --- a/drivers/net/ethernet/meta/Kconfig +++ b/drivers/net/ethernet/meta/Kconfig @@ -19,7 +19,7 @@ if NET_VENDOR_META config FBNIC tristate "Meta Platforms Host Network Interface" - depends on X86_64 || COMPILE_TEST + depends on 64BIT || COMPILE_TEST depends on !S390 depends on MAX_SKB_FRAGS < 22 depends on PCI_MSI -- 2.47.3