[v3] mbuf: deprecate GCC marker in rte mbuf struct
Checks
Commit Message
Provide a macro that allows conditional expansion of RTE_MARKER fields
to empty to allow rte_mbuf to be used with MSVC. It is proposed that
we announce the fields to be __rte_deprecated (currently disabled).
Introduce C11 anonymous unions to permit aliasing of well-known
offsets by name into the rte_mbuf structure by a *new* name and to
provide padding for cache alignment.
Signed-off-by: Tyler Retzlaff <roretzla@linux.microsoft.com>
---
lib/eal/include/rte_common.h | 6 +
lib/mbuf/rte_mbuf_core.h | 365 +++++++++++++++++++++++--------------------
2 files changed, 201 insertions(+), 170 deletions(-)
Comments
> From: Tyler Retzlaff [mailto:roretzla@linux.microsoft.com]
> Sent: Wednesday, 14 February 2024 00.33
>
> Provide a macro that allows conditional expansion of RTE_MARKER fields
> to empty to allow rte_mbuf to be used with MSVC. It is proposed that
> we announce the fields to be __rte_deprecated (currently disabled).
>
> Introduce C11 anonymous unions to permit aliasing of well-known
> offsets by name into the rte_mbuf structure by a *new* name and to
> provide padding for cache alignment.
>
> Signed-off-by: Tyler Retzlaff <roretzla@linux.microsoft.com>
> ---
I think you are nearly there now. Beautiful solution. :-)
Only one comment inline below.
> - /* remaining bytes are set on RX when pulling packet from
> descriptor */
> - RTE_MARKER rx_descriptor_fields1;
> + uint64_t ol_flags; /**< Offload features. */
>
> - /*
> - * The packet type, which is the combination of outer/inner L2,
> L3, L4
> - * and tunnel types. The packet_type is about data really present
> in the
> - * mbuf. Example: if vlan stripping is enabled, a received vlan
> packet
> - * would have RTE_PTYPE_L2_ETHER and not RTE_PTYPE_L2_VLAN
> because the
> - * vlan is stripped from the data.
> - */
> - union {
> - uint32_t packet_type; /**< L2/L3/L4 and tunnel information.
> */
> - __extension__
> - struct {
> - uint8_t l2_type:4; /**< (Outer) L2 type. */
> - uint8_t l3_type:4; /**< (Outer) L3 type. */
> - uint8_t l4_type:4; /**< (Outer) L4 type. */
> - uint8_t tun_type:4; /**< Tunnel type. */
> + /* remaining bytes are set on RX when pulling packet
> from descriptor */
> + __rte_marker(RTE_MARKER, rx_descriptor_fields1);
> union {
> - uint8_t inner_esp_next_proto;
> - /**< ESP next protocol type, valid if
> - * RTE_PTYPE_TUNNEL_ESP tunnel type is set
> - * on both Tx and Rx.
> - */
> - __extension__
> + char mbuf_rx_descriptor_fields1[sizeof(void
> *)];
The size of the mbuf_rx_descriptor_fields1 array - and the union it belongs to - may not be accurate.
The existing rx_descriptor_fields1 effectively has no type/size, and the associated comment "/* remaining bytes are set on RX" doesn't help; it omits how many bytes it refers to. I'll call it "an already existing bug" for the sake of discussion.
I think the struct should go all the way to the pool pointer, to reflect which "remaining bytes" are set on RX.
You might consider taking the opportunity to fix this existing "bug", i.e. update the comment and move more fields into the struct unionized with the mbuf_rx_descriptor_fields1 array. (This suggestion is in the category NICE TO HAVE, and certainly not a requirement!)
Regardless if you fix this existing "bug" or not, the size of the mbuf_rx_descriptor_fields1 array should match the size of the struct it is unionized with, rather than using sizeof(void*) (which is either 4 or 8 bytes, depending on CPU architecture).
Instinctively, I think that it is a bad idea to carry over the "sizeless" aspect of the rx_descriptor_fields1 marker into the mbuf_rx_descriptor_fields1 array. However, you have been working more in depth with this patch series, so I'm open for arguments for the way you did it!
> struct {
> - uint8_t inner_l2_type:4;
> - /**< Inner L2 type. */
> - uint8_t inner_l3_type:4;
> - /**< Inner L3 type. */
> + /*
> + * The packet type, which is the
> combination of outer/inner L2, L3, L4
> + * and tunnel types. The packet_type is
> about data really present in the
> + * mbuf. Example: if vlan stripping is
> enabled, a received vlan packet
> + * would have RTE_PTYPE_L2_ETHER and not
> RTE_PTYPE_L2_VLAN because the
> + * vlan is stripped from the data.
> + */
> + union {
> + uint32_t packet_type; /**< L2/L3/L4
> and tunnel information. */
> + __extension__
> + struct {
> + uint8_t l2_type:4; /**<
> (Outer) L2 type. */
> + uint8_t l3_type:4; /**<
> (Outer) L3 type. */
> + uint8_t l4_type:4; /**<
> (Outer) L4 type. */
> + uint8_t tun_type:4; /**<
> Tunnel type. */
> + union {
> + uint8_t
> inner_esp_next_proto;
> + /**< ESP next protocol
> type, valid if
> + * RTE_PTYPE_TUNNEL_ESP
> tunnel type is set
> + * on both Tx and Rx.
> + */
> + __extension__
> + struct {
> + uint8_t
> inner_l2_type:4;
> + /**< Inner L2
> type. */
> + uint8_t
> inner_l3_type:4;
> + /**< Inner L3
> type. */
> + };
> + };
> + uint8_t inner_l4_type:4; /**<
> Inner L4 type. */
> + };
> + };
> + uint32_t pkt_len; /**< Total pkt
> len: sum of all segments. */
> };
> };
> - uint8_t inner_l4_type:4; /**< Inner L4 type. */
> - };
> - };
>
> - uint32_t pkt_len; /**< Total pkt len: sum of all
> segments. */
> - uint16_t data_len; /**< Amount of data in segment buffer.
> */
> - /** VLAN TCI (CPU order), valid if RTE_MBUF_F_RX_VLAN is set. */
> - uint16_t vlan_tci;
> + uint16_t data_len; /**< Amount of data in
> segment buffer. */
> + /** VLAN TCI (CPU order), valid if RTE_MBUF_F_RX_VLAN
> is set. */
> + uint16_t vlan_tci;
>
> - union {
> - union {
> - uint32_t rss; /**< RSS hash result if RSS enabled
> */
> - struct {
> + union {
> union {
> + uint32_t rss; /**< RSS hash result if
> RSS enabled */
> struct {
> - uint16_t hash;
> - uint16_t id;
> - };
> - uint32_t lo;
> - /**< Second 4 flexible bytes */
> - };
> - uint32_t hi;
> - /**< First 4 flexible bytes or FD ID, dependent
> - * on RTE_MBUF_F_RX_FDIR_* flag in ol_flags.
> - */
> - } fdir; /**< Filter identifier if FDIR enabled */
> - struct rte_mbuf_sched sched;
> - /**< Hierarchical scheduler : 8 bytes */
> - struct {
> - uint32_t reserved1;
> - uint16_t reserved2;
> - uint16_t txq;
> - /**< The event eth Tx adapter uses this field
> - * to store Tx queue id.
> - * @see rte_event_eth_tx_adapter_txq_set()
> - */
> - } txadapter; /**< Eventdev ethdev Tx adapter */
> - uint32_t usr;
> - /**< User defined tags. See rte_distributor_process()
> */
> - } hash; /**< hash information */
> - };
> + union {
> + struct {
> + uint16_t hash;
> + uint16_t id;
> + };
> + uint32_t lo;
> + /**< Second 4 flexible bytes
> */
> + };
> + uint32_t hi;
> + /**< First 4 flexible bytes or FD
> ID, dependent
> + * on RTE_MBUF_F_RX_FDIR_* flag in
> ol_flags.
> + */
> + } fdir; /**< Filter identifier if
> FDIR enabled */
> + struct rte_mbuf_sched sched;
> + /**< Hierarchical scheduler : 8 bytes */
> + struct {
> + uint32_t reserved1;
> + uint16_t reserved2;
> + uint16_t txq;
> + /**< The event eth Tx adapter uses
> this field
> + * to store Tx queue id.
> + * @see
> rte_event_eth_tx_adapter_txq_set()
> + */
> + } txadapter; /**< Eventdev ethdev Tx
> adapter */
> + uint32_t usr;
> + /**< User defined tags. See
> rte_distributor_process() */
> + } hash; /**< hash information
> */
> + };
>
> - /** Outer VLAN TCI (CPU order), valid if RTE_MBUF_F_RX_QINQ is
> set. */
> - uint16_t vlan_tci_outer;
> + /** Outer VLAN TCI (CPU order), valid if
> RTE_MBUF_F_RX_QINQ is set. */
> + uint16_t vlan_tci_outer;
>
> - uint16_t buf_len; /**< Length of segment buffer. */
> + uint16_t buf_len; /**< Length of segment
> buffer. */
>
> - struct rte_mempool *pool; /**< Pool from which mbuf was
> allocated. */
> + struct rte_mempool *pool; /**< Pool from which mbuf
> was allocated. */
> + };
> + };
>
> /* second cache line - fields only used in slow path or on TX */
On Wed, Feb 14, 2024 at 11:46:01AM +0100, Morten Brørup wrote:
> > From: Tyler Retzlaff [mailto:roretzla@linux.microsoft.com]
> > Sent: Wednesday, 14 February 2024 00.33
> >
> > Provide a macro that allows conditional expansion of RTE_MARKER fields
> > to empty to allow rte_mbuf to be used with MSVC. It is proposed that
> > we announce the fields to be __rte_deprecated (currently disabled).
> >
> > Introduce C11 anonymous unions to permit aliasing of well-known
> > offsets by name into the rte_mbuf structure by a *new* name and to
> > provide padding for cache alignment.
> >
> > Signed-off-by: Tyler Retzlaff <roretzla@linux.microsoft.com>
> > ---
>
> I think you are nearly there now. Beautiful solution. :-)
>
> Only one comment inline below.
>
> > - /* remaining bytes are set on RX when pulling packet from
> > descriptor */
> > - RTE_MARKER rx_descriptor_fields1;
> > + uint64_t ol_flags; /**< Offload features. */
> >
> > - /*
> > - * The packet type, which is the combination of outer/inner L2,
> > L3, L4
> > - * and tunnel types. The packet_type is about data really present
> > in the
> > - * mbuf. Example: if vlan stripping is enabled, a received vlan
> > packet
> > - * would have RTE_PTYPE_L2_ETHER and not RTE_PTYPE_L2_VLAN
> > because the
> > - * vlan is stripped from the data.
> > - */
> > - union {
> > - uint32_t packet_type; /**< L2/L3/L4 and tunnel information.
> > */
> > - __extension__
> > - struct {
> > - uint8_t l2_type:4; /**< (Outer) L2 type. */
> > - uint8_t l3_type:4; /**< (Outer) L3 type. */
> > - uint8_t l4_type:4; /**< (Outer) L4 type. */
> > - uint8_t tun_type:4; /**< Tunnel type. */
> > + /* remaining bytes are set on RX when pulling packet
> > from descriptor */
> > + __rte_marker(RTE_MARKER, rx_descriptor_fields1);
> > union {
> > - uint8_t inner_esp_next_proto;
> > - /**< ESP next protocol type, valid if
> > - * RTE_PTYPE_TUNNEL_ESP tunnel type is set
> > - * on both Tx and Rx.
> > - */
> > - __extension__
> > + char mbuf_rx_descriptor_fields1[sizeof(void
> > *)];
>
> The size of the mbuf_rx_descriptor_fields1 array - and the union it belongs to - may not be accurate.
yeah, i just cloned the type out of the marker. but you are right it's
garbage. on 32-bit platforms access via that union member probably falls
into undefined behavior territory.
i'll replace it with [8] since that's the size of the struct member, at
least then it's as big as the other union fields.
i think my greatest concern at this point is making a mistake in adapting
the in-tree consumers to the new field that assumed the named thing was
void *[]. sometimes the address is taken, sometimes not, might be okay
since we're consistently using arrays now but it will likely need some
casts where previously didn't. definitely appreciate careful review.
thanks
>
> The existing rx_descriptor_fields1 effectively has no type/size, and the associated comment "/* remaining bytes are set on RX" doesn't help; it omits how many bytes it refers to. I'll call it "an already existing bug" for the sake of discussion.
> I think the struct should go all the way to the pool pointer, to reflect which "remaining bytes" are set on RX.
> You might consider taking the opportunity to fix this existing "bug", i.e. update the comment and move more fields into the struct unionized with the mbuf_rx_descriptor_fields1 array. (This suggestion is in the category NICE TO HAVE, and certainly not a requirement!)
>
> Regardless if you fix this existing "bug" or not, the size of the mbuf_rx_descriptor_fields1 array should match the size of the struct it is unionized with, rather than using sizeof(void*) (which is either 4 or 8 bytes, depending on CPU architecture).
> Instinctively, I think that it is a bad idea to carry over the "sizeless" aspect of the rx_descriptor_fields1 marker into the mbuf_rx_descriptor_fields1 array. However, you have been working more in depth with this patch series, so I'm open for arguments for the way you did it!
>
> > struct {
> > - uint8_t inner_l2_type:4;
> > - /**< Inner L2 type. */
> > - uint8_t inner_l3_type:4;
> > - /**< Inner L3 type. */
> > + /*
> > + * The packet type, which is the
> > combination of outer/inner L2, L3, L4
> > + * and tunnel types. The packet_type is
> > about data really present in the
> > + * mbuf. Example: if vlan stripping is
> > enabled, a received vlan packet
> > + * would have RTE_PTYPE_L2_ETHER and not
> > RTE_PTYPE_L2_VLAN because the
> > + * vlan is stripped from the data.
> > + */
> > + union {
> > + uint32_t packet_type; /**< L2/L3/L4
> > and tunnel information. */
> > + __extension__
> > + struct {
> > + uint8_t l2_type:4; /**<
> > (Outer) L2 type. */
> > + uint8_t l3_type:4; /**<
> > (Outer) L3 type. */
> > + uint8_t l4_type:4; /**<
> > (Outer) L4 type. */
> > + uint8_t tun_type:4; /**<
> > Tunnel type. */
> > + union {
> > + uint8_t
> > inner_esp_next_proto;
> > + /**< ESP next protocol
> > type, valid if
> > + * RTE_PTYPE_TUNNEL_ESP
> > tunnel type is set
> > + * on both Tx and Rx.
> > + */
> > + __extension__
> > + struct {
> > + uint8_t
> > inner_l2_type:4;
> > + /**< Inner L2
> > type. */
> > + uint8_t
> > inner_l3_type:4;
> > + /**< Inner L3
> > type. */
> > + };
> > + };
> > + uint8_t inner_l4_type:4; /**<
> > Inner L4 type. */
> > + };
> > + };
> > + uint32_t pkt_len; /**< Total pkt
> > len: sum of all segments. */
> > };
> > };
> > - uint8_t inner_l4_type:4; /**< Inner L4 type. */
> > - };
> > - };
> >
> > - uint32_t pkt_len; /**< Total pkt len: sum of all
> > segments. */
> > - uint16_t data_len; /**< Amount of data in segment buffer.
> > */
> > - /** VLAN TCI (CPU order), valid if RTE_MBUF_F_RX_VLAN is set. */
> > - uint16_t vlan_tci;
> > + uint16_t data_len; /**< Amount of data in
> > segment buffer. */
> > + /** VLAN TCI (CPU order), valid if RTE_MBUF_F_RX_VLAN
> > is set. */
> > + uint16_t vlan_tci;
> >
> > - union {
> > - union {
> > - uint32_t rss; /**< RSS hash result if RSS enabled
> > */
> > - struct {
> > + union {
> > union {
> > + uint32_t rss; /**< RSS hash result if
> > RSS enabled */
> > struct {
> > - uint16_t hash;
> > - uint16_t id;
> > - };
> > - uint32_t lo;
> > - /**< Second 4 flexible bytes */
> > - };
> > - uint32_t hi;
> > - /**< First 4 flexible bytes or FD ID, dependent
> > - * on RTE_MBUF_F_RX_FDIR_* flag in ol_flags.
> > - */
> > - } fdir; /**< Filter identifier if FDIR enabled */
> > - struct rte_mbuf_sched sched;
> > - /**< Hierarchical scheduler : 8 bytes */
> > - struct {
> > - uint32_t reserved1;
> > - uint16_t reserved2;
> > - uint16_t txq;
> > - /**< The event eth Tx adapter uses this field
> > - * to store Tx queue id.
> > - * @see rte_event_eth_tx_adapter_txq_set()
> > - */
> > - } txadapter; /**< Eventdev ethdev Tx adapter */
> > - uint32_t usr;
> > - /**< User defined tags. See rte_distributor_process()
> > */
> > - } hash; /**< hash information */
> > - };
> > + union {
> > + struct {
> > + uint16_t hash;
> > + uint16_t id;
> > + };
> > + uint32_t lo;
> > + /**< Second 4 flexible bytes
> > */
> > + };
> > + uint32_t hi;
> > + /**< First 4 flexible bytes or FD
> > ID, dependent
> > + * on RTE_MBUF_F_RX_FDIR_* flag in
> > ol_flags.
> > + */
> > + } fdir; /**< Filter identifier if
> > FDIR enabled */
> > + struct rte_mbuf_sched sched;
> > + /**< Hierarchical scheduler : 8 bytes */
> > + struct {
> > + uint32_t reserved1;
> > + uint16_t reserved2;
> > + uint16_t txq;
> > + /**< The event eth Tx adapter uses
> > this field
> > + * to store Tx queue id.
> > + * @see
> > rte_event_eth_tx_adapter_txq_set()
> > + */
> > + } txadapter; /**< Eventdev ethdev Tx
> > adapter */
> > + uint32_t usr;
> > + /**< User defined tags. See
> > rte_distributor_process() */
> > + } hash; /**< hash information
> > */
> > + };
> >
> > - /** Outer VLAN TCI (CPU order), valid if RTE_MBUF_F_RX_QINQ is
> > set. */
> > - uint16_t vlan_tci_outer;
> > + /** Outer VLAN TCI (CPU order), valid if
> > RTE_MBUF_F_RX_QINQ is set. */
> > + uint16_t vlan_tci_outer;
> >
> > - uint16_t buf_len; /**< Length of segment buffer. */
> > + uint16_t buf_len; /**< Length of segment
> > buffer. */
> >
> > - struct rte_mempool *pool; /**< Pool from which mbuf was
> > allocated. */
> > + struct rte_mempool *pool; /**< Pool from which mbuf
> > was allocated. */
> > + };
> > + };
> >
> > /* second cache line - fields only used in slow path or on TX */
@@ -582,6 +582,12 @@ static void __attribute__((destructor(RTE_PRIO(prio)), used)) func(void)
/** Marker for 8B alignment in a structure. */
__extension__ typedef uint64_t RTE_MARKER64[0];
+#define __rte_marker(type, name) type name /* __rte_deprecated */
+
+#else
+
+#define __rte_marker(type, name)
+
#endif
/*********** Macros for calculating min and max **********/
@@ -16,7 +16,10 @@
* New fields and flags should fit in the "dynamic space".
*/
+#include <assert.h>
+#include <stdalign.h>
#include <stdint.h>
+#include <stddef.h>
#include <rte_byteorder.h>
#include <rte_stdatomic.h>
@@ -464,206 +467,228 @@ enum {
* The generic rte_mbuf, containing a packet mbuf.
*/
struct rte_mbuf {
- RTE_MARKER cacheline0;
-
- void *buf_addr; /**< Virtual address of segment buffer. */
+ __rte_marker(RTE_MARKER, cacheline0);
+ union {
+ char mbuf_cacheline0[RTE_CACHE_LINE_MIN_SIZE];
+ struct {
+ void *buf_addr; /**< Virtual address of segment buffer. */
#if RTE_IOVA_IN_MBUF
- /**
- * Physical address of segment buffer.
- * This field is undefined if the build is configured to use only
- * virtual address as IOVA (i.e. RTE_IOVA_IN_MBUF is 0).
- * Force alignment to 8-bytes, so as to ensure we have the exact
- * same mbuf cacheline0 layout for 32-bit and 64-bit. This makes
- * working on vector drivers easier.
- */
- rte_iova_t buf_iova __rte_aligned(sizeof(rte_iova_t));
+ /**
+ * Physical address of segment buffer.
+ * This field is undefined if the build is configured to use only
+ * virtual address as IOVA (i.e. RTE_IOVA_IN_MBUF is 0).
+ * Force alignment to 8-bytes, so as to ensure we have the exact
+ * same mbuf cacheline0 layout for 32-bit and 64-bit. This makes
+ * working on vector drivers easier.
+ */
+ rte_iova_t buf_iova __rte_aligned(sizeof(rte_iova_t));
#else
- /**
- * Next segment of scattered packet.
- * This field is valid when physical address field is undefined.
- * Otherwise next pointer in the second cache line will be used.
- */
- struct rte_mbuf *next;
+ /**
+ * Next segment of scattered packet.
+ * This field is valid when physical address field is undefined.
+ * Otherwise next pointer in the second cache line will be used.
+ */
+ struct rte_mbuf *next;
#endif
- /* next 8 bytes are initialised on RX descriptor rearm */
- RTE_MARKER64 rearm_data;
- uint16_t data_off;
-
- /**
- * Reference counter. Its size should at least equal to the size
- * of port field (16 bits), to support zero-copy broadcast.
- * It should only be accessed using the following functions:
- * rte_mbuf_refcnt_update(), rte_mbuf_refcnt_read(), and
- * rte_mbuf_refcnt_set(). The functionality of these functions (atomic,
- * or non-atomic) is controlled by the RTE_MBUF_REFCNT_ATOMIC flag.
- */
- RTE_ATOMIC(uint16_t) refcnt;
-
- /**
- * Number of segments. Only valid for the first segment of an mbuf
- * chain.
- */
- uint16_t nb_segs;
-
- /** Input port (16 bits to support more than 256 virtual ports).
- * The event eth Tx adapter uses this field to specify the output port.
- */
- uint16_t port;
-
- uint64_t ol_flags; /**< Offload features. */
+ /* next 8 bytes are initialised on RX descriptor rearm */
+ __rte_marker(RTE_MARKER64, rearm_data);
+ union {
+ char mbuf_rearm_data[8];
+ struct {
+ uint16_t data_off;
+
+ /**
+ * Reference counter. Its size should at least equal to the size
+ * of port field (16 bits), to support zero-copy broadcast.
+ * It should only be accessed using the following functions:
+ * rte_mbuf_refcnt_update(), rte_mbuf_refcnt_read(), and
+ * rte_mbuf_refcnt_set(). The functionality of these functions (atomic,
+ * or non-atomic) is controlled by the RTE_MBUF_REFCNT_ATOMIC flag.
+ */
+ RTE_ATOMIC(uint16_t) refcnt;
+
+ /**
+ * Number of segments. Only valid for the first segment of an mbuf
+ * chain.
+ */
+ uint16_t nb_segs;
+
+ /** Input port (16 bits to support more than 256 virtual ports).
+ * The event eth Tx adapter uses this field to specify the output port.
+ */
+ uint16_t port;
+ };
+ };
- /* remaining bytes are set on RX when pulling packet from descriptor */
- RTE_MARKER rx_descriptor_fields1;
+ uint64_t ol_flags; /**< Offload features. */
- /*
- * The packet type, which is the combination of outer/inner L2, L3, L4
- * and tunnel types. The packet_type is about data really present in the
- * mbuf. Example: if vlan stripping is enabled, a received vlan packet
- * would have RTE_PTYPE_L2_ETHER and not RTE_PTYPE_L2_VLAN because the
- * vlan is stripped from the data.
- */
- union {
- uint32_t packet_type; /**< L2/L3/L4 and tunnel information. */
- __extension__
- struct {
- uint8_t l2_type:4; /**< (Outer) L2 type. */
- uint8_t l3_type:4; /**< (Outer) L3 type. */
- uint8_t l4_type:4; /**< (Outer) L4 type. */
- uint8_t tun_type:4; /**< Tunnel type. */
+ /* remaining bytes are set on RX when pulling packet from descriptor */
+ __rte_marker(RTE_MARKER, rx_descriptor_fields1);
union {
- uint8_t inner_esp_next_proto;
- /**< ESP next protocol type, valid if
- * RTE_PTYPE_TUNNEL_ESP tunnel type is set
- * on both Tx and Rx.
- */
- __extension__
+ char mbuf_rx_descriptor_fields1[sizeof(void *)];
struct {
- uint8_t inner_l2_type:4;
- /**< Inner L2 type. */
- uint8_t inner_l3_type:4;
- /**< Inner L3 type. */
+ /*
+ * The packet type, which is the combination of outer/inner L2, L3, L4
+ * and tunnel types. The packet_type is about data really present in the
+ * mbuf. Example: if vlan stripping is enabled, a received vlan packet
+ * would have RTE_PTYPE_L2_ETHER and not RTE_PTYPE_L2_VLAN because the
+ * vlan is stripped from the data.
+ */
+ union {
+ uint32_t packet_type; /**< L2/L3/L4 and tunnel information. */
+ __extension__
+ struct {
+ uint8_t l2_type:4; /**< (Outer) L2 type. */
+ uint8_t l3_type:4; /**< (Outer) L3 type. */
+ uint8_t l4_type:4; /**< (Outer) L4 type. */
+ uint8_t tun_type:4; /**< Tunnel type. */
+ union {
+ uint8_t inner_esp_next_proto;
+ /**< ESP next protocol type, valid if
+ * RTE_PTYPE_TUNNEL_ESP tunnel type is set
+ * on both Tx and Rx.
+ */
+ __extension__
+ struct {
+ uint8_t inner_l2_type:4;
+ /**< Inner L2 type. */
+ uint8_t inner_l3_type:4;
+ /**< Inner L3 type. */
+ };
+ };
+ uint8_t inner_l4_type:4; /**< Inner L4 type. */
+ };
+ };
+ uint32_t pkt_len; /**< Total pkt len: sum of all segments. */
};
};
- uint8_t inner_l4_type:4; /**< Inner L4 type. */
- };
- };
- uint32_t pkt_len; /**< Total pkt len: sum of all segments. */
- uint16_t data_len; /**< Amount of data in segment buffer. */
- /** VLAN TCI (CPU order), valid if RTE_MBUF_F_RX_VLAN is set. */
- uint16_t vlan_tci;
+ uint16_t data_len; /**< Amount of data in segment buffer. */
+ /** VLAN TCI (CPU order), valid if RTE_MBUF_F_RX_VLAN is set. */
+ uint16_t vlan_tci;
- union {
- union {
- uint32_t rss; /**< RSS hash result if RSS enabled */
- struct {
+ union {
union {
+ uint32_t rss; /**< RSS hash result if RSS enabled */
struct {
- uint16_t hash;
- uint16_t id;
- };
- uint32_t lo;
- /**< Second 4 flexible bytes */
- };
- uint32_t hi;
- /**< First 4 flexible bytes or FD ID, dependent
- * on RTE_MBUF_F_RX_FDIR_* flag in ol_flags.
- */
- } fdir; /**< Filter identifier if FDIR enabled */
- struct rte_mbuf_sched sched;
- /**< Hierarchical scheduler : 8 bytes */
- struct {
- uint32_t reserved1;
- uint16_t reserved2;
- uint16_t txq;
- /**< The event eth Tx adapter uses this field
- * to store Tx queue id.
- * @see rte_event_eth_tx_adapter_txq_set()
- */
- } txadapter; /**< Eventdev ethdev Tx adapter */
- uint32_t usr;
- /**< User defined tags. See rte_distributor_process() */
- } hash; /**< hash information */
- };
+ union {
+ struct {
+ uint16_t hash;
+ uint16_t id;
+ };
+ uint32_t lo;
+ /**< Second 4 flexible bytes */
+ };
+ uint32_t hi;
+ /**< First 4 flexible bytes or FD ID, dependent
+ * on RTE_MBUF_F_RX_FDIR_* flag in ol_flags.
+ */
+ } fdir; /**< Filter identifier if FDIR enabled */
+ struct rte_mbuf_sched sched;
+ /**< Hierarchical scheduler : 8 bytes */
+ struct {
+ uint32_t reserved1;
+ uint16_t reserved2;
+ uint16_t txq;
+ /**< The event eth Tx adapter uses this field
+ * to store Tx queue id.
+ * @see rte_event_eth_tx_adapter_txq_set()
+ */
+ } txadapter; /**< Eventdev ethdev Tx adapter */
+ uint32_t usr;
+ /**< User defined tags. See rte_distributor_process() */
+ } hash; /**< hash information */
+ };
- /** Outer VLAN TCI (CPU order), valid if RTE_MBUF_F_RX_QINQ is set. */
- uint16_t vlan_tci_outer;
+ /** Outer VLAN TCI (CPU order), valid if RTE_MBUF_F_RX_QINQ is set. */
+ uint16_t vlan_tci_outer;
- uint16_t buf_len; /**< Length of segment buffer. */
+ uint16_t buf_len; /**< Length of segment buffer. */
- struct rte_mempool *pool; /**< Pool from which mbuf was allocated. */
+ struct rte_mempool *pool; /**< Pool from which mbuf was allocated. */
+ };
+ };
/* second cache line - fields only used in slow path or on TX */
- RTE_MARKER cacheline1 __rte_cache_min_aligned;
-
-#if RTE_IOVA_IN_MBUF
- /**
- * Next segment of scattered packet. Must be NULL in the last
- * segment or in case of non-segmented packet.
- */
- struct rte_mbuf *next;
-#else
- /**
- * Reserved for dynamic fields
- * when the next pointer is in first cache line (i.e. RTE_IOVA_IN_MBUF is 0).
- */
- uint64_t dynfield2;
-#endif
-
- /* fields to support TX offloads */
+ __rte_marker(RTE_MARKER, cacheline1);
union {
- uint64_t tx_offload; /**< combined for easy fetch */
- __extension__
+ char mbuf_cacheline1[RTE_CACHE_LINE_MIN_SIZE];
struct {
- uint64_t l2_len:RTE_MBUF_L2_LEN_BITS;
- /**< L2 (MAC) Header Length for non-tunneling pkt.
- * Outer_L4_len + ... + Inner_L2_len for tunneling pkt.
+#if RTE_IOVA_IN_MBUF
+ /**
+ * Next segment of scattered packet. Must be NULL in the last
+ * segment or in case of non-segmented packet.
*/
- uint64_t l3_len:RTE_MBUF_L3_LEN_BITS;
- /**< L3 (IP) Header Length. */
- uint64_t l4_len:RTE_MBUF_L4_LEN_BITS;
- /**< L4 (TCP/UDP) Header Length. */
- uint64_t tso_segsz:RTE_MBUF_TSO_SEGSZ_BITS;
- /**< TCP TSO segment size */
-
- /*
- * Fields for Tx offloading of tunnels.
- * These are undefined for packets which don't request
- * any tunnel offloads (outer IP or UDP checksum,
- * tunnel TSO).
- *
- * PMDs should not use these fields unconditionally
- * when calculating offsets.
- *
- * Applications are expected to set appropriate tunnel
- * offload flags when they fill in these fields.
+ struct rte_mbuf *next;
+#else
+ /**
+ * Reserved for dynamic fields
+ * when the next pointer is in first cache line (i.e. RTE_IOVA_IN_MBUF is 0).
*/
- uint64_t outer_l3_len:RTE_MBUF_OUTL3_LEN_BITS;
- /**< Outer L3 (IP) Hdr Length. */
- uint64_t outer_l2_len:RTE_MBUF_OUTL2_LEN_BITS;
- /**< Outer L2 (MAC) Hdr Length. */
+ uint64_t dynfield2;
+#endif
- /* uint64_t unused:RTE_MBUF_TXOFLD_UNUSED_BITS; */
- };
- };
+ /* fields to support TX offloads */
+ union {
+ uint64_t tx_offload; /**< combined for easy fetch */
+ __extension__
+ struct {
+ uint64_t l2_len:RTE_MBUF_L2_LEN_BITS;
+ /**< L2 (MAC) Header Length for non-tunneling pkt.
+ * Outer_L4_len + ... + Inner_L2_len for tunneling pkt.
+ */
+ uint64_t l3_len:RTE_MBUF_L3_LEN_BITS;
+ /**< L3 (IP) Header Length. */
+ uint64_t l4_len:RTE_MBUF_L4_LEN_BITS;
+ /**< L4 (TCP/UDP) Header Length. */
+ uint64_t tso_segsz:RTE_MBUF_TSO_SEGSZ_BITS;
+ /**< TCP TSO segment size */
+
+ /*
+ * Fields for Tx offloading of tunnels.
+ * These are undefined for packets which don't request
+ * any tunnel offloads (outer IP or UDP checksum,
+ * tunnel TSO).
+ *
+ * PMDs should not use these fields unconditionally
+ * when calculating offsets.
+ *
+ * Applications are expected to set appropriate tunnel
+ * offload flags when they fill in these fields.
+ */
+ uint64_t outer_l3_len:RTE_MBUF_OUTL3_LEN_BITS;
+ /**< Outer L3 (IP) Hdr Length. */
+ uint64_t outer_l2_len:RTE_MBUF_OUTL2_LEN_BITS;
+ /**< Outer L2 (MAC) Hdr Length. */
+
+ /* uint64_t unused:RTE_MBUF_TXOFLD_UNUSED_BITS; */
+ };
+ };
- /** Shared data for external buffer attached to mbuf. See
- * rte_pktmbuf_attach_extbuf().
- */
- struct rte_mbuf_ext_shared_info *shinfo;
+ /** Shared data for external buffer attached to mbuf. See
+ * rte_pktmbuf_attach_extbuf().
+ */
+ struct rte_mbuf_ext_shared_info *shinfo;
- /** Size of the application private data. In case of an indirect
- * mbuf, it stores the direct mbuf private data size.
- */
- uint16_t priv_size;
+ /** Size of the application private data. In case of an indirect
+ * mbuf, it stores the direct mbuf private data size.
+ */
+ uint16_t priv_size;
- /** Timesync flags for use with IEEE1588. */
- uint16_t timesync;
+ /** Timesync flags for use with IEEE1588. */
+ uint16_t timesync;
- uint32_t dynfield1[9]; /**< Reserved for dynamic fields. */
+ uint32_t dynfield1[9]; /**< Reserved for dynamic fields. */
+ };
+ };
} __rte_cache_aligned;
+static_assert(alignof(struct rte_mbuf) == RTE_CACHE_LINE_SIZE, "alignof rte_mbuf");
+static_assert(offsetof(struct rte_mbuf, cacheline0) == 0, "cacheline0");
+static_assert(offsetof(struct rte_mbuf, cacheline1) == RTE_CACHE_LINE_MIN_SIZE, "cacheline1");
+static_assert(sizeof(struct rte_mbuf) == RTE_CACHE_LINE_MIN_SIZE * 2, "sizeof rte_mbuf");
+
/**
* Function typedef of callback to free externally attached buffer.
*/