- Sep 11, 2016
-
-
Mohamad Haj Yahia authored
Needed for lightweight and modular internal/pci error handling. Implement eswitch attach function which allocates/starts hw related resources. Implement eswitch detach function which releases/stops hw related resources. Init/cleanup function only handle eswitch software context allocation and destruction. Signed-off-by:
Mohamad Haj Yahia <mohamad@mellanox.com> Signed-off-by:
Saeed Mahameed <saeedm@mellanox.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Mohamad Haj Yahia authored
Needed for lightweight and modular internal/pci error handling. Implement sriov attach function which enables pre-saved number of vfs on the device side. Implement sriov detach function which disable the current vfs on the device side. Init/cleanup function only handles sriov software context allocation and destruction. Signed-off-by:
Mohamad Haj Yahia <mohamad@mellanox.com> Signed-off-by:
Saeed Mahameed <saeedm@mellanox.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Mohamad Haj Yahia authored
Gather all software context creating/destroying in one function and call it once in the first load and in the last unload. load/unload functions will now receive indication if we need to create/destroy the software contexts. In internal/pci error do the unload/load flows without releasing the software objects. In this way we perserve the sw core state and it help us restoring old driver state after PCI error/shutdown. Signed-off-by:
Mohamad Haj Yahia <mohamad@mellanox.com> Signed-off-by:
Saeed Mahameed <saeedm@mellanox.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Mohamad Haj Yahia authored
Add attach/detach callbacks to interface API. This is crucial for implementing seamless reset flow which releases the hardware and it's resources upon detach while keeping software structures and state (e.g netdev) then reset and reallocate the hardware needed resources upon attach. Signed-off-by:
Mohamad Haj Yahia <mohamad@mellanox.com> Signed-off-by:
Saeed Mahameed <saeedm@mellanox.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Mohamad Haj Yahia authored
Simplify the code and makes it look modular and symmetric. Split sriov enable/disable to two levels: device level and pci level. When user enable/disable sriov (via sriov_configure driver callback) we will enable/disable both device and pci sriov. When driver load/unload we will enable/disable (on demand) only device sriov while keeping the PCI sriov enabled for next driver load. On internal/pci error, VFs will be kept enabled on PCI and the reset is done only in device level. Signed-off-by:
Mohamad Haj Yahia <mohamad@mellanox.com> Signed-off-by:
Saeed Mahameed <saeedm@mellanox.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Mohamad Haj Yahia authored
In case of device in internal error state there is no need to wait for vf pages since they will be reclaimed manually later in the unload flow. Signed-off-by:
Mohamad Haj Yahia <mohamad@mellanox.com> Signed-off-by:
Saeed Mahameed <saeedm@mellanox.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
David S. Miller authored
Javier Martinez Canillas says: ==================== net: use IS_ENABLED() instead of checking for built-in or module This trivial series replace the open coding to check for a Kconfig symbol being built-in or module, with IS_ENABLED() macro that does exactly that. Using the macro makes the code more readable by helping abstract away some of the Kconfig built-in and module enable details. ==================== Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Javier Martinez Canillas authored
The IS_ENABLED() macro checks if a Kconfig symbol has been enabled either built-in or as a module, use that macro instead of open coding the same. Using the macro makes the code more readable by helping abstract away some of the Kconfig built-in and module enable details. Signed-off-by:
Javier Martinez Canillas <javier@osg.samsung.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Javier Martinez Canillas authored
The IS_ENABLED() macro checks if a Kconfig symbol has been enabled either built-in or as a module, use that macro instead of open coding the same. Using the macro makes the code more readable by helping abstract away some of the Kconfig built-in and module enable details. Signed-off-by:
Javier Martinez Canillas <javier@osg.samsung.com> Acked-by:
Neil Horman <nhorman@tuxdriver.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Javier Martinez Canillas authored
The IS_ENABLED() macro checks if a Kconfig symbol has been enabled either built-in or as a module, use that macro instead of open coding the same. Using the macro makes the code more readable by helping abstract away some of the Kconfig built-in and module enable details. Signed-off-by:
Javier Martinez Canillas <javier@osg.samsung.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Javier Martinez Canillas authored
The IS_ENABLED() macro checks if a Kconfig symbol has been enabled either built-in or as a module, use that macro instead of open coding the same. Using the macro makes the code more readable by helping abstract away some of the Kconfig built-in and module enable details. Signed-off-by:
Javier Martinez Canillas <javier@osg.samsung.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Javier Martinez Canillas authored
The IS_ENABLED() macro checks if a Kconfig symbol has been enabled either built-in or as a module, use that macro instead of open coding the same. Using the macro makes the code more readable by helping abstract away some of the Kconfig built-in and module enable details. Signed-off-by:
Javier Martinez Canillas <javier@osg.samsung.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Javier Martinez Canillas authored
The IS_ENABLED() macro checks if a Kconfig symbol has been enabled either built-in or as a module, use that macro instead of open coding the same. Using the macro makes the code more readable by helping abstract away some of the Kconfig built-in and module enable details. Signed-off-by:
Javier Martinez Canillas <javier@osg.samsung.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Javier Martinez Canillas authored
The IS_ENABLED() macro checks if a Kconfig symbol has been enabled either built-in or as a module, use that macro instead of open coding the same. Using the macro makes the code more readable by helping abstract away some of the Kconfig built-in and module enable details. Signed-off-by:
Javier Martinez Canillas <javier@osg.samsung.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Javier Martinez Canillas authored
The IS_ENABLED() macro checks if a Kconfig symbol has been enabled either built-in or as a module, use that macro instead of open coding the same. Using the macro makes the code more readable by helping abstract away some of the Kconfig built-in and module enable details. Signed-off-by:
Javier Martinez Canillas <javier@osg.samsung.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
David S. Miller authored
Christophe Leroy says: ==================== Optimisation of fs_enet ethernet driver This set optimises the freescale fs_enet ethernet driver: 1/ Merge of RX and TX NAPI functions in order to limit the amount of interrupts 2/ Do not unmap DMA when packets len is below copybreak, otherwise there is no benefit in copying the skb instead of allocating a new one 3/ Make copybreak value configurable as the optimised value is not the same on all targets ==================== Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Christophe Leroy authored
Measurement shows that on a MPC8xx running at 132MHz, the optimal limit is 112: * 114 bytes packets are processed in 147 TB ticks with higher copybreak * 114 bytes packets are processed in 148 TB ticks with lower copybreak * 128 bytes packets are processed in 154 TB ticks with higher copybreak * 128 bytes packets are processed in 148 TB ticks with lower copybreak * 238 bytes packets are processed in 172 TB ticks with higher copybreak * 238 bytes packets are processed in 148 TB ticks with lower copybreak However it might be different on other processors and/or frequencies. So it is useful to make it configurable. Signed-off-by:
Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Christophe Leroy authored
When the length of the packet is below the defined copybreak limit, the received packet is copied into a newly allocated skb in order to reuse the skb. This is only interesting if it allow us to avoid a new DMA mapping. We shall therefore not DMA unmap and remap the skb->data. Instead, we invalidate the cache with dma_sync_single_for_cpu() once the received data has been copied into the new skb. The following measures have been obtained on a mpc885 running at 132Mhz. Measurement is done using the timebase with packets sent to the target with 'ping -s 1' (packet len is 60): * Without this patch: 182 TB ticks * With this patch: 143 TB ticks As a comparison, if we set the copybreak limit to 0, then we get 148 TB ticks. It means that without this patch, duration is even worse when copying received data to a new skb instead of allocating a new skb for next packet to be received Signed-off-by:
Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Christophe Leroy authored
Initially, a NAPI TX routine has been implemented separately from NAPI RX, as done on the freescale/gianfar driver. By merging NAPI RX and NAPI TX, we reduce the amount of TX completion interrupts. Handling of the budget in association with TX interrupts is based on indications provided at https://wiki.linuxfoundation.org/networking/napi We never proceed more than the complete TX ring on a single run. At the same time, we fix an issue in the handling of fep->tx_free: It is only when fep->tx_free goes up to MAX_SKB_FRAGS that we need to wake up the queue. There is no need to call netif_wake_queue() at every packet successfully transmitted. Signed-off-by:
Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
David S. Miller authored
Hadar Hen Zion says: ==================== net/sched: ip tunnel metadata set/release/classify by using TC This patchset introduces ip tunnel manipulation support using the TC subsystem. In the decap flow, it enables the user to redirect packets from a shared tunnel device and classify by outer and inner headers. The outer headers are extracted from the metadata and used by the flower filter. A new action act_tunnel_key, releases the metadata. In the encap flow, act_tunnel_key creates a metadata object to be used by the shared tunnel device. The actual redirection to the tunnel device is done using act_mirred. For example: $ tc qdisc add dev vnet0 ingress $ tc filter add dev vnet0 protocol ip parent ffff: \ flower \ ip_proto 1 \ action tunnel_key set \ src_ip 11.11.0.1 \ dst_ip 11.11.0.2 \ id 11 \ action mirred egress redirect dev vxlan0 $ tc qdisc add dev vxlan0 ingress $ tc filter add dev vxlan0 protocol ip parent ffff: \ flower \ enc_src_ip 11.11.0.2 \ enc_dst_ip 11.11.0.1 \ enc_key_id 11 \ action tunnel_key release \ action mirred egress redirect dev vnet0 Amir & Hadar Changes from V6: - Add kfree_rcu to tunnel_key_release function - Use reverse Christmas tree order in tunnel_key_init function Changes from V5: - Add __rcu notation to struct tcf_tunnel_key_params in struct tcf_tunnel_key - Fix indentation in include/net/dst_metadata.h - Fix syntx error in commit message Changes from V4: - Fix tunnel_key_init function error flow. - Add 'action' variable to struct tcf_tunnel_key_params and use it instead of tcf_action variable which is not protected by rcu lock. Changes from V3: - Use percpu stats - No spinlock on datapatch - protecting parameters with rcu - Fix buggy handling of set/release dst - Use nla_get_in_addr and nla_put_in_addr - Fix change logs - Pass in6_addr by pointer - Rename utility functions to start with double underscore Changes from V2: - Use union in struct fl_flow_key for enc_ipv6 and enc_ipv4. - Rename functions _ip_tun_rx_dst and _ipv6_tun_rx_dst to _ip_tun_set_dst and _ipv6_tun_set_dst accordingly. - Remove local parameter 'encapdecap' from tunnel_key_init function. - Don't copy in6_addr values in tunnel_key_dump_addresses function, use pointers. Changes from V1: - More cleanups to key32_to_tunnel_id() and tunnel_id_to_key32() - IPv6 Support added - Set TUNNEL_KEY flag to make GRE work - Handle zero tunnel id properly in act_tunnel_key - Don't leave junk in decap action - Fix bug in act_tunnel_key initialization where (exists & ocr) is true - Remove BUG() from code - Rename action to tunnel_key - Improve grep-ability of code - Reuse code from ip_tun_rx_dst() and ipv6_tun_rx_dst() Changes from RFC: - Add a new action instead of making mirred too complex - No need to specify UDP port in action - it is already in the tunnel device configuration - Added a decap operation to drop tunnel metadata ==================== Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Amir Vadai authored
This action could be used before redirecting packets to a shared tunnel device, or when redirecting packets arriving from a such a device. The action will release the metadata created by the tunnel device (decap), or set the metadata with the specified values for encap operation. For example, the following flower filter will forward all ICMP packets destined to 11.11.11.2 through the shared vxlan device 'vxlan0'. Before redirecting, a metadata for the vxlan tunnel is created using the tunnel_key action and it's arguments: $ tc filter add dev net0 protocol ip parent ffff: \ flower \ ip_proto 1 \ dst_ip 11.11.11.2 \ action tunnel_key set \ src_ip 11.11.0.1 \ dst_ip 11.11.0.2 \ id 11 \ action mirred egress redirect dev vxlan0 Signed-off-by:
Amir Vadai <amir@vadai.me> Signed-off-by:
Hadar Hen Zion <hadarh@mellanox.com> Reviewed-by:
Shmulik Ladkani <shmulik.ladkani@gmail.com> Acked-by:
Jamal Hadi Salim <jhs@mojatatu.com> Acked-by:
Eric Dumazet <edumazet@google.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Amir Vadai authored
Introduce classifying by metadata extracted by the tunnel device. Outer header fields - source/dest ip and tunnel id, are extracted from the metadata when classifying. For example, the following will add a filter on the ingress Qdisc of shared vxlan device named 'vxlan0'. To forward packets with outer src ip 11.11.0.2, dst ip 11.11.0.1 and tunnel id 11. The packets will be forwarded to tap device 'vnet0' (after metadata is released): $ tc filter add dev vxlan0 protocol ip parent ffff: \ flower \ enc_src_ip 11.11.0.2 \ enc_dst_ip 11.11.0.1 \ enc_key_id 11 \ dst_ip 11.11.11.1 \ action tunnel_key release \ action mirred egress redirect dev vnet0 The action tunnel_key, will be introduced in the next patch in this series. Signed-off-by:
Amir Vadai <amir@vadai.me> Signed-off-by:
Hadar Hen Zion <hadarh@mellanox.com> Acked-by:
Jiri Pirko <jiri@mellanox.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Amir Vadai authored
Extract __ip_tun_set_dst() and __ipv6_tun_set_dst() out of ip_tun_rx_dst() and ipv6_tun_rx_dst(), to be used without supplying an skb. Signed-off-by:
Amir Vadai <amir@vadai.me> Signed-off-by:
Hadar Hen Zion <hadarh@mellanox.com> Acked-by:
Jiri Pirko <jiri@mellanox.com> Reviewed-by:
Shmulik Ladkani <shmulik.ladkani@gmail.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Amir Vadai authored
Add utility functions to convert a 32 bits key into a 64 bits tunnel and vice versa. These functions will be used instead of cloning code in GRE and VXLAN, and in tc act_iptunnel which will be introduced in a following patch in this patchset. Signed-off-by:
Amir Vadai <amir@vadai.me> Signed-off-by:
Hadar Hen Zion <hadarh@mellanox.com> Reviewed-by:
Shmulik Ladkani <shmulik.ladkani@gmail.com> Acked-by:
Jiri Benc <jbenc@redhat.com> Acked-by:
Jiri Pirko <jiri@mellanox.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
- Sep 10, 2016
-
-
Markus Elfring authored
* Multiplications for the size determination of memory allocations indicated that array data structures should be processed. Thus use the corresponding function "kmalloc_array". This issue was detected by using the Coccinelle software. * Replace the specification of data types by pointer dereferences to make the corresponding size determination a bit safer according to the Linux coding style convention. Signed-off-by:
Markus Elfring <elfring@users.sourceforge.net> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
David S. Miller authored
Tobias Regnery says: ==================== alx: add msi-x support This patchset adds msi-x support to the alx driver. It is a preparatory series for multi queue support, which I am currently working on. As there is no advantage over msi interrupts without multi queue support, msi-x interrupts are disabled by default. In order to test for regressions, a new module parameter is added to enable msi-x interrupts. Based on information of the downstream driver at github.com/qca/alx ==================== Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Tobias Regnery authored
msi-x support is default disabled in the alx driver. In order to test msi-x interrupts for regressions add a module parameter to the driver. Signed-off-by:
Tobias Regnery <tobias.regnery@gmail.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Tobias Regnery authored
Add msi-x support to the alx driver. This is in preparation for multi queue support. msi-x interrupts are disabled by default because without multi queue support there is no advantage over msi interrupts. The performance numbers observed with iperf stay the same. Based on information of the downstream driver at github.com/qca/alx Signed-off-by:
Tobias Regnery <tobias.regnery@gmail.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Tobias Regnery authored
Factor out the handling of misc interrupts into a new function. This function can be reused later for msi-x interrupts. Signed-off-by:
Tobias Regnery <tobias.regnery@gmail.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Tobias Regnery authored
Introduce a new flag field for the advanced interrupt capatibilities and add new functions to enable and disable msi interrupts. These functions will be extended later to cover msi-x interrupts. We enable msi interrupts earlier in alx_init_intr because with msi-x and multi queue support the number of queues must be set before we allocate resources for the rx and tx paths. Signed-off-by:
Tobias Regnery <tobias.regnery@gmail.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Baoyou Xie authored
We get a few warnings when building kernel with W=1: drivers/net/ethernet/qlogic/qed/qed_l2.c:112:5: warning: no previous prototype for 'qed_sp_vport_start' [-Wmissing-prototypes] drivers/net/ethernet/qlogic/qed/qed_sriov.c:110:6: warning: no previous prototype for 'qed_iov_is_valid_vfid' [-Wmissing-prototypes] drivers/net/ethernet/qlogic/qed/qed_sriov.c:188:5: warning: no previous prototype for 'qed_iov_post_vf_bulletin' [-Wmissing-prototypes] drivers/net/ethernet/qlogic/qed/qed_sriov.c:578:6: warning: no previous prototype for 'qed_iov_set_vfs_to_disable' [-Wmissing-prototypes] drivers/net/ethernet/qlogic/qed/qed_sriov.c:1135:28: warning: no previous prototype for 'qed_iov_get_public_vf_info' [-Wmissing-prototypes] drivers/net/ethernet/qlogic/qed/qed_sriov.c:1148:6: warning: no previous prototype for 'qed_iov_clean_vf' [-Wmissing-prototypes] drivers/net/ethernet/qlogic/qed/qed_sriov.c:2444:5: warning: no previous prototype for 'qed_iov_chk_ucast' [-Wmissing-prototypes] drivers/net/ethernet/qlogic/qed/qed_sriov.c:2762:5: warning: no previous prototype for 'qed_iov_vf_flr_cleanup' [-Wmissing-prototypes] .... In fact, these functions are only used in the file in which they are declared and don't need a declaration, but can be made static. so this patch marks these functions with 'static'. Signed-off-by:
Baoyou Xie <baoyou.xie@linaro.org> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
David S. Miller authored
Daniel Borkmann says: ==================== Some BPF helper cleanups This series contains a couple of misc cleanups and improvements for BPF helpers. For details please see individual patches. We let this also sit for a few days with Fengguang's kbuild test robot, and there were no issues seen (besides one false positive, see last one for details). ==================== Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Daniel Borkmann authored
This work adds BPF_CALL_<n>() macros and converts all the eBPF helper functions to use them, in a similar fashion like we do with SYSCALL_DEFINE<n>() macros that are used today. Motivation for this is to hide all the register handling and all necessary casts from the user, so that it is done automatically in the background when adding a BPF_CALL_<n>() call. This makes current helpers easier to review, eases to write future helpers, avoids getting the casting mess wrong, and allows for extending all helpers at once (f.e. build time checks, etc). It also helps detecting more easily in code reviews that unused registers are not instrumented in the code by accident, breaking compatibility with existing programs. BPF_CALL_<n>() internals are quite similar to SYSCALL_DEFINE<n>() ones with some fundamental differences, for example, for generating the actual helper function that carries all u64 regs, we need to fill unused regs, so that we always end up with 5 u64 regs as an argument. I reviewed several 0-5 generated BPF_CALL_<n>() variants of the .i results and they look all as expected. No sparse issue spotted. We let this also sit for a few days with Fengguang's kbuild test robot, and there were no issues seen. On s390, it barked on the "uses dynamic stack allocation" notice, which is an old one from bpf_perf_event_output{,_tp}() reappearing here due to the conversion to the call wrapper, just telling that the perf raw record/frag sits on stack (gcc with s390's -mwarn-dynamicstack), but that's all. Did various runtime tests and they were fine as well. All eBPF helpers are now converted to use these macros, getting rid of a good chunk of all the raw castings. Signed-off-by:
Daniel Borkmann <daniel@iogearbox.net> Acked-by:
Alexei Starovoitov <ast@kernel.org> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Daniel Borkmann authored
When fetching ifindex, we don't need to test dev for being NULL since we're always guaranteed to have a valid dev for clsact programs. Thus, avoid this test in fast path. Signed-off-by:
Daniel Borkmann <daniel@iogearbox.net> Acked-by:
Alexei Starovoitov <ast@kernel.org> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Daniel Borkmann authored
Add BPF_SIZEOF() and BPF_FIELD_SIZEOF() macros to improve the code a bit which otherwise often result in overly long bytes_to_bpf_size(sizeof()) and bytes_to_bpf_size(FIELD_SIZEOF()) lines. So place them into a macro helper instead. Moreover, we currently have a BUILD_BUG_ON(BPF_FIELD_SIZEOF()) check in convert_bpf_extensions(), but we should rather make that generic as well and add a BUILD_BUG_ON() test in all BPF_SIZEOF()/BPF_FIELD_SIZEOF() users to detect any rewriter size issues at compile time. Note, there are currently none, but we want to assert that it stays this way. Signed-off-by:
Daniel Borkmann <daniel@iogearbox.net> Acked-by:
Alexei Starovoitov <ast@kernel.org> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Daniel Borkmann authored
Some minor misc cleanups, f.e. use sizeof(__u32) instead of hardcoding and in __bpf_skb_max_len(), I missed that we always have skb->dev valid anyway, so we can drop the unneeded test for dev; also few more other misc bits addressed here. Signed-off-by:
Daniel Borkmann <daniel@iogearbox.net> Acked-by:
Alexei Starovoitov <ast@kernel.org> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Eric Dumazet authored
If skb has a valid l4 hash, there is no point clearing hash and force a further flow dissection when a tunnel encapsulation is added. Signed-off-by:
Eric Dumazet <edumazet@google.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Markus Elfring authored
* Multiplications for the size determination of memory allocations indicated that array data structures should be processed. Thus use the corresponding function "kmalloc_array". This issue was detected by using the Coccinelle software. * Replace the specification of data types by pointer dereferences to make the corresponding size determination a bit safer according to the Linux coding style convention. Signed-off-by:
Markus Elfring <elfring@users.sourceforge.net> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Markus Elfring authored
* A multiplication for the size determination of a memory allocation indicated that an array data structure should be processed. Thus use the corresponding function "kmalloc_array". This issue was detected by using the Coccinelle software. * Replace the specification of a data structure by a pointer dereference to make the corresponding size determination a bit safer according to the Linux coding style convention. Signed-off-by:
Markus Elfring <elfring@users.sourceforge.net> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
David S. Miller authored
Merge tag 'rxrpc-rewrite-20160908' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs David Howells says: ==================== rxrpc: Rewrite data and ack handling This patch set constitutes the main portion of the AF_RXRPC rewrite. It consists of five fix/helper patches: (1) Fix ASSERTCMP's and ASSERTIFCMP's handling of signed values. (2) Update some protocol definitions slightly. (3) Use of an hlist for RCU purposes. (4) Removal of per-call sk_buff accounting (not really needed when skbs aren't being queued on the main queue). (5) Addition of a tracepoint to log incoming packets in the data_ready callback and to log the end of the data_ready callback. And then there are two patches that form the main part: (6) Preallocation of resources for incoming calls so that in patch (7) the data_ready handler can be made to fully instantiate an incoming call and make it live. This extends through into AFS so that AFS can preallocate its own incoming call resources. The preallocation size is capped at the listen() backlog setting - and that is capped at a sysctl limit which can be set between 4 and 32. The preallocation is (re)charged either by accepting/rejecting pending calls or, in the case of AFS, manually. If insufficient preallocation resources exist, a BUSY packet will be transmitted. The advantage of using this preallocation is that once a call is set up in the data_ready handler, DATA packets can be queued on it immediately rather than the DATA packets being queued for a background work item to do all the allocation and then try and sort out the DATA packets whilst other DATA packets may still be coming in and going either to the background thread or the new call. (7) Rewrite the handling of DATA, ACK and ABORT packets. In the receive phase, DATA packets are now held in per-call circular buffers with deduplication, out of sequence detection and suchlike being done in data_ready. Since there is only one producer and only once consumer, no locks need be used on the receive queue. Received ACK and ABORT packets are now parsed and discarded in data_ready to recycle resources as fast as possible. sk_buffs are no longer pulled, trimmed or cloned, but rather the offset and size of the content is tracked. This particularly affects jumbo DATA packets which need insertion into the receive buffer in multiple places. Annotations are kept to track which bit is which. Packets are no longer queued on the socket receive queue; rather, calls are queued. Dummy packets to convey events therefore no longer need to be invented and metadata packets can be discarded as soon as parsed rather then being pushed onto the socket receive queue to indicate terminal events. The preallocation facility added in (6) is now used to set up incoming calls with very little locking required and no calls to the allocator in data_ready. Decryption and verification is now handled in recvmsg() rather than in a background thread. This allows for the future possibility of decrypting directly into the user buffer. With this patch, the code is a lot simpler and most of the mass of call event and state wangling code in call_event.c is gone. With this, the majority of the AF_RXRPC rewrite is complete. However, there are still things to be done, including: (*) Limit the number of active service calls to prevent an attacker from filling up a server's memory. (*) Limit the number of calls on the rebuff-with-BUSY queue. (*) Transmit delayed/deferred ACKs from recvmsg() if possible, rather than punting to the background thread. Ideally, the background thread shouldn't run at all, but data_ready can't call kernel_sendmsg() and we can't rely on recvmsg() attending to the call in a timely fashion. (*) Prevent the call at the front of the socket queue from hogging recvmsg()'s attention if there's a sufficiently continuous supply of data. (*) Distribute ICMP errors by connection rather than by call. Possibly parse the ICMP packet to try and pin down the exact connection and call. (*) Encrypt/decrypt directly between user buffers and socket buffers where possible. (*) IPv6. (*) Service ID upgrade. This is a facility whereby a special flag bit is set in the DATA packet header when making a call that tells the server that it is allowed to change the service ID to an upgraded one and reply with an equivalent call from the upgraded service. This is used, for example, to override certain AFS calls so that IPv6 addresses can be returned. (*) Allow userspace to preallocate call user IDs for incoming calls. ==================== Signed-off-by:
David S. Miller <davem@davemloft.net>
-