- 27 Apr, 2021 4 commits
-
-
Andrii Nakryiko authored
Negative field existence cases for have a broken assumption that FIELD_EXISTS CO-RE relo will fail for fields that match the name but have incompatible type signature. That's not how CO-RE relocations generally behave. Types and fields that match by name but not by expected type are treated as non-matching candidates and are skipped. Error later is reported if no matching candidate was found. That's what happens for most relocations, but existence relocations (FIELD_EXISTS and TYPE_EXISTS) are more permissive and they are designed to return 0 or 1, depending if a match is found. This allows to handle name-conflicting but incompatible types in BPF code easily. Combined with ___flavor suffixes, it's possible to handle pretty much any structural type changes in kernel within the compiled once BPF source code. So, long story short, negative field existence test cases are invalid in their assumptions, so this patch reworks them into a single consolidated positive case that doesn't match any of the fields. Fixes: c7566a69 ("selftests/bpf: Add field existence CO-RE relocs tests") Reported-by:
Lorenz Bauer <lmb@cloudflare.com> Signed-off-by:
Andrii Nakryiko <andrii@kernel.org> Signed-off-by:
Alexei Starovoitov <ast@kernel.org> Acked-by:
-
Andrii Nakryiko authored
Fix BPF_CORE_READ_BITFIELD() macro used for reading CO-RE-relocatable bitfields. Missing breaks in a switch caused 8-byte reads always. This can confuse libbpf because it does strict checks that memory load size corresponds to the original size of the field, which in this case quite often would be wrong. After fixing that, we run into another problem, which quite subtle, so worth documenting here. The issue is in Clang optimization and CO-RE relocation interactions. Without that asm volatile construct (also known as barrier_var()), Clang will re-order BYTE_OFFSET and BYTE_SIZE relocations and will apply BYTE_OFFSET 4 times for each switch case arm. This will result in the same error from libbpf about mismatch of memory load size and original field size. I.e., if we were reading u32, we'd still have *(u8 *), *(u16 *), *(u32 *), and *(u64 *) memory loads, three of which will fail. Using barrier_var() forces Clang to apply BYTE_OFFSET relocation first (and once) to calculate p, after which value of p is used without relocation in each of switch case arms, doing appropiately-sized memory load. Here's the list of relevant relocations and pieces of generated BPF code before and after this patch for test_core_reloc_bitfields_direct selftests. BEFORE ===== #45: core_reloc: insn #160 --> [5] + 0:5: byte_sz --> struct core_reloc_bitfields.u32 #46: core_reloc: insn #167 --> [5] + 0:5: byte_off --> struct core_reloc_bitfields.u32 #47: core_reloc: insn #174 --> [5] + 0:5: byte_off --> struct core_reloc_bitfields.u32 #48: core_reloc: insn #178 --> [5] + 0:5: byte_off --> struct core_reloc_bitfields.u32 #49: core_reloc: insn #182 --> [5] + 0:5: byte_off --> struct core_reloc_bitfields.u32 157: 18 02 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r2 = 0 ll 159: 7b 12 20 01 00 00 00 00 *(u64 *)(r2 + 288) = r1 160: b7 02 00 00 04 00 00 00 r2 = 4 ; BYTE_SIZE relocation here ^^^ 161: 66 02 07 00 03 00 00 00 if w2 s> 3 goto +7 <LBB0_63> 162: 16 02 0d 00 01 00 00 00 if w2 == 1 goto +13 <LBB0_65> 163: 16 02 01 00 02 00 00 00 if w2 == 2 goto +1 <LBB0_66> 164: 05 00 12 00 00 00 00 00 goto +18 <LBB0_69> 0000000000000528 <LBB0_66>: 165: 18 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r1 = 0 ll 167: 69 11 08 00 00 00 00 00 r1 = *(u16 *)(r1 + 8) ; BYTE_OFFSET relo here w/ WRONG size ^^^^^^^^^^^^^^^^ 168: 05 00 0e 00 00 00 00 00 goto +14 <LBB0_69> 0000000000000548 <LBB0_63>: 169: 16 02 0a 00 04 00 00 00 if w2 == 4 goto +10 <LBB0_67> 170: 16 02 01 00 08 00 00 00 if w2 == 8 goto +1 <LBB0_68> 171: 05 00 0b 00 00 00 00 00 goto +11 <LBB0_69> 0000000000000560 <LBB0_68>: 172: 18 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r1 = 0 ll 174: 79 11 08 00 00 00 00 00 r1 = *(u64 *)(r1 + 8) ; BYTE_OFFSET relo here w/ WRONG size ^^^^^^^^^^^^^^^^ 175: 05 00 07 00 00 00 00 00 goto +7 <LBB0_69> 0000000000000580 <LBB0_65>: 176: 18 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r1 = 0 ll 178: 71 11 08 00 00 00 00 00 r1 = *(u8 *)(r1 + 8) ; BYTE_OFFSET relo here w/ WRONG size ^^^^^^^^^^^^^^^^ 179: 05 00 03 00 00 00 00 00 goto +3 <LBB0_69> 00000000000005a0 <LBB0_67>: 180: 18 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r1 = 0 ll 182: 61 11 08 00 00 00 00 00 r1 = *(u32 *)(r1 + 8) ; BYTE_OFFSET relo here w/ RIGHT size ^^^^^^^^^^^^^^^^ 00000000000005b8 <LBB0_69>: 183: 67 01 00 00 20 00 00 00 r1 <<= 32 184: b7 02 00 00 00 00 00 00 r2 = 0 185: 16 02 02 00 00 00 00 00 if w2 == 0 goto +2 <LBB0_71> 186: c7 01 00 00 20 00 00 00 r1 s>>= 32 187: 05 00 01 00 00 00 00 00 goto +1 <LBB0_72> 00000000000005e0 <LBB0_71>: 188: 77 01 00 00 20 00 00 00 r1 >>= 32 AFTER ===== #30: core_reloc: insn #132 --> [5] + 0:5: byte_off --> struct core_reloc_bitfields.u32 #31: core_reloc: insn #134 --> [5] + 0:5: byte_sz --> struct core_reloc_bitfields.u32 129: 18 02 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r2 = 0 ll 131: 7b 12 20 01 00 00 00 00 *(u64 *)(r2 + 288) = r1 132: b7 01 00 00 08 00 00 00 r1 = 8 ; BYTE_OFFSET relo here ^^^ ; no size check for non-memory dereferencing instructions 133: 0f 12 00 00 00 00 00 00 r2 += r1 134: b7 03 00 00 04 00 00 00 r3 = 4 ; BYTE_SIZE relocation here ^^^ 135: 66 03 05 00 03 00 00 00 if w3 s> 3 goto +5 <LBB0_63> 136: 16 03 09 00 01 00 00 00 if w3 == 1 goto +9 <LBB0_65> 137: 16 03 01 00 02 00 00 00 if w3 == 2 goto +1 <LBB0_66> 138: 05 00 0a 00 00 00 00 00 goto +10 <LBB0_69> 0000000000000458 <LBB0_66>: 139: 69 21 00 00 00 00 00 00 r1 = *(u16 *)(r2 + 0) ; NO CO-RE relocation here ^^^^^^^^^^^^^^^^ 140: 05 00 08 00 00 00 00 00 goto +8 <LBB0_69> 0000000000000468 <LBB0_63>: 141: 16 03 06 00 04 00 00 00 if w3 == 4 goto +6 <LBB0_67> 142: 16 03 01 00 08 00 00 00 if w3 == 8 goto +1 <LBB0_68> 143: 05 00 05 00 00 00 00 00 goto +5 <LBB0_69> 0000000000000480 <LBB0_68>: 144: 79 21 00 00 00 00 00 00 r1 = *(u64 *)(r2 + 0) ; NO CO-RE relocation here ^^^^^^^^^^^^^^^^ 145: 05 00 03 00 00 00 00 00 goto +3 <LBB0_69> 0000000000000490 <LBB0_65>: 146: 71 21 00 00 00 00 00 00 r1 = *(u8 *)(r2 + 0) ; NO CO-RE relocation here ^^^^^^^^^^^^^^^^ 147: 05 00 01 00 00 00 00 00 goto +1 <LBB0_69> 00000000000004a0 <LBB0_67>: 148: 61 21 00 00 00 00 00 00 r1 = *(u32 *)(r2 + 0) ; NO CO-RE relocation here ^^^^^^^^^^^^^^^^ 00000000000004a8 <LBB0_69>: 149: 67 01 00 00 20 00 00 00 r1 <<= 32 150: b7 02 00 00 00 00 00 00 r2 = 0 151: 16 02 02 00 00 00 00 00 if w2 == 0 goto +2 <LBB0_71> 152: c7 01 00 00 20 00 00 00 r1 s>>= 32 153: 05 00 01 00 00 00 00 00 goto +1 <LBB0_72> 00000000000004d0 <LBB0_71>: 154: 77 01 00 00 20 00 00 00 r1 >>= 323 Fixes: ee26dade ("libbpf: Add support for relocatable bitfields") Signed-off-by: -
Andrii Nakryiko authored
Add BTF_KIND_FLOAT support when doing CO-RE field type compatibility check. Without this, relocations against float/double fields will fail. Also adjust one error message to emit instruction index instead of less convenient instruction byte offset. Fixes: 22541a9e ("libbpf: Add BTF_KIND_FLOAT support") Signed-off-by:
-
Andrii Nakryiko authored
Add ASSERT_TRUE/ASSERT_FALSE for conditions calculated with custom logic to true/false. Also add remaining arithmetical assertions: - ASSERT_LE -- less than or equal; - ASSERT_GT -- greater than; - ASSERT_GE -- greater than or equal. This should cover most scenarios where people fall back to error-prone CHECK()s. Also extend ASSERT_ERR() to print out errno, in addition to direct error. Also convert few CHECK() instances to ensure new ASSERT_xxx() variants work as expected. Subsequent patch will also use ASSERT_TRUE/ASSERT_FALSE more extensively. Signed-off-by:
-
- 26 Apr, 2021 27 commits
-
-
Alexei Starovoitov authored
Jiri Olsa says: ==================== hi, while adding test for pinning the module while there's trampoline attach to it, I noticed that we don't allow link detach and following re-attach for trampolines. Adding that for tracing and lsm programs. You need to have patch [1] from bpf tree for test module attach test to pass. v5 changes: - fixed missing hlist_del_init change - fixed several ASSERT calls - added extra patch for missing ';' - added ASSERT macros to lsm test - added acks thanks, jirka [1] https://lore.kernel.org/bpf/20210326105900.151466-1-jolsa@kernel.org/ ==================== Signed-off-by:
-
Jiri Olsa authored
Replacing CHECK with ASSERT macros. Suggested-by:
Jiri Olsa <jolsa@kernel.org> Signed-off-by:
-
Jiri Olsa authored
Adding test to verify that once we attach module's trampoline, the module can't be unloaded. Signed-off-by:
-
Jiri Olsa authored
Adding the test to re-attach (detach/attach again) lsm programs, plus check that already linked program can't be attached again. Signed-off-by:
-
Jiri Olsa authored
Adding the test to re-attach (detach/attach again) tracing fexit programs, plus check that already linked program can't be attached again. Also switching to ASSERT* macros. Signed-off-by:
-
Jiri Olsa authored
Adding the test to re-attach (detach/attach again) tracing fentry programs, plus check that already linked program can't be attached again. Signed-off-by:
-
Jiri Olsa authored
Currently we don't allow re-attaching of trampolines. Once it's detached, it can't be re-attach even when the program is still loaded. Adding the possibility to re-attach the loaded tracing and lsm programs. Fixing missing unlock with proper cleanup goto jump reported by Julia. Reported-by:
kernel test robot <lkp@intel.com> Reported-by:
Julia Lawall <julia.lawall@lip6.fr> Signed-off-by:
Toke Høiland-Jørgensen <toke@redhat.com> Acked-by:
KP Singh <kpsingh@kernel.org> Link: https://lore.kernel.org/bpf/20210414195147.1624932-2-jolsa@kernel.org
-
David S. Miller authored
Michael Chan says: ==================== bnxt_en: Updates for net-next. This series includes these main enhancements: 1. Link related changes - add NRZ/PAM4 link signal mode to the link up message if known - rely on firmware to bring down the link during ifdown 2. SRIOV related changes - allow VF promiscuous mode if the VF is trusted - allow ndo operations to configure VF when the PF is ifdown - fix the scenario of the VF taking back control of it's MAC address - add Hyper-V VF device IDs 3. Support the option to transmit without FCS/CRC. 4. Implement .ndo_features_check() to disable offload when the UDP encap. packets are not supported. v2: Patch10: Reverse the check for supported UDP ports to be more straight forward. ==================== Signed-off-by:David S. Miller <davem@davemloft.net>
-
Michael Chan authored
For UDP encapsultions, we only support the offloaded Vxlan port and Geneve port. All other ports included FOU and GUE are not supported so we need to turn off TSO and checksum features. v2: Reverse the check for supported UDP ports to be more straight forward. Reviewed-by:
Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com> Reviewed-by:
Edwin Peer <edwin.peer@broadcom.com> Signed-off-by:
Michael Chan <michael.chan@broadcom.com> Signed-off-by:
-
Michael Chan authored
If firmware is capable, set the IFF_SUPP_NOFCS flag to support the sockets option to transmit packets without FCS. This is mainly used for testing. Reviewed-by: Edwin Peer <edwin.peer@broadcom.com Signed-off-by:
-
Michael Chan authored
Support VF device IDs used by the Hyper-V hypervisor. Reviewed-by:
Vasundhara Volam <vasundhara-v.volam@broadcom.com> Reviewed-by:
Andy Gospodarek <gospo@broadcom.com> Signed-off-by:
-
Michael Chan authored
When the PF is no longer enforcing an assigned MAC address on a VF, the VF needs to call bnxt_approve_mac() to tell the PF what MAC address it is now using. Otherwise it gets out of sync and the PF won't know what MAC address the VF wants to use. Ultimately the VF will fail when it tries to setup the L2 MAC filter for the vnic. Reviewed-by:
-
Michael Chan authored
Move it before bnxt_update_vf_mac(). In the next patch, we need to call bnxt_approve_mac() from bnxt_update_mac() under some conditions. This will avoid forward declaration. Reviewed-by:
-
Edwin Peer authored
It is perfectly legal for the stack to query and configure VFs via PF NDOs while the NIC is administratively down. Remove the unnecessary check for the PF to be in open state. Signed-off-by:
-
Edwin Peer authored
Firmware previously only allowed promiscuous mode for VFs associated with a default VLAN. It is now possible to enable promiscuous mode for a VF having no VLAN configured provided that it is trusted. In such cases the VF will see all packets received by the PF, irrespective of destination MAC or VLAN. Note, it is necessary to query firmware at the time of bnxt_promisc_ok() instead of in bnxt_hwrm_func_qcfg() because the trusted status might be altered by the PF after the VF has been configured. This check must now also be deferred because the firmware call sleeps. Signed-off-by:
-
Michael Chan authored
In the current code, the driver will not shutdown the link during IFDOWN if there are still VFs sharing the port. Newer firmware will manage the link down decision when the port is shared by VFs, so we can just call firmware to shutdown the port unconditionally and let firmware make the final decision. Reviewed-by:
-
Michael Chan authored
Copy the phy related feature flags from the firmware call HWRM_PORT_PHY_QCAPS to this new field. We can also remove the flags field in the bnxt_test_info structure. It's cleaner to have all PHY related flags in one location, directly copied from the firmware. To keep the BNXT_PHY_CFG_ABLE() macro logic the same, we need to make a slight adjustment to check that it is a PF. Reviewed-by:
-
Edwin Peer authored
Firmware reports link signalling mode for certain speeds. In these cases, print the signalling modes in kernel log link up messages. Reviewed-by:
-
Jethro Beekman authored
The default behavior for source MACVLAN is to duplicate packets to appropriate type source devices, and then do the normal destination MACVLAN flow. This patch adds an option to skip destination MACVLAN processing if any matching source MACVLAN device has the option set. This allows setting up a "catch all" device for source MACVLAN: create one or more devices with type source nodst, and one device with e.g. type vepa, and incoming traffic will be received on exactly one device. v2: netdev wants non-standard line length Signed-off-by:
Jethro Beekman <kernel@jbeekman.nl> Signed-off-by:
-
git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linuxDavid S. Miller authored
Saeed Mahameed says: ==================== mlx5-updates-2021-04-21 devlink external port attribute for SF (Sub-Function) port flavour This adds the support to instantiate Sub-Functions on external hosts E.g when Eswitch manager is enabled on the ARM SmarNic SoC CPU, users are now able to spawn new Sub-Functions on the Host server CPU. Parav Pandit Says: ================== This series introduces and uses external attribute for the SF port to indicate that a SF port belongs to an external controller. This is needed to generate unique phys_port_name when PF and SF numbers are overlapping between local and external controllers. For example two controllers 0 and 1, both of these controller have a SF. having PF number 0, SF number 77. Here, phys_port_name has duplicate entry which doesn't have controller number in it. Hence, add controller number optionally when a SF port is for an external controller. This extension is similar to existing PF and VF eswitch ports of the external controller. When a SF is for external controller an example view of external SF port and config sequence: On eswitch system: $ devlink dev eswitch set pci/0033:01:00.0 mode switchdev $ devlink port show pci/0033:01:00.0/196607: type eth netdev enP51p1s0f0np0 flavour physical port 0 splittable false pci/0033:01:00.0/131072: type eth netdev eth0 flavour pcipf controller 1 pfnum 0 external true splittable false function: hw_addr 00:00:00:00:00:00 $ devlink port add pci/0033:01:00.0 flavour pcisf pfnum 0 sfnum 77 controller 1 pci/0033:01:00.0/163840: type eth netdev eth1 flavour pcisf controller 1 pfnum 0 sfnum 77 splittable false function: hw_addr 00:00:00:00:00:00 state inactive opstate detached phys_port_name construction: $ cat /sys/class/net/eth1/phys_port_name c1pf0sf77 Patch summary: First 3 patches prepares the eswitch to handle vports in more generic way using xarray to lookup vport from its unique vport number. Patch-1 returns maximum eswitch ports only when eswitch is enabled Patch-2 prepares eswitch to return eswitch max ports from a struct Patch-3 uses xarray for vport and representor lookup Patch-4 considers SF for an additioanl range of SF vports Patch-5 relies on SF hw table to check SF support Patch-6 extends SF devlink port attribute for external flag Patch-7 stores the per controller SF allocation attributes Patch-8 uses SF function id for filtering events Patch-9 uses helper for allocation and free Patch-10 splits hw table into per controller table and generic one Patch-11 extends sf table for additional range ================== ==================== Signed-off-by: -
Linus Walleij authored
This adds device tree probing to the IXP4xx ethernet driver. Add a platform data bool to tell us whether to register an MDIO bus for the device or not, as well as the corresponding NPE. We need to drop the memory region request as part of this since the OF core will request the memory for the device. Cc: Zoltan HERPAI <wigyori@uid0.hu> Cc: Raylynn Knight <rayknight@me.com> Signed-off-by:
Linus Walleij <linus.walleij@linaro.org> Signed-off-by:
-
Linus Walleij authored
This driver was using a really dated way of obtaining the phy by printing a string and using it with phy_connect(). Switch to using more reasonable modern interfaces. Suggested-by:
Andrew Lunn <andrew@lunn.ch> Reviewed-by:
-
Linus Walleij authored
This adds device tree bindings for the IXP4xx ethernet controller with optional MDIO bridge. Cc: Zoltan HERPAI <wigyori@uid0.hu> Cc: Raylynn Knight <rayknight@me.com> Cc: devicetree@vger.kernel.org Signed-off-by:
-
Hayes Wang authored
Remove DELL_TB_RX_AGG_BUG and LENOVO_MACPASSTHRU flags of rtl8152_flags. They are only set when initializing and wouldn't be change. It is enough to record them with variables. Signed-off-by:
Hayes Wang <hayeswang@realtek.com> Signed-off-by:
-
Dexuan Cui authored
Currently the netvsc/VF binding logic only checks the PCI serial number. The Microsoft Azure Network Adapter (MANA) supports multiple net_device interfaces (each such interface is called a "vPort", and has its unique MAC address) which are backed by the same VF PCI device, so the binding logic should check both the MAC address and the PCI serial number. The change should not break any other existing VF drivers, because Hyper-V NIC SR-IOV implementation requires the netvsc network interface and the VF network interface have the same MAC address. Co-developed-by:
Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by:
Shachar Raindel <shacharr@microsoft.com> Signed-off-by:
Stephen Hemminger <stephen@networkplumber.org> Signed-off-by:
Dexuan Cui <decui@microsoft.com> Signed-off-by:
-
Jiapeng Chong authored
Variable result is being assigned a value from a calculation however the variable is never read, so this redundant variable can be removed. Cleans up the following clang-analyzer warning: drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c:1488:2: warning: Value stored to 'pos' is never read [clang-analyzer-deadcode.DeadStores]. drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c:876:3: warning: Value stored to 'pos' is never read [clang-analyzer-deadcode.DeadStores]. drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c:36:3: warning: Value stored to 'start' is never read [clang-analyzer-deadcode.DeadStores]. Reported-by:
Abaci Robot <abaci@linux.alibaba.com> Signed-off-by:
Jiapeng Chong <jiapeng.chong@linux.alibaba.com> Signed-off-by:
-
git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-nextDavid S. Miller authored
Alexei Starovoitov says: ==================== pull-request: bpf-next 2021-04-23 The following pull-request contains BPF updates for your *net-next* tree. We've added 69 non-merge commits during the last 22 day(s) which contain a total of 69 files changed, 3141 insertions(+), 866 deletions(-). The main changes are: 1) Add BPF static linker support for extern resolution of global, from Andrii. 2) Refine retval for bpf_get_task_stack helper, from Dave. 3) Add a bpf_snprintf helper, from Florent. 4) A bunch of miscellaneous improvements from many developers. ==================== Signed-off-by:
-
- 24 Apr, 2021 9 commits
-
-
Parav Pandit authored
Extended the SF table to cover additioanl SF id range of external controller. A user optionallly provides the external controller number when user wants to create SF on the external controller. An example on eswitch system: $ devlink dev eswitch set pci/0033:01:00.0 mode switchdev $ devlink port show pci/0033:01:00.0/196607: type eth netdev enP51p1s0f0np0 flavour physical port 0 splittable false pci/0033:01:00.0/131072: type eth netdev eth0 flavour pcipf controller 1 pfnum 0 external true splittable false function: hw_addr 00:00:00:00:00:00 $ devlink port add pci/0033:01:00.0 flavour pcisf pfnum 0 sfnum 77 controller 1 pci/0033:01:00.0/163840: type eth netdev eth1 flavour pcisf controller 1 pfnum 0 sfnum 77 external true splittable false function: hw_addr 00:00:00:00:00:00 state inactive opstate detached Signed-off-by:Parav Pandit <parav@nvidia.com> Signed-off-by:
Saeed Mahameed <saeedm@nvidia.com>
-
Parav Pandit authored
Device has SF ids in two different contiguous ranges. One for the local controller and second for the external controller's PF. Each such range has its own maximum number of functions and base id. To allocate SF from either of the range, prepare code to split into range specific fields into its own structure. Signed-off-by:
Vu Pham <vuhuong@nvidia.com> Signed-off-by:
-
Parav Pandit authored
Use helper routines for SF id and SF table allocation and free so that subsequent patch can reuse it for multiple SF function id range. Signed-off-by:
-
Parav Pandit authored
Vhca events on eswitch manager are received for all the functions on the NIC, including for SFs of external host PF controllers. While SF device handler is only interested in SF devices events related to its own PF. Hence, validate if the function belongs to self or not. Signed-off-by:
-
Parav Pandit authored
SF ids in the device are in two different contiguous ranges. One for the local controller and second for the external host controller. Prepare code to handle multiple start function id by storing it in the table. Signed-off-by:
-
Parav Pandit authored
Extended SF port attributes to have optional external flag similar to PCI PF and VF port attributes. External atttibute is required to generate unique phys_port_name when PF number and SF number are overlapping between two controllers similar to SR-IOV VFs. When a SF is for external controller an example view of external SF port and config sequence. On eswitch system: $ devlink dev eswitch set pci/0033:01:00.0 mode switchdev $ devlink port show pci/0033:01:00.0/196607: type eth netdev enP51p1s0f0np0 flavour physical port 0 splittable false pci/0033:01:00.0/131072: type eth netdev eth0 flavour pcipf controller 1 pfnum 0 external true splittable false function: hw_addr 00:00:00:00:00:00 $ devlink port add pci/0033:01:00.0 flavour pcisf pfnum 0 sfnum 77 controller 1 pci/0033:01:00.0/163840: type eth netdev eth1 flavour pcisf controller 1 pfnum 0 sfnum 77 splittable false function: hw_addr 00:00:00:00:00:00 state inactive opstate detached phys_port_name construction: $ cat /sys/class/net/eth1/phys_port_name c1pf0sf77 Signed-off-by:Jiri Pirko <jiri@nvidia.com> Reviewed-by:
-
Parav Pandit authored
Supporting SF allocation is currently checked at two places: (a) SF devlink port allocator and (b) SF HW table handler. Both layers are using HCA CAP to identify it using helper routine mlx5_sf_supported() and mlx5_sf_max_functions(). Instead, rely on the HW table handler to check if SF is supported or not. Signed-off-by:
-
Parav Pandit authored
Query SF vports count and base id of host PF from the firmware. Account these ports in the total port calculation whenever it is non zero. Signed-off-by:
Roi Dayan <roid@nvidia.com> Reviewed-by:
-
Parav Pandit authored
Currently vport number to vport and its representor are mapped using an array and an index. Vport numbers of different types of functions are not contiguous. Adding new such discontiguous range using index and number mapping is increasingly complex and hard to maintain. Hence, maintain an xarray of vport and rep whose lookup is done based on the vport number. Each VF and SF entry is marked with a xarray mark to identify the function type. Additionally PF and VF needs special handling for legacy inline mode. They are additionally marked as host function using additional HOST_FN mark. Signed-off-by:
-
