diff mbox series

[bpf-next,V3,1/6] igc: enable and fix RX hash usage by netstack

Message ID 167950087738.2796265.17812597177704199765.stgit@firesoul (mailing list archive)
State Changes Requested
Delegated to: BPF
Headers show
Series XDP-hints kfuncs for Intel driver igc | expand

Checks

Context Check Description
bpf/vmtest-bpf-next-PR success PR summary
bpf/vmtest-bpf-next-VM_Test-13 success Logs for test_maps on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-19 success Logs for test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-20 success Logs for test_progs_no_alu32 on aarch64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-27 success Logs for test_progs_no_alu32_parallel on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-9 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-2 success Logs for build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-6 success Logs for build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-8 success Logs for build for x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-3 success Logs for build for aarch64 with llvm-15
bpf/vmtest-bpf-next-VM_Test-4 success Logs for build for aarch64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-7 success Logs for build for x86_64 with llvm-15
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for bpf-next
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit fail Errors and warnings before: 20 this patch: 21
netdev/cc_maintainers fail 1 blamed authors not CCed: sasha.neftin@intel.com; 1 maintainers not CCed: sasha.neftin@intel.com
netdev/build_clang success Errors and warnings before: 20 this patch: 20
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success Fixes tag looks correct
netdev/build_allmodconfig_warn fail Errors and warnings before: 20 this patch: 21
netdev/checkpatch fail CHECK: Please use a blank line after function/struct/union/enum declarations ERROR: space required after that ',' (ctx:VxV) WARNING: line length of 81 exceeds 80 columns WARNING: line length of 83 exceeds 80 columns
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
bpf/vmtest-bpf-next-VM_Test-5 success Logs for build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-10 success Logs for test_maps on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-11 success Logs for test_maps on aarch64 with llvm-15
bpf/vmtest-bpf-next-VM_Test-12 success Logs for test_maps on aarch64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-14 success Logs for test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-15 success Logs for test_maps on x86_64 with llvm-15
bpf/vmtest-bpf-next-VM_Test-16 success Logs for test_maps on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-17 success Logs for test_progs on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-18 success Logs for test_progs on aarch64 with llvm-15
bpf/vmtest-bpf-next-VM_Test-21 success Logs for test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-22 success Logs for test_progs on x86_64 with llvm-15
bpf/vmtest-bpf-next-VM_Test-23 success Logs for test_progs on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-24 success Logs for test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-25 success Logs for test_progs_no_alu32 on aarch64 with llvm-15
bpf/vmtest-bpf-next-VM_Test-26 success Logs for test_progs_no_alu32 on aarch64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-28 success Logs for test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-29 success Logs for test_progs_no_alu32 on x86_64 with llvm-15
bpf/vmtest-bpf-next-VM_Test-30 success Logs for test_progs_no_alu32 on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-31 success Logs for test_progs_no_alu32_parallel on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-32 success Logs for test_progs_no_alu32_parallel on aarch64 with llvm-15
bpf/vmtest-bpf-next-VM_Test-33 success Logs for test_progs_no_alu32_parallel on aarch64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-34 success Logs for test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-35 success Logs for test_progs_no_alu32_parallel on x86_64 with llvm-15
bpf/vmtest-bpf-next-VM_Test-36 success Logs for test_progs_no_alu32_parallel on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-37 success Logs for test_progs_parallel on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-38 success Logs for test_progs_parallel on aarch64 with llvm-15
bpf/vmtest-bpf-next-VM_Test-39 success Logs for test_progs_parallel on aarch64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-40 success Logs for test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-41 success Logs for test_progs_parallel on x86_64 with llvm-15
bpf/vmtest-bpf-next-VM_Test-42 success Logs for test_progs_parallel on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-43 success Logs for test_verifier on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-44 success Logs for test_verifier on aarch64 with llvm-15
bpf/vmtest-bpf-next-VM_Test-45 success Logs for test_verifier on aarch64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-46 success Logs for test_verifier on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-47 success Logs for test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-48 success Logs for test_verifier on x86_64 with llvm-15
bpf/vmtest-bpf-next-VM_Test-49 success Logs for test_verifier on x86_64 with llvm-16

Commit Message

Jesper Dangaard Brouer March 22, 2023, 4:01 p.m. UTC
When function igc_rx_hash() was introduced in v4.20 via commit 0507ef8a0372
("igc: Add transmit and receive fastpath and interrupt handlers"), the
hardware wasn't configured to provide RSS hash, thus it made sense to not
enable net_device NETIF_F_RXHASH feature bit.

The NIC hardware was configured to enable RSS hash info in v5.2 via commit
2121c2712f82 ("igc: Add multiple receive queues control supporting"), but
forgot to set the NETIF_F_RXHASH feature bit.

The original implementation of igc_rx_hash() didn't extract the associated
pkt_hash_type, but statically set PKT_HASH_TYPE_L3. The largest portions of
this patch are about extracting the RSS Type from the hardware and mapping
this to enum pkt_hash_types. This was based on Foxville i225 software user
manual rev-1.3.1 and tested on Intel Ethernet Controller I225-LM (rev 03).

For UDP it's worth noting that RSS (type) hashing have been disabled both for
IPv4 and IPv6 (see IGC_MRQC_RSS_FIELD_IPV4_UDP + IGC_MRQC_RSS_FIELD_IPV6_UDP)
because hardware RSS doesn't handle fragmented pkts well when enabled (can
cause out-of-order). This results in PKT_HASH_TYPE_L3 for UDP packets, and
hash value doesn't include UDP port numbers. Not being PKT_HASH_TYPE_L4, have
the effect that netstack will do a software based hash calc calling into
flow_dissect, but only when code calls skb_get_hash(), which doesn't
necessary happen for local delivery.

Fixes: 2121c2712f82 ("igc: Add multiple receive queues control supporting")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
---
 drivers/net/ethernet/intel/igc/igc.h      |   28 ++++++++++++++++++++++++++
 drivers/net/ethernet/intel/igc/igc_main.c |   31 +++++++++++++++++++++++++----
 2 files changed, 55 insertions(+), 4 deletions(-)

Comments

Song, Yoong Siang April 12, 2023, 11:38 a.m. UTC | #1
On Thursday, March 23, 2023 12:01 AM, Jesper Dangaard Brouer <brouer@redhat.com> wrote:
>When function igc_rx_hash() was introduced in v4.20 via commit 0507ef8a0372
>("igc: Add transmit and receive fastpath and interrupt handlers"), the hardware
>wasn't configured to provide RSS hash, thus it made sense to not enable
>net_device NETIF_F_RXHASH feature bit.
>
>The NIC hardware was configured to enable RSS hash info in v5.2 via commit
>2121c2712f82 ("igc: Add multiple receive queues control supporting"), but forgot
>to set the NETIF_F_RXHASH feature bit.
>
>The original implementation of igc_rx_hash() didn't extract the associated
>pkt_hash_type, but statically set PKT_HASH_TYPE_L3. The largest portions of this
>patch are about extracting the RSS Type from the hardware and mapping this to
>enum pkt_hash_types. This was based on Foxville i225 software user manual rev-
>1.3.1 and tested on Intel Ethernet Controller I225-LM (rev 03).
>
>For UDP it's worth noting that RSS (type) hashing have been disabled both for
>IPv4 and IPv6 (see IGC_MRQC_RSS_FIELD_IPV4_UDP +
>IGC_MRQC_RSS_FIELD_IPV6_UDP) because hardware RSS doesn't handle
>fragmented pkts well when enabled (can cause out-of-order). This results in
>PKT_HASH_TYPE_L3 for UDP packets, and hash value doesn't include UDP port
>numbers. Not being PKT_HASH_TYPE_L4, have the effect that netstack will do a
>software based hash calc calling into flow_dissect, but only when code calls
>skb_get_hash(), which doesn't necessary happen for local delivery.
>
>Fixes: 2121c2712f82 ("igc: Add multiple receive queues control supporting")
>Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
>---
> drivers/net/ethernet/intel/igc/igc.h      |   28 ++++++++++++++++++++++++++
> drivers/net/ethernet/intel/igc/igc_main.c |   31 +++++++++++++++++++++++++---
>-
> 2 files changed, 55 insertions(+), 4 deletions(-)
>
>diff --git a/drivers/net/ethernet/intel/igc/igc.h
>b/drivers/net/ethernet/intel/igc/igc.h
>index df3e26c0cf01..f83cbc4a1afa 100644
>--- a/drivers/net/ethernet/intel/igc/igc.h
>+++ b/drivers/net/ethernet/intel/igc/igc.h
>@@ -13,6 +13,7 @@
> #include <linux/ptp_clock_kernel.h>
> #include <linux/timecounter.h>
> #include <linux/net_tstamp.h>
>+#include <linux/bitfield.h>
>
> #include "igc_hw.h"
>
>@@ -311,6 +312,33 @@ extern char igc_driver_name[];
> #define IGC_MRQC_RSS_FIELD_IPV4_UDP	0x00400000
> #define IGC_MRQC_RSS_FIELD_IPV6_UDP	0x00800000
>
>+/* RX-desc Write-Back format RSS Type's */ enum igc_rss_type_num {
>+	IGC_RSS_TYPE_NO_HASH		= 0,
>+	IGC_RSS_TYPE_HASH_TCP_IPV4	= 1,
>+	IGC_RSS_TYPE_HASH_IPV4		= 2,
>+	IGC_RSS_TYPE_HASH_TCP_IPV6	= 3,
>+	IGC_RSS_TYPE_HASH_IPV6_EX	= 4,
>+	IGC_RSS_TYPE_HASH_IPV6		= 5,
>+	IGC_RSS_TYPE_HASH_TCP_IPV6_EX	= 6,
>+	IGC_RSS_TYPE_HASH_UDP_IPV4	= 7,
>+	IGC_RSS_TYPE_HASH_UDP_IPV6	= 8,
>+	IGC_RSS_TYPE_HASH_UDP_IPV6_EX	= 9,
>+	IGC_RSS_TYPE_MAX		= 10,
>+};
>+#define IGC_RSS_TYPE_MAX_TABLE		16
>+#define IGC_RSS_TYPE_MASK		GENMASK(3,0) /* 4-bits (3:0) = mask
>0x0F */
>+
>+/* igc_rss_type - Rx descriptor RSS type field */ static inline u32
>+igc_rss_type(const union igc_adv_rx_desc *rx_desc) {
>+	/* RSS Type 4-bits (3:0) number: 0-9 (above 9 is reserved)
>+	 * Accessing the same bits via u16 (wb.lower.lo_dword.hs_rss.pkt_info)
>+	 * is slightly slower than via u32 (wb.lower.lo_dword.data)
>+	 */
>+	return le32_get_bits(rx_desc->wb.lower.lo_dword.data,
>+IGC_RSS_TYPE_MASK); }
>+
> /* Interrupt defines */
> #define IGC_START_ITR			648 /* ~6000 ints/sec */
> #define IGC_4K_ITR			980
>diff --git a/drivers/net/ethernet/intel/igc/igc_main.c
>b/drivers/net/ethernet/intel/igc/igc_main.c
>index 2928a6c73692..f6a54feec011 100644
>--- a/drivers/net/ethernet/intel/igc/igc_main.c
>+++ b/drivers/net/ethernet/intel/igc/igc_main.c
>@@ -1677,14 +1677,36 @@ static void igc_rx_checksum(struct igc_ring *ring,
> 		   le32_to_cpu(rx_desc->wb.upper.status_error));
> }
>
>+/* Mapping HW RSS Type to enum pkt_hash_types */
>+enum pkt_hash_types igc_rss_type_table[IGC_RSS_TYPE_MAX_TABLE] = {

Hi Jesper,

Since igc_rss_type_table is used on igc_main.c only, we can make it static to
avoid following build warning:

drivers/net/ethernet/intel/igc/igc_main.c:1681:21: warning: symbol
'igc_rss_type_table' was not declared. Should it be static?

Thanks & Regards
Siang

>+	[IGC_RSS_TYPE_NO_HASH]		= PKT_HASH_TYPE_L2,
>+	[IGC_RSS_TYPE_HASH_TCP_IPV4]	= PKT_HASH_TYPE_L4,
>+	[IGC_RSS_TYPE_HASH_IPV4]	= PKT_HASH_TYPE_L3,
>+	[IGC_RSS_TYPE_HASH_TCP_IPV6]	= PKT_HASH_TYPE_L4,
>+	[IGC_RSS_TYPE_HASH_IPV6_EX]	= PKT_HASH_TYPE_L3,
>+	[IGC_RSS_TYPE_HASH_IPV6]	= PKT_HASH_TYPE_L3,
>+	[IGC_RSS_TYPE_HASH_TCP_IPV6_EX] = PKT_HASH_TYPE_L4,
>+	[IGC_RSS_TYPE_HASH_UDP_IPV4]	= PKT_HASH_TYPE_L4,
>+	[IGC_RSS_TYPE_HASH_UDP_IPV6]	= PKT_HASH_TYPE_L4,
>+	[IGC_RSS_TYPE_HASH_UDP_IPV6_EX] = PKT_HASH_TYPE_L4,
>+	[10] = PKT_HASH_TYPE_NONE, /* RSS Type above 9 "Reserved" by HW
>*/
>+	[11] = PKT_HASH_TYPE_NONE, /* keep array sized for SW bit-mask   */
>+	[12] = PKT_HASH_TYPE_NONE, /* to handle future HW revisons       */
>+	[13] = PKT_HASH_TYPE_NONE,
>+	[14] = PKT_HASH_TYPE_NONE,
>+	[15] = PKT_HASH_TYPE_NONE,
>+};
>+
> static inline void igc_rx_hash(struct igc_ring *ring,
> 			       union igc_adv_rx_desc *rx_desc,
> 			       struct sk_buff *skb)
> {
>-	if (ring->netdev->features & NETIF_F_RXHASH)
>-		skb_set_hash(skb,
>-			     le32_to_cpu(rx_desc->wb.lower.hi_dword.rss),
>-			     PKT_HASH_TYPE_L3);
>+	if (ring->netdev->features & NETIF_F_RXHASH) {
>+		u32 rss_hash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss);
>+		u32 rss_type = igc_rss_type(rx_desc);
>+
>+		skb_set_hash(skb, rss_hash, igc_rss_type_table[rss_type]);
>+	}
> }
>
> static void igc_rx_vlan(struct igc_ring *rx_ring, @@ -6543,6 +6565,7 @@ static
>int igc_probe(struct pci_dev *pdev,
> 	netdev->features |= NETIF_F_TSO;
> 	netdev->features |= NETIF_F_TSO6;
> 	netdev->features |= NETIF_F_TSO_ECN;
>+	netdev->features |= NETIF_F_RXHASH;
> 	netdev->features |= NETIF_F_RXCSUM;
> 	netdev->features |= NETIF_F_HW_CSUM;
> 	netdev->features |= NETIF_F_SCTP_CRC;
>
diff mbox series

Patch

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index df3e26c0cf01..f83cbc4a1afa 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -13,6 +13,7 @@ 
 #include <linux/ptp_clock_kernel.h>
 #include <linux/timecounter.h>
 #include <linux/net_tstamp.h>
+#include <linux/bitfield.h>
 
 #include "igc_hw.h"
 
@@ -311,6 +312,33 @@  extern char igc_driver_name[];
 #define IGC_MRQC_RSS_FIELD_IPV4_UDP	0x00400000
 #define IGC_MRQC_RSS_FIELD_IPV6_UDP	0x00800000
 
+/* RX-desc Write-Back format RSS Type's */
+enum igc_rss_type_num {
+	IGC_RSS_TYPE_NO_HASH		= 0,
+	IGC_RSS_TYPE_HASH_TCP_IPV4	= 1,
+	IGC_RSS_TYPE_HASH_IPV4		= 2,
+	IGC_RSS_TYPE_HASH_TCP_IPV6	= 3,
+	IGC_RSS_TYPE_HASH_IPV6_EX	= 4,
+	IGC_RSS_TYPE_HASH_IPV6		= 5,
+	IGC_RSS_TYPE_HASH_TCP_IPV6_EX	= 6,
+	IGC_RSS_TYPE_HASH_UDP_IPV4	= 7,
+	IGC_RSS_TYPE_HASH_UDP_IPV6	= 8,
+	IGC_RSS_TYPE_HASH_UDP_IPV6_EX	= 9,
+	IGC_RSS_TYPE_MAX		= 10,
+};
+#define IGC_RSS_TYPE_MAX_TABLE		16
+#define IGC_RSS_TYPE_MASK		GENMASK(3,0) /* 4-bits (3:0) = mask 0x0F */
+
+/* igc_rss_type - Rx descriptor RSS type field */
+static inline u32 igc_rss_type(const union igc_adv_rx_desc *rx_desc)
+{
+	/* RSS Type 4-bits (3:0) number: 0-9 (above 9 is reserved)
+	 * Accessing the same bits via u16 (wb.lower.lo_dword.hs_rss.pkt_info)
+	 * is slightly slower than via u32 (wb.lower.lo_dword.data)
+	 */
+	return le32_get_bits(rx_desc->wb.lower.lo_dword.data, IGC_RSS_TYPE_MASK);
+}
+
 /* Interrupt defines */
 #define IGC_START_ITR			648 /* ~6000 ints/sec */
 #define IGC_4K_ITR			980
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 2928a6c73692..f6a54feec011 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -1677,14 +1677,36 @@  static void igc_rx_checksum(struct igc_ring *ring,
 		   le32_to_cpu(rx_desc->wb.upper.status_error));
 }
 
+/* Mapping HW RSS Type to enum pkt_hash_types */
+enum pkt_hash_types igc_rss_type_table[IGC_RSS_TYPE_MAX_TABLE] = {
+	[IGC_RSS_TYPE_NO_HASH]		= PKT_HASH_TYPE_L2,
+	[IGC_RSS_TYPE_HASH_TCP_IPV4]	= PKT_HASH_TYPE_L4,
+	[IGC_RSS_TYPE_HASH_IPV4]	= PKT_HASH_TYPE_L3,
+	[IGC_RSS_TYPE_HASH_TCP_IPV6]	= PKT_HASH_TYPE_L4,
+	[IGC_RSS_TYPE_HASH_IPV6_EX]	= PKT_HASH_TYPE_L3,
+	[IGC_RSS_TYPE_HASH_IPV6]	= PKT_HASH_TYPE_L3,
+	[IGC_RSS_TYPE_HASH_TCP_IPV6_EX] = PKT_HASH_TYPE_L4,
+	[IGC_RSS_TYPE_HASH_UDP_IPV4]	= PKT_HASH_TYPE_L4,
+	[IGC_RSS_TYPE_HASH_UDP_IPV6]	= PKT_HASH_TYPE_L4,
+	[IGC_RSS_TYPE_HASH_UDP_IPV6_EX] = PKT_HASH_TYPE_L4,
+	[10] = PKT_HASH_TYPE_NONE, /* RSS Type above 9 "Reserved" by HW  */
+	[11] = PKT_HASH_TYPE_NONE, /* keep array sized for SW bit-mask   */
+	[12] = PKT_HASH_TYPE_NONE, /* to handle future HW revisons       */
+	[13] = PKT_HASH_TYPE_NONE,
+	[14] = PKT_HASH_TYPE_NONE,
+	[15] = PKT_HASH_TYPE_NONE,
+};
+
 static inline void igc_rx_hash(struct igc_ring *ring,
 			       union igc_adv_rx_desc *rx_desc,
 			       struct sk_buff *skb)
 {
-	if (ring->netdev->features & NETIF_F_RXHASH)
-		skb_set_hash(skb,
-			     le32_to_cpu(rx_desc->wb.lower.hi_dword.rss),
-			     PKT_HASH_TYPE_L3);
+	if (ring->netdev->features & NETIF_F_RXHASH) {
+		u32 rss_hash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss);
+		u32 rss_type = igc_rss_type(rx_desc);
+
+		skb_set_hash(skb, rss_hash, igc_rss_type_table[rss_type]);
+	}
 }
 
 static void igc_rx_vlan(struct igc_ring *rx_ring,
@@ -6543,6 +6565,7 @@  static int igc_probe(struct pci_dev *pdev,
 	netdev->features |= NETIF_F_TSO;
 	netdev->features |= NETIF_F_TSO6;
 	netdev->features |= NETIF_F_TSO_ECN;
+	netdev->features |= NETIF_F_RXHASH;
 	netdev->features |= NETIF_F_RXCSUM;
 	netdev->features |= NETIF_F_HW_CSUM;
 	netdev->features |= NETIF_F_SCTP_CRC;