summaryrefslogtreecommitdiffstats
path: root/src/vlib/buffer_funcs.h
AgeCommit message (Collapse)AuthorFilesLines
2019-01-31buffers: reinitialize metadata, add additional validationDamjan Marion1-13/+43
- DPDK overwrites metadata as part of rte_pktmbuf_init(...) so we need reinitialize it - additional checks added to ensure ref_count is never < 1 Change-Id: Ida336f81c4723e8f2e0ad4a70cb7b1ecfff978a0 Signed-off-by: Damjan Marion <damarion@cisco.com>
2019-01-30buffers: major cleanup and improvementsDamjan Marion1-187/+329
This patch introduces following changes: - deprecated free lists which are not used and not compatible with external buffer managers (i.e. DPDK) - introduces native support for per-numa buffer pools - significantly improves performance of buffer alloc and free Change-Id: I4a8e723ae47056717afd6cac0efe87cb731b5be7 Signed-off-by: Damjan Marion <damarion@cisco.com>
2019-01-29Fix error while compiling using 'vlib/vlib.h' dependencie.Dmitry Vakhrushev1-0/+2
This variable without any needed 'define' becoming unused. Change-Id: I661a75a78dba03abb861ed918ad1e634a8ecd0af Signed-off-by: Dmitry Vakhrushev <dmitry@netgate.com>
2019-01-24buffers: fix vector typesDamjan Marion1-1/+3
Change-Id: I9df96264e30806ac3daf7121f314f34f06232413 Signed-off-by: Damjan Marion <damjan.marion@gmail.com>
2019-01-23buffers: wrap vlib_buffer_t to union and expose vector typesDamjan Marion1-1/+12
Change-Id: I1c12e2941cae198ededbb65eb5be51a4eabe2c1b Signed-off-by: Damjan Marion <damarion@cisco.com>
2019-01-20buffers: remove VLIB_BUFFER_DEFAULT_FREE_LIST macro and fl->n_data_bytesDamjan Marion1-33/+3
Change-Id: I0ba5175be077c40556f2a3ce629c5bbcd71e0a81 Signed-off-by: Damjan Marion <damarion@cisco.com>
2019-01-20buffers: remove vlib_buffer_delete_free_listDamjan Marion1-16/+0
Change-Id: I5fe01e918b534d1ac1d47f0d7610536f45c3158c Signed-off-by: Damjan Marion <damarion@cisco.com>
2019-01-20buffers: don't init metadata, as it is already initializedDamjan Marion1-38/+1
Change-Id: Ia083050389853c25b069f0f8286d50d3f4aef527 Signed-off-by: Damjan Marion <damarion@cisco.com>
2019-01-20buffers: keep buffer_main in vlib_main_tDamjan Marion1-14/+22
Change-Id: I3bb1d9f83dd08f4b93acd4a281bfec0674e39c2e Signed-off-by: Damjan Marion <damarion@cisco.com>
2019-01-19buffers: remove free-list information from buffer metadataDamjan Marion1-45/+6
Change-Id: I6048c6a51efa826ac333f7d15919cb87dd766d74 Signed-off-by: Damjan Marion <damarion@cisco.com>
2019-01-18buffers: remove freelist argument from vlib_buffer_add_dataDamjan Marion1-3/+2
Change-Id: Idb224b807373128b78dc46f177b2d2e0ed288349 Signed-off-by: Damjan Marion <damarion@cisco.com>
2019-01-18Add vlib_buffer_copy_indices inline functionDamjan Marion1-2/+8
This reverts commit 1e59f9ddbdda14591967e1d66eab8623f9ba58e4. Change-Id: Iae1d372b887e170d28cac2fe4c61325ee5a5894a Signed-off-by: Damjan Marion <damarion@cisco.com>
2019-01-18deprecate clib_memcpy64_x4Damjan Marion1-6/+7
Storing buffer in local template seems to be better option.... Change-Id: I1a2fdd68cb956f99a5b36d2cd810fc623e089bcf Signed-off-by: Damjan Marion <damarion@cisco.com>
2019-01-07Handle buffer alloc failure in vlib_buffer_add_dataDave Barach1-2/+2
It's not OK to crash due to a transient buffer allocation failure. Return 1 if the requested operation failed, otherwise 0. Buffer index parameter change to a value-result, so the caller can differentiate between partial and complete allocation failure: callers which request an initial allocation (inbound bi = ~0) need to check the (out) value to decide whether or not to call vlib_buffer_free(...). Change-Id: I03029d7f2714c17dca4630dfd95a1eb578b68384 Signed-off-by: Dave Barach <dave@barachs.net>
2019-01-01buffers: remove unused codeDamjan Marion1-77/+2
Change-Id: If2bbfbc52994f5de0879763e0b7a7864498debb6 Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-12-13fix vlib_buffer_chain_compress assert in debugKlement Sekera1-1/+2
replace vlib_buffer_advance with its code to work around assert Change-Id: I6e332527f5e0c10d23305b6fc2e837d8b4f99e78 Signed-off-by: Klement Sekera <ksekera@cisco.com>
2018-11-20dhcp4:(VPP-1483) linearize chained packets before handlingEyal Bari1-0/+64
dhcp packets might (when flooded) arrive in chains of cloned buffers Change-Id: Ifddecd656b6a5d6ba8cd94184f5c021684e35548 Signed-off-by: Eyal Bari <ebari@cisco.com>
2018-11-14Remove c-11 memcpy checks from perf-critical codeDave Barach1-22/+22
Change-Id: Id4f37f5d4a03160572954a416efa1ef9b3d79ad1 Signed-off-by: Dave Barach <dave@barachs.net>
2018-11-13vlib:remove unused argumentEyal Bari1-3/+1
Change-Id: I88c3d3e516401bb1c84991515cd701c156ae19dd Signed-off-by: Eyal Bari <ebari@cisco.com>
2018-10-23Numa-aware, growable physical memory allocator (pmalloc)Damjan Marion1-4/+1
Change-Id: Ic4c46bc733afae8bf0d8146623ed15633928de30 Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-10-22vlib: introduce vlib_buffer_get_{pa,va,current_va,current_pa} inlinesDamjan Marion1-5/+8
Change-Id: I0b42ac6b05bc9910904a97924ea4bebc84507d4d Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-10-19vppinfra: add atomic macros for __sync builtinsSirshak Das1-3/+3
This is first part of addition of atomic macros with only macros for __sync builtins. - Based on earlier patch by Damjan (https://gerrit.fd.io/r/#/c/10729/) Additionally - clib_atomic_release macro added and used in the absence of any memory barrier. - clib_atomic_bool_cmp_and_swap added Change-Id: Ie4e48c1e184a652018d1d0d87c4be80ddd180a3b Original-patch-by: Damjan Marion <damarion@cisco.com> Signed-off-by: Sirshak Das <sirshak.das@arm.com> Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com> Reviewed-by: Ola Liljedahl <ola.liljedahl@arm.com> Reviewed-by: Steve Capper <steve.capper@arm.com>
2018-10-01API / CLI event-log tracingDave Barach1-0/+1
Add an "elog trace [api][cli][barrier]" debug CLI command. Removed the barrier elog test command. Remove unused reliable multicast code. Change-Id: Ib3ecde901b7c49fe92b313d0087cd7e776adcdce Signed-off-by: Dave Barach <dave@barachs.net>
2018-09-12Add and enable u32x4_extend_to_u64x2_high for aarch64 NEON intrinsics.Sirshak Das1-1/+5
This is the high version of extendto. This function accomplishes the same task as both shuffling and extending done by SSE intrinsics. This enables the NEON version for buffer indexes to buffer pointer translation. Change-Id: I52d7bbf3d76ba69c9acb0e518ff4bc6abf3bbbd4 Signed-off-by: Sirshak Das <sirshak.das@arm.com> Reviewed-by: Steve Capper <steve.capper@arm.com> Reviewed-by: Yi He <yi.he@arm.com> Verified-by: Lijian Zhang <lijian.zhang@arm.com>
2018-07-27128-bit SIMD version of vlib_get_buffersDamjan Marion1-0/+8
Change-Id: I1a28ddf535c80ecf4ba4bf31659ff2fead1d8a64 Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-07-23Buffer clone: copy opaque2Neale Ranns1-0/+2
Change-Id: I06e1dbfa0782bc03f2d0e77295b38b4fde7df35e Signed-off-by: Neale Ranns <nranns@cisco.com>
2018-06-09Fix bug in vlib_buffer_free_from_ring_no_nextDamjan Marion1-1/+1
Change-Id: I332bb4578d1a3c79770985bf1f315d2ed823a3e5 Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-05-31fix missing void pointer explicit type castZhiyong Yang1-1/+1
Change-Id: I5098e5d966abc44db045783883424b63083f08ee Signed-off-by: Zhiyong Yang <zhiyong.yang@intel.com>
2018-05-29Fixed vlib_buffer_clone with stale chained buffersYoann Desmouceaux1-2/+7
When calling vlib_buffer_clone() on a source vlib_buffer with no next buffer but whose total_length_not_including_first_buffer hadn't been properly zeroed out, the total_length_not_including_first_buffer of the clone was set to a wrong value. (see https://lists.fd.io/g/vpp-dev/topic/19869395) Change-Id: I4b503ece804e3933bb259be4c2148f84dafbea3e Signed-off-by: Yoann Desmouceaux <ydesmouc@cisco.com>
2018-05-17Add buffer pointer-to-index and index-to-pointer array functionsDamjan Marion1-0/+143
Change-Id: Ib3fcc3ceb7f315389bcdecbb7d9632540a5dd6ba Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-04-04memif: zero copy slaveDamjan Marion1-0/+24
Change-Id: I65306fb1f8e39221dd1d8c00737a7fb1c0129ba8 Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-03-14vlib: internal buffer manager reworkDamjan Marion1-45/+19
- buffer_main is no longer part of vlib_main_t - pool of free lists is still part of vlib_main_t - mheap is not used anymore for buffer allocation - simple bitmap bassed buffer alloc scheme is introduced Change-Id: I3e1e6d00e2c8122293ed0a741245eb841315a1ff Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-03-06vlib: avoid crash if fill_free_list returns 0 buffersDamjan Marion1-1/+2
Change-Id: If1284696e10df71b4029191b5e3adb32c21c0c5f Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-02-26vlib: add vlib_buffer_free_from_ringDamjan Marion1-0/+26
Change-Id: I63f7b14cd63eac9e64cace5d941190096ad148dc Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-02-07Refactor vlib_buffer flagsDamjan Marion1-68/+45
Change-Id: I853386aebfe488ebb10328435b81b6e3403c5dd0 Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-02-02vlib_buffer_clone: allow client to request the maximum number of clones; 256Neale Ranns1-12/+50
Change-Id: Id96dc5d86719546268b50a9999a06387d2d9075c Signed-off-by: Neale Ranns <neale.ranns@cisco.com>
2018-02-01IPv4/6 reassemblyKlement Sekera1-0/+62
Change-Id: Ic5dcadd13c88b8a5e7896dab82404509c081614a Signed-off-by: Klement Sekera <ksekera@cisco.com>
2018-01-31vlib: allocating buffers on thread-x and freeing them on thread-y causesSteven1-5/+5
a crash on debug image (VPP-1151) In debug image, there is extra code to validate the buffer when it is freed. It uses the hash table to lookup the buffer index with spinlock to prevent contention. However, there is one spinlock for each worker thread. So allocating the buffer on thread-x and freeing the same buffer on thread-y causes the validation to fail on thread-y. The fix is to have only one spinlock, stored in vlib_global_main. Change-Id: Ic383846cefe84a3e262255afcf82276742f0f62e Signed-off-by: Steven <sluong@cisco.com> (cherry picked from commit a7effa1b072463f12305a474f082aeaffb7ada4b)
2018-01-18vlib: add vlib_buffer_alloc_to_ring APIDamjan Marion1-0/+29
Change-Id: I4e2804754b443f5f41fb25eed8334908c4a70f84 Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-12-09vlib: PCI rework to support VFIODamjan Marion1-7/+5
Also fixes old ixge driver, so it works with recent physmem changes and vfio. Change-Id: Id4be74b34daed47cd281a77eec43d6692340d882 Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-11-27vlib: make vlib_buffer_alloc inline functionDamjan Marion1-21/+59
Currently, every alloc involves callback function call. With this change callback function is called only if there is no empty buffers on the free list. Change-Id: I2238c19ece7ce182c49ba0f2485add52f335f3b6 Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-11-09buffers: fix bug in free list n_alloc trackingKlement Sekera1-0/+1
This change avoids hitting ASSERT (vec_len (f->buffers) == f->n_alloc); in vlib_buffer_delete_free_list_internal by updating vlib_buffer_free_list_t->n_alloc in case when buffers are removed from the free list due to overfill. Change-Id: Id60fa97e8cb0f02ef529b05816265a57a4e7d998 Signed-off-by: Klement Sekera <ksekera@cisco.com>
2017-10-25vlib: add support for multiple buffer poolsDamjan Marion1-1/+4
Change-Id: Icaf7d7ad47284aea7a56e8006b69f45874d64202 Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-09-07vlib physmem reworkDamjan Marion1-38/+1
This patch adds supprot support for multiple numa-aware physmem regions. Change-Id: I5c69a6f4da33c8ee21bdb8604d52fd2886f2327e Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-08-30Thread safe internal buffer manager, take twoDamjan Marion1-4/+7
First attempt to make internal buffer manager thread safe was not succesfull, so trying again. This time with more testing. Change-Id: I01b8385a9c26d233934a3339255ea4bd31c865ac Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-08-11Fix tcp multi buffer segments retransmissionFlorin Coras1-1/+6
- Fix tcp/udp sw checksum computation - Fix allocation of multi buffer tcp segments for retransmits - Send FIN only if/when tx fifo is empty Change-Id: I2e43a14b87a72c9e547b4339b9a51811cf5732c4 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-07-27Thread safe internal buffer managerDamjan Marion1-2/+13
Change-Id: I45845b952aa42a854e1c2c396b85f905de987020 Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-07-14Introduce l{2,3,4}_hdr_offset fields in the buffer metadataDamjan Marion1-14/+36
To save space in the first cacheline following is changed: - total_length_not_including_first_buffer moved to the 2nd cacheline. This field is used only when VLIB_BUFFER_TOTAL_LENGTH_VALID and VLIB_BUFFER_NEXT_PRESENT are both set. - free_list_index is now stored in 4bits inside flags, which allows up to 16 free lists. In case we need more we can store index in the 2nd cachelin Change-Id: Ic8521350819391af470d31d3fa1013e67ecb7681 Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-07-13dpdk: fix dpdk_buffer_pool_create nameChris Luke1-3/+0
- vnet_buffer_pool_create should probably be named dpdk_buffer_pool_create since that is what it does. - Its prototype should also be in a DPDK plugin header, not in vlib/buffer_funcs.h, since the implementation is in the plugin and nobody else should be calling it. Change-Id: I7ba259afa4b888bc94f3ad257305e286b41e7370 Signed-off-by: Chris Luke <chrisy@flirble.org>
2017-07-10vlib: store buffer memory information in the buffer_mainDamjan Marion1-3/+10
Currently, buffer index is calculated as a offset to the physmem region shifted by log2_cacheline size. When DPDK is used we "hack" physmem data with information taken from dpdk mempool. This makes physmem code not usable with DPDK. This change makes buffer memory start and size independent of physmem basically allowing physmem to be used when DPDK plugin is loaded. Change-Id: Ieb399d398f147583b9baab467152a352d58c9c31 Signed-off-by: Damjan Marion <damarion@cisco.com>